#
# Revisions :
# $Log: re_filterfile,v $
+# Revision 1.22 2002/03/12 13:42:50 oes
+# Fixing & Optimizing REs
+#
+# Revision 1.21 2002/03/12 11:59:20 oes
+# Beefed up Buzzword Bingo
+#
+# Revision 1.20 2002/03/12 01:42:50 oes
+# Introduced modular filters
+#
# Revision 1.19 2002/03/10 19:49:24 oes
# Added expression to kill referer tracking in JavaScripts
#
#
# Syntax:
#
-# Filters start with a line "FILTER: name". They are then referrable
+#################################################################################
+#
+# Filters start with a line "FILTER: name description". They are then referrable
# from the actionsfile with +filter{name}
#
-# Inside the filters, write one Perl-Style substitution per line.
+# Inside the filters, write one Perl-Style substitution (job) per line.
+# Jobs that precede the first FILTER: line are ignored.
#
# For Details see the pcrs manpage contained in this distribution.
# (and the perlre, perlop and pcre manpages)
# html-annoyances: Get rid of particularly annoying HTML abuse
#
#################################################################################
-FILTER: html-annoyances
+FILTER: html-annoyances Get rid of particularly annoying HTML abuse
-# New browser windows should be resizeable and have a location and status bar
+# New browser windows (if allowed -- see no-popups filter below) should be
+# resizeable and have a location and status bar
#
-s/resizable="?(no|0)"?/resizable=1/ig s/noresize/yesresize/ig
-s/location="?(no|0)"?/location=1/ig s/status="?(no|0)"?/status=1/ig
-s/scrolling="?(no|0|Auto)"?/scrolling=1/ig
-s/menubar="?(no|0)"?/menubar=1/ig
+s/(<a\s+href[^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1resizable=1$3/igU
+s/(<a\s+href[^>]+)location=['"]?(no|0)['"]?(.*>)/$1location=1$3/igU
+s/(<a\s+href[^>]+)status=['"]?(no|0)['"]?(.*>)/$1status=1$3/igU
+s/(<a\s+href[^>]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling=no$3/igU
+s/(<a\s+href[^>]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar=1$3/igU
# The <BLINK> tag was a crime!
#
# Is this evil?
#
-#s/framespacing="?(no|0)"?//ig
#s/margin(height|width)=[0-9]*//gi
+#s/noresize/yesresize/igU
#################################################################################
# js-annoyances: Get rid of particularly annoying JavaScript abuse
#
#################################################################################
-FILTER: js-annoyances
-
-# JS cookies, like found on privacy.net:
-#
-s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
+FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
# Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm
#
s/(<body .*)onunload(.*>)/$1never$2/iU
-##################################################################################
+#################################################################################
#
-# no-poups: Kill all popups in JS and HTML
+# content-cookies: Kill cookies that come in the HTML or JS content
#
#################################################################################
-FILTER: no-poups
+FILTER: content-cookies Kill cookies that come in the HTML or JS content
+
+# JS cookies, like found on privacy.net:
+#
+s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
-s/window\.open\(/1;''\.concat\(/ig # JavaScript
-s/target=['"]?_blank['"]?/target_who/g # HTML
+# HTML cookies:
+#
+s|<meta\s+http-equiv=['"]?set-cookie['"]?\s+content=[^>].*>|<!--no cookies here -->|iUT
-#################################################################################
+##################################################################################
#
-# frameset-borders: Give frames a border
+# no-popups: Kill all popups in JS and HTML
#
#################################################################################
-FILTER: frameset-borders
+FILTER: no-popups Kill all popups in JS and HTML
-s/(<frameset[^>]+?)border=['"]?(no|0)['"]?/$1/ig
-s/(<frameset[^>]+?)frameborder=['"]?(no|0)['"]?/$1/ig
+s/window\.open\(/1;''\.concat\(/ig # JavaScript
+s/target=['"]?_blank['"]?/target_crunched/ig # HTML
+s/target=['"]?_new['"]?/target_crunched/ig # HTML
+#################################################################################
+#
+# frameset-borders: Give frames a border and make them resizable
+#
+#################################################################################
+FILTER: frameset-borders Give frames a border and make them resizable
+
+s/(<frameset [^>]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU
+s/(<frameset [^>]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU
+s/(<frame [^>]+)border=['"]?(no|0)['"]?(.*>)/$1$3/igU
+s/(<frame [^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1$3/igU
#################################################################################
#
# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
#
#################################################################################
-FILTER: webbugs
+FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
#################################################################################
#
-# no-refresh: Automatic refresh sucks on auto-dialup lines
+# no-refresh: Kill automatic refresh tags (for dial-on-demand setups)
#
#################################################################################
-FILTER: no-refresh
+FILTER: no-refresh Kill automatic refresh tags (for dial-on-demand setups)
-# FIXME: second line like first line for content value
-#
-s/<meta[^>]*http-equiv[^>]*refresh.*([0-9]+[0-9]|"[2-9]);URL=([^>]*?)"?>/<link rev="x-refresh" href=$2>/i
-s/<meta[^>]*http-equiv="?page-enter"?[^>]*content=[^>]*>/<!--no page enter for me-->/i
+s/<meta\s+http-equiv=['"]?refresh['"]?\s+content=['"]?[0-9]*;\s+url=([^>]*)['"]?>/<link rev="x-refresh" href=$1>/iU
+s/<meta\s+http-equiv=['"]?page-enter['"]?\s+content=[^>].*>/<!--no page enter for me-->/iU
#################################################################################
# fun: Text replacements for subversive browsing fun!
#
#################################################################################
-FILTER: fun
+FILTER: fun Text replacements for subversive browsing fun!
s/microsoft(?!.com)/MicroSuck/ig
-# Buzzword Bingo:
+# Buzzword Bingo (example for extended syntax)
#
-s/industry-leading|cutting-edge|award-winning/<font color=red><b>BINGO!</b></font>/ig
+s* industry[ -]leading \
+| cutting[ -]edge \
+| award[ -]winning # Comments are OK, too! \
+| high[ -]performance \
+| solutions[ -]based \
+| unmatched \
+| unparalleled \
+| unrivalled \
+*<font color=red><b>BINGO!</b></font> \
+*igx
#################################################################################
# nimda: Remove Nimda (virus) code
#
#################################################################################
-FILTER: nimda
+FILTER: nimda Remove Nimda (virus) code
s%<script language="JavaScript">(window\.open|1;''\.concat)\("readme\.eml", null, "resizable=no,top=6000,left=6000"\)</script>%<br><hr><font size=7><b>Internet J</b></font><b><font size=6>UNK</font><font size=5 color="red"><i>BUSTER</i></font></b><font size=7> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
# Use http://ijbswa.sourceforge.net/config/send-banner?type=auto to auto-select.
#
#################################################################################
-FILTER: banners-by-size
+FILTER: banners-by-size Kill banners by size
s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
# (Note #2: Is 'sex' a rude word?!)
#
#################################################################################
-FILTER: crude-parental
+FILTER: crude-parental Crude parental filtering (demo only)
s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<html><head><title>Blocked</title></head><body><h3>Blocked due to possible adult content. Please see <a href="http://dmoz.org/Kids_and_Teens/">this site</a>.</h3></body></html>%is
s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
projects / privoxy.git / blobdiff