From: oes Date: Tue, 15 May 2001 13:59:48 +0000 (+0000) Subject: *** empty log message *** X-Git-Tag: v_2_9_3~2 X-Git-Url: http://www.privoxy.org/gitweb/?a=commitdiff_plain;h=2b30c138a697426649a61910ba2571d01167ffa9;p=privoxy.git *** empty log message *** --- 2b30c138a697426649a61910ba2571d01167ffa9 diff --git a/.gitignore b/.gitignore new file mode 100644 index 00000000..40caffa8 --- /dev/null +++ b/.gitignore @@ -0,0 +1,28 @@ +# CVS default ignores begin +tags +TAGS +.make.state +.nse_depinfo +*~ +#* +.#* +,* +_$* +*$ +*.old +*.bak +*.BAK +*.orig +*.rej +.del-* +*.a +*.olb +*.o +*.obj +*.so +*.exe +*.Z +*.elc +*.ln +core +# CVS default ignores end diff --git a/pcre/Makefile.in b/pcre/Makefile.in new file mode 100644 index 00000000..94edf499 --- /dev/null +++ b/pcre/Makefile.in @@ -0,0 +1,219 @@ + +# Makefile.in for PCRE (Perl-Compatible Regular Expression) library. + +#---------------------------------------------------------------------------# +# To build mingw32 DLL uncomment the next two lines. This addition for # +# mingw32 was contributed by . I (Philip # +# Hazel) don't know anything about it! There are some additional targets at # +# the bottom of this Makefile. # +#---------------------------------------------------------------------------# +# +# include dll.mk +# DLL_LDFLAGS=-s + + +#---------------------------------------------------------------------------# +# The next few lines are modified by "configure" to insert data that it is # +# given in its arguments, or which it finds out for itself. # +#---------------------------------------------------------------------------# + +# BINDIR is the directory in which the pcregrep command is installed. +# INCDIR is the directory in which the public header file pcre.h is installed. +# LIBDIR is the directory in which the libraries are installed. +# MANDIR is the directory in which the man pages are installed. +# The pcretest program, as it is a test program, does not get installed +# anywhere. + +prefix = @prefix@ +exec_prefix = @exec_prefix@ + +BINDIR = @bindir@ +LIBDIR = @libdir@ +INCDIR = @includedir@ +MANDIR = @mandir@ + +CC = @CC@ +CFLAGS = @CFLAGS@ +RANLIB = @RANLIB@ +UTF8 = @UTF8@ + +# LIBTOOL defaults to "./libtool", which enables the building of shared +# libraries. If "configure" is called with --disable-shared-libraries, LIBTOOL +# is set to "", which stops shared libraries from being built, and LIBSUFFIX +# is set to "a" instead of "la", which causes the shared libraries not to be +# installed. + +LIBTOOL = @LIBTOOL@ +LIBSUFFIX = @LIBSUFFIX@ + +# These are the version numbers for the shared libraries + +PCRELIBVERSION = @PCRE_LIB_VERSION@ +PCREPOSIXLIBVERSION = @PCRE_POSIXLIB_VERSION@ + + +#---------------------------------------------------------------------------# +# A copy of install-sh is in this distribution and is used by default. # +#---------------------------------------------------------------------------# + +INSTALL = ./install-sh -c +INSTALL_DATA = ${INSTALL} -m 644 + + +#---------------------------------------------------------------------------# +# For almost all systems, the command to create a library is "ar cq", but # +# there is at least one where it is different, so this command must be # +# configurable. However, I haven't got round to learning how to make # +# "configure" find this out for itself. It is necessary to use a command # +# such as "make AR='ar -rc'" if you need to vary this. The setting of AR is # +# *not* passed over to ./ltconfig, because it does its own setting up. # +#---------------------------------------------------------------------------# + +AR = ar cq + + +############################################################################## + + +OBJ = maketables.o get.o study.o pcre.o +LOBJ = maketables.lo get.lo study.lo pcre.lo + +all: libtool libpcre.$(LIBSUFFIX) libpcreposix.$(LIBSUFFIX) pcretest pcregrep + +libtool: config.guess config.sub ltconfig ltmain.sh + @if test "$(LIBTOOL)" = "./libtool"; then \ + echo '--- Building libtool ---'; \ + CC=$(CC) CFLAGS='$(CFLAGS)' RANLIB='$(RANLIB)' ./ltconfig ./ltmain.sh; \ + echo '--- Built libtool ---'; fi + +pcregrep: libpcre.$(LIBSUFFIX) pcregrep.o + @echo ' ' + @echo '--- Building pcregrep utility' + @echo ' ' + $(LIBTOOL) $(CC) $(CFLAGS) -o pcregrep pcregrep.o libpcre.$(LIBSUFFIX) + +pcretest: libpcre.$(LIBSUFFIX) libpcreposix.$(LIBSUFFIX) pcretest.o + @echo ' ' + @echo '--- Building pcretest testing program' + @echo ' ' + $(LIBTOOL) $(PURIFY) $(CC) $(CFLAGS) -o pcretest pcretest.o \ + libpcre.$(LIBSUFFIX) libpcreposix.$(LIBSUFFIX) + +libpcre.a: $(OBJ) + @echo ' ' + @echo '--- Building static library: libpcre' + @echo ' ' + -rm -f libpcre.a + $(AR) libpcre.a $(OBJ) + $(RANLIB) libpcre.a + +libpcre.la: $(OBJ) + @echo ' ' + @echo '--- Building shared library: libpcre' + @echo ' ' + -rm -f libpcre.la + ./libtool $(CC) -version-info '$(PCRELIBVERSION)' -o libpcre.la -rpath $(LIBDIR) $(LOBJ) + +libpcreposix.a: pcreposix.o + @echo ' ' + @echo '--- Building static library: libpcreposix' + @echo ' ' + -rm -f libpcreposix.a + $(AR) libpcreposix.a pcreposix.o + $(RANLIB) libpcreposix.a + +libpcreposix.la: pcreposix.o + @echo ' ' + @echo '--- Building shared library: libpcreposix' + @echo ' ' + -rm -f libpcreposix.la + ./libtool $(CC) -version-info '$(PCREPOSIXLIBVERSION)' -o libpcreposix.la -rpath $(LIBDIR) pcreposix.lo + +pcre.o: chartables.c pcre.c pcre.h internal.h config.h Makefile + $(LIBTOOL) $(CC) -c $(CFLAGS) $(UTF8) pcre.c + +pcreposix.o: pcreposix.c pcreposix.h internal.h pcre.h config.h Makefile + $(LIBTOOL) $(CC) -c $(CFLAGS) pcreposix.c + +maketables.o: maketables.c pcre.h internal.h config.h Makefile + $(LIBTOOL) $(CC) -c $(CFLAGS) maketables.c + +get.o: get.c pcre.h internal.h config.h Makefile + $(LIBTOOL) $(CC) -c $(CFLAGS) get.c + +study.o: study.c pcre.h internal.h config.h Makefile + $(LIBTOOL) $(CC) -c $(CFLAGS) $(UTF8) study.c + +pcretest.o: pcretest.c pcre.h config.h Makefile + $(CC) -c $(CFLAGS) $(UTF8) pcretest.c + +pcregrep.o: pcregrep.c pcre.h Makefile config.h + $(CC) -c $(CFLAGS) $(UTF8) pcregrep.c + +# An auxiliary program makes the default character table source + +chartables.c: dftables + ./dftables >chartables.c + +dftables: dftables.c maketables.c pcre.h internal.h config.h Makefile + $(CC) -o dftables $(CFLAGS) dftables.c + +install: all + $(LIBTOOL) $(INSTALL_DATA) libpcre.$(LIBSUFFIX) $(DESTDIR)/$(LIBDIR)/libpcre.$(LIBSUFFIX) + $(LIBTOOL) $(INSTALL_DATA) libpcreposix.$(LIBSUFFIX) $(DESTDIR)/$(LIBDIR)/libpcreposix.$(LIBSUFFIX) + $(INSTALL_DATA) pcre.h $(DESTDIR)/$(INCDIR)/pcre.h + $(INSTALL_DATA) pcreposix.h $(DESTDIR)/$(INCDIR)/pcreposix.h + $(INSTALL_DATA) doc/pcre.3 $(DESTDIR)/$(MANDIR)/man3/pcre.3 + $(INSTALL_DATA) doc/pcreposix.3 $(DESTDIR)/$(MANDIR)/man3/pcreposix.3 + $(INSTALL_DATA) doc/pcregrep.1 $(DESTDIR)/$(MANDIR)/man1/pcregrep.1 + @if test "$(LIBTOOL)" = "./libtool"; then \ + echo ' '; \ + echo '--- Rebuilding pcregrep to use installed shared library ---'; \ + echo $(CC) $(CFLAGS) -o pcregrep pcregrep.o -L$(DESTDIR)/$(LIBDIR) -lpcre; \ + $(CC) $(CFLAGS) -o pcregrep pcregrep.o -L$(DESTDIR)/$(LIBDIR) -lpcre; \ + echo '--- Rebuilding pcretest to use installed shared library ---'; \ + echo $(CC) $(CFLAGS) -o pcretest pcretest.o -L$(DESTDIR)/$(LIBDIR) -lpcre -lpcreposix; \ + $(CC) $(CFLAGS) -o pcretest pcretest.o -L$(DESTDIR)/$(LIBDIR) -lpcre -lpcreposix; \ + fi + $(INSTALL) pcregrep $(DESTDIR)/$(BINDIR)/pcregrep + $(INSTALL) pcre-config $(DESTDIR)/$(BINDIR)/pcre-config + +# We deliberately omit dftables and chartables.c from 'make clean'; once made +# chartables.c shouldn't change, and if people have edited the tables by hand, +# you don't want to throw them away. + +clean:; -rm -rf *.o *.lo *.a *.la .libs pcretest pcregrep testtry + +# But "make distclean" should get back to a virgin distribution + +distclean: clean + -rm -f chartables.c libtool pcre-config pcre.h \ + Makefile config.h config.status config.log config.cache + +check: runtest + +test: runtest + +runtest: all + ./RunTest + +######## MINGW32 ############### MINGW32 ############### MINGW32 ############# + +# This addition for mingw32 was contributed by Paul Sokolovsky +# . I (PH) don't know anything about it! + +dll: _dll libpcre.dll.a pcregrep_d pcretest_d + +_dll: + $(MAKE) CFLAGS=-DSTATIC pcre.dll + +pcre.dll: $(OBJ) pcreposix.o pcre.def +libpcre.dll.a: pcre.def + +pcregrep_d: libpcre.dll.a pcregrep.o + $(CC) $(CFLAGS) -L. -o pcregrep pcregrep.o -lpcre.dll + +pcretest_d: libpcre.dll.a pcretest.o + $(PURIFY) $(CC) $(CFLAGS) -L. -o pcretest pcretest.o -lpcre.dll + +# End diff --git a/pcre/RunTest.in b/pcre/RunTest.in new file mode 100644 index 00000000..6e4eb085 --- /dev/null +++ b/pcre/RunTest.in @@ -0,0 +1,148 @@ +#! /bin/sh + +# This file is generated by configure from RunTest.in. Make any changes +# to that file. + +# Run PCRE tests + +cf=diff + +# Select which tests to run; if no selection, run all + +do1=no +do2=no +do3=no +do4=no +do5=no +do6=no + +while [ $# -gt 0 ] ; do + case $1 in + 1) do1=yes;; + 2) do2=yes;; + 3) do3=yes;; + 4) do4=yes;; + 5) do5=yes;; + 6) do6=yes;; + *) echo "Unknown test number $1"; exit 1;; + esac + shift +done + +if [ "@UTF8@" = "" ] ; then + if [ $do5 = yes ] ; then + echo "Can't run test 5 because UFT8 support is not configured" + exit 1 + fi + if [ $do6 = yes ] ; then + echo "Can't run test 6 because UFT8 support is not configured" + exit 1 + fi +fi + +if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a\ + $do5 = no -a $do6 = no ] ; then + do1=yes + do2=yes + do3=yes + do4=yes + if [ "@UTF8@" != "" ] ; then do5=yes; fi + if [ "@UTF8@" != "" ] ; then do6=yes; fi +fi + +# Primary test, Perl-compatible + +if [ $do1 = yes ] ; then + echo "Testing main functionality (Perl compatible)" + ./pcretest testdata/testinput1 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput1 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi +fi + +# PCRE tests that are not Perl-compatible - API & error tests, mostly + +if [ $do2 = yes ] ; then + echo "Testing API and error handling (not Perl compatible)" + ./pcretest -i testdata/testinput2 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput2 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi +fi + +# Additional Perl-compatible tests for Perl 5.005's new features + +if [ $do3 = yes ] ; then + echo "Testing Perl 5.005 features (Perl 5.005 compatible)" + ./pcretest testdata/testinput3 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput3 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi +fi + +if [ $do1 = yes -a $do2 = yes -a $do3 = yes ] ; then + echo " " + echo "The three main tests all ran OK" + echo " " +fi + +# Locale-specific tests, provided the "fr" locale is available + +if [ $do4 = yes ] ; then + locale -a | grep '^fr$' >/dev/null + if [ $? -eq 0 ] ; then + echo "Testing locale-specific features (using 'fr' locale)" + ./pcretest testdata/testinput4 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput4 + if [ $? != 0 ] ; then + echo " " + echo "Locale test did not run entirely successfully." + echo "This usually means that there is a problem with the locale" + echo "settings rather than a bug in PCRE." + else + echo "Locale test ran OK" + fi + echo " " + else exit 1 + fi + else + echo "Cannot test locale-specific features - 'fr' locale not found," + echo "or the \"locale\" command is not available to check for it." + echo " " + fi +fi + +# Additional tests for UTF8 support + +if [ $do5 = yes ] ; then + echo "Testing experimental, incomplete UTF8 support (Perl compatible)" + ./pcretest testdata/testinput5 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput5 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "UTF8 test ran OK" + echo " " +fi + +if [ $do6 = yes ] ; then + echo "Testing API and internals for UTF8 support (not Perl compatible)" + ./pcretest testdata/testinput6 testtry + if [ $? = 0 ] ; then + $cf testtry testdata/testoutput6 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "UTF8 internals test ran OK" + echo " " +fi + +# End diff --git a/pcre/config.guess b/pcre/config.guess new file mode 100644 index 00000000..e1b58717 --- /dev/null +++ b/pcre/config.guess @@ -0,0 +1,1121 @@ +#! /bin/sh +# Attempt to guess a canonical system name. +# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999 +# Free Software Foundation, Inc. +# +# This file is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# Written by Per Bothner . +# The master version of this file is at the FSF in /home/gd/gnu/lib. +# Please send patches to . +# +# This script attempts to guess a canonical system name similar to +# config.sub. If it succeeds, it prints the system name on stdout, and +# exits with 0. Otherwise, it exits with 1. +# +# The plan is that this can be called by configure scripts if you +# don't specify an explicit system type (host/target name). +# +# Only a few systems have been added to this list; please add others +# (but try to keep the structure clean). +# + +# Use $HOST_CC if defined. $CC may point to a cross-compiler +if test x"$CC_FOR_BUILD" = x; then + if test x"$HOST_CC" != x; then + CC_FOR_BUILD="$HOST_CC" + else + if test x"$CC" != x; then + CC_FOR_BUILD="$CC" + else + CC_FOR_BUILD=cc + fi + fi +fi + + +# This is needed to find uname on a Pyramid OSx when run in the BSD universe. +# (ghazi@noc.rutgers.edu 8/24/94.) +if (test -f /.attbin/uname) >/dev/null 2>&1 ; then + PATH=$PATH:/.attbin ; export PATH +fi + +UNAME_MACHINE=`(uname -m) 2>/dev/null` || UNAME_MACHINE=unknown +UNAME_RELEASE=`(uname -r) 2>/dev/null` || UNAME_RELEASE=unknown +UNAME_SYSTEM=`(uname -s) 2>/dev/null` || UNAME_SYSTEM=unknown +UNAME_VERSION=`(uname -v) 2>/dev/null` || UNAME_VERSION=unknown + +dummy=dummy-$$ +trap 'rm -f $dummy.c $dummy.o $dummy; exit 1' 1 2 15 + +# Note: order is significant - the case branches are not exclusive. + +case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in + alpha:OSF1:*:*) + if test $UNAME_RELEASE = "V4.0"; then + UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $3}'` + fi + # A Vn.n version is a released version. + # A Tn.n version is a released field test version. + # A Xn.n version is an unreleased experimental baselevel. + # 1.2 uses "1.2" for uname -r. + cat <$dummy.s + .globl main + .ent main +main: + .frame \$30,0,\$26,0 + .prologue 0 + .long 0x47e03d80 # implver $0 + lda \$2,259 + .long 0x47e20c21 # amask $2,$1 + srl \$1,8,\$2 + sll \$2,2,\$2 + sll \$0,3,\$0 + addl \$1,\$0,\$0 + addl \$2,\$0,\$0 + ret \$31,(\$26),1 + .end main +EOF + $CC_FOR_BUILD $dummy.s -o $dummy 2>/dev/null + if test "$?" = 0 ; then + ./$dummy + case "$?" in + 7) + UNAME_MACHINE="alpha" + ;; + 15) + UNAME_MACHINE="alphaev5" + ;; + 14) + UNAME_MACHINE="alphaev56" + ;; + 10) + UNAME_MACHINE="alphapca56" + ;; + 16) + UNAME_MACHINE="alphaev6" + ;; + esac + fi + rm -f $dummy.s $dummy + echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[VTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'` + exit 0 ;; + Alpha\ *:Windows_NT*:*) + # How do we know it's Interix rather than the generic POSIX subsystem? + # Should we change UNAME_MACHINE based on the output of uname instead + # of the specific Alpha model? + echo alpha-pc-interix + exit 0 ;; + 21064:Windows_NT:50:3) + echo alpha-dec-winnt3.5 + exit 0 ;; + Amiga*:UNIX_System_V:4.0:*) + echo m68k-cbm-sysv4 + exit 0;; + amiga:NetBSD:*:*) + echo m68k-cbm-netbsd${UNAME_RELEASE} + exit 0 ;; + amiga:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + *:[Aa]miga[Oo][Ss]:*:*) + echo ${UNAME_MACHINE}-unknown-amigaos + exit 0 ;; + arc64:OpenBSD:*:*) + echo mips64el-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + arc:OpenBSD:*:*) + echo mipsel-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + hkmips:OpenBSD:*:*) + echo mips-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + pmax:OpenBSD:*:*) + echo mipsel-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + sgi:OpenBSD:*:*) + echo mips-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + wgrisc:OpenBSD:*:*) + echo mipsel-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + *:OS/390:*:*) + echo i370-ibm-openedition + exit 0 ;; + arm:RISC*:1.[012]*:*|arm:riscix:1.[012]*:*) + echo arm-acorn-riscix${UNAME_RELEASE} + exit 0;; + arm32:NetBSD:*:*) + echo arm-unknown-netbsd`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'` + exit 0 ;; + SR2?01:HI-UX/MPP:*:*) + echo hppa1.1-hitachi-hiuxmpp + exit 0;; + Pyramid*:OSx*:*:* | MIS*:OSx*:*:* | MIS*:SMP_DC-OSx*:*:*) + # akee@wpdis03.wpafb.af.mil (Earle F. Ake) contributed MIS and NILE. + if test "`(/bin/universe) 2>/dev/null`" = att ; then + echo pyramid-pyramid-sysv3 + else + echo pyramid-pyramid-bsd + fi + exit 0 ;; + NILE*:*:*:dcosx) + echo pyramid-pyramid-svr4 + exit 0 ;; + sun4H:SunOS:5.*:*) + echo sparc-hal-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit 0 ;; + sun4*:SunOS:5.*:* | tadpole*:SunOS:5.*:*) + echo sparc-sun-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit 0 ;; + i86pc:SunOS:5.*:*) + echo i386-pc-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit 0 ;; + sun4*:SunOS:6*:*) + # According to config.sub, this is the proper way to canonicalize + # SunOS6. Hard to guess exactly what SunOS6 will be like, but + # it's likely to be more like Solaris than SunOS4. + echo sparc-sun-solaris3`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit 0 ;; + sun4*:SunOS:*:*) + case "`/usr/bin/arch -k`" in + Series*|S4*) + UNAME_RELEASE=`uname -v` + ;; + esac + # Japanese Language versions have a version number like `4.1.3-JL'. + echo sparc-sun-sunos`echo ${UNAME_RELEASE}|sed -e 's/-/_/'` + exit 0 ;; + sun3*:SunOS:*:*) + echo m68k-sun-sunos${UNAME_RELEASE} + exit 0 ;; + sun*:*:4.2BSD:*) + UNAME_RELEASE=`(head -1 /etc/motd | awk '{print substr($5,1,3)}') 2>/dev/null` + test "x${UNAME_RELEASE}" = "x" && UNAME_RELEASE=3 + case "`/bin/arch`" in + sun3) + echo m68k-sun-sunos${UNAME_RELEASE} + ;; + sun4) + echo sparc-sun-sunos${UNAME_RELEASE} + ;; + esac + exit 0 ;; + aushp:SunOS:*:*) + echo sparc-auspex-sunos${UNAME_RELEASE} + exit 0 ;; + atari*:NetBSD:*:*) + echo m68k-atari-netbsd${UNAME_RELEASE} + exit 0 ;; + atari*:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + # The situation for MiNT is a little confusing. The machine name + # can be virtually everything (everything which is not + # "atarist" or "atariste" at least should have a processor + # > m68000). The system name ranges from "MiNT" over "FreeMiNT" + # to the lowercase version "mint" (or "freemint"). Finally + # the system name "TOS" denotes a system which is actually not + # MiNT. But MiNT is downward compatible to TOS, so this should + # be no problem. + atarist[e]:*MiNT:*:* | atarist[e]:*mint:*:* | atarist[e]:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit 0 ;; + atari*:*MiNT:*:* | atari*:*mint:*:* | atarist[e]:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit 0 ;; + *falcon*:*MiNT:*:* | *falcon*:*mint:*:* | *falcon*:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit 0 ;; + milan*:*MiNT:*:* | milan*:*mint:*:* | *milan*:*TOS:*:*) + echo m68k-milan-mint${UNAME_RELEASE} + exit 0 ;; + hades*:*MiNT:*:* | hades*:*mint:*:* | *hades*:*TOS:*:*) + echo m68k-hades-mint${UNAME_RELEASE} + exit 0 ;; + *:*MiNT:*:* | *:*mint:*:* | *:*TOS:*:*) + echo m68k-unknown-mint${UNAME_RELEASE} + exit 0 ;; + sun3*:NetBSD:*:*) + echo m68k-sun-netbsd${UNAME_RELEASE} + exit 0 ;; + sun3*:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + mac68k:NetBSD:*:*) + echo m68k-apple-netbsd${UNAME_RELEASE} + exit 0 ;; + mac68k:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + mvme68k:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + mvme88k:OpenBSD:*:*) + echo m88k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + powerpc:machten:*:*) + echo powerpc-apple-machten${UNAME_RELEASE} + exit 0 ;; + macppc:NetBSD:*:*) + echo powerpc-apple-netbsd${UNAME_RELEASE} + exit 0 ;; + RISC*:Mach:*:*) + echo mips-dec-mach_bsd4.3 + exit 0 ;; + RISC*:ULTRIX:*:*) + echo mips-dec-ultrix${UNAME_RELEASE} + exit 0 ;; + VAX*:ULTRIX*:*:*) + echo vax-dec-ultrix${UNAME_RELEASE} + exit 0 ;; + 2020:CLIX:*:* | 2430:CLIX:*:*) + echo clipper-intergraph-clix${UNAME_RELEASE} + exit 0 ;; + mips:*:*:UMIPS | mips:*:*:RISCos) + sed 's/^ //' << EOF >$dummy.c +#ifdef __cplusplus + int main (int argc, char *argv[]) { +#else + int main (argc, argv) int argc; char *argv[]; { +#endif + #if defined (host_mips) && defined (MIPSEB) + #if defined (SYSTYPE_SYSV) + printf ("mips-mips-riscos%ssysv\n", argv[1]); exit (0); + #endif + #if defined (SYSTYPE_SVR4) + printf ("mips-mips-riscos%ssvr4\n", argv[1]); exit (0); + #endif + #if defined (SYSTYPE_BSD43) || defined(SYSTYPE_BSD) + printf ("mips-mips-riscos%sbsd\n", argv[1]); exit (0); + #endif + #endif + exit (-1); + } +EOF + $CC_FOR_BUILD $dummy.c -o $dummy \ + && ./$dummy `echo "${UNAME_RELEASE}" | sed -n 's/\([0-9]*\).*/\1/p'` \ + && rm $dummy.c $dummy && exit 0 + rm -f $dummy.c $dummy + echo mips-mips-riscos${UNAME_RELEASE} + exit 0 ;; + Night_Hawk:Power_UNIX:*:*) + echo powerpc-harris-powerunix + exit 0 ;; + m88k:CX/UX:7*:*) + echo m88k-harris-cxux7 + exit 0 ;; + m88k:*:4*:R4*) + echo m88k-motorola-sysv4 + exit 0 ;; + m88k:*:3*:R3*) + echo m88k-motorola-sysv3 + exit 0 ;; + AViiON:dgux:*:*) + # DG/UX returns AViiON for all architectures + UNAME_PROCESSOR=`/usr/bin/uname -p` + if [ $UNAME_PROCESSOR = mc88100 ] || [ $UNAME_PROCESSOR = mc88110] + then + if [ ${TARGET_BINARY_INTERFACE}x = m88kdguxelfx ] || \ + [ ${TARGET_BINARY_INTERFACE}x = x ] + then + echo m88k-dg-dgux${UNAME_RELEASE} + else + echo m88k-dg-dguxbcs${UNAME_RELEASE} + fi + else + echo i586-dg-dgux${UNAME_RELEASE} + fi + exit 0 ;; + M88*:DolphinOS:*:*) # DolphinOS (SVR3) + echo m88k-dolphin-sysv3 + exit 0 ;; + M88*:*:R3*:*) + # Delta 88k system running SVR3 + echo m88k-motorola-sysv3 + exit 0 ;; + XD88*:*:*:*) # Tektronix XD88 system running UTekV (SVR3) + echo m88k-tektronix-sysv3 + exit 0 ;; + Tek43[0-9][0-9]:UTek:*:*) # Tektronix 4300 system running UTek (BSD) + echo m68k-tektronix-bsd + exit 0 ;; + *:IRIX*:*:*) + echo mips-sgi-irix`echo ${UNAME_RELEASE}|sed -e 's/-/_/g'` + exit 0 ;; + ????????:AIX?:[12].1:2) # AIX 2.2.1 or AIX 2.1.1 is RT/PC AIX. + echo romp-ibm-aix # uname -m gives an 8 hex-code CPU id + exit 0 ;; # Note that: echo "'`uname -s`'" gives 'AIX ' + i?86:AIX:*:*) + echo i386-ibm-aix + exit 0 ;; + *:AIX:2:3) + if grep bos325 /usr/include/stdio.h >/dev/null 2>&1; then + sed 's/^ //' << EOF >$dummy.c + #include + + main() + { + if (!__power_pc()) + exit(1); + puts("powerpc-ibm-aix3.2.5"); + exit(0); + } +EOF + $CC_FOR_BUILD $dummy.c -o $dummy && ./$dummy && rm $dummy.c $dummy && exit 0 + rm -f $dummy.c $dummy + echo rs6000-ibm-aix3.2.5 + elif grep bos324 /usr/include/stdio.h >/dev/null 2>&1; then + echo rs6000-ibm-aix3.2.4 + else + echo rs6000-ibm-aix3.2 + fi + exit 0 ;; + *:AIX:*:4) + IBM_CPU_ID=`/usr/sbin/lsdev -C -c processor -S available | head -1 | awk '{ print $1 }'` + if /usr/sbin/lsattr -EHl ${IBM_CPU_ID} | grep POWER >/dev/null 2>&1; then + IBM_ARCH=rs6000 + else + IBM_ARCH=powerpc + fi + if [ -x /usr/bin/oslevel ] ; then + IBM_REV=`/usr/bin/oslevel` + else + IBM_REV=4.${UNAME_RELEASE} + fi + echo ${IBM_ARCH}-ibm-aix${IBM_REV} + exit 0 ;; + *:AIX:*:*) + echo rs6000-ibm-aix + exit 0 ;; + ibmrt:4.4BSD:*|romp-ibm:BSD:*) + echo romp-ibm-bsd4.4 + exit 0 ;; + ibmrt:*BSD:*|romp-ibm:BSD:*) # covers RT/PC NetBSD and + echo romp-ibm-bsd${UNAME_RELEASE} # 4.3 with uname added to + exit 0 ;; # report: romp-ibm BSD 4.3 + *:BOSX:*:*) + echo rs6000-bull-bosx + exit 0 ;; + DPX/2?00:B.O.S.:*:*) + echo m68k-bull-sysv3 + exit 0 ;; + 9000/[34]??:4.3bsd:1.*:*) + echo m68k-hp-bsd + exit 0 ;; + hp300:4.4BSD:*:* | 9000/[34]??:4.3bsd:2.*:*) + echo m68k-hp-bsd4.4 + exit 0 ;; + 9000/[34678]??:HP-UX:*:*) + case "${UNAME_MACHINE}" in + 9000/31? ) HP_ARCH=m68000 ;; + 9000/[34]?? ) HP_ARCH=m68k ;; + 9000/[678][0-9][0-9]) + sed 's/^ //' << EOF >$dummy.c + #include + #include + + int main () + { + #if defined(_SC_KERNEL_BITS) + long bits = sysconf(_SC_KERNEL_BITS); + #endif + long cpu = sysconf (_SC_CPU_VERSION); + + switch (cpu) + { + case CPU_PA_RISC1_0: puts ("hppa1.0"); break; + case CPU_PA_RISC1_1: puts ("hppa1.1"); break; + case CPU_PA_RISC2_0: + #if defined(_SC_KERNEL_BITS) + switch (bits) + { + case 64: puts ("hppa2.0w"); break; + case 32: puts ("hppa2.0n"); break; + default: puts ("hppa2.0"); break; + } break; + #else /* !defined(_SC_KERNEL_BITS) */ + puts ("hppa2.0"); break; + #endif + default: puts ("hppa1.0"); break; + } + exit (0); + } +EOF + (CCOPTS= $CC_FOR_BUILD $dummy.c -o $dummy 2>/dev/null ) && HP_ARCH=`./$dummy` + rm -f $dummy.c $dummy + esac + HPUX_REV=`echo ${UNAME_RELEASE}|sed -e 's/[^.]*.[0B]*//'` + echo ${HP_ARCH}-hp-hpux${HPUX_REV} + exit 0 ;; + 3050*:HI-UX:*:*) + sed 's/^ //' << EOF >$dummy.c + #include + int + main () + { + long cpu = sysconf (_SC_CPU_VERSION); + /* The order matters, because CPU_IS_HP_MC68K erroneously returns + true for CPU_PA_RISC1_0. CPU_IS_PA_RISC returns correct + results, however. */ + if (CPU_IS_PA_RISC (cpu)) + { + switch (cpu) + { + case CPU_PA_RISC1_0: puts ("hppa1.0-hitachi-hiuxwe2"); break; + case CPU_PA_RISC1_1: puts ("hppa1.1-hitachi-hiuxwe2"); break; + case CPU_PA_RISC2_0: puts ("hppa2.0-hitachi-hiuxwe2"); break; + default: puts ("hppa-hitachi-hiuxwe2"); break; + } + } + else if (CPU_IS_HP_MC68K (cpu)) + puts ("m68k-hitachi-hiuxwe2"); + else puts ("unknown-hitachi-hiuxwe2"); + exit (0); + } +EOF + $CC_FOR_BUILD $dummy.c -o $dummy && ./$dummy && rm $dummy.c $dummy && exit 0 + rm -f $dummy.c $dummy + echo unknown-hitachi-hiuxwe2 + exit 0 ;; + 9000/7??:4.3bsd:*:* | 9000/8?[79]:4.3bsd:*:* ) + echo hppa1.1-hp-bsd + exit 0 ;; + 9000/8??:4.3bsd:*:*) + echo hppa1.0-hp-bsd + exit 0 ;; + *9??*:MPE/iX:*:*) + echo hppa1.0-hp-mpeix + exit 0 ;; + hp7??:OSF1:*:* | hp8?[79]:OSF1:*:* ) + echo hppa1.1-hp-osf + exit 0 ;; + hp8??:OSF1:*:*) + echo hppa1.0-hp-osf + exit 0 ;; + i?86:OSF1:*:*) + if [ -x /usr/sbin/sysversion ] ; then + echo ${UNAME_MACHINE}-unknown-osf1mk + else + echo ${UNAME_MACHINE}-unknown-osf1 + fi + exit 0 ;; + parisc*:Lites*:*:*) + echo hppa1.1-hp-lites + exit 0 ;; + hppa*:OpenBSD:*:*) + echo hppa-unknown-openbsd + exit 0 ;; + C1*:ConvexOS:*:* | convex:ConvexOS:C1*:*) + echo c1-convex-bsd + exit 0 ;; + C2*:ConvexOS:*:* | convex:ConvexOS:C2*:*) + if getsysinfo -f scalar_acc + then echo c32-convex-bsd + else echo c2-convex-bsd + fi + exit 0 ;; + C34*:ConvexOS:*:* | convex:ConvexOS:C34*:*) + echo c34-convex-bsd + exit 0 ;; + C38*:ConvexOS:*:* | convex:ConvexOS:C38*:*) + echo c38-convex-bsd + exit 0 ;; + C4*:ConvexOS:*:* | convex:ConvexOS:C4*:*) + echo c4-convex-bsd + exit 0 ;; + CRAY*X-MP:*:*:*) + echo xmp-cray-unicos + exit 0 ;; + CRAY*Y-MP:*:*:*) + echo ymp-cray-unicos${UNAME_RELEASE} + exit 0 ;; + CRAY*[A-Z]90:*:*:*) + echo ${UNAME_MACHINE}-cray-unicos${UNAME_RELEASE} \ + | sed -e 's/CRAY.*\([A-Z]90\)/\1/' \ + -e y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/ + exit 0 ;; + CRAY*TS:*:*:*) + echo t90-cray-unicos${UNAME_RELEASE} + exit 0 ;; + CRAY*T3E:*:*:*) + echo alpha-cray-unicosmk${UNAME_RELEASE} + exit 0 ;; + CRAY-2:*:*:*) + echo cray2-cray-unicos + exit 0 ;; + F300:UNIX_System_V:*:*) + FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'` + FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'` + echo "f300-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}" + exit 0 ;; + F301:UNIX_System_V:*:*) + echo f301-fujitsu-uxpv`echo $UNAME_RELEASE | sed 's/ .*//'` + exit 0 ;; + hp3[0-9][05]:NetBSD:*:*) + echo m68k-hp-netbsd${UNAME_RELEASE} + exit 0 ;; + hp300:OpenBSD:*:*) + echo m68k-unknown-openbsd${UNAME_RELEASE} + exit 0 ;; + i?86:BSD/386:*:* | i?86:BSD/OS:*:*) + echo ${UNAME_MACHINE}-pc-bsdi${UNAME_RELEASE} + exit 0 ;; + sparc*:BSD/OS:*:*) + echo sparc-unknown-bsdi${UNAME_RELEASE} + exit 0 ;; + *:BSD/OS:*:*) + echo ${UNAME_MACHINE}-unknown-bsdi${UNAME_RELEASE} + exit 0 ;; + *:FreeBSD:*:*) + if test -x /usr/bin/objformat; then + if test "elf" = "`/usr/bin/objformat`"; then + echo ${UNAME_MACHINE}-unknown-freebsdelf`echo ${UNAME_RELEASE}|sed -e 's/[-_].*//'` + exit 0 + fi + fi + echo ${UNAME_MACHINE}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` + exit 0 ;; + *:NetBSD:*:*) + echo ${UNAME_MACHINE}-unknown-netbsd`echo ${UNAME_RELEASE}|sed -e 's/[-_].*//'` + exit 0 ;; + *:OpenBSD:*:*) + echo ${UNAME_MACHINE}-unknown-openbsd`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'` + exit 0 ;; + i*:CYGWIN*:*) + echo ${UNAME_MACHINE}-pc-cygwin + exit 0 ;; + i*:MINGW*:*) + echo ${UNAME_MACHINE}-pc-mingw32 + exit 0 ;; + i*:Windows_NT*:* | Pentium*:Windows_NT*:*) + # How do we know it's Interix rather than the generic POSIX subsystem? + # It also conflicts with pre-2.0 versions of AT&T UWIN. Should we + # UNAME_MACHINE based on the output of uname instead of i386? + echo i386-pc-interix + exit 0 ;; + i*:UWIN*:*) + echo ${UNAME_MACHINE}-pc-uwin + exit 0 ;; + p*:CYGWIN*:*) + echo powerpcle-unknown-cygwin + exit 0 ;; + prep*:SunOS:5.*:*) + echo powerpcle-unknown-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit 0 ;; + *:GNU:*:*) + echo `echo ${UNAME_MACHINE}|sed -e 's,[-/].*$,,'`-unknown-gnu`echo ${UNAME_RELEASE}|sed -e 's,/.*$,,'` + exit 0 ;; + *:Linux:*:*) + + # The BFD linker knows what the default object file format is, so + # first see if it will tell us. cd to the root directory to prevent + # problems with other programs or directories called `ld' in the path. + ld_help_string=`cd /; ld --help 2>&1` + ld_supported_emulations=`echo $ld_help_string \ + | sed -ne '/supported emulations:/!d + s/[ ][ ]*/ /g + s/.*supported emulations: *// + s/ .*// + p'` + case "$ld_supported_emulations" in + *ia64) + echo "${UNAME_MACHINE}-unknown-linux" + exit 0 + ;; + i?86linux) + echo "${UNAME_MACHINE}-pc-linux-gnuaout" + exit 0 + ;; + i?86coff) + echo "${UNAME_MACHINE}-pc-linux-gnucoff" + exit 0 + ;; + sparclinux) + echo "${UNAME_MACHINE}-unknown-linux-gnuaout" + exit 0 + ;; + armlinux) + echo "${UNAME_MACHINE}-unknown-linux-gnuaout" + exit 0 + ;; + elf32arm*) + echo "${UNAME_MACHINE}-unknown-linux-gnu" + exit 0 + ;; + armelf_linux*) + echo "${UNAME_MACHINE}-unknown-linux-gnu" + exit 0 + ;; + m68klinux) + echo "${UNAME_MACHINE}-unknown-linux-gnuaout" + exit 0 + ;; + elf32ppc) + # Determine Lib Version + cat >$dummy.c < +#if defined(__GLIBC__) +extern char __libc_version[]; +extern char __libc_release[]; +#endif +main(argc, argv) + int argc; + char *argv[]; +{ +#if defined(__GLIBC__) + printf("%s %s\n", __libc_version, __libc_release); +#else + printf("unkown\n"); +#endif + return 0; +} +EOF + LIBC="" + $CC_FOR_BUILD $dummy.c -o $dummy 2>/dev/null + if test "$?" = 0 ; then + ./$dummy | grep 1\.99 > /dev/null + if test "$?" = 0 ; then + LIBC="libc1" + fi + fi + rm -f $dummy.c $dummy + echo powerpc-unknown-linux-gnu${LIBC} + exit 0 + ;; + esac + + if test "${UNAME_MACHINE}" = "alpha" ; then + sed 's/^ //' <$dummy.s + .globl main + .ent main + main: + .frame \$30,0,\$26,0 + .prologue 0 + .long 0x47e03d80 # implver $0 + lda \$2,259 + .long 0x47e20c21 # amask $2,$1 + srl \$1,8,\$2 + sll \$2,2,\$2 + sll \$0,3,\$0 + addl \$1,\$0,\$0 + addl \$2,\$0,\$0 + ret \$31,(\$26),1 + .end main +EOF + LIBC="" + $CC_FOR_BUILD $dummy.s -o $dummy 2>/dev/null + if test "$?" = 0 ; then + ./$dummy + case "$?" in + 7) + UNAME_MACHINE="alpha" + ;; + 15) + UNAME_MACHINE="alphaev5" + ;; + 14) + UNAME_MACHINE="alphaev56" + ;; + 10) + UNAME_MACHINE="alphapca56" + ;; + 16) + UNAME_MACHINE="alphaev6" + ;; + esac + + objdump --private-headers $dummy | \ + grep ld.so.1 > /dev/null + if test "$?" = 0 ; then + LIBC="libc1" + fi + fi + rm -f $dummy.s $dummy + echo ${UNAME_MACHINE}-unknown-linux-gnu${LIBC} ; exit 0 + elif test "${UNAME_MACHINE}" = "mips" ; then + cat >$dummy.c </dev/null && ./$dummy "${UNAME_MACHINE}" && rm $dummy.c $dummy && exit 0 + rm -f $dummy.c $dummy + else + # Either a pre-BFD a.out linker (linux-gnuoldld) + # or one that does not give us useful --help. + # GCC wants to distinguish between linux-gnuoldld and linux-gnuaout. + # If ld does not provide *any* "supported emulations:" + # that means it is gnuoldld. + echo "$ld_help_string" | grep >/dev/null 2>&1 "supported emulations:" + test $? != 0 && echo "${UNAME_MACHINE}-pc-linux-gnuoldld" && exit 0 + + case "${UNAME_MACHINE}" in + i?86) + VENDOR=pc; + ;; + *) + VENDOR=unknown; + ;; + esac + # Determine whether the default compiler is a.out or elf + cat >$dummy.c < +#ifdef __cplusplus + int main (int argc, char *argv[]) { +#else + int main (argc, argv) int argc; char *argv[]; { +#endif +#ifdef __ELF__ +# ifdef __GLIBC__ +# if __GLIBC__ >= 2 + printf ("%s-${VENDOR}-linux-gnu\n", argv[1]); +# else + printf ("%s-${VENDOR}-linux-gnulibc1\n", argv[1]); +# endif +# else + printf ("%s-${VENDOR}-linux-gnulibc1\n", argv[1]); +# endif +#else + printf ("%s-${VENDOR}-linux-gnuaout\n", argv[1]); +#endif + return 0; +} +EOF + $CC_FOR_BUILD $dummy.c -o $dummy 2>/dev/null && ./$dummy "${UNAME_MACHINE}" && rm $dummy.c $dummy && exit 0 + rm -f $dummy.c $dummy + fi ;; +# ptx 4.0 does uname -s correctly, with DYNIX/ptx in there. earlier versions +# are messed up and put the nodename in both sysname and nodename. + i?86:DYNIX/ptx:4*:*) + echo i386-sequent-sysv4 + exit 0 ;; + i?86:UNIX_SV:4.2MP:2.*) + # Unixware is an offshoot of SVR4, but it has its own version + # number series starting with 2... + # I am not positive that other SVR4 systems won't match this, + # I just have to hope. -- rms. + # Use sysv4.2uw... so that sysv4* matches it. + echo ${UNAME_MACHINE}-pc-sysv4.2uw${UNAME_VERSION} + exit 0 ;; + i?86:*:4.*:* | i?86:SYSTEM_V:4.*:*) + UNAME_REL=`echo ${UNAME_RELEASE} | sed 's/\/MP$//'` + if grep Novell /usr/include/link.h >/dev/null 2>/dev/null; then + echo ${UNAME_MACHINE}-univel-sysv${UNAME_REL} + else + echo ${UNAME_MACHINE}-pc-sysv${UNAME_REL} + fi + exit 0 ;; + i?86:*:5:7*) + # Fixed at (any) Pentium or better + UNAME_MACHINE=i586 + if [ ${UNAME_SYSTEM} = "UnixWare" ] ; then + echo ${UNAME_MACHINE}-sco-sysv${UNAME_RELEASE}uw${UNAME_VERSION} + else + echo ${UNAME_MACHINE}-pc-sysv${UNAME_RELEASE} + fi + exit 0 ;; + i?86:*:3.2:*) + if test -f /usr/options/cb.name; then + UNAME_REL=`sed -n 's/.*Version //p' /dev/null >/dev/null ; then + UNAME_REL=`(/bin/uname -X|egrep Release|sed -e 's/.*= //')` + (/bin/uname -X|egrep i80486 >/dev/null) && UNAME_MACHINE=i486 + (/bin/uname -X|egrep '^Machine.*Pentium' >/dev/null) \ + && UNAME_MACHINE=i586 + (/bin/uname -X|egrep '^Machine.*Pent ?II' >/dev/null) \ + && UNAME_MACHINE=i686 + (/bin/uname -X|egrep '^Machine.*Pentium Pro' >/dev/null) \ + && UNAME_MACHINE=i686 + echo ${UNAME_MACHINE}-pc-sco$UNAME_REL + else + echo ${UNAME_MACHINE}-pc-sysv32 + fi + exit 0 ;; + pc:*:*:*) + # uname -m prints for DJGPP always 'pc', but it prints nothing about + # the processor, so we play safe by assuming i386. + echo i386-pc-msdosdjgpp + exit 0 ;; + Intel:Mach:3*:*) + echo i386-pc-mach3 + exit 0 ;; + paragon:*:*:*) + echo i860-intel-osf1 + exit 0 ;; + i860:*:4.*:*) # i860-SVR4 + if grep Stardent /usr/include/sys/uadmin.h >/dev/null 2>&1 ; then + echo i860-stardent-sysv${UNAME_RELEASE} # Stardent Vistra i860-SVR4 + else # Add other i860-SVR4 vendors below as they are discovered. + echo i860-unknown-sysv${UNAME_RELEASE} # Unknown i860-SVR4 + fi + exit 0 ;; + mini*:CTIX:SYS*5:*) + # "miniframe" + echo m68010-convergent-sysv + exit 0 ;; + M68*:*:R3V[567]*:*) + test -r /sysV68 && echo 'm68k-motorola-sysv' && exit 0 ;; + 3[34]??:*:4.0:3.0 | 3[34]??,*:*:4.0:3.0 | 4850:*:4.0:3.0) + OS_REL='' + test -r /etc/.relid \ + && OS_REL=.`sed -n 's/[^ ]* [^ ]* \([0-9][0-9]\).*/\1/p' < /etc/.relid` + /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ + && echo i486-ncr-sysv4.3${OS_REL} && exit 0 + /bin/uname -p 2>/dev/null | /bin/grep entium >/dev/null \ + && echo i586-ncr-sysv4.3${OS_REL} && exit 0 ;; + 3[34]??:*:4.0:* | 3[34]??,*:*:4.0:*) + /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ + && echo i486-ncr-sysv4 && exit 0 ;; + m68*:LynxOS:2.*:*) + echo m68k-unknown-lynxos${UNAME_RELEASE} + exit 0 ;; + mc68030:UNIX_System_V:4.*:*) + echo m68k-atari-sysv4 + exit 0 ;; + i?86:LynxOS:2.*:* | i?86:LynxOS:3.[01]*:*) + echo i386-unknown-lynxos${UNAME_RELEASE} + exit 0 ;; + TSUNAMI:LynxOS:2.*:*) + echo sparc-unknown-lynxos${UNAME_RELEASE} + exit 0 ;; + rs6000:LynxOS:2.*:* | PowerPC:LynxOS:2.*:*) + echo rs6000-unknown-lynxos${UNAME_RELEASE} + exit 0 ;; + SM[BE]S:UNIX_SV:*:*) + echo mips-dde-sysv${UNAME_RELEASE} + exit 0 ;; + RM*:ReliantUNIX-*:*:*) + echo mips-sni-sysv4 + exit 0 ;; + RM*:SINIX-*:*:*) + echo mips-sni-sysv4 + exit 0 ;; + *:SINIX-*:*:*) + if uname -p 2>/dev/null >/dev/null ; then + UNAME_MACHINE=`(uname -p) 2>/dev/null` + echo ${UNAME_MACHINE}-sni-sysv4 + else + echo ns32k-sni-sysv + fi + exit 0 ;; + PENTIUM:CPunix:4.0*:*) # Unisys `ClearPath HMP IX 4000' SVR4/MP effort + # says + echo i586-unisys-sysv4 + exit 0 ;; + *:UNIX_System_V:4*:FTX*) + # From Gerald Hewes . + # How about differentiating between stratus architectures? -djm + echo hppa1.1-stratus-sysv4 + exit 0 ;; + *:*:*:FTX*) + # From seanf@swdc.stratus.com. + echo i860-stratus-sysv4 + exit 0 ;; + mc68*:A/UX:*:*) + echo m68k-apple-aux${UNAME_RELEASE} + exit 0 ;; + news*:NEWS-OS:*:6*) + echo mips-sony-newsos6 + exit 0 ;; + R[34]000:*System_V*:*:* | R4000:UNIX_SYSV:*:* | R*000:UNIX_SV:*:*) + if [ -d /usr/nec ]; then + echo mips-nec-sysv${UNAME_RELEASE} + else + echo mips-unknown-sysv${UNAME_RELEASE} + fi + exit 0 ;; + BeBox:BeOS:*:*) # BeOS running on hardware made by Be, PPC only. + echo powerpc-be-beos + exit 0 ;; + BeMac:BeOS:*:*) # BeOS running on Mac or Mac clone, PPC only. + echo powerpc-apple-beos + exit 0 ;; + BePC:BeOS:*:*) # BeOS running on Intel PC compatible. + echo i586-pc-beos + exit 0 ;; + SX-4:SUPER-UX:*:*) + echo sx4-nec-superux${UNAME_RELEASE} + exit 0 ;; + SX-5:SUPER-UX:*:*) + echo sx5-nec-superux${UNAME_RELEASE} + exit 0 ;; + Power*:Rhapsody:*:*) + echo powerpc-apple-rhapsody${UNAME_RELEASE} + exit 0 ;; + *:Rhapsody:*:*) + echo ${UNAME_MACHINE}-apple-rhapsody${UNAME_RELEASE} + exit 0 ;; + *:QNX:*:4*) + echo i386-qnx-qnx${UNAME_VERSION} + exit 0 ;; +esac + +#echo '(No uname command or uname output not recognized.)' 1>&2 +#echo "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" 1>&2 + +cat >$dummy.c < +# include +#endif +main () +{ +#if defined (sony) +#if defined (MIPSEB) + /* BFD wants "bsd" instead of "newsos". Perhaps BFD should be changed, + I don't know.... */ + printf ("mips-sony-bsd\n"); exit (0); +#else +#include + printf ("m68k-sony-newsos%s\n", +#ifdef NEWSOS4 + "4" +#else + "" +#endif + ); exit (0); +#endif +#endif + +#if defined (__arm) && defined (__acorn) && defined (__unix) + printf ("arm-acorn-riscix"); exit (0); +#endif + +#if defined (hp300) && !defined (hpux) + printf ("m68k-hp-bsd\n"); exit (0); +#endif + +#if defined (NeXT) +#if !defined (__ARCHITECTURE__) +#define __ARCHITECTURE__ "m68k" +#endif + int version; + version=`(hostinfo | sed -n 's/.*NeXT Mach \([0-9]*\).*/\1/p') 2>/dev/null`; + if (version < 4) + printf ("%s-next-nextstep%d\n", __ARCHITECTURE__, version); + else + printf ("%s-next-openstep%d\n", __ARCHITECTURE__, version); + exit (0); +#endif + +#if defined (MULTIMAX) || defined (n16) +#if defined (UMAXV) + printf ("ns32k-encore-sysv\n"); exit (0); +#else +#if defined (CMU) + printf ("ns32k-encore-mach\n"); exit (0); +#else + printf ("ns32k-encore-bsd\n"); exit (0); +#endif +#endif +#endif + +#if defined (__386BSD__) + printf ("i386-pc-bsd\n"); exit (0); +#endif + +#if defined (sequent) +#if defined (i386) + printf ("i386-sequent-dynix\n"); exit (0); +#endif +#if defined (ns32000) + printf ("ns32k-sequent-dynix\n"); exit (0); +#endif +#endif + +#if defined (_SEQUENT_) + struct utsname un; + + uname(&un); + + if (strncmp(un.version, "V2", 2) == 0) { + printf ("i386-sequent-ptx2\n"); exit (0); + } + if (strncmp(un.version, "V1", 2) == 0) { /* XXX is V1 correct? */ + printf ("i386-sequent-ptx1\n"); exit (0); + } + printf ("i386-sequent-ptx\n"); exit (0); + +#endif + +#if defined (vax) +#if !defined (ultrix) + printf ("vax-dec-bsd\n"); exit (0); +#else + printf ("vax-dec-ultrix\n"); exit (0); +#endif +#endif + +#if defined (alliant) && defined (i860) + printf ("i860-alliant-bsd\n"); exit (0); +#endif + + exit (1); +} +EOF + +$CC_FOR_BUILD $dummy.c -o $dummy 2>/dev/null && ./$dummy && rm $dummy.c $dummy && exit 0 +rm -f $dummy.c $dummy + +# Apollos put the system type in the environment. + +test -d /usr/apollo && { echo ${ISP}-apollo-${SYSTYPE}; exit 0; } + +# Convex versions that predate uname can use getsysinfo(1) + +if [ -x /usr/convex/getsysinfo ] +then + case `getsysinfo -f cpu_type` in + c1*) + echo c1-convex-bsd + exit 0 ;; + c2*) + if getsysinfo -f scalar_acc + then echo c32-convex-bsd + else echo c2-convex-bsd + fi + exit 0 ;; + c34*) + echo c34-convex-bsd + exit 0 ;; + c38*) + echo c38-convex-bsd + exit 0 ;; + c4*) + echo c4-convex-bsd + exit 0 ;; + esac +fi + +#echo '(Unable to guess system type)' 1>&2 + +exit 1 diff --git a/pcre/config.in b/pcre/config.in new file mode 100644 index 00000000..02f42593 --- /dev/null +++ b/pcre/config.in @@ -0,0 +1,33 @@ + +/* On Unix systems config.in is converted by configure into config.h. PCRE is +written in Standard C, but there are a few non-standard things it can cope +with, allowing it to run on SunOS4 and other "close to standard" systems. + +On a non-Unix system you should just copy this file into config.h and change +the definitions of HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because +of the way autoconf works, these cannot be made the defaults. If your system +has bcopy() and not memmove(), change the definition of HAVE_BCOPY instead of +HAVE_MEMMOVE. If your system has neither bcopy() nor memmove(), leave them both +as 0; an emulation function will be used. */ + +/* Define to empty if the keyword does not work. */ + +#undef const + +/* Define to `unsigned' if doesn't define size_t. */ + +#undef size_t + +/* The following two definitions are mainly for the benefit of SunOS4, which +doesn't have the strerror() or memmove() functions that should be present in +all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should +normally be defined with the value 1 for other systems, but unfortunately we +can't make this the default because "configure" files generated by autoconf +will only change 0 to 1; they won't change 1 to 0 if the functions are not +found. If HAVE_MEMMOVE is set to 1, the value of HAVE_BCOPY is not relevant. */ + +#define HAVE_STRERROR 0 +#define HAVE_MEMMOVE 0 +#define HAVE_BCOPY 0 + +/* End */ diff --git a/pcre/config.sub b/pcre/config.sub new file mode 100644 index 00000000..28426bb8 --- /dev/null +++ b/pcre/config.sub @@ -0,0 +1,1232 @@ +#! /bin/sh +# Configuration validation subroutine script, version 1.1. +# Copyright (C) 1991, 92-97, 1998, 1999 Free Software Foundation, Inc. +# This file is (in principle) common to ALL GNU software. +# The presence of a machine in this file suggests that SOME GNU software +# can handle that machine. It does not imply ALL GNU software can. +# +# This file is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, +# Boston, MA 02111-1307, USA. + +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# Configuration subroutine to validate and canonicalize a configuration type. +# Supply the specified configuration type as an argument. +# If it is invalid, we print an error message on stderr and exit with code 1. +# Otherwise, we print the canonical config type on stdout and succeed. + +# This file is supposed to be the same for all GNU packages +# and recognize all the CPU types, system types and aliases +# that are meaningful with *any* GNU software. +# Each package is responsible for reporting which valid configurations +# it does not support. The user should be able to distinguish +# a failure to support a valid configuration from a meaningless +# configuration. + +# The goal of this file is to map all the various variations of a given +# machine specification into a single specification in the form: +# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM +# or in some cases, the newer four-part form: +# CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM +# It is wrong to echo any other type of specification. + +if [ x$1 = x ] +then + echo Configuration name missing. 1>&2 + echo "Usage: $0 CPU-MFR-OPSYS" 1>&2 + echo "or $0 ALIAS" 1>&2 + echo where ALIAS is a recognized configuration type. 1>&2 + exit 1 +fi + +# First pass through any local machine types. +case $1 in + *local*) + echo $1 + exit 0 + ;; + *) + ;; +esac + +# Separate what the user gave into CPU-COMPANY and OS or KERNEL-OS (if any). +# Here we must recognize all the valid KERNEL-OS combinations. +maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'` +case $maybe_os in + linux-gnu*) + os=-$maybe_os + basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'` + ;; + *) + basic_machine=`echo $1 | sed 's/-[^-]*$//'` + if [ $basic_machine != $1 ] + then os=`echo $1 | sed 's/.*-/-/'` + else os=; fi + ;; +esac + +### Let's recognize common machines as not being operating systems so +### that things like config.sub decstation-3100 work. We also +### recognize some manufacturers as not being operating systems, so we +### can provide default operating systems below. +case $os in + -sun*os*) + # Prevent following clause from handling this invalid input. + ;; + -dec* | -mips* | -sequent* | -encore* | -pc532* | -sgi* | -sony* | \ + -att* | -7300* | -3300* | -delta* | -motorola* | -sun[234]* | \ + -unicom* | -ibm* | -next | -hp | -isi* | -apollo | -altos* | \ + -convergent* | -ncr* | -news | -32* | -3600* | -3100* | -hitachi* |\ + -c[123]* | -convex* | -sun | -crds | -omron* | -dg | -ultra | -tti* | \ + -harris | -dolphin | -highlevel | -gould | -cbm | -ns | -masscomp | \ + -apple) + os= + basic_machine=$1 + ;; + -sim | -cisco | -oki | -wec | -winbond) + os= + basic_machine=$1 + ;; + -scout) + ;; + -wrs) + os=-vxworks + basic_machine=$1 + ;; + -hiux*) + os=-hiuxwe2 + ;; + -sco5) + os=-sco3.2v5 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco4) + os=-sco3.2v4 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco3.2.[4-9]*) + os=`echo $os | sed -e 's/sco3.2./sco3.2v/'` + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco3.2v[4-9]*) + # Don't forget version if it is 3.2v4 or newer. + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco*) + os=-sco3.2v2 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -udk*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -isc) + os=-isc2.2 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -clix*) + basic_machine=clipper-intergraph + ;; + -isc*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -lynx*) + os=-lynxos + ;; + -ptx*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-sequent/'` + ;; + -windowsnt*) + os=`echo $os | sed -e 's/windowsnt/winnt/'` + ;; + -psos*) + os=-psos + ;; + -mint | -mint[0-9]*) + basic_machine=m68k-atari + os=-mint + ;; +esac + +# Decode aliases for certain CPU-COMPANY combinations. +case $basic_machine in + # Recognize the basic CPU types without company name. + # Some are omitted here because they have special meanings below. + tahoe | i860 | ia64 | m32r | m68k | m68000 | m88k | ns32k | arc | arm \ + | arme[lb] | pyramid | mn10200 | mn10300 | tron | a29k \ + | 580 | i960 | h8300 \ + | hppa | hppa1.0 | hppa1.1 | hppa2.0 | hppa2.0w | hppa2.0n \ + | alpha | alphaev[4-7] | alphaev56 | alphapca5[67] \ + | we32k | ns16k | clipper | i370 | sh | powerpc | powerpcle \ + | 1750a | dsp16xx | pdp11 | mips16 | mips64 | mipsel | mips64el \ + | mips64orion | mips64orionel | mipstx39 | mipstx39el \ + | mips64vr4300 | mips64vr4300el | mips64vr4100 | mips64vr4100el \ + | mips64vr5000 | miprs64vr5000el | mcore \ + | sparc | sparclet | sparclite | sparc64 | sparcv9 | v850 | c4x \ + | thumb | d10v | fr30) + basic_machine=$basic_machine-unknown + ;; + m88110 | m680[12346]0 | m683?2 | m68360 | m5200 | z8k | v70 | h8500 | w65 | pj | pjl) + ;; + + # We use `pc' rather than `unknown' + # because (1) that's what they normally are, and + # (2) the word "unknown" tends to confuse beginning users. + i[34567]86) + basic_machine=$basic_machine-pc + ;; + # Object if more than one company name word. + *-*-*) + echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 + exit 1 + ;; + # Recognize the basic CPU types with company name. + # FIXME: clean up the formatting here. + vax-* | tahoe-* | i[34567]86-* | i860-* | ia64-* | m32r-* | m68k-* | m68000-* \ + | m88k-* | sparc-* | ns32k-* | fx80-* | arc-* | arm-* | c[123]* \ + | mips-* | pyramid-* | tron-* | a29k-* | romp-* | rs6000-* \ + | power-* | none-* | 580-* | cray2-* | h8300-* | h8500-* | i960-* \ + | xmp-* | ymp-* \ + | hppa-* | hppa1.0-* | hppa1.1-* | hppa2.0-* | hppa2.0w-* | hppa2.0n-* \ + | alpha-* | alphaev[4-7]-* | alphaev56-* | alphapca5[67]-* \ + | we32k-* | cydra-* | ns16k-* | pn-* | np1-* | xps100-* \ + | clipper-* | orion-* \ + | sparclite-* | pdp11-* | sh-* | powerpc-* | powerpcle-* \ + | sparc64-* | sparcv9-* | sparc86x-* | mips16-* | mips64-* | mipsel-* \ + | mips64el-* | mips64orion-* | mips64orionel-* \ + | mips64vr4100-* | mips64vr4100el-* | mips64vr4300-* | mips64vr4300el-* \ + | mipstx39-* | mipstx39el-* | mcore-* \ + | f301-* | armv*-* | t3e-* \ + | m88110-* | m680[01234]0-* | m683?2-* | m68360-* | z8k-* | d10v-* \ + | thumb-* | v850-* | d30v-* | tic30-* | c30-* | fr30-* ) + ;; + # Recognize the various machine names and aliases which stand + # for a CPU type and a company and sometimes even an OS. + 386bsd) + basic_machine=i386-unknown + os=-bsd + ;; + 3b1 | 7300 | 7300-att | att-7300 | pc7300 | safari | unixpc) + basic_machine=m68000-att + ;; + 3b*) + basic_machine=we32k-att + ;; + a29khif) + basic_machine=a29k-amd + os=-udi + ;; + adobe68k) + basic_machine=m68010-adobe + os=-scout + ;; + alliant | fx80) + basic_machine=fx80-alliant + ;; + altos | altos3068) + basic_machine=m68k-altos + ;; + am29k) + basic_machine=a29k-none + os=-bsd + ;; + amdahl) + basic_machine=580-amdahl + os=-sysv + ;; + amiga | amiga-*) + basic_machine=m68k-cbm + ;; + amigaos | amigados) + basic_machine=m68k-cbm + os=-amigaos + ;; + amigaunix | amix) + basic_machine=m68k-cbm + os=-sysv4 + ;; + apollo68) + basic_machine=m68k-apollo + os=-sysv + ;; + apollo68bsd) + basic_machine=m68k-apollo + os=-bsd + ;; + aux) + basic_machine=m68k-apple + os=-aux + ;; + balance) + basic_machine=ns32k-sequent + os=-dynix + ;; + convex-c1) + basic_machine=c1-convex + os=-bsd + ;; + convex-c2) + basic_machine=c2-convex + os=-bsd + ;; + convex-c32) + basic_machine=c32-convex + os=-bsd + ;; + convex-c34) + basic_machine=c34-convex + os=-bsd + ;; + convex-c38) + basic_machine=c38-convex + os=-bsd + ;; + cray | ymp) + basic_machine=ymp-cray + os=-unicos + ;; + cray2) + basic_machine=cray2-cray + os=-unicos + ;; + [ctj]90-cray) + basic_machine=c90-cray + os=-unicos + ;; + crds | unos) + basic_machine=m68k-crds + ;; + da30 | da30-*) + basic_machine=m68k-da30 + ;; + decstation | decstation-3100 | pmax | pmax-* | pmin | dec3100 | decstatn) + basic_machine=mips-dec + ;; + delta | 3300 | motorola-3300 | motorola-delta \ + | 3300-motorola | delta-motorola) + basic_machine=m68k-motorola + ;; + delta88) + basic_machine=m88k-motorola + os=-sysv3 + ;; + dpx20 | dpx20-*) + basic_machine=rs6000-bull + os=-bosx + ;; + dpx2* | dpx2*-bull) + basic_machine=m68k-bull + os=-sysv3 + ;; + ebmon29k) + basic_machine=a29k-amd + os=-ebmon + ;; + elxsi) + basic_machine=elxsi-elxsi + os=-bsd + ;; + encore | umax | mmax) + basic_machine=ns32k-encore + ;; + es1800 | OSE68k | ose68k | ose | OSE) + basic_machine=m68k-ericsson + os=-ose + ;; + fx2800) + basic_machine=i860-alliant + ;; + genix) + basic_machine=ns32k-ns + ;; + gmicro) + basic_machine=tron-gmicro + os=-sysv + ;; + h3050r* | hiux*) + basic_machine=hppa1.1-hitachi + os=-hiuxwe2 + ;; + h8300hms) + basic_machine=h8300-hitachi + os=-hms + ;; + h8300xray) + basic_machine=h8300-hitachi + os=-xray + ;; + h8500hms) + basic_machine=h8500-hitachi + os=-hms + ;; + harris) + basic_machine=m88k-harris + os=-sysv3 + ;; + hp300-*) + basic_machine=m68k-hp + ;; + hp300bsd) + basic_machine=m68k-hp + os=-bsd + ;; + hp300hpux) + basic_machine=m68k-hp + os=-hpux + ;; + hp3k9[0-9][0-9] | hp9[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hp9k2[0-9][0-9] | hp9k31[0-9]) + basic_machine=m68000-hp + ;; + hp9k3[2-9][0-9]) + basic_machine=m68k-hp + ;; + hp9k6[0-9][0-9] | hp6[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hp9k7[0-79][0-9] | hp7[0-79][0-9]) + basic_machine=hppa1.1-hp + ;; + hp9k78[0-9] | hp78[0-9]) + # FIXME: really hppa2.0-hp + basic_machine=hppa1.1-hp + ;; + hp9k8[67]1 | hp8[67]1 | hp9k80[24] | hp80[24] | hp9k8[78]9 | hp8[78]9 | hp9k893 | hp893) + # FIXME: really hppa2.0-hp + basic_machine=hppa1.1-hp + ;; + hp9k8[0-9][13679] | hp8[0-9][13679]) + basic_machine=hppa1.1-hp + ;; + hp9k8[0-9][0-9] | hp8[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hppa-next) + os=-nextstep3 + ;; + hppaosf) + basic_machine=hppa1.1-hp + os=-osf + ;; + hppro) + basic_machine=hppa1.1-hp + os=-proelf + ;; + i370-ibm* | ibm*) + basic_machine=i370-ibm + ;; +# I'm not sure what "Sysv32" means. Should this be sysv3.2? + i[34567]86v32) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv32 + ;; + i[34567]86v4*) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv4 + ;; + i[34567]86v) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv + ;; + i[34567]86sol2) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-solaris2 + ;; + i386mach) + basic_machine=i386-mach + os=-mach + ;; + i386-vsta | vsta) + basic_machine=i386-unknown + os=-vsta + ;; + i386-go32 | go32) + basic_machine=i386-unknown + os=-go32 + ;; + i386-mingw32 | mingw32) + basic_machine=i386-unknown + os=-mingw32 + ;; + i386-qnx | qnx) + basic_machine=i386-qnx + ;; + iris | iris4d) + basic_machine=mips-sgi + case $os in + -irix*) + ;; + *) + os=-irix4 + ;; + esac + ;; + isi68 | isi) + basic_machine=m68k-isi + os=-sysv + ;; + m88k-omron*) + basic_machine=m88k-omron + ;; + magnum | m3230) + basic_machine=mips-mips + os=-sysv + ;; + merlin) + basic_machine=ns32k-utek + os=-sysv + ;; + miniframe) + basic_machine=m68000-convergent + ;; + *mint | -mint[0-9]* | *MiNT | *MiNT[0-9]*) + basic_machine=m68k-atari + os=-mint + ;; + mipsel*-linux*) + basic_machine=mipsel-unknown + os=-linux-gnu + ;; + mips*-linux*) + basic_machine=mips-unknown + os=-linux-gnu + ;; + mips3*-*) + basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'` + ;; + mips3*) + basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'`-unknown + ;; + monitor) + basic_machine=m68k-rom68k + os=-coff + ;; + msdos) + basic_machine=i386-unknown + os=-msdos + ;; + mvs) + basic_machine=i370-ibm + os=-mvs + ;; + ncr3000) + basic_machine=i486-ncr + os=-sysv4 + ;; + netbsd386) + basic_machine=i386-unknown + os=-netbsd + ;; + netwinder) + basic_machine=armv4l-rebel + os=-linux + ;; + news | news700 | news800 | news900) + basic_machine=m68k-sony + os=-newsos + ;; + news1000) + basic_machine=m68030-sony + os=-newsos + ;; + news-3600 | risc-news) + basic_machine=mips-sony + os=-newsos + ;; + necv70) + basic_machine=v70-nec + os=-sysv + ;; + next | m*-next ) + basic_machine=m68k-next + case $os in + -nextstep* ) + ;; + -ns2*) + os=-nextstep2 + ;; + *) + os=-nextstep3 + ;; + esac + ;; + nh3000) + basic_machine=m68k-harris + os=-cxux + ;; + nh[45]000) + basic_machine=m88k-harris + os=-cxux + ;; + nindy960) + basic_machine=i960-intel + os=-nindy + ;; + mon960) + basic_machine=i960-intel + os=-mon960 + ;; + np1) + basic_machine=np1-gould + ;; + op50n-* | op60c-*) + basic_machine=hppa1.1-oki + os=-proelf + ;; + OSE68000 | ose68000) + basic_machine=m68000-ericsson + os=-ose + ;; + os68k) + basic_machine=m68k-none + os=-os68k + ;; + pa-hitachi) + basic_machine=hppa1.1-hitachi + os=-hiuxwe2 + ;; + paragon) + basic_machine=i860-intel + os=-osf + ;; + pbd) + basic_machine=sparc-tti + ;; + pbb) + basic_machine=m68k-tti + ;; + pc532 | pc532-*) + basic_machine=ns32k-pc532 + ;; + pentium | p5 | k5 | k6 | nexen) + basic_machine=i586-pc + ;; + pentiumpro | p6 | 6x86) + basic_machine=i686-pc + ;; + pentiumii | pentium2) + basic_machine=i786-pc + ;; + pentium-* | p5-* | k5-* | k6-* | nexen-*) + basic_machine=i586-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentiumpro-* | p6-* | 6x86-*) + basic_machine=i686-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentiumii-* | pentium2-*) + basic_machine=i786-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pn) + basic_machine=pn-gould + ;; + power) basic_machine=rs6000-ibm + ;; + ppc) basic_machine=powerpc-unknown + ;; + ppc-*) basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ppcle | powerpclittle | ppc-le | powerpc-little) + basic_machine=powerpcle-unknown + ;; + ppcle-* | powerpclittle-*) + basic_machine=powerpcle-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ps2) + basic_machine=i386-ibm + ;; + rom68k) + basic_machine=m68k-rom68k + os=-coff + ;; + rm[46]00) + basic_machine=mips-siemens + ;; + rtpc | rtpc-*) + basic_machine=romp-ibm + ;; + sa29200) + basic_machine=a29k-amd + os=-udi + ;; + sequent) + basic_machine=i386-sequent + ;; + sh) + basic_machine=sh-hitachi + os=-hms + ;; + sparclite-wrs) + basic_machine=sparclite-wrs + os=-vxworks + ;; + sps7) + basic_machine=m68k-bull + os=-sysv2 + ;; + spur) + basic_machine=spur-unknown + ;; + st2000) + basic_machine=m68k-tandem + ;; + stratus) + basic_machine=i860-stratus + os=-sysv4 + ;; + sun2) + basic_machine=m68000-sun + ;; + sun2os3) + basic_machine=m68000-sun + os=-sunos3 + ;; + sun2os4) + basic_machine=m68000-sun + os=-sunos4 + ;; + sun3os3) + basic_machine=m68k-sun + os=-sunos3 + ;; + sun3os4) + basic_machine=m68k-sun + os=-sunos4 + ;; + sun4os3) + basic_machine=sparc-sun + os=-sunos3 + ;; + sun4os4) + basic_machine=sparc-sun + os=-sunos4 + ;; + sun4sol2) + basic_machine=sparc-sun + os=-solaris2 + ;; + sun3 | sun3-*) + basic_machine=m68k-sun + ;; + sun4) + basic_machine=sparc-sun + ;; + sun386 | sun386i | roadrunner) + basic_machine=i386-sun + ;; + symmetry) + basic_machine=i386-sequent + os=-dynix + ;; + t3e) + basic_machine=t3e-cray + os=-unicos + ;; + tx39) + basic_machine=mipstx39-unknown + ;; + tx39el) + basic_machine=mipstx39el-unknown + ;; + tower | tower-32) + basic_machine=m68k-ncr + ;; + udi29k) + basic_machine=a29k-amd + os=-udi + ;; + ultra3) + basic_machine=a29k-nyu + os=-sym1 + ;; + v810 | necv810) + basic_machine=v810-nec + os=-none + ;; + vaxv) + basic_machine=vax-dec + os=-sysv + ;; + vms) + basic_machine=vax-dec + os=-vms + ;; + vpp*|vx|vx-*) + basic_machine=f301-fujitsu + ;; + vxworks960) + basic_machine=i960-wrs + os=-vxworks + ;; + vxworks68) + basic_machine=m68k-wrs + os=-vxworks + ;; + vxworks29k) + basic_machine=a29k-wrs + os=-vxworks + ;; + w65*) + basic_machine=w65-wdc + os=-none + ;; + w89k-*) + basic_machine=hppa1.1-winbond + os=-proelf + ;; + xmp) + basic_machine=xmp-cray + os=-unicos + ;; + xps | xps100) + basic_machine=xps100-honeywell + ;; + z8k-*-coff) + basic_machine=z8k-unknown + os=-sim + ;; + none) + basic_machine=none-none + os=-none + ;; + +# Here we handle the default manufacturer of certain CPU types. It is in +# some cases the only manufacturer, in others, it is the most popular. + w89k) + basic_machine=hppa1.1-winbond + ;; + op50n) + basic_machine=hppa1.1-oki + ;; + op60c) + basic_machine=hppa1.1-oki + ;; + mips) + if [ x$os = x-linux-gnu ]; then + basic_machine=mips-unknown + else + basic_machine=mips-mips + fi + ;; + romp) + basic_machine=romp-ibm + ;; + rs6000) + basic_machine=rs6000-ibm + ;; + vax) + basic_machine=vax-dec + ;; + pdp11) + basic_machine=pdp11-dec + ;; + we32k) + basic_machine=we32k-att + ;; + sparc | sparcv9) + basic_machine=sparc-sun + ;; + cydra) + basic_machine=cydra-cydrome + ;; + orion) + basic_machine=orion-highlevel + ;; + orion105) + basic_machine=clipper-highlevel + ;; + mac | mpw | mac-mpw) + basic_machine=m68k-apple + ;; + pmac | pmac-mpw) + basic_machine=powerpc-apple + ;; + c4x*) + basic_machine=c4x-none + os=-coff + ;; + *) + echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 + exit 1 + ;; +esac + +# Here we canonicalize certain aliases for manufacturers. +case $basic_machine in + *-digital*) + basic_machine=`echo $basic_machine | sed 's/digital.*/dec/'` + ;; + *-commodore*) + basic_machine=`echo $basic_machine | sed 's/commodore.*/cbm/'` + ;; + *) + ;; +esac + +# Decode manufacturer-specific aliases for certain operating systems. + +if [ x"$os" != x"" ] +then +case $os in + # First match some system type aliases + # that might get confused with valid system types. + # -solaris* is a basic system type, with this one exception. + -solaris1 | -solaris1.*) + os=`echo $os | sed -e 's|solaris1|sunos4|'` + ;; + -solaris) + os=-solaris2 + ;; + -svr4*) + os=-sysv4 + ;; + -unixware*) + os=-sysv4.2uw + ;; + -gnu/linux*) + os=`echo $os | sed -e 's|gnu/linux|linux-gnu|'` + ;; + # First accept the basic system types. + # The portable systems comes first. + # Each alternative MUST END IN A *, to match a version number. + # -sysv* is not here because it comes later, after sysvr4. + -gnu* | -bsd* | -mach* | -minix* | -genix* | -ultrix* | -irix* \ + | -*vms* | -sco* | -esix* | -isc* | -aix* | -sunos | -sunos[34]*\ + | -hpux* | -unos* | -osf* | -luna* | -dgux* | -solaris* | -sym* \ + | -amigaos* | -amigados* | -msdos* | -newsos* | -unicos* | -aof* \ + | -aos* \ + | -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \ + | -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \ + | -hiux* | -386bsd* | -netbsd* | -openbsd* | -freebsd* | -riscix* \ + | -lynxos* | -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \ + | -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \ + | -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \ + | -cygwin* | -pe* | -psos* | -moss* | -proelf* | -rtems* \ + | -mingw32* | -linux-gnu* | -uxpv* | -beos* | -mpeix* | -udk* \ + | -interix* | -uwin* | -rhapsody* | -opened* | -openstep* | -oskit*) + # Remember, each alternative MUST END IN *, to match a version number. + ;; + -sim | -es1800* | -hms* | -xray | -os68k* | -none* | -v88r* \ + | -windows* | -osx | -abug | -netware* | -os9* | -beos* \ + | -macos* | -mpw* | -magic* | -mon960* | -lnews*) + ;; + -mac*) + os=`echo $os | sed -e 's|mac|macos|'` + ;; + -linux*) + os=`echo $os | sed -e 's|linux|linux-gnu|'` + ;; + -sunos5*) + os=`echo $os | sed -e 's|sunos5|solaris2|'` + ;; + -sunos6*) + os=`echo $os | sed -e 's|sunos6|solaris3|'` + ;; + -opened*) + os=-openedition + ;; + -osfrose*) + os=-osfrose + ;; + -osf*) + os=-osf + ;; + -utek*) + os=-bsd + ;; + -dynix*) + os=-bsd + ;; + -acis*) + os=-aos + ;; + -386bsd) + os=-bsd + ;; + -ctix* | -uts*) + os=-sysv + ;; + -ns2 ) + os=-nextstep2 + ;; + # Preserve the version number of sinix5. + -sinix5.*) + os=`echo $os | sed -e 's|sinix|sysv|'` + ;; + -sinix*) + os=-sysv4 + ;; + -triton*) + os=-sysv3 + ;; + -oss*) + os=-sysv3 + ;; + -qnx) + os=-qnx4 + ;; + -svr4) + os=-sysv4 + ;; + -svr3) + os=-sysv3 + ;; + -sysvr4) + os=-sysv4 + ;; + # This must come after -sysvr4. + -sysv*) + ;; + -ose*) + os=-ose + ;; + -es1800*) + os=-ose + ;; + -xenix) + os=-xenix + ;; + -*mint | -*MiNT) + os=-mint + ;; + -none) + ;; + *) + # Get rid of the `-' at the beginning of $os. + os=`echo $os | sed 's/[^-]*-//'` + echo Invalid configuration \`$1\': system \`$os\' not recognized 1>&2 + exit 1 + ;; +esac +else + +# Here we handle the default operating systems that come with various machines. +# The value should be what the vendor currently ships out the door with their +# machine or put another way, the most popular os provided with the machine. + +# Note that if you're going to try to match "-MANUFACTURER" here (say, +# "-sun"), then you have to tell the case statement up towards the top +# that MANUFACTURER isn't an operating system. Otherwise, code above +# will signal an error saying that MANUFACTURER isn't an operating +# system, and we'll never get to this point. + +case $basic_machine in + *-acorn) + os=-riscix1.2 + ;; + arm*-rebel) + os=-linux + ;; + arm*-semi) + os=-aout + ;; + pdp11-*) + os=-none + ;; + *-dec | vax-*) + os=-ultrix4.2 + ;; + m68*-apollo) + os=-domain + ;; + i386-sun) + os=-sunos4.0.2 + ;; + m68000-sun) + os=-sunos3 + # This also exists in the configure program, but was not the + # default. + # os=-sunos4 + ;; + m68*-cisco) + os=-aout + ;; + mips*-cisco) + os=-elf + ;; + mips*-*) + os=-elf + ;; + *-tti) # must be before sparc entry or we get the wrong os. + os=-sysv3 + ;; + sparc-* | *-sun) + os=-sunos4.1.1 + ;; + *-be) + os=-beos + ;; + *-ibm) + os=-aix + ;; + *-wec) + os=-proelf + ;; + *-winbond) + os=-proelf + ;; + *-oki) + os=-proelf + ;; + *-hp) + os=-hpux + ;; + *-hitachi) + os=-hiux + ;; + i860-* | *-att | *-ncr | *-altos | *-motorola | *-convergent) + os=-sysv + ;; + *-cbm) + os=-amigaos + ;; + *-dg) + os=-dgux + ;; + *-dolphin) + os=-sysv3 + ;; + m68k-ccur) + os=-rtu + ;; + m88k-omron*) + os=-luna + ;; + *-next ) + os=-nextstep + ;; + *-sequent) + os=-ptx + ;; + *-crds) + os=-unos + ;; + *-ns) + os=-genix + ;; + i370-*) + os=-mvs + ;; + *-next) + os=-nextstep3 + ;; + *-gould) + os=-sysv + ;; + *-highlevel) + os=-bsd + ;; + *-encore) + os=-bsd + ;; + *-sgi) + os=-irix + ;; + *-siemens) + os=-sysv4 + ;; + *-masscomp) + os=-rtu + ;; + f301-fujitsu) + os=-uxpv + ;; + *-rom68k) + os=-coff + ;; + *-*bug) + os=-coff + ;; + *-apple) + os=-macos + ;; + *-atari*) + os=-mint + ;; + *) + os=-none + ;; +esac +fi + +# Here we handle the case where we know the os, and the CPU type, but not the +# manufacturer. We pick the logical manufacturer. +vendor=unknown +case $basic_machine in + *-unknown) + case $os in + -riscix*) + vendor=acorn + ;; + -sunos*) + vendor=sun + ;; + -aix*) + vendor=ibm + ;; + -beos*) + vendor=be + ;; + -hpux*) + vendor=hp + ;; + -mpeix*) + vendor=hp + ;; + -hiux*) + vendor=hitachi + ;; + -unos*) + vendor=crds + ;; + -dgux*) + vendor=dg + ;; + -luna*) + vendor=omron + ;; + -genix*) + vendor=ns + ;; + -mvs* | -opened*) + vendor=ibm + ;; + -ptx*) + vendor=sequent + ;; + -vxsim* | -vxworks*) + vendor=wrs + ;; + -aux*) + vendor=apple + ;; + -hms*) + vendor=hitachi + ;; + -mpw* | -macos*) + vendor=apple + ;; + -*mint | -*MiNT) + vendor=atari + ;; + esac + basic_machine=`echo $basic_machine | sed "s/unknown/$vendor/"` + ;; +esac + +echo $basic_machine$os diff --git a/pcre/configure b/pcre/configure new file mode 100644 index 00000000..fbd3831e --- /dev/null +++ b/pcre/configure @@ -0,0 +1,1568 @@ +#! /bin/sh + +# Guess values for system-dependent variables and create Makefiles. +# Generated automatically using autoconf version 2.13 +# Copyright (C) 1992, 93, 94, 95, 96 Free Software Foundation, Inc. +# +# This configure script is free software; the Free Software Foundation +# gives unlimited permission to copy, distribute and modify it. + +# Defaults: +ac_help= +ac_default_prefix=/usr/local +# Any additions from configure.in: +ac_help="$ac_help + --disable-shared build PCRE as a static library" +ac_help="$ac_help + --enable-utf8 enable UTF8 support (incomplete)" + +# Initialize some variables set by options. +# The variables have the same names as the options, with +# dashes changed to underlines. +build=NONE +cache_file=./config.cache +exec_prefix=NONE +host=NONE +no_create= +nonopt=NONE +no_recursion= +prefix=NONE +program_prefix=NONE +program_suffix=NONE +program_transform_name=s,x,x, +silent= +site= +srcdir= +target=NONE +verbose= +x_includes=NONE +x_libraries=NONE +bindir='${exec_prefix}/bin' +sbindir='${exec_prefix}/sbin' +libexecdir='${exec_prefix}/libexec' +datadir='${prefix}/share' +sysconfdir='${prefix}/etc' +sharedstatedir='${prefix}/com' +localstatedir='${prefix}/var' +libdir='${exec_prefix}/lib' +includedir='${prefix}/include' +oldincludedir='/usr/include' +infodir='${prefix}/info' +mandir='${prefix}/man' + +# Initialize some other variables. +subdirs= +MFLAGS= MAKEFLAGS= +SHELL=${CONFIG_SHELL-/bin/sh} +# Maximum number of lines to put in a shell here document. +ac_max_here_lines=12 + +ac_prev= +for ac_option +do + + # If the previous option needs an argument, assign it. + if test -n "$ac_prev"; then + eval "$ac_prev=\$ac_option" + ac_prev= + continue + fi + + case "$ac_option" in + -*=*) ac_optarg=`echo "$ac_option" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) ac_optarg= ;; + esac + + # Accept the important Cygnus configure options, so we can diagnose typos. + + case "$ac_option" in + + -bindir | --bindir | --bindi | --bind | --bin | --bi) + ac_prev=bindir ;; + -bindir=* | --bindir=* | --bindi=* | --bind=* | --bin=* | --bi=*) + bindir="$ac_optarg" ;; + + -build | --build | --buil | --bui | --bu) + ac_prev=build ;; + -build=* | --build=* | --buil=* | --bui=* | --bu=*) + build="$ac_optarg" ;; + + -cache-file | --cache-file | --cache-fil | --cache-fi \ + | --cache-f | --cache- | --cache | --cach | --cac | --ca | --c) + ac_prev=cache_file ;; + -cache-file=* | --cache-file=* | --cache-fil=* | --cache-fi=* \ + | --cache-f=* | --cache-=* | --cache=* | --cach=* | --cac=* | --ca=* | --c=*) + cache_file="$ac_optarg" ;; + + -datadir | --datadir | --datadi | --datad | --data | --dat | --da) + ac_prev=datadir ;; + -datadir=* | --datadir=* | --datadi=* | --datad=* | --data=* | --dat=* \ + | --da=*) + datadir="$ac_optarg" ;; + + -disable-* | --disable-*) + ac_feature=`echo $ac_option|sed -e 's/-*disable-//'` + # Reject names that are not valid shell variable names. + if test -n "`echo $ac_feature| sed 's/[-a-zA-Z0-9_]//g'`"; then + { echo "configure: error: $ac_feature: invalid feature name" 1>&2; exit 1; } + fi + ac_feature=`echo $ac_feature| sed 's/-/_/g'` + eval "enable_${ac_feature}=no" ;; + + -enable-* | --enable-*) + ac_feature=`echo $ac_option|sed -e 's/-*enable-//' -e 's/=.