X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=72ec7a2e8d67de83c0bb2c7cc4a6273eeb5f802b;hp=b489818600a3af56b8a0d2a5f6557696cd15abe0;hb=58842b486231d1910f7d11132f55e805ec333ed4;hpb=68386cd533fb3d75a011957aa66fee96eb782c3f

diff --git a/default.filter b/default.filter
index b4898186..72ec7a2e 100644
--- a/default.filter
+++ b/default.filter
@@ -2,11 +2,11 @@
 # 
 #  File        :  $Source: /cvsroot/ijbswa/current/default.filter,v $
 # 
-#  $Id: default.filter,v 1.13 2002/09/11 16:04:20 oes Exp $
+#  $Id: default.filter,v 1.81 2011/06/23 13:58:53 fabiankeil Exp $
 #
 #  Purpose     :  Rules to process the content of web pages
 # 
-#  Copyright   :  Written by and Copyright
+#  Copyright   :  Written by and Copyright (C) 2001-2010 the
 #                 Privoxy team. http://www.privoxy.org/
 #
 # We value your feedback. However, to provide you with the best support,
@@ -37,8 +37,12 @@
 #
 # Syntax:
 #
-# Filters start with a line "FILTER: name description". They are then referrable
-# from the actionsfile with +filter{name}
+# Generally filters start with a line like "FILTER: name description".
+# They are then referrable from the actionsfile with +filter{name}
+#
+# FILTER marks a filter as content filter, other filter
+# types are CLIENT-HEADER-FILTER, CLIENT-HEADER-TAGGER,
+# SERVER-HEADER-FILTER and SERVER-HEADER-TAGGER.
 #
 # Inside the filters, write one Perl-Style substitution (job) per line.
 # Jobs that precede the first FILTER: line are ignored.
@@ -46,48 +50,62 @@
 # For Details see the pcrs manpage contained in this distribution.
 # (and the perlre, perlop and pcre manpages)
 #
-# Note that you are free to choose the delimter as you see fit.
+# Note that you are free to choose the delimiter as you see fit.
 #
-# Note2: In addidion to the Perl options gimsx, the following nonstandard
+# Note2: In addition to the Perl options gimsx, the following nonstandard
 # options are supported:
 # 
 # 'U' turns the default to ungreedy matching.  Add ? to quantifiers to
 #     switch back to greedy.
+#
 # 'T' (trivial) prevents parsing for backreferences in the substitute.
 #     Use if you want to include text like '$&' in your substitute without
 #     quoting.
+#
+# 'D' (Dynamic) allows the use of variables. Supported variables are:
+#     $host, $origin (the IP address the request came from), $path and $url.
+#
+#     Note that '$' is a bad choice as delimiter for dynamic filters as you
+#     might end up with unintended variables if you use a variable name
+#     directly after the delimiter. Variables will be resolved without
+#     escaping anything, therefore you also have to be careful not to chose
+#     delimiters that appear in the replacement text. For example '<' should
+#     be save, while '?' will sooner or later cause conflicts with $url.
 # 
 #################################################################################
 
 
 #################################################################################
 #
-# js-annoyances: Get rid of particularly annoying JavaScript abuse
+# js-annoyances: Get rid of particularly annoying JavaScript abuse.
 #
 #################################################################################
-FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
+FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse.
 
 # Note: Most of these jobs would be safer if restricted to a
 # <script> context as in:
 #
 # s/(<script.*)nasty-item(?=.*<\/script>)/$1replacement/sigU
 #
-# but that would make them match only the first occurance of
+# but that would make them match only the first occurrence of
 # nasty-item in each <script>. We need nestable jobs!
 
 # Get rid of Javascript referrer tracking. 
 # Test page: http://www.javascript-page.com/referrer.html
 #
-s|document\.referrer|"Not Your Business!"|gisU
+s|(?:\w+\.)+referrer|"Not Your Business!"|gisU
 
 # The status bar is for displaying link targets, not pointless blahblah
 #
-s/([\n =;{}]|window\.)(default)?status\s*=/$1dUmMy=/ig
+s@([\W]\s*)((?:this|window)\.(?:default)?status)\s*=\s*((['"]).*?\4)@$1$2 =\
+ (typeof(this.href) != 'undefined')?($3 + ' URL: ' + this.href):($2)@ig
+
+s/(?:(?:this|window)\.(?:default)?status)\s*=\s*\w*\s*;//ig
 
 # Kill OnUnload popups. Yummy.
 # Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
 #
-s/(<body\s+[^>]*)onunload(.*>)/$1never$2/siU
+s/(<body\s+[^>]*)onunload/$1never/siU
 s|(<script.*)window\.onunload(?=.*</script>)|$1never|sigU
 
 # If we allow window.open, we want normal window features: 
@@ -102,17 +120,30 @@ s/(open\s*\([^\)]+toolbar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
 s/(open\s*\([^\)]+directories=)(["']?)(?:no|0)\2/$1$2yes$2/sigU 
 s/(open\s*\([^\)]+fullscreen=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
 s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
-s/(open\s*\([^\)]+zlock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
+s/(open\s*\([^\)]+z-?lock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
 s/(open\s*\([^\)]+hotkeys=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
-s/(open\s*\([^\)]+titlebar=)(["']?)(?:yes|1)\2/$1$2yes$2/sigU
+s/(open\s*\([^\)]+titlebar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
+s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
 
 
 #################################################################################
 #
-# html-annoyances: Get rid of particularly annoying HTML abuse
+# js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites).
 #
 #################################################################################
-FILTER: html-annoyances Get rid of particularly annoying HTML abuse
+FILTER: js-events Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites).
+
+s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig
+# Not events, but abused on the same type of sites:
+s/(alert|confirm)\s*\(/concat(/ig
+s/settimeout\(/concat(/ig
+
+#################################################################################
+#
+# html-annoyances: Get rid of particularly annoying HTML abuse.
+#
+#################################################################################
+FILTER: html-annoyances Get rid of particularly annoying HTML abuse.
 
