X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=c845cedb487cd364827cde4982dfe26f16b02d1c;hp=ed3200548321af80dd82a26e197fa71d5c80b5b4;hb=54b4e8c141117d636f6113ec4c43579248b77ed7;hpb=86a2fdbbb9d15c0a498cd7285daaa27f3678e454

diff --git a/default.filter b/default.filter
index ed320054..c845cedb 100644
--- a/default.filter
+++ b/default.filter
@@ -2,11 +2,11 @@
 # 
 #  File        :  $Source: /cvsroot/ijbswa/current/default.filter,v $
 # 
-#  $Id: default.filter,v 1.45 2007/08/11 16:54:12 fabiankeil Exp $
+#  $Id: default.filter,v 1.75 2009/10/03 10:39:33 fabiankeil Exp $
 #
 #  Purpose     :  Rules to process the content of web pages
 # 
-#  Copyright   :  Written by and Copyright (C) 2001 - 2007 the
+#  Copyright   :  Written by and Copyright (C) 2001-2009 the
 #                 Privoxy team. http://www.privoxy.org/
 #
 # We value your feedback. However, to provide you with the best support,
@@ -52,7 +52,7 @@
 #
 # 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
@@ -77,17 +77,17 @@
 
 #################################################################################
 #
-# 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. 
@@ -128,10 +128,10 @@ s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
 
 #################################################################################
 #
-# js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites)
+# js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites).
 #
 #################################################################################
-FILTER: js-events Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites)
+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:
@@ -140,10 +140,10 @@ s/settimeout\(/concat(/ig
 
 #################################################################################
 #
-# html-annoyances: Get rid of particularly annoying HTML abuse
+# html-annoyances: Get rid of particularly annoying HTML abuse.
 #
 #################################################################################
-FILTER: 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
@@ -161,10 +161,10 @@ 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, except those used by antiadbuster.com to detect us:
 #
@@ -177,10 +177,10 @@ s|<meta\s+http-equiv=['"]?set-cookie.*>|<!-- ZappedCookie -->|igU
 
 #################################################################################
 #
-# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups)
+# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups).
 #
 #################################################################################
-FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups)
+FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups).
 
 # Note: Only deactivates refreshes with more than 9 seconds delay to
 #       preserve monster-stupid but common redirections via meta tags.
@@ -190,10 +190,10 @@ s/<meta\s+http-equiv\s*=\s*(['"]?)refresh\1\s+content\s*=\s*(['"]?)\d{2,}\s*(;\s
 
 #################################################################################
 #
-# unsolicited-popups: Disable unsolicited pop-up windows
+# unsolicited-popups: Disable unsolicited pop-up windows.
 #
 #################################################################################
-FILTER: unsolicited-popups Disable only unsolicited pop-up windows
+FILTER: unsolicited-popups Disable only unsolicited pop-up windows.
 
 s+([^'"]\s*<head.*>)(?=\s*[^'"])+$1<script>function PrivoxyWindowOpen(){return(null);}</script>+isU
 s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig
@@ -202,10 +202,10 @@ s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c
 
 ##################################################################################
 #
-# all-popups: Kill all popups in JavaScript and HTML
+# all-popups: Kill all popups in JavaScript and HTML.
 #
 #################################################################################
-FILTER: all-popups Kill all popups in JavaScript and HTML
+FILTER: all-popups Kill all popups in JavaScript and HTML.
 
 s@((\W\s*)(?:map)?(window|this|parent)\.?)open\s*\\?\(@$1concat(@ig  # JavaScript
 #s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig        # HTML
@@ -213,25 +213,28 @@ 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 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]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|<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.
 #
 #################################################################################
 #
@@ -244,7 +247,7 @@ s|<img (src=(?:(['"])[^>\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\
 # 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)[^>]*?(?=/?>)@\
@@ -282,10 +285,10 @@ s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(h
 
 #################################################################################
 #
-# banners-by-link: Kill banners by their links to known clicktrackers (Experimental)
+# 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:
 #
@@ -293,7 +296,7 @@ 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 \
+| 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 \
@@ -307,20 +310,20 @@ s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:ad(?:click|vert)|atwola\.com/(?:link|redi
 
 ################################################################################
 #
-# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
+# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking).
 #
 #################################################################################
-FILTER: 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
+# 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
+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
@@ -328,19 +331,19 @@ s/(<textarea[^>]*?)wrap=(['"]?)hard\2/$1/ig
 