*//'` + # Reject names that are not valid shell variable names. + if test -n "`echo $ac_feature| sed 's/[-_a-zA-Z0-9]//g'`"; then + { echo "configure: error: $ac_feature: invalid feature name" 1>&2; exit 1; } + fi + ac_feature=`echo $ac_feature| sed 's/-/_/g'` + case "$ac_option" in + *=*) ;; + *) ac_optarg=yes ;; + esac + eval "enable_${ac_feature}='$ac_optarg'" ;; + + -exec-prefix | --exec_prefix | --exec-prefix | --exec-prefi \ + | --exec-pref | --exec-pre | --exec-pr | --exec-p | --exec- \ + | --exec | --exe | --ex) + ac_prev=exec_prefix ;; + -exec-prefix=* | --exec_prefix=* | --exec-prefix=* | --exec-prefi=* \ + | --exec-pref=* | --exec-pre=* | --exec-pr=* | --exec-p=* | --exec-=* \ + | --exec=* | --exe=* | --ex=*) + exec_prefix="$ac_optarg" ;; + + -gas | --gas | --ga | --g) + # Obsolete; use --with-gas. + with_gas=yes ;; + + -help | --help | --hel | --he) + # Omit some internal or obsolete options to make the list less imposing. + # The list generated by autoconf has been trimmed to remove many + # options that are totally irrelevant to PCRE (e.g. relating to X), + # or are not supported by its Makefile. + # The list generated by autoconf has been trimmed to remove many + # options that are totally irrelevant to PCRE (e.g. relating to X), + # or are not supported by its Makefile. + # The list generated by autoconf has been trimmed to remove many + # options that are totally irrelevant to PCRE (e.g. relating to X), + # or are not supported by its Makefile. + # This message is too long to be a string in the A/UX 3.1 sh. + cat << EOF +Usage: ./configure [options] +Options: [defaults in brackets after descriptions] +Configuration: + --cache-file=FILE cache test results in FILE + --help print this message + --no-create do not create output files + --quiet, --silent do not print \`checking...' messages + --version print the version of autoconf that created configure +Directory and file names: + --prefix=PREFIX install architecture-independent files in PREFIX + [$ac_default_prefix] + --exec-prefix=EPREFIX install architecture-dependent files in EPREFIX + [same as prefix] + --bindir=DIR user executables in DIR [EPREFIX/bin] + --libdir=DIR object code libraries in DIR [EPREFIX/lib] + --includedir=DIR C header files in DIR [PREFIX/include] + --mandir=DIR man documentation in DIR [PREFIX/man] +EOF + cat << EOF +EOF + if test -n "$ac_help"; then + echo "--enable and --with options recognized:$ac_help" + fi + exit 0 ;; + + -host | --host | --hos | --ho) + ac_prev=host ;; + -host=* | --host=* | --hos=* | --ho=*) + host="$ac_optarg" ;; + + -includedir | --includedir | --includedi | --included | --include \ + | --includ | --inclu | --incl | --inc) + ac_prev=includedir ;; + -includedir=* | --includedir=* | --includedi=* | --included=* | --include=* \ + | --includ=* | --inclu=* | --incl=* | --inc=*) + includedir="$ac_optarg" ;; + + -infodir | --infodir | --infodi | --infod | --info | --inf) + ac_prev=infodir ;; + -infodir=* | --infodir=* | --infodi=* | --infod=* | --info=* | --inf=*) + infodir="$ac_optarg" ;; + + -libdir | --libdir | --libdi | --libd) + ac_prev=libdir ;; + -libdir=* | --libdir=* | --libdi=* | --libd=*) + libdir="$ac_optarg" ;; + + -libexecdir | --libexecdir | --libexecdi | --libexecd | --libexec \ + | --libexe | --libex | --libe) + ac_prev=libexecdir ;; + -libexecdir=* | --libexecdir=* | --libexecdi=* | --libexecd=* | --libexec=* \ + | --libexe=* | --libex=* | --libe=*) + libexecdir="$ac_optarg" ;; + + -localstatedir | --localstatedir | --localstatedi | --localstated \ + | --localstate | --localstat | --localsta | --localst \ + | --locals | --local | --loca | --loc | --lo) + ac_prev=localstatedir ;; + -localstatedir=* | --localstatedir=* | --localstatedi=* | --localstated=* \ + | --localstate=* | --localstat=* | --localsta=* | --localst=* \ + | --locals=* | --local=* | --loca=* | --loc=* | --lo=*) + localstatedir="$ac_optarg" ;; + + -mandir | --mandir | --mandi | --mand | --man | --ma | --m) + ac_prev=mandir ;; + -mandir=* | --mandir=* | --mandi=* | --mand=* | --man=* | --ma=* | --m=*) + mandir="$ac_optarg" ;; + + -nfp | --nfp | --nf) + # Obsolete; use --without-fp. + with_fp=no ;; + + -no-create | --no-create | --no-creat | --no-crea | --no-cre \ + | --no-cr | --no-c) + no_create=yes ;; + + -no-recursion | --no-recursion | --no-recursio | --no-recursi \ + | --no-recurs | --no-recur | --no-recu | --no-rec | --no-re | --no-r) + no_recursion=yes ;; + + -oldincludedir | --oldincludedir | --oldincludedi | --oldincluded \ + | --oldinclude | --oldinclud | --oldinclu | --oldincl | --oldinc \ + | --oldin | --oldi | --old | --ol | --o) + ac_prev=oldincludedir ;; + -oldincludedir=* | --oldincludedir=* | --oldincludedi=* | --oldincluded=* \ + | --oldinclude=* | --oldinclud=* | --oldinclu=* | --oldincl=* | --oldinc=* \ + | --oldin=* | --oldi=* | --old=* | --ol=* | --o=*) + oldincludedir="$ac_optarg" ;; + + -prefix | --prefix | --prefi | --pref | --pre | --pr | --p) + ac_prev=prefix ;; + -prefix=* | --prefix=* | --prefi=* | --pref=* | --pre=* | --pr=* | --p=*) + prefix="$ac_optarg" ;; + + -program-prefix | --program-prefix | --program-prefi | --program-pref \ + | --program-pre | --program-pr | --program-p) + ac_prev=program_prefix ;; + -program-prefix=* | --program-prefix=* | --program-prefi=* \ + | --program-pref=* | --program-pre=* | --program-pr=* | --program-p=*) + program_prefix="$ac_optarg" ;; + + -program-suffix | --program-suffix | --program-suffi | --program-suff \ + | --program-suf | --program-su | --program-s) + ac_prev=program_suffix ;; + -program-suffix=* | --program-suffix=* | --program-suffi=* \ + | --program-suff=* | --program-suf=* | --program-su=* | --program-s=*) + program_suffix="$ac_optarg" ;; + + -program-transform-name | --program-transform-name \ + | --program-transform-nam | --program-transform-na \ + | --program-transform-n | --program-transform- \ + | --program-transform | --program-transfor \ + | --program-transfo | --program-transf \ + | --program-trans | --program-tran \ + | --progr-tra | --program-tr | --program-t) + ac_prev=program_transform_name ;; + -program-transform-name=* | --program-transform-name=* \ + | --program-transform-nam=* | --program-transform-na=* \ + | --program-transform-n=* | --program-transform-=* \ + | --program-transform=* | --program-transfor=* \ + | --program-transfo=* | --program-transf=* \ + | --program-trans=* | --program-tran=* \ + | --progr-tra=* | --program-tr=* | --program-t=*) + program_transform_name="$ac_optarg" ;; + + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil) + silent=yes ;; + + -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb) + ac_prev=sbindir ;; + -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \ + | --sbi=* | --sb=*) + sbindir="$ac_optarg" ;; + + -sharedstatedir | --sharedstatedir | --sharedstatedi \ + | --sharedstated | --sharedstate | --sharedstat | --sharedsta \ + | --sharedst | --shareds | --shared | --share | --shar \ + | --sha | --sh) + ac_prev=sharedstatedir ;; + -sharedstatedir=* | --sharedstatedir=* | --sharedstatedi=* \ + | --sharedstated=* | --sharedstate=* | --sharedstat=* | --sharedsta=* \ + | --sharedst=* | --shareds=* | --shared=* | --share=* | --shar=* \ + | --sha=* | --sh=*) + sharedstatedir="$ac_optarg" ;; + + -site | --site | --sit) + ac_prev=site ;; + -site=* | --site=* | --sit=*) + site="$ac_optarg" ;; + + -srcdir | --srcdir | --srcdi | --srcd | --src | --sr) + ac_prev=srcdir ;; + -srcdir=* | --srcdir=* | --srcdi=* | --srcd=* | --src=* | --sr=*) + srcdir="$ac_optarg" ;; + + -sysconfdir | --sysconfdir | --sysconfdi | --sysconfd | --sysconf \ + | --syscon | --sysco | --sysc | --sys | --sy) + ac_prev=sysconfdir ;; + -sysconfdir=* | --sysconfdir=* | --sysconfdi=* | --sysconfd=* | --sysconf=* \ + | --syscon=* | --sysco=* | --sysc=* | --sys=* | --sy=*) + sysconfdir="$ac_optarg" ;; + + -target | --target | --targe | --targ | --tar | --ta | --t) + ac_prev=target ;; + -target=* | --target=* | --targe=* | --targ=* | --tar=* | --ta=* | --t=*) + target="$ac_optarg" ;; + + -v | -verbose | --verbose | --verbos | --verbo | --verb) + verbose=yes ;; + + -version | --version | --versio | --versi | --vers) + echo "configure generated by autoconf version 2.13" + exit 0 ;; + + -with-* | --with-*) + ac_package=`echo $ac_option|sed -e 's/-*with-//' -e 's/=.*//'` + # Reject names that are not valid shell variable names. + if test -n "`echo $ac_package| sed 's/[-_a-zA-Z0-9]//g'`"; then + { echo "configure: error: $ac_package: invalid package name" 1>&2; exit 1; } + fi + ac_package=`echo $ac_package| sed 's/-/_/g'` + case "$ac_option" in + *=*) ;; + *) ac_optarg=yes ;; + esac + eval "with_${ac_package}='$ac_optarg'" ;; + + -without-* | --without-*) + ac_package=`echo $ac_option|sed -e 's/-*without-//'` + # Reject names that are not valid shell variable names. + if test -n "`echo $ac_package| sed 's/[-a-zA-Z0-9_]//g'`"; then + { echo "configure: error: $ac_package: invalid package name" 1>&2; exit 1; } + fi + ac_package=`echo $ac_package| sed 's/-/_/g'` + eval "with_${ac_package}=no" ;; + + --x) + # Obsolete; use --with-x. + with_x=yes ;; + + -x-includes | --x-includes | --x-include | --x-includ | --x-inclu \ + | --x-incl | --x-inc | --x-in | --x-i) + ac_prev=x_includes ;; + -x-includes=* | --x-includes=* | --x-include=* | --x-includ=* | --x-inclu=* \ + | --x-incl=* | --x-inc=* | --x-in=* | --x-i=*) + x_includes="$ac_optarg" ;; + + -x-libraries | --x-libraries | --x-librarie | --x-librari \ + | --x-librar | --x-libra | --x-libr | --x-lib | --x-li | --x-l) + ac_prev=x_libraries ;; + -x-libraries=* | --x-libraries=* | --x-librarie=* | --x-librari=* \ + | --x-librar=* | --x-libra=* | --x-libr=* | --x-lib=* | --x-li=* | --x-l=*) + x_libraries="$ac_optarg" ;; + + -*) { echo "configure: error: $ac_option: invalid option; use --help to show usage" 1>&2; exit 1; } + ;; + + *) + if test -n "`echo $ac_option| sed 's/[-a-z0-9.]//g'`"; then + echo "configure: warning: $ac_option: invalid host type" 1>&2 + fi + if test "x$nonopt" != xNONE; then + { echo "configure: error: can only configure for one host and one target at a time" 1>&2; exit 1; } + fi + nonopt="$ac_option" + ;; + + esac +done + +if test -n "$ac_prev"; then + { echo "configure: error: missing argument to --`echo $ac_prev | sed 's/_/-/g'`" 1>&2; exit 1; } +fi + +trap 'rm -fr conftest* confdefs* core core.* *.core $ac_clean_files; exit 1' 1 2 15 + +# File descriptor usage: +# 0 standard input +# 1 file creation +# 2 errors and warnings +# 3 some systems may open it to /dev/tty +# 4 used on the Kubota Titan +# 6 checking for... messages and results +# 5 compiler messages saved in config.log +if test "$silent" = yes; then + exec 6>/dev/null +else + exec 6>&1 +fi +exec 5>./config.log + +echo "\ +This file contains any messages produced by compilers while +running configure, to aid debugging if configure makes a mistake. +" 1>&5 + +# Strip out --no-create and --no-recursion so they do not pile up. +# Also quote any args containing shell metacharacters. +ac_configure_args= +for ac_arg +do + case "$ac_arg" in + -no-create | --no-create | --no-creat | --no-crea | --no-cre \ + | --no-cr | --no-c) ;; + -no-recursion | --no-recursion | --no-recursio | --no-recursi \ + | --no-recurs | --no-recur | --no-recu | --no-rec | --no-re | --no-r) ;; + *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?]*) + ac_configure_args="$ac_configure_args '$ac_arg'" ;; + *) ac_configure_args="$ac_configure_args $ac_arg" ;; + esac +done + +# NLS nuisances. +# Only set these to C if already set. These must not be set unconditionally +# because not all systems understand e.g. LANG=C (notably SCO). +# Fixing LC_MESSAGES prevents Solaris sh from translating var values in `set'! +# Non-C LC_CTYPE values break the ctype check. +if test "${LANG+set}" = set; then LANG=C; export LANG; fi +if test "${LC_ALL+set}" = set; then LC_ALL=C; export LC_ALL; fi +if test "${LC_MESSAGES+set}" = set; then LC_MESSAGES=C; export LC_MESSAGES; fi +if test "${LC_CTYPE+set}" = set; then LC_CTYPE=C; export LC_CTYPE; fi + +# confdefs.h avoids OS command line length limits that DEFS can exceed. +rm -rf conftest* confdefs.h +# AIX cpp loses on an empty file, so make sure it contains at least a newline. +echo > confdefs.h + +# A filename unique to this package, relative to the directory that +# configure is in, which we can look for to find out if srcdir is correct. +ac_unique_file=dftables.c + +# Find the source files, if location was not specified. +if test -z "$srcdir"; then + ac_srcdir_defaulted=yes + # Try the directory containing this script, then its parent. + ac_prog=$0 + ac_confdir=`echo $ac_prog|sed 's%/[^/][^/]*$%%'` + test "x$ac_confdir" = "x$ac_prog" && ac_confdir=. + srcdir=$ac_confdir + if test ! -r $srcdir/$ac_unique_file; then + srcdir=.. + fi +else + ac_srcdir_defaulted=no +fi +if test ! -r $srcdir/$ac_unique_file; then + if test "$ac_srcdir_defaulted" = yes; then + { echo "configure: error: can not find sources in $ac_confdir or .." 1>&2; exit 1; } + else + { echo "configure: error: can not find sources in $srcdir" 1>&2; exit 1; } + fi +fi +srcdir=`echo "${srcdir}" | sed 's%\([^/]\)/*$%\1%'` + +# Prefer explicitly selected file to automatically selected ones. +if test -z "$CONFIG_SITE"; then + if test "x$prefix" != xNONE; then + CONFIG_SITE="$prefix/share/config.site $prefix/etc/config.site" + else + CONFIG_SITE="$ac_default_prefix/share/config.site $ac_default_prefix/etc/config.site" + fi +fi +for ac_site_file in $CONFIG_SITE; do + if test -r "$ac_site_file"; then + echo "loading site script $ac_site_file" + . "$ac_site_file" + fi +done + +if test -r "$cache_file"; then + echo "loading cache $cache_file" + . $cache_file +else + echo "creating cache $cache_file" + > $cache_file +fi + +ac_ext=c +# CFLAGS is not in ac_cpp because -g, -O, etc. are not valid cpp options. +ac_cpp='$CPP $CPPFLAGS' +ac_compile='${CC-cc} -c $CFLAGS $CPPFLAGS conftest.$ac_ext 1>&5' +ac_link='${CC-cc} -o conftest${ac_exeext} $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS 1>&5' +cross_compiling=$ac_cv_prog_cc_cross + +ac_exeext= +ac_objext=o +if (echo "testing\c"; echo 1,2,3) | grep c >/dev/null; then + # Stardent Vistra SVR4 grep lacks -e, says ghazi@caip.rutgers.edu. + if (echo -n testing; echo 1,2,3) | sed s/-n/xn/ | grep xn >/dev/null; then + ac_n= ac_c=' +' ac_t=' ' + else + ac_n=-n ac_c= ac_t= + fi +else + ac_n= ac_c='\c' ac_t= +fi + + + + + + +PCRE_MAJOR=3 +PCRE_MINOR=4 +PCRE_DATE=22-Aug-2000 +PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR} + + +PCRE_LIB_VERSION=0:1:0 +PCRE_POSIXLIB_VERSION=0:0:0 + + +# Extract the first word of "gcc", so it can be a program name with args. +set dummy gcc; ac_word=$2 +echo $ac_n "checking for $ac_word""... $ac_c" 1>&6 +echo "configure:546: checking for $ac_word" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_CC'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" + ac_dummy="$PATH" + for ac_dir in $ac_dummy; do + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/$ac_word; then + ac_cv_prog_CC="gcc" + break + fi + done + IFS="$ac_save_ifs" +fi +fi +CC="$ac_cv_prog_CC" +if test -n "$CC"; then + echo "$ac_t""$CC" 1>&6 +else + echo "$ac_t""no" 1>&6 +fi + +if test -z "$CC"; then + # Extract the first word of "cc", so it can be a program name with args. +set dummy cc; ac_word=$2 +echo $ac_n "checking for $ac_word""... $ac_c" 1>&6 +echo "configure:576: checking for $ac_word" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_CC'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" + ac_prog_rejected=no + ac_dummy="$PATH" + for ac_dir in $ac_dummy; do + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/$ac_word; then + if test "$ac_dir/$ac_word" = "/usr/ucb/cc"; then + ac_prog_rejected=yes + continue + fi + ac_cv_prog_CC="cc" + break + fi + done + IFS="$ac_save_ifs" +if test $ac_prog_rejected = yes; then + # We found a bogon in the path, so make sure we never use it. + set dummy $ac_cv_prog_CC + shift + if test $# -gt 0; then + # We chose a different compiler from the bogus one. + # However, it has the same basename, so the bogon will be chosen + # first if we set CC to just the basename; use the full file name. + shift + set dummy "$ac_dir/$ac_word" "$@" + shift + ac_cv_prog_CC="$@" + fi +fi +fi +fi +CC="$ac_cv_prog_CC" +if test -n "$CC"; then + echo "$ac_t""$CC" 1>&6 +else + echo "$ac_t""no" 1>&6 +fi + + if test -z "$CC"; then + case "`uname -s`" in + *win32* | *WIN32*) + # Extract the first word of "cl", so it can be a program name with args. +set dummy cl; ac_word=$2 +echo $ac_n "checking for $ac_word""... $ac_c" 1>&6 +echo "configure:627: checking for $ac_word" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_CC'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" + ac_dummy="$PATH" + for ac_dir in $ac_dummy; do + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/$ac_word; then + ac_cv_prog_CC="cl" + break + fi + done + IFS="$ac_save_ifs" +fi +fi +CC="$ac_cv_prog_CC" +if test -n "$CC"; then + echo "$ac_t""$CC" 1>&6 +else + echo "$ac_t""no" 1>&6 +fi + ;; + esac + fi + test -z "$CC" && { echo "configure: error: no acceptable cc found in \$PATH" 1>&2; exit 1; } +fi + +echo $ac_n "checking whether the C compiler ($CC $CFLAGS $LDFLAGS) works""... $ac_c" 1>&6 +echo "configure:659: checking whether the C compiler ($CC $CFLAGS $LDFLAGS) works" >&5 + +ac_ext=c +# CFLAGS is not in ac_cpp because -g, -O, etc. are not valid cpp options. +ac_cpp='$CPP $CPPFLAGS' +ac_compile='${CC-cc} -c $CFLAGS $CPPFLAGS conftest.$ac_ext 1>&5' +ac_link='${CC-cc} -o conftest${ac_exeext} $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS 1>&5' +cross_compiling=$ac_cv_prog_cc_cross + +cat > conftest.$ac_ext << EOF + +#line 670 "configure" +#include "confdefs.h" + +main(){return(0);} +EOF +if { (eval echo configure:675: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + ac_cv_prog_cc_works=yes + # If we can't run a trivial program, we are probably using a cross compiler. + if (./conftest; exit) 2>/dev/null; then + ac_cv_prog_cc_cross=no + else + ac_cv_prog_cc_cross=yes + fi +else + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + ac_cv_prog_cc_works=no +fi +rm -fr conftest* +ac_ext=c +# CFLAGS is not in ac_cpp because -g, -O, etc. are not valid cpp options. +ac_cpp='$CPP $CPPFLAGS' +ac_compile='${CC-cc} -c $CFLAGS $CPPFLAGS conftest.$ac_ext 1>&5' +ac_link='${CC-cc} -o conftest${ac_exeext} $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS 1>&5' +cross_compiling=$ac_cv_prog_cc_cross + +echo "$ac_t""$ac_cv_prog_cc_works" 1>&6 +if test $ac_cv_prog_cc_works = no; then + { echo "configure: error: installation or configuration problem: C compiler cannot create executables." 1>&2; exit 1; } +fi +echo $ac_n "checking whether the C compiler ($CC $CFLAGS $LDFLAGS) is a cross-compiler""... $ac_c" 1>&6 +echo "configure:701: checking whether the C compiler ($CC $CFLAGS $LDFLAGS) is a cross-compiler" >&5 +echo "$ac_t""$ac_cv_prog_cc_cross" 1>&6 +cross_compiling=$ac_cv_prog_cc_cross + +echo $ac_n "checking whether we are using GNU C""... $ac_c" 1>&6 +echo "configure:706: checking whether we are using GNU C" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_gcc'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.c <&5; (eval $ac_try) 2>&5; }; } | egrep yes >/dev/null 2>&1; then + ac_cv_prog_gcc=yes +else + ac_cv_prog_gcc=no +fi +fi + +echo "$ac_t""$ac_cv_prog_gcc" 1>&6 + +if test $ac_cv_prog_gcc = yes; then + GCC=yes +else + GCC= +fi + +ac_test_CFLAGS="${CFLAGS+set}" +ac_save_CFLAGS="$CFLAGS" +CFLAGS= +echo $ac_n "checking whether ${CC-cc} accepts -g""... $ac_c" 1>&6 +echo "configure:734: checking whether ${CC-cc} accepts -g" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_cc_g'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + echo 'void f(){}' > conftest.c +if test -z "`${CC-cc} -g -c conftest.c 2>&1`"; then + ac_cv_prog_cc_g=yes +else + ac_cv_prog_cc_g=no +fi +rm -f conftest* + +fi + +echo "$ac_t""$ac_cv_prog_cc_g" 1>&6 +if test "$ac_test_CFLAGS" = set; then + CFLAGS="$ac_save_CFLAGS" +elif test $ac_cv_prog_cc_g = yes; then + if test "$GCC" = yes; then + CFLAGS="-g -O2" + else + CFLAGS="-g" + fi +else + if test "$GCC" = yes; then + CFLAGS="-O2" + else + CFLAGS= + fi +fi + +# Extract the first word of "ranlib", so it can be a program name with args. +set dummy ranlib; ac_word=$2 +echo $ac_n "checking for $ac_word""... $ac_c" 1>&6 +echo "configure:768: checking for $ac_word" >&5 +if eval "test \"`echo '$''{'ac_cv_prog_RANLIB'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test -n "$RANLIB"; then + ac_cv_prog_RANLIB="$RANLIB" # Let the user override the test. +else + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" + ac_dummy="$PATH" + for ac_dir in $ac_dummy; do + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/$ac_word; then + ac_cv_prog_RANLIB="ranlib" + break + fi + done + IFS="$ac_save_ifs" + test -z "$ac_cv_prog_RANLIB" && ac_cv_prog_RANLIB=":" +fi +fi +RANLIB="$ac_cv_prog_RANLIB" +if test -n "$RANLIB"; then + echo "$ac_t""$RANLIB" 1>&6 +else + echo "$ac_t""no" 1>&6 +fi + + + +echo $ac_n "checking how to run the C preprocessor""... $ac_c" 1>&6 +echo "configure:798: checking how to run the C preprocessor" >&5 +# On Suns, sometimes $CPP names a directory. +if test -n "$CPP" && test -d "$CPP"; then + CPP= +fi +if test -z "$CPP"; then +if eval "test \"`echo '$''{'ac_cv_prog_CPP'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + # This must be in double quotes, not single quotes, because CPP may get + # substituted into the Makefile and "${CC-cc}" will confuse make. + CPP="${CC-cc} -E" + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. + cat > conftest.$ac_ext < +Syntax Error +EOF +ac_try="$ac_cpp conftest.$ac_ext >/dev/null 2>conftest.out" +{ (eval echo configure:819: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + : +else + echo "$ac_err" >&5 + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + CPP="${CC-cc} -E -traditional-cpp" + cat > conftest.$ac_ext < +Syntax Error +EOF +ac_try="$ac_cpp conftest.$ac_ext >/dev/null 2>conftest.out" +{ (eval echo configure:836: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + : +else + echo "$ac_err" >&5 + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + CPP="${CC-cc} -nologo -E" + cat > conftest.$ac_ext < +Syntax Error +EOF +ac_try="$ac_cpp conftest.$ac_ext >/dev/null 2>conftest.out" +{ (eval echo configure:853: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + : +else + echo "$ac_err" >&5 + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + CPP=/lib/cpp +fi +rm -f conftest* +fi +rm -f conftest* +fi +rm -f conftest* + ac_cv_prog_CPP="$CPP" +fi + CPP="$ac_cv_prog_CPP" +else + ac_cv_prog_CPP="$CPP" +fi +echo "$ac_t""$CPP" 1>&6 + +echo $ac_n "checking for ANSI C header files""... $ac_c" 1>&6 +echo "configure:878: checking for ANSI C header files" >&5 +if eval "test \"`echo '$''{'ac_cv_header_stdc'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +#include +#include +#include +EOF +ac_try="$ac_cpp conftest.$ac_ext >/dev/null 2>conftest.out" +{ (eval echo configure:891: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + rm -rf conftest* + ac_cv_header_stdc=yes +else + echo "$ac_err" >&5 + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + ac_cv_header_stdc=no +fi +rm -f conftest* + +if test $ac_cv_header_stdc = yes; then + # SunOS 4.x string.h does not declare mem*, contrary to ANSI. +cat > conftest.$ac_ext < +EOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + egrep "memchr" >/dev/null 2>&1; then + : +else + rm -rf conftest* + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. +cat > conftest.$ac_ext < +EOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + egrep "free" >/dev/null 2>&1; then + : +else + rm -rf conftest* + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. +if test "$cross_compiling" = yes; then + : +else + cat > conftest.$ac_ext < +#define ISLOWER(c) ('a' <= (c) && (c) <= 'z') +#define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) +#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) +int main () { int i; for (i = 0; i < 256; i++) +if (XOR (islower (i), ISLOWER (i)) || toupper (i) != TOUPPER (i)) exit(2); +exit (0); } + +EOF +if { (eval echo configure:958: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext} && (./conftest; exit) 2>/dev/null +then + : +else + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -fr conftest* + ac_cv_header_stdc=no +fi +rm -fr conftest* +fi + +fi +fi + +echo "$ac_t""$ac_cv_header_stdc" 1>&6 +if test $ac_cv_header_stdc = yes; then + cat >> confdefs.h <<\EOF +#define STDC_HEADERS 1 +EOF + +fi + +for ac_hdr in limits.h +do +ac_safe=`echo "$ac_hdr" | sed 'y%./+-%__p_%'` +echo $ac_n "checking for $ac_hdr""... $ac_c" 1>&6 +echo "configure:985: checking for $ac_hdr" >&5 +if eval "test \"`echo '$''{'ac_cv_header_$ac_safe'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +EOF +ac_try="$ac_cpp conftest.$ac_ext >/dev/null 2>conftest.out" +{ (eval echo configure:995: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + rm -rf conftest* + eval "ac_cv_header_$ac_safe=yes" +else + echo "$ac_err" >&5 + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_header_$ac_safe=no" +fi +rm -f conftest* +fi +if eval "test \"`echo '$ac_cv_header_'$ac_safe`\" = yes"; then + echo "$ac_t""yes" 1>&6 + ac_tr_hdr=HAVE_`echo $ac_hdr | sed 'y%abcdefghijklmnopqrstuvwxyz./-%ABCDEFGHIJKLMNOPQRSTUVWXYZ___%'` + cat >> confdefs.h <&6 +fi +done + + + +echo $ac_n "checking for working const""... $ac_c" 1>&6 +echo "configure:1024: checking for working const" >&5 +if eval "test \"`echo '$''{'ac_cv_c_const'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext <j = 5; +} +{ /* ULTRIX-32 V3.1 (Rev 9) vcc rejects this */ + const int foo = 10; +} + +; return 0; } +EOF +if { (eval echo configure:1078: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>&5; }; then + rm -rf conftest* + ac_cv_c_const=yes +else + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + ac_cv_c_const=no +fi +rm -f conftest* +fi + +echo "$ac_t""$ac_cv_c_const" 1>&6 +if test $ac_cv_c_const = no; then + cat >> confdefs.h <<\EOF +#define const +EOF + +fi + +echo $ac_n "checking for size_t""... $ac_c" 1>&6 +echo "configure:1099: checking for size_t" >&5 +if eval "test \"`echo '$''{'ac_cv_type_size_t'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +#if STDC_HEADERS +#include +#include +#endif +EOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + egrep "(^|[^a-zA-Z_0-9])size_t[^a-zA-Z_0-9]" >/dev/null 2>&1; then + rm -rf conftest* + ac_cv_type_size_t=yes +else + rm -rf conftest* + ac_cv_type_size_t=no +fi +rm -f conftest* + +fi +echo "$ac_t""$ac_cv_type_size_t" 1>&6 +if test $ac_cv_type_size_t = no; then + cat >> confdefs.h <<\EOF +#define size_t unsigned +EOF + +fi + + + +for ac_func in bcopy memmove strerror +do +echo $ac_n "checking for $ac_func""... $ac_c" 1>&6 +echo "configure:1136: checking for $ac_func" >&5 +if eval "test \"`echo '$''{'ac_cv_func_$ac_func'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +/* Override any gcc2 internal prototype to avoid an error. */ +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char $ac_func(); + +int main() { + +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_$ac_func) || defined (__stub___$ac_func) +choke me +#else +$ac_func(); +#endif + +; return 0; } +EOF +if { (eval echo configure:1164: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_func_$ac_func=yes" +else + echo "configure: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_func_$ac_func=no" +fi +rm -f conftest* +fi + +if eval "test \"`echo '$ac_cv_func_'$ac_func`\" = yes"; then + echo "$ac_t""yes" 1>&6 + ac_tr_func=HAVE_`echo $ac_func | tr 'abcdefghijklmnopqrstuvwxyz' 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'` + cat >> confdefs.h <&6 +fi +done + + + +LIBTOOL=./libtool +LIBSUFFIX=la +# Check whether --enable-shared or --disable-shared was given. +if test "${enable_shared+set}" = set; then + enableval="$enable_shared" + if test "$enableval" = "no"; then + LIBTOOL= + LIBSUFFIX=a +fi + +fi + + + +# Check whether --enable-utf8 or --disable-utf8 was given. +if test "${enable_utf8+set}" = set; then + enableval="$enable_utf8" + if test "$enableval" = "yes"; then + UTF8=-DSUPPORT_UTF8 +fi + +fi + + + + + + + + + + + + + + + +trap '' 1 2 15 +cat > confcache <<\EOF +# This file is a shell script that caches the results of configure +# tests run on this system so they can be shared between configure +# scripts and configure runs. It is not useful on other systems. +# If it contains results you don't want to keep, you may remove or edit it. +# +# By default, configure uses ./config.cache as the cache file, +# creating it if it does not exist already. You can give configure +# the --cache-file=FILE option to use a different cache file; that is +# what configure does when it calls configure scripts in +# subdirectories, so they share the cache. +# Giving --cache-file=/dev/null disables caching, for debugging configure. +# config.status only pays attention to the cache file if you give it the +# --recheck option to rerun configure. +# +EOF +# The following way of writing the cache mishandles newlines in values, +# but we know of no workaround that is simple, portable, and efficient. +# So, don't put newlines in cache variables' values. +# Ultrix sh set writes to stderr and can't be redirected directly, +# and sets the high bit in the cache file unless we assign to the vars. +(set) 2>&1 | + case `(ac_space=' '; set | grep ac_space) 2>&1` in + *ac_space=\ *) + # `set' does not quote correctly, so add quotes (double-quote substitution + # turns \\\\ into \\, and sed turns \\ into \). + sed -n \ + -e "s/'/'\\\\''/g" \ + -e "s/^\\([a-zA-Z0-9_]*_cv_[a-zA-Z0-9_]*\\)=\\(.*\\)/\\1=\${\\1='\\2'}/p" + ;; + *) + # `set' quotes correctly as required by POSIX, so do not add quotes. + sed -n -e 's/^\([a-zA-Z0-9_]*_cv_[a-zA-Z0-9_]*\)=\(.*\)/\1=${\1=\2}/p' + ;; + esac >> confcache +if cmp -s $cache_file confcache; then + : +else + if test -w $cache_file; then + echo "updating cache $cache_file" + cat confcache > $cache_file + else + echo "not updating unwritable cache $cache_file" + fi +fi +rm -f confcache + +trap 'rm -fr conftest* confdefs* core core.* *.core $ac_clean_files; exit 1' 1 2 15 + +test "x$prefix" = xNONE && prefix=$ac_default_prefix +# Let make expand exec_prefix. +test "x$exec_prefix" = xNONE && exec_prefix='${prefix}' + +# Any assignment to VPATH causes Sun make to only execute +# the first set of double-colon rules, so remove it if not needed. +# If there is a colon in the path, we need to keep it. +if test "x$srcdir" = x.; then + ac_vpsub='/^[ ]*VPATH[ ]*=[^:]*$/d' +fi + +trap 'rm -f $CONFIG_STATUS conftest*; exit 1' 1 2 15 + +DEFS=-DHAVE_CONFIG_H + +# Without the "./", some shells look in PATH for config.status. +: ${CONFIG_STATUS=./config.status} + +echo creating $CONFIG_STATUS +rm -f $CONFIG_STATUS +cat > $CONFIG_STATUS </dev/null | sed 1q`: +# +# $0 $ac_configure_args +# +# Compiler output produced by configure, useful for debugging +# configure, is in ./config.log if it exists. + +ac_cs_usage="Usage: $CONFIG_STATUS [--recheck] [--version] [--help]" +for ac_option +do + case "\$ac_option" in + -recheck | --recheck | --rechec | --reche | --rech | --rec | --re | --r) + echo "running \${CONFIG_SHELL-/bin/sh} $0 $ac_configure_args --no-create --no-recursion" + exec \${CONFIG_SHELL-/bin/sh} $0 $ac_configure_args --no-create --no-recursion ;; + -version | --version | --versio | --versi | --vers | --ver | --ve | --v) + echo "$CONFIG_STATUS generated by autoconf version 2.13" + exit 0 ;; + -help | --help | --hel | --he | --h) + echo "\$ac_cs_usage"; exit 0 ;; + *) echo "\$ac_cs_usage"; exit 1 ;; + esac +done + +ac_given_srcdir=$srcdir + +trap 'rm -fr `echo "Makefile pcre.h:pcre.in pcre-config:pcre-config.in RunTest:RunTest.in config.h:config.in" | sed "s/:[^ ]*//g"` conftest*; exit 1' 1 2 15 +EOF +cat >> $CONFIG_STATUS < conftest.subs <<\\CEOF +$ac_vpsub +$extrasub +s%@SHELL@%$SHELL%g +s%@CFLAGS@%$CFLAGS%g +s%@CPPFLAGS@%$CPPFLAGS%g +s%@CXXFLAGS@%$CXXFLAGS%g +s%@FFLAGS@%$FFLAGS%g +s%@DEFS@%$DEFS%g +s%@LDFLAGS@%$LDFLAGS%g +s%@LIBS@%$LIBS%g +s%@exec_prefix@%$exec_prefix%g +s%@prefix@%$prefix%g +s%@program_transform_name@%$program_transform_name%g +s%@bindir@%$bindir%g +s%@sbindir@%$sbindir%g +s%@libexecdir@%$libexecdir%g +s%@datadir@%$datadir%g +s%@sysconfdir@%$sysconfdir%g +s%@sharedstatedir@%$sharedstatedir%g +s%@localstatedir@%$localstatedir%g +s%@libdir@%$libdir%g +s%@includedir@%$includedir%g +s%@oldincludedir@%$oldincludedir%g +s%@infodir@%$infodir%g +s%@mandir@%$mandir%g +s%@CC@%$CC%g +s%@RANLIB@%$RANLIB%g +s%@CPP@%$CPP%g +s%@HAVE_MEMMOVE@%$HAVE_MEMMOVE%g +s%@HAVE_STRERROR@%$HAVE_STRERROR%g +s%@LIBTOOL@%$LIBTOOL%g +s%@LIBSUFFIX@%$LIBSUFFIX%g +s%@UTF8@%$UTF8%g +s%@PCRE_MAJOR@%$PCRE_MAJOR%g +s%@PCRE_MINOR@%$PCRE_MINOR%g +s%@PCRE_DATE@%$PCRE_DATE%g +s%@PCRE_VERSION@%$PCRE_VERSION%g +s%@PCRE_LIB_VERSION@%$PCRE_LIB_VERSION%g +s%@PCRE_POSIXLIB_VERSION@%$PCRE_POSIXLIB_VERSION%g + +CEOF +EOF + +cat >> $CONFIG_STATUS <<\EOF + +# Split the substitutions into bite-sized pieces for seds with +# small command number limits, like on Digital OSF/1 and HP-UX. +ac_max_sed_cmds=90 # Maximum number of lines to put in a sed script. +ac_file=1 # Number of current file. +ac_beg=1 # First line for current file. +ac_end=$ac_max_sed_cmds # Line after last line for current file. +ac_more_lines=: +ac_sed_cmds="" +while $ac_more_lines; do + if test $ac_beg -gt 1; then + sed "1,${ac_beg}d; ${ac_end}q" conftest.subs > conftest.s$ac_file + else + sed "${ac_end}q" conftest.subs > conftest.s$ac_file + fi + if test ! -s conftest.s$ac_file; then + ac_more_lines=false + rm -f conftest.s$ac_file + else + if test -z "$ac_sed_cmds"; then + ac_sed_cmds="sed -f conftest.s$ac_file" + else + ac_sed_cmds="$ac_sed_cmds | sed -f conftest.s$ac_file" + fi + ac_file=`expr $ac_file + 1` + ac_beg=$ac_end + ac_end=`expr $ac_end + $ac_max_sed_cmds` + fi +done +if test -z "$ac_sed_cmds"; then + ac_sed_cmds=cat +fi +EOF + +cat >> $CONFIG_STATUS <> $CONFIG_STATUS <<\EOF +for ac_file in .. $CONFIG_FILES; do if test "x$ac_file" != x..; then + # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". + case "$ac_file" in + *:*) ac_file_in=`echo "$ac_file"|sed 's%[^:]*:%%'` + ac_file=`echo "$ac_file"|sed 's%:.*%%'` ;; + *) ac_file_in="${ac_file}.in" ;; + esac + + # Adjust a relative srcdir, top_srcdir, and INSTALL for subdirectories. + + # Remove last slash and all that follows it. Not all systems have dirname. + ac_dir=`echo $ac_file|sed 's%/[^/][^/]*$%%'` + if test "$ac_dir" != "$ac_file" && test "$ac_dir" != .; then + # The file is in a subdirectory. + test ! -d "$ac_dir" && mkdir "$ac_dir" + ac_dir_suffix="/`echo $ac_dir|sed 's%^\./%%'`" + # A "../" for each directory in $ac_dir_suffix. + ac_dots=`echo $ac_dir_suffix|sed 's%/[^/]*%../%g'` + else + ac_dir_suffix= ac_dots= + fi + + case "$ac_given_srcdir" in + .) srcdir=. + if test -z "$ac_dots"; then top_srcdir=. + else top_srcdir=`echo $ac_dots|sed 's%/$%%'`; fi ;; + /*) srcdir="$ac_given_srcdir$ac_dir_suffix"; top_srcdir="$ac_given_srcdir" ;; + *) # Relative path. + srcdir="$ac_dots$ac_given_srcdir$ac_dir_suffix" + top_srcdir="$ac_dots$ac_given_srcdir" ;; + esac + + + echo creating "$ac_file" + rm -f "$ac_file" + configure_input="Generated automatically from `echo $ac_file_in|sed 's%.*/%%'` by configure." + case "$ac_file" in + *Makefile*) ac_comsub="1i\\ +# $configure_input" ;; + *) ac_comsub= ;; + esac + + ac_file_inputs=`echo $ac_file_in|sed -e "s%^%$ac_given_srcdir/%" -e "s%:% $ac_given_srcdir/%g"` + sed -e "$ac_comsub +s%@configure_input@%$configure_input%g +s%@srcdir@%$srcdir%g +s%@top_srcdir@%$top_srcdir%g +" $ac_file_inputs | (eval "$ac_sed_cmds") > $ac_file +fi; done +rm -f conftest.s* + +# These sed commands are passed to sed as "A NAME B NAME C VALUE D", where +# NAME is the cpp macro being defined and VALUE is the value it is being given. +# +# ac_d sets the value in "#define NAME VALUE" lines. +ac_dA='s%^\([ ]*\)#\([ ]*define[ ][ ]*\)' +ac_dB='\([ ][ ]*\)[^ ]*%\1#\2' +ac_dC='\3' +ac_dD='%g' +# ac_u turns "#undef NAME" with trailing blanks into "#define NAME VALUE". +ac_uA='s%^\([ ]*\)#\([ ]*\)undef\([ ][ ]*\)' +ac_uB='\([ ]\)%\1#\2define\3' +ac_uC=' ' +ac_uD='\4%g' +# ac_e turns "#undef NAME" without trailing blanks into "#define NAME VALUE". +ac_eA='s%^\([ ]*\)#\([ ]*\)undef\([ ][ ]*\)' +ac_eB='$%\1#\2define\3' +ac_eC=' ' +ac_eD='%g' + +if test "${CONFIG_HEADERS+set}" != set; then +EOF +cat >> $CONFIG_STATUS <> $CONFIG_STATUS <<\EOF +fi +for ac_file in .. $CONFIG_HEADERS; do if test "x$ac_file" != x..; then + # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". + case "$ac_file" in + *:*) ac_file_in=`echo "$ac_file"|sed 's%[^:]*:%%'` + ac_file=`echo "$ac_file"|sed 's%:.*%%'` ;; + *) ac_file_in="${ac_file}.in" ;; + esac + + echo creating $ac_file + + rm -f conftest.frag conftest.in conftest.out + ac_file_inputs=`echo $ac_file_in|sed -e "s%^%$ac_given_srcdir/%" -e "s%:% $ac_given_srcdir/%g"` + cat $ac_file_inputs > conftest.in + +EOF + +# Transform confdefs.h into a sed script conftest.vals that substitutes +# the proper values into config.h.in to produce config.h. And first: +# Protect against being on the right side of a sed subst in config.status. +# Protect against being in an unquoted here document in config.status. +rm -f conftest.vals +cat > conftest.hdr <<\EOF +s/[\\&%]/\\&/g +s%[\\$`]%\\&%g +s%#define \([A-Za-z_][A-Za-z0-9_]*\) *\(.*\)%${ac_dA}\1${ac_dB}\1${ac_dC}\2${ac_dD}%gp +s%ac_d%ac_u%gp +s%ac_u%ac_e%gp +EOF +sed -n -f conftest.hdr confdefs.h > conftest.vals +rm -f conftest.hdr + +# This sed command replaces #undef with comments. This is necessary, for +# example, in the case of _POSIX_SOURCE, which is predefined and required +# on some systems where configure will not decide to define it. +cat >> conftest.vals <<\EOF +s%^[ ]*#[ ]*undef[ ][ ]*[a-zA-Z_][a-zA-Z_0-9]*%/* & */% +EOF + +# Break up conftest.vals because some shells have a limit on +# the size of here documents, and old seds have small limits too. + +rm -f conftest.tail +while : +do + ac_lines=`grep -c . conftest.vals` + # grep -c gives empty output for an empty file on some AIX systems. + if test -z "$ac_lines" || test "$ac_lines" -eq 0; then break; fi + # Write a limited-size here document to conftest.frag. + echo ' cat > conftest.frag <> $CONFIG_STATUS + sed ${ac_max_here_lines}q conftest.vals >> $CONFIG_STATUS + echo 'CEOF + sed -f conftest.frag conftest.in > conftest.out + rm -f conftest.in + mv conftest.out conftest.in +' >> $CONFIG_STATUS + sed 1,${ac_max_here_lines}d conftest.vals > conftest.tail + rm -f conftest.vals + mv conftest.tail conftest.vals +done +rm -f conftest.vals + +cat >> $CONFIG_STATUS <<\EOF + rm -f conftest.frag conftest.h + echo "/* $ac_file. Generated automatically by configure. */" > conftest.h + cat conftest.in >> conftest.h + rm -f conftest.in + if cmp -s $ac_file conftest.h 2>/dev/null; then + echo "$ac_file is unchanged" + rm -f conftest.h + else + # Remove last slash and all that follows it. Not all systems have dirname. + ac_dir=`echo $ac_file|sed 's%/[^/][^/]*$%%'` + if test "$ac_dir" != "$ac_file" && test "$ac_dir" != .; then + # The file is in a subdirectory. + test ! -d "$ac_dir" && mkdir "$ac_dir" + fi + rm -f $ac_file + mv conftest.h $ac_file + fi +fi; done + +EOF +cat >> $CONFIG_STATUS <> $CONFIG_STATUS <<\EOF +chmod a+x RunTest pcre-config +exit 0 +EOF +chmod +x $CONFIG_STATUS +rm -fr confdefs* $ac_clean_files +test "$no_create" = yes || ${CONFIG_SHELL-/bin/sh} $CONFIG_STATUS || exit 1 + diff --git a/pcre/configure.in b/pcre/configure.in new file mode 100644 index 00000000..c98387d2 --- /dev/null +++ b/pcre/configure.in @@ -0,0 +1,85 @@ +dnl Process this file with autoconf to produce a configure script. + +dnl This is required at the start; the name is the name of a file +dnl it should be seeing, to verify it is in the same directory. + +AC_INIT(dftables.c) + +dnl Arrange to build config.h from config.in. Note that pcre.h is +dnl built differently, as it is just a "substitution" file. +dnl Manual says this macro should come right after AC_INIT. +AC_CONFIG_HEADER(config.h:config.in) + +dnl Provide the current PCRE version information. Do not use numbers +dnl with leading zeros for the minor version, as they end up in a C +dnl macro, and may be treated as octal constants. Stick to single +dnl digits for minor numbers less than 10. There are unlikely to be +dnl that many releases anyway. + +PCRE_MAJOR=3 +PCRE_MINOR=4 +PCRE_DATE=22-Aug-2000 +PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR} + +dnl Provide versioning information for libtool shared libraries that +dnl are built by default on Unix systems. + +PCRE_LIB_VERSION=0:1:0 +PCRE_POSIXLIB_VERSION=0:0:0 + +dnl Checks for programs. + +AC_PROG_CC +AC_PROG_RANLIB + +dnl Checks for header files. + +AC_HEADER_STDC +AC_CHECK_HEADERS(limits.h) + +dnl Checks for typedefs, structures, and compiler characteristics. + +AC_C_CONST +AC_TYPE_SIZE_T + +dnl Checks for library functions. + +AC_CHECK_FUNCS(bcopy memmove strerror) + +dnl Handle --enable-shared-libraries + +LIBTOOL=./libtool +LIBSUFFIX=la +AC_ARG_ENABLE(shared, +[ --disable-shared build PCRE as a static library], +if test "$enableval" = "no"; then + LIBTOOL= + LIBSUFFIX=a +fi +) + +dnl Handle --enable-utf8 + +AC_ARG_ENABLE(utf8, +[ --enable-utf8 enable UTF8 support (incomplete)], +if test "$enableval" = "yes"; then + UTF8=-DSUPPORT_UTF8 +fi +) + +dnl "Export" these variables + +AC_SUBST(HAVE_MEMMOVE) +AC_SUBST(HAVE_STRERROR) +AC_SUBST(LIBTOOL) +AC_SUBST(LIBSUFFIX) +AC_SUBST(UTF8) +AC_SUBST(PCRE_MAJOR) +AC_SUBST(PCRE_MINOR) +AC_SUBST(PCRE_DATE) +AC_SUBST(PCRE_VERSION) +AC_SUBST(PCRE_LIB_VERSION) +AC_SUBST(PCRE_POSIXLIB_VERSION) + +dnl This must be last; it determines what files are written +AC_OUTPUT(Makefile pcre.h:pcre.in pcre-config:pcre-config.in RunTest:RunTest.in,[chmod a+x RunTest pcre-config]) diff --git a/pcre/dftables.c b/pcre/dftables.c new file mode 100644 index 00000000..d572dfd3 --- /dev/null +++ b/pcre/dftables.c @@ -0,0 +1,148 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Written by: Philip Hazel + + Copyright (c) 1997-2000 University of Cambridge + +----------------------------------------------------------------------------- +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. +----------------------------------------------------------------------------- + +See the file Tech.Notes for some information on the internals. +*/ + + +/* This is a support program to generate the file chartables.c, containing +character tables of various kinds. They are built according to the default C +locale and used as the default tables by PCRE. Now that pcre_maketables is +a function visible to the outside world, we make use of its code from here in +order to be consistent. */ + +#include +#include +#include + +#include "internal.h" + +#define DFTABLES /* maketables.c notices this */ +#include "maketables.c" + + +int main(void) +{ +int i; +unsigned const char *tables = pcre_maketables(); + +printf( + "/*************************************************\n" + "* Perl-Compatible Regular Expressions *\n" + "*************************************************/\n\n" + "/* This file is automatically written by the dftables auxiliary \n" + "program. If you edit it by hand, you might like to edit the Makefile to \n" + "prevent its ever being regenerated.\n\n" + "This file is #included in the compilation of pcre.c to build the default\n" + "character tables which are used when no tables are passed to the compile\n" + "function. */\n\n" + "static unsigned char pcre_default_tables[] = {\n\n" + "/* This table is a lower casing table. */\n\n"); + +printf(" "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) printf("\n "); + printf("%3d", *tables++); + if (i != 255) printf(","); + } +printf(",\n\n"); + +printf("/* This table is a case flipping table. */\n\n"); + +printf(" "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) printf("\n "); + printf("%3d", *tables++); + if (i != 255) printf(","); + } +printf(",\n\n"); + +printf( + "/* This table contains bit maps for various character classes.\n" + "Each map is 32 bytes long and the bits run from the least\n" + "significant end of each byte. The classes that have their own\n" + "maps are: space, xdigit, digit, upper, lower, word, graph\n" + "print, punct, and cntrl. Other classes are built from combinations. */\n\n"); + +printf(" "); +for (i = 0; i < cbit_length; i++) + { + if ((i & 7) == 0 && i != 0) + { + if ((i & 31) == 0) printf("\n"); + printf("\n "); + } + printf("0x%02x", *tables++); + if (i != cbit_length - 1) printf(","); + } +printf(",\n\n"); + +printf( + "/* This table identifies various classes of character by individual bits:\n" + " 0x%02x white space character\n" + " 0x%02x letter\n" + " 0x%02x decimal digit\n" + " 0x%02x hexadecimal digit\n" + " 0x%02x alphanumeric or '_'\n" + " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", + ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, + ctype_meta); + +printf(" "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) + { + printf(" /* "); + if (isprint(i-8)) printf(" %c -", i-8); + else printf("%3d-", i-8); + if (isprint(i-1)) printf(" %c ", i-1); + else printf("%3d", i-1); + printf(" */\n "); + } + printf("0x%02x", *tables++); + if (i != 255) printf(","); + } + +printf("};/* "); +if (isprint(i-8)) printf(" %c -", i-8); + else printf("%3d-", i-8); +if (isprint(i-1)) printf(" %c ", i-1); + else printf("%3d", i-1); +printf(" */\n\n/* End of chartables.c */\n"); + +return 0; +} + +/* End of dftables.c */ diff --git a/pcre/dll.mk b/pcre/dll.mk new file mode 100644 index 00000000..d8b728e5 --- /dev/null +++ b/pcre/dll.mk @@ -0,0 +1,60 @@ +# dll.mk - auxilary Makefile to easy build dll's for mingw32 target +# ver. 0.6 of 1999-03-25 +# +# Homepage of this makefile - http://www.is.lg.ua/~paul/devel/ +# Homepage of original mingw32 project - +# http://www.fu.is.saga-u.ac.jp/~colin/gcc.html +# +# How to use: +# This makefile can: +# 1. Create automatical .def file from list of objects +# 2. Create .dll from objects and .def file, either automatical, or your +# hand-written (maybe) file, which must have same basename as dll +# WARNING! There MUST be object, which name match dll's name. Make sux. +# 3. Create import library from .def (as for .dll, only its name required, +# not dll itself) +# By convention implibs for dll have .dll.a suffix, e.g. libstuff.dll.a +# Why not just libstuff.a? 'Cos that's name for static lib, ok? +# Process divided into 3 phases because: +# 1. Pre-existent .def possible +# 2. Generating implib is enough time-consuming +# +# Variables: +# DLL_LDLIBS - libs for linking dll +# DLL_LDFLAGS - flags for linking dll +# +# By using $(DLL_SUFFIX) instead of 'dll', e.g. stuff.$(DLL_SUFFIX) +# you may help porting makefiles to other platforms +# +# Put this file in your make's include path (e.g. main include dir, for +# more information see include section in make doc). Put in the beginning +# of your own Makefile line "include dll.mk". Specify dependences, e.g.: +# +# Do all stuff in one step +# libstuff.dll.a: $(OBJECTS) stuff.def +# stuff.def: $(OBJECTS) +# +# Steps separated, pre-provided .def, link with user32 +# +# DLL_LDLIBS=-luser32 +# stuff.dll: $(OBJECTS) +# libstuff.dll.a: $(OBJECTS) + + +DLLWRAP=dllwrap +DLLTOOL=dlltool + +DLL_SUFFIX=dll + +.SUFFIXES: .o .$(DLL_SUFFIX) + +_%.def: %.o + $(DLLTOOL) --export-all --output-def $@ $^ + +%.$(DLL_SUFFIX): %.o + $(DLLWRAP) --dllname $(notdir $@) --driver-name $(CC) --def $*.def -o $@ $(filter %.o,$^) $(DLL_LDFLAGS) $(DLL_LDLIBS) + +lib%.$(DLL_SUFFIX).a:%.def + $(DLLTOOL) --dllname $(notdir $*.dll) --def $< --output-lib $@ + +# End diff --git a/pcre/doc/ChangeLog b/pcre/doc/ChangeLog new file mode 100644 index 00000000..2133dd76 --- /dev/null +++ b/pcre/doc/ChangeLog @@ -0,0 +1,655 @@ +ChangeLog for PCRE +------------------ + + +Version 3.4 22-Aug-00 +--------------------- + +1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. + +2. Diagnose condition (?(0) as an error instead of crashing on matching. + + +Version 3.3 01-Aug-00 +--------------------- + +1. If an octal character was given, but the value was greater than \377, it +was not getting masked to the least significant bits, as documented. This could +lead to crashes in some systems. + +2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats +the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. + +3. Added the functions pcre_free_substring() and pcre_free_substring_list(). +These just pass their arguments on to (pcre_free)(), but they are provided +because some uses of PCRE bind it to non-C systems that can call its functions, +but cannot call free() or pcre_free() directly. + +4. Add "make test" as a synonym for "make check". Corrected some comments in +the Makefile. + +5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the +Makefile. + +6. Changed the name of pgrep to pcregrep, because Solaris has introduced a +command called pgrep for grepping around the active processes. + +7. Added the beginnings of support for UTF-8 character strings. + +8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and +RANLIB to ./ltconfig so that they are used by libtool. I think these are all +the relevant ones. (AR is not passed because ./ltconfig does its own figuring +out for the ar command.) + + +Version 3.2 12-May-00 +--------------------- + +This is purely a bug fixing release. + +1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead +of ZA. This was just one example of several cases that could provoke this bug, +which was introduced by change 9 of version 2.00. The code for breaking +infinite loops after an iteration that matches an empty string was't working +correctly. + +2. The pcretest program was not imitating Perl correctly for the pattern /a*/g +when matched against abbab (for example). After matching an empty string, it +wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this +caused it to match further down the string than it should. + +3. The code contained an inclusion of sys/types.h. It isn't clear why this +was there because it doesn't seem to be needed, and it causes trouble on some +systems, as it is not a Standard C header. It has been removed. + +4. Made 4 silly changes to the source to avoid stupid compiler warnings that +were reported on the Macintosh. The changes were from + + while ((c = *(++ptr)) != 0 && c != '\n'); +to + while ((c = *(++ptr)) != 0 && c != '\n') ; + +Totally extraordinary, but if that's what it takes... + +5. PCRE is being used in one environment where neither memmove() nor bcopy() is +available. Added HAVE_BCOPY and an autoconf test for it; if neither +HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which +assumes the way PCRE uses memmove() (always moving upwards). + +6. PCRE is being used in one environment where strchr() is not available. There +was only one use in pcre.c, and writing it out to avoid strchr() probably gives +faster code anyway. + + +Version 3.1 09-Feb-00 +--------------------- + +The only change in this release is the fixing of some bugs in Makefile.in for +the "install" target: + +(1) It was failing to install pcreposix.h. + +(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. + + +Version 3.0 01-Feb-00 +--------------------- + +1. Add support for the /+ modifier to perltest (to output $` like it does in +pcretest). + +2. Add support for the /g modifier to perltest. + +3. Fix pcretest so that it behaves even more like Perl for /g when the pattern +matches null strings. + +4. Fix perltest so that it doesn't do unwanted things when fed an empty +pattern. Perl treats empty patterns specially - it reuses the most recent +pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this +effect. + +5. The POSIX interface was broken in that it was just handing over the POSIX +captured string vector to pcre_exec(), but (since release 2.00) PCRE has +required a bigger vector, with some working space on the end. This means that +the POSIX wrapper now has to get and free some memory, and copy the results. + +6. Added some simple autoconf support, placing the test data and the +documentation in separate directories, re-organizing some of the +information files, and making it build pcre-config (a GNU standard). Also added +libtool support for building PCRE as a shared library, which is now the +default. + +7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and +09 are not valid octal constants. Single digits will be used for minor values +less than 10. + +8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that +existing programs that set these in the POSIX interface can use PCRE without +modification. + +9. Added a new function, pcre_fullinfo() with an extensible interface. It can +return all that pcre_info() returns, plus additional data. The pcre_info() +function is retained for compatibility, but is considered to be obsolete. + +10. Added experimental recursion feature (?R) to handle one common case that +Perl 5.6 will be able to do with (?p{...}). + +11. Added support for POSIX character classes like [:alpha:], which Perl is +adopting. + + +Version 2.08 31-Aug-99 +---------------------- + +1. When startoffset was not zero and the pattern began with ".*", PCRE was not +trying to match at the startoffset position, but instead was moving forward to +the next newline as if a previous match had failed. + +2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, +and could get into a loop if a null string was matched other than at the start +of the subject. + +3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can +be distinguished at compile time, and for completeness also added PCRE_DATE. + +5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL +in GnuWin32 environments. + + +Version 2.07 29-Jul-99 +---------------------- + +1. The documentation is now supplied in plain text form and HTML as well as in +the form of man page sources. + +2. C++ compilers don't like assigning (void *) values to other pointer types. +In particular this affects malloc(). Although there is no problem in Standard +C, I've put in casts to keep C++ compilers happy. + +3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call +should be (const char *). + +4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may +be useful for non-Unix systems who don't want to bother with the POSIX stuff. +However, I haven't made this a standard facility. The documentation doesn't +mention it, and the Makefile doesn't support it. + +5. The Makefile now contains an "install" target, with editable destinations at +the top of the file. The pcretest program is not installed. + +6. pgrep -V now gives the PCRE version number and date. + +7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was +causing the entire string to be ignored, instead of just the last character. + +8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a +non-matching string, it can take a very, very long time, even for strings of +quite modest length, because of the nested recursion. PCRE now does better in +some of these cases. It does this by remembering the last required literal +character in the pattern, and pre-searching the subject to ensure it is present +before running the real match. In other words, it applies a heuristic to detect +some types of certain failure quickly, and in the above example, if presented +with a string that has no trailing " it gives "no match" very quickly. + +9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; +other alternatives are tried instead. + + +Version 2.06 09-Jun-99 +---------------------- + +1. Change pcretest's output for amount of store used to show just the code +space, because the remainder (the data block) varies in size between 32-bit and +64-bit systems. + +2. Added an extra argument to pcre_exec() to supply an offset in the subject to +start matching at. This allows lookbehinds to work when searching for multiple +occurrences in a string. + +3. Added additional options to pcretest for testing multiple occurrences: + + /+ outputs the rest of the string that follows a match + /g loops for multiple occurrences, using the new startoffset argument + /G loops for multiple occurrences by passing an incremented pointer + +4. PCRE wasn't doing the "first character" optimization for patterns starting +with \b or \B, though it was doing it for other lookbehind assertions. That is, +it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with +the letter 'x'. On long subject strings, this gives a significant speed-up. + + +Version 2.05 21-Apr-99 +---------------------- + +1. Changed the type of magic_number from int to long int so that it works +properly on 16-bit systems. + +2. Fixed a bug which caused patterns starting with .* not to work correctly +when the subject string contained newline characters. PCRE was assuming +anchoring for such patterns in all cases, which is not correct because .* will +not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if +DOTALL is set at top level; otherwise it knows that patterns starting with .* +must be retried after every newline in the subject. + + +Version 2.04 18-Feb-99 +---------------------- + +1. For parenthesized subpatterns with repeats whose minimum was zero, the +computation of the store needed to hold the pattern was incorrect (too large). +If such patterns were nested a few deep, this could multiply and become a real +problem. + +2. Added /M option to pcretest to show the memory requirement of a specific +pattern. Made -m a synonym of -s (which does this globally) for compatibility. + +3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being +compiled in such a way that the backtracking after subsequent failure was +pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of +((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. + + +Version 2.03 02-Feb-99 +---------------------- + +1. Fixed typo and small mistake in man page. + +2. Added 4th condition (GPL supersedes if conflict) and created separate +LICENCE file containing the conditions. + +3. Updated pcretest so that patterns such as /abc\/def/ work like they do in +Perl, that is the internal \ allows the delimiter to be included in the +pattern. Locked out the use of \ as a delimiter. If \ immediately follows +the final delimiter, add \ to the end of the pattern (to test the error). + +4. Added the convenience functions for extracting substrings after a successful +match. Updated pcretest to make it able to test these functions. + + +Version 2.02 14-Jan-99 +---------------------- + +1. Initialized the working variables associated with each extraction so that +their saving and restoring doesn't refer to uninitialized store. + +2. Put dummy code into study.c in order to trick the optimizer of the IBM C +compiler for OS/2 into generating correct code. Apparently IBM isn't going to +fix the problem. + +3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution +calls, and wasn't printing the correct value for compiling calls. Increased the +default value of LOOPREPEAT, and the number of significant figures in the +times. + +4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. + +5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid +a building problem on Windows NT with a FAT file system. + + +Version 2.01 21-Oct-98 +---------------------- + +1. Changed the API for pcre_compile() to allow for the provision of a pointer +to character tables built by pcre_maketables() in the current locale. If NULL +is passed, the default tables are used. + + +Version 2.00 24-Sep-98 +---------------------- + +1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable +it any more. + +2. Allow quantification of (?>) groups, and make it work correctly. + +3. The first character computation wasn't working for (?>) groups. + +4. Correct the implementation of \Z (it is permitted to match on the \n at the +end of the subject) and add 5.005's \z, which really does match only at the +very end of the subject. + +5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. + +6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and +DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 +localized options. All options to pcre_study() were also removed. + +7. Add other new features from 5.005: + + $(?<= positive lookbehind + $(?a*))*/ (a PCRE_EXTRA facility). + + +Version 1.00 18-Nov-97 +---------------------- + +1. Added compile-time macros to support systems such as SunOS4 which don't have +memmove() or strerror() but have other things that can be used instead. + +2. Arranged that "make clean" removes the executables. + + +Version 0.99 27-Oct-97 +---------------------- + +1. Fixed bug in code for optimizing classes with only one character. It was +initializing a 32-byte map regardless, which could cause it to run off the end +of the memory it had got. + +2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. + + +Version 0.98 22-Oct-97 +---------------------- + +1. Fixed bug in code for handling temporary memory usage when there are more +back references than supplied space in the ovector. This could cause segfaults. + + +Version 0.97 21-Oct-97 +---------------------- + +1. Added the \X "cut" facility, conditional on PCRE_EXTRA. + +2. Optimized negated single characters not to use a bit map. + +3. Brought error texts together as macro definitions; clarified some of them; +fixed one that was wrong - it said "range out of order" when it meant "invalid +escape sequence". + +4. Changed some char * arguments to const char *. + +5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). + +6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in +pcretest. + + +Version 0.96 16-Oct-97 +---------------------- + +1. Added a simple "pgrep" utility to the distribution. + +2. Fixed an incompatibility with Perl: "{" is now treated as a normal character +unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" +where "ddd" means "one or more decimal digits". + +3. Fixed serious bug. If a pattern had a back reference, but the call to +pcre_exec() didn't supply a large enough ovector to record the related +identifying subpattern, the match always failed. PCRE now remembers the number +of the largest back reference, and gets some temporary memory in which to save +the offsets during matching if necessary, in order to ensure that +backreferences always work. + +4. Increased the compatibility with Perl in a number of ways: + + (a) . no longer matches \n by default; an option PCRE_DOTALL is provided + to request this handling. The option can be set at compile or exec time. + + (b) $ matches before a terminating newline by default; an option + PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline + mode). The option can be set at compile or exec time. + + (c) The handling of \ followed by a digit other than 0 is now supposed to be + the same as Perl's. If the decimal number it represents is less than 10 + or there aren't that many previous left capturing parentheses, an octal + escape is read. Inside a character class, it's always an octal escape, + even if it is a single digit. + + (d) An escaped but undefined alphabetic character is taken as a literal, + unless PCRE_EXTRA is set. Currently this just reserves the remaining + escapes. + + (e) {0} is now permitted. (The previous item is removed from the compiled + pattern). + +5. Changed all the names of code files so that the basic parts are no longer +than 10 characters, and abolished the teeny "globals.c" file. + +6. Changed the handling of character classes; they are now done with a 32-byte +bit map always. + +7. Added the -d and /D options to pcretest to make it possible to look at the +internals of compilation without having to recompile pcre. + + +Version 0.95 23-Sep-97 +---------------------- + +1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or +\x20 at the start of a run of normal characters. These were being treated as +real characters, instead of the source characters being re-checked. + + +Version 0.94 18-Sep-97 +---------------------- + +1. The functions are now thread-safe, with the caveat that the global variables +containing pointers to malloc() and free() or alternative functions are the +same for all threads. + +2. Get pcre_study() to generate a bitmap of initial characters for non- +anchored patterns when this is possible, and use it if passed to pcre_exec(). + + +Version 0.93 15-Sep-97 +---------------------- + +1. /(b)|(:+)/ was computing an incorrect first character. + +2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), +but not actually doing anything yet. + +3. Treat "-" characters in classes that cannot be part of ranges as literals, +as Perl does (e.g. [-az] or [az-]). + +4. Set the anchored flag if a branch starts with .* or .*? because that tests +all possible positions. + +5. Split up into different modules to avoid including unneeded functions in a +compiled binary. However, compile and exec are still in one module. The "study" +function is split off. + +6. The character tables are now in a separate module whose source is generated +by an auxiliary program - but can then be edited by hand if required. There are +now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or +toupper() in the code. + +7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and +make them global. Abolish the function for setting them, as the caller can now +set them directly. + + +Version 0.92 11-Sep-97 +---------------------- + +1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character +(e.g. /a{1,3}/) was broken (I mis-optimized it). + +2. Caseless matching was not working in character classes if the characters in +the pattern were in upper case. + +3. Make ranges like [W-c] work in the same way as Perl for caseless matching. + +4. Make PCRE_ANCHORED public and accept as a compile option. + +5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and +PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to +pass them. + +6. Give an error if bad option bits passed at compile or run time. + +7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to +pcretest to cause it to pass that flag. + +8. Add pcre_info(), to get the number of identifying subpatterns, the stored +options, and the first character, if set. + +9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. + + +Version 0.91 10-Sep-97 +---------------------- + +1. PCRE was failing to diagnose unlimited repeats of subpatterns that could +match the empty string as in /(a*)*/. It was looping and ultimately crashing. + +2. PCRE was looping on encountering an indefinitely repeated back reference to +a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what +Perl does - treats the match as successful. + +**** diff --git a/pcre/doc/NON-UNIX-USE b/pcre/doc/NON-UNIX-USE new file mode 100644 index 00000000..09a74324 --- /dev/null +++ b/pcre/doc/NON-UNIX-USE @@ -0,0 +1,50 @@ +Compiling PCRE on non-Unix systems +---------------------------------- + +If you want to compile PCRE for a non-Unix system, note that it consists +entirely of code written in Standard C, and so should compile successfully +on any machine with a Standard C compiler and library, using normal compiling +commands to do the following: + +(1) Copy or rename the file config.in as config.h, and change the macros that +define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. +Unfortunately, because of the way Unix autoconf works, the default setting has +to be 0. + +(2) Copy or rename the file pcre.in as pcre.h, and change the macro definitions +for PCRE_MAJOR, PCRE_MINOR, and PCRE_DATE near its start to the values set in +configure.in. + +(3) Compile dftables.c as a stand-alone program, and then run it with +the standard output sent to chartables.c. This generates a set of standard +character tables. + +(4) Compile maketables.c, get.c, study.c and pcre.c and link them all +together into an object library in whichever form your system keeps such +libraries. This is the pcre library (chartables.c gets included by means of an +#include directive). + +(5) Similarly, compile pcreposix.c and link it as the pcreposix library. + +(6) Compile the test program pcretest.c. This needs the functions in the +pcre and pcreposix libraries when linking. + +(7) Run pcretest on the testinput files in the testdata directory, and check +that the output matches the corresponding testoutput files. You must use the +-i option when checking testinput2. + +If you have a system without "configure" but where you can use a Makefile, edit +Makefile.in to create Makefile, substituting suitable values for the variables +at the head of the file. + +Some help in building a Win32 DLL of PCRE in GnuWin32 environments was +contributed by Paul.Sokolovsky@technologist.com. These environments are +Mingw32 (http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and +CygWin (http://sourceware.cygnus.com/cygwin/). Paul comments: + + For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get + pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically + linked pgrep and pcretest. If you have /bin/sh, run RunTest (three + main test go ok, locale not supported). + +**** diff --git a/pcre/doc/Tech.Notes b/pcre/doc/Tech.Notes new file mode 100644 index 00000000..7b96e5b6 --- /dev/null +++ b/pcre/doc/Tech.Notes @@ -0,0 +1,243 @@ +Technical Notes about PCRE +-------------------------- + +Many years ago I implemented some regular expression functions to an algorithm +suggested by Martin Richards. These were not Unix-like in form, and were quite +restricted in what they could do by comparison with Perl. The interesting part +about the algorithm was that the amount of space required to hold the compiled +form of an expression was known in advance. The code to apply an expression did +not operate by backtracking, as the Henry Spencer and Perl code does, but +instead checked all possibilities simultaneously by keeping a list of current +states and checking all of them as it advanced through the subject string. (In +the terminology of Jeffrey Friedl's book, it was a "DFA algorithm".) When the +pattern was all used up, all remaining states were possible matches, and the +one matching the longest subset of the subject string was chosen. This did not +necessarily maximize the individual wild portions of the pattern, as is +expected in Unix and Perl-style regular expressions. + +By contrast, the code originally written by Henry Spencer and subsequently +heavily modified for Perl actually compiles the expression twice: once in a +dummy mode in order to find out how much store will be needed, and then for +real. The execution function operates by backtracking and maximizing (or, +optionally, minimizing in Perl) the amount of the subject that matches +individual wild portions of the pattern. This is an "NFA algorithm" in Friedl's +terminology. + +For the set of functions that forms PCRE (which are unrelated to those +mentioned above), I tried at first to invent an algorithm that used an amount +of store bounded by a multiple of the number of characters in the pattern, to +save on compiling time. However, because of the greater complexity in Perl +regular expressions, I couldn't do this. In any case, a first pass through the +pattern is needed, in order to find internal flag settings like (?i) at top +level. So PCRE works by running a very degenerate first pass to calculate a +maximum store size, and then a second pass to do the real compile - which may +use a bit less than the predicted amount of store. The idea is that this is +going to turn out faster because the first pass is degenerate and the second +pass can just store stuff straight into the vector. It does make the compiling +functions bigger, of course, but they have got quite big anyway to handle all +the Perl stuff. + +The compiled form of a pattern is a vector of bytes, containing items of +variable length. The first byte in an item is an opcode, and the length of the +item is either implicit in the opcode or contained in the data bytes which +follow it. A list of all the opcodes follows: + +Opcodes with no following data +------------------------------ + +These items are all just one byte long + + OP_END end of pattern + OP_ANY match any character + OP_SOD match start of data: \A + OP_CIRC ^ (start of data, or after \n in multiline) + OP_NOT_WORD_BOUNDARY \W + OP_WORD_BOUNDARY \w + OP_NOT_DIGIT \D + OP_DIGIT \d + OP_NOT_WHITESPACE \S + OP_WHITESPACE \s + OP_NOT_WORDCHAR \W + OP_WORDCHAR \w + OP_EODN match end of data or \n at end: \Z + OP_EOD match end of data: \z + OP_DOLL $ (end of data, or before \n in multiline) + OP_RECURSE match the pattern recursively + + +Repeating single characters +--------------------------- + +The common repeats (*, +, ?) when applied to a single character appear as +two-byte items using the following opcodes: + + OP_STAR + OP_MINSTAR + OP_PLUS + OP_MINPLUS + OP_QUERY + OP_MINQUERY + +Those with "MIN" in their name are the minimizing versions. Each is followed by +the character that is to be repeated. Other repeats make use of + + OP_UPTO + OP_MINUPTO + OP_EXACT + +which are followed by a two-byte count (most significant first) and the +repeated character. OP_UPTO matches from 0 to the given number. A repeat with a +non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an +OP_UPTO (or OP_MINUPTO). + + +Repeating character types +------------------------- + +Repeats of things like \d are done exactly as for single characters, except +that instead of a character, the opcode for the type is stored in the data +byte. The opcodes are: + + OP_TYPESTAR + OP_TYPEMINSTAR + OP_TYPEPLUS + OP_TYPEMINPLUS + OP_TYPEQUERY + OP_TYPEMINQUERY + OP_TYPEUPTO + OP_TYPEMINUPTO + OP_TYPEEXACT + + +Matching a character string +--------------------------- + +The OP_CHARS opcode is followed by a one-byte count and then that number of +characters. If there are more than 255 characters in sequence, successive +instances of OP_CHARS are used. + + +Character classes +----------------- + +OP_CLASS is used for a character class, provided there are at least two +characters in the class. If there is only one character, OP_CHARS is used for a +positive class, and OP_NOT for a negative one (that is, for something like +[^a]). Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a +repeated, negated, single-character class. The normal ones (OP_STAR etc.) are +used for a repeated positive single-character class. + +OP_CLASS is followed by a 32-byte bit map containing a 1 bit for every +character that is acceptable. The bits are counted from the least significant +end of each byte. + + +Back references +--------------- + +OP_REF is followed by a single byte containing the reference number. + + +Repeating character classes and back references +----------------------------------------------- + +Single-character classes are handled specially (see above). This applies to +OP_CLASS and OP_REF. In both cases, the repeat information follows the base +item. The matching code looks at the following opcode to see if it is one of + + OP_CRSTAR + OP_CRMINSTAR + OP_CRPLUS + OP_CRMINPLUS + OP_CRQUERY + OP_CRMINQUERY + OP_CRRANGE + OP_CRMINRANGE + +All but the last two are just single-byte items. The others are followed by +four bytes of data, comprising the minimum and maximum repeat counts. + + +Brackets and alternation +------------------------ + +A pair of non-capturing (round) brackets is wrapped round each expression at +compile time, so alternation always happens in the context of brackets. +Non-capturing brackets use the opcode OP_BRA, while capturing brackets use +OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English +speakers, including myself, can be round, square, curly, or pointy. Hence this +usage.] + +A bracket opcode is followed by two bytes which give the offset to the next +alternative OP_ALT or, if there aren't any branches, to the matching KET +opcode. Each OP_ALT is followed by two bytes giving the offset to the next one, +or to the KET opcode. + +OP_KET is used for subpatterns that do not repeat indefinitely, while +OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or +maximally respectively. All three are followed by two bytes giving (as a +positive number) the offset back to the matching BRA opcode. + +If a subpattern is quantified such that it is permitted to match zero times, it +is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte +opcodes which tell the matcher that skipping this subpattern entirely is a +valid branch. + +A subpattern with an indefinite maximum repetition is replicated in the +compiled data its minimum number of times (or once with a BRAZERO if the +minimum is zero), with the final copy terminating with a KETRMIN or KETRMAX as +appropriate. + +A subpattern with a bounded maximum repetition is replicated in a nested +fashion up to the maximum number of times, with BRAZERO or BRAMINZERO before +each replication after the minimum, so that, for example, (abc){2,5} is +compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. The 200-bracket limit does not +apply to these internally generated brackets. + + +Assertions +---------- + +Forward assertions are just like other subpatterns, but starting with one of +the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes +OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion +is OP_REVERSE, followed by a two byte count of the number of characters to move +back the pointer in the subject string. When operating in UTF-8 mode, the count +is a character count rather than a byte count. A separate count is present in +each alternative of a lookbehind assertion, allowing them to have different +fixed lengths. + + +Once-only subpatterns +--------------------- + +These are also just like other subpatterns, but they start with the opcode +OP_ONCE. + + +Conditional subpatterns +----------------------- + +These are like other subpatterns, but they start with the opcode OP_COND. If +the condition is a back reference, this is stored at the start of the +subpattern using the opcode OP_CREF followed by one byte containing the +reference number. Otherwise, a conditional subpattern will always start with +one of the assertions. + + +Changing options +---------------- + +If any of the /i, /m, or /s options are changed within a parenthesized group, +an OP_OPT opcode is compiled, followed by one byte containing the new settings +of these flags. If there are several alternatives in a group, there is an +occurrence of OP_OPT at the start of all those following the first options +change, to set appropriate options for the start of the alternative. +Immediately after the end of the group there is another such item to reset the +flags to their previous values. Other changes of flag within the pattern can be +handled entirely at compile time, and so do not cause anything to be put into +the compiled data. + + +Philip Hazel +August 2000 diff --git a/pcre/doc/authors b/pcre/doc/authors new file mode 100644 index 00000000..bfe1b5d8 --- /dev/null +++ b/pcre/doc/authors @@ -0,0 +1,6 @@ +Written by: Philip Hazel + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2000 University of Cambridge diff --git a/pcre/doc/copying b/pcre/doc/copying new file mode 100644 index 00000000..34d20db9 --- /dev/null +++ b/pcre/doc/copying @@ -0,0 +1,46 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Written by: Philip Hazel + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2000 University of Cambridge + +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. In practice, this means that if you use + PCRE in software which you distribute to others, commercially or + otherwise, you must put a sentence like this + + Regular expression support is provided by the PCRE library package, + which is open source software, written by Philip Hazel, and copyright + by the University of Cambridge, England. + + somewhere reasonably visible in your documentation and in any relevant + files or online help data or similar. A reference to the ftp site for + the source, that is, to + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/ + + should also be given in the documentation. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. + +End diff --git a/pcre/doc/news b/pcre/doc/news new file mode 100644 index 00000000..56fccdfa --- /dev/null +++ b/pcre/doc/news @@ -0,0 +1,54 @@ +News about PCRE releases +------------------------ + +Release 3.3 01-Aug-00 +--------------------- + +There is some support for UTF-8 character strings. This is incomplete and +experimental. The documentation describes what is and what is not implemented. +Otherwise, this is just a bug-fixing release. + + +Release 3.0 01-Feb-00 +--------------------- + +1. A "configure" script is now used to configure PCRE for Unix systems. It +builds a Makefile, a config.h file, and the pcre-config script. + +2. PCRE is built as a shared library by default. + +3. There is support for POSIX classes such as [:alpha:]. + +5. There is an experimental recursion feature. + +---------------------------------------------------------------------------- + IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 + +Please note that there has been a change in the API such that a larger +ovector is required at matching time, to provide some additional workspace. +The new man page has details. This change was necessary in order to support +some of the new functionality in Perl 5.005. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 + +Another (I hope this is the last!) change has been made to the API for the +pcre_compile() function. An additional argument has been added to make it +possible to pass over a pointer to character tables built in the current +locale by pcre_maketables(). To use the default tables, this new arguement +should be passed as NULL. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 + +Yet another (and again I hope this really is the last) change has been made +to the API for the pcre_exec() function. An additional argument has been +added to make it possible to start the match other than at the start of the +subject string. This is important if there are lookbehinds. The new man +page has the details, but you just want to convert existing programs, all +you need to do is to stick in a new fifth argument to pcre_exec(), with a +value of zero. For example, change + + pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) +to + pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) + +**** diff --git a/pcre/doc/pcre.3 b/pcre/doc/pcre.3 new file mode 100644 index 00000000..bb812f47 --- /dev/null +++ b/pcre/doc/pcre.3 @@ -0,0 +1,1810 @@ +.TH PCRE 3 +.SH NAME +pcre - Perl-compatible regular expressions. +.SH SYNOPSIS +.B #include +.PP +.SM +.br +.B pcre *pcre_compile(const char *\fIpattern\fR, int \fIoptions\fR, +.ti +5n +.B const char **\fIerrptr\fR, int *\fIerroffset\fR, +.ti +5n +.B const unsigned char *\fItableptr\fR); +.PP +.br +.B pcre_extra *pcre_study(const pcre *\fIcode\fR, int \fIoptions\fR, +.ti +5n +.B const char **\fIerrptr\fR); +.PP +.br +.B int pcre_exec(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," +.ti +5n +.B "const char *\fIsubject\fR," int \fIlength\fR, int \fIstartoffset\fR, +.ti +5n +.B int \fIoptions\fR, int *\fIovector\fR, int \fIovecsize\fR); +.PP +.br +.B int pcre_copy_substring(const char *\fIsubject\fR, int *\fIovector\fR, +.ti +5n +.B int \fIstringcount\fR, int \fIstringnumber\fR, char *\fIbuffer\fR, +.ti +5n +.B int \fIbuffersize\fR); +.PP +.br +.B int pcre_get_substring(const char *\fIsubject\fR, int *\fIovector\fR, +.ti +5n +.B int \fIstringcount\fR, int \fIstringnumber\fR, +.ti +5n +.B const char **\fIstringptr\fR); +.PP +.br +.B int pcre_get_substring_list(const char *\fIsubject\fR, +.ti +5n +.B int *\fIovector\fR, int \fIstringcount\fR, "const char ***\fIlistptr\fR);" +.PP +.br +.B void pcre_free_substring(const char *\fIstringptr\fR); +.PP +.br +.B void pcre_free_substring_list(const char **\fIstringptr\fR); +.PP +.br +.B const unsigned char *pcre_maketables(void); +.PP +.br +.B int pcre_fullinfo(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," +.ti +5n +.B int \fIwhat\fR, void *\fIwhere\fR); +.PP +.br +.B int pcre_info(const pcre *\fIcode\fR, int *\fIoptptr\fR, int +.B *\fIfirstcharptr\fR); +.PP +.br +.B char *pcre_version(void); +.PP +.br +.B void *(*pcre_malloc)(size_t); +.PP +.br +.B void (*pcre_free)(void *); + + + +.SH DESCRIPTION +The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl 5, with just a few +differences (see below). The current implementation corresponds to Perl 5.005, +with some additional features from later versions. This includes some +experimental, incomplete support for UTF-8 encoded strings. Details of exactly +what is and what is not supported are given below. + +PCRE has its own native API, which is described in this document. There is also +a set of wrapper functions that correspond to the POSIX regular expression API. +These are described in the \fBpcreposix\fR documentation. + +The native API function prototypes are defined in the header file \fBpcre.h\fR, +and on Unix systems the library itself is called \fBlibpcre.a\fR, so can be +accessed by adding \fB-lpcre\fR to the command for linking an application which +calls it. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to +contain the major and minor release numbers for the library. Applications can +use these to include support for different releases. + +The functions \fBpcre_compile()\fR, \fBpcre_study()\fR, and \fBpcre_exec()\fR +are used for compiling and matching regular expressions. + +The functions \fBpcre_copy_substring()\fR, \fBpcre_get_substring()\fR, and +\fBpcre_get_substring_list()\fR are convenience functions for extracting +captured substrings from a matched subject string; \fBpcre_free_substring()\fR +and \fBpcre_free_substring_list()\fR are also provided, to free the memory used +for extracted strings. + +The function \fBpcre_maketables()\fR is used (optionally) to build a set of +character tables in the current locale for passing to \fBpcre_compile()\fR. + +The function \fBpcre_fullinfo()\fR is used to find out information about a +compiled pattern; \fBpcre_info()\fR is an obsolete version which returns only +some of the available information, but is retained for backwards compatibility. +The function \fBpcre_version()\fR returns a pointer to a string containing the +version of PCRE and its date of release. + +The global variables \fBpcre_malloc\fR and \fBpcre_free\fR initially contain +the entry points of the standard \fBmalloc()\fR and \fBfree()\fR functions +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. + + +.SH MULTI-THREADING +The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by \fBpcre_malloc\fR +and \fBpcre_free\fR are shared by all threads. + +The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. + + +.SH COMPILING A PATTERN +The function \fBpcre_compile()\fR is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument \fIpattern\fR. A pointer to a single block of memory +that is obtained via \fBpcre_malloc\fR is returned. This contains the +compiled code and related data. The \fBpcre\fR type is defined for this for +convenience, but in fact \fBpcre\fR is just a typedef for \fBvoid\fR, since the +contents of the block are not externally defined. It is up to the caller to +free the memory when it is no longer required. +.PP +The size of a compiled pattern is roughly proportional to the length of the +pattern string, except that each character class (other than those containing +just a single character, negated or not) requires 33 bytes, and repeat +quantifiers with a minimum greater than one or a bounded maximum cause the +relevant portions of the compiled pattern to be replicated. +.PP +The \fIoptions\fR argument contains independent bits that affect the +compilation. It should be zero if no options are required. Some of the options, +in particular, those that are compatible with Perl, can also be set and unset +from within the pattern (see the detailed description of regular expressions +below). For these options, the contents of the \fIoptions\fR argument specifies +their initial settings at the start of compilation and execution. The +PCRE_ANCHORED option can be set at the time of matching as well as at compile +time. +.PP +If \fIerrptr\fR is NULL, \fBpcre_compile()\fR returns NULL immediately. +Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fR returns +NULL, and sets the variable pointed to by \fIerrptr\fR to point to a textual +error message. The offset from the start of the pattern to the character where +the error was discovered is placed in the variable pointed to by +\fIerroffset\fR, which must not be NULL. If it is, an immediate error is given. +.PP +If the final argument, \fItableptr\fR, is NULL, PCRE uses a default set of +character tables which are built when it is compiled, using the default C +locale. Otherwise, \fItableptr\fR must be the result of a call to +\fBpcre_maketables()\fR. See the section on locale support below. +.PP +The following option bits are defined in the header file: + + PCRE_ANCHORED + +If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the start of the string which is being searched +(the "subject string"). This effect can also be achieved by appropriate +constructs in the pattern itself, which is the only way to do it in Perl. + + PCRE_CASELESS + +If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option. + + PCRE_DOLLAR_ENDONLY + +If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before the final character if it is a newline (but not before any +other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is +set. There is no equivalent to this option in Perl. + + PCRE_DOTALL + +If this bit is set, a dot metacharater in the pattern matches all characters, +including newlines. Without it, newlines are excluded. This option is +equivalent to Perl's /s option. A negative class such as [^a] always matches a +newline character, independent of the setting of this option. + + PCRE_EXTENDED + +If this bit is set, whitespace data characters in the pattern are totally +ignored except when escaped or inside a character class, and characters between +an unescaped # outside a character class and the next newline character, +inclusive, are also ignored. This is equivalent to Perl's /x option, and makes +it possible to include comments inside complicated patterns. Note, however, +that this applies only to data characters. Whitespace characters may never +appear within special character sequences in a pattern, for example within the +sequence (?( which introduces a conditional subpattern. + + PCRE_EXTRA + +This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. There are at present no other features +controlled by this option. It can also be set by a (?X) option setting within a +pattern. + + PCRE_MULTILINE + +By default, PCRE treats the subject string as consisting of a single "line" of +characters (even if it actually contains several newlines). The "start of line" +metacharacter (^) matches only at the start of the string, while the "end of +line" metacharacter ($) matches only at the end of the string, or before a +terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as +Perl. + +When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before any newline in the subject +string, respectively, as well as at the very start and end. This is equivalent +to Perl's /m option. If there are no "\\n" characters in a subject string, or +no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no +effect. + + PCRE_UNGREEDY + +This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. + + PCRE_UTF8 + +This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of just byte strings. However, it is available only +if PCRE has been built to include UTF-8 support. If not, the use of this option +provokes an error. Support for UTF-8 is new, experimental, and incomplete. +Details of exactly what it entails are given below. + + +.SH STUDYING A PATTERN +When a pattern is going to be used several times, it is worth spending more +time analyzing it in order to speed up the time taken for matching. The +function \fBpcre_study()\fR takes a pointer to a compiled pattern as its first +argument, and returns a pointer to a \fBpcre_extra\fR block (another \fBvoid\fR +typedef) containing additional information about the pattern; this can be +passed to \fBpcre_exec()\fR. If no additional information is available, NULL +is returned. + +The second argument contains option bits. At present, no options are defined +for \fBpcre_study()\fR, and this argument should always be zero. + +The third argument for \fBpcre_study()\fR is a pointer to an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it points to a textual error message. + +At present, studying a pattern is useful only for non-anchored patterns that do +not have a single fixed starting character. A bitmap of possible starting +characters is created. + + +.SH LOCALE SUPPORT +PCRE handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables. The library contains a +default set of tables which is created in the default C locale when PCRE is +compiled. This is used when the final argument of \fBpcre_compile()\fR is NULL, +and is sufficient for many applications. + +An alternative set of tables can, however, be supplied. Such tables are built +by calling the \fBpcre_maketables()\fR function, which has no arguments, in the +relevant locale. The result can then be passed to \fBpcre_compile()\fR as often +as necessary. For example, to build and use tables that are appropriate for the +French locale (where accented characters with codes greater than 128 are +treated as letters), the following code could be used: + + setlocale(LC_CTYPE, "fr"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); + +The tables are built in memory that is obtained via \fBpcre_malloc\fR. The +pointer that is passed to \fBpcre_compile\fR is saved with the compiled +pattern, and the same tables are used via this pointer by \fBpcre_study()\fR +and \fBpcre_exec()\fR. Thus for any single pattern, compilation, studying and +matching all happen in the same locale, but different patterns can be compiled +in different locales. It is the caller's responsibility to ensure that the +memory containing the tables remains available for as long as it is needed. + + +.SH INFORMATION ABOUT A PATTERN +The \fBpcre_fullinfo()\fR function returns information about a compiled +pattern. It replaces the obsolete \fBpcre_info()\fR function, which is +nevertheless retained for backwards compability (and is documented below). + +The first argument for \fBpcre_fullinfo()\fR is a pointer to the compiled +pattern. The second argument is the result of \fBpcre_study()\fR, or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, while the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: + + PCRE_ERROR_NULL the argument \fIcode\fR was NULL + the argument \fIwhere\fR was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of \fIwhat\fR was invalid + +The possible values for the third argument are defined in \fBpcre.h\fR, and are +as follows: + + PCRE_INFO_OPTIONS + +Return a copy of the options with which the pattern was compiled. The fourth +argument should point to au \fBunsigned long int\fR variable. These option bits +are those specified in the call to \fBpcre_compile()\fR, modified by any +top-level option settings within the pattern itself, and with the PCRE_ANCHORED +bit forcibly set if the form of the pattern implies that it can match only at +the start of a subject string. + + PCRE_INFO_SIZE + +Return the size of the compiled pattern, that is, the value that was passed as +the argument to \fBpcre_malloc()\fR when PCRE was getting memory in which to +place the compiled data. The fourth argument should point to a \fBsize_t\fR +variable. + + PCRE_INFO_CAPTURECOUNT + +Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an \fbint\fR variable. + + PCRE_INFO_BACKREFMAX + +Return the number of the highest back reference in the pattern. The fourth +argument should point to an \fBint\fR variable. Zero is returned if there are +no back references. + + PCRE_INFO_FIRSTCHAR + +Return information about the first character of any matched string, for a +non-anchored pattern. If there is a fixed first character, e.g. from a pattern +such as (cat|cow|coyote), it is returned in the integer pointed to by +\fIwhere\fR. Otherwise, if either + +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or + +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), + +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any "\\n" within the string. Otherwise -2 is returned. +For anchored patterns, -2 is returned. + + PCRE_INFO_FIRSTTABLE + +If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of characters for the first character in any +matching string, a pointer to the table is returned. Otherwise NULL is +returned. The fourth argument should point to an \fBunsigned char *\fR +variable. + + PCRE_INFO_LASTLITERAL + +For a non-anchored pattern, return the value of the rightmost literal character +which must exist in any matched string, other than at its start. The fourth +argument should point to an \fBint\fR variable. If there is no such character, +or if the pattern is anchored, -1 is returned. For example, for the pattern +/a\\d+z\\d+/ the returned value is 'z'. + +The \fBpcre_info()\fR function is now obsolete because its interface is too +restrictive to return all the available data about a compiled pattern. New +programs should use \fBpcre_fullinfo()\fR instead. The yield of +\fBpcre_info()\fR is the number of capturing subpatterns, or one of the +following negative numbers: + + PCRE_ERROR_NULL the argument \fIcode\fR was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + +If the \fIoptptr\fR argument is not NULL, a copy of the options with which the +pattern was compiled is placed in the integer it points to (see +PCRE_INFO_OPTIONS above). + +If the pattern is not anchored and the \fIfirstcharptr\fR argument is not NULL, +it is used to pass back information about the first character of any matched +string (see PCRE_INFO_FIRSTCHAR above). + + +.SH MATCHING A PATTERN +The function \fBpcre_exec()\fR is called to match a subject string against a +pre-compiled pattern, which is passed in the \fIcode\fR argument. If the +pattern has been studied, the result of the study should be passed in the +\fIextra\fR argument. Otherwise this must be NULL. + +The PCRE_ANCHORED option can be passed in the \fIoptions\fR argument, whose +unused bits must be zero. However, if a pattern was compiled with +PCRE_ANCHORED, or turned out to be anchored by virtue of its contents, it +cannot be made unachored at matching time. + +There are also three further options that can be set only at matching time: + + PCRE_NOTBOL + +The first character of the string is not the beginning of a line, so the +circumflex metacharacter should not match before it. Setting this without +PCRE_MULTILINE (at compile time) causes circumflex never to match. + + PCRE_NOTEOL + +The end of the string is not the end of a line, so the dollar metacharacter +should not match it nor (except in multiline mode) a newline immediately before +it. Setting this without PCRE_MULTILINE (at compile time) causes dollar never +to match. + + PCRE_NOTEMPTY + +An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern + + a?b? + +is applied to a string not beginning with "a" or "b", it matches the empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". + +Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case +of a pattern match of the empty string within its \fBsplit()\fR function, and +when using the /g modifier. It is possible to emulate Perl's behaviour after +matching a null string by first trying the match again at the same offset with +PCRE_NOTEMPTY set, and then if that fails by advancing the starting offset (see +below) and trying an ordinary match again. + +The subject string is passed as a pointer in \fIsubject\fR, a length in +\fIlength\fR, and a starting offset in \fIstartoffset\fR. Unlike the pattern +string, it may contain binary zero characters. When the starting offset is +zero, the search for a match starts at the beginning of the subject, and this +is by far the most common case. + +A non-zero starting offset is useful when searching for another match in the +same subject by calling \fBpcre_exec()\fR again after a previous success. +Setting \fIstartoffset\fR differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern + + \\Biss\\B + +which finds occurrences of "iss" in the middle of words. (\\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to \fBpcre_exec()\fR finds the first +occurrence. If \fBpcre_exec()\fR is called again with just the remainder of the +subject, namely "issipi", it does not match, because \\B is always false at the +start of the subject, which is deemed to be a word boundary. However, if +\fBpcre_exec()\fR is passed the entire string again, but with \fIstartoffset\fR +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. + +If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is tried. This can only succeed if the +pattern does not require the match to be at the start of the subject. + +In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. + +Captured substrings are returned to the caller via a vector of integer offsets +whose address is passed in \fIovector\fR. The number of elements in the vector +is passed in \fIovecsize\fR. The first two-thirds of the vector is used to pass +back captured substrings, each substring using a pair of integers. The +remaining third of the vector is used as workspace by \fBpcre_exec()\fR while +matching capturing subpatterns, and is not available for passing back +information. The length passed in \fIovecsize\fR should always be a multiple of +three. If it is not, it is rounded down. + +When a match has been successful, information about captured substrings is +returned in pairs of integers, starting at the beginning of \fIovector\fR, and +continuing up to two-thirds of its length at the most. The first element of a +pair is set to the offset of the first character in a substring, and the second +is set to the offset of the first character after the end of a substring. The +first pair, \fIovector[0]\fR and \fIovector[1]\fR, identify the portion of the +subject string matched by the entire pattern. The next pair is used for the +first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fR +is the number of pairs that have been set. If there are no capturing +subpatterns, the return value from a successful match is 1, indicating that +just the first pair of offsets has been set. + +Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described in the following section. + +It is possible for an capturing subpattern number \fIn+1\fR to match some +part of the subject when subpattern \fIn\fR has not been used at all. For +example, if the string "abc" is matched against the pattern (a|(z))(bc) +subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset +values corresponding to the unused subpattern are set to -1. + +If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that gets returned. + +If the vector is too small to hold all the captured substrings, it is used as +far as possible (up to two-thirds of its length), and the function returns a +value of zero. In particular, if the substring offsets are not of interest, +\fBpcre_exec()\fR may be called with \fIovector\fR passed as NULL and +\fIovecsize\fR as zero. However, if the pattern contains back references and +the \fIovector\fR isn't big enough to remember the related substrings, PCRE has +to get additional memory for use during matching. Thus it is usually advisable +to supply an \fIovector\fR. + +Note that \fBpcre_info()\fR can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +\fIovector\fR that will allow for \fIn\fR captured substrings in addition to +the offsets of the substring matched by the whole pattern is (\fIn\fR+1)*3. + +If \fBpcre_exec()\fR fails, it returns a negative number. The following are +defined in the header file: + + PCRE_ERROR_NOMATCH (-1) + +The subject string did not match the pattern. + + PCRE_ERROR_NULL (-2) + +Either \fIcode\fR or \fIsubject\fR was passed as NULL, or \fIovector\fR was +NULL and \fIovecsize\fR was not zero. + + PCRE_ERROR_BADOPTION (-3) + +An unrecognized bit was set in the \fIoptions\fR argument. + + PCRE_ERROR_BADMAGIC (-4) + +PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer. This is the error it gives when the +magic number isn't present. + + PCRE_ERROR_UNKNOWN_NODE (-5) + +While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. + + PCRE_ERROR_NOMEMORY (-6) + +If a pattern contains back references, but the \fIovector\fR that is passed to +\fBpcre_exec()\fR is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via \fBpcre_malloc()\fR fails, this error is given. The memory is freed at +the end of matching. + + +.SH EXTRACTING CAPTURED SUBSTRINGS +Captured substrings can be accessed directly by using the offsets returned by +\fBpcre_exec()\fR in \fIovector\fR. For convenience, the functions +\fBpcre_copy_substring()\fR, \fBpcre_get_substring()\fR, and +\fBpcre_get_substring_list()\fR are provided for extracting captured substrings +as new, separate, zero-terminated strings. A substring that contains a binary +zero is correctly extracted and has a further zero added on the end, but the +result does not, of course, function as a C string. + +The first three arguments are the same for all three functions: \fIsubject\fR +is the subject string which has just been successfully matched, \fIovector\fR +is a pointer to the vector of integer offsets that was passed to +\fBpcre_exec()\fR, and \fIstringcount\fR is the number of substrings that +were captured by the match, including the substring that matched the entire +regular expression. This is the value returned by \fBpcre_exec\fR if it +is greater than zero. If \fBpcre_exec()\fR returned zero, indicating that it +ran out of space in \fIovector\fR, the value passed as \fIstringcount\fR should +be the size of the vector divided by three. + +The functions \fBpcre_copy_substring()\fR and \fBpcre_get_substring()\fR +extract a single substring, whose number is given as \fIstringnumber\fR. A +value of zero extracts the substring that matched the entire pattern, while +higher values extract the captured substrings. For \fBpcre_copy_substring()\fR, +the string is placed in \fIbuffer\fR, whose length is given by +\fIbuffersize\fR, while for \fBpcre_get_substring()\fR a new block of memory is +obtained via \fBpcre_malloc\fR, and its address is returned via +\fIstringptr\fR. The yield of the function is the length of the string, not +including the terminating zero, or one of + + PCRE_ERROR_NOMEMORY (-6) + +The buffer was too small for \fBpcre_copy_substring()\fR, or the attempt to get +memory failed for \fBpcre_get_substring()\fR. + + PCRE_ERROR_NOSUBSTRING (-7) + +There is no substring whose number is \fIstringnumber\fR. + +The \fBpcre_get_substring_list()\fR function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory which is obtained via \fBpcre_malloc\fR. The address of the memory block +is returned via \fIlistptr\fR, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or + + PCRE_ERROR_NOMEMORY (-6) + +if the attempt to get the memory block failed. + +When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number \fIn+1\fR matches some part of the +subject, but subpattern \fIn\fR has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in \fIovector\fR, which is negative for unset +substrings. + +The two convenience functions \fBpcre_free_substring()\fR and +\fBpcre_free_substring_list()\fR can be used to free the memory returned by +a previous call of \fBpcre_get_substring()\fR or +\fBpcre_get_substring_list()\fR, respectively. They do nothing more than call +the function pointed to by \fBpcre_free\fR, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language which cannot use +\fBpcre_free\fR directly; it is for these cases that the functions are +provided. + + +.SH LIMITATIONS +There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +The maximum length of a compiled pattern is 65539 (sic) bytes. +All values in repeating quantifiers must be less than 65536. +The maximum number of capturing subpatterns is 99. +The maximum number of all parenthesized subpatterns, including capturing +subpatterns, assertions, and other types of subpattern, is 200. + +The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, PCRE uses recursion to handle subpatterns +and indefinite repetition. This means that the available stack space may limit +the size of a subject string that can be processed by certain patterns. + + +.SH DIFFERENCES FROM PERL +The differences described here are with respect to Perl 5.005. + +1. By default, a whitespace character is any character that the C library +function \fBisspace()\fR recognizes, though it is possible to compile PCRE with +alternative character type tables. Normally \fBisspace()\fR matches space, +formfeed, newline, carriage return, horizontal tab, and vertical tab. Perl 5 +no longer includes vertical tab in its set of whitespace characters. The \\v +escape that was in the Perl documentation for a long time was never in fact +recognized. However, the character itself was treated as whitespace at least +up to 5.002. In 5.004 and 5.005 it does not match \\s. + +2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits +them, but they do not mean what you might think. For example, (?!a){3} does +not assert that the next three characters are not "a". It just asserts that the +next character is not "a" three times. + +3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sets its +numerical variables from any such patterns that are matched before the +assertion fails to match something (thereby succeeding), but only if the +negative lookahead assertion contains just one branch. + +4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence "\\0" can be used in the pattern to +represent a binary zero. + +5. The following Perl escape sequences are not supported: \\l, \\u, \\L, \\U, +\\E, \\Q. In fact these are implemented by Perl's general string-handling and +are not part of its pattern matching engine. + +6. The Perl \\G assertion is not supported as it is not relevant to single +pattern matches. + +7. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) +constructions. However, there is some experimental support for recursive +patterns using the non-Perl item (?R). + +8. There are at the time of writing some oddities in Perl 5.005_02 concerned +with the settings of captured strings when part of a pattern is repeated. For +example, matching "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value +"b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 unset. However, if +the pattern is changed to /^(aa(b(b))?)+$/ then $2 (and $3) are set. + +In Perl 5.004 $2 is set in both cases, and that is also true of PCRE. If in the +future Perl changes to a consistent state that is different, PCRE may change to +follow. + +9. Another as yet unresolved discrepancy is that in Perl 5.005_02 the pattern +/^(a)?(?(1)a|b)+$/ matches the string "a", whereas in PCRE it does not. +However, in both Perl and PCRE /^(a)?a/ matched against "a" leaves $1 unset. + +10. PCRE provides some extensions to the Perl regular expression facilities: + +(a) Although lookbehind assertions must match fixed length strings, each +alternative branch of a lookbehind assertion can match a different length of +string. Perl 5.005 requires them all to have the same length. + +(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta- +character matches only at the very end of the string. + +(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. + +(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. + +(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the start +of the subject. + +(f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options for +\fBpcre_exec()\fR have no Perl equivalents. + +(g) The (?R) construct allows for recursive pattern matching (Perl 5.6 can do +this using the (?p{code}) construct, which PCRE cannot of course support.) + + +.SH REGULAR EXPRESSION DETAILS +The syntax and semantics of the regular expressions supported by PCRE are +described below. Regular expressions are also described in the Perl +documentation and in a number of other books, some of which have copious +examples. Jeffrey Friedl's "Mastering Regular Expressions", published by +O'Reilly (ISBN 1-56592-257), covers them in great detail. + +The description here is intended as reference documentation. The basic +operation of PCRE is on strings of bytes. However, there is the beginnings of +some support for UTF-8 character strings. To use this support you must +configure PCRE to include it, and then call \fBpcre_compile()\fR with the +PCRE_UTF8 option. How this affects the pattern matching is described in the +final section of this document. + +A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern + + The quick brown fox + +matches a portion of a subject string that is identical to itself. The power of +regular expressions comes from the ability to include alternatives and +repetitions in the pattern. These are encoded in the pattern by the use of +\fImeta-characters\fR, which do not stand for themselves but instead are +interpreted in some special way. + +There are two different sets of meta-characters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized in square brackets. Outside square brackets, the meta-characters are +as follows: + + \\ general escape character with several uses + ^ assert start of subject (or line, in multiline mode) + $ assert end of subject (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + { start min/max quantifier + +Part of a pattern that is in square brackets is called a "character class". In +a character class the only meta-characters are: + + \\ general escape character + ^ negate the class, but only if the first character + - indicates character range + ] terminates the character class + +The following sections describe the use of each of the meta-characters. + + +.SH BACKSLASH +The backslash character has several uses. Firstly, if it is followed by a +non-alphameric character, it takes away any special meaning that character may +have. This use of backslash as an escape character applies both inside and +outside character classes. + +For example, if you want to match a "*" character, you write "\\*" in the +pattern. This applies whether or not the following character would otherwise be +interpreted as a meta-character, so it is always safe to precede a +non-alphameric with "\\" to specify that it stands for itself. In particular, +if you want to match a backslash, you write "\\\\". + +If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the +pattern (other than in a character class) and characters between a "#" outside +a character class and the next newline character are ignored. An escaping +backslash can be used to include a whitespace or "#" character as part of the +pattern. + +A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is usually easier to +use one of the following escape sequences than the binary character it +represents: + + \\a alarm, that is, the BEL character (hex 07) + \\cx "control-x", where x is any character + \\e escape (hex 1B) + \\f formfeed (hex 0C) + \\n newline (hex 0A) + \\r carriage return (hex 0D) + \\t tab (hex 09) + \\xhh character with hex code hh + \\ddd character with octal code ddd, or backreference + +The precise effect of "\\cx" is as follows: if "x" is a lower case letter, it +is converted to upper case. Then bit 6 of the character (hex 40) is inverted. +Thus "\\cz" becomes hex 1A, but "\\c{" becomes hex 3B, while "\\c;" becomes hex +7B. + +After "\\x", up to two hexadecimal digits are read (letters can be in upper or +lower case). + +After "\\0" up to two further octal digits are read. In both cases, if there +are fewer than two digits, just those that are present are used. Thus the +sequence "\\0\\x\\07" specifies two binary zeros followed by a BEL character. +Make sure you supply two digits after the initial zero if the character that +follows is itself an octal digit. + +The handling of a backslash followed by a digit other than 0 is complicated. +Outside a character class, PCRE reads it and any following digits as a decimal +number. If the number is less than 10, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a \fIback reference\fR. A description of how this works is given +later, following the discussion of parenthesized subpatterns. + +Inside a character class, or if the decimal number is greater than 9 and there +have not been that many capturing subpatterns, PCRE re-reads up to three octal +digits following the backslash, and generates a single byte from the least +significant 8 bits of the value. Any subsequent digits stand for themselves. +For example: + + \\040 is another way of writing a space + \\40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \\7 is always a back reference + \\11 might be a back reference, or another way of + writing a tab + \\011 is always a tab + \\0113 is a tab followed by the character "3" + \\113 is the character with octal code 113 (since there + can be no more than 99 back references) + \\377 is a byte consisting entirely of 1 bits + \\81 is either a back reference, or a binary zero + followed by the two characters "8" and "1" + +Note that octal values of 100 or greater must not be introduced by a leading +zero, because no more than three octal digits are ever read. + +All the sequences that define a single byte value can be used both inside and +outside character classes. In addition, inside a character class, the sequence +"\\b" is interpreted as the backspace character (hex 08). Outside a character +class it has a different meaning (see below). + +The third use of backslash is for specifying generic character types: + + \\d any decimal digit + \\D any character that is not a decimal digit + \\s any whitespace character + \\S any character that is not a whitespace character + \\w any "word" character + \\W any "non-word" character + +Each pair of escape sequences partitions the complete set of characters into +two disjoint sets. Any given character matches one, and only one, of each pair. + +A "word" character is any letter or digit or the underscore character, that is, +any character which can be part of a Perl "word". The definition of letters and +digits is controlled by PCRE's character tables, and may vary if locale- +specific matching is taking place (see "Locale support" above). For example, in +the "fr" (French) locale, some character codes greater than 128 are used for +accented letters, and these are matched by \\w. + +These character type sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, since +there is no character to match. + +The fourth use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described below. The backslashed +assertions are + + \\b word boundary + \\B not a word boundary + \\A start of subject (independent of multiline mode) + \\Z end of subject or newline at end (independent of multiline mode) + \\z end of subject (independent of multiline mode) + +These assertions may not appear in character classes (but note that "\\b" has a +different meaning, namely the backspace character, inside a character class). + +A word boundary is a position in the subject string where the current character +and the previous character do not both match \\w or \\W (i.e. one matches +\\w and the other matches \\W), or the start or end of the string if the +first or last character matches \\w, respectively. + +The \\A, \\Z, and \\z assertions differ from the traditional circumflex and +dollar (described below) in that they only ever match at the very start and end +of the subject string, whatever options are set. They are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options. If the \fIstartoffset\fR argument of +\fBpcre_exec()\fR is non-zero, \\A can never match. The difference between \\Z +and \\z is that \\Z matches before a newline that is the last character of the +string as well as at the end of the string, whereas \\z matches only at the +end. + + +.SH CIRCUMFLEX AND DOLLAR +Outside a character class, in the default matching mode, the circumflex +character is an assertion which is true only if the current matching point is +at the start of the subject string. If the \fIstartoffset\fR argument of +\fBpcre_exec()\fR is non-zero, circumflex can never match. Inside a character +class, circumflex has an entirely different meaning (see below). + +Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) + +A dollar character is an assertion which is true only if the current matching +point is at the end of the subject string, or immediately before a newline +character that is the last character in the string (by default). Dollar need +not be the last character of the pattern if a number of alternatives are +involved, but it should be the last item in any branch in which it appears. +Dollar has no special meaning in a character class. + +The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile or matching +time. This does not affect the \\Z assertion. + +The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, they match immediately +after and immediately before an internal "\\n" character, respectively, in +addition to matching at the start and end of the subject string. For example, +the pattern /^abc$/ matches the subject string "def\\nabc" in multiline mode, +but not otherwise. Consequently, patterns that are anchored in single line mode +because all branches start with "^" are not anchored in multiline mode, and a +match for circumflex is possible when the \fIstartoffset\fR argument of +\fBpcre_exec()\fR is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if +PCRE_MULTILINE is set. + +Note that the sequences \\A, \\Z, and \\z can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\\A is it always anchored, whether PCRE_MULTILINE is set or not. + + +.SH FULL STOP (PERIOD, DOT) +Outside a character class, a dot in the pattern matches any one character in +the subject, including a non-printing character, but not (by default) newline. +If the PCRE_DOTALL option is set, dots match newlines as well. The handling of +dot is entirely independent of the handling of circumflex and dollar, the only +relationship being that they both involve newline characters. Dot has no +special meaning in a character class. + + +.SH SQUARE BRACKETS +An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special. If a +closing square bracket is required as a member of the class, it should be the +first data character in the class (after an initial circumflex, if present) or +escaped with a backslash. + +A character class matches a single character in the subject; the character must +be in the set of characters defined by the class, unless the first character in +the class is a circumflex, in which case the subject character must not be in +the set defined by the class. If a circumflex is actually required as a member +of the class, ensure it is not the first character, or escape it with a +backslash. + +For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters which +are in the class by enumerating those that are not. It is not an assertion: it +still consumes a character from the subject string, and fails if the current +pointer is at the end of the string. + +When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. + +The newline character is never treated in any special way in character classes, +whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class +such as [^a] will always match a newline. + +The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class. + +It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\\]46] is interpreted as a single class containing a +range followed by two separate characters. The octal or hexadecimal +representation of "]" can also be used to end a range. + +Ranges operate in ASCII collating sequence. They can also be used for +characters specified numerically, for example [\\000-\\037]. If a range that +includes letters is used when caseless matching is set, it matches the letters +in either case. For example, [W-c] is equivalent to [][\\^_`wxyzabc], matched +caselessly, and if character tables for the "fr" locale are in use, +[\\xc8-\\xcb] matches accented E characters in both cases. + +The character types \\d, \\D, \\s, \\S, \\w, and \\W may also appear in a +character class, and add the characters that they match to the class. For +example, [\\dABCDEF] matches any hexadecimal digit. A circumflex can +conveniently be used with the upper case character types to specify a more +restricted set of characters than the matching lower case type. For example, +the class [^\\W_] matches any letter or digit, but not underscore. + +All non-alphameric characters other than \\, -, ^ (at the start) and the +terminating ] are non-special in character classes, but it does no harm if they +are escaped. + + +.SH POSIX CHARACTER CLASSES +Perl 5.6 (not yet released at the time of writing) is going to support the +POSIX notation for character classes, which uses names enclosed by [: and :] +within the enclosing square brackets. PCRE supports this notation. For example, + + [01[:alpha:]%] + +matches "0", "1", any alphabetic character, or "%". The supported class names +are + + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + cntrl control characters + digit decimal digits (same as \\d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits + space white space (same as \\s) + upper upper case letters + word "word" characters (same as \\w) + xdigit hexadecimal digits + +The names "ascii" and "word" are Perl extensions. Another Perl extension is +negation, which is indicated by a ^ character after the colon. For example, + + [12[:^digit:]] + +matches "1", "2", or any non-digit. PCRE (and Perl) also recogize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. + + +.SH VERTICAL BAR +Vertical bar characters are used to separate alternative patterns. For example, +the pattern + + gilbert|sullivan + +matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). +The matching process tries each alternative in turn, from left to right, +and the first one that succeeds is used. If the alternatives are within a +subpattern (defined below), "succeeds" means matching the rest of the main +pattern as well as the alternative in the subpattern. + + +.SH INTERNAL OPTION SETTING +The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and PCRE_EXTENDED +can be changed from within the pattern by a sequence of Perl option letters +enclosed between "(?" and ")". The option letters are + + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED + +For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. + +The scope of these option changes depends on where in the pattern the setting +occurs. For settings that are outside any subpattern (defined below), the +effect is the same as if the options were set or unset at the start of +matching. The following patterns all behave in exactly the same way: + + (?i)abc + a(?i)bc + ab(?i)c + abc(?i) + +which in turn is the same as compiling the pattern abc with PCRE_CASELESS set. +In other words, such "top level" settings apply to the whole pattern (unless +there are other changes inside subpatterns). If there is more than one setting +of the same option at top level, the rightmost setting is used. + +If an option change occurs inside a subpattern, the effect is different. This +is a change of behaviour in Perl 5.005. An option change inside a subpattern +affects only that part of the subpattern that follows it, so + + (a(?i)b)c + +matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, + + (a(?i)b|c) + +matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. + +The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the +same way as the Perl-compatible options by using the characters U and X +respectively. The (?X) flag setting is special in that it must always occur +earlier in the pattern than any of the additional features it turns on, even +when it is at top level. It is best put at the start. + + +.SH SUBPATTERNS +Subpatterns are delimited by parentheses (round brackets), which can be nested. +Marking part of a pattern as a subpattern does two things: + +1. It localizes a set of alternatives. For example, the pattern + + cat(aract|erpillar|) + +matches one of the words "cat", "cataract", or "caterpillar". Without the +parentheses, it would match "cataract", "erpillar" or the empty string. + +2. It sets up the subpattern as a capturing subpattern (as defined above). +When the whole pattern matches, that portion of the subject string that matched +the subpattern is passed back to the caller via the \fIovector\fR argument of +\fBpcre_exec()\fR. Opening parentheses are counted from left to right (starting +from 1) to obtain the numbers of the capturing subpatterns. + +For example, if the string "the red king" is matched against the pattern + + the ((red|white) (king|queen)) + +the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3. + +The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by "?:", the +subpattern does not do any capturing, and is not counted when computing the +number of any subsequent capturing subpatterns. For example, if the string "the +white queen" is matched against the pattern + + the ((?:red|white) (king|queen)) + +the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of captured substrings is 99, and the maximum number of +all subpatterns, both capturing and non-capturing, is 200. + +As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns + + (?i:saturday|sunday) + (?:(?i)saturday|sunday) + +match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". + + +.SH REPETITION +Repetition is specified by quantifiers, which can follow any of the following +items: + + a single character, possibly escaped + the . metacharacter + a character class + a back reference (see next section) + a parenthesized subpattern (unless it is an assertion - see below) + +The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: + + z{2,4} + +matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus + + [aeiou]{3,} + +matches at least 3 successive vowels, but may match many more, while + + \\d{8} + +matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. + +The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. + +For convenience (and historical compatibility) the three most common +quantifiers have single-character abbreviations: + + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} + +It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: + + (a?)* + +Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. + +By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between the +sequences /* and */ and within the sequence, individual * and / characters may +appear. An attempt to match C comments by applying the pattern + + /\\*.*\\*/ + +to the string + + /* first command */ not comment /* second comment */ + +fails, because it matches the entire string owing to the greediness of the .* +item. + +However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern + + /\\*.*?\\*/ + +does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in + + \\d??\\d + +which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. + +If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. + +When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more store is required for the +compiled pattern, in proportion to the size of the minimum or maximum. + +If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE treats such a pattern as +though it were preceded by \\A. In cases where it is known that the subject +string contains no newlines, it is worth setting PCRE_DOTALL when the pattern +begins with .* in order to obtain this optimization, or alternatively using ^ +to indicate anchoring explicitly. + +When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after + + (tweedle[dume]{3}\\s*)+ + +has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after + + /(a|(b))+/ + +matches "aba" the value of the second captured substring is "b". + + +.SH BACK REFERENCES +Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(i.e. to its left) in the pattern, provided there have been that many previous +capturing left parentheses. + +However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. See the section entitled "Backslash" above for further +details of the handling of digits following a backslash. + +A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself. So the pattern + + (sens|respons)e and \\1ibility + +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, + + ((?i)rah)\\s+\\1 + +matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. + +There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail. For example, the pattern + + (a|(bc))\\2 + +always fails if it starts to match "a" rather than "bc". Because there may be +up to 99 back references, all digits following the backslash are taken +as part of a potential back reference number. If the pattern continues with a +digit character, some delimiter must be used to terminate the back reference. +If the PCRE_EXTENDED option is set, this can be whitespace. Otherwise an empty +comment can be used. + +A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\\1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern + + (a|b\\1)+ + +matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. + + +.SH ASSERTIONS +An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \\b, \\B, \\A, \\Z, \\z, ^ and $ are described above. More +complicated assertions are coded as subpatterns. There are two kinds: those +that look ahead of the current position in the subject string, and those that +look behind it. + +An assertion subpattern is matched in the normal way, except that it does not +cause the current matching position to be changed. Lookahead assertions start +with (?= for positive assertions and (?! for negative assertions. For example, + + \\w+(?=;) + +matches a word followed by a semicolon, but does not include the semicolon in +the match, and + + foo(?!bar) + +matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern + + (?!foo)bar + +does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve this effect. + +Lookbehind assertions start with (?<= for positive assertions and (? as in this example: + + (?>\\d+)bar + +This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. + +An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. + +Once-only subpatterns are not capturing subpatterns. Simple cases such as the +above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \\d+ and \\d+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\\d+) can only match an entire sequence of digits. + +This construction can of course contain arbitrarily complicated subpatterns, +and it can be nested. + +Once-only subpatterns can be used in conjunction with lookbehind assertions to +specify efficient matching at the end of the subject string. Consider a simple +pattern such as + + abcd$ + +when applied to a long string which does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as + + ^.*abcd$ + +the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as + + ^(?>.*)(?<=abcd) + +there can be no backtracking for the .* item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. + +When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of a once-only subpattern is +the only way to avoid some failing matches taking a very long time indeed. +The pattern + + (\\D+|<\\d+>)*[!?] + +matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to + + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +it takes a long time before reporting failure. This is because the string can +be divided between the two repeats in a large number of ways, and all have to +be tried. (The example used [!?] rather than a single character at the end, +because both PCRE and Perl have an optimization that allows for fast failure +when a single character is used. They remember the last single character that +is required for a match, and fail early if it is not present in the string.) +If the pattern is changed to + + ((?>\\D+)|<\\d+>)*[!?] + +sequences of non-digits cannot be broken, and failure happens quickly. + + +.SH CONDITIONAL SUBPATTERNS +It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a previous capturing subpattern matched +or not. The two possible forms of conditional subpattern are + + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + +If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. + +There are two kinds of condition. If the text between the parentheses consists +of a sequence of digits, the condition is satisfied if the capturing subpattern +of that number has previously matched. The number must be greater than zero. +Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: + + ( \\( )? [^()]+ (?(1) \\) ) + +The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether the first set of parentheses matched +or not. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. + +If the condition is not a sequence of digits, it must be an assertion. This may +be a positive or negative lookahead or lookbehind assertion. Consider this +pattern, again containing non-significant white space, and with the two +alternatives on the second line: + + (?(?=[^a-z]*[a-z]) + \\d{2}-[a-z]{3}-\\d{2} | \\d{2}-\\d{2}-\\d{2} ) + +The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. + + +.SH COMMENTS +The sequence (?# marks the start of a comment which continues up to the next +closing parenthesis. Nested parentheses are not permitted. The characters +that make up a comment play no part in the pattern matching at all. + +If the PCRE_EXTENDED option is set, an unescaped # character outside a +character class introduces a comment that continues up to the next newline +character in the pattern. + + +.SH RECURSIVE PATTERNS +Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. Perl 5.6 has provided an +experimental facility that allows regular expressions to recurse (amongst other +things). It does this by interpolating Perl code in the expression at run time, +and the code can refer to the expression itself. A Perl pattern to solve the +parentheses problem can be created like this: + + $re = qr{\\( (?: (?>[^()]+) | (?p{$re}) )* \\)}x; + +The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. Obviously, PCRE cannot support +the interpolation of Perl code. Instead, the special item (?R) is provided for +the specific case of recursion. This PCRE pattern solves the parentheses +problem (assume the PCRE_EXTENDED option is set so that white space is +ignored): + + \\( ( (?>[^()]+) | (?R) )* \\) + +First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (i.e. a correctly parenthesized substring). Finally +there is a closing parenthesis. + +This particular example pattern contains nested unlimited repeats, and so the +use of a once-only subpattern for matching strings of non-parentheses is +important when applying the pattern to strings that do not match. For example, +when it is applied to + + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() + +it yields "no match" quickly. However, if a once-only subpattern is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. + +The values set for any capturing subpatterns are those from the outermost level +of the recursion at which the subpattern value is set. If the pattern above is +matched against + + (ab(cd)ef) + +the value for the capturing parentheses is "ef", which is the last value taken +on at the top level. If additional parentheses are added, giving + + \\( ( ( (?>[^()]+) | (?R) )* ) \\) + ^ ^ + ^ ^ +the string they capture is "ab(cd)ef", the contents of the top level +parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE +has to obtain extra memory to store data during a recursion, which it does by +using \fBpcre_malloc\fR, freeing it via \fBpcre_free\fR afterwards. If no +memory can be obtained, it saves data for the first 15 capturing parentheses +only, as there is no way to give an out-of-memory error from within a +recursion. + + +.SH PERFORMANCE +Certain items that may appear in patterns are more efficient than others. It is +more efficient to use a character class like [aeiou] than a set of alternatives +such as (a|e|i|o|u). In general, the simplest construction that provides the +required behaviour is usually the most efficient. Jeffrey Friedl's book +contains a lot of discussion about optimizing regular expressions for efficient +performance. + +When a pattern begins with .* and the PCRE_DOTALL option is set, the pattern is +implicitly anchored by PCRE, since it can match only at the start of a subject +string. However, if PCRE_DOTALL is not set, PCRE cannot make this optimization, +because the . metacharacter does not then match a newline, and if the subject +string contains newlines, the pattern may match from the character immediately +following one of them instead of from the very start. For example, the pattern + + (.*) second + +matches the subject "first\\nand second" (where \\n stands for a newline +character) with the first captured substring being "and". In order to do this, +PCRE has to retry the match starting after every newline in the subject. + +If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* to indicate explicit anchoring. That saves PCRE from +having to scan along the subject looking for a newline to restart at. + +Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment + + (a+)* + +This can match "aaaa" in 33 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time. + +An optimization catches some of the more simple cases such as + + (a+)*b + +where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of + + (a+)*\\d + +with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. + + +.SH UTF-8 SUPPORT +Starting at release 3.3, PCRE has some support for character strings encoded +in the UTF-8 format. This is incomplete, and is regarded as experimental. In +order to use it, you must configure PCRE to include UTF-8 support in the code, +and, in addition, you must call \fBpcre_compile()\fR with the PCRE_UTF8 option +flag. When you do this, both the pattern and any subject strings that are +matched against it are treated as UTF-8 strings instead of just strings of +bytes, but only in the cases that are mentioned below. + +If you compile PCRE with UTF-8 support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF8 flag in several places, so should not be very large. + +PCRE assumes that the strings it is given contain valid UTF-8 codes. It does +not diagnose invalid UTF-8 strings. If you pass invalid UTF-8 strings to PCRE, +the results are undefined. + +Running with PCRE_UTF8 set causes these changes in the way PCRE works: + +1. In a pattern, the escape sequence \\x{...}, where the contents of the braces +is a string of hexadecimal digits, is interpreted as a UTF-8 character whose +code number is the given hexadecimal number, for example: \\x{1234}. This +inserts from one to six literal bytes into the pattern, using the UTF-8 +encoding. If a non-hexadecimal digit appears between the braces, the item is +not recognized. + +2. The original hexadecimal escape sequence, \\xhh, generates a two-byte UTF-8 +character if its value is greater than 127. + +3. Repeat quantifiers are NOT correctly handled if they follow a multibyte +character. For example, \\x{100}* and \\xc3+ do not work. If you want to +repeat such characters, you must enclose them in non-capturing parentheses, +for example (?:\\x{100}), at present. + +4. The dot metacharacter matches one UTF-8 character instead of a single byte. + +5. Unlike literal UTF-8 characters, the dot metacharacter followed by a +repeat quantifier does operate correctly on UTF-8 characters instead of +single bytes. + +4. Although the \\x{...} escape is permitted in a character class, characters +whose values are greater than 255 cannot be included in a class. + +5. A class is matched against a UTF-8 character instead of just a single byte, +but it can match only characters whose values are less than 256. Characters +with greater values always fail to match a class. + +6. Repeated classes work correctly on multiple characters. + +7. Classes containing just a single character whose value is greater than 127 +(but less than 256), for example, [\\x80] or [^\\x{93}], do not work because +these are optimized into single byte matches. In the first case, of course, +the class brackets are just redundant. + +8. Lookbehind assertions move backwards in the subject by a fixed number of +characters instead of a fixed number of bytes. Simple cases have been tested +to work correctly, but there may be hidden gotchas herein. + +9. The character types such as \\d and \\w do not work correctly with UTF-8 +characters. They continue to test a single byte. + +10. Anything not explicitly mentioned here continues to work in bytes rather +than in characters. + +The following UTF-8 features of Perl 5.6 are not implemented: + +1. The escape sequence \\C to match a single byte. + +2. The use of Unicode tables and properties and escapes \\p, \\P, and \\X. + +.SH AUTHOR +Philip Hazel +.br +University Computing Service, +.br +New Museums Site, +.br +Cambridge CB2 3QG, England. +.br +Phone: +44 1223 334714 + +Last updated: 28 August 2000, +.br + the 250th anniversary of the death of J.S. Bach. +.br +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcre.html b/pcre/doc/pcre.html new file mode 100644 index 00000000..b12b2126 --- /dev/null +++ b/pcre/doc/pcre.html @@ -0,0 +1,2397 @@ + + +pcre specification + + +