 # New browser windows (if allowed -- see no-popups filter below) should be
 # resizeable and have a location and status bar
@@ -123,21 +154,21 @@ s/(<a\s+href[^>]+status=)(['"]?)(?:no|0)\2/$1$2yes1$2/igU
 s/(<a\s+href[^>]+scrolling=)(['"]?)(?:no|0)\2/$1$2auto$2/igU
 s/(<a\s+href[^>]+menubar=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
 
-# The <BLINK> tag was a crime!
+# The <BLINK> and <MARQUEE> tags were crimes!
 #
-s*<blink>|</blink>**ig
+s-</?(blink|marquee).*>--sigU
 
 
 #################################################################################
 #
-# content-cookies: Kill cookies that come in the HTML or JS content
+# content-cookies: Kill cookies that come in the HTML or JS content.
 #
 #################################################################################
-FILTER: content-cookies Kill cookies that come in the HTML or JS content
+FILTER: content-cookies Kill cookies that come in the HTML or JS content.
 
-# JS cookies, like found on privacy.net:
+# JS cookies, except those used by antiadbuster.com to detect us:
 #
-s|document\.cookie(?=[ \t\r\n]*=)|ZappedCookie|ig
+s|(\w+\.)+cookie(?=[ \t\r\n]*=)(?!='aab)|ZappedCookie|ig
 
 # HTML cookies:
 #
@@ -146,74 +177,64 @@ s|<meta\s+http-equiv=['"]?set-cookie.*>|<!-- ZappedCookie -->|igU
 
 #################################################################################
 #
-# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
+# refresh-tags: Kill automatic refresh tags if refresh time is larger than 9 seconds.
 #
 #################################################################################
-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)[^>]*?>//siUg
-
+FILTER: refresh-tags Kill automatic refresh tags if refresh time is larger than 9 seconds.
 
-##################################################################################
-#
-# popups: Kill all popups in JS and HTML
+# Note: Only deactivates refreshes with more than 9 seconds delay to
+#       preserve monster-stupid but common redirections via meta tags.
 #
-#################################################################################
-FILTER: popups Kill all popups in JS and HTML
-
-s/([\n =;{}]|window\.)open\s*\\?\(/$1concat(/ig      # JavaScript
-s/ target\s*=\s*(['"]?)(_blank|_new)\1?/ notarget/ig # HTML
+s@<meta\s+http-equiv\s*=\s*(['"]?)refresh\1\s+content\s*=\s*(['"]?)\d{2,}\s*(;(?:\s*url\s*=\s*)?([^>\2]*))?\2@<link rev="x-refresh" href="$4"@ig
 
 
 #################################################################################
 #
-# frameset-borders: Give frames a border, make them resizable and scrollable
+# unsolicited-popups: Disable unsolicited pop-up windows.
 #
 #################################################################################
-FILTER: frameset-borders Give frames a border and make them resizable
+FILTER: unsolicited-popups Disable only unsolicited pop-up windows.
 
-s/(<frameset\s+[^>]*)framespacing=(['"]?)(no|0)\2/$1/igU
-s/(<frameset\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
-s/(<frameset\s+[^>]*)border=(['"]?)(no|0)\2/$1/igU
-s/(<frame\s+[^>]*)noresize/$1/igU
-s/(<frame\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU 
-s/(<frame\s+[^>]*)scrolling=(['"]?)(no|0)\2/$1/igU
+s+([^'"]\s*<head.*>)(?=\s*[^'"])+$1<script>function PrivoxyWindowOpen(){return(null);}</script>+isU
+s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig
+s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c){return(window.open(a, b, c));}</script>+iU     
 
 
-#################################################################################
+##################################################################################
 #
-# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups)
+# all-popups: Kill all popups in JavaScript and HTML.
 #
 #################################################################################
-FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups)
+FILTER: all-popups Kill all popups in JavaScript and HTML.
 
-# Note: Only deactivates refreshes with more than 9 seconds delay to
-#       preserve monster-stupid but common redirections via meta tags.
-#
-s/<meta\s+http-equiv\s*=\s*(['"]?)refresh\1\s+content\s*=\s*(['"]?)\d{2,}\s*(;\s*url\s*=\s*([^>\2]*))?\2\s*>/<link rev="x-refresh" href="$4">/iU
+s@((\W\s*)(?:map)?(window|this|parent)\.?)open\s*\\?\(@$1concat(@ig  # JavaScript
+#s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig        # HTML
+s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ /ig        # (X)HTML
 
-
-#################################################################################
+##################################################################################
 #
-# img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective
+# img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective.
 #
 #################################################################################
-FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective
+FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective.
 
 # In the first step src is moved to the start, then width is moved to the second
-# place to guarantee an order of src, width, height.
+# place to guarantee an order of src, width, height. Also does some white-space
+# normalization.
+#
 # This makes banners-by-size more effective and allows both banners-by-size
-# and banners-by-link to preserve the original image URL in the alt attribute.
+# and banners-by-link to preserve the original image URL in the title attribute.
 
