From b372098f33a0ba88171370233a9a63556e3cde1a Mon Sep 17 00:00:00 2001 From: Fabian Keil Date: Thu, 17 Apr 2008 14:53:31 +0000 Subject: [PATCH] Move simplematch() into urlmatch.c as it's only used to match (old-school) domain patterns. --- miscutil.c | 143 ++--------------------------------------------------- miscutil.h | 8 +-- urlmatch.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 151 insertions(+), 143 deletions(-) diff --git a/miscutil.c b/miscutil.c index 462eb835..3eb707ca 100644 --- a/miscutil.c +++ b/miscutil.c @@ -1,4 +1,4 @@ -const char miscutil_rcs[] = "$Id: miscutil.c,v 1.56 2007/12/01 12:59:05 fabiankeil Exp $"; +const char miscutil_rcs[] = "$Id: miscutil.c,v 1.57 2008/03/24 15:29:51 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/miscutil.c,v $ @@ -44,6 +44,9 @@ const char miscutil_rcs[] = "$Id: miscutil.c,v 1.56 2007/12/01 12:59:05 fabianke * * Revisions : * $Log: miscutil.c,v $ + * Revision 1.57 2008/03/24 15:29:51 fabiankeil + * Pet gcc43. + * * Revision 1.56 2007/12/01 12:59:05 fabiankeil * Some sanity checks for pick_from_range(). * @@ -790,144 +793,6 @@ char *string_toupper(const char *string) } -/********************************************************************* - * - * Function : simplematch - * - * Description : String matching, with a (greedy) '*' wildcard that - * stands for zero or more arbitrary characters and - * character classes in [], which take both enumerations - * and ranges. - * - * Parameters : - * 1 : pattern = pattern for matching - * 2 : text = text to be matched - * - * Returns : 0 if match, else nonzero - * - *********************************************************************/ -int simplematch(char *pattern, char *text) -{ - unsigned char *pat = (unsigned char *) pattern; - unsigned char *txt = (unsigned char *) text; - unsigned char *fallback = pat; - int wildcard = 0; - - unsigned char lastchar = 'a'; - unsigned i; - unsigned char charmap[32]; - - while (*txt) - { - - /* EOF pattern but !EOF text? */ - if (*pat == '\0') - { - if (wildcard) - { - pat = fallback; - } - else - { - return 1; - } - } - - /* '*' in the pattern? */ - if (*pat == '*') - { - - /* The pattern ends afterwards? Speed up the return. */ - if (*++pat == '\0') - { - return 0; - } - - /* Else, set wildcard mode and remember position after '*' */ - wildcard = 1; - fallback = pat; - } - - /* Character range specification? */ - if (*pat == '[') - { - memset(charmap, '\0', sizeof(charmap)); - - while (*++pat != ']') - { - if (!*pat) - { - return 1; - } - else if (*pat == '-') - { - if ((*++pat == ']') || *pat == '\0') - { - return(1); - } - for (i = lastchar; i <= *pat; i++) - { - charmap[i / 8] |= (unsigned char)(1 << (i % 8)); - } - } - else - { - charmap[*pat / 8] |= (unsigned char)(1 << (*pat % 8)); - lastchar = *pat; - } - } - } /* -END- if Character range specification */ - - - /* - * Char match, or char range match? - */ - if ( (*pat == *txt) - || (*pat == '?') - || ((*pat == ']') && (charmap[*txt / 8] & (1 << (*txt % 8)))) ) - { - /* - * Sucess: Go ahead - */ - pat++; - } - else if (!wildcard) - { - /* - * No match && no wildcard: No luck - */ - return 1; - } - else if (pat != fallback) - { - /* - * Increment text pointer if in char range matching - */ - if (*pat == ']') - { - txt++; - } - /* - * Wildcard mode && nonmatch beyond fallback: Rewind pattern - */ - pat = fallback; - /* - * Restart matching from current text pointer - */ - continue; - } - txt++; - } - - /* Cut off extra '*'s */ - if(*pat == '*') pat++; - - /* If this is the pattern's end, fine! */ - return(*pat); - -} - - /********************************************************************* * * Function : bindup diff --git a/miscutil.h b/miscutil.h index 38fb85ba..b3200d4d 100644 --- a/miscutil.h +++ b/miscutil.h @@ -1,6 +1,6 @@ #ifndef MISCUTIL_H_INCLUDED #define MISCUTIL_H_INCLUDED -#define MISCUTIL_H_VERSION "$Id: miscutil.h,v 1.28 2007/05/11 11:48:16 fabiankeil Exp $" +#define MISCUTIL_H_VERSION "$Id: miscutil.h,v 1.29 2007/09/09 18:20:20 fabiankeil Exp $" /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/miscutil.h,v $ @@ -37,6 +37,10 @@ * * Revisions : * $Log: miscutil.h,v $ + * Revision 1.29 2007/09/09 18:20:20 fabiankeil + * Turn privoxy_strlcpy() into a function and try to work with + * b0rked snprintf() implementations too. Reported by icmp30. + * * Revision 1.28 2007/05/11 11:48:16 fabiankeil * - Delete strsav() which was replaced * by string_append() years ago. @@ -203,8 +207,6 @@ extern jb_err string_join (char **target_string, char *text_to_append); extern char *string_toupper(const char *string); extern char *chomp(char *string); -extern int simplematch(char *pattern, char *text); - extern char *bindup(const char *string, size_t len); extern char *make_path(const char * dir, const char * file); diff --git a/urlmatch.c b/urlmatch.c index 8795f80e..37d0f3f3 100644 --- a/urlmatch.c +++ b/urlmatch.c @@ -1,4 +1,4 @@ -const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.35 2008/04/14 18:11:21 fabiankeil Exp $"; +const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.36 2008/04/14 18:19:48 fabiankeil Exp $"; /********************************************************************* * * File : $Source: /cvsroot/ijbswa/current/urlmatch.c,v $ @@ -33,6 +33,9 @@ const char urlmatch_rcs[] = "$Id: urlmatch.c,v 1.35 2008/04/14 18:11:21 fabianke * * Revisions : * $Log: urlmatch.c,v $ + * Revision 1.36 2008/04/14 18:19:48 fabiankeil + * Remove now-pointless cast in create_url_spec(). + * * Revision 1.35 2008/04/14 18:11:21 fabiankeil * The compiler might not notice it, but the buffer passed to * create_url_spec() is modified later on and thus shouldn't @@ -943,6 +946,144 @@ static jb_err compile_host_pattern(struct url_spec *url, const char *host_patter } +/********************************************************************* + * + * Function : simplematch + * + * Description : String matching, with a (greedy) '*' wildcard that + * stands for zero or more arbitrary characters and + * character classes in [], which take both enumerations + * and ranges. + * + * Parameters : + * 1 : pattern = pattern for matching + * 2 : text = text to be matched + * + * Returns : 0 if match, else nonzero + * + *********************************************************************/ +static int simplematch(char *pattern, char *text) +{ + unsigned char *pat = (unsigned char *) pattern; + unsigned char *txt = (unsigned char *) text; + unsigned char *fallback = pat; + int wildcard = 0; + + unsigned char lastchar = 'a'; + unsigned i; + unsigned char charmap[32]; + + while (*txt) + { + + /* EOF pattern but !EOF text? */ + if (*pat == '\0') + { + if (wildcard) + { + pat = fallback; + } + else + { + return 1; + } + } + + /* '*' in the pattern? */ + if (*pat == '*') + { + + /* The pattern ends afterwards? Speed up the return. */ + if (*++pat == '\0') + { + return 0; + } + + /* Else, set wildcard mode and remember position after '*' */ + wildcard = 1; + fallback = pat; + } + + /* Character range specification? */ + if (*pat == '[') + { + memset(charmap, '\0', sizeof(charmap)); + + while (*++pat != ']') + { + if (!*pat) + { + return 1; + } + else if (*pat == '-') + { + if ((*++pat == ']') || *pat == '\0') + { + return(1); + } + for (i = lastchar; i <= *pat; i++) + { + charmap[i / 8] |= (unsigned char)(1 << (i % 8)); + } + } + else + { + charmap[*pat / 8] |= (unsigned char)(1 << (*pat % 8)); + lastchar = *pat; + } + } + } /* -END- if Character range specification */ + + + /* + * Char match, or char range match? + */ + if ( (*pat == *txt) + || (*pat == '?') + || ((*pat == ']') && (charmap[*txt / 8] & (1 << (*txt % 8)))) ) + { + /* + * Sucess: Go ahead + */ + pat++; + } + else if (!wildcard) + { + /* + * No match && no wildcard: No luck + */ + return 1; + } + else if (pat != fallback) + { + /* + * Increment text pointer if in char range matching + */ + if (*pat == ']') + { + txt++; + } + /* + * Wildcard mode && nonmatch beyond fallback: Rewind pattern + */ + pat = fallback; + /* + * Restart matching from current text pointer + */ + continue; + } + txt++; + } + + /* Cut off extra '*'s */ + if(*pat == '*') pat++; + + /* If this is the pattern's end, fine! */ + return(*pat); + +} + + /********************************************************************* * * Function : simple_domaincmp -- 2.39.2