pcre specification

+This HTML document has been generated automatically from the original man page. +If there is any nonsense in it, please consult the man page in case the +conversion went wrong. + +
  • NAME +

    +pcre - Perl-compatible regular expressions. +

    +
  • SYNOPSIS +

    +#include <pcre.h> +

    +

    +pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

    +

    +pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +

    +

    +int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +

    +

    +int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +

    +

    +int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +

    +

    +int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +

    +

    +void pcre_free_substring(const char *stringptr); +

    +

    +void pcre_free_substring_list(const char **stringptr); +

    +

    +const unsigned char *pcre_maketables(void); +

    +

    +int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +

    +

    +int pcre_info(const pcre *code, int *optptr, int +*firstcharptr); +

    +

    +char *pcre_version(void); +

    +

    +void *(*pcre_malloc)(size_t); +

    +

    +void (*pcre_free)(void *); +

    +
  • DESCRIPTION +

    +The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl 5, with just a few +differences (see below). The current implementation corresponds to Perl 5.005, +with some additional features from later versions. This includes some +experimental, incomplete support for UTF-8 encoded strings. Details of exactly +what is and what is not supported are given below. +

    +

    +PCRE has its own native API, which is described in this document. There is also +a set of wrapper functions that correspond to the POSIX regular expression API. +These are described in the pcreposix documentation. +

    +

    +The native API function prototypes are defined in the header file pcre.h, +and on Unix systems the library itself is called libpcre.a, so can be +accessed by adding -lpcre to the command for linking an application which +calls it. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to +contain the major and minor release numbers for the library. Applications can +use these to include support for different releases. +

    +

    +The functions pcre_compile(), pcre_study(), and pcre_exec() +are used for compiling and matching regular expressions. +

    +

    +The functions pcre_copy_substring(), pcre_get_substring(), and +pcre_get_substring_list() are convenience functions for extracting +captured substrings from a matched subject string; pcre_free_substring() +and pcre_free_substring_list() are also provided, to free the memory used +for extracted strings. +

    +

    +The function pcre_maketables() is used (optionally) to build a set of +character tables in the current locale for passing to pcre_compile(). +

    +

    +The function pcre_fullinfo() is used to find out information about a +compiled pattern; pcre_info() is an obsolete version which returns only +some of the available information, but is retained for backwards compatibility. +The function pcre_version() returns a pointer to a string containing the +version of PCRE and its date of release. +

    +

    +The global variables pcre_malloc and pcre_free initially contain +the entry points of the standard malloc() and free() functions +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +

    +
  • MULTI-THREADING +

    +The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by pcre_malloc +and pcre_free are shared by all threads. +

    +

    +The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +

    +
  • COMPILING A PATTERN +

    +The function pcre_compile() is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument pattern. A pointer to a single block of memory +that is obtained via pcre_malloc is returned. This contains the +compiled code and related data. The pcre type is defined for this for +convenience, but in fact pcre is just a typedef for void, since the +contents of the block are not externally defined. It is up to the caller to +free the memory when it is no longer required. +

    +

    +The size of a compiled pattern is roughly proportional to the length of the +pattern string, except that each character class (other than those containing +just a single character, negated or not) requires 33 bytes, and repeat +quantifiers with a minimum greater than one or a bounded maximum cause the +relevant portions of the compiled pattern to be replicated. +

    +

    +The options argument contains independent bits that affect the +compilation. It should be zero if no options are required. Some of the options, +in particular, those that are compatible with Perl, can also be set and unset +from within the pattern (see the detailed description of regular expressions +below). For these options, the contents of the options argument specifies +their initial settings at the start of compilation and execution. The +PCRE_ANCHORED option can be set at the time of matching as well as at compile +time. +

    +

    +If errptr is NULL, pcre_compile() returns NULL immediately. +Otherwise, if compilation of a pattern fails, pcre_compile() returns +NULL, and sets the variable pointed to by errptr to point to a textual +error message. The offset from the start of the pattern to the character where +the error was discovered is placed in the variable pointed to by +erroffset, which must not be NULL. If it is, an immediate error is given. +

    +

    +If the final argument, tableptr, is NULL, PCRE uses a default set of +character tables which are built when it is compiled, using the default C +locale. Otherwise, tableptr must be the result of a call to +pcre_maketables(). See the section on locale support below. +

    +

    +The following option bits are defined in the header file: +

    +

    +

    +  PCRE_ANCHORED
+
    +

    +

    +If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the start of the string which is being searched +(the "subject string"). This effect can also be achieved by appropriate +constructs in the pattern itself, which is the only way to do it in Perl. +

    +

    +

    +  PCRE_CASELESS
+
    +

    +

    +If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option. +

    +

    +

    +  PCRE_DOLLAR_ENDONLY
+
    +

    +

    +If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before the final character if it is a newline (but not before any +other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is +set. There is no equivalent to this option in Perl. +

    +

    +

    +  PCRE_DOTALL
+
    +

    +

    +If this bit is set, a dot metacharater in the pattern matches all characters, +including newlines. Without it, newlines are excluded. This option is +equivalent to Perl's /s option. A negative class such as [^a] always matches a +newline character, independent of the setting of this option. +

    +

    +

    +  PCRE_EXTENDED
+
    +

    +

    +If this bit is set, whitespace data characters in the pattern are totally +ignored except when escaped or inside a character class, and characters between +an unescaped # outside a character class and the next newline character, +inclusive, are also ignored. This is equivalent to Perl's /x option, and makes +it possible to include comments inside complicated patterns. Note, however, +that this applies only to data characters. Whitespace characters may never +appear within special character sequences in a pattern, for example within the +sequence (?( which introduces a conditional subpattern. +

    +

    +

    +  PCRE_EXTRA
+
    +

    +

    +This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. There are at present no other features +controlled by this option. It can also be set by a (?X) option setting within a +pattern. +

    +

    +

    +  PCRE_MULTILINE
+
    +

    +

    +By default, PCRE treats the subject string as consisting of a single "line" of +characters (even if it actually contains several newlines). The "start of line" +metacharacter (^) matches only at the start of the string, while the "end of +line" metacharacter ($) matches only at the end of the string, or before a +terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as +Perl. +

    +

    +When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before any newline in the subject +string, respectively, as well as at the very start and end. This is equivalent +to Perl's /m option. If there are no "\n" characters in a subject string, or +no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no +effect. +

    +

    +

    +  PCRE_UNGREEDY
+
    +

    +

    +This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +

    +

    +

    +  PCRE_UTF8
+
    +

    +

    +This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of just byte strings. However, it is available only +if PCRE has been built to include UTF-8 support. If not, the use of this option +provokes an error. Support for UTF-8 is new, experimental, and incomplete. +Details of exactly what it entails are given below. +

    +
  • STUDYING A PATTERN +

    +When a pattern is going to be used several times, it is worth spending more +time analyzing it in order to speed up the time taken for matching. The +function pcre_study() takes a pointer to a compiled pattern as its first +argument, and returns a pointer to a pcre_extra block (another void +typedef) containing additional information about the pattern; this can be +passed to pcre_exec(). If no additional information is available, NULL +is returned. +

    +

    +The second argument contains option bits. At present, no options are defined +for pcre_study(), and this argument should always be zero. +

    +

    +The third argument for pcre_study() is a pointer to an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it points to a textual error message. +

    +

    +At present, studying a pattern is useful only for non-anchored patterns that do +not have a single fixed starting character. A bitmap of possible starting +characters is created. +

    +
  • LOCALE SUPPORT +

    +PCRE handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables. The library contains a +default set of tables which is created in the default C locale when PCRE is +compiled. This is used when the final argument of pcre_compile() is NULL, +and is sufficient for many applications. +

    +

    +An alternative set of tables can, however, be supplied. Such tables are built +by calling the pcre_maketables() function, which has no arguments, in the +relevant locale. The result can then be passed to pcre_compile() as often +as necessary. For example, to build and use tables that are appropriate for the +French locale (where accented characters with codes greater than 128 are +treated as letters), the following code could be used: +

    +

    +

    +  setlocale(LC_CTYPE, "fr");
+  tables = pcre_maketables();
+  re = pcre_compile(..., tables);
+
    +

    +

    +The tables are built in memory that is obtained via pcre_malloc. The +pointer that is passed to pcre_compile is saved with the compiled +pattern, and the same tables are used via this pointer by pcre_study() +and pcre_exec(). Thus for any single pattern, compilation, studying and +matching all happen in the same locale, but different patterns can be compiled +in different locales. It is the caller's responsibility to ensure that the +memory containing the tables remains available for as long as it is needed. +

    +
  • INFORMATION ABOUT A PATTERN +

    +The pcre_fullinfo() function returns information about a compiled +pattern. It replaces the obsolete pcre_info() function, which is +nevertheless retained for backwards compability (and is documented below). +

    +

    +The first argument for pcre_fullinfo() is a pointer to the compiled +pattern. The second argument is the result of pcre_study(), or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, while the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +

    +

    +

    +  PCRE_ERROR_NULL       the argument code was NULL
+                        the argument where was NULL
+  PCRE_ERROR_BADMAGIC   the "magic number" was not found
+  PCRE_ERROR_BADOPTION  the value of what was invalid
+
    +

    +

    +The possible values for the third argument are defined in pcre.h, and are +as follows: +

    +

    +

    +  PCRE_INFO_OPTIONS
+
    +

    +

    +Return a copy of the options with which the pattern was compiled. The fourth +argument should point to au unsigned long int variable. These option bits +are those specified in the call to pcre_compile(), modified by any +top-level option settings within the pattern itself, and with the PCRE_ANCHORED +bit forcibly set if the form of the pattern implies that it can match only at +the start of a subject string. +

    +

    +

    +  PCRE_INFO_SIZE
+
    +

    +

    +Return the size of the compiled pattern, that is, the value that was passed as +the argument to pcre_malloc() when PCRE was getting memory in which to +place the compiled data. The fourth argument should point to a size_t +variable. +

    +

    +

    +  PCRE_INFO_CAPTURECOUNT
+
    +

    +

    +Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an \fbint\fR variable. +

    +

    +

    +  PCRE_INFO_BACKREFMAX
+
    +

    +

    +Return the number of the highest back reference in the pattern. The fourth +argument should point to an int variable. Zero is returned if there are +no back references. +

    +

    +

    +  PCRE_INFO_FIRSTCHAR
+
    +

    +

    +Return information about the first character of any matched string, for a +non-anchored pattern. If there is a fixed first character, e.g. from a pattern +such as (cat|cow|coyote), it is returned in the integer pointed to by +where. Otherwise, if either +

    +

    +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +

    +

    +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +

    +

    +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any "\n" within the string. Otherwise -2 is returned. +For anchored patterns, -2 is returned. +

    +

    +

    +  PCRE_INFO_FIRSTTABLE
+
    +

    +

    +If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of characters for the first character in any +matching string, a pointer to the table is returned. Otherwise NULL is +returned. The fourth argument should point to an unsigned char * +variable. +

    +

    +

    +  PCRE_INFO_LASTLITERAL
+
    +

    +

    +For a non-anchored pattern, return the value of the rightmost literal character +which must exist in any matched string, other than at its start. The fourth +argument should point to an int variable. If there is no such character, +or if the pattern is anchored, -1 is returned. For example, for the pattern +/a\d+z\d+/ the returned value is 'z'. +

    +

    +The pcre_info() function is now obsolete because its interface is too +restrictive to return all the available data about a compiled pattern. New +programs should use pcre_fullinfo() instead. The yield of +pcre_info() is the number of capturing subpatterns, or one of the +following negative numbers: +

    +

    +

    +  PCRE_ERROR_NULL       the argument code was NULL
+  PCRE_ERROR_BADMAGIC   the "magic number" was not found
+
    +

    +

    +If the optptr argument is not NULL, a copy of the options with which the +pattern was compiled is placed in the integer it points to (see +PCRE_INFO_OPTIONS above). +

    +

    +If the pattern is not anchored and the firstcharptr argument is not NULL, +it is used to pass back information about the first character of any matched +string (see PCRE_INFO_FIRSTCHAR above). +

    +
  • MATCHING A PATTERN +

    +The function pcre_exec() is called to match a subject string against a +pre-compiled pattern, which is passed in the code argument. If the +pattern has been studied, the result of the study should be passed in the +extra argument. Otherwise this must be NULL. +

    +

    +The PCRE_ANCHORED option can be passed in the options argument, whose +unused bits must be zero. However, if a pattern was compiled with +PCRE_ANCHORED, or turned out to be anchored by virtue of its contents, it +cannot be made unachored at matching time. +

    +

    +There are also three further options that can be set only at matching time: +

    +

    +

    +  PCRE_NOTBOL
+
    +

    +

    +The first character of the string is not the beginning of a line, so the +circumflex metacharacter should not match before it. Setting this without +PCRE_MULTILINE (at compile time) causes circumflex never to match. +

    +

    +

    +  PCRE_NOTEOL
+
    +

    +

    +The end of the string is not the end of a line, so the dollar metacharacter +should not match it nor (except in multiline mode) a newline immediately before +it. Setting this without PCRE_MULTILINE (at compile time) causes dollar never +to match. +

    +

    +

    +  PCRE_NOTEMPTY
+
    +

    +

    +An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +

    +

    +

    +  a?b?
+
    +

    +

    +is applied to a string not beginning with "a" or "b", it matches the empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +

    +

    +Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case +of a pattern match of the empty string within its split() function, and +when using the /g modifier. It is possible to emulate Perl's behaviour after +matching a null string by first trying the match again at the same offset with +PCRE_NOTEMPTY set, and then if that fails by advancing the starting offset (see +below) and trying an ordinary match again. +

    +

    +The subject string is passed as a pointer in subject, a length in +length, and a starting offset in startoffset. Unlike the pattern +string, it may contain binary zero characters. When the starting offset is +zero, the search for a match starts at the beginning of the subject, and this +is by far the most common case. +

    +

    +A non-zero starting offset is useful when searching for another match in the +same subject by calling pcre_exec() again after a previous success. +Setting startoffset differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +

    +

    +

    +  \Biss\B
+
    +

    +

    +which finds occurrences of "iss" in the middle of words. (\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to pcre_exec() finds the first +occurrence. If pcre_exec() is called again with just the remainder of the +subject, namely "issipi", it does not match, because \B is always false at the +start of the subject, which is deemed to be a word boundary. However, if +pcre_exec() is passed the entire string again, but with startoffset +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. +

    +

    +If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is tried. This can only succeed if the +pattern does not require the match to be at the start of the subject. +

    +

    +In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +

    +

    +Captured substrings are returned to the caller via a vector of integer offsets +whose address is passed in ovector. The number of elements in the vector +is passed in ovecsize. The first two-thirds of the vector is used to pass +back captured substrings, each substring using a pair of integers. The +remaining third of the vector is used as workspace by pcre_exec() while +matching capturing subpatterns, and is not available for passing back +information. The length passed in ovecsize should always be a multiple of +three. If it is not, it is rounded down. +

    +

    +When a match has been successful, information about captured substrings is +returned in pairs of integers, starting at the beginning of ovector, and +continuing up to two-thirds of its length at the most. The first element of a +pair is set to the offset of the first character in a substring, and the second +is set to the offset of the first character after the end of a substring. The +first pair, ovector[0] and ovector[1], identify the portion of the +subject string matched by the entire pattern. The next pair is used for the +first capturing subpattern, and so on. The value returned by pcre_exec() +is the number of pairs that have been set. If there are no capturing +subpatterns, the return value from a successful match is 1, indicating that +just the first pair of offsets has been set. +

    +

    +Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described in the following section. +

    +

    +It is possible for an capturing subpattern number n+1 to match some +part of the subject when subpattern n has not been used at all. For +example, if the string "abc" is matched against the pattern (a|(z))(bc) +subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset +values corresponding to the unused subpattern are set to -1. +

    +

    +If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that gets returned. +

    +

    +If the vector is too small to hold all the captured substrings, it is used as +far as possible (up to two-thirds of its length), and the function returns a +value of zero. In particular, if the substring offsets are not of interest, +pcre_exec() may be called with ovector passed as NULL and +ovecsize as zero. However, if the pattern contains back references and +the ovector isn't big enough to remember the related substrings, PCRE has +to get additional memory for use during matching. Thus it is usually advisable +to supply an ovector. +

    +

    +Note that pcre_info() can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +ovector that will allow for n captured substrings in addition to +the offsets of the substring matched by the whole pattern is (n+1)*3. +

    +

    +If pcre_exec() fails, it returns a negative number. The following are +defined in the header file: +

    +

    +

    +  PCRE_ERROR_NOMATCH        (-1)
+
    +

    +

    +The subject string did not match the pattern. +

    +

    +

    +  PCRE_ERROR_NULL           (-2)
+
    +

    +

    +Either code or subject was passed as NULL, or ovector was +NULL and ovecsize was not zero. +

    +

    +

    +  PCRE_ERROR_BADOPTION      (-3)
+
    +

    +

    +An unrecognized bit was set in the options argument. +

    +

    +

    +  PCRE_ERROR_BADMAGIC       (-4)
+
    +

    +

    +PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer. This is the error it gives when the +magic number isn't present. +

    +

    +

    +  PCRE_ERROR_UNKNOWN_NODE   (-5)
+
    +

    +

    +While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +

    +

    +

    +  PCRE_ERROR_NOMEMORY       (-6)
+
    +

    +

    +If a pattern contains back references, but the ovector that is passed to +pcre_exec() is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via pcre_malloc() fails, this error is given. The memory is freed at +the end of matching. +

    +
  • EXTRACTING CAPTURED SUBSTRINGS +

    +Captured substrings can be accessed directly by using the offsets returned by +pcre_exec() in ovector. For convenience, the functions +pcre_copy_substring(), pcre_get_substring(), and +pcre_get_substring_list() are provided for extracting captured substrings +as new, separate, zero-terminated strings. A substring that contains a binary +zero is correctly extracted and has a further zero added on the end, but the +result does not, of course, function as a C string. +

    +

    +The first three arguments are the same for all three functions: subject +is the subject string which has just been successfully matched, ovector +is a pointer to the vector of integer offsets that was passed to +pcre_exec(), and stringcount is the number of substrings that +were captured by the match, including the substring that matched the entire +regular expression. This is the value returned by pcre_exec if it +is greater than zero. If pcre_exec() returned zero, indicating that it +ran out of space in ovector, the value passed as stringcount should +be the size of the vector divided by three. +

    +

    +The functions pcre_copy_substring() and pcre_get_substring() +extract a single substring, whose number is given as stringnumber. A +value of zero extracts the substring that matched the entire pattern, while +higher values extract the captured substrings. For pcre_copy_substring(), +the string is placed in buffer, whose length is given by +buffersize, while for pcre_get_substring() a new block of memory is +obtained via pcre_malloc, and its address is returned via +stringptr. The yield of the function is the length of the string, not +including the terminating zero, or one of +

    +

    +

    +  PCRE_ERROR_NOMEMORY       (-6)
+
    +

    +

    +The buffer was too small for pcre_copy_substring(), or the attempt to get +memory failed for pcre_get_substring(). +

    +

    +

    +  PCRE_ERROR_NOSUBSTRING    (-7)
+
    +

    +

    +There is no substring whose number is stringnumber. +

    +

    +The pcre_get_substring_list() function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory which is obtained via pcre_malloc. The address of the memory block +is returned via listptr, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or +

    +

    +

    +  PCRE_ERROR_NOMEMORY       (-6)
+
    +

    +

    +if the attempt to get the memory block failed. +

    +

    +When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number n+1 matches some part of the +subject, but subpattern n has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in ovector, which is negative for unset +substrings. +

    +

    +The two convenience functions pcre_free_substring() and +pcre_free_substring_list() can be used to free the memory returned by +a previous call of pcre_get_substring() or +pcre_get_substring_list(), respectively. They do nothing more than call +the function pointed to by pcre_free, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language which cannot use +pcre_free directly; it is for these cases that the functions are +provided. +

    +
  • LIMITATIONS +

    +There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +The maximum length of a compiled pattern is 65539 (sic) bytes. +All values in repeating quantifiers must be less than 65536. +The maximum number of capturing subpatterns is 99. +The maximum number of all parenthesized subpatterns, including capturing +subpatterns, assertions, and other types of subpattern, is 200. +

    +

    +The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, PCRE uses recursion to handle subpatterns +and indefinite repetition. This means that the available stack space may limit +the size of a subject string that can be processed by certain patterns. +

    +
  • DIFFERENCES FROM PERL +

    +The differences described here are with respect to Perl 5.005. +

    +

    +1. By default, a whitespace character is any character that the C library +function isspace() recognizes, though it is possible to compile PCRE with +alternative character type tables. Normally isspace() matches space, +formfeed, newline, carriage return, horizontal tab, and vertical tab. Perl 5 +no longer includes vertical tab in its set of whitespace characters. The \v +escape that was in the Perl documentation for a long time was never in fact +recognized. However, the character itself was treated as whitespace at least +up to 5.002. In 5.004 and 5.005 it does not match \s. +

    +

    +2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits +them, but they do not mean what you might think. For example, (?!a){3} does +not assert that the next three characters are not "a". It just asserts that the +next character is not "a" three times. +

    +

    +3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sets its +numerical variables from any such patterns that are matched before the +assertion fails to match something (thereby succeeding), but only if the +negative lookahead assertion contains just one branch. +

    +

    +4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence "\0" can be used in the pattern to +represent a binary zero. +

    +

    +5. The following Perl escape sequences are not supported: \l, \u, \L, \U, +\E, \Q. In fact these are implemented by Perl's general string-handling and +are not part of its pattern matching engine. +

    +

    +6. The Perl \G assertion is not supported as it is not relevant to single +pattern matches. +

    +

    +7. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) +constructions. However, there is some experimental support for recursive +patterns using the non-Perl item (?R). +

    +

    +8. There are at the time of writing some oddities in Perl 5.005_02 concerned +with the settings of captured strings when part of a pattern is repeated. For +example, matching "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value +"b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 unset. However, if +the pattern is changed to /^(aa(b(b))?)+$/ then $2 (and $3) are set. +

    +

    +In Perl 5.004 $2 is set in both cases, and that is also true of PCRE. If in the +future Perl changes to a consistent state that is different, PCRE may change to +follow. +

    +

    +9. Another as yet unresolved discrepancy is that in Perl 5.005_02 the pattern +/^(a)?(?(1)a|b)+$/ matches the string "a", whereas in PCRE it does not. +However, in both Perl and PCRE /^(a)?a/ matched against "a" leaves $1 unset. +

    +

    +10. PCRE provides some extensions to the Perl regular expression facilities: +

    +

    +(a) Although lookbehind assertions must match fixed length strings, each +alternative branch of a lookbehind assertion can match a different length of +string. Perl 5.005 requires them all to have the same length. +

    +

    +(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta- +character matches only at the very end of the string. +

    +

    +(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. +

    +

    +(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +

    +

    +(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the start +of the subject. +

    +

    +(f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options for +pcre_exec() have no Perl equivalents. +

    +

    +(g) The (?R) construct allows for recursive pattern matching (Perl 5.6 can do +this using the (?p{code}) construct, which PCRE cannot of course support.) +

    +
  • REGULAR EXPRESSION DETAILS +

    +The syntax and semantics of the regular expressions supported by PCRE are +described below. Regular expressions are also described in the Perl +documentation and in a number of other books, some of which have copious +examples. Jeffrey Friedl's "Mastering Regular Expressions", published by +O'Reilly (ISBN 1-56592-257), covers them in great detail. +

    +

    +The description here is intended as reference documentation. The basic +operation of PCRE is on strings of bytes. However, there is the beginnings of +some support for UTF-8 character strings. To use this support you must +configure PCRE to include it, and then call pcre_compile() with the +PCRE_UTF8 option. How this affects the pattern matching is described in the +final section of this document. +

    +

    +A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +

    +

    +

    +  The quick brown fox
+
    +

    +

    +matches a portion of a subject string that is identical to itself. The power of +regular expressions comes from the ability to include alternatives and +repetitions in the pattern. These are encoded in the pattern by the use of +meta-characters, which do not stand for themselves but instead are +interpreted in some special way. +

    +

    +There are two different sets of meta-characters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized in square brackets. Outside square brackets, the meta-characters are +as follows: +

    +

    +

    +  \      general escape character with several uses
+  ^      assert start of subject (or line, in multiline mode)
+  $      assert end of subject (or line, in multiline mode)
+  .      match any character except newline (by default)
+  [      start character class definition
+  |      start of alternative branch
+  (      start subpattern
+  )      end subpattern
+  ?      extends the meaning of (
+         also 0 or 1 quantifier
+         also quantifier minimizer
+  *      0 or more quantifier
+  +      1 or more quantifier
+  {      start min/max quantifier
+
    +

    +

    +Part of a pattern that is in square brackets is called a "character class". In +a character class the only meta-characters are: +

    +

    +

    +  \      general escape character
+  ^      negate the class, but only if the first character
+  -      indicates character range
+  ]      terminates the character class
+
    +

    +

    +The following sections describe the use of each of the meta-characters. +

    +
  • BACKSLASH +

    +The backslash character has several uses. Firstly, if it is followed by a +non-alphameric character, it takes away any special meaning that character may +have. This use of backslash as an escape character applies both inside and +outside character classes. +

    +

    +For example, if you want to match a "*" character, you write "\*" in the +pattern. This applies whether or not the following character would otherwise be +interpreted as a meta-character, so it is always safe to precede a +non-alphameric with "\" to specify that it stands for itself. In particular, +if you want to match a backslash, you write "\\". +

    +

    +If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the +pattern (other than in a character class) and characters between a "#" outside +a character class and the next newline character are ignored. An escaping +backslash can be used to include a whitespace or "#" character as part of the +pattern. +

    +

    +A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is usually easier to +use one of the following escape sequences than the binary character it +represents: +

    +

    +

    +  \a     alarm, that is, the BEL character (hex 07)
+  \cx    "control-x", where x is any character
+  \e     escape (hex 1B)
+  \f     formfeed (hex 0C)
+  \n     newline (hex 0A)
+  \r     carriage return (hex 0D)
+  \t     tab (hex 09)
+  \xhh   character with hex code hh
+  \ddd   character with octal code ddd, or backreference
+
    +

    +

    +The precise effect of "\cx" is as follows: if "x" is a lower case letter, it +is converted to upper case. Then bit 6 of the character (hex 40) is inverted. +Thus "\cz" becomes hex 1A, but "\c{" becomes hex 3B, while "\c;" becomes hex +7B. +

    +

    +After "\x", up to two hexadecimal digits are read (letters can be in upper or +lower case). +

    +

    +After "\0" up to two further octal digits are read. In both cases, if there +are fewer than two digits, just those that are present are used. Thus the +sequence "\0\x\07" specifies two binary zeros followed by a BEL character. +Make sure you supply two digits after the initial zero if the character that +follows is itself an octal digit. +

    +

    +The handling of a backslash followed by a digit other than 0 is complicated. +Outside a character class, PCRE reads it and any following digits as a decimal +number. If the number is less than 10, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a back reference. A description of how this works is given +later, following the discussion of parenthesized subpatterns. +

    +

    +Inside a character class, or if the decimal number is greater than 9 and there +have not been that many capturing subpatterns, PCRE re-reads up to three octal +digits following the backslash, and generates a single byte from the least +significant 8 bits of the value. Any subsequent digits stand for themselves. +For example: +

    +

    +

    +  \040   is another way of writing a space
+  \40    is the same, provided there are fewer than 40
+            previous capturing subpatterns
+  \7     is always a back reference
+  \11    might be a back reference, or another way of
+            writing a tab
+  \011   is always a tab
+  \0113  is a tab followed by the character "3"
+  \113   is the character with octal code 113 (since there
+            can be no more than 99 back references)
+  \377   is a byte consisting entirely of 1 bits
+  \81    is either a back reference, or a binary zero
+            followed by the two characters "8" and "1"
+
    +

    +

    +Note that octal values of 100 or greater must not be introduced by a leading +zero, because no more than three octal digits are ever read. +

    +

    +All the sequences that define a single byte value can be used both inside and +outside character classes. In addition, inside a character class, the sequence +"\b" is interpreted as the backspace character (hex 08). Outside a character +class it has a different meaning (see below). +

    +

    +The third use of backslash is for specifying generic character types: +

    +

    +

    +  \d     any decimal digit
+  \D     any character that is not a decimal digit
+  \s     any whitespace character
+  \S     any character that is not a whitespace character
+  \w     any "word" character
+  \W     any "non-word" character
+
    +

    +

    +Each pair of escape sequences partitions the complete set of characters into +two disjoint sets. Any given character matches one, and only one, of each pair. +

    +

    +A "word" character is any letter or digit or the underscore character, that is, +any character which can be part of a Perl "word". The definition of letters and +digits is controlled by PCRE's character tables, and may vary if locale- +specific matching is taking place (see "Locale support" above). For example, in +the "fr" (French) locale, some character codes greater than 128 are used for +accented letters, and these are matched by \w. +

    +

    +These character type sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, since +there is no character to match. +

    +

    +The fourth use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described below. The backslashed +assertions are +

    +

    +

    +  \b     word boundary
+  \B     not a word boundary
+  \A     start of subject (independent of multiline mode)
+  \Z     end of subject or newline at end (independent of multiline mode)
+  \z     end of subject (independent of multiline mode)
+
    +

    +

    +These assertions may not appear in character classes (but note that "\b" has a +different meaning, namely the backspace character, inside a character class). +

    +

    +A word boundary is a position in the subject string where the current character +and the previous character do not both match \w or \W (i.e. one matches +\w and the other matches \W), or the start or end of the string if the +first or last character matches \w, respectively. +

    +

    +The \A, \Z, and \z assertions differ from the traditional circumflex and +dollar (described below) in that they only ever match at the very start and end +of the subject string, whatever options are set. They are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options. If the startoffset argument of +pcre_exec() is non-zero, \A can never match. The difference between \Z +and \z is that \Z matches before a newline that is the last character of the +string as well as at the end of the string, whereas \z matches only at the +end. +

    +
  • CIRCUMFLEX AND DOLLAR +

    +Outside a character class, in the default matching mode, the circumflex +character is an assertion which is true only if the current matching point is +at the start of the subject string. If the startoffset argument of +pcre_exec() is non-zero, circumflex can never match. Inside a character +class, circumflex has an entirely different meaning (see below). +

    +

    +Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +

    +

    +A dollar character is an assertion which is true only if the current matching +point is at the end of the subject string, or immediately before a newline +character that is the last character in the string (by default). Dollar need +not be the last character of the pattern if a number of alternatives are +involved, but it should be the last item in any branch in which it appears. +Dollar has no special meaning in a character class. +

    +

    +The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile or matching +time. This does not affect the \Z assertion. +

    +

    +The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, they match immediately +after and immediately before an internal "\n" character, respectively, in +addition to matching at the start and end of the subject string. For example, +the pattern /^abc$/ matches the subject string "def\nabc" in multiline mode, +but not otherwise. Consequently, patterns that are anchored in single line mode +because all branches start with "^" are not anchored in multiline mode, and a +match for circumflex is possible when the startoffset argument of +pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if +PCRE_MULTILINE is set. +

    +

    +Note that the sequences \A, \Z, and \z can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\A is it always anchored, whether PCRE_MULTILINE is set or not. +

    +
  • FULL STOP (PERIOD, DOT) +

    +Outside a character class, a dot in the pattern matches any one character in +the subject, including a non-printing character, but not (by default) newline. +If the PCRE_DOTALL option is set, dots match newlines as well. The handling of +dot is entirely independent of the handling of circumflex and dollar, the only +relationship being that they both involve newline characters. Dot has no +special meaning in a character class. +

    +
  • SQUARE BRACKETS +

    +An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special. If a +closing square bracket is required as a member of the class, it should be the +first data character in the class (after an initial circumflex, if present) or +escaped with a backslash. +

    +

    +A character class matches a single character in the subject; the character must +be in the set of characters defined by the class, unless the first character in +the class is a circumflex, in which case the subject character must not be in +the set defined by the class. If a circumflex is actually required as a member +of the class, ensure it is not the first character, or escape it with a +backslash. +

    +

    +For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters which +are in the class by enumerating those that are not. It is not an assertion: it +still consumes a character from the subject string, and fails if the current +pointer is at the end of the string. +

    +

    +When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. +

    +

    +The newline character is never treated in any special way in character classes, +whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class +such as [^a] will always match a newline. +

    +

    +The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class. +

    +

    +It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\]46] is interpreted as a single class containing a +range followed by two separate characters. The octal or hexadecimal +representation of "]" can also be used to end a range. +

    +

    +Ranges operate in ASCII collating sequence. They can also be used for +characters specified numerically, for example [\000-\037]. If a range that +includes letters is used when caseless matching is set, it matches the letters +in either case. For example, [W-c] is equivalent to [][\^_`wxyzabc], matched +caselessly, and if character tables for the "fr" locale are in use, +[\xc8-\xcb] matches accented E characters in both cases. +

    +

    +The character types \d, \D, \s, \S, \w, and \W may also appear in a +character class, and add the characters that they match to the class. For +example, [\dABCDEF] matches any hexadecimal digit. A circumflex can +conveniently be used with the upper case character types to specify a more +restricted set of characters than the matching lower case type. For example, +the class [^\W_] matches any letter or digit, but not underscore. +

    +

    +All non-alphameric characters other than \, -, ^ (at the start) and the +terminating ] are non-special in character classes, but it does no harm if they +are escaped. +

    +
  • POSIX CHARACTER CLASSES +

    +Perl 5.6 (not yet released at the time of writing) is going to support the +POSIX notation for character classes, which uses names enclosed by [: and :] +within the enclosing square brackets. PCRE supports this notation. For example, +

    +

    +

    +  [01[:alpha:]%]
+
    +

    +

    +matches "0", "1", any alphabetic character, or "%". The supported class names +are +

    +

    +

    +  alnum    letters and digits
+  alpha    letters
+  ascii    character codes 0 - 127
+  cntrl    control characters
+  digit    decimal digits (same as \d)
+  graph    printing characters, excluding space
+  lower    lower case letters
+  print    printing characters, including space
+  punct    printing characters, excluding letters and digits
+  space    white space (same as \s)
+  upper    upper case letters
+  word     "word" characters (same as \w)
+  xdigit   hexadecimal digits
+
    +

    +

    +The names "ascii" and "word" are Perl extensions. Another Perl extension is +negation, which is indicated by a ^ character after the colon. For example, +

    +

    +

    +  [12[:^digit:]]
+
    +

    +

    +matches "1", "2", or any non-digit. PCRE (and Perl) also recogize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. +

    +
  • VERTICAL BAR +

    +Vertical bar characters are used to separate alternative patterns. For example, +the pattern +

    +

    +

    +  gilbert|sullivan
+
    +

    +

    +matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). +The matching process tries each alternative in turn, from left to right, +and the first one that succeeds is used. If the alternatives are within a +subpattern (defined below), "succeeds" means matching the rest of the main +pattern as well as the alternative in the subpattern. +

    +
  • INTERNAL OPTION SETTING +

    +The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and PCRE_EXTENDED +can be changed from within the pattern by a sequence of Perl option letters +enclosed between "(?" and ")". The option letters are +

    +

    +

    +  i  for PCRE_CASELESS
+  m  for PCRE_MULTILINE
+  s  for PCRE_DOTALL
+  x  for PCRE_EXTENDED
+
    +

    +

    +For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. +

    +

    +The scope of these option changes depends on where in the pattern the setting +occurs. For settings that are outside any subpattern (defined below), the +effect is the same as if the options were set or unset at the start of +matching. The following patterns all behave in exactly the same way: +

    +

    +

    +  (?i)abc
+  a(?i)bc
+  ab(?i)c
+  abc(?i)
+
    +

    +

    +which in turn is the same as compiling the pattern abc with PCRE_CASELESS set. +In other words, such "top level" settings apply to the whole pattern (unless +there are other changes inside subpatterns). If there is more than one setting +of the same option at top level, the rightmost setting is used. +

    +

    +If an option change occurs inside a subpattern, the effect is different. This +is a change of behaviour in Perl 5.005. An option change inside a subpattern +affects only that part of the subpattern that follows it, so +

    +

    +

    +  (a(?i)b)c
+
    +

    +

    +matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +

    +

    +

    +  (a(?i)b|c)
+
    +

    +

    +matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. +

    +

    +The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the +same way as the Perl-compatible options by using the characters U and X +respectively. The (?X) flag setting is special in that it must always occur +earlier in the pattern than any of the additional features it turns on, even +when it is at top level. It is best put at the start. +

    +
  • SUBPATTERNS +

    +Subpatterns are delimited by parentheses (round brackets), which can be nested. +Marking part of a pattern as a subpattern does two things: +

    +

    +1. It localizes a set of alternatives. For example, the pattern +

    +

    +

    +  cat(aract|erpillar|)
+
    +

    +

    +matches one of the words "cat", "cataract", or "caterpillar". Without the +parentheses, it would match "cataract", "erpillar" or the empty string. +

    +

    +2. It sets up the subpattern as a capturing subpattern (as defined above). +When the whole pattern matches, that portion of the subject string that matched +the subpattern is passed back to the caller via the ovector argument of +pcre_exec(). Opening parentheses are counted from left to right (starting +from 1) to obtain the numbers of the capturing subpatterns. +

    +

    +For example, if the string "the red king" is matched against the pattern +

    +

    +

    +  the ((red|white) (king|queen))
+
    +

    +

    +the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3. +

    +

    +The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by "?:", the +subpattern does not do any capturing, and is not counted when computing the +number of any subsequent capturing subpatterns. For example, if the string "the +white queen" is matched against the pattern +

    +

    +

    +  the ((?:red|white) (king|queen))
+
    +

    +

    +the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of captured substrings is 99, and the maximum number of +all subpatterns, both capturing and non-capturing, is 200. +

    +

    +As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +

    +

    +

    +  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+
    +

    +

    +match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". +

    +
  • REPETITION +

    +Repetition is specified by quantifiers, which can follow any of the following +items: +

    +

    +

    +  a single character, possibly escaped
+  the . metacharacter
+  a character class
+  a back reference (see next section)
+  a parenthesized subpattern (unless it is an assertion - see below)
+
    +

    +

    +The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +

    +

    +

    +  z{2,4}
+
    +

    +

    +matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus +

    +

    +

    +  [aeiou]{3,}
+
    +

    +

    +matches at least 3 successive vowels, but may match many more, while +

    +

    +

    +  \d{8}
+
    +

    +

    +matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. +

    +

    +The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. +

    +

    +For convenience (and historical compatibility) the three most common +quantifiers have single-character abbreviations: +

    +

    +

    +  *    is equivalent to {0,}
+  +    is equivalent to {1,}
+  ?    is equivalent to {0,1}
+
    +

    +

    +It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: +

    +

    +

    +  (a?)*
+
    +

    +

    +Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. +

    +

    +By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between the +sequences /* and */ and within the sequence, individual * and / characters may +appear. An attempt to match C comments by applying the pattern +

    +

    +

    +  /\*.*\*/
+
    +

    +

    +to the string +

    +

    +

    +  /* first command */  not comment  /* second comment */
+
    +

    +

    +fails, because it matches the entire string owing to the greediness of the .* +item. +

    +

    +However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +

    +

    +

    +  /\*.*?\*/
+
    +

    +

    +does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +

    +

    +

    +  \d??\d
+
    +

    +

    +which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. +

    +

    +If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +

    +

    +When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more store is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +

    +

    +If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE treats such a pattern as +though it were preceded by \A. In cases where it is known that the subject +string contains no newlines, it is worth setting PCRE_DOTALL when the pattern +begins with .* in order to obtain this optimization, or alternatively using ^ +to indicate anchoring explicitly. +

    +

    +When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +

    +

    +

    +  (tweedle[dume]{3}\s*)+
+
    +

    +

    +has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after +

    +

    +

    +  /(a|(b))+/
+
    +

    +

    +matches "aba" the value of the second captured substring is "b". +

    +
  • BACK REFERENCES +

    +Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(i.e. to its left) in the pattern, provided there have been that many previous +capturing left parentheses. +

    +

    +However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. See the section entitled "Backslash" above for further +details of the handling of digits following a backslash. +

    +

    +A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself. So the pattern +

    +

    +

    +  (sens|respons)e and \1ibility
+
    +

    +

    +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +

    +

    +

    +  ((?i)rah)\s+\1
+
    +

    +

    +matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. +

    +

    +There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail. For example, the pattern +

    +

    +

    +  (a|(bc))\2
+
    +

    +

    +always fails if it starts to match "a" rather than "bc". Because there may be +up to 99 back references, all digits following the backslash are taken +as part of a potential back reference number. If the pattern continues with a +digit character, some delimiter must be used to terminate the back reference. +If the PCRE_EXTENDED option is set, this can be whitespace. Otherwise an empty +comment can be used. +

    +

    +A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +

    +

    +

    +  (a|b\1)+
+
    +

    +

    +matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. +

    +
  • ASSERTIONS +

    +An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \b, \B, \A, \Z, \z, ^ and $ are described above. More +complicated assertions are coded as subpatterns. There are two kinds: those +that look ahead of the current position in the subject string, and those that +look behind it. +

    +

    +An assertion subpattern is matched in the normal way, except that it does not +cause the current matching position to be changed. Lookahead assertions start +with (?= for positive assertions and (?! for negative assertions. For example, +

    +

    +

    +  \w+(?=;)
+
    +

    +

    +matches a word followed by a semicolon, but does not include the semicolon in +the match, and +

    +

    +

    +  foo(?!bar)
+
    +

    +

    +matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +

    +

    +

    +  (?!foo)bar
+
    +

    +

    +does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve this effect. +

    +

    +Lookbehind assertions start with (?<= for positive assertions and (?<! for +negative assertions. For example, +

    +

    +

    +  (?<!foo)bar
+
    +

    +

    +does find an occurrence of "bar" that is not preceded by "foo". The contents of +a lookbehind assertion are restricted such that all the strings it matches must +have a fixed length. However, if there are several alternatives, they do not +all have to have the same fixed length. Thus +

    +

    +

    +  (?<=bullock|donkey)
+
    +

    +

    +is permitted, but +

    +

    +

    +  (?<!dogs?|cats?)
+
    +

    +

    +causes an error at compile time. Branches that match different length strings +are permitted only at the top level of a lookbehind assertion. This is an +extension compared with Perl 5.005, which requires all branches to match the +same length of string. An assertion such as +

    +

    +

    +  (?<=ab(c|de))
+
    +

    +

    +is not permitted, because its single top-level branch can match two different +lengths, but it is acceptable if rewritten to use two top-level branches: +

    +

    +

    +  (?<=abc|abde)
+
    +

    +

    +The implementation of lookbehind assertions is, for each alternative, to +temporarily move the current position back by the fixed width and then try to +match. If there are insufficient characters before the current position, the +match is deemed to fail. Lookbehinds in conjunction with once-only subpatterns +can be particularly useful for matching at the ends of strings; an example is +given at the end of the section on once-only subpatterns. +

    +

    +Several assertions (of any sort) may occur in succession. For example, +

    +

    +

    +  (?<=\d{3})(?<!999)foo
+
    +

    +

    +matches "foo" preceded by three digits that are not "999". Notice that each of +the assertions is applied independently at the same point in the subject +string. First there is a check that the previous three characters are all +digits, and then there is a check that the same three characters are not "999". +This pattern does not match "foo" preceded by six characters, the first +of which are digits and the last three of which are not "999". For example, it +doesn't match "123abcfoo". A pattern to do that is +

    +

    +

    +  (?<=\d{3}...)(?<!999)foo
+
    +

    +

    +This time the first assertion looks at the preceding six characters, checking +that the first three are digits, and then the second assertion checks that the +preceding three characters are not "999". +

    +

    +Assertions can be nested in any combination. For example, +

    +

    +

    +  (?<=(?<!foo)bar)baz
+
    +

    +

    +matches an occurrence of "baz" that is preceded by "bar" which in turn is not +preceded by "foo", while +

    +

    +

    +  (?<=\d{3}(?!999)...)foo
+
    +

    +

    +is another pattern which matches "foo" preceded by three digits and any three +characters that are not "999". +

    +

    +Assertion subpatterns are not capturing subpatterns, and may not be repeated, +because it makes no sense to assert the same thing several times. If any kind +of assertion contains capturing subpatterns within it, these are counted for +the purposes of numbering the capturing subpatterns in the whole pattern. +However, substring capturing is carried out only for positive assertions, +because it does not make sense for negative assertions. +

    +

    +Assertions count towards the maximum of 200 parenthesized subpatterns. +

    +
  • ONCE-ONLY SUBPATTERNS +

    +With both maximizing and minimizing repetition, failure of what follows +normally causes the repeated item to be re-evaluated to see if a different +number of repeats allows the rest of the pattern to match. Sometimes it is +useful to prevent this, either to change the nature of the match, or to cause +it fail earlier than it otherwise might, when the author of the pattern knows +there is no point in carrying on. +

    +

    +Consider, for example, the pattern \d+foo when applied to the subject line +

    +

    +

    +  123456bar
+
    +

    +

    +After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \d+ +item, and then with 4, and so on, before ultimately failing. Once-only +subpatterns provide the means for specifying that once a portion of the pattern +has matched, it is not to be re-evaluated in this way, so the matcher would +give up immediately on failing to match "foo" the first time. The notation is +another kind of special parenthesis, starting with (?> as in this example: +

    +

    +

    +  (?>\d+)bar
+
    +

    +

    +This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. +

    +

    +An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +

    +

    +Once-only subpatterns are not capturing subpatterns. Simple cases such as the +above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \d+ and \d+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\d+) can only match an entire sequence of digits. +

    +

    +This construction can of course contain arbitrarily complicated subpatterns, +and it can be nested. +

    +

    +Once-only subpatterns can be used in conjunction with lookbehind assertions to +specify efficient matching at the end of the subject string. Consider a simple +pattern such as +

    +

    +

    +  abcd$
+
    +

    +

    +when applied to a long string which does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as +

    +

    +

    +  ^.*abcd$
+
    +

    +

    +the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as +

    +

    +

    +  ^(?>.*)(?<=abcd)
+
    +

    +

    +there can be no backtracking for the .* item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. +

    +

    +When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of a once-only subpattern is +the only way to avoid some failing matches taking a very long time indeed. +The pattern +

    +

    +

    +  (\D+|<\d+>)*[!?]
+
    +

    +

    +matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +

    +

    +

    +  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
    +

    +

    +it takes a long time before reporting failure. This is because the string can +be divided between the two repeats in a large number of ways, and all have to +be tried. (The example used [!?] rather than a single character at the end, +because both PCRE and Perl have an optimization that allows for fast failure +when a single character is used. They remember the last single character that +is required for a match, and fail early if it is not present in the string.) +If the pattern is changed to +

    +

    +

    +  ((?>\D+)|<\d+>)*[!?]
+
    +

    +

    +sequences of non-digits cannot be broken, and failure happens quickly. +

    +
  • CONDITIONAL SUBPATTERNS +

    +It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a previous capturing subpattern matched +or not. The two possible forms of conditional subpattern are +

    +

    +

    +  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+
    +

    +

    +If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. +

    +

    +There are two kinds of condition. If the text between the parentheses consists +of a sequence of digits, the condition is satisfied if the capturing subpattern +of that number has previously matched. The number must be greater than zero. +Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +

    +

    +

    +  ( \( )?    [^()]+    (?(1) \) )
+
    +

    +

    +The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether the first set of parentheses matched +or not. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. +

    +

    +If the condition is not a sequence of digits, it must be an assertion. This may +be a positive or negative lookahead or lookbehind assertion. Consider this +pattern, again containing non-significant white space, and with the two +alternatives on the second line: +

    +

    +

    +  (?(?=[^a-z]*[a-z])
+  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
+
    +

    +

    +The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. +

    +
  • COMMENTS +

    +The sequence (?# marks the start of a comment which continues up to the next +closing parenthesis. Nested parentheses are not permitted. The characters +that make up a comment play no part in the pattern matching at all. +