-s|<img\s+?([^>]*)src\s*=\s*(['"])([^>\\\2]+)\2|<img src=$2$3$2$1|siUg
-s|<img\s+?([^>]*)src\s*=\s*([^'">\\\s]+)|<img src=$2$1|sig
+s|<img\s+?([^>]*)\ssrc\s*=\s*(['"])([^>\\\2]+)\2|<img src=$2$3$2 $1|siUg
+s|<img\s+?([^>]*)\ssrc\s*=\s*([^'">\\\s]+)|<img src=$2 $1|sig
+s|(<img[^>]+height)\s*=\s*|$1=|sig
 
-s|<img (src=(?:(['"])[^>\\\\2]+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+?)|<img $1 width=$4$5$4$3|siUg
+s|<img (src=(?:(['"])[^>\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*((["']?)\d+?\5)(?=[\s>])|<img $1 width=$4$3|siUg
 
 
 #################################################################################
 #
-# banners-by-size: Kill banners by size
+# banners-by-size: Kill banners by size.
 #
 #################################################################################
 #
@@ -226,53 +247,171 @@ s|<img (src=(?:(['"])[^>\\\\2]+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+?
 # Note2: Use img-reorder before this filter to ensure maximum matching success
 #
 #################################################################################
-FILTER: banners-by-size Kill banners by size
+FILTER: banners-by-size Kill banners by size.
 
 # 88*31
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 120*60, 120*90, 120*240, 120*600
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 125*125
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 160*600
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 180*150
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 234*60, 468*60 (Most Banners!)
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 240*400
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 250*250, 300*250
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 # 336*280
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*?(?=/?>)@\
+  <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 
 # Note: 200*50 was also proposed, but it probably causes too much collateral damage:
 #
-#s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed-$2-by-size$1 $3 $5>@sig
+#s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*?(?=/?>)@\
+#   <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 
 
 #################################################################################
 #
-# banners-by-link: Kill banners by their links to known clicktrackers
+# banners-by-link: Kill banners by their links to known clicktrackers (Experimental).
 #
 #################################################################################
-FILTER: banners-by-link Kill banners by their links to known clicktrackers
+FILTER: banners-by-link Kill banners by their links to known clicktrackers.
 
 # Common case with width and height attributes:
 #
 s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:\
   adclick                             # See www.dn.se \
+| advert                              # see dict.leo.org \
 | atwola\.com/(?:link|redir)          # see www.cnn.com \
-| /jump/                              # redirs for doublecklick.net ads \
-| tracker | counter                   # common \
+| doubleclick\.net/jump/              # redirs for doublecklick.net ads \
+| counter                             # common \
+| (?<!&type=)tracker                  # (&type=tracker is used in sf's project statistics) \
 | adlog\.pl                           # see sf.net \
-)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*>\
-@<img $5 $7 src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed $4 by link to $2$1>@sigx
+)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*?(?=/?>)\
+@<img $5 $7 src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@sigx
 
 # Rare case w/o explicit dimensions:
 #
-s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 alt=$1Killed $4 by link to $2$1>@sig
+s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:ad(?:click|vert)|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|(?<!&type=)tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*?(?=/?>)@<img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@sig
+
+
+################################################################################
+#
+# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking).
+#
+#################################################################################
+FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking).
+
+s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@@siUg
+
+
+#################################################################################
+#
+# tiny-textforms: Extend those tiny textareas up to 40x80 and kill the hard wrap.
+#
+#################################################################################
+FILTER: tiny-textforms Extend those tiny textareas up to 40x80 and kill the hard wrap.
+
+s/(<textarea[^>]*?)(?:\s*(?:rows|cols)=(['"]?)\d+\2)+/$1 rows=$2\40$2 cols=$2\80$2/ig 
+s/(<textarea[^>]*?)wrap=(['"]?)hard\2/$1/ig
+
+
+#################################################################################
+#
+# jumping-windows: Prevent windows from resizing and moving themselves.
+#
+#################################################################################
+FILTER: jumping-windows Prevent windows from resizing and moving themselves.
+
+s/(?<=[\W])(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig
+
+#################################################################################
+#
+# frameset-borders: Give frames a border, make them resizable and scrollable.
+#
+#################################################################################
+FILTER: frameset-borders Give frames a border and make them resizable.
+
+s/(<frameset\s+[^>]*)framespacing=(['"]?)(no|0)\2/$1/igU
+s/(<frameset\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
+s/(<frameset\s+[^>]*)border=(['"]?)(no|0)\2/$1/igU
+s/(<frame\s+[^>]*)noresize/$1/igU
+s/(<frame\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU 
+s/(<frame\s+[^>]*)scrolling=(['"]?)(no|0)\2/$1/igU
+
+
+
+#################################################################################
+#
+# demoronizer: Correct Microsoft's abuse of standardized character sets, which 
+#              leave the browser to (mis)-interpret unknown characters, with 
+#              sometimes bizarre results on non-MS platforms.
+#
+# credit: ripped from the demoroniser.pl script by: 
+#         John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser
+#
+#################################################################################
+FILTER: demoronizer Fix MS's non-standard use of standard charsets.
+
+s/(&\#[0-2]\d\d)\s/$1; /g
+# per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess.
+# Must come before x94 below.
+s/\xE2\x80\x94/ -- /g
+s/\x82/,/g
+#s-\x83-<em>f</em>-g
+s/\x84/,,/g
+s/\x85/.../g
+#s/\x88/^/g
+#s-\x89- °/°°-g
+s/\x8B/</g
+s/\x8C/Oe/g
+s/\x91/`/g
+s/\x92/'/g
+s/(\x93|\x94)/"/g
+# Bullet type character.
+s/\x95/&middot;/g
+s/\x96/-/g
+s/\x97/--/g
+#s-\x98-<sup>~</sup>-g
+#s-\x99-<sup>TM</sup>-g
+# per Robert Lynch.
+s/\x9B/>/g                  # 155
+
+
+#################################################################################
+#
+# shockwave-flash: Kill embedded Shockwave Flash objects.
+#                  Note: Better just block "/.*\.swf$"!
+#
+#################################################################################
+FILTER: shockwave-flash Kill embedded Shockwave Flash objects.
+
+s|<object [^>]*macromedia.*</object>|<!-- Squished Shockwave Object -->|sigU
+s|<embed [^>]*(application/x-shockwave-flash\|\.swf).*>(.*</embed>)?|<!-- Squished Shockwave Flash Embed -->|sigU
+
+
+#################################################################################
+#
+# quicktime-kioskmode: Make Quicktime movies saveable.
+#
+#################################################################################
+FILTER: quicktime-kioskmode Make Quicktime movies saveable.
+
+s/(<embed\s+[^>]*)kioskmode\s*=\s*(["']?)true\2/$1/ig 
+
 