 #################################################################################
 #
-# jumping-windows: Prevent windows from resizing and moving themselves
+# jumping-windows: Prevent windows from resizing and moving themselves.
 #
 #################################################################################
-FILTER: 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
+# frameset-borders: Give frames a border, make them resizable and scrollable.
 #
 #################################################################################
-FILTER: frameset-borders Give frames a border and make them resizable
+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
@@ -361,7 +364,7 @@ s/(<frame\s+[^>]*)scrolling=(['"]?)(no|0)\2/$1/igU
 #         John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser
 #
 #################################################################################
-FILTER: demoronizer Fix MS's non-standard use of standard charsets
+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.
@@ -390,11 +393,11 @@ s/\x9B/>/g                  # 155
 
 #################################################################################
 #
-# shockwave-flash: Kill embedded Shockwave Flash objects
+# shockwave-flash: Kill embedded Shockwave Flash objects.
 #                  Note: Better just block "/.*\.swf$"!
 #
 #################################################################################
-FILTER: shockwave-flash Kill embedded Shockwave Flash objects
+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
@@ -402,10 +405,10 @@ s|<embed [^>]*(application/x-shockwave-flash\|\.swf).*>(.*</embed>)?|<!-- Squish
 
 #################################################################################
 #
-# quicktime-kioskmode: Make Quicktime movies saveable
+# quicktime-kioskmode: Make Quicktime movies saveable.
 #
 #################################################################################
-FILTER: quicktime-kioskmode Make Quicktime movies saveable
+FILTER: quicktime-kioskmode Make Quicktime movies saveable.
 
 s/(<embed\s+[^>]*)kioskmode\s*=\s*(["']?)true\2/$1/ig 
 
@@ -446,7 +449,7 @@ s/(M|m)edien(?![^<]*>)/$1&auml;dchen/Ug
 #                 Pages are "blocked" based on keyword matching.
 #
 #################################################################################
-FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliable.
+FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliably.
 
 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
 # (Note #2: Is 'sex' a rude word?!)
@@ -458,7 +461,7 @@ s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not sea
 
 # Remove by description
 s/^.*\
-(?:(suck|lick|tounge|rub|fuck|fingering|finger|chicks?)\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).*$\
 /This page has been blocked by Privoxy's crude-parental content filter\
@@ -487,10 +490,10 @@ s/^.*(Section 2257|18 U.?S.?C.? 2257).*$\
 
 #################################################################################
 #
-# IE-Exploits: Disable some known Internet Explorer bug exploits
+# IE-Exploits: Disable some known Internet Explorer bug exploits.
 #
 #################################################################################
-FILTER: ie-exploits Disable some known Internet Explorer bug exploits
+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.
@@ -571,12 +574,15 @@ s@(<a(?:rea)?[^>]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\
 #
 #################################################################################
 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 {width: 100%}\n</style>\n$0@
+ .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\"\
@@ -591,13 +597,22 @@ s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
 #
 #################################################################################
 FILTER: yahoo CSS-based block for Yahoo text ads. Also removes a width limitation.
+
 s@</head>@\n<style type="text/css">\n\
  /* Style sheet inserted by Privoxy's yahoo filter. */\n\
- \#symadbn, \#ymadbn, .yschbox, \#yschsec, .yschhd, \#yschanswr, .yschftad,\
- .yschspn, .yschspns, \#ygrp-sponsored-links, \#ks-ypn-ads {display: none !important;}\n\
- \#yschpri, \#yschweb {width: 100% !important; max-width: 100% !important;}\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 {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\
-</style>\n$0@
+ \#composebox \#compose_editorArea {width: 70% !important; /* reasonably sized reply textarea please */\n\
+ </style>\n$0\n@
+
+s@(<textarea\s+id="composeArea"[^>]*)width:545px;@$1width:70%;@isU
 
 #################################################################################
 #
@@ -606,26 +621,24 @@ s@</head>@\n<style type="text/css">\n\
 #
 #################################################################################
 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 {display: none !important;}\n\
- \#results, .flank, .results_area_flank, .results_area_stroke, .SearchSection .not\
- {width: 99% /*!important*/; min-width: 99% !important;\
+ .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\
- /* Make continue links harder to miss */\n\
- \#pagination_bottom a {padding: .3em .5em .3em .5em; border: 1px solid \#e6e6e6;}\n\
- \#pagination_bottom li, \#pagination_bottom li .selected, li .nextPage \
- {margin: 0 !important; cursor: auto; border: none; padding:.1em;}\n\
- \#pagination_bottom li .prevPage {padding-right: 1.5em !important;}\n\
- \#pagination_bottom li .selected {border: none;}\n\
- .selected a {background-color: \#d2eaf6; border: 1px solid \#b7d8ee;}\n\
  /* Remove "suggestions". They are next to worthless but partly overlap with the search results */\n\
- .suggestion, \#nys_right {clear: both; display:none;}\n\
+ .suggestion, \#nys_right, \#nys {clear: both; display:none;}\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
-s@<div id=\"ar\">(<h2>Sponsored sites</h2>)@<div class="msn_ads">$1@
 