    +

    +If the PCRE_EXTENDED option is set, an unescaped # character outside a +character class introduces a comment that continues up to the next newline +character in the pattern. +

    +
  • RECURSIVE PATTERNS +

    +Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. Perl 5.6 has provided an +experimental facility that allows regular expressions to recurse (amongst other +things). It does this by interpolating Perl code in the expression at run time, +and the code can refer to the expression itself. A Perl pattern to solve the +parentheses problem can be created like this: +

    +

    +

    +  $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
+
    +

    +

    +The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. Obviously, PCRE cannot support +the interpolation of Perl code. Instead, the special item (?R) is provided for +the specific case of recursion. This PCRE pattern solves the parentheses +problem (assume the PCRE_EXTENDED option is set so that white space is +ignored): +

    +

    +

    +  \( ( (?>[^()]+) | (?R) )* \)
+
    +

    +

    +First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (i.e. a correctly parenthesized substring). Finally +there is a closing parenthesis. +

    +

    +This particular example pattern contains nested unlimited repeats, and so the +use of a once-only subpattern for matching strings of non-parentheses is +important when applying the pattern to strings that do not match. For example, +when it is applied to +

    +

    +

    +  (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
+
    +

    +

    +it yields "no match" quickly. However, if a once-only subpattern is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. +

    +

    +The values set for any capturing subpatterns are those from the outermost level +of the recursion at which the subpattern value is set. If the pattern above is +matched against +

    +

    +

    +  (ab(cd)ef)
+
    +

    +

    +the value for the capturing parentheses is "ef", which is the last value taken +on at the top level. If additional parentheses are added, giving +

    +

    +

    +  \( ( ( (?>[^()]+) | (?R) )* ) \)
+     ^                        ^
+     ^                        ^
+
    +the string they capture is "ab(cd)ef", the contents of the top level +parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE +has to obtain extra memory to store data during a recursion, which it does by +using pcre_malloc, freeing it via pcre_free afterwards. If no +memory can be obtained, it saves data for the first 15 capturing parentheses +only, as there is no way to give an out-of-memory error from within a +recursion. +

    +
  • PERFORMANCE +

    +Certain items that may appear in patterns are more efficient than others. It is +more efficient to use a character class like [aeiou] than a set of alternatives +such as (a|e|i|o|u). In general, the simplest construction that provides the +required behaviour is usually the most efficient. Jeffrey Friedl's book +contains a lot of discussion about optimizing regular expressions for efficient +performance. +

    +

    +When a pattern begins with .* and the PCRE_DOTALL option is set, the pattern is +implicitly anchored by PCRE, since it can match only at the start of a subject +string. However, if PCRE_DOTALL is not set, PCRE cannot make this optimization, +because the . metacharacter does not then match a newline, and if the subject +string contains newlines, the pattern may match from the character immediately +following one of them instead of from the very start. For example, the pattern +

    +

    +

    +  (.*) second
+
    +

    +

    +matches the subject "first\nand second" (where \n stands for a newline +character) with the first captured substring being "and". In order to do this, +PCRE has to retry the match starting after every newline in the subject. +

    +

    +If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* to indicate explicit anchoring. That saves PCRE from +having to scan along the subject looking for a newline to restart at. +

    +

    +Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +

    +

    +

    +  (a+)*
+
    +

    +

    +This can match "aaaa" in 33 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time. +

    +

    +An optimization catches some of the more simple cases such as +

    +

    +

    +  (a+)*b
+
    +

    +

    +where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +

    +

    +

    +  (a+)*\d
+
    +

    +

    +with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. +

    +
  • UTF-8 SUPPORT +

    +Starting at release 3.3, PCRE has some support for character strings encoded +in the UTF-8 format. This is incomplete, and is regarded as experimental. In +order to use it, you must configure PCRE to include UTF-8 support in the code, +and, in addition, you must call pcre_compile() with the PCRE_UTF8 option +flag. When you do this, both the pattern and any subject strings that are +matched against it are treated as UTF-8 strings instead of just strings of +bytes, but only in the cases that are mentioned below. +

    +

    +If you compile PCRE with UTF-8 support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF8 flag in several places, so should not be very large. +

    +

    +PCRE assumes that the strings it is given contain valid UTF-8 codes. It does +not diagnose invalid UTF-8 strings. If you pass invalid UTF-8 strings to PCRE, +the results are undefined. +

    +

    +Running with PCRE_UTF8 set causes these changes in the way PCRE works: +

    +

    +1. In a pattern, the escape sequence \x{...}, where the contents of the braces +is a string of hexadecimal digits, is interpreted as a UTF-8 character whose +code number is the given hexadecimal number, for example: \x{1234}. This +inserts from one to six literal bytes into the pattern, using the UTF-8 +encoding. If a non-hexadecimal digit appears between the braces, the item is +not recognized. +

    +

    +2. The original hexadecimal escape sequence, \xhh, generates a two-byte UTF-8 +character if its value is greater than 127. +

    +

    +3. Repeat quantifiers are NOT correctly handled if they follow a multibyte +character. For example, \x{100}* and \xc3+ do not work. If you want to +repeat such characters, you must enclose them in non-capturing parentheses, +for example (?:\x{100}), at present. +

    +

    +4. The dot metacharacter matches one UTF-8 character instead of a single byte. +

    +

    +5. Unlike literal UTF-8 characters, the dot metacharacter followed by a +repeat quantifier does operate correctly on UTF-8 characters instead of +single bytes. +

    +

    +4. Although the \x{...} escape is permitted in a character class, characters +whose values are greater than 255 cannot be included in a class. +

    +

    +5. A class is matched against a UTF-8 character instead of just a single byte, +but it can match only characters whose values are less than 256. Characters +with greater values always fail to match a class. +

    +

    +6. Repeated classes work correctly on multiple characters. +

    +

    +7. Classes containing just a single character whose value is greater than 127 +(but less than 256), for example, [\x80] or [^\x{93}], do not work because +these are optimized into single byte matches. In the first case, of course, +the class brackets are just redundant. +

    +

    +8. Lookbehind assertions move backwards in the subject by a fixed number of +characters instead of a fixed number of bytes. Simple cases have been tested +to work correctly, but there may be hidden gotchas herein. +

    +

    +9. The character types such as \d and \w do not work correctly with UTF-8 +characters. They continue to test a single byte. +

    +

    +10. Anything not explicitly mentioned here continues to work in bytes rather +than in characters. +

    +

    +The following UTF-8 features of Perl 5.6 are not implemented: +

    +

    +1. The escape sequence \C to match a single byte. +

    +

    +2. The use of Unicode tables and properties and escapes \p, \P, and \X. +

    +
  • AUTHOR +

    +Philip Hazel <ph10@cam.ac.uk> +
    +University Computing Service, +
    +New Museums Site, +
    +Cambridge CB2 3QG, England. +
    +Phone: +44 1223 334714 +

    +

    +Last updated: 28 August 2000, +
    +

    +  the 250th anniversary of the death of J.S. Bach.
+
    
+
    +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcre.txt b/pcre/doc/pcre.txt new file mode 100644 index 00000000..1db4b537 --- /dev/null +++ b/pcre/doc/pcre.txt @@ -0,0 +1,2125 @@ +NAME + pcre - Perl-compatible regular expressions. + + + +SYNOPSIS + #include + + pcre *pcre_compile(const char *pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre_extra *pcre_study(const pcre *code, int options, + const char **errptr); + + int pcre_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre_copy_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, char *buffer, + int buffersize); + + int pcre_get_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, + const char **stringptr); + + int pcre_get_substring_list(const char *subject, + int *ovector, int stringcount, const char ***listptr); + + void pcre_free_substring(const char *stringptr); + + void pcre_free_substring_list(const char **stringptr); + + const unsigned char *pcre_maketables(void); + + int pcre_fullinfo(const pcre *code, const pcre_extra *extra, + int what, void *where); + + int pcre_info(const pcre *code, int *optptr, *firstcharptr); + + char *pcre_version(void); + + void *(*pcre_malloc)(size_t); + + void (*pcre_free)(void *); + + + + +DESCRIPTION + The PCRE library is a set of functions that implement regu- + lar expression pattern matching using the same syntax and + semantics as Perl 5, with just a few differences (see + + below). The current implementation corresponds to Perl + 5.005, with some additional features from later versions. + This includes some experimental, incomplete support for + UTF-8 encoded strings. Details of exactly what is and what + is not supported are given below. + + PCRE has its own native API, which is described in this + document. There is also a set of wrapper functions that + correspond to the POSIX regular expression API. These are + described in the pcreposix documentation. + + The native API function prototypes are defined in the header + file pcre.h, and on Unix systems the library itself is + called libpcre.a, so can be accessed by adding -lpcre to the + command for linking an application which calls it. The + header file defines the macros PCRE_MAJOR and PCRE_MINOR to + contain the major and minor release numbers for the library. + Applications can use these to include support for different + releases. + + The functions pcre_compile(), pcre_study(), and pcre_exec() + are used for compiling and matching regular expressions. + + The functions pcre_copy_substring(), pcre_get_substring(), + and pcre_get_substring_list() are convenience functions for + extracting captured substrings from a matched subject + string; pcre_free_substring() and pcre_free_substring_list() + are also provided, to free the memory used for extracted + strings. + + The function pcre_maketables() is used (optionally) to build + a set of character tables in the current locale for passing + to pcre_compile(). + + The function pcre_fullinfo() is used to find out information + about a compiled pattern; pcre_info() is an obsolete version + which returns only some of the available information, but is + retained for backwards compatibility. The function + pcre_version() returns a pointer to a string containing the + version of PCRE and its date of release. + + The global variables pcre_malloc and pcre_free initially + contain the entry points of the standard malloc() and free() + functions respectively. PCRE calls the memory management + functions via these variables, so a calling program can + replace them if it wishes to intercept the calls. This + should be done before calling any PCRE functions. + + + +MULTI-THREADING + The PCRE functions can be used in multi-threading + + + + + +SunOS 5.8 Last change: 2 + + + + applications, with the proviso that the memory management + functions pointed to by pcre_malloc and pcre_free are shared + by all threads. + + The compiled form of a regular expression is not altered + during matching, so the same compiled pattern can safely be + used by several threads at once. + + + +COMPILING A PATTERN + The function pcre_compile() is called to compile a pattern + into an internal form. The pattern is a C string terminated + by a binary zero, and is passed in the argument pattern. A + pointer to a single block of memory that is obtained via + pcre_malloc is returned. This contains the compiled code and + related data. The pcre type is defined for this for conveni- + ence, but in fact pcre is just a typedef for void, since the + contents of the block are not externally defined. It is up + to the caller to free the memory when it is no longer + required. + + The size of a compiled pattern is roughly proportional to + the length of the pattern string, except that each character + class (other than those containing just a single character, + negated or not) requires 33 bytes, and repeat quantifiers + with a minimum greater than one or a bounded maximum cause + the relevant portions of the compiled pattern to be repli- + cated. + + The options argument contains independent bits that affect + the compilation. It should be zero if no options are + required. Some of the options, in particular, those that are + compatible with Perl, can also be set and unset from within + the pattern (see the detailed description of regular expres- + sions below). For these options, the contents of the options + argument specifies their initial settings at the start of + compilation and execution. The PCRE_ANCHORED option can be + set at the time of matching as well as at compile time. + + If errptr is NULL, pcre_compile() returns NULL immediately. + Otherwise, if compilation of a pattern fails, pcre_compile() + returns NULL, and sets the variable pointed to by errptr to + point to a textual error message. The offset from the start + of the pattern to the character where the error was + discovered is placed in the variable pointed to by + erroffset, which must not be NULL. If it is, an immediate + error is given. + + If the final argument, tableptr, is NULL, PCRE uses a + default set of character tables which are built when it is + compiled, using the default C locale. Otherwise, tableptr + must be the result of a call to pcre_maketables(). See the + section on locale support below. + + The following option bits are defined in the header file: + + PCRE_ANCHORED + + If this bit is set, the pattern is forced to be "anchored", + that is, it is constrained to match only at the start of the + string which is being searched (the "subject string"). This + effect can also be achieved by appropriate constructs in the + pattern itself, which is the only way to do it in Perl. + + PCRE_CASELESS + + If this bit is set, letters in the pattern match both upper + and lower case letters. It is equivalent to Perl's /i + option. + + PCRE_DOLLAR_ENDONLY + + If this bit is set, a dollar metacharacter in the pattern + matches only at the end of the subject string. Without this + option, a dollar also matches immediately before the final + character if it is a newline (but not before any other new- + lines). The PCRE_DOLLAR_ENDONLY option is ignored if + PCRE_MULTILINE is set. There is no equivalent to this option + in Perl. + + PCRE_DOTALL + + If this bit is set, a dot metacharater in the pattern + matches all characters, including newlines. Without it, new- + lines are excluded. This option is equivalent to Perl's /s + option. A negative class such as [^a] always matches a new- + line character, independent of the setting of this option. + + PCRE_EXTENDED + + If this bit is set, whitespace data characters in the pat- + tern are totally ignored except when escaped or inside a + character class, and characters between an unescaped # out- + side a character class and the next newline character, + inclusive, are also ignored. This is equivalent to Perl's /x + option, and makes it possible to include comments inside + complicated patterns. Note, however, that this applies only + to data characters. Whitespace characters may never appear + within special character sequences in a pattern, for example + within the sequence (?( which introduces a conditional sub- + pattern. + + PCRE_EXTRA + + This option was invented in order to turn on additional + functionality of PCRE that is incompatible with Perl, but it + is currently of very little use. When set, any backslash in + a pattern that is followed by a letter that has no special + meaning causes an error, thus reserving these combinations + for future expansion. By default, as in Perl, a backslash + followed by a letter with no special meaning is treated as a + literal. There are at present no other features controlled + by this option. It can also be set by a (?X) option setting + within a pattern. + + PCRE_MULTILINE + + By default, PCRE treats the subject string as consisting of + a single "line" of characters (even if it actually contains + several newlines). The "start of line" metacharacter (^) + matches only at the start of the string, while the "end of + line" metacharacter ($) matches only at the end of the + string, or before a terminating newline (unless + PCRE_DOLLAR_ENDONLY is set). This is the same as Perl. + + When PCRE_MULTILINE it is set, the "start of line" and "end + of line" constructs match immediately following or immedi- + ately before any newline in the subject string, respec- + tively, as well as at the very start and end. This is + equivalent to Perl's /m option. If there are no "\n" charac- + ters in a subject string, or no occurrences of ^ or $ in a + pattern, setting PCRE_MULTILINE has no effect. + + PCRE_UNGREEDY + + This option inverts the "greediness" of the quantifiers so + that they are not greedy by default, but become greedy if + followed by "?". It is not compatible with Perl. It can also + be set by a (?U) option setting within the pattern. + + PCRE_UTF8 + + This option causes PCRE to regard both the pattern and the + subject as strings of UTF-8 characters instead of just byte + strings. However, it is available only if PCRE has been + built to include UTF-8 support. If not, the use of this + option provokes an error. Support for UTF-8 is new, experi- + mental, and incomplete. Details of exactly what it entails + are given below. + + + +STUDYING A PATTERN + When a pattern is going to be used several times, it is + worth spending more time analyzing it in order to speed up + the time taken for matching. The function pcre_study() takes + + a pointer to a compiled pattern as its first argument, and + returns a pointer to a pcre_extra block (another void + typedef) containing additional information about the pat- + tern; this can be passed to pcre_exec(). If no additional + information is available, NULL is returned. + + The second argument contains option bits. At present, no + options are defined for pcre_study(), and this argument + should always be zero. + + The third argument for pcre_study() is a pointer to an error + message. If studying succeeds (even if no data is returned), + the variable it points to is set to NULL. Otherwise it + points to a textual error message. + + At present, studying a pattern is useful only for non- + anchored patterns that do not have a single fixed starting + character. A bitmap of possible starting characters is + created. + + + +LOCALE SUPPORT + PCRE handles caseless matching, and determines whether char- + acters are letters, digits, or whatever, by reference to a + set of tables. The library contains a default set of tables + which is created in the default C locale when PCRE is com- + piled. This is used when the final argument of + pcre_compile() is NULL, and is sufficient for many applica- + tions. + + An alternative set of tables can, however, be supplied. Such + tables are built by calling the pcre_maketables() function, + which has no arguments, in the relevant locale. The result + can then be passed to pcre_compile() as often as necessary. + For example, to build and use tables that are appropriate + for the French locale (where accented characters with codes + greater than 128 are treated as letters), the following code + could be used: + + setlocale(LC_CTYPE, "fr"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); + + The tables are built in memory that is obtained via + pcre_malloc. The pointer that is passed to pcre_compile is + saved with the compiled pattern, and the same tables are + used via this pointer by pcre_study() and pcre_exec(). Thus + for any single pattern, compilation, studying and matching + all happen in the same locale, but different patterns can be + compiled in different locales. It is the caller's responsi- + bility to ensure that the memory containing the tables + remains available for as long as it is needed. + + + +INFORMATION ABOUT A PATTERN + The pcre_fullinfo() function returns information about a + compiled pattern. It replaces the obsolete pcre_info() func- + tion, which is nevertheless retained for backwards compabil- + ity (and is documented below). + + The first argument for pcre_fullinfo() is a pointer to the + compiled pattern. The second argument is the result of + pcre_study(), or NULL if the pattern was not studied. The + third argument specifies which piece of information is + required, while the fourth argument is a pointer to a vari- + able to receive the data. The yield of the function is zero + for success, or one of the following negative numbers: + + PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of what was invalid + + The possible values for the third argument are defined in + pcre.h, and are as follows: + + PCRE_INFO_OPTIONS + + Return a copy of the options with which the pattern was com- + piled. The fourth argument should point to au unsigned long + int variable. These option bits are those specified in the + call to pcre_compile(), modified by any top-level option + settings within the pattern itself, and with the + PCRE_ANCHORED bit forcibly set if the form of the pattern + implies that it can match only at the start of a subject + string. + + PCRE_INFO_SIZE + + Return the size of the compiled pattern, that is, the value + that was passed as the argument to pcre_malloc() when PCRE + was getting memory in which to place the compiled data. The + fourth argument should point to a size_t variable. + + PCRE_INFO_CAPTURECOUNT + + Return the number of capturing subpatterns in the pattern. + The fourth argument should point to an int variable. + + PCRE_INFO_BACKREFMAX + + Return the number of the highest back reference in the + pattern. The fourth argument should point to an int vari- + able. Zero is returned if there are no back references. + + PCRE_INFO_FIRSTCHAR + + Return information about the first character of any matched + string, for a non-anchored pattern. If there is a fixed + first character, e.g. from a pattern such as + (cat|cow|coyote), it is returned in the integer pointed to + by where. Otherwise, if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, + and every branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and + PCRE_DOTALL is not set (if it were set, the pattern would be + anchored), + + -1 is returned, indicating that the pattern matches only at + the start of a subject string or after any "\n" within the + string. Otherwise -2 is returned. For anchored patterns, -2 + is returned. + + PCRE_INFO_FIRSTTABLE + + If the pattern was studied, and this resulted in the con- + struction of a 256-bit table indicating a fixed set of char- + acters for the first character in any matching string, a + pointer to the table is returned. Otherwise NULL is + returned. The fourth argument should point to an unsigned + char * variable. + + PCRE_INFO_LASTLITERAL + + For a non-anchored pattern, return the value of the right- + most literal character which must exist in any matched + string, other than at its start. The fourth argument should + point to an int variable. If there is no such character, or + if the pattern is anchored, -1 is returned. For example, for + the pattern /a\d+z\d+/ the returned value is 'z'. + + The pcre_info() function is now obsolete because its inter- + face is too restrictive to return all the available data + about a compiled pattern. New programs should use + pcre_fullinfo() instead. The yield of pcre_info() is the + number of capturing subpatterns, or one of the following + negative numbers: + + PCRE_ERROR_NULL the argument code was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + + If the optptr argument is not NULL, a copy of the options + with which the pattern was compiled is placed in the integer + it points to (see PCRE_INFO_OPTIONS above). + + If the pattern is not anchored and the firstcharptr argument + is not NULL, it is used to pass back information about the + first character of any matched string (see + PCRE_INFO_FIRSTCHAR above). + + + +MATCHING A PATTERN + The function pcre_exec() is called to match a subject string + against a pre-compiled pattern, which is passed in the code + argument. If the pattern has been studied, the result of the + study should be passed in the extra argument. Otherwise this + must be NULL. + + The PCRE_ANCHORED option can be passed in the options argu- + ment, whose unused bits must be zero. However, if a pattern + was compiled with PCRE_ANCHORED, or turned out to be + anchored by virtue of its contents, it cannot be made + unachored at matching time. + + There are also three further options that can be set only at + matching time: + + PCRE_NOTBOL + + The first character of the string is not the beginning of a + line, so the circumflex metacharacter should not match + before it. Setting this without PCRE_MULTILINE (at compile + time) causes circumflex never to match. + + PCRE_NOTEOL + + The end of the string is not the end of a line, so the dol- + lar metacharacter should not match it nor (except in multi- + line mode) a newline immediately before it. Setting this + without PCRE_MULTILINE (at compile time) causes dollar never + to match. + + PCRE_NOTEMPTY + + An empty string is not considered to be a valid match if + this option is set. If there are alternatives in the pat- + tern, they are tried. If all the alternatives match the + empty string, the entire match fails. For example, if the + pattern + + a?b? + + is applied to a string not beginning with "a" or "b", it + matches the empty string at the start of the subject. With + PCRE_NOTEMPTY set, this match is not valid, so PCRE searches + further into the string for occurrences of "a" or "b". + + Perl has no direct equivalent of PCRE_NOTEMPTY, but it does + make a special case of a pattern match of the empty string + within its split() function, and when using the /g modifier. + It is possible to emulate Perl's behaviour after matching a + null string by first trying the match again at the same + offset with PCRE_NOTEMPTY set, and then if that fails by + advancing the starting offset (see below) and trying an + ordinary match again. + + The subject string is passed as a pointer in subject, a + length in length, and a starting offset in startoffset. + Unlike the pattern string, it may contain binary zero char- + acters. When the starting offset is zero, the search for a + match starts at the beginning of the subject, and this is by + far the most common case. + + A non-zero starting offset is useful when searching for + another match in the same subject by calling pcre_exec() + again after a previous success. Setting startoffset differs + from just passing over a shortened string and setting + PCRE_NOTBOL in the case of a pattern that begins with any + kind of lookbehind. For example, consider the pattern + + \Biss\B + + which finds occurrences of "iss" in the middle of words. (\B + matches only if the current position in the subject is not a + word boundary.) When applied to the string "Mississipi" the + first call to pcre_exec() finds the first occurrence. If + pcre_exec() is called again with just the remainder of the + subject, namely "issipi", it does not match, because \B is + always false at the start of the subject, which is deemed to + be a word boundary. However, if pcre_exec() is passed the + entire string again, but with startoffset set to 4, it finds + the second occurrence of "iss" because it is able to look + behind the starting point to discover that it is preceded by + a letter. + + If a non-zero starting offset is passed when the pattern is + anchored, one attempt to match at the given offset is tried. + This can only succeed if the pattern does not require the + match to be at the start of the subject. + + In general, a pattern matches a certain portion of the sub- + ject, and in addition, further substrings from the subject + may be picked out by parts of the pattern. Following the + usage in Jeffrey Friedl's book, this is called "capturing" + in what follows, and the phrase "capturing subpattern" is + used for a fragment of a pattern that picks out a substring. + PCRE supports several other kinds of parenthesized subpat- + tern that do not cause substrings to be captured. + + Captured substrings are returned to the caller via a vector + of integer offsets whose address is passed in ovector. The + number of elements in the vector is passed in ovecsize. The + first two-thirds of the vector is used to pass back captured + substrings, each substring using a pair of integers. The + remaining third of the vector is used as workspace by + pcre_exec() while matching capturing subpatterns, and is not + available for passing back information. The length passed in + ovecsize should always be a multiple of three. If it is not, + it is rounded down. + + When a match has been successful, information about captured + substrings is returned in pairs of integers, starting at the + beginning of ovector, and continuing up to two-thirds of its + length at the most. The first element of a pair is set to + the offset of the first character in a substring, and the + second is set to the offset of the first character after the + end of a substring. The first pair, ovector[0] and ovec- + tor[1], identify the portion of the subject string matched + by the entire pattern. The next pair is used for the first + capturing subpattern, and so on. The value returned by + pcre_exec() is the number of pairs that have been set. If + there are no capturing subpatterns, the return value from a + successful match is 1, indicating that just the first pair + of offsets has been set. + + Some convenience functions are provided for extracting the + captured substrings as separate strings. These are described + in the following section. + + It is possible for an capturing subpattern number n+1 to + match some part of the subject when subpattern n has not + been used at all. For example, if the string "abc" is + matched against the pattern (a|(z))(bc) subpatterns 1 and 3 + are matched, but 2 is not. When this happens, both offset + values corresponding to the unused subpattern are set to -1. + + If a capturing subpattern is matched repeatedly, it is the + last portion of the string that it matched that gets + returned. + + If the vector is too small to hold all the captured sub- + strings, it is used as far as possible (up to two-thirds of + its length), and the function returns a value of zero. In + particular, if the substring offsets are not of interest, + pcre_exec() may be called with ovector passed as NULL and + ovecsize as zero. However, if the pattern contains back + references and the ovector isn't big enough to remember the + related substrings, PCRE has to get additional memory for + use during matching. Thus it is usually advisable to supply + an ovector. + + Note that pcre_info() can be used to find out how many cap- + turing subpatterns there are in a compiled pattern. The + smallest size for ovector that will allow for n captured + substrings in addition to the offsets of the substring + matched by the whole pattern is (n+1)*3. + + If pcre_exec() fails, it returns a negative number. The fol- + lowing are defined in the header file: + + PCRE_ERROR_NOMATCH (-1) + + The subject string did not match the pattern. + + PCRE_ERROR_NULL (-2) + + Either code or subject was passed as NULL, or ovector was + NULL and ovecsize was not zero. + + PCRE_ERROR_BADOPTION (-3) + + An unrecognized bit was set in the options argument. + + PCRE_ERROR_BADMAGIC (-4) + + PCRE stores a 4-byte "magic number" at the start of the com- + piled code, to catch the case when it is passed a junk + pointer. This is the error it gives when the magic number + isn't present. + + PCRE_ERROR_UNKNOWN_NODE (-5) + + While running the pattern match, an unknown item was encoun- + tered in the compiled pattern. This error could be caused by + a bug in PCRE or by overwriting of the compiled pattern. + + PCRE_ERROR_NOMEMORY (-6) + + If a pattern contains back references, but the ovector that + is passed to pcre_exec() is not big enough to remember the + referenced substrings, PCRE gets a block of memory at the + start of matching to use for this purpose. If the call via + pcre_malloc() fails, this error is given. The memory is + freed at the end of matching. + + + +EXTRACTING CAPTURED SUBSTRINGS + Captured substrings can be accessed directly by using the + + + + + +SunOS 5.8 Last change: 12 + + + + offsets returned by pcre_exec() in ovector. For convenience, + the functions pcre_copy_substring(), pcre_get_substring(), + and pcre_get_substring_list() are provided for extracting + captured substrings as new, separate, zero-terminated + strings. A substring that contains a binary zero is + correctly extracted and has a further zero added on the end, + but the result does not, of course, function as a C string. + + The first three arguments are the same for all three func- + tions: subject is the subject string which has just been + successfully matched, ovector is a pointer to the vector of + integer offsets that was passed to pcre_exec(), and + stringcount is the number of substrings that were captured + by the match, including the substring that matched the + entire regular expression. This is the value returned by + pcre_exec if it is greater than zero. If pcre_exec() + returned zero, indicating that it ran out of space in ovec- + tor, the value passed as stringcount should be the size of + the vector divided by three. + + The functions pcre_copy_substring() and pcre_get_substring() + extract a single substring, whose number is given as string- + number. A value of zero extracts the substring that matched + the entire pattern, while higher values extract the captured + substrings. For pcre_copy_substring(), the string is placed + in buffer, whose length is given by buffersize, while for + pcre_get_substring() a new block of memory is obtained via + pcre_malloc, and its address is returned via stringptr. The + yield of the function is the length of the string, not + including the terminating zero, or one of + + PCRE_ERROR_NOMEMORY (-6) + + The buffer was too small for pcre_copy_substring(), or the + attempt to get memory failed for pcre_get_substring(). + + PCRE_ERROR_NOSUBSTRING (-7) + + There is no substring whose number is stringnumber. + + The pcre_get_substring_list() function extracts all avail- + able substrings and builds a list of pointers to them. All + this is done in a single block of memory which is obtained + via pcre_malloc. The address of the memory block is returned + via listptr, which is also the start of the list of string + pointers. The end of the list is marked by a NULL pointer. + The yield of the function is zero if all went well, or + + PCRE_ERROR_NOMEMORY (-6) + + if the attempt to get the memory block failed. + + When any of these functions encounter a substring that is + unset, which can happen when capturing subpattern number n+1 + matches some part of the subject, but subpattern n has not + been used at all, they return an empty string. This can be + distinguished from a genuine zero-length substring by + inspecting the appropriate offset in ovector, which is nega- + tive for unset substrings. + + The two convenience functions pcre_free_substring() and + pcre_free_substring_list() can be used to free the memory + returned by a previous call of pcre_get_substring() or + pcre_get_substring_list(), respectively. They do nothing + more than call the function pointed to by pcre_free, which + of course could be called directly from a C program. How- + ever, PCRE is used in some situations where it is linked via + a special interface to another programming language which + cannot use pcre_free directly; it is for these cases that + the functions are provided. + + + +LIMITATIONS + There are some size limitations in PCRE but it is hoped that + they will never in practice be relevant. The maximum length + of a compiled pattern is 65539 (sic) bytes. All values in + repeating quantifiers must be less than 65536. The maximum + number of capturing subpatterns is 99. The maximum number + of all parenthesized subpatterns, including capturing sub- + patterns, assertions, and other types of subpattern, is 200. + + The maximum length of a subject string is the largest posi- + tive number that an integer variable can hold. However, PCRE + uses recursion to handle subpatterns and indefinite repeti- + tion. This means that the available stack space may limit + the size of a subject string that can be processed by cer- + tain patterns. + + + +DIFFERENCES FROM PERL + The differences described here are with respect to Perl + 5.005. + + 1. By default, a whitespace character is any character that + the C library function isspace() recognizes, though it is + possible to compile PCRE with alternative character type + tables. Normally isspace() matches space, formfeed, newline, + carriage return, horizontal tab, and vertical tab. Perl 5 no + longer includes vertical tab in its set of whitespace char- + acters. The \v escape that was in the Perl documentation for + a long time was never in fact recognized. However, the char- + acter itself was treated as whitespace at least up to 5.002. + In 5.004 and 5.005 it does not match \s. + + 2. PCRE does not allow repeat quantifiers on lookahead + assertions. Perl permits them, but they do not mean what you + might think. For example, (?!a){3} does not assert that the + next three characters are not "a". It just asserts that the + next character is not "a" three times. + + 3. Capturing subpatterns that occur inside negative looka- + head assertions are counted, but their entries in the + offsets vector are never set. Perl sets its numerical vari- + ables from any such patterns that are matched before the + assertion fails to match something (thereby succeeding), but + only if the negative lookahead assertion contains just one + branch. + + 4. Though binary zero characters are supported in the sub- + ject string, they are not allowed in a pattern string + because it is passed as a normal C string, terminated by + zero. The escape sequence "\0" can be used in the pattern to + represent a binary zero. + + 5. The following Perl escape sequences are not supported: + \l, \u, \L, \U, \E, \Q. In fact these are implemented by + Perl's general string-handling and are not part of its pat- + tern matching engine. + + 6. The Perl \G assertion is not supported as it is not + relevant to single pattern matches. + + 7. Fairly obviously, PCRE does not support the (?{code}) and + (?p{code}) constructions. However, there is some experimen- + tal support for recursive patterns using the non-Perl item + (?R). + + 8. There are at the time of writing some oddities in Perl + 5.005_02 concerned with the settings of captured strings + when part of a pattern is repeated. For example, matching + "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value + "b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 + unset. However, if the pattern is changed to + /^(aa(b(b))?)+$/ then $2 (and $3) are set. + + In Perl 5.004 $2 is set in both cases, and that is also true + of PCRE. If in the future Perl changes to a consistent state + that is different, PCRE may change to follow. + + 9. Another as yet unresolved discrepancy is that in Perl + 5.005_02 the pattern /^(a)?(?(1)a|b)+$/ matches the string + "a", whereas in PCRE it does not. However, in both Perl and + PCRE /^(a)?a/ matched against "a" leaves $1 unset. + + 10. PCRE provides some extensions to the Perl regular + expression facilities: + + (a) Although lookbehind assertions must match fixed length + strings, each alternative branch of a lookbehind assertion + can match a different length of string. Perl 5.005 requires + them all to have the same length. + + (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not + set, the $ meta- character matches only at the very end of + the string. + + (c) If PCRE_EXTRA is set, a backslash followed by a letter + with no special meaning is faulted. + + (d) If PCRE_UNGREEDY is set, the greediness of the repeti- + tion quantifiers is inverted, that is, by default they are + not greedy, but if followed by a question mark they are. + + (e) PCRE_ANCHORED can be used to force a pattern to be tried + only at the start of the subject. + + (f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options + for pcre_exec() have no Perl equivalents. + + (g) The (?R) construct allows for recursive pattern matching + (Perl 5.6 can do this using the (?p{code}) construct, which + PCRE cannot of course support.) + + + +REGULAR EXPRESSION DETAILS + The syntax and semantics of the regular expressions sup- + ported by PCRE are described below. Regular expressions are + also described in the Perl documentation and in a number of + other books, some of which have copious examples. Jeffrey + Friedl's "Mastering Regular Expressions", published by + O'Reilly (ISBN 1-56592-257), covers them in great detail. + + The description here is intended as reference documentation. + The basic operation of PCRE is on strings of bytes. However, + there is the beginnings of some support for UTF-8 character + strings. To use this support you must configure PCRE to + include it, and then call pcre_compile() with the PCRE_UTF8 + option. How this affects the pattern matching is described + in the final section of this document. + + A regular expression is a pattern that is matched against a + subject string from left to right. Most characters stand for + themselves in a pattern, and match the corresponding charac- + ters in the subject. As a trivial example, the pattern + + The quick brown fox + + matches a portion of a subject string that is identical to + itself. The power of regular expressions comes from the + ability to include alternatives and repetitions in the pat- + tern. These are encoded in the pattern by the use of meta- + characters, which do not stand for themselves but instead + are interpreted in some special way. + + There are two different sets of meta-characters: those that + are recognized anywhere in the pattern except within square + brackets, and those that are recognized in square brackets. + Outside square brackets, the meta-characters are as follows: + + \ general escape character with several uses + ^ assert start of subject (or line, in multiline + mode) + $ assert end of subject (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + { start min/max quantifier + + Part of a pattern that is in square brackets is called a + "character class". In a character class the only meta- + characters are: + + \ general escape character + ^ negate the class, but only if the first character + - indicates character range + ] terminates the character class + + The following sections describe the use of each of the + meta-characters. + + + +BACKSLASH + The backslash character has several uses. Firstly, if it is + followed by a non-alphameric character, it takes away any + special meaning that character may have. This use of + backslash as an escape character applies both inside and + outside character classes. + + For example, if you want to match a "*" character, you write + "\*" in the pattern. This applies whether or not the follow- + ing character would otherwise be interpreted as a meta- + character, so it is always safe to precede a non-alphameric + with "\" to specify that it stands for itself. In particu- + lar, if you want to match a backslash, you write "\\". + + If a pattern is compiled with the PCRE_EXTENDED option, whi- + tespace in the pattern (other than in a character class) and + characters between a "#" outside a character class and the + next newline character are ignored. An escaping backslash + can be used to include a whitespace or "#" character as part + of the pattern. + + A second use of backslash provides a way of encoding non- + printing characters in patterns in a visible manner. There + is no restriction on the appearance of non-printing charac- + ters, apart from the binary zero that terminates a pattern, + but when a pattern is being prepared by text editing, it is + usually easier to use one of the following escape sequences + than the binary character it represents: + + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any character + \e escape (hex 1B) + \f formfeed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \xhh character with hex code hh + \ddd character with octal code ddd, or backreference + + The precise effect of "\cx" is as follows: if "x" is a lower + case letter, it is converted to upper case. Then bit 6 of + the character (hex 40) is inverted. Thus "\cz" becomes hex + 1A, but "\c{" becomes hex 3B, while "\c;" becomes hex 7B. + + After "\x", up to two hexadecimal digits are read (letters + can be in upper or lower case). + + After "\0" up to two further octal digits are read. In both + cases, if there are fewer than two digits, just those that + are present are used. Thus the sequence "\0\x\07" specifies + two binary zeros followed by a BEL character. Make sure you + supply two digits after the initial zero if the character + that follows is itself an octal digit. + + The handling of a backslash followed by a digit other than 0 + is complicated. Outside a character class, PCRE reads it + and any following digits as a decimal number. If the number + is less than 10, or if there have been at least that many + previous capturing left parentheses in the expression, the + entire sequence is taken as a back reference. A description + of how this works is given later, following the discussion + of parenthesized subpatterns. + + Inside a character class, or if the decimal number is + greater than 9 and there have not been that many capturing + subpatterns, PCRE re-reads up to three octal digits follow- + ing the backslash, and generates a single byte from the + least significant 8 bits of the value. Any subsequent digits + stand for themselves. For example: + + \040 is another way of writing a space + \40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \7 is always a back reference + \11 might be a back reference, or another way of + writing a tab + \011 is always a tab + \0113 is a tab followed by the character "3" + \113 is the character with octal code 113 (since there + can be no more than 99 back references) + \377 is a byte consisting entirely of 1 bits + \81 is either a back reference, or a binary zero + followed by the two characters "8" and "1" + + Note that octal values of 100 or greater must not be intro- + duced by a leading zero, because no more than three octal + digits are ever read. + + All the sequences that define a single byte value can be + used both inside and outside character classes. In addition, + inside a character class, the sequence "\b" is interpreted + as the backspace character (hex 08). Outside a character + class it has a different meaning (see below). + + The third use of backslash is for specifying generic charac- + ter types: + + \d any decimal digit + \D any character that is not a decimal digit + \s any whitespace character + \S any character that is not a whitespace character + \w any "word" character + \W any "non-word" character + + Each pair of escape sequences partitions the complete set of + characters into two disjoint sets. Any given character + matches one, and only one, of each pair. + + A "word" character is any letter or digit or the underscore + character, that is, any character which can be part of a + Perl "word". The definition of letters and digits is con- + trolled by PCRE's character tables, and may vary if locale- + specific matching is taking place (see "Locale support" + above). For example, in the "fr" (French) locale, some char- + acter codes greater than 128 are used for accented letters, + and these are matched by \w. + + These character type sequences can appear both inside and + outside character classes. They each match one character of + the appropriate type. If the current matching point is at + the end of the subject string, all of them fail, since there + is no character to match. + + The fourth use of backslash is for certain simple asser- + tions. An assertion specifies a condition that has to be met + at a particular point in a match, without consuming any + characters from the subject string. The use of subpatterns + for more complicated assertions is described below. The + backslashed assertions are + + \b word boundary + \B not a word boundary + \A start of subject (independent of multiline mode) + \Z end of subject or newline at end (independent of + multiline mode) + \z end of subject (independent of multiline mode) + + These assertions may not appear in character classes (but + note that "\b" has a different meaning, namely the backspace + character, inside a character class). + + A word boundary is a position in the subject string where + the current character and the previous character do not both + match \w or \W (i.e. one matches \w and the other matches + \W), or the start or end of the string if the first or last + character matches \w, respectively. + + The \A, \Z, and \z assertions differ from the traditional + circumflex and dollar (described below) in that they only + ever match at the very start and end of the subject string, + whatever options are set. They are not affected by the + PCRE_NOTBOL or PCRE_NOTEOL options. If the startoffset argu- + ment of pcre_exec() is non-zero, \A can never match. The + difference between \Z and \z is that \Z matches before a + newline that is the last character of the string as well as + at the end of the string, whereas \z matches only at the + end. + + + +CIRCUMFLEX AND DOLLAR + Outside a character class, in the default matching mode, the + circumflex character is an assertion which is true only if + the current matching point is at the start of the subject + + string. If the startoffset argument of pcre_exec() is non- + zero, circumflex can never match. Inside a character class, + circumflex has an entirely different meaning (see below). + + Circumflex need not be the first character of the pattern if + a number of alternatives are involved, but it should be the + first thing in each alternative in which it appears if the + pattern is ever to match that branch. If all possible alter- + natives start with a circumflex, that is, if the pattern is + constrained to match only at the start of the subject, it is + said to be an "anchored" pattern. (There are also other con- + structs that can cause a pattern to be anchored.) + + A dollar character is an assertion which is true only if the + current matching point is at the end of the subject string, + or immediately before a newline character that is the last + character in the string (by default). Dollar need not be the + last character of the pattern if a number of alternatives + are involved, but it should be the last item in any branch + in which it appears. Dollar has no special meaning in a + character class. + + The meaning of dollar can be changed so that it matches only + at the very end of the string, by setting the + PCRE_DOLLAR_ENDONLY option at compile or matching time. This + does not affect the \Z assertion. + + The meanings of the circumflex and dollar characters are + changed if the PCRE_MULTILINE option is set. When this is + the case, they match immediately after and immediately + before an internal "\n" character, respectively, in addition + to matching at the start and end of the subject string. For + example, the pattern /^abc$/ matches the subject string + "def\nabc" in multiline mode, but not otherwise. Conse- + quently, patterns that are anchored in single line mode + because all branches start with "^" are not anchored in mul- + tiline mode, and a match for circumflex is possible when the + startoffset argument of pcre_exec() is non-zero. The + PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is + set. + + Note that the sequences \A, \Z, and \z can be used to match + the start and end of the subject in both modes, and if all + branches of a pattern start with \A is it always anchored, + whether PCRE_MULTILINE is set or not. + + + +FULL STOP (PERIOD, DOT) + Outside a character class, a dot in the pattern matches any + one character in the subject, including a non-printing char- + acter, but not (by default) newline. If the PCRE_DOTALL + + option is set, dots match newlines as well. The handling of + dot is entirely independent of the handling of circumflex + and dollar, the only relationship being that they both + involve newline characters. Dot has no special meaning in a + character class. + + + +SQUARE BRACKETS + An opening square bracket introduces a character class, ter- + minated by a closing square bracket. A closing square + bracket on its own is not special. If a closing square + bracket is required as a member of the class, it should be + the first data character in the class (after an initial cir- + cumflex, if present) or escaped with a backslash. + + A character class matches a single character in the subject; + the character must be in the set of characters defined by + the class, unless the first character in the class is a cir- + cumflex, in which case the subject character must not be in + the set defined by the class. If a circumflex is actually + required as a member of the class, ensure it is not the + first character, or escape it with a backslash. + + For example, the character class [aeiou] matches any lower + case vowel, while [^aeiou] matches any character that is not + a lower case vowel. Note that a circumflex is just a con- + venient notation for specifying the characters which are in + the class by enumerating those that are not. It is not an + assertion: it still consumes a character from the subject + string, and fails if the current pointer is at the end of + the string. + + When caseless matching is set, any letters in a class + represent both their upper case and lower case versions, so + for example, a caseless [aeiou] matches "A" as well as "a", + and a caseless [^aeiou] does not match "A", whereas a case- + ful version would. + + The newline character is never treated in any special way in + character classes, whatever the setting of the PCRE_DOTALL + or PCRE_MULTILINE options is. A class such as [^a] will + always match a newline. + + The minus (hyphen) character can be used to specify a range + of characters in a character class. For example, [d-m] + matches any letter between d and m, inclusive. If a minus + character is required in a class, it must be escaped with a + backslash or appear in a position where it cannot be inter- + preted as indicating a range, typically as the first or last + character in the class. + + It is not possible to have the literal character "]" as the + end character of a range. A pattern such as [W-]46] is + interpreted as a class of two characters ("W" and "-") fol- + lowed by a literal string "46]", so it would match "W46]" or + "-46]". However, if the "]" is escaped with a backslash it + is interpreted as the end of range, so [W-\]46] is inter- + preted as a single class containing a range followed by two + separate characters. The octal or hexadecimal representation + of "]" can also be used to end a range. + + Ranges operate in ASCII collating sequence. They can also be + used for characters specified numerically, for example + [\000-\037]. If a range that includes letters is used when + caseless matching is set, it matches the letters in either + case. For example, [W-c] is equivalent to [][\^_`wxyzabc], + matched caselessly, and if character tables for the "fr" + locale are in use, [\xc8-\xcb] matches accented E characters + in both cases. + + The character types \d, \D, \s, \S, \w, and \W may also + appear in a character class, and add the characters that + they match to the class. For example, [\dABCDEF] matches any + hexadecimal digit. A circumflex can conveniently be used + with the upper case character types to specify a more res- + tricted set of characters than the matching lower case type. + For example, the class [^\W_] matches any letter or digit, + but not underscore. + + All non-alphameric characters other than \, -, ^ (at the + start) and the terminating ] are non-special in character + classes, but it does no harm if they are escaped. + + + +POSIX CHARACTER CLASSES + Perl 5.6 (not yet released at the time of writing) is going + to support the POSIX notation for character classes, which + uses names enclosed by [: and :] within the enclosing + square brackets. PCRE supports this notation. For example, + + [01[:alpha:]%] + + matches "0", "1", any alphabetic character, or "%". The sup- + ported class names are + + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + cntrl control characters + digit decimal digits (same as \d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits + space white space (same as \s) + upper upper case letters + word "word" characters (same as \w) + xdigit hexadecimal digits + + The names "ascii" and "word" are Perl extensions. Another + Perl extension is negation, which is indicated by a ^ char- + acter after the colon. For example, + + [12[:^digit:]] + + matches "1", "2", or any non-digit. PCRE (and Perl) also + recogize the POSIX syntax [.ch.] and [=ch=] where "ch" is a + "collating element", but these are not supported, and an + error is given if they are encountered. + + + +VERTICAL BAR + Vertical bar characters are used to separate alternative + patterns. For example, the pattern + + gilbert|sullivan + + matches either "gilbert" or "sullivan". Any number of alter- + natives may appear, and an empty alternative is permitted + (matching the empty string). The matching process tries + each alternative in turn, from left to right, and the first + one that succeeds is used. If the alternatives are within a + subpattern (defined below), "succeeds" means matching the + rest of the main pattern as well as the alternative in the + subpattern. + + + +INTERNAL OPTION SETTING + The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, + and PCRE_EXTENDED can be changed from within the pattern by + a sequence of Perl option letters enclosed between "(?" and + ")". The option letters are + + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED + + For example, (?im) sets caseless, multiline matching. It is + also possible to unset these options by preceding the letter + with a hyphen, and a combined setting and unsetting such as + (?im-sx), which sets PCRE_CASELESS and PCRE_MULTILINE while + unsetting PCRE_DOTALL and PCRE_EXTENDED, is also permitted. + If a letter appears both before and after the hyphen, the + option is unset. + + The scope of these option changes depends on where in the + pattern the setting occurs. For settings that are outside + any subpattern (defined below), the effect is the same as if + the options were set or unset at the start of matching. The + following patterns all behave in exactly the same way: + + (?i)abc + a(?i)bc + ab(?i)c + abc(?i) + + which in turn is the same as compiling the pattern abc with + PCRE_CASELESS set. In other words, such "top level" set- + tings apply to the whole pattern (unless there are other + changes inside subpatterns). If there is more than one set- + ting of the same option at top level, the rightmost setting + is used. + + If an option change occurs inside a subpattern, the effect + is different. This is a change of behaviour in Perl 5.005. + An option change inside a subpattern affects only that part + of the subpattern that follows it, so + + (a(?i)b)c + + matches abc and aBc and no other strings (assuming + PCRE_CASELESS is not used). By this means, options can be + made to have different settings in different parts of the + pattern. Any changes made in one alternative do carry on + into subsequent branches within the same subpattern. For + example, + + (a(?i)b|c) + + matches "ab", "aB", "c", and "C", even though when matching + "C" the first branch is abandoned before the option setting. + This is because the effects of option settings happen at + compile time. There would be some very weird behaviour oth- + erwise. + + The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can + be changed in the same way as the Perl-compatible options by + using the characters U and X respectively. The (?X) flag + setting is special in that it must always occur earlier in + the pattern than any of the additional features it turns on, + even when it is at top level. It is best put at the start. + + + +SUBPATTERNS + Subpatterns are delimited by parentheses (round brackets), + which can be nested. Marking part of a pattern as a subpat- + tern does two things: + + 1. It localizes a set of alternatives. For example, the pat- + tern + + cat(aract|erpillar|) + + matches one of the words "cat", "cataract", or "caterpil- + lar". Without the parentheses, it would match "cataract", + "erpillar" or the empty string. + + 2. It sets up the subpattern as a capturing subpattern (as + defined above). When the whole pattern matches, that por- + tion of the subject string that matched the subpattern is + passed back to the caller via the ovector argument of + pcre_exec(). Opening parentheses are counted from left to + right (starting from 1) to obtain the numbers of the captur- + ing subpatterns. + + For example, if the string "the red king" is matched against + the pattern + + the ((red|white) (king|queen)) + + the captured substrings are "red king", "red", and "king", + and are numbered 1, 2, and 3. + + The fact that plain parentheses fulfil two functions is not + always helpful. There are often times when a grouping sub- + pattern is required without a capturing requirement. If an + opening parenthesis is followed by "?:", the subpattern does + not do any capturing, and is not counted when computing the + number of any subsequent capturing subpatterns. For example, + if the string "the white queen" is matched against the pat- + tern + + the ((?:red|white) (king|queen)) + + the captured substrings are "white queen" and "queen", and + are numbered 1 and 2. The maximum number of captured sub- + strings is 99, and the maximum number of all subpatterns, + both capturing and non-capturing, is 200. + + As a convenient shorthand, if any option settings are + required at the start of a non-capturing subpattern, the + option letters may appear between the "?" and the ":". Thus + the two patterns + + (?i:saturday|sunday) + (?:(?i)saturday|sunday) + + match exactly the same set of strings. Because alternative + branches are tried from left to right, and options are not + reset until the end of the subpattern is reached, an option + setting in one branch does affect subsequent branches, so + the above patterns match "SUNDAY" as well as "Saturday". + + + +REPETITION + Repetition is specified by quantifiers, which can follow any + of the following items: + + a single character, possibly escaped + the . metacharacter + a character class + a back reference (see next section) + a parenthesized subpattern (unless it is an assertion - + see below) + + The general repetition quantifier specifies a minimum and + maximum number of permitted matches, by giving the two + numbers in curly brackets (braces), separated by a comma. + The numbers must be less than 65536, and the first must be + less than or equal to the second. For example: + + z{2,4} + + matches "zz", "zzz", or "zzzz". A closing brace on its own + is not a special character. If the second number is omitted, + but the comma is present, there is no upper limit; if the + second number and the comma are both omitted, the quantifier + specifies an exact number of required matches. Thus + + [aeiou]{3,} + + matches at least 3 successive vowels, but may match many + more, while + + \d{8} + + matches exactly 8 digits. An opening curly bracket that + appears in a position where a quantifier is not allowed, or + one that does not match the syntax of a quantifier, is taken + as a literal character. For example, {,6} is not a quantif- + ier, but a literal string of four characters. + + The quantifier {0} is permitted, causing the expression to + behave as if the previous item and the quantifier were not + present. + + For convenience (and historical compatibility) the three + most common quantifiers have single-character abbreviations: + + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} + + It is possible to construct infinite loops by following a + subpattern that can match no characters with a quantifier + that has no upper limit, for example: + + (a?)* + + Earlier versions of Perl and PCRE used to give an error at + compile time for such patterns. However, because there are + cases where this can be useful, such patterns are now + accepted, but if any repetition of the subpattern does in + fact match no characters, the loop is forcibly broken. + + By default, the quantifiers are "greedy", that is, they + match as much as possible (up to the maximum number of per- + mitted times), without causing the rest of the pattern to + fail. The classic example of where this gives problems is in + trying to match comments in C programs. These appear between + the sequences /* and */ and within the sequence, individual + * and / characters may appear. An attempt to match C com- + ments by applying the pattern + + /\*.*\*/ + + to the string + + /* first command */ not comment /* second comment */ + + fails, because it matches the entire string owing to the + greediness of the .* item. + + However, if a quantifier is followed by a question mark, it + ceases to be greedy, and instead matches the minimum number + of times possible, so the pattern + + /\*.*?\*/ + + does the right thing with the C comments. The meaning of the + various quantifiers is not otherwise changed, just the pre- + ferred number of matches. Do not confuse this use of ques- + tion mark with its use as a quantifier in its own right. + Because it has two uses, it can sometimes appear doubled, as + in + + \d??\d + + which matches one digit by preference, but can match two if + that is the only way the rest of the pattern matches. + + If the PCRE_UNGREEDY option is set (an option which is not + available in Perl), the quantifiers are not greedy by + default, but individual ones can be made greedy by following + them with a question mark. In other words, it inverts the + default behaviour. + + When a parenthesized subpattern is quantified with a minimum + repeat count that is greater than 1 or with a limited max- + imum, more store is required for the compiled pattern, in + proportion to the size of the minimum or maximum. + + If a pattern starts with .* or .{0,} and the PCRE_DOTALL + option (equivalent to Perl's /s) is set, thus allowing the . + to match newlines, the pattern is implicitly anchored, + because whatever follows will be tried against every charac- + ter position in the subject string, so there is no point in + retrying the overall match at any position after the first. + PCRE treats such a pattern as though it were preceded by \A. + In cases where it is known that the subject string contains + no newlines, it is worth setting PCRE_DOTALL when the pat- + tern begins with .* in order to obtain this optimization, or + alternatively using ^ to indicate anchoring explicitly. + + When a capturing subpattern is repeated, the value captured + is the substring that matched the final iteration. For exam- + ple, after + + (tweedle[dume]{3}\s*)+ + + has matched "tweedledum tweedledee" the value of the cap- + tured substring is "tweedledee". However, if there are + nested capturing subpatterns, the corresponding captured + values may have been set in previous iterations. For exam- + ple, after + + /(a|(b))+/ + + matches "aba" the value of the second captured substring is + "b". + + + +BACK REFERENCES + Outside a character class, a backslash followed by a digit + greater than 0 (and possibly further digits) is a back + reference to a capturing subpattern earlier (i.e. to its + left) in the pattern, provided there have been that many + previous capturing left parentheses. + + However, if the decimal number following the backslash is + less than 10, it is always taken as a back reference, and + causes an error only if there are not that many capturing + left parentheses in the entire pattern. In other words, the + parentheses that are referenced need not be to the left of + the reference for numbers less than 10. See the section + entitled "Backslash" above for further details of the han- + dling of digits following a backslash. + + A back reference matches whatever actually matched the cap- + turing subpattern in the current subject string, rather than + anything matching the subpattern itself. So the pattern + + (sens|respons)e and \1ibility + + matches "sense and sensibility" and "response and responsi- + bility", but not "sense and responsibility". If caseful + matching is in force at the time of the back reference, the + case of letters is relevant. For example, + + ((?i)rah)\s+\1 + + matches "rah rah" and "RAH RAH", but not "RAH rah", even + though the original capturing subpattern is matched case- + lessly. + + There may be more than one back reference to the same sub- + pattern. If a subpattern has not actually been used in a + particular match, any back references to it always fail. For + example, the pattern + + (a|(bc))\2 + + always fails if it starts to match "a" rather than "bc". + Because there may be up to 99 back references, all digits + following the backslash are taken as part of a potential + back reference number. If the pattern continues with a digit + character, some delimiter must be used to terminate the back + reference. If the PCRE_EXTENDED option is set, this can be + whitespace. Otherwise an empty comment can be used. + + A back reference that occurs inside the parentheses to which + it refers fails when the subpattern is first used, so, for + example, (a\1) never matches. However, such references can + be useful inside repeated subpatterns. For example, the pat- + tern + + (a|b\1)+ + + matches any number of "a"s and also "aba", "ababbaa" etc. At + each iteration of the subpattern, the back reference matches + the character string corresponding to the previous + iteration. In order for this to work, the pattern must be + such that the first iteration does not need to match the + back reference. This can be done using alternation, as in + the example above, or by a quantifier with a minimum of + zero. + + + +ASSERTIONS + An assertion is a test on the characters following or + preceding the current matching point that does not actually + consume any characters. The simple assertions coded as \b, + \B, \A, \Z, \z, ^ and $ are described above. More compli- + cated assertions are coded as subpatterns. There are two + kinds: those that look ahead of the current position in the + subject string, and those that look behind it. + + An assertion subpattern is matched in the normal way, except + that it does not cause the current matching position to be + changed. Lookahead assertions start with (?= for positive + assertions and (?! for negative assertions. For example, + + \w+(?=;) + + matches a word followed by a semicolon, but does not include + the semicolon in the match, and + + foo(?!bar) + + matches any occurrence of "foo" that is not followed by + "bar". Note that the apparently similar pattern + + (?!foo)bar + + does not find an occurrence of "bar" that is preceded by + something other than "foo"; it finds any occurrence of "bar" + whatsoever, because the assertion (?!foo) is always true + when the next three characters are "bar". A lookbehind + assertion is needed to achieve this effect. + + Lookbehind assertions start with (?<= for positive asser- + tions and (? as in this example: + + (?>\d+)bar + + This kind of parenthesis "locks up" the part of the pattern + it contains once it has matched, and a failure further into + the pattern is prevented from backtracking into it. + Backtracking past it to previous items, however, works as + normal. + + An alternative description is that a subpattern of this type + matches the string of characters that an identical stan- + dalone pattern would match, if anchored at the current point + in the subject string. + + Once-only subpatterns are not capturing subpatterns. Simple + cases such as the above example can be thought of as a max- + imizing repeat that must swallow everything it can. So, + while both \d+ and \d+? are prepared to adjust the number of + digits they match in order to make the rest of the pattern + match, (?>\d+) can only match an entire sequence of digits. + + This construction can of course contain arbitrarily compli- + cated subpatterns, and it can be nested. + + Once-only subpatterns can be used in conjunction with look- + behind assertions to specify efficient matching at the end + of the subject string. Consider a simple pattern such as + + abcd$ + + when applied to a long string which does not match. Because + matching proceeds from left to right, PCRE will look for + each "a" in the subject and then see if what follows matches + the rest of the pattern. If the pattern is specified as + + ^.*abcd$ + + the initial .* matches the entire string at first, but when + this fails (because there is no following "a"), it back- + tracks to match all but the last character, then all but the + last two characters, and so on. Once again the search for + "a" covers the entire string, from right to left, so we are + no better off. However, if the pattern is written as + + ^(?>.*)(?<=abcd) + + there can be no backtracking for the .* item; it can match + only the entire string. The subsequent lookbehind assertion + does a single test on the last four characters. If it fails, + the match fails immediately. For long strings, this approach + makes a significant difference to the processing time. + + When a pattern contains an unlimited repeat inside a subpat- + tern that can itself be repeated an unlimited number of + times, the use of a once-only subpattern is the only way to + avoid some failing matches taking a very long time indeed. + The pattern + + (\D+|<\d+>)*[!?] + + matches an unlimited number of substrings that either con- + sist of non-digits, or digits enclosed in <>, followed by + either ! or ?. When it matches, it runs quickly. However, if + it is applied to + + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + + it takes a long time before reporting failure. This is + because the string can be divided between the two repeats in + a large number of ways, and all have to be tried. (The exam- + ple used [!?] rather than a single character at the end, + because both PCRE and Perl have an optimization that allows + for fast failure when a single character is used. They + remember the last single character that is required for a + match, and fail early if it is not present in the string.) + If the pattern is changed to + + ((?>\D+)|<\d+>)*[!?] + + sequences of non-digits cannot be broken, and failure hap- + pens quickly. + + + +CONDITIONAL SUBPATTERNS + It is possible to cause the matching process to obey a sub- + pattern conditionally or to choose between two alternative + subpatterns, depending on the result of an assertion, or + whether a previous capturing subpattern matched or not. The + two possible forms of conditional subpattern are + + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + If the condition is satisfied, the yes-pattern is used; oth- + erwise the no-pattern (if present) is used. If there are + more than two alternatives in the subpattern, a compile-time + error occurs. + + There are two kinds of condition. If the text between the + parentheses consists of a sequence of digits, the condition + is satisfied if the capturing subpattern of that number has + previously matched. The number must be greater than zero. + Consider the following pattern, which contains non- + significant white space to make it more readable (assume the + PCRE_EXTENDED option) and to divide it into three parts for + ease of discussion: + + ( \( )? [^()]+ (?(1) \) ) + + The first part matches an optional opening parenthesis, and + if that character is present, sets it as the first captured + substring. The second part matches one or more characters + that are not parentheses. The third part is a conditional + subpattern that tests whether the first set of parentheses + matched or not. If they did, that is, if subject started + with an opening parenthesis, the condition is true, and so + the yes-pattern is executed and a closing parenthesis is + required. Otherwise, since no-pattern is not present, the + subpattern matches nothing. In other words, this pattern + matches a sequence of non-parentheses, optionally enclosed + in parentheses. + + If the condition is not a sequence of digits, it must be an + assertion. This may be a positive or negative lookahead or + lookbehind assertion. Consider this pattern, again contain- + ing non-significant white space, and with the two alterna- + tives on the second line: + + (?(?=[^a-z]*[a-z]) + \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) + + The condition is a positive lookahead assertion that matches + an optional sequence of non-letters followed by a letter. In + other words, it tests for the presence of at least one + letter in the subject. If a letter is found, the subject is + matched against the first alternative; otherwise it is + matched against the second. This pattern matches strings in + one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + letters and dd are digits. + + + +COMMENTS + The sequence (?# marks the start of a comment which contin- + ues up to the next closing parenthesis. Nested parentheses + are not permitted. The characters that make up a comment + play no part in the pattern matching at all. + + If the PCRE_EXTENDED option is set, an unescaped # character + outside a character class introduces a comment that contin- + ues up to the next newline character in the pattern. + + + +RECURSIVE PATTERNS + Consider the problem of matching a string in parentheses, + allowing for unlimited nested parentheses. Without the use + of recursion, the best that can be done is to use a pattern + that matches up to some fixed depth of nesting. It is not + possible to handle an arbitrary nesting depth. Perl 5.6 has + provided an experimental facility that allows regular + expressions to recurse (amongst other things). It does this + by interpolating Perl code in the expression at run time, + and the code can refer to the expression itself. A Perl pat- + tern to solve the parentheses problem can be created like + this: + + $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; + + The (?p{...}) item interpolates Perl code at run time, and + in this case refers recursively to the pattern in which it + appears. Obviously, PCRE cannot support the interpolation of + Perl code. Instead, the special item (?R) is provided for + the specific case of recursion. This PCRE pattern solves the + parentheses problem (assume the PCRE_EXTENDED option is set + so that white space is ignored): + + \( ( (?>[^()]+) | (?R) )* \) + + First it matches an opening parenthesis. Then it matches any + number of substrings which can either be a sequence of non- + parentheses, or a recursive match of the pattern itself + (i.e. a correctly parenthesized substring). Finally there is + a closing parenthesis. + + This particular example pattern contains nested unlimited + repeats, and so the use of a once-only subpattern for match- + ing strings of non-parentheses is important when applying + the pattern to strings that do not match. For example, when + it is applied to + + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() + + it yields "no match" quickly. However, if a once-only sub- + pattern is not used, the match runs for a very long time + indeed because there are so many different ways the + and * + repeats can carve up the subject, and all have to be tested + before failure can be reported. + + The values set for any capturing subpatterns are those from + the outermost level of the recursion at which the subpattern + value is set. If the pattern above is matched against + + (ab(cd)ef) + + the value for the capturing parentheses is "ef", which is + the last value taken on at the top level. If additional + parentheses are added, giving + + \( ( ( (?>[^()]+) | (?R) )* ) \) + ^ ^ + ^ ^ the string they capture is + "ab(cd)ef", the contents of the top level parentheses. If + there are more than 15 capturing parentheses in a pattern, + PCRE has to obtain extra memory to store data during a + recursion, which it does by using pcre_malloc, freeing it + via pcre_free afterwards. If no memory can be obtained, it + saves data for the first 15 capturing parentheses only, as + there is no way to give an out-of-memory error from within a + recursion. + + + +PERFORMANCE + Certain items that may appear in patterns are more efficient + than others. It is more efficient to use a character class + like [aeiou] than a set of alternatives such as (a|e|i|o|u). + In general, the simplest construction that provides the + required behaviour is usually the most efficient. Jeffrey + Friedl's book contains a lot of discussion about optimizing + regular expressions for efficient performance. + + When a pattern begins with .* and the PCRE_DOTALL option is + set, the pattern is implicitly anchored by PCRE, since it + can match only at the start of a subject string. However, if + PCRE_DOTALL is not set, PCRE cannot make this optimization, + because the . metacharacter does not then match a newline, + and if the subject string contains newlines, the pattern may + match from the character immediately following one of them + instead of from the very start. For example, the pattern + + (.*) second + + matches the subject "first\nand second" (where \n stands for + a newline character) with the first captured substring being + "and". In order to do this, PCRE has to retry the match + starting after every newline in the subject. + + If you are using such a pattern with subject strings that do + not contain newlines, the best performance is obtained by + setting PCRE_DOTALL, or starting the pattern with ^.* to + indicate explicit anchoring. That saves PCRE from having to + scan along the subject looking for a newline to restart at. + + Beware of patterns that contain nested indefinite repeats. + These can take a long time to run when applied to a string + that does not match. Consider the pattern fragment + + (a+)* + + This can match "aaaa" in 33 different ways, and this number + increases very rapidly as the string gets longer. (The * + repeat can match 0, 1, 2, 3, or 4 times, and for each of + those cases other than 0, the + repeats can match different + numbers of times.) When the remainder of the pattern is such + that the entire match is going to fail, PCRE has in princi- + ple to try every possible variation, and this can take an + extremely long time. + + An optimization catches some of the more simple cases such + as + + (a+)*b + + where a literal character follows. Before embarking on the + standard matching procedure, PCRE checks that there is a "b" + later in the subject string, and if there is not, it fails + the match immediately. However, when there is no following + literal this optimization cannot be used. You can see the + difference by comparing the behaviour of + + (a+)*\d + + with the pattern above. The former gives a failure almost + instantly when applied to a whole line of "a" characters, + whereas the latter takes an appreciable time with strings + longer than about 20 characters. + + + +UTF-8 SUPPORT + Starting at release 3.3, PCRE has some support for character + strings encoded in the UTF-8 format. This is incomplete, and + is regarded as experimental. In order to use it, you must + configure PCRE to include UTF-8 support in the code, and, in + addition, you must call pcre_compile() with the PCRE_UTF8 + option flag. When you do this, both the pattern and any sub- + ject strings that are matched against it are treated as + UTF-8 strings instead of just strings of bytes, but only in + the cases that are mentioned below. + + If you compile PCRE with UTF-8 support, but do not use it at + run time, the library will be a bit bigger, but the addi- + tional run time overhead is limited to testing the PCRE_UTF8 + flag in several places, so should not be very large. + + PCRE assumes that the strings it is given contain valid + UTF-8 codes. It does not diagnose invalid UTF-8 strings. If + you pass invalid UTF-8 strings to PCRE, the results are + undefined. + + Running with PCRE_UTF8 set causes these changes in the way + PCRE works: + + 1. In a pattern, the escape sequence \x{...}, where the con- + tents of the braces is a string of hexadecimal digits, is + interpreted as a UTF-8 character whose code number is the + given hexadecimal number, for example: \x{1234}. This + inserts from one to six literal bytes into the pattern, + using the UTF-8 encoding. If a non-hexadecimal digit appears + between the braces, the item is not recognized. + + 2. The original hexadecimal escape sequence, \xhh, generates + a two-byte UTF-8 character if its value is greater than 127. + + 3. Repeat quantifiers are NOT correctly handled if they fol- + low a multibyte character. For example, \x{100}* and \xc3+ + do not work. If you want to repeat such characters, you must + enclose them in non-capturing parentheses, for example + (?:\x{100}), at present. + + 4. The dot metacharacter matches one UTF-8 character instead + of a single byte. + + 5. Unlike literal UTF-8 characters, the dot metacharacter + followed by a repeat quantifier does operate correctly on + UTF-8 characters instead of single bytes. + + 4. Although the \x{...} escape is permitted in a character + class, characters whose values are greater than 255 cannot + be included in a class. + + 5. A class is matched against a UTF-8 character instead of + just a single byte, but it can match only characters whose + values are less than 256. Characters with greater values + always fail to match a class. + + 6. Repeated classes work correctly on multiple characters. + + 7. Classes containing just a single character whose value is + greater than 127 (but less than 256), for example, [\x80] or + [^\x{93}], do not work because these are optimized into sin- + gle byte matches. In the first case, of course, the class + brackets are just redundant. + + 8. Lookbehind assertions move backwards in the subject by a + fixed number of characters instead of a fixed number of + bytes. Simple cases have been tested to work correctly, but + there may be hidden gotchas herein. + + 9. The character types such as \d and \w do not work + correctly with UTF-8 characters. They continue to test a + single byte. + + 10. Anything not explicitly mentioned here continues to work + in bytes rather than in characters. + + The following UTF-8 features of Perl 5.6 are not imple- + mented: + 1. The escape sequence \C to match a single byte. + + 2. The use of Unicode tables and properties and escapes \p, + \P, and \X. + + + +AUTHOR + Philip Hazel + University Computing Service, + New Museums Site, + Cambridge CB2 3QG, England. + Phone: +44 1223 334714 + + Last updated: 28 August 2000, + the 250th anniversary of the death of J.S. Bach. + Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcregrep.1 b/pcre/doc/pcregrep.1 new file mode 100644 index 00000000..ec733fa1 --- /dev/null +++ b/pcre/doc/pcregrep.1 @@ -0,0 +1,76 @@ +.TH PCREGREP 1 +.SH NAME +pcregrep - a grep with Perl-compatible regular expressions. +.SH SYNOPSIS +.B pcregrep [-Vchilnsvx] pattern [file] ... + + +.SH DESCRIPTION +\fBpcregrep\fR searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +\fBpcre(3)\fR for a full description of syntax and semantics. + +If no files are specified, \fBpcregrep\fR reads the standard input. By default, +each line that matches the pattern is copied to the standard output, and if +there is more than one file, the file name is printed before each line of +output. However, there are options that can change how \fBpcregrep\fR behaves. + +Lines are limited to BUFSIZ characters. BUFSIZ is defined in \fB\fR. +The newline character is removed from the end of each line before it is matched +against the pattern. + + +.SH OPTIONS +.TP 10 +\fB-V\fR +Write the version number of the PCRE library being used to the standard error +stream. +.TP +\fB-c\fR +Do not print individual lines; instead just print a count of the number of +lines that would otherwise have been printed. If several files are given, a +count is printed for each of them. +.TP +\fB-h\fR +Suppress printing of filenames when searching multiple files. +.TP +\fB-i\fR +Ignore upper/lower case distinctions during comparisons. +.TP +\fB-l\fR +Instead of printing lines from the files, just print the names of the files +containing lines that would have been printed. Each file name is printed +once, on a separate line. +.TP +\fB-n\fR +Precede each line by its line number in the file. +.TP +\fB-s\fR +Work silently, that is, display nothing except error messages. +The exit status indicates whether any matches were found. +.TP +\fB-v\fR +Invert the sense of the match, so that lines which do \fInot\fR match the +pattern are now the ones that are found. +.TP +\fB-x\fR +Force the pattern to be anchored (it must start matching at the beginning of +the line) and in addition, require it to match the entire line. This is +equivalent to having ^ and $ characters at the start and end of each +alternative branch in the regular expression. + + +.SH SEE ALSO +\fBpcre(3)\fR, Perl 5 documentation + + +.SH DIAGNOSTICS +Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors or inacessible files (even if matches were found). + + +.SH AUTHOR +Philip Hazel +.br +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcregrep.html b/pcre/doc/pcregrep.html new file mode 100644 index 00000000..19f733c4 --- /dev/null +++ b/pcre/doc/pcregrep.html @@ -0,0 +1,105 @@ + + +pcregrep specification + + +

    pcregrep specification

    +This HTML document has been generated automatically from the original man page. +If there is any nonsense in it, please consult the man page in case the +conversion went wrong. + +
  • NAME +