 #################################################################################
 #
@@ -281,11 +420,13 @@ s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|double
 #################################################################################
 FILTER: fun Text replacements for subversive browsing fun!
 
-s/microsoft(?!.com)/MicroSuck/ig
+# SCNR
+#
+s/microsoft(?!\.[^\s])/MicroSuck/ig
 
 # Buzzword Bingo (example for extended regex syntax)
 #
-s* industry[ -]leading \
+s* (?:industry|world)[ -]leading \
 |  cutting[ -]edge \
 |  customer[ -]focused \
 |  market[ -]driven \
@@ -295,226 +436,437 @@ s* industry[ -]leading \
 |  unmatched \
 |  unparalleled \
 |  unrivalled \
-*<font color="red"><b>BINGO!</b></font> \
+*$0<sup><font color="red"><b>Bingo!</b></font></sup> \
 *igx
 
+# For Germans only
+#
+s/(M|m)edien(?![^<]*>)/$1&auml;dchen/Ug
 
 #################################################################################
 #
-# nimda: Remove Nimda (virus) code
+# crude-parental: Crude parental filtering. Use with a suitable blocklist.
+#                 Pages are "blocked" based on keyword matching.
 #
 #################################################################################
-FILTER: nimda Remove Nimda (virus) code
+FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliably.
 
-s%<script language="JavaScript">(window\.open|1;''\.concat)\("readme\.eml", null, "resizable=no,top=6000,left=6000"\)</script>%<br><font size="7"> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
+# (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
+# (Note #2: Is 'sex' a rude word?!)
+
+s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<html><head><title>Blocked</title></head><body>\
+<h3>Blocked by Privoxy's crude-parental filter due to possible adult content.</h3></body></html>%is
+
+s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
+
+# Remove by description
+s/^.*\
+(?:(suck|lick|tongue|rub|fuck|fingering|finger|chicks?)\s*)?\
+(?:(her|your|my|hard|with|big|wet|tight|pink|hot|moist|young|teen)\s*)+\
+(dicks?|penis|cocks?|balls?|tits?|pussy|cunt|clit|ass|mouth).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by link text
+s/^.*\
+(download|broadband|view|watch|free|get|extreem)?\s*\
+(sex|xxx|porn|cumshot|fuck(ing|s)?|anal|ass|asian|adult|Amateur|org(y|ies)|close ups?|hand?job|nail(ed)?)+\s*\
+(movies?|pics?|videos?|dvds?|dvd's|links?).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by age disclaimer
+s/^.*\
+(models?|chicks?|girls?|women|persons)\s*\
+(who|are|were)+ (over|at least) (16|18|21) years (old|of age).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by regulations
+s/^.*(Section 2257|18 U.?S.?C.? 2257).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is 
 
 
 #################################################################################
 #
-# shockwave-flash: Kill embedded Shockwave Flash objects
+# IE-Exploits: Disable some known Internet Explorer bug exploits.
 #
 #################################################################################
-FILTER: shockwave-flash Kill embedded Shockwave Flash objects
+FILTER: ie-exploits Disable some known Internet Explorer bug exploits.
+
+# Note: This is basically a demo and waits for someone more interested in IE
+# security (sic!) to take over.
+
+# Cross-site-scripting:
+#
+s%f\("javascript:location.replace\('mk:@MSITStore:C:'\)"\);%alert\("This page looks like it tries to use a vulnerability described here:\n http://online.securityfocus.com/archive/1/298748/2002-11-02/2002-11-08/2"\);%siU
 
-s|<embed [^>]*application/x-shockwave-flash.*</embed>|<!-- Squished Shockwave Flash Embed -->|sigU
+# Address bar spoofing (http://www.secunia.com/advisories/10395/):
+#
+s/(<a[^>]*href[^>]*)(?:\x01|\x02|\x03|%0[012])@/$1MALICIOUS-LINK@/ig
+
+# Nimda:
+#
+s%<script language="JavaScript">(window\.open|1;''\.concat)\("readme\.eml", null, "resizable=no,top=6000,left=6000"\)</script>%<br><font size="7"> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
 
 
 #################################################################################
 #
-# quicktime-kioskmode: Make Quicktime movies saveable
+#
+# site-specifics: Cure for site-specific problems. Don't apply generally!
+#
+#   Note: The fixes contained here are so specific to the problems of the
+#         particular web sites they are designed for that they would be a
+#         waste of CPU cycles (or even destructive!) on 99.9% of the web
+#         sites where they don't apply.
 #
 #################################################################################
-FILTER: quicktime-kioskmode Make Quicktime movies saveable
+FILTER: site-specifics Cure for site-specific problems. Don't apply generally!
 