    +pcregrep - a grep with Perl-compatible regular expressions. +

    +
  • SYNOPSIS +

    +pcregrep [-Vchilnsvx] pattern [file] ... +

    +
  • DESCRIPTION +

    +pcregrep searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +pcre(3) for a full description of syntax and semantics. +

    +

    +If no files are specified, pcregrep reads the standard input. By default, +each line that matches the pattern is copied to the standard output, and if +there is more than one file, the file name is printed before each line of +output. However, there are options that can change how pcregrep behaves. +

    +

    +Lines are limited to BUFSIZ characters. BUFSIZ is defined in <stdio.h>. +The newline character is removed from the end of each line before it is matched +against the pattern. +

    +
  • OPTIONS +

    +-V +Write the version number of the PCRE library being used to the standard error +stream. +

    +

    +-c +Do not print individual lines; instead just print a count of the number of +lines that would otherwise have been printed. If several files are given, a +count is printed for each of them. +

    +

    +-h +Suppress printing of filenames when searching multiple files. +

    +

    +-i +Ignore upper/lower case distinctions during comparisons. +

    +

    +-l +Instead of printing lines from the files, just print the names of the files +containing lines that would have been printed. Each file name is printed +once, on a separate line. +

    +

    +-n +Precede each line by its line number in the file. +

    +

    +-s +Work silently, that is, display nothing except error messages. +The exit status indicates whether any matches were found. +

    +

    +-v +Invert the sense of the match, so that lines which do not match the +pattern are now the ones that are found. +

    +

    +-x +Force the pattern to be anchored (it must start matching at the beginning of +the line) and in addition, require it to match the entire line. This is +equivalent to having ^ and $ characters at the start and end of each +alternative branch in the regular expression. +

    +
  • SEE ALSO +

    +pcre(3), Perl 5 documentation +

    +
  • DIAGNOSTICS +

    +Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors or inacessible files (even if matches were found). +

    +
  • AUTHOR +

    +Philip Hazel <ph10@cam.ac.uk> +
    +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcregrep.txt b/pcre/doc/pcregrep.txt new file mode 100644 index 00000000..871350ca --- /dev/null +++ b/pcre/doc/pcregrep.txt @@ -0,0 +1,87 @@ +NAME + pcregrep - a grep with Perl-compatible regular expressions. + + + +SYNOPSIS + pcregrep [-Vchilnsvx] pattern [file] ... + + + +DESCRIPTION + pcregrep searches files for character patterns, in the same + way as other grep commands do, but it uses the PCRE regular + expression library to support patterns that are compatible + with the regular expressions of Perl 5. See pcre(3) for a + full description of syntax and semantics. + + If no files are specified, pcregrep reads the standard + input. By default, each line that matches the pattern is + copied to the standard output, and if there is more than one + file, the file name is printed before each line of output. + However, there are options that can change how pcregrep + behaves. + + Lines are limited to BUFSIZ characters. BUFSIZ is defined in + . The newline character is removed from the end of + each line before it is matched against the pattern. + + + +OPTIONS + -V Write the version number of the PCRE library being + used to the standard error stream. + + -c Do not print individual lines; instead just print + a count of the number of lines that would other- + wise have been printed. If several files are + given, a count is printed for each of them. + + -h Suppress printing of filenames when searching mul- + tiple files. + + -i Ignore upper/lower case distinctions during com- + parisons. + + -l Instead of printing lines from the files, just + print the names of the files containing lines that + would have been printed. Each file name is printed + once, on a separate line. + + -n Precede each line by its line number in the file. + + -s Work silently, that is, display nothing except + error messages. The exit status indicates whether + any matches were found. + + -v Invert the sense of the match, so that lines which + do not match the pattern are now the ones that are + found. + + -x Force the pattern to be anchored (it must start + matching at the beginning of the line) and in + addition, require it to match the entire line. + This is equivalent to having ^ and $ characters at + the start and end of each alternative branch in + the regular expression. + + + +SEE ALSO + pcre(3), Perl 5 documentation + + + + + +DIAGNOSTICS + Exit status is 0 if any matches were found, 1 if no matches + were found, and 2 for syntax errors or inacessible files + (even if matches were found). + + + +AUTHOR + Philip Hazel + Copyright (c) 1997-2000 University of Cambridge. + diff --git a/pcre/doc/pcreposix.3 b/pcre/doc/pcreposix.3 new file mode 100644 index 00000000..4853a97f --- /dev/null +++ b/pcre/doc/pcreposix.3 @@ -0,0 +1,149 @@ +.TH PCRE 3 +.SH NAME +pcreposix - POSIX API for Perl-compatible regular expressions. +.SH SYNOPSIS +.B #include +.PP +.SM +.br +.B int regcomp(regex_t *\fIpreg\fR, const char *\fIpattern\fR, +.ti +5n +.B int \fIcflags\fR); +.PP +.br +.B int regexec(regex_t *\fIpreg\fR, const char *\fIstring\fR, +.ti +5n +.B size_t \fInmatch\fR, regmatch_t \fIpmatch\fR[], int \fIeflags\fR); +.PP +.br +.B size_t regerror(int \fIerrcode\fR, const regex_t *\fIpreg\fR, +.ti +5n +.B char *\fIerrbuf\fR, size_t \fIerrbuf_size\fR); +.PP +.br +.B void regfree(regex_t *\fIpreg\fR); + + +.SH DESCRIPTION +This set of functions provides a POSIX-style API to the PCRE regular expression +package. See the \fBpcre\fR documentation for a description of the native API, +which contains additional functionality. + +The functions described here are just wrapper functions that ultimately call +the native API. Their prototypes are defined in the \fBpcreposix.h\fR header +file, and on Unix systems the library itself is called \fBpcreposix.a\fR, so +can be accessed by adding \fB-lpcreposix\fR to the command for linking an +application which uses them. Because the POSIX functions call the native ones, +it is also necessary to add \fR-lpcre\fR. + +I have implemented only those option bits that can be reasonably mapped to PCRE +native options. In addition, the options REG_EXTENDED and REG_NOSUB are defined +with the value zero. They have no effect, but since programs that are written +to the POSIX interface often use them, this makes it easier to slot in PCRE as +a replacement library. Other POSIX options are not even defined. + +When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. + +The header for these functions is supplied as \fBpcreposix.h\fR to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as \fBregex.h\fR, which is the "correct" name. It provides two +structure types, \fIregex_t\fR for compiled internal forms, and +\fIregmatch_t\fR for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. + + +.SH COMPILING A PATTERN + +The function \fBregcomp()\fR is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument \fIpattern\fR. The \fIpreg\fR argument is a pointer +to a regex_t structure which is used as a base for storing information about +the compiled expression. + +The argument \fIcflags\fR is either zero, or contains one or more of the bits +defined by the following macros: + + REG_ICASE + +The PCRE_CASELESS option is set when the expression is passed for compilation +to the native function. + + REG_NEWLINE + +The PCRE_MULTILINE option is set when the expression is passed for compilation +to the native function. + +In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +\fIsome\fR of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they aren't) or a negative class such as [^a] (they +are). + +The yield of \fBregcomp()\fR is zero on success, and non-zero otherwise. The +\fIpreg\fR structure is filled in on success, and one member of the structure +is publicized: \fIre_nsub\fR contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. + + +.SH MATCHING A PATTERN +The function \fBregexec()\fR is called to match a pre-compiled pattern +\fIpreg\fR against a given \fIstring\fR, which is terminated by a zero byte, +subject to the options in \fIeflags\fR. These can be: + + REG_NOTBOL + +The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. + + REG_NOTEOL + +The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. + +The portion of the string that was matched, and also any captured substrings, +are returned via the \fIpmatch\fR argument, which points to an array of +\fInmatch\fR structures of type \fIregmatch_t\fR, containing the members +\fIrm_so\fR and \fIrm_eo\fR. These contain the offset to the first character of +each substring and the offset to the first character after the end of each +substring, respectively. The 0th element of the vector relates to the entire +portion of \fIstring\fR that was matched; subsequent elements relate to the +capturing subpatterns of the regular expression. Unused entries in the array +have both structure members set to -1. + +A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. + + +.SH ERROR MESSAGES +The \fBregerror()\fR function maps a non-zero errorcode from either +\fBregcomp\fR or \fBregexec\fR to a printable message. If \fIpreg\fR is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in \fIerrbuf\fR. The length of the +message, including the zero, is limited to \fIerrbuf_size\fR. The yield of the +function is the size of buffer needed to hold the whole message. + + +.SH STORAGE +Compiling a regular expression causes memory to be allocated and associated +with the \fIpreg\fR structure. The function \fBregfree()\fR frees all such +memory, after which \fIpreg\fR may no longer be used as a compiled expression. + + +.SH AUTHOR +Philip Hazel +.br +University Computing Service, +.br +New Museums Site, +.br +Cambridge CB2 3QG, England. +.br +Phone: +44 1223 334714 + +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcreposix.html b/pcre/doc/pcreposix.html new file mode 100644 index 00000000..79ff544b --- /dev/null +++ b/pcre/doc/pcreposix.html @@ -0,0 +1,191 @@ + + +pcreposix specification + + +

    pcreposix specification

    +This HTML document has been generated automatically from the original man page. +If there is any nonsense in it, please consult the man page in case the +conversion went wrong. + +
  • NAME +

    +pcreposix - POSIX API for Perl-compatible regular expressions. +

    +
  • SYNOPSIS +

    +#include <pcreposix.h> +

    +

    +int regcomp(regex_t *preg, const char *pattern, +int cflags); +

    +

    +int regexec(regex_t *preg, const char *string, +size_t nmatch, regmatch_t pmatch[], int eflags); +

    +

    +size_t regerror(int errcode, const regex_t *preg, +char *errbuf, size_t errbuf_size); +

    +

    +void regfree(regex_t *preg); +

    +
  • DESCRIPTION +

    +This set of functions provides a POSIX-style API to the PCRE regular expression +package. See the pcre documentation for a description of the native API, +which contains additional functionality. +

    +

    +The functions described here are just wrapper functions that ultimately call +the native API. Their prototypes are defined in the pcreposix.h header +file, and on Unix systems the library itself is called pcreposix.a, so +can be accessed by adding -lpcreposix to the command for linking an +application which uses them. Because the POSIX functions call the native ones, +it is also necessary to add \fR-lpcre\fR. +

    +

    +I have implemented only those option bits that can be reasonably mapped to PCRE +native options. In addition, the options REG_EXTENDED and REG_NOSUB are defined +with the value zero. They have no effect, but since programs that are written +to the POSIX interface often use them, this makes it easier to slot in PCRE as +a replacement library. Other POSIX options are not even defined. +

    +

    +When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. +

    +

    +The header for these functions is supplied as pcreposix.h to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as regex.h, which is the "correct" name. It provides two +structure types, regex_t for compiled internal forms, and +regmatch_t for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +

    +
  • COMPILING A PATTERN +

    +The function regcomp() is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument pattern. The preg argument is a pointer +to a regex_t structure which is used as a base for storing information about +the compiled expression. +

    +

    +The argument cflags is either zero, or contains one or more of the bits +defined by the following macros: +

    +

    +

    +  REG_ICASE
+
    +

    +

    +The PCRE_CASELESS option is set when the expression is passed for compilation +to the native function. +

    +

    +

    +  REG_NEWLINE
+
    +

    +

    +The PCRE_MULTILINE option is set when the expression is passed for compilation +to the native function. +

    +

    +In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +some of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they aren't) or a negative class such as [^a] (they +are). +

    +

    +The yield of regcomp() is zero on success, and non-zero otherwise. The +preg structure is filled in on success, and one member of the structure +is publicized: re_nsub contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +

    +
  • MATCHING A PATTERN +

    +The function regexec() is called to match a pre-compiled pattern +preg against a given string, which is terminated by a zero byte, +subject to the options in eflags. These can be: +

    +

    +

    +  REG_NOTBOL
+
    +

    +

    +The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +

    +

    +

    +  REG_NOTEOL
+
    +

    +

    +The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +

    +

    +The portion of the string that was matched, and also any captured substrings, +are returned via the pmatch argument, which points to an array of +nmatch structures of type regmatch_t, containing the members +rm_so and rm_eo. These contain the offset to the first character of +each substring and the offset to the first character after the end of each +substring, respectively. The 0th element of the vector relates to the entire +portion of string that was matched; subsequent elements relate to the +capturing subpatterns of the regular expression. Unused entries in the array +have both structure members set to -1. +

    +

    +A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +

    +
  • ERROR MESSAGES +

    +The regerror() function maps a non-zero errorcode from either +regcomp or regexec to a printable message. If preg is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in errbuf. The length of the +message, including the zero, is limited to errbuf_size. The yield of the +function is the size of buffer needed to hold the whole message. +

    +
  • STORAGE +

    +Compiling a regular expression causes memory to be allocated and associated +with the preg structure. The function regfree() frees all such +memory, after which preg may no longer be used as a compiled expression. +

    +
  • AUTHOR +

    +Philip Hazel <ph10@cam.ac.uk> +
    +University Computing Service, +
    +New Museums Site, +
    +Cambridge CB2 3QG, England. +
    +Phone: +44 1223 334714 +