-s/(<embed\s+[^>]*)kioskmode\s*=\s*(["']?)true\2/$1/ig 
+# www.spiegel.de excludes X11 users from viewing Flash5 objects - shame.
+# Apply to: www.spiegel.de/static/js/flash-plugin.js 
+#
+s/indexOf\("x11"\)/indexOf("x13")/
 
+# www.quelle-bausparkasse.de uses a very stupid redirect mechanism that
+# relies on a webbug being present. Can we tolerate that? No!
+# Apply to: www.quelle-bausparkasse.de/$
+#
+s/mylogfunc()//g
 
-#################################################################################
+# groups.yahoo.com has splash pages that one needs to click through in
+# order to access the actual messages. Let the browser do that. Thanks
+# to Paul Jobson for this one:
+#
+s|<a href="(.+?)">(?:Continue to message\|Weiter zu Nachricht)</a>|<meta http-equiv="refresh" content="0; URL=$1">|ig
+
+# monster.com has two very similar gimmicks:
 #
-# js-events: Kill all JS event bindings (Radically destructive! Only for extra nasty sites)
+s|<input type="hidden" name="REDIRECT" value="(.+?)">|<meta http-equiv="refresh" content="0; URL=$1">|i
+ 
+s|<IMG SRC="http://media.monster.com/mm/usen/my/no_thanks_211x40.gif".+?>|<meta http-equiv="refresh" content="0; URL=http://my.monster.com/resume.asp">|i 
+
+# nytimes.com triggers popups through the onload handler of dummy images
+# to fool popup-blockers.  
+#
+s|(<img [^>]*)onload|$1never|sig
+
+# Pre-check all the "Discard" buttons in GNU Mailman's web interface.
+# (This saves a lot of mouse aiming practice when flushing spamtraps)
 #
+s|(<INPUT name="\d{2,4}" type="RADIO" value="0") CHECKED |$1|g
+s|<INPUT name="\d{2,4}" type="RADIO" value="3" |$0 checked|g
+
 #################################################################################
-FILTER: js-events Kill all JS event bindings (Radically destructive! Only for extra nasty sites)
+#
+# no-ping: Removes non-standard ping attributes in <a> and <area> tags.
+#          
+#################################################################################
+FILTER: no-ping Removes non-standard ping attributes in <a> and <area> tags.
+s@(<a(?:rea)?[^>]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\
+<strong style="color:white; background-color:red;" title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
 
-s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig
-# Not events, but abused on the same type of sites:
-s/(alert|confirm)\s*\(/concat(/ig
+#################################################################################
+#
+# google: CSS-based block for Google text ads. Also removes
+#         a width limitation and the toolbar advertisement.
+#
+#################################################################################
+FILTER: google CSS-based block for Google text ads. Also removes a width limitation and the toolbar advertisement.
 
+s@</head>@<style type="text/css">\n\
+ /* Style sheet inserted by Privoxy's google filter. */\n\
+ \#fbc, \#fbl, \#ra, .rhh {visibility: hidden !important;}\n\
+ \#tpa1,\#tpa2,\#tpa3,\#tpa4,\#tpa5,\#tpa5, \#spl, .ch, \#ads,\
+ \#toolbar, \#google_ads_frame, \#mbEnd {display: none !important;}\n\
+ .main_body, .j, \#res, .med, .hd, .g, .s\n\
+ {width: 99%; max-width: 100%; margin-left: 0; margin-right: 0;}\n\
+ </style>\n$0@
+s@<div style=\"padding-top:11px;min-width:500px\">@<div id="main_body">@
+s@(<table cellspacing=0 cellpadding=0 width=25% align=right bgcolor=\#ffffff border=0\
+|</font></td></tr></tbody></table><table align=\"right\" bgcolor=\"\#ffffff\"\
+|<table cellspacing=0 cellpadding=0 align=right bgcolor=\#ffffff border=0\
+|<table style=\"clear:both\" align=right width=25% cellspacing=\"0\" cellpadding=\"0\"\
+ border=\"0\" bgcolor=\"\#ffffff\")@$0 id="ads"@
+s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
 
 #################################################################################
 #
-# crude-parental: Crude parental filtering?  (Use along with a suitable blocklist).
-#                 Shows how to deny access to whole page based on a keyword.
+# yahoo: CSS-based block for Yahoo text ads. Also removes a width limitation.
 #
 #################################################################################
-FILTER: crude-parental Crude parental filtering (demo only)
+FILTER: yahoo CSS-based block for Yahoo text ads. Also removes a width limitation.
 
-# (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
-# (Note #2: Is 'sex' a rude word?!)
+s@</head>@\n<style type="text/css">\n\
+ /* Style sheet inserted by Privoxy's yahoo filter. */\n\
+ \#symadbn, \#ymadbn, .yschbox, .yschhd, .bbox, \#yschsec, \#sec,\
+ \#yschanswr, .yschftad, .yschspn, .yschspns, \#ygrp-sponsored-links,\
+ \#nwad, \#MWA2, \#MSCM, \#yregad, \#sponsored-links,\
+ \#ks-ypn-ads, .ad, \#east, \#ygrp-vital, .ads {display: none !important;}\n\
+ \#yschpri, \#yschweb, \#pri, \#web, \#main, .yschttl, .abstr, .res \n\
+ {width: 99% !important; max-width: 100% !important;}\n\
+ .yschttl, .res, .res.indent, \#web {padding: 0px; margin: 0px !important;}\n\
+ \#web {padding-left: 0.5em}\n\
+ \#yschqcon, \#yschtg {width: auto !important; /* No useless horizontal scrollbar please */}\n\
+ \#composebox \#compose_editorArea {width: 70% !important; /* reasonably sized reply textarea please */\n\
+ </style>\n$0\n@
 