    +

    +Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcreposix.txt b/pcre/doc/pcreposix.txt new file mode 100644 index 00000000..2d76f7cd --- /dev/null +++ b/pcre/doc/pcreposix.txt @@ -0,0 +1,159 @@ +NAME + pcreposix - POSIX API for Perl-compatible regular expres- + sions. + + + +SYNOPSIS + #include + + int regcomp(regex_t *preg, const char *pattern, + int cflags); + + int regexec(regex_t *preg, const char *string, + size_t nmatch, regmatch_t pmatch[], int eflags); + + size_t regerror(int errcode, const regex_t *preg, + char *errbuf, size_t errbuf_size); + + void regfree(regex_t *preg); + + + +DESCRIPTION + This set of functions provides a POSIX-style API to the PCRE + regular expression package. See the pcre documentation for a + description of the native API, which contains additional + functionality. + + The functions described here are just wrapper functions that + ultimately call the native API. Their prototypes are defined + in the pcreposix.h header file, and on Unix systems the + library itself is called pcreposix.a, so can be accessed by + adding -lpcreposix to the command for linking an application + which uses them. Because the POSIX functions call the native + ones, it is also necessary to add -lpcre. + + I have implemented only those option bits that can be rea- + sonably mapped to PCRE native options. In addition, the + options REG_EXTENDED and REG_NOSUB are defined with the + value zero. They have no effect, but since programs that are + written to the POSIX interface often use them, this makes it + easier to slot in PCRE as a replacement library. Other POSIX + options are not even defined. + + When PCRE is called via these functions, it is only the API + that is POSIX-like in style. The syntax and semantics of the + regular expressions themselves are still those of Perl, sub- + ject to the setting of various PCRE options, as described + below. + + The header for these functions is supplied as pcreposix.h to + avoid any potential clash with other POSIX libraries. It + can, of course, be renamed or aliased as regex.h, which is + the "correct" name. It provides two structure types, regex_t + for compiled internal forms, and regmatch_t for returning + captured substrings. It also defines some constants whose + names start with "REG_"; these are used for setting options + and identifying error codes. + + + +COMPILING A PATTERN + The function regcomp() is called to compile a pattern into + an internal form. The pattern is a C string terminated by a + binary zero, and is passed in the argument pattern. The preg + argument is a pointer to a regex_t structure which is used + as a base for storing information about the compiled expres- + sion. + + The argument cflags is either zero, or contains one or more + of the bits defined by the following macros: + + REG_ICASE + + The PCRE_CASELESS option is set when the expression is + passed for compilation to the native function. + + REG_NEWLINE + + The PCRE_MULTILINE option is set when the expression is + passed for compilation to the native function. + + In the absence of these flags, no options are passed to the + native function. This means the the regex is compiled with + PCRE default semantics. In particular, the way it handles + newline characters in the subject string is the Perl way, + not the POSIX way. Note that setting PCRE_MULTILINE has only + some of the effects specified for REG_NEWLINE. It does not + affect the way newlines are matched by . (they aren't) or a + negative class such as [^a] (they are). + + The yield of regcomp() is zero on success, and non-zero oth- + erwise. The preg structure is filled in on success, and one + member of the structure is publicized: re_nsub contains the + number of capturing subpatterns in the regular expression. + Various error codes are defined in the header file. + + + +MATCHING A PATTERN + The function regexec() is called to match a pre-compiled + pattern preg against a given string, which is terminated by + a zero byte, subject to the options in eflags. These can be: + + REG_NOTBOL + + The PCRE_NOTBOL option is set when calling the underlying + PCRE matching function. + + REG_NOTEOL + + The PCRE_NOTEOL option is set when calling the underlying + PCRE matching function. + + The portion of the string that was matched, and also any + captured substrings, are returned via the pmatch argument, + which points to an array of nmatch structures of type + regmatch_t, containing the members rm_so and rm_eo. These + contain the offset to the first character of each substring + and the offset to the first character after the end of each + substring, respectively. The 0th element of the vector + relates to the entire portion of string that was matched; + subsequent elements relate to the capturing subpatterns of + the regular expression. Unused entries in the array have + both structure members set to -1. + + A successful match yields a zero return; various error codes + are defined in the header file, of which REG_NOMATCH is the + "expected" failure code. + + + +ERROR MESSAGES + The regerror() function maps a non-zero errorcode from + either regcomp or regexec to a printable message. If preg is + not NULL, the error should have arisen from the use of that + structure. A message terminated by a binary zero is placed + in errbuf. The length of the message, including the zero, is + limited to errbuf_size. The yield of the function is the + size of buffer needed to hold the whole message. + + + +STORAGE + Compiling a regular expression causes memory to be allocated + and associated with the preg structure. The function reg- + free() frees all such memory, after which preg may no longer + be used as a compiled expression. + + + +AUTHOR + Philip Hazel + University Computing Service, + New Museums Site, + Cambridge CB2 3QG, England. + Phone: +44 1223 334714 + + Copyright (c) 1997-2000 University of Cambridge. diff --git a/pcre/doc/pcretest.txt b/pcre/doc/pcretest.txt new file mode 100644 index 00000000..722e6b86 --- /dev/null +++ b/pcre/doc/pcretest.txt @@ -0,0 +1,246 @@ +The pcretest program +-------------------- + +This program is intended for testing PCRE, but it can also be used for +experimenting with regular expressions. + +If it is given two filename arguments, it reads from the first and writes to +the second. If it is given only one filename argument, it reads from that file +and writes to stdout. Otherwise, it reads from stdin and writes to stdout, and +prompts for each line of input, using "re>" to prompt for regular expressions, +and "data>" to prompt for data lines. + +The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against the pattern. An empty line signals the end of the +data lines, at which point a new regular expression is read. The regular +expressions are given enclosed in any non-alphameric delimiters other than +backslash, for example + + /(a|bc)x+yz/ + +White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. See the test input files in the testdata directory for many +examples. It is possible to include the delimiter within the pattern by +escaping it, for example + + /abc\/def/ + +If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphameric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, + + /abc/\ + +then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because + + /abc\/ + +is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. + + +PATTERN MODIFIERS +----------------- + +The pattern may be followed by i, m, s, or x to set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively. For +example: + + /caseless/i + +These modifier letters have the same effect as they do in Perl. There are +others which set PCRE options that do not correspond to anything in Perl: /A, +/E, and /X set PCRE_ANCHORED, PCRE_DOLLAR_ENDONLY, and PCRE_EXTRA respectively. + +Searching for all possible matches within each subject string can be requested +by the /g or /G modifier. After finding a match, PCRE is called again to search +the remainder of the subject string. The difference between /g and /G is that +the former uses the startoffset argument to pcre_exec() to start searching at +a new point within the entire string (which is in effect what Perl does), +whereas the latter passes over a shortened substring. This makes a difference +to the matching process if the pattern begins with a lookbehind assertion +(including \b or \B). + +If any call to pcre_exec() in a /g or /G sequence matches an empty string, the +next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set in order +to search for another, non-empty, match at the same point. If this second match +fails, the start offset is advanced by one, and the normal match is retried. +This imitates the way Perl handles such cases when using the /g modifier or the +split() function. + +There are a number of other modifiers for controlling the way pcretest +operates. + +The /+ modifier requests that as well as outputting the substring that matched +the entire pattern, pcretest should in addition output the remainder of the +subject string. This is useful for tests where the subject contains multiple +copies of the same substring. + +The /L modifier must be followed directly by the name of a locale, for example, + + /pattern/Lfr + +For this reason, it must be the last modifier letter. The given locale is set, +pcre_maketables() is called to build a set of character tables for the locale, +and this is then passed to pcre_compile() when compiling the regular +expression. Without an /L modifier, NULL is passed as the tables pointer; that +is, /L applies only to the expression on which it appears. + +The /I modifier requests that pcretest output information about the compiled +expression (whether it is anchored, has a fixed first character, and so on). It +does this by calling pcre_fullinfo() after compiling an expression, and +outputting the information it gets back. If the pattern is studied, the results +of that are also output. + +The /D modifier is a PCRE debugging feature, which also assumes /I. It causes +the internal form of compiled regular expressions to be output after +compilation. + +The /S modifier causes pcre_study() to be called after the expression has been +compiled, and the results used when the expression is matched. + +The /M modifier causes the size of memory block used to hold the compiled +pattern to be output. + +The /P modifier causes pcretest to call PCRE via the POSIX wrapper API rather +than its native API. When this is done, all other modifiers except /i, /m, and +/+ are ignored. REG_ICASE is set if /i is present, and REG_NEWLINE is set if /m +is present. The wrapper functions force PCRE_DOLLAR_ENDONLY always, and +PCRE_DOTALL unless REG_NEWLINE is set. + +The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option set. +This turns on the (currently incomplete) support for UTF-8 character handling +in PCRE, provided that it was compiled with this support enabled. This modifier +also causes any non-printing characters in output strings to be printed using +the \x{hh...} notation if they are valid UTF-8 sequences. + + +DATA LINES +---------- + +Before each data line is passed to pcre_exec(), leading and trailing whitespace +is removed, and it is then scanned for \ escapes. The following are recognized: + + \a alarm (= BEL) + \b backspace + \e escape + \f formfeed + \n newline + \r carriage return + \t tab + \v vertical tab + \nnn octal character (up to 3 octal digits) + \xhh hexadecimal character (up to 2 hex digits) + \x{hh...} hexadecimal UTF-8 character + + \A pass the PCRE_ANCHORED option to pcre_exec() + \B pass the PCRE_NOTBOL option to pcre_exec() + \Cdd call pcre_copy_substring() for substring dd after a successful + match (any decimal number less than 32) + \Gdd call pcre_get_substring() for substring dd after a successful + match (any decimal number less than 32) + \L call pcre_get_substringlist() after a successful match + \N pass the PCRE_NOTEMPTY option to pcre_exec() + \Odd set the size of the output vector passed to pcre_exec() to dd + (any number of decimal digits) + \Z pass the PCRE_NOTEOL option to pcre_exec() + +A backslash followed by anything else just escapes the anything else. If the +very last character is a backslash, it is ignored. This gives a way of passing +an empty line as data, since a real empty line terminates the data input. + +If /P was present on the regex, causing the POSIX wrapper API to be used, only +\B, and \Z have any effect, causing REG_NOTBOL and REG_NOTEOL to be passed to +regexec() respectively. + +The use of \x{hh...} to represent UTF-8 characters is not dependent on the use +of the /8 modifier on the pattern. It is recognized always. There may be any +number of hexadecimal digits inside the braces. The result is from one to six +bytes, encoded according to the UTF-8 rules. + + +OUTPUT FROM PCRETEST +-------------------- + +When a match succeeds, pcretest outputs the list of captured substrings that +pcre_exec() returns, starting with number 0 for the string that matched the +whole pattern. Here is an example of an interactive pcretest run. + + $ pcretest + PCRE version 2.06 08-Jun-1999 + + re> /^abc(\d+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match + +If the strings contain any non-printing characters, they are output as \0x +escapes, or as \x{...} escapes if the /8 modifier was present on the pattern. +If the pattern has the /+ modifier, then the output for substring 0 is followed +by the the rest of the subject string, identified by "0+" like this: + + re> /cat/+ + data> cataract + 0: cat + 0+ aract + +If the pattern has the /g or /G modifier, the results of successive matching +attempts are output in sequence, like this: + + re> /\Bi(\w\w)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp + +"No match" is output only if the first match attempt fails. + +If any of \C, \G, or \L are present in a data line that is successfully +matched, the substrings extracted by the convenience functions are output with +C, G, or L after the string number instead of a colon. This is in addition to +the normal full list. The string length (that is, the return from the +extraction function) is given in parentheses after each string for \C and \G. + +Note that while patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \n escape. + + +COMMAND LINE OPTIONS +-------------------- + +If the -p option is given to pcretest, it is equivalent to adding /P to each +regular expression: the POSIX wrapper API is used to call PCRE. None of the +following flags has any effect in this case. + +If the option -d is given to pcretest, it is equivalent to adding /D to each +regular expression: the internal form is output after compilation. + +If the option -i is given to pcretest, it is equivalent to adding /I to each +regular expression: information about the compiled pattern is given after +compilation. + +If the option -m is given to pcretest, it outputs the size of each compiled +pattern after it has been compiled. It is equivalent to adding /M to each +regular expression. For compatibility with earlier versions of pcretest, -s is +a synonym for -m. + +If the -t option is given, each compile, study, and match is run 20000 times +while being timed, and the resulting time per compile or match is output in +milliseconds. Do not set -t with -m, because you will then get the size output +20000 times and the timing will be distorted. If you want to change the number +of repetitions used for timing, edit the definition of LOOPREPEAT at the top of +pcretest.c + +Philip Hazel +August 2000 diff --git a/pcre/doc/perltest.txt b/pcre/doc/perltest.txt new file mode 100644 index 00000000..33155c1a --- /dev/null +++ b/pcre/doc/perltest.txt @@ -0,0 +1,29 @@ +The perltest program +-------------------- + +The perltest program tests Perl's regular expressions; it has the same +specification as pcretest, and so can be given identical input, except that +input patterns can be followed only by Perl's lower case modifiers and /+ (as +used by pcretest), which is recognized and handled by the program. + +The data lines are processed as Perl double-quoted strings, so if they contain +" \ $ or @ characters, these have to be escaped. For this reason, all such +characters in testinput1 and testinput3 are escaped so that they can be used +for perltest as well as for pcretest, and the special upper case modifiers such +as /A that pcretest recognizes are not used in these files. The output should +be identical, apart from the initial identifying banner. + +For testing UTF-8 features, an alternative form of perltest, called perltest8, +is supplied. This requires Perl 5.6 or higher. It recognizes the special +modifier /8 that pcretest uses to invoke UTF-8 functionality. The testinput5 +file can be fed to perltest8. + +The testinput2 and testinput4 files are not suitable for feeding to perltest, +since they do make use of the special upper case modifiers and escapes that +pcretest uses to test some features of PCRE. The first of these files also +contains malformed regular expressions, in order to check that PCRE diagnoses +them correctly. Similarly, testinput6 tests UTF-8 features that do not relate +to Perl. + +Philip Hazel +August 2000 diff --git a/pcre/doc/readme b/pcre/doc/readme new file mode 100644 index 00000000..d124ee01 --- /dev/null +++ b/pcre/doc/readme @@ -0,0 +1,270 @@ +README file for PCRE (Perl-compatible regular expression library) +----------------------------------------------------------------- + +The latest release of PCRE is always available from + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + +Please read the NEWS file if you are upgrading from a previous release. + +PCRE has its own native API, but a set of "wrapper" functions that are based on +the POSIX API are also supplied in the library libpcreposix. Note that this +just provides a POSIX calling interface to PCRE: the regular expressions +themselves still follow Perl syntax and semantics. The header file +for the POSIX-style functions is called pcreposix.h. The official POSIX name is +regex.h, but I didn't want to risk possible problems with existing files of +that name by distributing it that way. To use it with an existing program that +uses the POSIX API, it will have to be renamed or pointed at by a link. + + +Building PCRE on a Unix system +------------------------------ + +To build PCRE on a Unix system, run the "configure" command in the PCRE +distribution directory. This is a standard GNU "autoconf" configuration script, +for which generic instructions are supplied in INSTALL. On many systems just +running "./configure" is sufficient, but the usual methods of changing standard +defaults are available. For example, + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +specifies that the C compiler should be run with the flags '-O2 -Wall' instead +of the default, and that "make install" should install PCRE under /opt/local +instead of the default /usr/local. + +If you want to make use of the experimential, incomplete support for UTF-8 +character strings in PCRE, you must add --enable-utf8 to the "configure" +command. Without it, the code for handling UTF-8 is not included in the +library. (Even when included, it still has to be enabled by an option at run +time.) + +The "configure" script builds four files: + +. Makefile is built by copying Makefile.in and making substitutions. +. config.h is built by copying config.in and making substitutions. +. pcre-config is built by copying pcre-config.in and making substitutions. +. RunTest is a script for running tests + +Once "configure" has run, you can run "make". It builds two libraries called +libpcre and libpcreposix, a test program called pcretest, and the pcregrep +command. You can use "make install" to copy these, and the public header file +pcre.h, to appropriate live directories on your system, in the normal way. + +Running "make install" also installs the command pcre-config, which can be used +to recall information about the PCRE configuration and installation. For +example, + + pcre-config --version + +prints the version number, and + + pcre-config --libs + +outputs information about where the library is installed. This command can be +included in makefiles for programs that use PCRE, saving the programmer from +having to remember too many details. + + +Shared libraries on Unix systems +-------------------------------- + +The default distribution builds PCRE as two shared libraries. This support is +new and experimental and may not work on all systems. It relies on the +"libtool" scripts - these are distributed with PCRE. It should build a +"libtool" script and use this to compile and link shared libraries, which are +placed in a subdirectory called .libs. The programs pcretest and pcregrep are +built to use these uninstalled libraries by means of wrapper scripts. When you +use "make install" to install shared libraries, pcregrep and pcretest are +automatically re-built to use the newly installed libraries. However, only +pcregrep is installed, as pcretest is really just a test program. + +To build PCRE using static libraries you must use --disable-shared when +configuring it. For example + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. + + +Building on non-Unix systems +---------------------------- + +For a non-Unix system, read the comments in the file NON-UNIX-USE. PCRE has +been compiled on Windows systems and on Macintoshes, but I don't know the +details because I don't use those systems. It should be straightforward to +build PCRE on any system that has a Standard C compiler, because it uses only +Standard C functions. + + +Testing PCRE +------------ + +To test PCRE on a Unix system, run the RunTest script in the pcre directory. +(This can also be run by "make runtest", "make check", or "make test".) For +other systems, see the instruction in NON-UNIX-USE. + +The script runs the pcretest test program (which is documented in +doc/pcretest.txt) on each of the testinput files (in the testdata directory) in +turn, and compares the output with the contents of the corresponding testoutput +file. A file called testtry is used to hold the output from pcretest. To run +pcretest on just one of the test files, give its number as an argument to +RunTest, for example: + + RunTest 3 + +The first and third test files can also be fed directly into the perltest +script to check that Perl gives the same results. The third file requires the +additional features of release 5.005, which is why it is kept separate from the +main test input, which needs only Perl 5.004. In the long run, when 5.005 (or +higher) is widespread, these two test files may get amalgamated. + +The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), +pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error +detection, and run-time flags that are specific to PCRE, as well as the POSIX +wrapper API. It also uses the debugging flag to check some of the internals of +pcre_compile(). + +If you build PCRE with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. Where the comparison test output contains [\x00-\x7f] the +test will contain [\x00-\xff], and similarly in some other cases. This is not a +bug in PCRE. + +The fourth set of tests checks pcre_maketables(), the facility for building a +set of character tables for a specific locale and using them instead of the +default tables. The tests make use of the "fr" (French) locale. Before running +the test, the script checks for the presence of this locale by running the +"locale" command. If that command fails, or if it doesn't include "fr" in the +list of available locales, the fourth test cannot be run, and a comment is +output to say why. If running this test produces instances of the error + + ** Failed to set locale "fr" + +in the comparison output, it means that locale is not available on your system, +despite being listed by "locale". This does not mean that PCRE is broken. + +The fifth test checks the experimental, incomplete UTF-8 support. It is not run +automatically unless PCRE is built with UTF-8 support. This file can be fed +directly to the perltest8 script, which requires Perl 5.6 or higher. The sixth +file tests internal UTF-8 features of PCRE that are not relevant to Perl. + + +Character tables +---------------- + +PCRE uses four tables for manipulating and identifying characters. The final +argument of the pcre_compile() function is a pointer to a block of memory +containing the concatenated tables. A call to pcre_maketables() can be used to +generate a set of tables in the current locale. If the final argument for +pcre_compile() is passed as NULL, a set of default tables that is built into +the binary is used. + +The source file called chartables.c contains the default set of tables. This is +not supplied in the distribution, but is built by the program dftables +(compiled from dftables.c), which uses the ANSI C character handling functions +such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table +sources. This means that the default C locale which is set for your system will +control the contents of these default tables. You can change the default tables +by editing chartables.c and then re-building PCRE. If you do this, you should +probably also edit Makefile to ensure that the file doesn't ever get +re-generated. + +The first two 256-byte tables provide lower casing and case flipping functions, +respectively. The next table consists of three 32-byte bit maps which identify +digits, "word" characters, and white space, respectively. These are used when +building 32-byte bit maps that represent character classes. + +The final 256-byte table has bits indicating various character types, as +follows: + + 1 white space character + 2 letter + 4 decimal digit + 8 hexadecimal digit + 16 alphanumeric or '_' + 128 regular expression metacharacter or binary zero + +You should not alter the set of characters that contain the 128 bit, as that +will cause PCRE to malfunction. + + +Manifest +-------- + +The distribution should contain the following files: + +(A) The actual source files of the PCRE library functions and their + headers: + + dftables.c auxiliary program for building chartables.c + get.c ) + maketables.c ) + study.c ) source of + pcre.c ) the functions + pcreposix.c ) + pcre.in "source" for the header for the external API; pcre.h + is built from this by "configure" + pcreposix.h header for the external POSIX wrapper API + internal.h header for internal use + config.in template for config.h, which is built by configure + +(B) Auxiliary files: + + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in template for Unix Makefile, which is built by configure + NEWS important changes in this release + NON-UNIX-USE notes on building PCRE on non-Unix systems + README this file + RunTest.in template for a Unix shell script for running tests + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.in the autoconf input used to build configure + doc/Tech.Notes notes on the encoding + doc/pcre.3 man page source for the PCRE functions + doc/pcre.html HTML version + doc/pcre.txt plain text version + doc/pcreposix.3 man page source for the POSIX wrapper API + doc/pcreposix.html HTML version + doc/pcreposix.txt plain text version + doc/pcretest.txt documentation of test program + doc/perltest.txt documentation of Perl test program + doc/pcregrep.1 man page source for the pcregrep utility + doc/pcregrep.html HTML version + doc/pcregrep.txt plain text version + install-sh a shell script for installing files + ltconfig ) files used to build "libtool", + ltmain.sh ) used only when building a shared library + pcretest.c test program + perltest Perl test program + perltest8 Perl test program for UTF-8 tests + pcregrep.c source of a grep utility that uses PCRE + pcre-config.in source of script which retains PCRE information + testdata/testinput1 test data, compatible with Perl 5.004 and 5.005 + testdata/testinput2 test data for error messages and non-Perl things + testdata/testinput3 test data, compatible with Perl 5.005 + testdata/testinput4 test data for locale-specific tests + testdata/testinput5 test data for UTF-8 tests compatible with Perl 5.6 + testdata/testinput6 test data for other UTF-8 tests + testdata/testoutput1 test results corresponding to testinput1 + testdata/testoutput2 test results corresponding to testinput2 + testdata/testoutput3 test results corresponding to testinput3 + testdata/testoutput4 test results corresponding to testinput4 + testdata/testoutput5 test results corresponding to testinput5 + testdata/testoutput6 test results corresponding to testinput6 + +(C) Auxiliary files for Win32 DLL + + dll.mk + pcre.def + +Philip Hazel +August 2000 diff --git a/pcre/get.c b/pcre/get.c new file mode 100644 index 00000000..42e9bd49 --- /dev/null +++ b/pcre/get.c @@ -0,0 +1,227 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* +This is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. See +the file Tech.Notes for some information on the internals. + +Written by: Philip Hazel + + Copyright (c) 1997-2000 University of Cambridge + +----------------------------------------------------------------------------- +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. +----------------------------------------------------------------------------- +*/ + +/* This module contains some convenience functions for extracting substrings +from the subject string after a regex match has succeeded. The original idea +for these functions came from Scott Wimer . */ + + +/* Include the internals header, which itself includes Standard C headers plus +the external pcre header. */ + +#include "internal.h" + + + +/************************************************* +* Copy captured string to given buffer * +*************************************************/ + +/* This function copies a single captured substring into a given buffer. +Note that we use memcpy() rather than strncpy() in case there are binary zeros +in the string. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + buffer where to put the substring + size the size of the buffer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) buffer too small + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +int +pcre_copy_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, char *buffer, int size) +{ +int yield; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +if (size < yield + 1) return PCRE_ERROR_NOMEMORY; +memcpy(buffer, subject + ovector[stringnumber], yield); +buffer[yield] = 0; +return yield; +} + + + +/************************************************* +* Copy all captured strings to new store * +*************************************************/ + +/* This function gets one chunk of store and builds a list of pointers and all +of the captured substrings in it. A NULL pointer is put on the end of the list. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + listptr set to point to the list of pointers + +Returns: if successful: 0 + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store +*/ + +int +pcre_get_substring_list(const char *subject, int *ovector, int stringcount, + const char ***listptr) +{ +int i; +int size = sizeof(char *); +int double_count = stringcount * 2; +char **stringlist; +char *p; + +for (i = 0; i < double_count; i += 2) + size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; + +stringlist = (char **)(pcre_malloc)(size); +if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; + +*listptr = (const char **)stringlist; +p = (char *)(stringlist + stringcount + 1); + +for (i = 0; i < double_count; i += 2) + { + int len = ovector[i+1] - ovector[i]; + memcpy(p, subject + ovector[i], len); + *stringlist++ = p; + p += len; + *p++ = 0; + } + +*stringlist = NULL; +return 0; +} + + + +/************************************************* +* Free store obtained by get_substring_list * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (pcre_free)() directly. + +Argument: the result of a previous pcre_get_substring_list() +Returns: nothing +*/ + +void +pcre_free_substring_list(const char **pointer) +{ +(pcre_free)((void *)pointer); +} + + + +/************************************************* +* Copy captured string to new store * +*************************************************/ + +/* This function copies a single captured substring into a piece of new +store + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + stringptr where to put a pointer to the substring + +Returns: if successful: + the length of the string, not including the zero that + is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store + PCRE_ERROR_NOSUBSTRING (-7) substring not present +*/ + +int +pcre_get_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, const char **stringptr) +{ +int yield; +char *substring; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +substring = (char *)(pcre_malloc)(yield + 1); +if (substring == NULL) return PCRE_ERROR_NOMEMORY; +memcpy(substring, subject + ovector[stringnumber], yield); +substring[yield] = 0; +*stringptr = substring; +return yield; +} + + + +/************************************************* +* Free store obtained by get_substring * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (pcre_free)() directly. + +Argument: the result of a previous pcre_get_substring() +Returns: nothing +*/ + +void +pcre_free_substring(const char *pointer) +{ +(pcre_free)((void *)pointer); +} + +/* End of get.c */ diff --git a/pcre/install b/pcre/install new file mode 100644 index 00000000..08802812 --- /dev/null +++ b/pcre/install @@ -0,0 +1,185 @@ +Basic Installation +================== + + These are generic installation instructions that apply to systems that +can run the `configure' shell script - Unix systems and any that imitate +it. They are not specific to PCRE. There are PCRE-specific instructions +for non-Unix systems in the file NON-UNIX-USE. + + The `configure' shell script attempts to guess correct values for +various system-dependent variables used during compilation. It uses +those values to create a `Makefile' in each directory of the package. +It may also create one or more `.h' files containing system-dependent +definitions. Finally, it creates a shell script `config.status' that +you can run in the future to recreate the current configuration, a file +`config.cache' that saves the results of its tests to speed up +reconfiguring, and a file `config.log' containing compiler output +(useful mainly for debugging `configure'). + + If you need to do unusual things to compile the package, please try +to figure out how `configure' could check whether to do them, and mail +diffs or instructions to the address given in the `README' so they can +be considered for the next release. If at some point `config.cache' +contains results you don't want to keep, you may remove or edit it. + + The file `configure.in' is used to create `configure' by a program +called `autoconf'. You only need `configure.in' if you want to change +it or regenerate `configure' using a newer version of `autoconf'. + +The simplest way to compile this package is: + + 1. `cd' to the directory containing the package's source code and type + `./configure' to configure the package for your system. If you're + using `csh' on an old version of System V, you might need to type + `sh ./configure' instead to prevent `csh' from trying to execute + `configure' itself. + + Running `configure' takes awhile. While running, it prints some + messages telling which features it is checking for. + + 2. Type `make' to compile the package. + + 3. Optionally, type `make check' to run any self-tests that come with + the package. + + 4. Type `make install' to install the programs and any data files and + documentation. + + 5. You can remove the program binaries and object files from the + source code directory by typing `make clean'. To also remove the + files that `configure' created (so you can compile the package for + a different kind of computer), type `make distclean'. There is + also a `make maintainer-clean' target, but that is intended mainly + for the package's developers. If you use it, you may have to get + all sorts of other programs in order to regenerate files that came + with the distribution. + +Compilers and Options +===================== + + Some systems require unusual options for compilation or linking that +the `configure' script does not know about. You can give `configure' +initial values for variables by setting them in the environment. Using +a Bourne-compatible shell, you can do that on the command line like +this: + CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure + +Or on systems that have the `env' program, you can do it like this: + env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure + +Compiling For Multiple Architectures +==================================== + + You can compile the package for more than one kind of computer at the +same time, by placing the object files for each architecture in their +own directory. To do this, you must use a version of `make' that +supports the `VPATH' variable, such as GNU `make'. `cd' to the +directory where you want the object files and executables to go and run +the `configure' script. `configure' automatically checks for the +source code in the directory that `configure' is in and in `..'. + + If you have to use a `make' that does not supports the `VPATH' +variable, you have to compile the package for one architecture at a time +in the source code directory. After you have installed the package for +one architecture, use `make distclean' before reconfiguring for another +architecture. + +Installation Names +================== + + By default, `make install' will install the package's files in +`/usr/local/bin', `/usr/local/man', etc. You can specify an +installation prefix other than `/usr/local' by giving `configure' the +option `--prefix=PATH'. + + You can specify separate installation prefixes for +architecture-specific files and architecture-independent files. If you +give `configure' the option `--exec-prefix=PATH', the package will use +PATH as the prefix for installing programs and libraries. +Documentation and other data files will still use the regular prefix. + + In addition, if you use an unusual directory layout you can give +options like `--bindir=PATH' to specify different values for particular +kinds of files. Run `configure --help' for a list of the directories +you can set and what kinds of files go in them. + + If the package supports it, you can cause programs to be installed +with an extra prefix or suffix on their names by giving `configure' the +option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. + +Optional Features +================= + + Some packages pay attention to `--enable-FEATURE' options to +`configure', where FEATURE indicates an optional part of the package. +They may also pay attention to `--with-PACKAGE' options, where PACKAGE +is something like `gnu-as' or `x' (for the X Window System). The +`README' should mention any `--enable-' and `--with-' options that the +package recognizes. + + For packages that use the X Window System, `configure' can usually +find the X include and library files automatically, but if it doesn't, +you can use the `configure' options `--x-includes=DIR' and +`--x-libraries=DIR' to specify their locations. + +Specifying the System Type +========================== + + There may be some features `configure' can not figure out +automatically, but needs to determine by the type of host the package +will run on. Usually `configure' can figure that out, but if it prints +a message saying it can not guess the host type, give it the +`--host=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name with three fields: + CPU-COMPANY-SYSTEM + +See the file `config.sub' for the possible values of each field. If +`config.sub' isn't included in this package, then this package doesn't +need to know the host type. + + If you are building compiler tools for cross-compiling, you can also +use the `--target=TYPE' option to select the type of system they will +produce code for and the `--build=TYPE' option to select the type of +system on which you are compiling the package. + +Sharing Defaults +================ + + If you want to set default values for `configure' scripts to share, +you can create a site shell script called `config.site' that gives +default values for variables like `CC', `cache_file', and `prefix'. +`configure' looks for `PREFIX/share/config.site' if it exists, then +`PREFIX/etc/config.site' if it exists. Or, you can set the +`CONFIG_SITE' environment variable to the location of the site script. +A warning: not all `configure' scripts look for a site script. + +Operation Controls +================== + + `configure' recognizes the following options to control how it +operates. + +`--cache-file=FILE' + Use and save the results of the tests in FILE instead of + `./config.cache'. Set FILE to `/dev/null' to disable caching, for + debugging `configure'. + +`--help' + Print a summary of the options to `configure', and exit. + +`--quiet' +`--silent' +`-q' + Do not print messages saying which checks are being made. To + suppress all normal output, redirect it to `/dev/null' (any error + messages will still be shown). + +`--srcdir=DIR' + Look for the package's source code in directory DIR. Usually + `configure' can determine that directory automatically. + +`--version' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`configure' also accepts some other, not widely useful, options. diff --git a/pcre/install-sh b/pcre/install-sh new file mode 100644 index 00000000..e9de2384 --- /dev/null +++ b/pcre/install-sh @@ -0,0 +1,251 @@ +#!/bin/sh +# +# install - install a program, script, or datafile +# This comes from X11R5 (mit/util/scripts/install.sh). +# +# Copyright 1991 by the Massachusetts Institute of Technology +# +# Permission to use, copy, modify, distribute, and sell this software and its +# documentation for any purpose is hereby granted without fee, provided that +# the above copyright notice appear in all copies and that both that +# copyright notice and this permission notice appear in supporting +# documentation, and that the name of M.I.T. not be used in advertising or +# publicity pertaining to distribution of the software without specific, +# written prior permission. M.I.T. makes no representations about the +# suitability of this software for any purpose. It is provided "as is" +# without express or implied warranty. +# +# Calling this script install-sh is preferred over install.sh, to prevent +# `make' implicit rules from creating a file called install from it +# when there is no Makefile. +# +# This script is compatible with the BSD install script, but was written +# from scratch. It can only install one file at a time, a restriction +# shared with many OS's install programs. + + +# set DOITPROG to echo to test this script + +# Don't use :- since 4.3BSD and earlier shells don't like it. +doit="${DOITPROG-}" + + +# put in absolute paths if you don't have them in your path; or use env. vars. + +mvprog="${MVPROG-mv}" +cpprog="${CPPROG-cp}" +chmodprog="${CHMODPROG-chmod}" +chownprog="${CHOWNPROG-chown}" +chgrpprog="${CHGRPPROG-chgrp}" +stripprog="${STRIPPROG-strip}" +rmprog="${RMPROG-rm}" +mkdirprog="${MKDIRPROG-mkdir}" + +transformbasename="" +transform_arg="" +instcmd="$mvprog" +chmodcmd="$chmodprog 0755" +chowncmd="" +chgrpcmd="" +stripcmd="" +rmcmd="$rmprog -f" +mvcmd="$mvprog" +src="" +dst="" +dir_arg="" + +while [ x"$1" != x ]; do + case $1 in + -c) instcmd="$cpprog" + shift + continue;; + + -d) dir_arg=true + shift + continue;; + + -m) chmodcmd="$chmodprog $2" + shift + shift + continue;; + + -o) chowncmd="$chownprog $2" + shift + shift + continue;; + + -g) chgrpcmd="$chgrpprog $2" + shift + shift + continue;; + + -s) stripcmd="$stripprog" + shift + continue;; + + -t=*) transformarg=`echo $1 | sed 's/-t=//'` + shift + continue;; + + -b=*) transformbasename=`echo $1 | sed 's/-b=//'` + shift + continue;; + + *) if [ x"$src" = x ] + then + src=$1 + else + # this colon is to work around a 386BSD /bin/sh bug + : + dst=$1 + fi + shift + continue;; + esac +done + +if [ x"$src" = x ] +then + echo "install: no input file specified" + exit 1 +else + true +fi + +if [ x"$dir_arg" != x ]; then + dst=$src + src="" + + if [ -d $dst ]; then + instcmd=: + chmodcmd="" + else + instcmd=mkdir + fi +else + +# Waiting for this to be detected by the "$instcmd $src $dsttmp" command +# might cause directories to be created, which would be especially bad +# if $src (and thus $dsttmp) contains '*'. + + if [ -f $src -o -d $src ] + then + true + else + echo "install: $src does not exist" + exit 1 + fi + + if [ x"$dst" = x ] + then + echo "install: no destination specified" + exit 1 + else + true + fi + +# If destination is a directory, append the input filename; if your system +# does not like double slashes in filenames, you may need to add some logic + + if [ -d $dst ] + then + dst="$dst"/`basename $src` + else + true + fi +fi + +## this sed command emulates the dirname command +dstdir=`echo $dst | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'` + +# Make sure that the destination directory exists. +# this part is taken from Noah Friedman's mkinstalldirs script + +# Skip lots of stat calls in the usual case. +if [ ! -d "$dstdir" ]; then +defaultIFS=' +' +IFS="${IFS-${defaultIFS}}" + +oIFS="${IFS}" +# Some sh's can't handle IFS=/ for some reason. +IFS='%' +set - `echo ${dstdir} | sed -e 's@/@%@g' -e 's@^%@/@'` +IFS="${oIFS}" + +pathcomp='' + +while [ $# -ne 0 ] ; do + pathcomp="${pathcomp}${1}" + shift + + if [ ! -d "${pathcomp}" ] ; + then + $mkdirprog "${pathcomp}" + else + true + fi + + pathcomp="${pathcomp}/" +done +fi + +if [ x"$dir_arg" != x ] +then + $doit $instcmd $dst && + + if [ x"$chowncmd" != x ]; then $doit $chowncmd $dst; else true ; fi && + if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dst; else true ; fi && + if [ x"$stripcmd" != x ]; then $doit $stripcmd $dst; else true ; fi && + if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dst; else true ; fi +else + +# If we're going to rename the final executable, determine the name now. + + if [ x"$transformarg" = x ] + then + dstfile=`basename $dst` + else + dstfile=`basename $dst $transformbasename | + sed $transformarg`$transformbasename + fi + +# don't allow the sed command to completely eliminate the filename + + if [ x"$dstfile" = x ] + then + dstfile=`basename $dst` + else + true + fi + +# Make a temp file name in the proper directory. + + dsttmp=$dstdir/#inst.$$# + +# Move or copy the file name to the temp name + + $doit $instcmd $src $dsttmp && + + trap "rm -f ${dsttmp}" 0 && + +# and set any options; do chmod last to preserve setuid bits + +# If any of these fail, we abort the whole thing. If we want to +# ignore errors from any of these, just make sure not to ignore +# errors from the above "$doit $instcmd $src $dsttmp" command. + + if [ x"$chowncmd" != x ]; then $doit $chowncmd $dsttmp; else true;fi && + if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dsttmp; else true;fi && + if [ x"$stripcmd" != x ]; then $doit $stripcmd $dsttmp; else true;fi && + if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dsttmp; else true;fi && + +# Now rename the file to the real destination. + + $doit $rmcmd -f $dstdir/$dstfile && + $doit $mvcmd $dsttmp $dstdir/$dstfile + +fi && + + +exit 0 diff --git a/pcre/internal.h b/pcre/internal.h new file mode 100644 index 00000000..25bb7f8f --- /dev/null +++ b/pcre/internal.h @@ -0,0 +1,381 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + + +/* This is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. See +the file Tech.Notes for some information on the internals. + +Written by: Philip Hazel + + Copyright (c) 1997-2000 University of Cambridge + +----------------------------------------------------------------------------- +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. +----------------------------------------------------------------------------- +*/ + +/* This header contains definitions that are shared between the different +modules, but which are not relevant to the outside. */ + +/* Get the definitions provided by running "configure" */ + +#include "config.h" + +/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), +define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY +is set. Otherwise, include an emulating function for those systems that have +neither (there some non-Unix environments where this is the case). This assumes +that all calls to memmove are moving strings upwards in store, which is the +case in PCRE. */ + +#if ! HAVE_MEMMOVE +#undef memmove /* some systems may have a macro */ +#if HAVE_BCOPY +#define memmove(a, b, c) bcopy(b, a, c) +#else +void * +pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) +{ +int i; +dest += n; +src += n; +for (i = 0; i < n; ++i) *(--dest) = *(--src); +} +#define memmove(a, b, c) pcre_memmove(a, b, c) +#endif +#endif + +/* Standard C headers plus the external interface definition */ + +#include +#include +#include +#include +#include +#include +#include "pcre.h" + +/* In case there is no definition of offsetof() provided - though any proper +Standard C system should have one. */ + +#ifndef offsetof +#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field)) +#endif + +/* These are the public options that can change during matching. */ + +#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) + +/* Private options flags start at the most significant end of the four bytes, +but skip the top bit so we can use ints for convenience without getting tangled +with negative values. The public options defined in pcre.h start at the least +significant end. Make sure they don't overlap, though now that we have expanded +to four bytes there is plenty of space. */ + +#define PCRE_FIRSTSET 0x40000000 /* first_char is set */ +#define PCRE_REQCHSET 0x20000000 /* req_char is set */ +#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ +#define PCRE_INGROUP 0x08000000 /* compiling inside a group */ +#define PCRE_ICHANGED 0x04000000 /* i option changes within regex */ + +/* Options for the "extra" block produced by pcre_study(). */ + +#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ + +/* Masks for identifying the public options which are permitted at compile +time, run time or study time, respectively. */ + +#define PUBLIC_OPTIONS \ + (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ + PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8) + +#define PUBLIC_EXEC_OPTIONS \ + (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY) + +#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ + +/* Magic number to provide a small check against being handed junk. */ + +#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ + +/* Miscellaneous definitions */ + +typedef int BOOL; + +#define FALSE 0 +#define TRUE 1 + +/* These are escaped items that aren't just an encoding of a particular data +value such as \n. They must have non-zero values, as check_escape() returns +their negation. Also, they must appear in the same order as in the opcode +definitions below, up to ESC_z. The final one must be ESC_REF as subsequent +values are used for \1, \2, \3, etc. There is a test in the code for an escape +greater than ESC_b and less than ESC_X to detect the types that may be +repeated. If any new escapes are put in-between that don't consume a character, +that code will have to change. */ + +enum { ESC_A = 1, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, ESC_w, + ESC_Z, ESC_z, ESC_REF }; + +/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets +that extract substrings. Starting from 1 (i.e. after OP_END), the values up to +OP_EOD must correspond in order to the list of escapes immediately above. */ + +enum { + OP_END, /* End of pattern */ + + /* Values corresponding to backslashed metacharacters */ + + OP_SOD, /* Start of data: \A */ + OP_NOT_WORD_BOUNDARY, /* \B */ + OP_WORD_BOUNDARY, /* \b */ + OP_NOT_DIGIT, /* \D */ + OP_DIGIT, /* \d */ + OP_NOT_WHITESPACE, /* \S */ + OP_WHITESPACE, /* \s */ + OP_NOT_WORDCHAR, /* \W */ + OP_WORDCHAR, /* \w */ + OP_EODN, /* End of data or \n at end of data: \Z. */ + OP_EOD, /* End of data: \z */ + + OP_OPT, /* Set runtime options */ + OP_CIRC, /* Start of line - varies with multiline switch */ + OP_DOLL, /* End of line - varies with multiline switch */ + OP_ANY, /* Match any character */ + OP_CHARS, /* Match string of characters */ + OP_NOT, /* Match anything but the following char */ + + OP_STAR, /* The maximizing and minimizing versions of */ + OP_MINSTAR, /* all these opcodes must come in pairs, with */ + OP_PLUS, /* the minimizing one second. */ + OP_MINPLUS, /* This first set applies to single characters */ + OP_QUERY, + OP_MINQUERY, + OP_UPTO, /* From 0 to n matches */ + OP_MINUPTO, + OP_EXACT, /* Exactly n matches */ + + OP_NOTSTAR, /* The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* all these opcodes must come in pairs, with */ + OP_NOTPLUS, /* the minimizing one second. */ + OP_NOTMINPLUS, /* This first set applies to "not" single characters */ + OP_NOTQUERY, + OP_NOTMINQUERY, + OP_NOTUPTO, /* From 0 to n matches */ + OP_NOTMINUPTO, + OP_NOTEXACT, /* Exactly n matches */ + + OP_TYPESTAR, /* The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* all these opcodes must come in pairs, with */ + OP_TYPEPLUS, /* the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* be in exactly the same order as those above. */ + OP_TYPEQUERY, /* This set applies to character types such as \d */ + OP_TYPEMINQUERY, + OP_TYPEUPTO, /* From 0 to n matches */ + OP_TYPEMINUPTO, + OP_TYPEEXACT, /* Exactly n matches */ + + OP_CRSTAR, /* The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* all these opcodes must come in pairs, with */ + OP_CRPLUS, /* the minimizing one second. These codes must */ + OP_CRMINPLUS, /* be in exactly the same order as those above. */ + OP_CRQUERY, /* These are for character classes and back refs */ + OP_CRMINQUERY, + OP_CRRANGE, /* These are different to the three seta above. */ + OP_CRMINRANGE, + + OP_CLASS, /* Match a character class */ + OP_REF, /* Match a back reference */ + OP_RECURSE, /* Match this pattern recursively */ + + OP_ALT, /* Start of alternation */ + OP_KET, /* End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* These two must remain together and in this */ + OP_KETRMIN, /* order. They are for groups the repeat for ever. */ + + /* The assertions must come before ONCE and COND */ + + OP_ASSERT, /* Positive lookahead */ + OP_ASSERT_NOT, /* Negative lookahead */ + OP_ASSERTBACK, /* Positive lookbehind */ + OP_ASSERTBACK_NOT, /* Negative lookbehind */ + OP_REVERSE, /* Move pointer back - used in lookbehind assertions */ + + /* ONCE and COND must come after the assertions, with ONCE first, as there's + a test for >= ONCE for a subpattern that isn't an assertion. */ + + OP_ONCE, /* Once matched, don't back up into the subpattern */ + OP_COND, /* Conditional group */ + OP_CREF, /* Used to hold an extraction string number */ + + OP_BRAZERO, /* These two must remain together and in this */ + OP_BRAMINZERO, /* order. */ + + OP_BRA /* This and greater values are used for brackets that + extract substrings. */ +}; + +/* The highest extraction number. This is limited by the number of opcodes +left after OP_BRA, i.e. 255 - OP_BRA. We actually set it somewhat lower. */ + +#define EXTRACT_MAX 99 + +/* The texts of compile-time error messages are defined as macros here so that +they can be accessed by the POSIX wrapper and converted into error codes. Yes, +I could have used error codes in the first place, but didn't feel like changing +just to accommodate the POSIX wrapper. */ + +#define ERR1 "\\ at end of pattern" +#define ERR2 "\\c at end of pattern" +#define ERR3 "unrecognized character follows \\" +#define ERR4 "numbers out of order in {} quantifier" +#define ERR5 "number too big in {} quantifier" +#define ERR6 "missing terminating ] for character class" +#define ERR7 "invalid escape sequence in character class" +#define ERR8 "range out of order in character class" +#define ERR9 "nothing to repeat" +#define ERR10 "operand of unlimited repeat could match the empty string" +#define ERR11 "internal error: unexpected repeat" +#define ERR12 "unrecognized character after (?" +#define ERR13 "too many capturing parenthesized sub-patterns" +#define ERR14 "missing )" +#define ERR15 "back reference to non-existent subpattern" +#define ERR16 "erroffset passed as NULL" +#define ERR17 "unknown option bit(s) set" +#define ERR18 "missing ) after comment" +#define ERR19 "too many sets of parentheses" +#define ERR20 "regular expression too large" +#define ERR21 "failed to get memory" +#define ERR22 "unmatched parentheses" +#define ERR23 "internal error: code overflow" +#define ERR24 "unrecognized character after (?<" +#define ERR25 "lookbehind assertion is not fixed length" +#define ERR26 "malformed number after (?(" +#define ERR27 "conditional group contains more than two branches" +#define ERR28 "assertion expected after (?(" +#define ERR29 "(?p must be followed by )" +#define ERR30 "unknown POSIX class name" +#define ERR31 "POSIX collating elements are not supported" +#define ERR32 "this version of PCRE is not compiled with PCRE_UTF8 support" +#define ERR33 "characters with values > 255 are not yet supported in classes" +#define ERR34 "character value in \\x{...} sequence is too large" +#define ERR35 "invalid condition (?(0)" + +/* All character handling must be done as unsigned characters. Otherwise there +are problems with top-bit-set characters and functions such as isspace(). +However, we leave the interface to the outside world as char *, because that +should make things easier for callers. We define a short type for unsigned char +to save lots of typing. I tried "uchar", but it causes problems on Digital +Unix, where it is defined in sys/types, so use "uschar" instead. */ + +typedef unsigned char uschar; + +/* The real format of the start of the pcre block; the actual code vector +runs on as long as necessary after the end. */ + +typedef struct real_pcre { + unsigned long int magic_number; + size_t size; + const unsigned char *tables; + unsigned long int options; + uschar top_bracket; + uschar top_backref; + uschar first_char; + uschar req_char; + uschar code[1]; +} real_pcre; + +/* The real format of the extra block returned by pcre_study(). */ + +typedef struct real_pcre_extra { + uschar options; + uschar start_bits[32]; +} real_pcre_extra; + + +/* Structure for passing "static" information around between the functions +doing the compiling, so that they are thread-safe. */ + +typedef struct compile_data { + const uschar *lcc; /* Points to lower casing table */ + const uschar *fcc; /* Points to case-flipping table */ + const uschar *cbits; /* Points to character type table */ + const uschar *ctypes; /* Points to table of type maps */ +} compile_data; + +/* Structure for passing "static" information around between the functions +doing the matching, so that they are thread-safe. */ + +typedef struct match_data { + int errorcode; /* As it says */ + int *offset_vector; /* Offset vector */ + int offset_end; /* One past the end */ + int offset_max; /* The maximum usable for return data */ + const uschar *lcc; /* Points to lower casing table */ + const uschar *ctypes; /* Points to table of type maps */ + BOOL offset_overflow; /* Set if too many extractions */ + BOOL notbol; /* NOTBOL flag */ + BOOL noteol; /* NOTEOL flag */ + BOOL utf8; /* UTF8 flag */ + BOOL endonly; /* Dollar not before final \n */ + BOOL notempty; /* Empty string match not wanted */ + const uschar *start_pattern; /* For use when recursing */ + const uschar *start_subject; /* Start of the subject string */ + const uschar *end_subject; /* End of the subject string */ + const uschar *start_match; /* Start of this match attempt */ + const uschar *end_match_ptr; /* Subject position at end match */ + int end_offset_top; /* Highwater mark at end of match */ +} match_data; + +/* Bit definitions for entries in the pcre_ctypes table. */ + +#define ctype_space 0x01 +#define ctype_letter 0x02 +#define ctype_digit 0x04 +#define ctype_xdigit 0x08 +#define ctype_word 0x10 /* alphameric or '_' */ +#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ + +/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set +of bits for a class map. Some classes are built by combining these tables. */ + +#define cbit_space 0 /* [:space:] or \s */ +#define cbit_xdigit 32 /* [:xdigit:] */ +#define cbit_digit 64 /* [:digit:] or \d */ +#define cbit_upper 96 /* [:upper:] */ +#define cbit_lower 128 /* [:lower:] */ +#define cbit_word 160 /* [:word:] or \w */ +#define cbit_graph 192 /* [:graph:] */ +#define cbit_print 224 /* [:print:] */ +#define cbit_punct 256 /* [:punct:] */ +#define cbit_cntrl 288 /* [:cntrl:] */ +#define cbit_length 320 /* Length of the cbits table */ + +/* Offsets of the various tables from the base tables pointer, and +total length. */ + +#define lcc_offset 0 +#define fcc_offset 256 +#define cbits_offset 512 +#define ctypes_offset (cbits_offset + cbit_length) +#define tables_length (ctypes_offset + 256) + +/* End of internal.h */ diff --git a/pcre/licence b/pcre/licence new file mode 100644 index 00000000..34d20db9 --- /dev/null +++ b/pcre/licence @@ -0,0 +1,46 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Written by: Philip Hazel + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2000 University of Cambridge + +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. In practice, this means that if you use + PCRE in software which you distribute to others, commercially or + otherwise, you must put a sentence like this + + Regular expression support is provided by the PCRE library package, + which is open source software, written by Philip Hazel, and copyright + by the University of Cambridge, England. + + somewhere reasonably visible in your documentation and in any relevant + files or online help data or similar. A reference to the ftp site for + the source, that is, to + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/ + + should also be given in the documentation. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. + +End diff --git a/pcre/ltconfig b/pcre/ltconfig new file mode 100644 index 00000000..a01334f9 --- /dev/null +++ b/pcre/ltconfig @@ -0,0 +1,3078 @@ +#! /bin/sh + +# ltconfig - Create a system-specific libtool. +# Copyright (C) 1996-1999 Free Software Foundation, Inc. +# Originally by Gordon Matzigkeit , 1996 +# +# This file is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# A lot of this script is taken from autoconf-2.10. + +# Check that we are running under the correct shell. +SHELL=${CONFIG_SHELL-/bin/sh} +echo=echo +if test "X$1" = X--no-reexec; then + # Discard the --no-reexec flag, and continue. + shift +elif test "X$1" = X--fallback-echo; then + # Avoid inline document here, it may be left over + : +elif test "X`($echo '\t') 2>/dev/null`" = 'X\t'; then + # Yippee, $echo works! + : +else + # Restart under the correct shell. + exec "$SHELL" "$0" --no-reexec ${1+"$@"} +fi + +if test "X$1" = X--fallback-echo; then + # used as fallback echo + shift + cat </dev/null`} + case X$UNAME in + *-DOS) PATH_SEPARATOR=';' ;; + *) PATH_SEPARATOR=':' ;; + esac +fi + +# The HP-UX ksh and POSIX shell print the target directory to stdout +# if CDPATH is set. +if test "X${CDPATH+set}" = Xset; then CDPATH=:; export CDPATH; fi + +if test "X${echo_test_string+set}" != Xset; then + # find a string as large as possible, as long as the shell can cope with it + for cmd in 'sed 50q "$0"' 'sed 20q "$0"' 'sed 10q "$0"' 'sed 2q "$0"' 'echo test'; do + # expected sizes: less than 2Kb, 1Kb, 512 bytes, 16 bytes, ... + if (echo_test_string="`eval $cmd`") 2>/dev/null && + echo_test_string="`eval $cmd`" && + (test "X$echo_test_string" = "X$echo_test_string") 2>/dev/null; then + break + fi + done +fi + +if test "X`($echo '\t') 2>/dev/null`" != 'X\t' || + test "X`($echo "$echo_test_string") 2>/dev/null`" != X"$echo_test_string"; then + # The Solaris, AIX, and Digital Unix default echo programs unquote + # backslashes. This makes it impossible to quote backslashes using + # echo "$something" | sed 's/\\/\\\\/g' + # + # So, first we look for a working echo in the user's PATH. + + IFS="${IFS= }"; save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + for dir in $PATH /usr/ucb; do + if (test -f $dir/echo || test -f $dir/echo$ac_exeext) && + test "X`($dir/echo '\t') 2>/dev/null`" = 'X\t' && + test "X`($dir/echo "$echo_test_string") 2>/dev/null`" = X"$echo_test_string"; then + echo="$dir/echo" + break + fi + done + IFS="$save_ifs" + + if test "X$echo" = Xecho; then + # We didn't find a better echo, so look for alternatives. + if test "X`(print -r '\t') 2>/dev/null`" = 'X\t' && + test "X`(print -r "$echo_test_string") 2>/dev/null`" = X"$echo_test_string"; then + # This shell has a builtin print -r that does the trick. + echo='print -r' + elif (test -f /bin/ksh || test -f /bin/ksh$ac_exeext) && + test "X$CONFIG_SHELL" != X/bin/ksh; then + # If we have ksh, try running ltconfig again with it. + ORIGINAL_CONFIG_SHELL="${CONFIG_SHELL-/bin/sh}" + export ORIGINAL_CONFIG_SHELL + CONFIG_SHELL=/bin/ksh + export CONFIG_SHELL + exec "$CONFIG_SHELL" "$0" --no-reexec ${1+"$@"} + else + # Try using printf. + echo='printf "%s\n"' + if test "X`($echo '\t') 2>/dev/null`" = 'X\t' && + test "X`($echo "$echo_test_string") 2>/dev/null`" = X"$echo_test_string"; then + # Cool, printf works + : + elif test "X`("$ORIGINAL_CONFIG_SHELL" "$0" --fallback-echo '\t') 2>/dev/null`" = 'X\t' && + test "X`("$ORIGINAL_CONFIG_SHELL" "$0" --fallback-echo "$echo_test_string") 2>/dev/null`" = X"$echo_test_string"; then + CONFIG_SHELL="$ORIGINAL_CONFIG_SHELL" + export CONFIG_SHELL + SHELL="$CONFIG_SHELL" + export SHELL + echo="$CONFIG_SHELL $0 --fallback-echo" + elif test "X`("$CONFIG_SHELL" "$0" --fallback-echo '\t') 2>/dev/null`" = 'X\t' && + test "X`("$CONFIG_SHELL" "$0" --fallback-echo "$echo_test_string") 2>/dev/null`" = X"$echo_test_string"; then + echo="$CONFIG_SHELL $0 --fallback-echo" + else + # maybe with a smaller string... + prev=: + + for cmd in 'echo test' 'sed 2q "$0"' 'sed 10q "$0"' 'sed 20q "$0"' 'sed 50q "$0"'; do + if (test "X$echo_test_string" = "X`eval $cmd`") 2>/dev/null; then + break + fi + prev="$cmd" + done + + if test "$prev" != 'sed 50q "$0"'; then + echo_test_string=`eval $prev` + export echo_test_string + exec "${ORIGINAL_CONFIG_SHELL}" "$0" ${1+"$@"} + else + # Oops. We lost completely, so just stick with echo. + echo=echo + fi + fi + fi + fi +fi + +# Sed substitution that helps us do robust quoting. It backslashifies +# metacharacters that are still active within double-quoted strings. +Xsed='sed -e s/^X//' +sed_quote_subst='s/\([\\"\\`$\\\\]\)/\\\1/g' + +# Same as above, but do not quote variable references. +double_quote_subst='s/\([\\"\\`\\\\]\)/\\\1/g' + +# Sed substitution to delay expansion of an escaped shell variable in a +# double_quote_subst'ed string. +delay_variable_subst='s/\\\\\\\\\\\$/\\\\\\$/g' + +# The name of this program. +progname=`$echo "X$0" | $Xsed -e 's%^.*/%%'` + +# Constants: +PROGRAM=ltconfig +PACKAGE=libtool +VERSION=1.3.4 +TIMESTAMP=" (1.385.2.196 1999/12/07 21:47:57)" +ac_compile='${CC-cc} -c $CFLAGS $CPPFLAGS conftest.$ac_ext 1>&5' +ac_link='${CC-cc} -o conftest $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS 1>&5' +rm="rm -f" + +help="Try \`$progname --help' for more information." + +# Global variables: +default_ofile=libtool +can_build_shared=yes +enable_shared=yes +# All known linkers require a `.a' archive for static linking (except M$VC, +# which needs '.lib'). +enable_static=yes +enable_fast_install=yes +enable_dlopen=unknown +enable_win32_dll=no +ltmain= +silent= +srcdir= +ac_config_guess= +ac_config_sub= +host= +nonopt= +ofile="$default_ofile" +verify_host=yes +with_gcc=no +with_gnu_ld=no +need_locks=yes +ac_ext=c +objext=o +libext=a +exeext= +cache_file= + +old_AR="$AR" +old_CC="$CC" +old_CFLAGS="$CFLAGS" +old_CPPFLAGS="$CPPFLAGS" +old_LDFLAGS="$LDFLAGS" +old_LD="$LD" +old_LN_S="$LN_S" +old_LIBS="$LIBS" +old_NM="$NM" +old_RANLIB="$RANLIB" +old_DLLTOOL="$DLLTOOL" +old_OBJDUMP="$OBJDUMP" +old_AS="$AS" + +# Parse the command line options. +args= +prev= +for option +do + case "$option" in + -*=*) optarg=`echo "$option" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + # If the previous option needs an argument, assign it. + if test -n "$prev"; then + eval "$prev=\$option" + prev= + continue + fi + + case "$option" in + --help) cat <&2 + echo "$help" 1>&2 + exit 1 + ;; + + *) + if test -z "$ltmain"; then + ltmain="$option" + elif test -z "$host"; then +# This generates an unnecessary warning for sparc-sun-solaris4.1.3_U1 +# if test -n "`echo $option| sed 's/[-a-z0-9.]//g'`"; then +# echo "$progname: warning \`$option' is not a valid host type" 1>&2 +# fi + host="$option" + else + echo "$progname: too many arguments" 1>&2 + echo "$help" 1>&2 + exit 1 + fi ;; + esac +done + +if test -z "$ltmain"; then + echo "$progname: you must specify a LTMAIN file" 1>&2 + echo "$help" 1>&2 + exit 1 +fi + +if test ! -f "$ltmain"; then + echo "$progname: \`$ltmain' does not exist" 1>&2 + echo "$help" 1>&2 + exit 1 +fi + +# Quote any args containing shell metacharacters. +ltconfig_args= +for arg +do + case "$arg" in + *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?]*) + ltconfig_args="$ltconfig_args '$arg'" ;; + *) ltconfig_args="$ltconfig_args $arg" ;; + esac +done + +# A relevant subset of AC_INIT. + +# File descriptor usage: +# 0 standard input +# 1 file creation +# 2 errors and warnings +# 3 some systems may open it to /dev/tty +# 4 used on the Kubota Titan +# 5 compiler messages saved in config.log +# 6 checking for... messages and results +if test "$silent" = yes; then + exec 6>/dev/null +else + exec 6>&1 +fi +exec 5>>./config.log + +# NLS nuisances. +# Only set LANG and LC_ALL to C if already set. +# These must not be set unconditionally because not all systems understand +# e.g. LANG=C (notably SCO). +if test "X${LC_ALL+set}" = Xset; then LC_ALL=C; export LC_ALL; fi +if test "X${LANG+set}" = Xset; then LANG=C; export LANG; fi + +if test -n "$cache_file" && test -r "$cache_file"; then + echo "loading cache $cache_file within ltconfig" + . $cache_file +fi + +if (echo "testing\c"; echo 1,2,3) | grep c >/dev/null; then + # Stardent Vistra SVR4 grep lacks -e, says ghazi@caip.rutgers.edu. + if (echo -n testing; echo 1,2,3) | sed s/-n/xn/ | grep xn >/dev/null; then + ac_n= ac_c=' +' ac_t=' ' + else + ac_n=-n ac_c= ac_t= + fi +else + ac_n= ac_c='\c' ac_t= +fi + +if test -z "$srcdir"; then + # Assume the source directory is the same one as the path to LTMAIN. + srcdir=`$echo "X$ltmain" | $Xsed -e 's%/[^/]*$%%'` + test "$srcdir" = "$ltmain" && srcdir=. +fi + +trap "$rm conftest*; exit 1" 1 2 15 +if test "$verify_host" = yes; then + # Check for config.guess and config.sub. + ac_aux_dir= + for ac_dir in $srcdir $srcdir/.. $srcdir/../..; do + if test -f $ac_dir/config.guess; then + ac_aux_dir=$ac_dir + break + fi + done + if test -z "$ac_aux_dir"; then + echo "$progname: cannot find config.guess in $srcdir $srcdir/.. $srcdir/../.." 1>&2 + echo "$help" 1>&2 + exit 1 + fi + ac_config_guess=$ac_aux_dir/config.guess + ac_config_sub=$ac_aux_dir/config.sub + + # Make sure we can run config.sub. + if $SHELL $ac_config_sub sun4 >/dev/null 2>&1; then : + else + echo "$progname: cannot run $ac_config_sub" 1>&2 + echo "$help" 1>&2 + exit 1 + fi + + echo $ac_n "checking host system type""... $ac_c" 1>&6 + + host_alias=$host + case "$host_alias" in + "") + if host_alias=`$SHELL $ac_config_guess`; then : + else + echo "$progname: cannot guess host type; you must specify one" 1>&2 + echo "$help" 1>&2 + exit 1 + fi ;; + esac + host=`$SHELL $ac_config_sub $host_alias` + echo "$ac_t$host" 1>&6 + + # Make sure the host verified. + test -z "$host" && exit 1 + +elif test -z "$host"; then + echo "$progname: you must specify a host type if you use \`--no-verify'" 1>&2 + echo "$help" 1>&2 + exit 1 +else + host_alias=$host +fi + +# Transform linux* to *-*-linux-gnu*, to support old configure scripts. +case "$host_os" in +linux-gnu*) ;; +linux*) host=`echo $host | sed 's/^\(.*-.*-linux\)\(.*\)$/\1-gnu\2/'` +esac + +host_cpu=`echo $host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` +host_vendor=`echo $host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` +host_os=`echo $host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` + +case "$host_os" in +aix3*) + # AIX sometimes has problems with the GCC collect2 program. For some + # reason, if we set the COLLECT_NAMES environment variable, the problems + # vanish in a puff of smoke. + if test "X${COLLECT_NAMES+set}" != Xset; then + COLLECT_NAMES= + export COLLECT_NAMES + fi + ;; +esac + +# Determine commands to create old-style static archives. +old_archive_cmds='$AR cru $oldlib$oldobjs' +old_postinstall_cmds='chmod 644 $oldlib' +old_postuninstall_cmds= + +# Set a sane default for `AR'. +test -z "$AR" && AR=ar + +# Set a sane default for `OBJDUMP'. +test -z "$OBJDUMP" && OBJDUMP=objdump + +# If RANLIB is not set, then run the test. +if test "${RANLIB+set}" != "set"; then + result=no + + echo $ac_n "checking for ranlib... $ac_c" 1>&6 + IFS="${IFS= }"; save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + for dir in $PATH; do + test -z "$dir" && dir=. + if test -f $dir/ranlib || test -f $dir/ranlib$ac_exeext; then + RANLIB="ranlib" + result="ranlib" + break + fi + done + IFS="$save_ifs" + + echo "$ac_t$result" 1>&6 +fi + +if test -n "$RANLIB"; then + old_archive_cmds="$old_archive_cmds~\$RANLIB \$oldlib" + old_postinstall_cmds="\$RANLIB \$oldlib~$old_postinstall_cmds" +fi + +# Set sane defaults for `DLLTOOL', `OBJDUMP', and `AS', used on cygwin. +test -z "$DLLTOOL" && DLLTOOL=dlltool +test -z "$OBJDUMP" && OBJDUMP=objdump +test -z "$AS" && AS=as + +# Check to see if we are using GCC. +if test "$with_gcc" != yes || test -z "$CC"; then + # If CC is not set, then try to find GCC or a usable CC. + if test -z "$CC"; then + echo $ac_n "checking for gcc... $ac_c" 1>&6 + IFS="${IFS= }"; save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + for dir in $PATH; do + test -z "$dir" && dir=. + if test -f $dir/gcc || test -f $dir/gcc$ac_exeext; then + CC="gcc" + break + fi + done + IFS="$save_ifs" + + if test -n "$CC"; then + echo "$ac_t$CC" 1>&6 + else + echo "$ac_t"no 1>&6 + fi + fi + + # Not "gcc", so try "cc", rejecting "/usr/ucb/cc". + if test -z "$CC"; then + echo $ac_n "checking for cc... $ac_c" 1>&6 + IFS="${IFS= }"; save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + cc_rejected=no + for dir in $PATH; do + test -z "$dir" && dir=. + if test -f $dir/cc || test -f $dir/cc$ac_exeext; then + if test "$dir/cc" = "/usr/ucb/cc"; then + cc_rejected=yes + continue + fi + CC="cc" + break + fi + done + IFS="$save_ifs" + if test $cc_rejected = yes; then + # We found a bogon in the path, so make sure we never use it. + set dummy $CC + shift + if test $# -gt 0; then + # We chose a different compiler from the bogus one. + # However, it has the same name, so the bogon will be chosen + # first if we set CC to just the name; use the full file name. + shift + set dummy "$dir/cc" "$@" + shift + CC="$@" + fi + fi + + if test -n "$CC"; then + echo "$ac_t$CC" 1>&6 + else + echo "$ac_t"no 1>&6 + fi + + if test -z "$CC"; then + echo "$progname: error: no acceptable cc found in \$PATH" 1>&2 + exit 1 + fi + fi + + # Now see if the compiler is really GCC. + with_gcc=no + echo $ac_n "checking whether we are using GNU C... $ac_c" 1>&6 + echo "$progname:581: checking whether we are using GNU C" >&5 + + $rm conftest.c + cat > conftest.c <&5; (eval $ac_try) 2>&5; }; } | egrep yes >/dev/null 2>&1; then + with_gcc=yes + fi + $rm conftest.c + echo "$ac_t$with_gcc" 1>&6 +fi + +# Allow CC to be a program name with arguments. +set dummy $CC +compiler="$2" + +echo $ac_n "checking for object suffix... $ac_c" 1>&6 +$rm conftest* +echo 'int i = 1;' > conftest.c +echo "$progname:603: checking for object suffix" >& 5 +if { (eval echo $progname:604: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>conftest.err; }; then + # Append any warnings to the config.log. + cat conftest.err 1>&5 + + for ac_file in conftest.*; do + case $ac_file in + *.c) ;; + *) objext=`echo $ac_file | sed -e s/conftest.//` ;; + esac + done +else + cat conftest.err 1>&5 + echo "$progname: failed program was:" >&5 + cat conftest.c >&5 +fi +$rm conftest* +echo "$ac_t$objext" 1>&6 + +echo $ac_n "checking for executable suffix... $ac_c" 1>&6 +if eval "test \"`echo '$''{'ac_cv_exeext'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + ac_cv_exeext="no" + $rm conftest* + echo 'main () { return 0; }' > conftest.c + echo "$progname:629: checking for executable suffix" >& 5 + if { (eval echo $progname:630: \"$ac_link\") 1>&5; (eval $ac_link) 2>conftest.err; }; then + # Append any warnings to the config.log. + cat conftest.err 1>&5 + + for ac_file in conftest.*; do + case $ac_file in + *.c | *.err | *.$objext ) ;; + *) ac_cv_exeext=.`echo $ac_file | sed -e s/conftest.//` ;; + esac + done + else + cat conftest.err 1>&5 + echo "$progname: failed program was:" >&5 + cat conftest.c >&5 + fi + $rm conftest* +fi +if test "X$ac_cv_exeext" = Xno; then + exeext="" +else + exeext="$ac_cv_exeext" +fi +echo "$ac_t$ac_cv_exeext" 1>&6 + +echo $ac_n "checking for $compiler option to produce PIC... $ac_c" 1>&6 +pic_flag= +special_shlib_compile_flags= +wl= +link_static_flag= +no_builtin_flag= + +if test "$with_gcc" = yes; then + wl='-Wl,' + link_static_flag='-static' + + case "$host_os" in + beos* | irix5* | irix6* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + aix*) + # Below there is a dirty hack to force normal static linking with -ldl + # The problem is because libdl dynamically linked with both libc and + # libC (AIX C++ library), which obviously doesn't included in libraries + # list by gcc. This cause undefined symbols with -static flags. + # This hack allows C programs to be linked with "-static -ldl", but + # we not sure about C++ programs. + link_static_flag="$link_static_flag ${wl}-lC" + ;; + cygwin* | mingw* | os2*) + # We can build DLLs from non-PIC. + ;; + amigaos*) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the `-m68020' flag to GCC prevents building anything better, + # like `-m68040'. + pic_flag='-m68020 -resident32 -malways-restore-a4' + ;; + sysv4*MP*) + if test -d /usr/nec; then + pic_flag=-Kconform_pic + fi + ;; + *) + pic_flag='-fPIC' + ;; + esac +else + # PORTME Check for PIC flags for the system compiler. + case "$host_os" in + aix3* | aix4*) + # All AIX code is PIC. + link_static_flag='-bnso -bI:/lib/syscalls.exp' + ;; + + hpux9* | hpux10* | hpux11*) + # Is there a better link_static_flag that works with the bundled CC? + wl='-Wl,' + link_static_flag="${wl}-a ${wl}archive" + pic_flag='+Z' + ;; + + irix5* | irix6*) + wl='-Wl,' + link_static_flag='-non_shared' + # PIC (with -KPIC) is the default. + ;; + + cygwin* | mingw* | os2*) + # We can build DLLs from non-PIC. + ;; + + osf3* | osf4* | osf5*) + # All OSF/1 code is PIC. + wl='-Wl,' + link_static_flag='-non_shared' + ;; + + sco3.2v5*) + pic_flag='-Kpic' + link_static_flag='-dn' + special_shlib_compile_flags='-belf' + ;; + + solaris*) + pic_flag='-KPIC' + link_static_flag='-Bstatic' + wl='-Wl,' + ;; + + sunos4*) + pic_flag='-PIC' + link_static_flag='-Bstatic' + wl='-Qoption ld ' + ;; + + sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) + pic_flag='-KPIC' + link_static_flag='-Bstatic' + wl='-Wl,' + ;; + + uts4*) + pic_flag='-pic' + link_static_flag='-Bstatic' + ;; + sysv4*MP*) + if test -d /usr/nec ;then + pic_flag='-Kconform_pic' + link_static_flag='-Bstatic' + fi + ;; + *) + can_build_shared=no + ;; + esac +fi + +if test -n "$pic_flag"; then + echo "$ac_t$pic_flag" 1>&6 + + # Check to make sure the pic_flag actually works. + echo $ac_n "checking if $compiler PIC flag $pic_flag works... $ac_c" 1>&6 + $rm conftest* + echo "int some_variable = 0;" > conftest.c + save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS $pic_flag -DPIC" + echo "$progname:776: checking if $compiler PIC flag $pic_flag works" >&5 + if { (eval echo $progname:777: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>conftest.err; } && test -s conftest.$objext; then + # Append any warnings to the config.log. + cat conftest.err 1>&5 + + case "$host_os" in + hpux9* | hpux10* | hpux11*) + # On HP-UX, both CC and GCC only warn that PIC is supported... then they + # create non-PIC objects. So, if there were any warnings, we assume that + # PIC is not supported. + if test -s conftest.err; then + echo "$ac_t"no 1>&6 + can_build_shared=no + pic_flag= + else + echo "$ac_t"yes 1>&6 + pic_flag=" $pic_flag" + fi + ;; + *) + echo "$ac_t"yes 1>&6 + pic_flag=" $pic_flag" + ;; + esac + else + # Append any errors to the config.log. + cat conftest.err 1>&5 + can_build_shared=no + pic_flag= + echo "$ac_t"no 1>&6 + fi + CFLAGS="$save_CFLAGS" + $rm conftest* +else + echo "$ac_t"none 1>&6 +fi + +# Check to see if options -o and -c are simultaneously supported by compiler +echo $ac_n "checking if $compiler supports -c -o file.o... $ac_c" 1>&6 +$rm -r conftest 2>/dev/null +mkdir conftest +cd conftest +$rm conftest* +echo "int some_variable = 0;" > conftest.c +mkdir out +# According to Tom Tromey, Ian Lance Taylor reported there are C compilers +# that will create temporary files in the current directory regardless of +# the output directory. Thus, making CWD read-only will cause this test +# to fail, enabling locking or at least warning the user not to do parallel +# builds. +chmod -w . +save_CFLAGS="$CFLAGS" +CFLAGS="$CFLAGS -o out/conftest2.o" +echo "$progname:829: checking if $compiler supports -c -o file.o" >&5 +if { (eval echo $progname:830: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>out/conftest.err; } && test -s out/conftest2.o; then + + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s out/conftest.err; then + echo "$ac_t"no 1>&6 + compiler_c_o=no + else + echo "$ac_t"yes 1>&6 + compiler_c_o=yes + fi +else + # Append any errors to the config.log. + cat out/conftest.err 1>&5 + compiler_c_o=no + echo "$ac_t"no 1>&6 +fi +CFLAGS="$save_CFLAGS" +chmod u+w . +$rm conftest* out/* +rmdir out +cd .. +rmdir conftest +$rm -r conftest 2>/dev/null + +if test x"$compiler_c_o" = x"yes"; then + # Check to see if we can write to a .lo + echo $ac_n "checking if $compiler supports -c -o file.lo... $ac_c" 1>&6 + $rm conftest* + echo "int some_variable = 0;" > conftest.c + save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS -c -o conftest.lo" + echo "$progname:862: checking if $compiler supports -c -o file.lo" >&5 +if { (eval echo $progname:863: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>conftest.err; } && test -s conftest.lo; then + + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + echo "$ac_t"no 1>&6 + compiler_o_lo=no + else + echo "$ac_t"yes 1>&6 + compiler_o_lo=yes + fi + else + # Append any errors to the config.log. + cat conftest.err 1>&5 + compiler_o_lo=no + echo "$ac_t"no 1>&6 + fi + CFLAGS="$save_CFLAGS" + $rm conftest* +else + compiler_o_lo=no +fi + +# Check to see if we can do hard links to lock some files if needed +hard_links="nottested" +if test "$compiler_c_o" = no && test "$need_locks" != no; then + # do not overwrite the value of need_locks provided by the user + echo $ac_n "checking if we can lock with hard links... $ac_c" 1>&6 + hard_links=yes + $rm conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + echo "$ac_t$hard_links" 1>&6 + $rm conftest* + if test "$hard_links" = no; then + echo "*** WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2 + need_locks=warn + fi +else + need_locks=no +fi + +if test "$with_gcc" = yes; then + # Check to see if options -fno-rtti -fno-exceptions are supported by compiler + echo $ac_n "checking if $compiler supports -fno-rtti -fno-exceptions ... $ac_c" 1>&6 + $rm conftest* + echo "int some_variable = 0;" > conftest.c + save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS -fno-rtti -fno-exceptions -c conftest.c" + echo "$progname:914: checking if $compiler supports -fno-rtti -fno-exceptions" >&5 + if { (eval echo $progname:915: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>conftest.err; } && test -s conftest.o; then + + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + echo "$ac_t"no 1>&6 + compiler_rtti_exceptions=no + else + echo "$ac_t"yes 1>&6 + compiler_rtti_exceptions=yes + fi + else + # Append any errors to the config.log. + cat conftest.err 1>&5 + compiler_rtti_exceptions=no + echo "$ac_t"no 1>&6 + fi + CFLAGS="$save_CFLAGS" + $rm conftest* + + if test "$compiler_rtti_exceptions" = "yes"; then + no_builtin_flag=' -fno-builtin -fno-rtti -fno-exceptions' + else + no_builtin_flag=' -fno-builtin' + fi + +fi + +# Check for any special shared library compilation flags. +if test -n "$special_shlib_compile_flags"; then + echo "$progname: warning: \`$CC' requires \`$special_shlib_compile_flags' to build shared libraries" 1>&2 + if echo "$old_CC $old_CFLAGS " | egrep -e "[ ]$special_shlib_compile_flags[ ]" >/dev/null; then : + else + echo "$progname: add \`$special_shlib_compile_flags' to the CC or CFLAGS env variable and reconfigure" 1>&2 + can_build_shared=no + fi +fi + +echo $ac_n "checking if $compiler static flag $link_static_flag works... $ac_c" 1>&6 +$rm conftest* +echo 'main(){return(0);}' > conftest.c +save_LDFLAGS="$LDFLAGS" +LDFLAGS="$LDFLAGS $link_static_flag" +echo "$progname:958: checking if $compiler static flag $link_static_flag works" >&5 +if { (eval echo $progname:959: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest; then + echo "$ac_t$link_static_flag" 1>&6 +else + echo "$ac_t"none 1>&6 + link_static_flag= +fi +LDFLAGS="$save_LDFLAGS" +$rm conftest* + +if test -z "$LN_S"; then + # Check to see if we can use ln -s, or we need hard links. + echo $ac_n "checking whether ln -s works... $ac_c" 1>&6 + $rm conftest.dat + if ln -s X conftest.dat 2>/dev/null; then + $rm conftest.dat + LN_S="ln -s" + else + LN_S=ln + fi + if test "$LN_S" = "ln -s"; then + echo "$ac_t"yes 1>&6 + else + echo "$ac_t"no 1>&6 + fi +fi + +# Make sure LD is an absolute path. +if test -z "$LD"; then + ac_prog=ld + if test "$with_gcc" = yes; then + # Check if gcc -print-prog-name=ld gives a path. + echo $ac_n "checking for ld used by GCC... $ac_c" 1>&6 + echo "$progname:991: checking for ld used by GCC" >&5 + ac_prog=`($CC -print-prog-name=ld) 2>&5` + case "$ac_prog" in + # Accept absolute paths. + [\\/]* | [A-Za-z]:[\\/]*) + re_direlt='/[^/][^/]*/\.\./' + # Canonicalize the path of ld + ac_prog=`echo $ac_prog| sed 's%\\\\%/%g'` + while echo $ac_prog | grep "$re_direlt" > /dev/null 2>&1; do + ac_prog=`echo $ac_prog| sed "s%$re_direlt%/%"` + done + test -z "$LD" && LD="$ac_prog" + ;; + "") + # If it fails, then pretend we are not using GCC. + ac_prog=ld + ;; + *) + # If it is relative, then search for the first ld in PATH. + with_gnu_ld=unknown + ;; + esac + elif test "$with_gnu_ld" = yes; then + echo $ac_n "checking for GNU ld... $ac_c" 1>&6 + echo "$progname:1015: checking for GNU ld" >&5 + else + echo $ac_n "checking for non-GNU ld""... $ac_c" 1>&6 + echo "$progname:1018: checking for non-GNU ld" >&5 + fi + + if test -z "$LD"; then + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + for ac_dir in $PATH; do + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then + LD="$ac_dir/$ac_prog" + # Check to see if the program is GNU ld. I'd rather use --version, + # but apparently some GNU ld's only accept -v. + # Break only if it was the GNU/non-GNU ld that we prefer. + if "$LD" -v 2>&1 < /dev/null | egrep '(GNU|with BFD)' > /dev/null; then + test "$with_gnu_ld" != no && break + else + test "$with_gnu_ld" != yes && break + fi + fi + done + IFS="$ac_save_ifs" + fi + + if test -n "$LD"; then + echo "$ac_t$LD" 1>&6 + else + echo "$ac_t"no 1>&6 + fi + + if test -z "$LD"; then + echo "$progname: error: no acceptable ld found in \$PATH" 1>&2 + exit 1 + fi +fi + +# Check to see if it really is or is not GNU ld. +echo $ac_n "checking if the linker ($LD) is GNU ld... $ac_c" 1>&6 +# I'd rather use --version here, but apparently some GNU ld's only accept -v. +if $LD -v 2>&1 &5; then + with_gnu_ld=yes +else + with_gnu_ld=no +fi +echo "$ac_t$with_gnu_ld" 1>&6 + +# See if the linker supports building shared libraries. +echo $ac_n "checking whether the linker ($LD) supports shared libraries... $ac_c" 1>&6 + +allow_undefined_flag= +no_undefined_flag= +need_lib_prefix=unknown +need_version=unknown +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +archive_cmds= +archive_expsym_cmds= +old_archive_from_new_cmds= +export_dynamic_flag_spec= +whole_archive_flag_spec= +thread_safe_flag_spec= +hardcode_libdir_flag_spec= +hardcode_libdir_separator= +hardcode_direct=no +hardcode_minus_L=no +hardcode_shlibpath_var=unsupported +runpath_var= +always_export_symbols=no +export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | sed '\''s/.* //'\'' | sort | uniq > $export_symbols' +# include_expsyms should be a list of space-separated symbols to be *always* +# included in the symbol list +include_expsyms= +# exclude_expsyms can be an egrep regular expression of symbols to exclude +# it will be wrapped by ` (' and `)$', so one must not match beginning or +# end of line. Example: `a|bc|.*d.*' will exclude the symbols `a' and `bc', +# as well as any symbol that contains `d'. +exclude_expsyms="_GLOBAL_OFFSET_TABLE_" +# Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out +# platforms (ab)use it in PIC code, but their linkers get confused if +# the symbol is explicitly referenced. Since portable code cannot +# rely on this symbol name, it's probably fine to never include it in +# preloaded symbol tables. + +case "$host_os" in +cygwin* | mingw*) + # FIXME: the MSVC++ port hasn't been tested in a loooong time + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + if test "$with_gcc" != yes; then + with_gnu_ld=no + fi + ;; + +esac + +ld_shlibs=yes +if test "$with_gnu_ld" = yes; then + # If archive_cmds runs LD, not CC, wlarc should be empty + wlarc='${wl}' + + # See if GNU ld supports shared libraries. + case "$host_os" in + aix3* | aix4*) + # On AIX, the GNU linker is very broken + ld_shlibs=no + cat <&2 + +*** Warning: the GNU linker, at least up to release 2.9.1, is reported +*** to be unable to reliably create shared libraries on AIX. +*** Therefore, libtool is disabling shared libraries support. If you +*** really care for shared libraries, you may want to modify your PATH +*** so that a non-GNU linker is found, and then restart. + +EOF + ;; + + amigaos*) + archive_cmds='$rm $objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $objdir/a2ixlibrary.data~$AR cru $lib $libobjs~$RANLIB $lib~(cd $objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + + # Samuel A. Falvo II reports + # that the semantics of dynamic libraries on AmigaOS, at least up + # to version 4, is to share data among multiple programs linked + # with the same dynamic library. Since this doesn't match the + # behavior of shared libraries on other platforms, we can use + # them. + ld_shlibs=no + ;; + + beos*) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds='$CC -nostart $libobjs $deplibs $linkopts ${wl}-soname $wl$soname -o $lib' + else + ld_shlibs=no + fi + ;; + + cygwin* | mingw*) + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + hardcode_libdir_flag_spec='-L$libdir' + allow_undefined_flag=unsupported + always_export_symbols=yes + + # Extract the symbol export list from an `--export-all' def file, + # then regenerate the def file from the symbol export list, so that + # the compiled dll only exports the symbol export list. + export_symbols_cmds='test -f $objdir/$soname-ltdll.c || sed -e "/^# \/\* ltdll\.c starts here \*\//,/^# \/\* ltdll.c ends here \*\// { s/^# //; p; }" -e d < $0 > $objdir/$soname-ltdll.c~ + test -f $objdir/$soname-ltdll.$objext || (cd $objdir && $CC -c $soname-ltdll.c)~ + $DLLTOOL --export-all --exclude-symbols DllMain@12,_cygwin_dll_entry@12,_cygwin_noncygwin_dll_entry@12 --output-def $objdir/$soname-def $objdir/$soname-ltdll.$objext $libobjs $convenience~ + sed -e "1,/EXPORTS/d" -e "s/ @ [0-9]* ; *//" < $objdir/$soname-def > $export_symbols' + + archive_expsym_cmds='echo EXPORTS > $objdir/$soname-def~ + _lt_hint=1; + for symbol in `cat $export_symbols`; do + echo " \$symbol @ \$_lt_hint ; " >> $objdir/$soname-def; + _lt_hint=`expr 1 + \$_lt_hint`; + done~ + test -f $objdir/$soname-ltdll.c || sed -e "/^# \/\* ltdll\.c starts here \*\//,/^# \/\* ltdll.c ends here \*\// { s/^# //; p; }" -e d < $0 > $objdir/$soname-ltdll.c~ + test -f $objdir/$soname-ltdll.$objext || (cd $objdir && $CC -c $soname-ltdll.c)~ + $CC -Wl,--base-file,$objdir/$soname-base -Wl,--dll -nostartfiles -Wl,-e,__cygwin_dll_entry@12 -o $lib $objdir/$soname-ltdll.$objext $libobjs $deplibs $linkopts~ + $DLLTOOL --as=$AS --dllname $soname --exclude-symbols DllMain@12,_cygwin_dll_entry@12,_cygwin_noncygwin_dll_entry@12 --def $objdir/$soname-def --base-file $objdir/$soname-base --output-exp $objdir/$soname-exp~ + $CC -Wl,--base-file,$objdir/$soname-base $objdir/$soname-exp -Wl,--dll -nostartfiles -Wl,-e,__cygwin_dll_entry@12 -o $lib $objdir/$soname-ltdll.$objext $libobjs $deplibs $linkopts~ + $DLLTOOL --as=$AS --dllname $soname --exclude-symbols DllMain@12,_cygwin_dll_entry@12,_cygwin_noncygwin_dll_entry@12 --def $objdir/$soname-def --base-file $objdir/$soname-base --output-exp $objdir/$soname-exp~ + $CC $objdir/$soname-exp -Wl,--dll -nostartfiles -Wl,-e,__cygwin_dll_entry@12 -o $lib $objdir/$soname-ltdll.