-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
+s@(<textarea\s+id="composeArea"[^>]*)width:545px;@$1width:70%;@isU
 
+#################################################################################
+#
+# msn: CSS-based block for MSN text ads. Also removes tracking URLs
+#      and a width limitation.
+#
+#################################################################################
+FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a width limitation.
+
+s@</head>@<style type="text/css">\n\
+ /* Style sheet inserted by Privoxy's msn filter. */\n\
+ .msn_ads, \#at, \#ar, .mktmsg {display: none !important;}\n\
+ \#results, .flank, .results_area_flank, .results_area_stroke,\n\
+ \#results_area, \#content, .sb_tlst, .sa_cc, .sb_ph, \#sw_main,\n\
+.content, \#sw_foot, \#bf, \#sw_content, \#sidebar, \#pag\n\
+ {width: 99% !important; min-width: 99% !important;\n\
+ max-width: 100% !important; /* width:100% sometimes causes horizontal scrollbars */}\n\
+ /* Remove "suggestions". They are next to worthless but partly overlap with the search results */\n\
+ .suggestion, \#nys_right, \#nys {clear: both; display:none;}\n\
+ \#s_notf_div,\n \
+ /* Overlay ads to enable Facebook 'likes' in search results. */\n\
+ .sn_container {display:none !important;}\n\
+ \#content {padding-right: 0;}\n\
+ </style>\n$0@
+# Are these ids still in use?
+s@(<div[^>]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig
+s@(<div[^>]*) class=(["']?)sb_ads[^\2]*\2@$1 class="msn_ads"@Uig
+s@(<a[^>]*href=\")http://g.msn.com/.*\?(http://.*)(&amp;&amp;DI=.*)(\")@$1$2$4@Ug
+s@(<a[^>]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
 
 #################################################################################
 #
-# demoronizer: Correct Microsoft's abuse of standardized character sets, which 
-#              leave the browser to (mis)-interpret unknown characters, with 
-#              sometimes bizarre results on non-MS platforms.
+# blogspot: Cleans up some Blogspot blogs. Read the fine print before using this.
 #
-# credit: ripped from the demoroniser.pl script by: 
-#         John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser
+#           This filter also intentionally removes some navigation stuff and
+#           sets the page width to 100%. As a result, some rounded "corners" would
+#           appear to early or not at all and as fixing this would require a browser
+#           that understands background-size (CSS3), they are removed instead.
+#
+#           When applied to feeds, it removes comment titles that
+#           only contain the beginning of the actual comment.
 #
 #################################################################################
-FILTER: demoronizer fixing MS's non-standard use of std charsets.
+FILTER: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
 
-s/(&\#[0-2]\d\d)\s/$1; /g
-# per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess.
-# Must come before x94 below.
-s/\xE2\x80\x94/ -- /g
-s/\x82/,/g
-#s-\x83-<em>f</em>-g
-s/\x84/,,/g
-s/\x85/.../g
-#s/\x88/^/g
-#s-\x89- °/°°-g
-s/\x8B/</g
-s/\x8C/Oe/g
-s/\x91/`/g
-s/\x92/'/g
-s/(\x93|\x94)/"/g
-# Bullet type character.
-s/\x95/&middot;/g
-s/\x96/-/g
-s/\x97/--/g
-#s-\x98-<sup>~</sup>-g
-#s-\x99-<sup>TM</sup>-g
-# per Robert Lynch.
-s/\x9B/>/g                  # 155
+s@</head>@<style type="text/css">\n\
+ /* Style sheet inserted by Privoxy's blogspot filter. */\n\
+ \#powered-by {display: none !important;}\n\
+ \#wrap4, \#wrapper {margin-top: 0px }\n\
+ \#blogheader, \#header {margin-top: 0.5em !important}\n\
+ \#content {width: 98% }\n\
+ \#main {width: 70% }\n\
+ \#sidebar {width: 29% }\n\
+ .post-body {overflow: auto;}\n\
+ .blogComments {width: 100%; overflow: auto;}\n</style>\n$0@
+s@<body.*(?:<div id="space-for-ie"></div>|(<div id="(?:content|wrap4|wrapper)))@<body>\
+ <!-- Privoxy's blogspot filter ditched some garbage here -->$1@Us
+s@(<div style=\"[^\"]*width:)30em@$1 100%@
+s@background:url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;@/*$0*/@Ug
+s@(background:\#[a-f\d]{3})( url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;)@$1 ;/*$2*/@Ug
+# Do the feed filtering magic as described above.
+s@<title(?:\s+type=\'text\')?>([^<]*)(?:\.\.\.)?\s*</title>\s*\
+(<content(?:\s+type=\'(?:html|text)\')?>\s*\1)@<title></title>$2@ig
 