$objext $libobjs $deplibs $linkopts' + + old_archive_from_new_cmds='$DLLTOOL --as=$AS --dllname $soname --def $objdir/$soname-def --output-lib $objdir/$libname.a' + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + archive_cmds='$LD -Bshareable $libobjs $deplibs $linkopts -o $lib' + # can we support soname and/or expsyms with a.out? -oliva + fi + ;; + + solaris* | sysv5*) + if $LD -v 2>&1 | egrep 'BFD 2\.8' > /dev/null; then + ld_shlibs=no + cat <&2 + +*** Warning: The releases 2.8.* of the GNU linker cannot reliably +*** create shared libraries on Solaris systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.9.1 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +EOF + elif $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + + sunos4*) + archive_cmds='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linkopts' + wlarc= + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + *) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + esac + + if test "$ld_shlibs" = yes; then + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec='${wl}--export-dynamic' + case $host_os in + cygwin* | mingw*) + # dlltool doesn't understand --whole-archive et. al. + whole_archive_flag_spec= + ;; + *) + # ancient GNU ld didn't support --whole-archive et. al. + if $LD --help 2>&1 | egrep 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + else + whole_archive_flag_spec= + fi + ;; + esac + fi +else + # PORTME fill in a description of your system's linker (not GNU ld) + case "$host_os" in + aix3*) + allow_undefined_flag=unsupported + always_export_symbols=yes + archive_expsym_cmds='$LD -o $objdir/$soname $libobjs $deplibs $linkopts -bE:$export_symbols -T512 -H512 -bM:SRE~$AR cru $lib $objdir/$soname' + # Note: this linker hardcodes the directories in LIBPATH if there + # are no directories specified by -L. + hardcode_minus_L=yes + if test "$with_gcc" = yes && test -z "$link_static_flag"; then + # Neither direct hardcoding nor static linking is supported with a + # broken collect2. + hardcode_direct=unsupported + fi + ;; + + aix4*) + hardcode_libdir_flag_spec='${wl}-b ${wl}nolibpath ${wl}-b ${wl}libpath:$libdir:/usr/lib:/lib' + hardcode_libdir_separator=':' + if test "$with_gcc" = yes; then + collect2name=`${CC} -print-prog-name=collect2` + if test -f "$collect2name" && \ + strings "$collect2name" | grep resolve_lib_name >/dev/null + then + # We have reworked collect2 + hardcode_direct=yes + else + # We have old collect2 + hardcode_direct=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L=yes + hardcode_libdir_flag_spec='-L$libdir' + hardcode_libdir_separator= + fi + shared_flag='-shared' + else + shared_flag='${wl}-bM:SRE' + hardcode_direct=yes + fi + allow_undefined_flag=' ${wl}-berok' + archive_cmds="\$CC $shared_flag"' -o $objdir/$soname $libobjs $deplibs $linkopts ${wl}-bexpall ${wl}-bnoentry${allow_undefined_flag}' + archive_expsym_cmds="\$CC $shared_flag"' -o $objdir/$soname $libobjs $deplibs $linkopts ${wl}-bE:$export_symbols ${wl}-bnoentry${allow_undefined_flag}' + case "$host_os" in aix4.[01]|aix4.[01].*) + # According to Greg Wooledge, -bexpall is only supported from AIX 4.2 on + always_export_symbols=yes ;; + esac + ;; + + amigaos*) + archive_cmds='$rm $objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $objdir/a2ixlibrary.data~$AR cru $lib $libobjs~$RANLIB $lib~(cd $objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + # see comment about different semantics on the GNU ld section + ld_shlibs=no + ;; + + cygwin* | mingw*) + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + hardcode_libdir_flag_spec=' ' + allow_undefined_flag=unsupported + # Tell ltmain to make .lib files, not .a files. + libext=lib + # FIXME: Setting linknames here is a bad hack. + archive_cmds='$CC -o $lib $libobjs $linkopts `echo "$deplibs" | sed -e '\''s/ -lc$//'\''` -link -dll~linknames=' + # The linker will automatically build a .lib file if we build a DLL. + old_archive_from_new_cmds='true' + # FIXME: Should let the user specify the lib program. + old_archive_cmds='lib /OUT:$oldlib$oldobjs' + fix_srcfile_path='`cygpath -w $srcfile`' + ;; + + freebsd1*) + ld_shlibs=no + ;; + + # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor + # support. Future versions do this automatically, but an explicit c++rt0.o + # does not break anything, and helps significantly (at the cost of a little + # extra space). + freebsd2.2*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linkopts /usr/lib/c++rt0.o' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + # Unfortunately, older versions of FreeBSD 2 do not have this feature. + freebsd2*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linkopts' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + # FreeBSD 3 and greater uses gcc -shared to do shared libraries. + freebsd*) + archive_cmds='$CC -shared -o $lib $libobjs $deplibs $linkopts' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + hpux9* | hpux10* | hpux11*) + case "$host_os" in + hpux9*) archive_cmds='$rm $objdir/$soname~$LD -b +b $install_libdir -o $objdir/$soname $libobjs $deplibs $linkopts~test $objdir/$soname = $lib || mv $objdir/$soname $lib' ;; + *) archive_cmds='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linkopts' ;; + esac + hardcode_libdir_flag_spec='${wl}+b ${wl}$libdir' + hardcode_libdir_separator=: + hardcode_direct=yes + hardcode_minus_L=yes # Not in the search PATH, but as the default + # location of the library. + export_dynamic_flag_spec='${wl}-E' + ;; + + irix5* | irix6*) + if test "$with_gcc" = yes; then + archive_cmds='$CC -shared $libobjs $deplibs $linkopts ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${objdir}/so_locations -o $lib' + else + archive_cmds='$LD -shared $libobjs $deplibs $linkopts -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linkopts' # a.out + else + archive_cmds='$LD -shared -o $lib $libobjs $deplibs $linkopts' # ELF + fi + hardcode_libdir_flag_spec='${wl}-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + openbsd*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linkopts' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + os2*) + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + allow_undefined_flag=unsupported + archive_cmds='$echo "LIBRARY $libname INITINSTANCE" > $objdir/$libname.def~$echo "DESCRIPTION \"$libname\"" >> $objdir/$libname.def~$echo DATA >> $objdir/$libname.def~$echo " SINGLE NONSHARED" >> $objdir/$libname.def~$echo EXPORTS >> $objdir/$libname.def~emxexp $libobjs >> $objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $linkopts $objdir/$libname.def' + old_archive_from_new_cmds='emximp -o $objdir/$libname.a $objdir/$libname.def' + ;; + + osf3*) + if test "$with_gcc" = yes; then + allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $linkopts ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${objdir}/so_locations -o $lib' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linkopts -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + ;; + + osf4* | osf5*) # As osf3* with the addition of the -msym flag + if test "$with_gcc" = yes; then + allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $linkopts ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${objdir}/so_locations -o $lib' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linkopts -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + ;; + + sco3.2v5*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + hardcode_shlibpath_var=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ;; + + solaris*) + no_undefined_flag=' -z text' + # $CC -shared without GNU ld will not create a library from C++ + # object files and a static libstdc++, better avoid it by now + archive_cmds='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linkopts' + archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linkopts~$rm $lib.exp' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_shlibpath_var=no + case "$host_os" in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) # Supported since Solaris 2.6 (maybe 2.5.1?) + whole_archive_flag_spec='-z allextract$convenience -z defaultextract' ;; + esac + ;; + + sunos4*) + archive_cmds='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linkopts' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + sysv4) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var=no + hardcode_direct=no #Motorola manual says yes, but my tests say they lie + ;; + + sysv4.3*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + hardcode_shlibpath_var=no + export_dynamic_flag_spec='-Bexport' + ;; + + sysv5*) + no_undefined_flag=' -z text' + # $CC -shared without GNU ld will not create a library from C++ + # object files and a static libstdc++, better avoid it by now + archive_cmds='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linkopts' + archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linkopts~$rm $lib.exp' + hardcode_libdir_flag_spec= + hardcode_shlibpath_var=no + runpath_var='LD_RUN_PATH' + ;; + + uts4*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + dgux*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + sysv4*MP*) + if test -d /usr/nec; then + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + hardcode_shlibpath_var=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ld_shlibs=yes + fi + ;; + + sysv4.2uw2*) + archive_cmds='$LD -G -o $lib $libobjs $deplibs $linkopts' + hardcode_direct=yes + hardcode_minus_L=no + hardcode_shlibpath_var=no + hardcode_runpath_var=yes + runpath_var=LD_RUN_PATH + ;; + + unixware7*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var=no + ;; + + *) + ld_shlibs=no + ;; + esac +fi +echo "$ac_t$ld_shlibs" 1>&6 +test "$ld_shlibs" = no && can_build_shared=no + +if test -z "$NM"; then + echo $ac_n "checking for BSD-compatible nm... $ac_c" 1>&6 + case "$NM" in + [\\/]* | [A-Za-z]:[\\/]*) ;; # Let the user override the test with a path. + *) + IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" + for ac_dir in $PATH /usr/ucb /usr/ccs/bin /bin; do + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/nm || test -f $ac_dir/nm$ac_exeext; then + # Check to see if the nm accepts a BSD-compat flag. + # Adding the `sed 1q' prevents false positives on HP-UX, which says: + # nm: unknown option "B" ignored + if ($ac_dir/nm -B /dev/null 2>&1 | sed '1q'; exit 0) | egrep /dev/null >/dev/null; then + NM="$ac_dir/nm -B" + break + elif ($ac_dir/nm -p /dev/null 2>&1 | sed '1q'; exit 0) | egrep /dev/null >/dev/null; then + NM="$ac_dir/nm -p" + break + else + NM=${NM="$ac_dir/nm"} # keep the first match, but + continue # so that we can try to find one that supports BSD flags + fi + fi + done + IFS="$ac_save_ifs" + test -z "$NM" && NM=nm + ;; + esac + echo "$ac_t$NM" 1>&6 +fi + +# Check for command to grab the raw symbol name followed by C symbol from nm. +echo $ac_n "checking command to parse $NM output... $ac_c" 1>&6 + +# These are sane defaults that work on at least a few old systems. +# [They come from Ultrix. What could be older than Ultrix?!! ;)] + +# Character class describing NM global symbol codes. +symcode='[BCDEGRST]' + +# Regexp to match symbols that can be accessed directly from C. +sympat='\([_A-Za-z][_A-Za-z0-9]*\)' + +# Transform the above into a raw symbol and a C symbol. +symxfrm='\1 \2\3 \3' + +# Transform an extracted symbol line into a proper C declaration +global_symbol_to_cdecl="sed -n -e 's/^. .* \(.*\)$/extern char \1;/p'" + +# Define system-specific variables. +case "$host_os" in +aix*) + symcode='[BCDT]' + ;; +cygwin* | mingw*) + symcode='[ABCDGISTW]' + ;; +hpux*) # Its linker distinguishes data from code symbols + global_symbol_to_cdecl="sed -n -e 's/^T .* \(.*\)$/extern char \1();/p' -e 's/^. .* \(.*\)$/extern char \1;/p'" + ;; +irix*) + symcode='[BCDEGRST]' + ;; +solaris*) + symcode='[BDT]' + ;; +sysv4) + symcode='[DFNSTU]' + ;; +esac + +# If we're using GNU nm, then use its standard symbol codes. +if $NM -V 2>&1 | egrep '(GNU|with BFD)' > /dev/null; then + symcode='[ABCDGISTW]' +fi + +# Try without a prefix undercore, then with it. +for ac_symprfx in "" "_"; do + + # Write the raw and C identifiers. + global_symbol_pipe="sed -n -e 's/^.*[ ]\($symcode\)[ ][ ]*\($ac_symprfx\)$sympat$/$symxfrm/p'" + + # Check to see that the pipe works correctly. + pipe_works=no + $rm conftest* + cat > conftest.c <&5 + if { (eval echo $progname:1636: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>&5; } && test -s conftest.$objext; then + # Now try to grab the symbols. + nlist=conftest.nm + if { echo "$progname:1639: eval \"$NM conftest.$objext | $global_symbol_pipe > $nlist\"" >&5; eval "$NM conftest.$objext | $global_symbol_pipe > $nlist 2>&5"; } && test -s "$nlist"; then + + # Try sorting and uniquifying the output. + if sort "$nlist" | uniq > "$nlist"T; then + mv -f "$nlist"T "$nlist" + else + rm -f "$nlist"T + fi + + # Make sure that we snagged all the symbols we need. + if egrep ' nm_test_var$' "$nlist" >/dev/null; then + if egrep ' nm_test_func$' "$nlist" >/dev/null; then + cat < conftest.c +#ifdef __cplusplus +extern "C" { +#endif + +EOF + # Now generate the symbol file. + eval "$global_symbol_to_cdecl"' < "$nlist" >> conftest.c' + + cat <> conftest.c +#if defined (__STDC__) && __STDC__ +# define lt_ptr_t void * +#else +# define lt_ptr_t char * +# define const +#endif + +/* The mapping between symbol names and symbols. */ +const struct { + const char *name; + lt_ptr_t address; +} +lt_preloaded_symbols[] = +{ +EOF + sed 's/^. \(.*\) \(.*\)$/ {"\2", (lt_ptr_t) \&\2},/' < "$nlist" >> conftest.c + cat <<\EOF >> conftest.c + {0, (lt_ptr_t) 0} +}; + +#ifdef __cplusplus +} +#endif +EOF + # Now try linking the two files. + mv conftest.$objext conftstm.$objext + save_LIBS="$LIBS" + save_CFLAGS="$CFLAGS" + LIBS="conftstm.$objext" + CFLAGS="$CFLAGS$no_builtin_flag" + if { (eval echo $progname:1691: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest; then + pipe_works=yes + else + echo "$progname: failed program was:" >&5 + cat conftest.c >&5 + fi + LIBS="$save_LIBS" + else + echo "cannot find nm_test_func in $nlist" >&5 + fi + else + echo "cannot find nm_test_var in $nlist" >&5 + fi + else + echo "cannot run $global_symbol_pipe" >&5 + fi + else + echo "$progname: failed program was:" >&5 + cat conftest.c >&5 + fi + $rm conftest* conftst* + + # Do not use the global_symbol_pipe unless it works. + if test "$pipe_works" = yes; then + break + else + global_symbol_pipe= + fi +done +if test "$pipe_works" = yes; then + echo "${ac_t}ok" 1>&6 +else + echo "${ac_t}failed" 1>&6 +fi + +if test -z "$global_symbol_pipe"; then + global_symbol_to_cdecl= +fi + +# Check hardcoding attributes. +echo $ac_n "checking how to hardcode library paths into programs... $ac_c" 1>&6 +hardcode_action= +if test -n "$hardcode_libdir_flag_spec" || \ + test -n "$runpath_var"; then + + # We can hardcode non-existant directories. + if test "$hardcode_direct" != no && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test "$hardcode_shlibpath_var" != no && + test "$hardcode_minus_L" != no; then + # Linking always hardcodes the temporary library directory. + hardcode_action=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action=unsupported +fi +echo "$ac_t$hardcode_action" 1>&6 + + +reload_flag= +reload_cmds='$LD$reload_flag -o $output$reload_objs' +echo $ac_n "checking for $LD option to reload object files... $ac_c" 1>&6 +# PORTME Some linkers may need a different reload flag. +reload_flag='-r' +echo "$ac_t$reload_flag" 1>&6 +test -n "$reload_flag" && reload_flag=" $reload_flag" + +# PORTME Fill in your ld.so characteristics +library_names_spec= +libname_spec='lib$name' +soname_spec= +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +file_magic_cmd= +file_magic_test_file= +deplibs_check_method='unknown' +# Need to set the preceding variable on all platforms that support +# interlibrary dependencies. +# 'none' -- dependencies not supported. +# `unknown' -- same as none, but documents that we really don't know. +# 'pass_all' -- all dependencies passed with no checks. +# 'test_compile' -- check by making test program. +# 'file_magic [regex]' -- check by looking for files in library path +# which responds to the $file_magic_cmd with a given egrep regex. +# If you have `file' or equivalent on your system and you're not sure +# whether `pass_all' will *always* work, you probably want this one. +echo $ac_n "checking dynamic linker characteristics... $ac_c" 1>&6 +case "$host_os" in +aix3*) + version_type=linux + library_names_spec='${libname}${release}.so$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX has no versioning support, so we append a major version to the name. + soname_spec='${libname}${release}.so$major' + ;; + +aix4*) + version_type=linux + # AIX has no versioning support, so currently we can not hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + # We preserve .a as extension for shared libraries though AIX4.2 + # and later linker supports .so + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.a' + shlibpath_var=LIBPATH + deplibs_check_method=pass_all + ;; + +amigaos*) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "(cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a)"; (cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a) || exit 1; done' + ;; + +beos*) + library_names_spec='${libname}.so' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + deplibs_check_method=pass_all + lt_cv_dlopen="load_add_on" + lt_cv_dlopen_libs= + lt_cv_dlopen_self=yes + ;; + +bsdi4*) + version_type=linux + need_version=no + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib)' + file_magic_cmd=/usr/bin/file + file_magic_test_file=/shlib/libc.so + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + export_dynamic_flag_spec=-rdynamic + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw*) + version_type=windows + need_version=no + need_lib_prefix=no + if test "$with_gcc" = yes; then + library_names_spec='${libname}`echo ${release} | sed -e 's/[.]/-/g'`${versuffix}.dll $libname.a' + else + library_names_spec='${libname}`echo ${release} | sed -e 's/[.]/-/g'`${versuffix}.dll $libname.lib' + fi + dynamic_linker='Win32 ld.exe' + deplibs_check_method='file_magic file format pei*-i386(.*architecture: i386)?' + file_magic_cmd='${OBJDUMP} -f' + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + lt_cv_dlopen="LoadLibrary" + lt_cv_dlopen_libs= + ;; + +freebsd1*) + dynamic_linker=no + ;; + +freebsd*) + objformat=`test -x /usr/bin/objformat && /usr/bin/objformat || echo aout` + version_type=freebsd-$objformat + case "$version_type" in + freebsd-elf*) + deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB shared object' + file_magic_cmd=/usr/bin/file + file_magic_test_file=`echo /usr/lib/libc.so*` + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so $libname.so' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + deplibs_check_method=unknown + library_names_spec='${libname}${release}.so$versuffix $libname.so$versuffix' + need_version=yes + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case "$host_os" in + freebsd2* | freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + ;; + *) # from 3.2 on + shlibpath_overrides_runpath=no + ;; + esac + ;; + +gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so${major} ${libname}.so' + soname_spec='${libname}${release}.so$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + dynamic_linker="$host_os dld.sl" + version_type=sunos + need_lib_prefix=no + need_version=no + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='${libname}${release}.sl$versuffix ${libname}${release}.sl$major $libname.sl' + soname_spec='${libname}${release}.sl$major' + # HP-UX runs *really* slowly unless shared libraries are mode 555. + postinstall_cmds='chmod 555 $lib' + ;; + +irix5* | irix6*) + version_type=irix + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}.so.$major' + library_names_spec='${libname}${release}.so.$versuffix ${libname}${release}.so.$major ${libname}${release}.so $libname.so' + case "$host_os" in + irix5*) + libsuff= shlibsuff= + # this will be overridden with pass_all, but let us keep it just in case + deplibs_check_method="file_magic ELF 32-bit MSB dynamic lib MIPS - version 1" + ;; + *) + case "$LD" in # libtool.m4 will add one of these switches to LD + *-32|*"-32 ") libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 ") libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 ") libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" + sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" + file_magic_cmd=/usr/bin/file + file_magic_test_file=`echo /lib${libsuff}/libc.so*` + deplibs_check_method='pass_all' + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux-gnuoldld* | linux-gnuaout* | linux-gnucoff*) + dynamic_linker=no + ;; + +# This must be Linux ELF. +linux-gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB (shared object|dynamic lib )' + file_magic_cmd=/usr/bin/file + file_magic_test_file=`echo /lib/libc.so* /lib/libc-*.so` + + if test -f /lib/ld.so.1; then + dynamic_linker='GNU ld.so' + else + # Only the GNU ld.so supports shared libraries on MkLinux. + case "$host_cpu" in + powerpc*) dynamic_linker=no ;; + *) dynamic_linker='Linux ld.so' ;; + esac + fi + ;; + +netbsd*) + version_type=sunos + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major ${libname}${release}.so ${libname}.so' + soname_spec='${libname}${release}.so$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + ;; + +openbsd*) + version_type=sunos + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + need_version=no + fi + library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + ;; + +os2*) + libname_spec='$name' + need_lib_prefix=no + library_names_spec='$libname.dll $libname.a' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=LIBPATH + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_version=no + soname_spec='${libname}${release}.so' + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so $libname.so' + shlibpath_var=LD_LIBRARY_PATH + # this will be overridden with pass_all, but let us keep it just in case + deplibs_check_method='file_magic COFF format alpha shared library' + file_magic_cmd=/usr/bin/file + file_magic_test_file=/shlib/libc.so + deplibs_check_method='pass_all' + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" + ;; + +sco3.2v5*) + version_type=osf + soname_spec='${libname}${release}.so$major' + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + shlibpath_var=LD_LIBRARY_PATH + ;; + +solaris*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + deplibs_check_method="file_magic ELF [0-9][0-9]-bit [LM]SB dynamic lib" + file_magic_cmd=/usr/bin/file + file_magic_test_file=/lib/libc.so + ;; + +sunos4*) + version_type=sunos + library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) + version_type=linux + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + shlibpath_var=LD_LIBRARY_PATH + case "$host_vendor" in + ncr) + deplibs_check_method='pass_all' + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib) M[0-9][0-9]* Version [0-9]' + file_magic_cmd=/usr/bin/file + file_magic_test_file=`echo /usr/lib/libc.so*` + ;; + esac + ;; + +uts4*) + version_type=linux + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +dgux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' + soname_spec='${libname}${release}.so$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +sysv4*MP*) + if test -d /usr/nec ;then + version_type=linux + library_names_spec='$libname.so.$versuffix $libname.so.$major $libname.so' + soname_spec='$libname.so.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +*) + dynamic_linker=no + ;; +esac +echo "$ac_t$dynamic_linker" 1>&6 +test "$dynamic_linker" = no && can_build_shared=no + +# Report the final consequences. +echo "checking if libtool supports shared libraries... $can_build_shared" 1>&6 + +# Only try to build win32 dlls if AC_LIBTOOL_WIN32_DLL was used in +# configure.in, otherwise build static only libraries. +case "$host_os" in +cygwin* | mingw* | os2*) + if test x$can_build_shared = xyes; then + test x$enable_win32_dll = xno && can_build_shared=no + echo "checking if package supports dlls... $can_build_shared" 1>&6 + fi +;; +esac + +if test -n "$file_magic_test_file" && test -n "$file_magic_cmd"; then + case "$deplibs_check_method" in + "file_magic "*) + file_magic_regex="`expr \"$deplibs_check_method\" : \"file_magic \(.*\)\"`" + if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | + egrep "$file_magic_regex" > /dev/null; then + : + else + cat <&2 + +*** Warning: the command libtool uses to detect shared libraries, +*** $file_magic_cmd, produces output that libtool cannot recognize. +*** The result is that libtool may fail to recognize shared libraries +*** as such. This will affect the creation of libtool libraries that +*** depend on shared libraries, but programs linked with such libtool +*** libraries will work regardless of this problem. Nevertheless, you +*** may want to report the problem to your system manager and/or to +*** bug-libtool@gnu.org + +EOF + fi ;; + esac +fi + +echo $ac_n "checking whether to build shared libraries... $ac_c" 1>&6 +test "$can_build_shared" = "no" && enable_shared=no + +# On AIX, shared libraries and static libraries use the same namespace, and +# are all built from PIC. +case "$host_os" in +aix3*) + test "$enable_shared" = yes && enable_static=no + if test -n "$RANLIB"; then + archive_cmds="$archive_cmds~\$RANLIB \$lib" + postinstall_cmds='$RANLIB $lib' + fi + ;; + +aix4*) + test "$enable_shared" = yes && enable_static=no + ;; +esac + +echo "$ac_t$enable_shared" 1>&6 + +# Make sure either enable_shared or enable_static is yes. +test "$enable_shared" = yes || enable_static=yes + +echo "checking whether to build static libraries... $enable_static" 1>&6 + +if test "$hardcode_action" = relink; then + # Fast installation is not supported + enable_fast_install=no +elif test "$shlibpath_overrides_runpath" = yes || + test "$enable_shared" = no; then + # Fast installation is not necessary + enable_fast_install=needless +fi + +echo $ac_n "checking for objdir... $ac_c" 1>&6 +rm -f .libs 2>/dev/null +mkdir .libs 2>/dev/null +if test -d .libs; then + objdir=.libs +else + # MS-DOS does not allow filenames that begin with a dot. + objdir=_libs +fi +rmdir .libs 2>/dev/null +echo "$ac_t$objdir" 1>&6 + +if test "x$enable_dlopen" != xyes; then + enable_dlopen=unknown + enable_dlopen_self=unknown + enable_dlopen_self_static=unknown +else +if eval "test \"`echo '$''{'lt_cv_dlopen'+set}'`\" != set"; then + lt_cv_dlopen=no lt_cv_dlopen_libs= +echo $ac_n "checking for dlopen in -ldl""... $ac_c" 1>&6 +echo "$progname:2212: checking for dlopen in -ldl" >&5 +ac_lib_var=`echo dl'_'dlopen | sed 'y%./+-%__p_%'` +if eval "test \"`echo '$''{'ac_cv_lib_$ac_lib_var'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + ac_save_LIBS="$LIBS" +LIBS="-ldl $LIBS" +cat > conftest.$ac_ext <&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=yes" +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=no" +fi +rm -f conftest* +LIBS="$ac_save_LIBS" + +fi +if eval "test \"`echo '$ac_cv_lib_'$ac_lib_var`\" = yes"; then + echo "$ac_t""yes" 1>&6 + lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-ldl" +else + echo "$ac_t""no" 1>&6 +echo $ac_n "checking for dlopen""... $ac_c" 1>&6 +echo "$progname:2252: checking for dlopen" >&5 +if eval "test \"`echo '$''{'ac_cv_func_dlopen'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +/* Override any gcc2 internal prototype to avoid an error. */ +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char dlopen(); + +int main() { + +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_dlopen) || defined (__stub___dlopen) +choke me +#else +dlopen(); +#endif + +; return 0; } +EOF +if { (eval echo $progname:2282: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_func_dlopen=yes" +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_func_dlopen=no" +fi +rm -f conftest* +fi +if eval "test \"`echo '$ac_cv_func_'dlopen`\" = yes"; then + echo "$ac_t""yes" 1>&6 + lt_cv_dlopen="dlopen" +else + echo "$ac_t""no" 1>&6 +echo $ac_n "checking for dld_link in -ldld""... $ac_c" 1>&6 +echo "$progname:2299: checking for dld_link in -ldld" >&5 +ac_lib_var=`echo dld'_'dld_link | sed 'y%./+-%__p_%'` +if eval "test \"`echo '$''{'ac_cv_lib_$ac_lib_var'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + ac_save_LIBS="$LIBS" +LIBS="-ldld $LIBS" +cat > conftest.$ac_ext <&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=yes" +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=no" +fi +rm -f conftest* +LIBS="$ac_save_LIBS" + +fi +if eval "test \"`echo '$ac_cv_lib_'$ac_lib_var`\" = yes"; then + echo "$ac_t""yes" 1>&6 + lt_cv_dlopen="dld_link" lt_cv_dlopen_libs="-ldld" +else + echo "$ac_t""no" 1>&6 +echo $ac_n "checking for shl_load""... $ac_c" 1>&6 +echo "$progname:2339: checking for shl_load" >&5 +if eval "test \"`echo '$''{'ac_cv_func_shl_load'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +/* Override any gcc2 internal prototype to avoid an error. */ +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char shl_load(); + +int main() { + +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_shl_load) || defined (__stub___shl_load) +choke me +#else +shl_load(); +#endif + +; return 0; } +EOF +if { (eval echo $progname:2369: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_func_shl_load=yes" +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_func_shl_load=no" +fi +rm -f conftest* +fi + +if eval "test \"`echo '$ac_cv_func_'shl_load`\" = yes"; then + echo "$ac_t""yes" 1>&6 + lt_cv_dlopen="shl_load" +else + echo "$ac_t""no" 1>&6 +echo $ac_n "checking for shl_load in -ldld""... $ac_c" 1>&6 +echo "$progname:2387: checking for shl_load in -ldld" >&5 +ac_lib_var=`echo dld'_'shl_load | sed 'y%./+-%__p_%'` +if eval "test \"`echo '$''{'ac_cv_lib_$ac_lib_var'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + ac_save_LIBS="$LIBS" +LIBS="-ldld $LIBS" +cat > conftest.$ac_ext <&5; (eval $ac_link) 2>&5; } && test -s conftest${ac_exeext}; then + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=yes" +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_lib_$ac_lib_var=no" +fi +rm -f conftest* +LIBS="$ac_save_LIBS" + +fi +if eval "test \"`echo '$ac_cv_lib_'$ac_lib_var`\" = yes"; then + echo "$ac_t""yes" 1>&6 + lt_cv_dlopen="shl_load" lt_cv_dlopen_libs="-ldld" +else + echo "$ac_t""no" 1>&6 +fi + + +fi + + +fi + + +fi + + +fi + +fi + + if test "x$lt_cv_dlopen" != xno; then + enable_dlopen=yes + fi + + case "$lt_cv_dlopen" in + dlopen) +for ac_hdr in dlfcn.h; do +ac_safe=`echo "$ac_hdr" | sed 'y%./+-%__p_%'` +echo $ac_n "checking for $ac_hdr""... $ac_c" 1>&6 +echo "$progname:2452: checking for $ac_hdr" >&5 +if eval "test \"`echo '$''{'ac_cv_header_$ac_safe'+set}'`\" = set"; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + cat > conftest.$ac_ext < +int fnord = 0; +EOF +ac_try="$ac_compile >/dev/null 2>conftest.out" +{ (eval echo $progname:2462: \"$ac_try\") 1>&5; (eval $ac_try) 2>&5; } +ac_err=`grep -v '^ *+' conftest.out | grep -v "^conftest.${ac_ext}\$"` +if test -z "$ac_err"; then + rm -rf conftest* + eval "ac_cv_header_$ac_safe=yes" +else + echo "$ac_err" >&5 + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -rf conftest* + eval "ac_cv_header_$ac_safe=no" +fi +rm -f conftest* +fi +if eval "test \"`echo '$ac_cv_header_'$ac_safe`\" = yes"; then + echo "$ac_t""yes" 1>&6 +else + echo "$ac_t""no" 1>&6 +fi +done + + if test "x$ac_cv_header_dlfcn_h" = xyes; then + CPPFLAGS="$CPPFLAGS -DHAVE_DLFCN_H" + fi + eval LDFLAGS=\"\$LDFLAGS $export_dynamic_flag_spec\" + LIBS="$lt_cv_dlopen_libs $LIBS" + + echo $ac_n "checking whether a program can dlopen itself""... $ac_c" 1>&6 +echo "$progname:2490: checking whether a program can dlopen itself" >&5 +if test "${lt_cv_dlopen_self+set}" = set; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test "$cross_compiling" = yes; then + lt_cv_dlopen_self=cross + else + cat > conftest.c < +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LTDL_GLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LTDL_GLOBAL DL_GLOBAL +# else +# define LTDL_GLOBAL 0 +# endif +#endif + +/* We may have to define LTDL_LAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LTDL_LAZY_OR_NOW +# ifdef RTLD_LAZY +# define LTDL_LAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LTDL_LAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LTDL_LAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LTDL_LAZY_OR_NOW DL_NOW +# else +# define LTDL_LAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +fnord() { int i=42;} +main() { void *self, *ptr1, *ptr2; self=dlopen(0,LTDL_GLOBAL|LTDL_LAZY_OR_NOW); + if(self) { ptr1=dlsym(self,"fnord"); ptr2=dlsym(self,"_fnord"); + if(ptr1 || ptr2) { dlclose(self); exit(0); } } exit(1); } + +EOF +if { (eval echo $progname:2544: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest && (./conftest; exit) 2>/dev/null +then + lt_cv_dlopen_self=yes +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -fr conftest* + lt_cv_dlopen_self=no +fi +rm -fr conftest* +fi + +fi + +echo "$ac_t""$lt_cv_dlopen_self" 1>&6 + + if test "$lt_cv_dlopen_self" = yes; then + LDFLAGS="$LDFLAGS $link_static_flag" + echo $ac_n "checking whether a statically linked program can dlopen itself""... $ac_c" 1>&6 +echo "$progname:2563: checking whether a statically linked program can dlopen itself" >&5 +if test "${lt_cv_dlopen_self_static+set}" = set; then + echo $ac_n "(cached) $ac_c" 1>&6 +else + if test "$cross_compiling" = yes; then + lt_cv_dlopen_self_static=cross + else + cat > conftest.c < +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LTDL_GLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LTDL_GLOBAL DL_GLOBAL +# else +# define LTDL_GLOBAL 0 +# endif +#endif + +/* We may have to define LTDL_LAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LTDL_LAZY_OR_NOW +# ifdef RTLD_LAZY +# define LTDL_LAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LTDL_LAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LTDL_LAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LTDL_LAZY_OR_NOW DL_NOW +# else +# define LTDL_LAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +fnord() { int i=42;} +main() { void *self, *ptr1, *ptr2; self=dlopen(0,LTDL_GLOBAL|LTDL_LAZY_OR_NOW); + if(self) { ptr1=dlsym(self,"fnord"); ptr2=dlsym(self,"_fnord"); + if(ptr1 || ptr2) { dlclose(self); exit(0); } } exit(1); } + +EOF +if { (eval echo $progname:2617: \"$ac_link\") 1>&5; (eval $ac_link) 2>&5; } && test -s conftest && (./conftest; exit) 2>/dev/null +then + lt_cv_dlopen_self_static=yes +else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + rm -fr conftest* + lt_cv_dlopen_self_static=no +fi +rm -fr conftest* +fi + +fi + +echo "$ac_t""$lt_cv_dlopen_self_static" 1>&6 +fi + ;; + esac + + case "$lt_cv_dlopen_self" in + yes|no) enable_dlopen_self=$lt_cv_dlopen_self ;; + *) enable_dlopen_self=unknown ;; + esac + + case "$lt_cv_dlopen_self_static" in + yes|no) enable_dlopen_self_static=$lt_cv_dlopen_self_static ;; + *) enable_dlopen_self_static=unknown ;; + esac +fi + +# Copy echo and quote the copy, instead of the original, because it is +# used later. +ltecho="$echo" +if test "X$ltecho" = "X$CONFIG_SHELL $0 --fallback-echo"; then + ltecho="$CONFIG_SHELL \$0 --fallback-echo" +fi +LTSHELL="$SHELL" + +LTCONFIG_VERSION="$VERSION" + +# Only quote variables if we're using ltmain.sh. +case "$ltmain" in +*.sh) + # Now quote all the things that may contain metacharacters. + for var in ltecho old_CC old_CFLAGS old_CPPFLAGS \ + old_LD old_LDFLAGS old_LIBS \ + old_NM old_RANLIB old_LN_S old_DLLTOOL old_OBJDUMP old_AS \ + AR CC LD LN_S NM LTSHELL LTCONFIG_VERSION \ + reload_flag reload_cmds wl \ + pic_flag link_static_flag no_builtin_flag export_dynamic_flag_spec \ + thread_safe_flag_spec whole_archive_flag_spec libname_spec \ + library_names_spec soname_spec \ + RANLIB old_archive_cmds old_archive_from_new_cmds old_postinstall_cmds \ + old_postuninstall_cmds archive_cmds archive_expsym_cmds postinstall_cmds postuninstall_cmds \ + file_magic_cmd export_symbols_cmds deplibs_check_method allow_undefined_flag no_undefined_flag \ + finish_cmds finish_eval global_symbol_pipe global_symbol_to_cdecl \ + hardcode_libdir_flag_spec hardcode_libdir_separator \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + compiler_c_o compiler_o_lo need_locks exclude_expsyms include_expsyms; do + + case "$var" in + reload_cmds | old_archive_cmds | old_archive_from_new_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + export_symbols_cmds | archive_cmds | archive_expsym_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + finish_cmds | sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case "$ltecho" in + *'\$0 --fallback-echo"') + ltecho=`$echo "X$ltecho" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + + trap "$rm \"$ofile\"; exit 1" 1 2 15 + echo "creating $ofile" + $rm "$ofile" + cat < "$ofile" +#! $SHELL + +# `$echo "$ofile" | sed 's%^.*/%%'` - Provide generalized library-building support services. +# Generated automatically by $PROGRAM (GNU $PACKAGE $VERSION$TIMESTAMP) +# NOTE: Changes made to this file will be lost: look at ltconfig or ltmain.sh. +# +# Copyright (C) 1996-1999 Free Software Foundation, Inc. +# Originally by Gordon Matzigkeit , 1996 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# Sed that helps us avoid accidentally triggering echo(1) options like -n. +Xsed="sed -e s/^X//" + +# The HP-UX ksh and POSIX shell print the target directory to stdout +# if CDPATH is set. +if test "X\${CDPATH+set}" = Xset; then CDPATH=:; export CDPATH; fi + +### BEGIN LIBTOOL CONFIG +EOF + cfgfile="$ofile" + ;; + +*) + # Double-quote the variables that need it (for aesthetics). + for var in old_CC old_CFLAGS old_CPPFLAGS \ + old_LD old_LDFLAGS old_LIBS \ + old_NM old_RANLIB old_LN_S old_DLLTOOL old_OBJDUMP old_AS; do + eval "$var=\\\"\$var\\\"" + done + + # Just create a config file. + cfgfile="$ofile.cfg" + trap "$rm \"$cfgfile\"; exit 1" 1 2 15 + echo "creating $cfgfile" + $rm "$cfgfile" + cat < "$cfgfile" +# `$echo "$cfgfile" | sed 's%^.*/%%'` - Libtool configuration file. +# Generated automatically by $PROGRAM (GNU $PACKAGE $VERSION$TIMESTAMP) +EOF + ;; +esac + +cat <> "$cfgfile" +# Libtool was configured as follows, on host `(hostname || uname -n) 2>/dev/null | sed 1q`: +# +# CC=$old_CC CFLAGS=$old_CFLAGS CPPFLAGS=$old_CPPFLAGS \\ +# LD=$old_LD LDFLAGS=$old_LDFLAGS LIBS=$old_LIBS \\ +# NM=$old_NM RANLIB=$old_RANLIB LN_S=$old_LN_S \\ +# DLLTOOL=$old_DLLTOOL OBJDUMP=$old_OBJDUMP AS=$old_AS \\ +# $0$ltconfig_args +# +# Compiler and other test output produced by $progname, useful for +# debugging $progname, is in ./config.log if it exists. + +# The version of $progname that generated this script. +LTCONFIG_VERSION=$LTCONFIG_VERSION + +# Shell to use when invoking shell scripts. +SHELL=$LTSHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host + +# An echo program that does not interpret backslashes. +echo=$ltecho + +# The archiver. +AR=$AR + +# The default C compiler. +CC=$CC + +# The linker used to build libraries. +LD=$LD + +# Whether we need hard or soft links. +LN_S=$LN_S + +# A BSD-compatible nm program. +NM=$NM + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$reload_flag +reload_cmds=$reload_cmds + +# How to pass a linker flag through the compiler. +wl=$wl + +# Object file suffix (normally "o"). +objext="$objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$pic_flag + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$compiler_c_o + +# Can we write directly to a .lo ? +compiler_o_lo=$compiler_o_lo + +# Must we lock files when doing compilation ? +need_locks=$need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$link_static_flag + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$no_builtin_flag + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$export_dynamic_flag_spec + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$whole_archive_flag_spec + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$thread_safe_flag_spec + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$RANLIB +old_archive_cmds=$old_archive_cmds +old_postinstall_cmds=$old_postinstall_cmds +old_postuninstall_cmds=$old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$old_archive_from_new_cmds + +# Commands used to build and install a shared archive. +archive_cmds=$archive_cmds +archive_expsym_cmds=$archive_expsym_cmds +postinstall_cmds=$postinstall_cmds +postuninstall_cmds=$postuninstall_cmds + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$allow_undefined_flag + +# Flag that forces no undefined symbols. +no_undefined_flag=$no_undefined_flag + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$global_symbol_to_cdecl + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$hardcode_libdir_flag_spec + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$hardcode_libdir_separator + +# Set to yes if using DIR/libNAME.so during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols + +# The commands to list exported symbols. +export_symbols_cmds=$export_symbols_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$exclude_expsyms + +# Symbols that must always be exported. +include_expsyms=$include_expsyms + +EOF + +case "$ltmain" in +*.sh) + echo '### END LIBTOOL CONFIG' >> "$ofile" + echo >> "$ofile" + case "$host_os" in + aix3*) + cat <<\EOF >> "$ofile" + +# AIX sometimes has problems with the GCC collect2 program. For some +# reason, if we set the COLLECT_NAMES environment variable, the problems +# vanish in a puff of smoke. +if test "X${COLLECT_NAMES+set}" != Xset; then + COLLECT_NAMES= + export COLLECT_NAMES +fi +EOF + ;; + esac + + # Append the ltmain.sh script. + sed '$q' "$ltmain" >> "$ofile" || (rm -f "$ofile"; exit 1) + # We use sed instead of cat because bash on DJGPP gets confused if + # if finds mixed CR/LF and LF-only lines. Since sed operates in + # text mode, it properly converts lines to CR/LF. This bash problem + # is reportedly fixed, but why not run on old versions too? + + chmod +x "$ofile" + ;; + +*) + # Compile the libtool program. + echo "FIXME: would compile $ltmain" + ;; +esac + +test -n "$cache_file" || exit 0 + +# AC_CACHE_SAVE +trap '' 1 2 15 +cat > confcache <<\EOF +# This file is a shell script that caches the results of configure +# tests run on this system so they can be shared between configure +# scripts and configure runs. It is not useful on other systems. +# If it contains results you don't want to keep, you may remove or edit it. +# +# By default, configure uses ./config.cache as the cache file, +# creating it if it does not exist already. You can give configure +# the --cache-file=FILE option to use a different cache file; that is +# what configure does when it calls configure scripts in +# subdirectories, so they share the cache. +# Giving --cache-file=/dev/null disables caching, for debugging configure. +# config.status only pays attention to the cache file if you give it the +# --recheck option to rerun configure. +# +EOF +# The following way of writing the cache mishandles newlines in values, +# but we know of no workaround that is simple, portable, and efficient. +# So, don't put newlines in cache variables' values. +# Ultrix sh set writes to stderr and can't be redirected directly, +# and sets the high bit in the cache file unless we assign to the vars. +(set) 2>&1 | + case `(ac_space=' '; set | grep ac_space) 2>&1` in + *ac_space=\ *) + # `set' does not quote correctly, so add quotes (double-quote substitution + # turns \\\\ into \\, and sed turns \\ into \). + sed -n \ + -e "s/'/'\\\\''/g" \ + -e "s/^\\([a-zA-Z0-9_]*_cv_[a-zA-Z0-9_]*\\)=\\(.*\\)/\\1=\${\\1='\\2'}/p" + ;; + *) + # `set' quotes correctly as required by POSIX, so do not add quotes. + sed -n -e 's/^\([a-zA-Z0-9_]*_cv_[a-zA-Z0-9_]*\)=\(.*\)/\1=${\1=\2}/p' + ;; + esac >> confcache +if cmp -s $cache_file confcache; then + : +else + if test -w $cache_file; then + echo "updating cache $cache_file" + cat confcache > $cache_file + else + echo "not updating unwritable cache $cache_file" + fi +fi +rm -f confcache + +exit 0 + +# Local Variables: +# mode:shell-script +# sh-indentation:2 +# End: diff --git a/pcre/maketables.c b/pcre/maketables.c new file mode 100644 index 00000000..c0f06c03 --- /dev/null +++ b/pcre/maketables.c @@ -0,0 +1,132 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Written by: Philip Hazel + + Copyright (c) 1997-2000 University of Cambridge + +----------------------------------------------------------------------------- +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. +----------------------------------------------------------------------------- + +See the file Tech.Notes for some information on the internals. +*/ + + +/* This file is compiled on its own as part of the PCRE library. However, +it is also included in the compilation of dftables.c, in which case the macro +DFTABLES is defined. */ + +#ifndef DFTABLES +#include "internal.h" +#endif + + + +/************************************************* +* Create PCRE character tables * +*************************************************/ + +/* This function builds a set of character tables for use by PCRE and returns +a pointer to them. They are build using the ctype functions, and consequently +their contents will depend upon the current locale setting. When compiled as +part of the library, the store is obtained via pcre_malloc(), but when compiled +inside dftables, use malloc(). + +Arguments: none +Returns: pointer to the contiguous block of data +*/ + +unsigned const char * +pcre_maketables(void) +{ +unsigned char *yield, *p; +int i; + +#ifndef DFTABLES +yield = (unsigned char*)(pcre_malloc)(tables_length); +#else +yield = (unsigned char*)malloc(tables_length); +#endif + +if (yield == NULL) return NULL; +p = yield; + +/* First comes the lower casing table */ + +for (i = 0; i < 256; i++) *p++ = tolower(i); + +/* Next the case-flipping table */ + +for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); + +/* Then the character class tables. Don't try to be clever and save effort +on exclusive ones - in some locales things may be different. */ + +memset(p, 0, cbit_length); +for (i = 0; i < 256; i++) + { + if (isdigit(i)) + { + p[cbit_digit + i/8] |= 1 << (i&7); + p[cbit_word + i/8] |= 1 << (i&7); + } + if (isupper(i)) + { + p[cbit_upper + i/8] |= 1 << (i&7); + p[cbit_word + i/8] |= 1 << (i&7); + } + if (islower(i)) + { + p[cbit_lower + i/8] |= 1 << (i&7); + p[cbit_word + i/8] |= 1 << (i&7); + } + if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); + if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); + if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); + if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); + if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); + if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); + if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); + } +p += cbit_length; + +/* Finally, the character type table */ + +for (i = 0; i < 256; i++) + { + int x = 0; + if (isspace(i)) x += ctype_space; + if (isalpha(i)) x += ctype_letter; + if (isdigit(i)) x += ctype_digit; + if (isxdigit(i)) x += ctype_xdigit; + if (isalnum(i) || i == '_') x += ctype_word; + if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; + *p++ = x; + } + +return yield; +} + +/* End of maketables.c */ diff --git a/pcre/pcre-config b/pcre/pcre-config new file mode 100644 index 00000000..ac9ccfe9 --- /dev/null +++ b/pcre/pcre-config @@ -0,0 +1,59 @@ +#!/bin/sh + +prefix=/usr/local +exec_prefix=${prefix} +exec_prefix_set=no + +usage="\ +Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" + +if test $# -eq 0; then + echo "${usage}" 1>&2 + exit 1 +fi + +while test $# -gt 0; do + case "$1" in + -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + case $1 in + --prefix=*) + prefix=$optarg + if test $exec_prefix_set = no ; then + exec_prefix=$optarg + fi + ;; + --prefix) + echo $prefix + ;; + --exec-prefix=*) + exec_prefix=$optarg + exec_prefix_set=yes + ;; + --exec-prefix) + echo $exec_prefix + ;; + --version) + echo 3.4 + ;; + --cflags | --cflags-posix) + if test ${prefix}/include != /usr/include ; then + includes=-I${prefix}/include + fi + echo $includes + ;; + --libs-posix) + echo -L${exec_prefix}/lib -lpcreposix -lpcre + ;; + --libs) + echo -L${exec_prefix}/lib -lpcre + ;; + *) + echo "${usage}" 1>&2 + exit 1 + ;; + esac + shift +done diff --git a/pcre/pcre-config.in b/pcre/pcre-config.in new file mode 100644 index 00000000..8daded9f --- /dev/null +++ b/pcre/pcre-config.in @@ -0,0 +1,59 @@ +#!/bin/sh + +prefix=@prefix@ +exec_prefix=@exec_prefix@ +exec_prefix_set=no + +usage="\ +Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" + +if test $# -eq 0; then + echo "${usage}" 1>&2 + exit 1 +fi + +while test $# -gt 0; do + case "$1" in + -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + case $1 in + --prefix=*) + prefix=$optarg + if test $exec_prefix_set = no ; then + exec_prefix=$optarg + fi + ;; + --prefix) + echo $prefix + ;; + --exec-prefix=*) + exec_prefix=$optarg + exec_prefix_set=yes + ;; + --exec-prefix) + echo $exec_prefix + ;; + --version) + echo @PCRE_VERSION@ + ;; + --cflags | --cflags-posix) + if test @includedir@ != /usr/include ; then + includes=-I@includedir@ + fi + echo $includes + ;; + --libs-posix) + echo -L@libdir@ -lpcreposix -lpcre + ;; + --libs) + echo -L@libdir@ -lpcre + ;; + *) + echo "${usage}" 1>&2 + exit 1 + ;; + esac + shift +done diff --git a/pcre/pcre.def b/pcre/pcre.def new file mode 100644 index 00000000..0e8cf3f4 --- /dev/null +++ b/pcre/pcre.def @@ -0,0 +1,19 @@ +EXPORTS + +pcre_malloc DATA +pcre_free DATA + +pcre_compile +pcre_copy_substring +pcre_exec +pcre_get_substring +pcre_get_substring_list +pcre_info +pcre_maketables +pcre_study +pcre_version + +regcomp +regexec +regerror +regfree diff --git a/pcre/pcregrep.c b/pcre/pcregrep.c new file mode 100644 index 00000000..e8c934ef --- /dev/null +++ b/pcre/pcregrep.c @@ -0,0 +1,228 @@ +/************************************************* +* pcregrep program * +*************************************************/ + +/* This is a grep program that uses the PCRE regular expression library to do +its pattern matching. */ + +#include +#include +#include +#include +#include "config.h" +#include "pcre.h" + +#define FALSE 0 +#define TRUE 1 + +typedef int BOOL; + + + +/************************************************* +* Global variables * +*************************************************/ + +static pcre *pattern; +static pcre_extra *hints; + +static BOOL count_only = FALSE; +static BOOL filenames_only = FALSE; +static BOOL invert = FALSE; +static BOOL number = FALSE; +static BOOL silent = FALSE; +static BOOL whole_lines = FALSE; + + + +#if ! HAVE_STRERROR +/************************************************* +* Provide strerror() for non-ANSI libraries * +*************************************************/ + +/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() +in their libraries, but can provide the same facility by this simple +alternative function. */ + +extern int sys_nerr; +extern char *sys_errlist[]; + +char * +strerror(int n) +{ +if (n < 0 || n >= sys_nerr) return "unknown error number"; +return sys_errlist[n]; +} +#endif /* HAVE_STRERROR */ + + + +/************************************************* +* Grep an individual file * +*************************************************/ + +static int +pcregrep(FILE *in, char *name) +{ +int rc = 1; +int linenumber = 0; +int count = 0; +int offsets[99]; +char buffer[BUFSIZ]; + +while (fgets(buffer, sizeof(buffer), in) != NULL) + { + BOOL match; + int length = (int)strlen(buffer); + if (length > 0 && buffer[length-1] == '\n') buffer[--length] = 0; + linenumber++; + + match = pcre_exec(pattern, hints, buffer, length, 0, 0, offsets, 99) >= 0; + if (match && whole_lines && offsets[1] != length) match = FALSE; + + if (match != invert) + { + if (count_only) count++; + + else if (filenames_only) + { + fprintf(stdout, "%s\n", (name == NULL)? "" : name); + return 0; + } + + else if (silent) return 0; + + else + { + if (name != NULL) fprintf(stdout, "%s:", name); + if (number) fprintf(stdout, "%d:", linenumber); + fprintf(stdout, "%s\n", buffer); + } + + rc = 0; + } + } + +if (count_only) + { + if (name != NULL) fprintf(stdout, "%s:", name); + fprintf(stdout, "%d\n", count); + } + +return rc; +} + + + + +/************************************************* +* Usage function * +*************************************************/ + +static int +usage(int rc) +{ +fprintf(stderr, "Usage: pcregrep [-Vchilnsvx] pattern [file] ...\n"); +return rc; +} + + + + +/************************************************* +* Main program * +*************************************************/ + +int +main(int argc, char **argv) +{ +int i; +int rc = 1; +int options = 0; +int errptr; +const char *error; +BOOL filenames = TRUE; + +/* Process the options */ + +for (i = 1; i < argc; i++) + { + char *s; + if (argv[i][0] != '-') break; + s = argv[i] + 1; + while (*s != 0) + { + switch (*s++) + { + case 'c': count_only = TRUE; break; + case 'h': filenames = FALSE; break; + case 'i': options |= PCRE_CASELESS; break; + case 'l': filenames_only = TRUE; + case 'n': number = TRUE; break; + case 's': silent = TRUE; break; + case 'v': invert = TRUE; break; + case 'x': whole_lines = TRUE; options |= PCRE_ANCHORED; break; + + case 'V': + fprintf(stderr, "PCRE version %s\n", pcre_version()); + break; + + default: + fprintf(stderr, "pcregrep: unknown option %c\n", s[-1]); + return usage(2); + } + } + } + +/* There must be at least a regexp argument */ + +if (i >= argc) return usage(0); + +/* Compile the regular expression. */ + +pattern = pcre_compile(argv[i++], options, &error, &errptr, NULL); +if (pattern == NULL) + { + fprintf(stderr, "pcregrep: error in regex at offset %d: %s\n", errptr, error); + return 2; + } + +/* Study the regular expression, as we will be running it may times */ + +hints = pcre_study(pattern, 0, &error); +if (error != NULL) + { + fprintf(stderr, "pcregrep: error while studing regex: %s\n", error); + return 2; + } + +/* If there are no further arguments, do the business on stdin and exit */ + +if (i >= argc) return pcregrep(stdin, NULL); + +/* Otherwise, work through the remaining arguments as files. If there is only +one, don't give its name on the output. */ + +if (i == argc - 1) filenames = FALSE; +if (filenames_only) filenames = TRUE; + +for (; i < argc; i++) + { + FILE *in = fopen(argv[i], "r"); + if (in == NULL) + { + fprintf(stderr, "%s: failed to open: %s\n", argv[i], strerror(errno)); + rc = 2; + } + else + { + int frc = pcregrep(in, filenames? argv[i] : NULL); + if (frc == 0 && rc == 1) rc = 0; + fclose(in); + } + } + +return rc; +} + +/* End */ diff --git a/pcre/pcreposix.h b/pcre/pcreposix.h new file mode 100644 index 00000000..7660acbd --- /dev/null +++ b/pcre/pcreposix.h @@ -0,0 +1,88 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* Copyright (c) 1997-2000 University of Cambridge */ + +#ifndef _PCREPOSIX_H +#define _PCREPOSIX_H + +/* This is the header for the POSIX wrapper interface to the PCRE Perl- +Compatible Regular Expression library. It defines the things POSIX says should +be there. I hope. */ + +/* Have to include stdlib.h in order to ensure that size_t is defined. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options defined by POSIX. */ + +#define REG_ICASE 0x01 +#define REG_NEWLINE 0x02 +#define REG_NOTBOL 0x04 +#define REG_NOTEOL 0x08 + +/* These are not used by PCRE, but by defining them we make it easier +to slot PCRE into existing programs that make POSIX calls. */ + +#define REG_EXTENDED 0 +#define REG_NOSUB 0 + +/* Error values. Not all these are relevant or used by the wrapper. */ + +enum { + REG_ASSERT = 1, /* internal error ? */ + REG_BADBR, /* invalid repeat counts in {} */ + REG_BADPAT, /* pattern error */ + REG_BADRPT, /* ? * + invalid */ + REG_EBRACE, /* unbalanced {} */ + REG_EBRACK, /* unbalanced [] */ + REG_ECOLLATE, /* collation error - not relevant */ + REG_ECTYPE, /* bad class */ + REG_EESCAPE, /* bad escape sequence */ + REG_EMPTY, /* empty expression */ + REG_EPAREN, /* unbalanced () */ + REG_ERANGE, /* bad range inside [] */ + REG_ESIZE, /* expression too big */ + REG_ESPACE, /* failed to get memory */ + REG_ESUBREG, /* bad back reference */ + REG_INVARG, /* bad argument */ + REG_NOMATCH /* match failed */ +}; + + +/* The structure representing a compiled regular expression. */ + +typedef struct { + void *re_pcre; + size_t re_nsub; + size_t re_erroffset; +} regex_t; + +/* The structure in which a captured offset is returned. */ + +typedef int regoff_t; + +typedef struct { + regoff_t rm_so; + regoff_t rm_eo; +} regmatch_t; + +/* The functions */ + +extern int regcomp(regex_t *, const char *, int); +extern int regexec(regex_t *, const char *, size_t, regmatch_t *, int); +extern size_t regerror(int, const regex_t *, char *, size_t); +extern void regfree(regex_t *); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcreposix.h */ diff --git a/pcre/pcretest.c b/pcre/pcretest.c new file mode 100644 index 00000000..ee5df5f0 --- /dev/null +++ b/pcre/pcretest.c @@ -0,0 +1,1225 @@ +/************************************************* +* PCRE testing program * +*************************************************/ + +#include +#include +#include +#include +#include +#include + +/* Use the internal info for displaying the results of pcre_study(). */ + +#include "internal.h" + +/* It is possible to compile this test program without including support for +testing the POSIX interface, though this is not available via the standard +Makefile. */ + +#if !defined NOPOSIX +#include "pcreposix.h" +#endif + +#ifndef CLOCKS_PER_SEC +#ifdef CLK_TCK +#define CLOCKS_PER_SEC CLK_TCK +#else +#define CLOCKS_PER_SEC 100 +#endif +#endif + +#define LOOPREPEAT 20000 + + +static FILE *outfile; +static int log_store = 0; +static size_t gotten_store; + + + +static int utf8_table1[] = { + 0x0000007f, 0x000007ff, 0x0000ffff, 0x001fffff, 0x03ffffff, 0x7fffffff}; + +static int utf8_table2[] = { + 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; + +static int utf8_table3[] = { + 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; + + +/************************************************* +* Convert character value to UTF-8 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x7fffffff +and encodes it as a UTF-8 character in 0 to 6 bytes. + +Arguments: + cvalue the character value + buffer pointer to buffer for result - at least 6 bytes long + +Returns: number of characters placed in the buffer + -1 if input character is negative + 0 if input character is positive but too big (only when + int is longer than 32 bits) +*/ + +static int +ord2utf8(int cvalue, unsigned char *buffer) +{ +register int i, j; +for (i = 0; i < sizeof(utf8_table1)/sizeof(int); i++) + if (cvalue <= utf8_table1[i]) break; +if (i >= sizeof(utf8_table1)/sizeof(int)) return 0; +if (cvalue < 0) return -1; +*buffer++ = utf8_table2[i] | (cvalue & utf8_table3[i]); +cvalue >>= 6 - i; +for (j = 0; j < i; j++) + { + *buffer++ = 0x80 | (cvalue & 0x3f); + cvalue >>= 6; + } +return i + 1; +} + + +/************************************************* +* Convert UTF-8 string to value * +*************************************************/ + +/* This function takes one or more bytes that represents a UTF-8 character, +and returns the value of the character. + +Argument: + buffer a pointer to the byte vector + vptr a pointer to an int to receive the value + +Returns: > 0 => the number of bytes consumed + -6 to 0 => malformed UTF-8 character at offset = (-return) +*/ + +int +utf82ord(unsigned char *buffer, int *vptr) +{ +int c = *buffer++; +int d = c; +int i, j, s; + +for (i = -1; i < 6; i++) /* i is number of additional bytes */ + { + if ((d & 0x80) == 0) break; + d <<= 1; + } + +if (i == -1) { *vptr = c; return 1; } /* ascii character */ +if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ + +/* i now has a value in the range 1-5 */ + +d = c & utf8_table3[i]; +s = 6 - i; + +for (j = 0; j < i; j++) + { + c = *buffer++; + if ((c & 0xc0) != 0x80) return -(j+1); + d |= (c & 0x3f) << s; + s += 6; + } + +/* Check that encoding was the correct unique one */ + +for (j = 0; j < sizeof(utf8_table1)/sizeof(int); j++) + if (d <= utf8_table1[j]) break; +if (j != i) return -(i+1); + +/* Valid value */ + +*vptr = d; +return i+1; +} + + + + + + +/* Debugging function to print the internal form of the regex. This is the same +code as contained in pcre.c under the DEBUG macro. */ + +static const char *OP_names[] = { + "End", "\\A", "\\B", "\\b", "\\D", "\\d", + "\\S", "\\s", "\\W", "\\w", "\\Z", "\\z", + "Opt", "^", "$", "Any", "chars", "not", + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", + "*", "*?", "+", "+?", "?", "??", "{", "{", + "class", "Ref", "Recurse", + "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", + "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cref", + "Brazero", "Braminzero", "Bra" +}; + + +static void print_internals(pcre *re) +{ +unsigned char *code = ((real_pcre *)re)->code; + +fprintf(outfile, "------------------------------------------------------------------\n"); + +for(;;) + { + int c; + int charlength; + + fprintf(outfile, "%3d ", (int)(code - ((real_pcre *)re)->code)); + + if (*code >= OP_BRA) + { + fprintf(outfile, "%3d Bra %d", (code[1] << 8) + code[2], *code - OP_BRA); + code += 2; + } + + else switch(*code) + { + case OP_END: + fprintf(outfile, " %s\n", OP_names[*code]); + fprintf(outfile, "------------------------------------------------------------------\n"); + return; + + case OP_OPT: + fprintf(outfile, " %.2x %s", code[1], OP_names[*code]); + code++; + break; + + case OP_COND: + fprintf(outfile, "%3d Cond", (code[1] << 8) + code[2]); + code += 2; + break; + + case OP_CREF: + fprintf(outfile, " %.2d %s", code[1], OP_names[*code]); + code++; + break; + + case OP_CHARS: + charlength = *(++code); + fprintf(outfile, "%3d ", charlength); + while (charlength-- > 0) + if (isprint(c = *(++code))) fprintf(outfile, "%c", c); + else fprintf(outfile, "\\x%02x", c); + break; + + case OP_KETRMAX: + case OP_KETRMIN: + case OP_ALT: + case OP_KET: + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + fprintf(outfile, "%3d %s", (code[1] << 8) + code[2], OP_names[*code]); + code += 2; + break; + + case OP_REVERSE: + fprintf(outfile, "%3d %s", (code[1] << 8) + code[2], OP_names[*code]); + code += 2; + break; + + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + if (*code >= OP_TYPESTAR) + fprintf(outfile, " %s", OP_names[code[1]]); + else if (isprint(c = code[1])) fprintf(outfile, " %c", c); + else fprintf(outfile, " \\x%02x", c); + fprintf(outfile, "%s", OP_names[*code++]); + break; + + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + if (isprint(c = code[3])) fprintf(outfile, " %c{", c); + else fprintf(outfile, " \\x%02x{", c); + if (*code != OP_EXACT) fprintf(outfile, ","); + fprintf(outfile, "%d}", (code[1] << 8) + code[2]); + if (*code == OP_MINUPTO) fprintf(outfile, "?"); + code += 3; + break; + + case OP_TYPEEXACT: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + fprintf(outfile, " %s{", OP_names[code[3]]); + if (*code != OP_TYPEEXACT) fprintf(outfile, "0,"); + fprintf(outfile, "%d}", (code[1] << 8) + code[2]); + if (*code == OP_TYPEMINUPTO) fprintf(outfile, "?"); + code += 3; + break; + + case OP_NOT: + if (isprint(c = *(++code))) fprintf(outfile, " [^%c]", c); + else fprintf(outfile, " [^\\x%02x]", c); + break; + + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + if (isprint(c = code[1])) fprintf(outfile, " [^%c]", c); + else fprintf(outfile, " [^\\x%02x]", c); + fprintf(outfile, "%s", OP_names[*code++]); + break; + + case OP_NOTEXACT: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + if (isprint(c = code[3])) fprintf(outfile, " [^%c]{", c); + else fprintf(outfile, " [^\\x%02x]{", c); + if (*code != OP_NOTEXACT) fprintf(outfile, ","); + fprintf(outfile, "%d}", (code[1] << 8) + code[2]); + if (*code == OP_NOTMINUPTO) fprintf(outfile, "?"); + code += 3; + break; + + case OP_REF: + fprintf(outfile, " \\%d", *(++code)); + code++; + goto CLASS_REF_REPEAT; + + case OP_CLASS: + { + int i, min, max; + code++; + fprintf(outfile, " ["); + + for (i = 0; i < 256; i++) + { + if ((code[i/8] & (1 << (i&7))) != 0) + { + int j; + for (j = i+1; j < 256; j++) + if ((code[j/8] & (1 << (j&7))) == 0) break; + if (i == '-' || i == ']') fprintf(outfile, "\\"); + if (isprint(i)) fprintf(outfile, "%c", i); else fprintf(outfile, "\\x%02x", i); + if (--j > i) + { + fprintf(outfile, "-"); + if (j == '-' || j == ']') fprintf(outfile, "\\"); + if (isprint(j)) fprintf(outfile, "%c", j); else fprintf(outfile, "\\x%02x", j); + } + i = j; + } + } + fprintf(outfile, "]"); + code += 32; + + CLASS_REF_REPEAT: + + switch(*code) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + fprintf(outfile, "%s", OP_names[*code]); + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + min = (code[1] << 8) + code[2]; + max = (code[3] << 8) + code[4]; + if (max == 0) fprintf(outfile, "{%d,}", min); + else fprintf(outfile, "{%d,%d}", min, max); + if (*code == OP_CRMINRANGE) fprintf(outfile, "?"); + code += 4; + break; + + default: + code--; + } + } + break; + + /* Anything else is just a one-node item */ + + default: + fprintf(outfile, " %s", OP_names[*code]); + break; + } + + code++; + fprintf(outfile, "\n"); + } +} + + + +/* Character string printing function. A "normal" and a UTF-8 version. */ + +static void pchars(unsigned char *p, int length, int utf8) +{ +int c; +while (length-- > 0) + { + if (utf8) + { + int rc = utf82ord(p, &c); + if (rc > 0) + { + length -= rc - 1; + p += rc; + if (c < 256 && isprint(c)) fprintf(outfile, "%c", c); + else fprintf(outfile, "\\x{%02x}", c); + continue; + } + } + + /* Not UTF-8, or malformed UTF-8 */ + + if (isprint(c = *(p++))) fprintf(outfile, "%c", c); + else fprintf(outfile, "\\x%02x", c); + } +} + + + +/* Alternative malloc function, to test functionality and show the size of the +compiled re. */ + +static void *new_malloc(size_t size) +{ +gotten_store = size; +if (log_store) + fprintf(outfile, "Memory allocation (code space): %d\n", + (int)((int)size - offsetof(real_pcre, code[0]))); +return malloc(size); +} + + + + +/* Get one piece of information from the pcre_fullinfo() function */ + +static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) +{ +int rc; +if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) + fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); +} + + + + +/* Read lines from named file or stdin and write to named file or stdout; lines +consist of a regular expression, in delimiters and optionally followed by +options, followed by a set of test data, terminated by an empty line. */ + +int main(int argc, char **argv) +{ +FILE *infile = stdin; +int options = 0; +int study_options = 0; +int op = 1; +int timeit = 0; +int showinfo = 0; +int showstore = 0; +int posix = 0; +int debug = 0; +int done = 0; +unsigned char buffer[30000]; +unsigned char dbuffer[1024]; + +/* Static so that new_malloc can use it. */ + +outfile = stdout; + +/* Scan options */ + +while (argc > 1 && argv[op][0] == '-') + { + if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) + showstore = 1; + else if (strcmp(argv[op], "-t") == 0) timeit = 1; + else if (strcmp(argv[op], "-i") == 0) showinfo = 1; + else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; + else if (strcmp(argv[op], "-p") == 0) posix = 1; + else + { + printf("*** Unknown option %s\n", argv[op]); + printf("Usage: pcretest [-d] [-i] [-p] [-s] [-t] [ []]\n"); + printf(" -d debug: show compiled code; implies -i\n" + " -i show information about compiled pattern\n" + " -p use POSIX interface\n" + " -s output store information\n" + " -t time compilation and execution\n"); + return 1; + } + op++; + argc--; + } + +/* Sort out the input and output files */ + +if (argc > 1) + { + infile = fopen(argv[op], "r"); + if (infile == NULL) + { + printf("** Failed to open %s\n", argv[op]); + return 1; + } + } + +if (argc > 2) + { + outfile = fopen(argv[op+1], "w"); + if (outfile == NULL) + { + printf("** Failed to open %s\n", argv[op+1]); + return 1; + } + } + +/* Set alternative malloc function */ + +pcre_malloc = new_malloc; + +/* Heading line, then prompt for first regex if stdin */ + +fprintf(outfile, "PCRE version %s\n\n", pcre_version()); + +/* Main loop */ + +while (!done) + { + pcre *re = NULL; + pcre_extra *extra = NULL; + +#if !defined NOPOSIX /* There are still compilers that require no indent */ + regex_t preg; + int do_posix = 0; +#endif + + const char *error; + unsigned char *p, *pp, *ppp; + unsigned const char *tables = NULL; + int do_study = 0; + int do_debug = debug; + int do_G = 0; + int do_g = 0; + int do_showinfo = showinfo; + int do_showrest = 0; + int utf8 = 0; + int erroroffset, len, delimiter; + + if (infile == stdin) printf(" re> "); + if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) break; + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + + p = buffer; + while (isspace(*p)) p++; + if (*p == 0) continue; + + /* Get the delimiter and seek the end of the pattern; if is isn't + complete, read more. */ + + delimiter = *p++; + + if (isalnum(delimiter) || delimiter == '\\') + { + fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); + goto SKIP_DATA; + } + + pp = p; + + for(;;) + { + while (*pp != 0) + { + if (*pp == '\\' && pp[1] != 0) pp++; + else if (*pp == delimiter) break; + pp++; + } + if (*pp != 0) break; + + len = sizeof(buffer) - (pp - buffer); + if (len < 256) + { + fprintf(outfile, "** Expression too long - missing delimiter?\n"); + goto SKIP_DATA; + } + + if (infile == stdin) printf(" > "); + if (fgets((char *)pp, len, infile) == NULL) + { + fprintf(outfile, "** Unexpected EOF\n"); + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)pp); + } + + /* If the first character after the delimiter is backslash, make + the pattern end with backslash. This is purely to provide a way + of testing for the error message when a pattern ends with backslash. */ + + if (pp[1] == '\\') *pp++ = '\\'; + + /* Terminate the pattern at the delimiter */ + + *pp++ = 0; + + /* Look for options after final delimiter */ + + options = 0; + study_options = 0; + log_store = showstore; /* default from command line */ + + while (*pp != 0) + { + switch (*pp++) + { + case 'g': do_g = 1; break; + case 'i': options |= PCRE_CASELESS; break; + case 'm': options |= PCRE_MULTILINE; break; + case 's': options |= PCRE_DOTALL; break; + case 'x': options |= PCRE_EXTENDED; break; + + case '+': do_showrest = 1; break; + case 'A': options |= PCRE_ANCHORED; break; + case 'D': do_debug = do_showinfo = 1; break; + case 'E': options |= PCRE_DOLLAR_ENDONLY; break; + case 'G': do_G = 1; break; + case 'I': do_showinfo = 1; break; + case 'M': log_store = 1; break; + +#if !defined NOPOSIX + case 'P': do_posix = 1; break; +#endif + + case 'S': do_study = 1; break; + case 'U': options |= PCRE_UNGREEDY; break; + case 'X': options |= PCRE_EXTRA; break; + case '8': options |= PCRE_UTF8; utf8 = 1; break; + + case 'L': + ppp = pp; + while (*ppp != '\n' && *ppp != ' ') ppp++; + *ppp = 0; + if (setlocale(LC_CTYPE, (const char *)pp) == NULL) + { + fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); + goto SKIP_DATA; + } + tables = pcre_maketables(); + pp = ppp; + break; + + case '\n': case ' ': break; + default: + fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); + goto SKIP_DATA; + } + } + + /* Handle compiling via the POSIX interface, which doesn't support the + timing, showing, or debugging options, nor the ability to pass over + local character tables. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int cflags = 0; + if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; + if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; + rc = regcomp(&preg, (char *)p, cflags); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, sizeof(buffer)); + fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); + goto SKIP_DATA; + } + } + + /* Handle compiling via the native interface */ + + else +#endif /* !defined NOPOSIX */ + + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < LOOPREPEAT; i++) + { + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + if (re != NULL) free(re); + } + time_taken = clock() - start_time; + fprintf(outfile, "Compile time %.3f milliseconds\n", + ((double)time_taken * 1000.0) / + ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); + } + + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (re == NULL) + { + fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); + SKIP_DATA: + if (infile != stdin) + { + for (;;) + { + if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) + { + done = 1; + goto CONTINUE; + } + len = (int)strlen((char *)buffer); + while (len > 0 && isspace(buffer[len-1])) len--; + if (len == 0) break; + } + fprintf(outfile, "\n"); + } + goto CONTINUE; + } + + /* Compilation succeeded; print data if required. There are now two + info-returning functions. The old one has a limited interface and + returns only limited data. Check that it agrees with the newer one. */ + + if (do_showinfo) + { + int old_first_char, old_options, old_count; + int count, backrefmax, first_char, need_char; + size_t size; + + if (do_debug) print_internals(re); + + new_info(re, NULL, PCRE_INFO_OPTIONS, &options); + new_info(re, NULL, PCRE_INFO_SIZE, &size); + new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); + new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); + new_info(re, NULL, PCRE_INFO_FIRSTCHAR, &first_char); + new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); + + old_count = pcre_info(re, &old_options, &old_first_char); + if (count < 0) fprintf(outfile, + "Error %d from pcre_info()\n", count); + else + { + if (old_count != count) fprintf(outfile, + "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, + old_count); + + if (old_first_char != first_char) fprintf(outfile, + "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", + first_char, old_first_char); + + if (old_options != options) fprintf(outfile, + "Options disagreement: pcre_fullinfo=%d pcre_info=%d\n", options, + old_options); + } + + if (size != gotten_store) fprintf(outfile, + "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", + size, gotten_store); + + fprintf(outfile, "Capturing subpattern count = %d\n", count); + if (backrefmax > 0) + fprintf(outfile, "Max back reference = %d\n", backrefmax); + if (options == 0) fprintf(outfile, "No options\n"); + else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s\n", + ((options & PCRE_ANCHORED) != 0)? " anchored" : "", + ((options & PCRE_CASELESS) != 0)? " caseless" : "", + ((options & PCRE_EXTENDED) != 0)? " extended" : "", + ((options & PCRE_MULTILINE) != 0)? " multiline" : "", + ((options & PCRE_DOTALL) != 0)? " dotall" : "", + ((options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", + ((options & PCRE_EXTRA) != 0)? " extra" : "", + ((options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", + ((options & PCRE_UTF8) != 0)? " utf8" : ""); + + if (((((real_pcre *)re)->options) & PCRE_ICHANGED) != 0) + fprintf(outfile, "Case state changes\n"); + + if (first_char == -1) + { + fprintf(outfile, "First char at start or follows \\n\n"); + } + else if (first_char < 0) + { + fprintf(outfile, "No first char\n"); + } + else + { + if (isprint(first_char)) + fprintf(outfile, "First char = \'%c\'\n", first_char); + else + fprintf(outfile, "First char = %d\n", first_char); + } + + if (need_char < 0) + { + fprintf(outfile, "No need char\n"); + } + else + { + if (isprint(need_char)) + fprintf(outfile, "Need char = \'%c\'\n", need_char); + else + fprintf(outfile, "Need char = %d\n", need_char); + } + } + + /* If /S was present, study the regexp to generate additional info to + help with the matching. */ + + if (do_study) + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < LOOPREPEAT; i++) + extra = pcre_study(re, study_options, &error); + time_taken = clock() - start_time; + if (extra != NULL) free(extra); + fprintf(outfile, " Study time %.3f milliseconds\n", + ((double)time_taken * 1000.0)/ + ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); + } + + extra = pcre_study(re, study_options, &error); + if (error != NULL) + fprintf(outfile, "Failed to study: %s\n", error); + else if (extra == NULL) + fprintf(outfile, "Study returned NULL\n"); + + else if (do_showinfo) + { + uschar *start_bits = NULL; + new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); + if (start_bits == NULL) + fprintf(outfile, "No starting character set\n"); + else + { + int i; + int c = 24; + fprintf(outfile, "Starting character set: "); + for (i = 0; i < 256; i++) + { + if ((start_bits[i/8] & (1<<(i%8))) != 0) + { + if (c > 75) + { + fprintf(outfile, "\n "); + c = 2; + } + if (isprint(i) && i != ' ') + { + fprintf(outfile, "%c ", i); + c += 2; + } + else + { + fprintf(outfile, "\\x%02x ", i); + c += 5; + } + } + } + fprintf(outfile, "\n"); + } + } + } + } + + /* Read data lines and test them */ + + for (;;) + { + unsigned char *q; + unsigned char *bptr = dbuffer; + int count, c; + int copystrings = 0; + int getstrings = 0; + int getlist = 0; + int gmatched = 0; + int start_offset = 0; + int g_notempty = 0; + int offsets[45]; + int size_offsets = sizeof(offsets)/sizeof(int); + + options = 0; + + if (infile == stdin) printf("data> "); + if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) + { + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + + len = (int)strlen((char *)buffer); + while (len > 0 && isspace(buffer[len-1])) len--; + buffer[len] = 0; + if (len == 0) break; + + p = buffer; + while (isspace(*p)) p++; + + q = dbuffer; + while ((c = *p++) != 0) + { + int i = 0; + int n = 0; + if (c == '\\') switch ((c = *p++)) + { + case 'a': c = 7; break; + case 'b': c = '\b'; break; + case 'e': c = 27; break; + case 'f': c = '\f'; break; + case 'n': c = '\n'; break; + case 'r': c = '\r'; break; + case 't': c = '\t'; break; + case 'v': c = '\v'; break; + + case '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + c -= '0'; + while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') + c = c * 8 + *p++ - '0'; + break; + + case 'x': + + /* Handle \x{..} specially - new Perl thing for utf8 */ + + if (*p == '{') + { + unsigned char *pt = p; + c = 0; + while (isxdigit(*(++pt))) + c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); + if (*pt == '}') + { + unsigned char buffer[8]; + int ii, utn; + utn = ord2utf8(c, buffer); + for (ii = 0; ii < utn - 1; ii++) *q++ = buffer[ii]; + c = buffer[ii]; /* Last byte */ + p = pt + 1; + break; + } + /* Not correct form; fall through */ + } + + /* Ordinary \x */ + + c = 0; + while (i++ < 2 && isxdigit(*p)) + { + c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); + p++; + } + break; + + case 0: /* Allows for an empty line */ + p--; + continue; + + case 'A': /* Option setting */ + options |= PCRE_ANCHORED; + continue; + + case 'B': + options |= PCRE_NOTBOL; + continue; + + case 'C': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + copystrings |= 1 << n; + continue; + + case 'G': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + getstrings |= 1 << n; + continue; + + case 'L': + getlist = 1; + continue; + + case 'N': + options |= PCRE_NOTEMPTY; + continue; + + case 'O': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (n <= (int)(sizeof(offsets)/sizeof(int))) size_offsets = n; + continue; + + case 'Z': + options |= PCRE_NOTEOL; + continue; + } + *q++ = c; + } + *q = 0; + len = q - dbuffer; + + /* Handle matching via the POSIX interface, which does not + support timing. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int eflags = 0; + regmatch_t pmatch[sizeof(offsets)/sizeof(int)]; + if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; + if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; + + rc = regexec(&preg, (const char *)bptr, size_offsets, pmatch, eflags); + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, sizeof(buffer)); + fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); + } + else + { + size_t i; + for (i = 0; i < size_offsets; i++) + { + if (pmatch[i].rm_so >= 0) + { + fprintf(outfile, "%2d: ", (int)i); + pchars(dbuffer + pmatch[i].rm_so, + pmatch[i].rm_eo - pmatch[i].rm_so, utf8); + fprintf(outfile, "\n"); + if (i == 0 && do_showrest) + { + fprintf(outfile, " 0+ "); + pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, utf8); + fprintf(outfile, "\n"); + } + } + } + } + } + + /* Handle matching via the native interface - repeats for /g and /G */ + + else +#endif /* !defined NOPOSIX */ + + for (;; gmatched++) /* Loop for /g or /G */ + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < LOOPREPEAT; i++) + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, offsets, size_offsets); + time_taken = clock() - start_time; + fprintf(outfile, "Execute time %.3f milliseconds\n", + ((double)time_taken * 1000.0)/ + ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); + } + + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, offsets, size_offsets); + + if (count == 0) + { + fprintf(outfile, "Matched, but too many substrings\n"); + count = size_offsets/3; + } + + /* Matched */ + + if (count >= 0) + { + int i; + for (i = 0; i < count * 2; i += 2) + { + if (offsets[i] < 0) + fprintf(outfile, "%2d: \n", i/2); + else + { + fprintf(outfile, "%2d: ", i/2); + pchars(bptr + offsets[i], offsets[i+1] - offsets[i], utf8); + fprintf(outfile, "\n"); + if (i == 0) + { + if (do_showrest) + { + fprintf(outfile, " 0+ "); + pchars(bptr + offsets[i+1], len - offsets[i+1], utf8); + fprintf(outfile, "\n"); + } + } + } + } + + for (i = 0; i < 32; i++) + { + if ((copystrings & (1 << i)) != 0) + { + char copybuffer[16]; + int rc = pcre_copy_substring((char *)bptr, offsets, count, + i, copybuffer, sizeof(copybuffer)); + if (rc < 0) + fprintf(outfile, "copy substring %d failed %d\n", i, rc); + else + fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); + } + } + + for (i = 0; i < 32; i++) + { + if ((getstrings & (1 << i)) != 0) + { + const char *substring; + int rc = pcre_get_substring((char *)bptr, offsets, count, + i, &substring); + if (rc < 0) + fprintf(outfile, "get substring %d failed %d\n", i, rc); + else + { + fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); + /* free((void *)substring); */ + pcre_free_substring(substring); + } + } + } + + if (getlist) + { + const char **stringlist; + int rc = pcre_get_substring_list((char *)bptr, offsets, count, + &stringlist); + if (rc < 0) + fprintf(outfile, "get substring list failed %d\n", rc); + else + { + for (i = 0; i < count; i++) + fprintf(outfile, "%2dL %s\n", i, stringlist[i]); + if (stringlist[i] != NULL) + fprintf(outfile, "string list not terminated by NULL\n"); + /* free((void *)stringlist); */ + pcre_free_substring_list(stringlist); + } + } + } + + /* Failed to match. If this is a /g or /G loop and we previously set + g_notempty after a null match, this is not necessarily the end. + We want to advance the start offset, and continue. Fudge the offset + values to achieve this. We won't be at the end of the string - that + was checked before setting g_notempty. */ + + else + { + if (g_notempty != 0) + { + offsets[0] = start_offset; + offsets[1] = start_offset + 1; + } + else + { + if (gmatched == 0) /* Error if no previous matches */ + { + if (count == -1) fprintf(outfile, "No match\n"); + else fprintf(outfile, "Error %d\n", count); + } + break; /* Out of the /g loop */ + } + } + + /* If not /g or /G we are done */ + + if (!do_g && !do_G) break; + + /* If we have matched an empty string, first check to see if we are at + the end of the subject. If so, the /g loop is over. Otherwise, mimic + what Perl's /g options does. This turns out to be rather cunning. First + we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the + same point. If this fails (picked up above) we advance to the next + character. */ + + g_notempty = 0; + if (offsets[0] == offsets[1]) + { + if (offsets[0] == len) break; + g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; + } + + /* For /g, update the start offset, leaving the rest alone */ + + if (do_g) start_offset = offsets[1]; + + /* For /G, update the pointer and length */ + + else + { + bptr += offsets[1]; + len -= offsets[1]; + } + } /* End of loop for /g and /G */ + } /* End of loop for data lines */ + + CONTINUE: + +#if !defined NOPOSIX + if (posix || do_posix) regfree(&preg); +#endif + + if (re != NULL) free(re); + if (extra != NULL) free(extra); + if (tables != NULL) + { + free((void *)tables); + setlocale(LC_CTYPE, "C"); + } + } + +fprintf(outfile, "\n"); +return 0; +} + +/* End */ diff --git a/pcre/study.c b/pcre/study.c new file mode 100644 index 00000000..676db946 --- /dev/null +++ b/pcre/study.c @@ -0,0 +1,397 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* +This is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. See +the file Tech.Notes for some information on the internals. + +Written by: Philip Hazel + + Copyright (c) 1997-2000 University of Cambridge + +----------------------------------------------------------------------------- +Permission is granted to anyone to use this software for any purpose on any +computer system, and to redistribute it freely, subject to the following +restrictions: + +1. This software is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +2. The origin of this software must not be misrepresented, either by + explicit claim or by omission. + +3. Altered versions must be plainly marked as such, and must not be + misrepresented as being the original software. + +4. If PCRE is embedded in any software that is released under the GNU + General Purpose Licence (GPL), then the terms of that licence shall + supersede any condition above with which it is incompatible. +----------------------------------------------------------------------------- +*/ + + +/* Include the internals header, which itself includes Standard C headers plus +the external pcre header. */ + +#include "internal.h" + + + +/************************************************* +* Set a bit and maybe its alternate case * +*************************************************/ + +/* Given a character, set its bit in the table, and also the bit for the other +version of a letter if we are caseless. + +Arguments: + start_bits points to the bit map + c is the character + caseless the caseless flag + cd the block with char table pointers + +Returns: nothing +*/ + +static void +set_bit(uschar *start_bits, int c, BOOL caseless, compile_data *cd) +{ +start_bits[c/8] |= (1 << (c&7)); +if (caseless && (cd->ctypes[c] & ctype_letter) != 0) + start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); +} + + + +/************************************************* +* Create bitmap of starting chars * +*************************************************/ + +/* This function scans a compiled unanchored expression and attempts to build a +bitmap of the set of initial characters. If it can't, it returns FALSE. As time +goes by, we may be able to get more clever at doing this. + +Arguments: + code points to an expression + start_bits points to a 32-byte table, initialized to 0 + caseless the current state of the caseless flag + cd the block with char table pointers + +Returns: TRUE if table built, FALSE otherwise +*/ + +static BOOL +set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, + compile_data *cd) +{ +register int c; + +/* This next statement and the later reference to dummy are here in order to +trick the optimizer of the IBM C compiler for OS/2 into generating correct +code. Apparently IBM isn't going to fix the problem, and we would rather not +disable optimization (in this module it actually makes a big difference, and +the pcre module can use all the optimization it can get). */ + +volatile int dummy; + +do + { + const uschar *tcode = code + 3; + BOOL try_next = TRUE; + + while (try_next) + { + try_next = FALSE; + + /* If a branch starts with a bracket or a positive lookahead assertion, + recurse to set bits from within them. That's all for this branch. */ + + if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) + { + if (!set_start_bits(tcode, start_bits, caseless, cd)) + return FALSE; + } + + else switch(*tcode) + { + default: + return FALSE; + + /* Skip over lookbehind and negative lookahead assertions */ + + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + try_next = TRUE; + do tcode += (tcode[1] << 8) + tcode[2]; while (*tcode == OP_ALT); + tcode += 3; + break; + + /* Skip over an option setting, changing the caseless flag */ + + case OP_OPT: + caseless = (tcode[1] & PCRE_CASELESS) != 0; + tcode += 2; + try_next = TRUE; + break; + + /* BRAZERO does the bracket, but carries on. */ + + case OP_BRAZERO: + case OP_BRAMINZERO: + if (!set_start_bits(++tcode, start_bits, caseless, cd)) + return FALSE; + dummy = 1; + do tcode += (tcode[1] << 8) + tcode[2]; while (*tcode == OP_ALT); + tcode += 3; + try_next = TRUE; + break; + + /* Single-char * or ? sets the bit and tries the next item */ + + case OP_STAR: + case OP_MINSTAR: + case OP_QUERY: + case OP_MINQUERY: + set_bit(start_bits, tcode[1], caseless, cd); + tcode += 2; + try_next = TRUE; + break; + + /* Single-char upto sets the bit and tries the next */ + + case OP_UPTO: + case OP_MINUPTO: + set_bit(start_bits, tcode[3], caseless, cd); + tcode += 4; + try_next = TRUE; + break; + + /* At least one single char sets the bit and stops */ + + case OP_EXACT: /* Fall through */ + tcode++; + + case OP_CHARS: /* Fall through */ + tcode++; + + case OP_PLUS: + case OP_MINPLUS: + set_bit(start_bits, tcode[1], caseless, cd); + break; + + /* Single character type sets the bits and stops */ + + case OP_NOT_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_digit]; + break; + + case OP_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_digit]; + break; + + case OP_NOT_WHITESPACE: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_space]; + break; + + case OP_WHITESPACE: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_space]; + break; + + case OP_NOT_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_word]; + break; + + case OP_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_word]; + break; + + /* One or more character type fudges the pointer and restarts, knowing + it will hit a single character type and stop there. */ + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + tcode++; + try_next = TRUE; + break; + + case OP_TYPEEXACT: + tcode += 3; + try_next = TRUE; + break; + + /* Zero or more repeats of character types set the bits and then + try again. */ + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + tcode += 2; /* Fall through */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + switch(tcode[1]) + { + case OP_NOT_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_digit]; + break; + + case OP_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_digit]; + break; + + case OP_NOT_WHITESPACE: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_space]; + break; + + case OP_WHITESPACE: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_space]; + break; + + case OP_NOT_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_word]; + break; + + case OP_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_word]; + break; + } + + tcode += 2; + try_next = TRUE; + break; + + /* Character class: set the bits and either carry on or not, + according to the repeat count. */ + + case OP_CLASS: + { + tcode++; + for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; + tcode += 32; + switch (*tcode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + tcode++; + try_next = TRUE; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + if (((tcode[1] << 8) + tcode[2]) == 0) + { + tcode += 5; + try_next = TRUE; + } + break; + } + } + break; /* End of class handling */ + + } /* End of switch */ + } /* End of try_next loop */ + + code += (code[1] << 8) + code[2]; /* Advance to next branch */ + } +while (*code == OP_ALT); +return TRUE; +} + + + +/************************************************* +* Study a compiled expression * +*************************************************/ + +/* This function is handed a compiled expression that it must study to produce +information that will speed up the matching. It returns a pcre_extra block +which then gets handed back to pcre_exec(). + +Arguments: + re points to the compiled expression + options contains option bits + errorptr points to where to place error messages; + set NULL unless error + +Returns: pointer to a pcre_extra block, + NULL on error or if no optimization possible +*/ + +pcre_extra * +pcre_study(const pcre *external_re, int options, const char **errorptr) +{ +uschar start_bits[32]; +real_pcre_extra *extra; +const real_pcre *re = (const real_pcre *)external_re; +compile_data compile_block; + +*errorptr = NULL; + +if (re == NULL || re->magic_number != MAGIC_NUMBER) + { + *errorptr = "argument is not a compiled regular expression"; + return NULL; + } + +if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) + { + *errorptr = "unknown or incorrect option bit(s) set"; + return NULL; + } + +/* For an anchored pattern, or an unchored pattern that has a first char, or a +multiline pattern that matches only at "line starts", no further processing at +present. */ + +if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) + return NULL; + +/* Set the character tables in the block which is passed around */ + +compile_block.lcc = re->tables + lcc_offset; +compile_block.fcc = re->tables + fcc_offset; +compile_block.cbits = re->tables + cbits_offset; +compile_block.ctypes = re->tables + ctypes_offset; + +/* See if we can find a fixed set of initial characters for the pattern. */ + +memset(start_bits, 0, 32 * sizeof(uschar)); +if (!set_start_bits(re->code, start_bits, (re->options & PCRE_CASELESS) != 0, + &compile_block)) return NULL; + +/* Get an "extra" block and put the information therein. */ + +extra = (real_pcre_extra *)(pcre_malloc)(sizeof(real_pcre_extra)); + +if (extra == NULL) + { + *errorptr = "failed to get memory"; + return NULL; + } + +extra->options = PCRE_STUDY_MAPPED; +memcpy(extra->start_bits, start_bits, sizeof(start_bits)); + +return (pcre_extra *)extra; +} + +/* End of study.c */