-############################################################################## 
+#################################################################################
 #
-#  Revisions   :
-#     $Log: default.filter,v $
-#     Revision 1.13  2002/09/11 16:04:20  oes
-#     Preserve original quoting style in <img> tags wherever possible. Fixes Bug #605956
+# x-httpd-php-to-html: Changes the Content-Type header from
+#                      x-httpd-php to html. "Content-Type: x-httpd-php"
+#                      is set by clueless PHP users and causes many
+#                      browsers do open a download menu instead of
+#                      rendering the page.
 #
-#     Revision 1.12  2002/09/05 14:55:38  oes
-#     Synced with the stable branch:
-#         Revision 1.11.2.6  2002/08/23 14:12:26  oes
-#         Proofed frameset-borders against "fremaborder=0 border=0"
+#################################################################################
+SERVER-HEADER-FILTER: x-httpd-php-to-html Changes the Content-Type header from x-httpd-php to html.
+
+s@^(Content-Type:)\s*application/x-httpd-php@$1 text/html@i
+
+#################################################################################
 #
-#         Revision 1.11.2.5  2002/08/22 15:05:20  oes
-#         Added Filter to make Quicktime movies saveable (thanks to aaron@linville.org for the idea)
+# html-to-xml: Changes the Content-Type header from html to xml.
 #
-#         Revision 1.11.2.4  2002/08/10 11:32:29  oes
-#         Attribute values in replacement tags of banners-by-size filter now undelimited. (Fixes bug #592493)
+#################################################################################
+SERVER-HEADER-FILTER: html-to-xml Changes the Content-Type header from html to xml.
+
+s@^(Content-Type:)\s*text/html(;.*)?$@$1 application/xhtml+xml$2@i
+
+#################################################################################
 #
-#         Revision 1.11.2.3  2002/08/05 11:43:56  oes
-#         Fixed a bug in the popups filter that was introduced with the last fix :-(
+# xml-to-html: Changes the Content-Type header from xml to html.
 #
-#         Revision 1.11.2.2  2002/08/01 11:20:13  oes
-#         Fixed bugs 587802, 577802 and an unreported one
+#################################################################################
+SERVER-HEADER-FILTER: xml-to-html Changes the Content-Type header from xml to html.
+
+s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@i
+
+#################################################################################
 #
-#         Revision 1.11.2.1  2002/07/26 15:18:26  oes
-#         - All filters reviewed and many shorcomings fixed
-#         - New filters: img-reorder, banners-by-link and js-events
-#         - Jobs reorderd because they are now executed in order of
-#           appearance
+# hide-tor-exit-notation: Remove the Tor exit node notation in Host and Referer headers.
 #
-#     Revision 1.11  2002/05/24 00:57:18  oes
-#     Made WeBugs job ungreedy; Fixes bug 559190
+#   Note: If Privoxy and Tor are chained and Privoxy is configured to
+#         use socks4a, one can use http://www.example.org.foobar.exit/
+#         to access the host www.example.org through Tor exit node foobar.
 #
-#     Revision 1.10  2002/04/18 10:14:19  oes
-#     renamed some filters
+#         As the HTTP client isn't aware of this notation, it treats the
+#         whole string "www.example.org.foobar.exit" as host and uses it
+#         for the "Host" and "Referer" headers. From the server's point of
+#         view the resulting headers are invalid and can cause problems.
 #
-#     Revision 1.9  2002/04/11 07:36:35  oes
-#     Generalized js-popup filter
+#         An invalid "Referer" header can trigger "hot-linking" protections,
+#         an invalid "Host" header will make it impossible for the server to
+#         find the right vhost (several domains hosted on the same IP address).
 #
-#     Revision 1.8  2002/04/10 17:07:21  oes
-#     Fixed potentially desctructive jobs, added noflash filter
+#         This filter removes the "foo.exit" part in those headers
+#         to prevent the mentioned problems. Note that it only modifies
+#         the HTTP headers, it doesn't make it impossible for the server
+#         to detect your Tor exit node based on the IP address the request is
+#         coming from.
 #
-#     Revision 1.7  2002/04/09 18:34:51  oes
-#     Fixed HTML syntax in replacements
+#################################################################################
+CLIENT-HEADER-FILTER: hide-tor-exit-notation Removes the Tor exit node notation in Host and Referer headers.
+
+s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i
+
+#################################################################################
 #
-#     Revision 1.6  2002/04/03 19:49:52  swa
-#     name change
+# less-download-windows: Prevents annoying download windows for content types
+#                        the browser can handle itself.
 #
-#     Revision 1.5  2002/03/27 15:30:26  swa
-#     have a consistent appearance
+#################################################################################
+SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself.
+
+s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i
+s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh(?:\s|$))\s*@$1 text/plain@i
+
+#################################################################################
 #
-#     Revision 1.4  2002/03/26 22:29:54  swa
-#     we have a new homepage!
+# image-requests: Tags detected image requests as "IMAGE-REQUEST". Whether
+#                 or not the detection actually works depends on the browser.
 #
-#     Revision 1.3  2002/03/24 16:08:03  jongfoster
-#     Fixing banners-by-size for new config URLs
+#################################################################################
+CLIENT-HEADER-TAGGER: image-requests Tags detected image requests as "IMAGE-REQUEST".
+
+s@^Accept:\s*image/.*@IMAGE-REQUEST@i
+
+#################################################################################
 #
-#     Revision 1.2  2002/03/24 13:02:18  swa
-#     name change related issues.
+# css-requests:  Tags detected CSS requests as "CSS-REQUEST". Whether
+#                or not the detection actually works depends on the browser.
 #
-#     Revision 1.1  2002/03/24 11:37:39  jongfoster
-#     Name change
+#################################################################################
+CLIENT-HEADER-TAGGER: css-requests Tags detected CSS requests as "CSS-REQUEST".
+
+s@^Accept:\s*text/css.*@CSS-REQUEST@i
+
+#################################################################################
 #
-#     Revision 1.24  2002/03/16 20:39:54  oes
-#      - Added descriptions to the filters so users will know what they select in the cgi editor
-#      - Added content-cookies filter
-#      - Bugfixed many jobs (Thanks to Al for some hints)
+# range-requests: Tags range requests as "RANGE-REQUEST".
 #
-#     Revision 1.22  2002/03/12 13:42:50  oes
-#     Fixing & Optimizing REs
+#                 By default Privoxy removes Range headers for requests to
+#                 ressources that will be filtered to make sure the filters
+#                 get the whole picture. Otherwise Range requests could be
+#                 intentionally used to circumvent filters or, less likely,
+#                 filtering a partial response may damage it because it matched
+#                 a pattern that the ressource as a whole wouldn't.
 #
-#     Revision 1.21  2002/03/12 11:59:20  oes
-#     Beefed up Buzzword Bingo
+#                 Range requests can be useful and save bandwidth so instead
+#                 of removing Range headers for requests to ressources that
+#                 will be filtered, you may prefer to simply disable filtering
+#                 for those requests.
 #
-#     Revision 1.20  2002/03/12 01:42:50  oes
-#     Introduced modular filters
+#                 That's what this tagger is all about. After enabling it,
+#                 you can disable filtering for range requests using the following
+#                 action section:
 #
-#     Revision 1.19  2002/03/10 19:49:24  oes
-#     Added expression to kill referer tracking in JavaScripts
+#                 {-filter -deanimate-gifs}
+#                 TAG:^RANGE-REQUEST
 #
-#     Revision 1.18  2002/03/08 17:14:12  oes
-#     PNG -> image in comments
+#################################################################################
+CLIENT-HEADER-TAGGER: range-requests Tags range requests as "RANGE-REQUEST".
+
+s@^Range:.*@RANGE-REQUEST@i
+
+#################################################################################
 #
-#     Revision 1.17  2002/03/07 03:50:54  oes
-#     Adapted comments to new built-in images
+# client-ip-address: Tags the request with the client's IP address.
 #
-#     Revision 1.16  2002/02/21 00:12:19  jongfoster
-#     Modifying the banner regexps to use long URLS and to autodetect
-#     whether to show a logo or a transparent GIF, based on actionsfile
-#     setting.
+#################################################################################
+CLIENT-HEADER-TAGGER: client-ip-address Tags the request with the client's IP address.
+
+s@^\w*\s+.*\s+HTTP/\d\.\d\s*@IP-ADDRESS: $origin@D
+
+#################################################################################
 #
-#     Revision 1.15  2001/12/28 23:54:20  steudten
-#     Fix for feature Req #495374: http-equiv problem
+# http-method: Tags the request with its HTTP method.
 #
-#     Revision 1.14  2001/12/09 18:55:11  david__schmidt
-#     Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
-#     for 2.9.10 beta
+#################################################################################
+CLIENT-HEADER-TAGGER: http-method Tags the request with its HTTP method.
+
+s@^(\w*).*HTTP/\d\.\d\s*$@$1@i
+
+#################################################################################
 #
-#     Revision 1.13  2001/10/13 13:11:20  joergs
-#     Fixed WebBug filter.
+# allow-post: Tags POST requests as "ALLOWED-POST".
 #
-#     Revision 1.12  2001/10/07 15:46:42  oes
-#     Followed Guy's proposal to change the document.cookie job
+#################################################################################
+CLIENT-HEADER-TAGGER: allow-post Tags POST requests as "ALLOWED-POST".
+
+s@^(?:POST)\s+.*\s+HTTP/\d\.\d\s*@ALLOWED-POST@i
+
+#################################################################################
 #
-#     Revision 1.11  2001/09/21 12:34:00  joergs
-#     Added filter to replace "Nimda" code by a warning.
+# complete-url: Tags the request with the whole request URL.
 #
-#     Revision 1.10  2001/07/20 11:04:26  oes
-#     Added Rodneys javascript cookie filter
+#################################################################################
+CLIENT-HEADER-TAGGER: complete-url Tags the request with the whole request URL.
+
+s@^\w*\s+(.*)\s+HTTP/\d\.\d\s*$@$1@i
+
+#################################################################################
 #
-#     Revision 1.9  2001/07/13 14:03:48  oes
-#     Elimiated yet another bug in the banner-by-size jobs. Shame on me!
+# user-agent: Tags the request with the complete User-Agent header.
 #
-#     Revision 1.8  2001/06/29 13:34:00  oes
-#     - Added explanation for U and T options
-#     - Added hint on image replacement by CGI call
-#     - Fixed bug in banner-by-size jobs
+#################################################################################
+CLIENT-HEADER-TAGGER: user-agent Tags the request with the complete User-Agent header.
+
+s@^User-Agent:.*@$0@i
+
+#################################################################################
 #
-#     Revision 1.7  2001/06/19 14:21:56  oes
-#     Fixed microsuck line
+# content-type: Tags the request with the content type declared by the server.
 #
-#     Revision 1.6  2001/06/09 14:01:57  swa
-#     header. cosmetics. default: no messing ala microsuck.
+#################################################################################
+SERVER-HEADER-TAGGER: content-type Tags the request with the content type declared by the server.
+
+s@^Content-Type:\s*([^;]+).*@$1@i
+
+#################################################################################
 #
+# privoxy-control: The taggers create tags with the content of X-Privoxy-Control
+#                  headers, the filters remove said headers.
 #
-# 
+#################################################################################
+CLIENT-HEADER-TAGGER: privoxy-control Creates tags with the content of X-Privoxy-Control headers.
+
+s@^X-Privoxy-Control:\s*@@i
+
+CLIENT-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers.
+
+s@^X-Privoxy-Control:.*@@i
+
+SERVER-HEADER-TAGGER: privoxy-control Creates tags with the content of X-Privoxy-Control headers.
+
+s@^X-Privoxy-Control:\s*@@i
+
+SERVER-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers.
+
+s@^X-Privoxy-Control:.*@@i