 #################################################################################
 #
@@ -636,8 +649,12 @@ s@<div id=\"ar\">(<h2>Sponsored sites</h2>)@<div class="msn_ads">$1@
 #           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: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
+
 s@</head>@<style type="text/css">\n\
  /* Style sheet inserted by Privoxy's blogspot filter. */\n\
  \#powered-by {display: none !important;}\n\
@@ -653,6 +670,9 @@ s@<body.*(?:<div id="space-for-ie"></div>|(<div id="(?:content|wrap4|wrapper)))@
 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
 
 #################################################################################
 #
@@ -664,6 +684,7 @@ s@(background:\#[a-f\d]{3})( url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*
 #
 #################################################################################
 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
 
 #################################################################################
@@ -672,6 +693,7 @@ s@^(Content-Type:)\s*application/x-httpd-php@$1 text/html@i
 #
 #################################################################################
 SERVER-HEADER-FILTER: html-to-xml Changes the Content-Type header from html to xml.
+
 s@^(Content-Type:)\s*text/html(;.*)?$@$1 application/xhtml+xml$2@i
 
 #################################################################################
@@ -680,6 +702,7 @@ s@^(Content-Type:)\s*text/html(;.*)?$@$1 application/xhtml+xml$2@i
 #
 #################################################################################
 SERVER-HEADER-FILTER: xml-to-html Changes the Content-Type header from xml to html.
+
 s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@i
 
 #################################################################################
@@ -707,6 +730,7 @@ s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@
 #
 #################################################################################
 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
 
 #################################################################################
@@ -715,9 +739,10 @@ s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i
 #                        the browser can handle itself.
 #
 #################################################################################
-SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself
+SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself.
+
 s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i
-s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh)\s*@$1 text/plain@i
+s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh(?:\s|$))\s*@$1 text/plain@i
 
 #################################################################################
 #
@@ -726,7 +751,8 @@ s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh)\s*@$
 #
 #################################################################################
 CLIENT-HEADER-TAGGER: image-requests Tags detected image requests as "IMAGE-REQUEST".
-s@Accept:\s*image/.*@IMAGE-REQUEST@i
+
+s@^Accept:\s*image/.*@IMAGE-REQUEST@i
 
 #################################################################################
 #
@@ -735,355 +761,81 @@ s@Accept:\s*image/.*@IMAGE-REQUEST@i
 #
 #################################################################################
 CLIENT-HEADER-TAGGER: css-requests Tags detected CSS requests as "CSS-REQUEST".
-s@Accept:\s*text/css.*@CSS-REQUEST@i
 
-############################################################################## 
-#
-#  Revisions   :
-#     $Log: default.filter,v $
-#     Revision 1.45  2007/08/11 16:54:12  fabiankeil
-#     - Complete the changes from r1.42.
-#     - Make crude-parental less sensitive to the amount of white-space,
-#       add the note that it doesn't work too well again and replace the
-#       DMOZ link with a less confusing explanation.
-#
-#     Revision 1.44  2007/07/18 11:06:56  hal9
-#     Replace notarget with '' in all popups filter to keep from breaking xhmtl per
-#     report from Siegfried Gipp.
-#
-#     Revision 1.43  2007/06/01 14:17:04  fabiankeil
-#     Mention possible delimiter conflicts with variables in dynamic pcrs commands.
-#
-#     Revision 1.42  2007/05/17 15:55:36  fabiankeil
-#     Undo an improperly tested last-minute change
-#     and turn "text-requests" back into "css-requests".
-#
-#     Revision 1.41  2007/05/17 15:45:41  fabiankeil
-#     - Mention new filter types and the 'D' option.
-#     - Header filters are now case-insensitive and accept a
-#       varying amount of whitespace after the colon.
-#     - Add another selector for yahoo ads.
-#     - New server-header filter: less-download-windows
-#     - New client-header taggers: text-requests and image-requests.
-#
-#     Revision 1.40  2007/03/20 15:40:00  fabiankeil
-#     Adjust to new world order with dedicated header-filter actions.
-#
-#     Revision 1.39  2007/02/21 14:10:23  fabiankeil
-#     - Fix a js-annoyances pcrs command that broke
-#       evaluated code. (BR #1124071, thanks to Bor Gergely)
-#     - Have unsolicited-popups and all-popups catch the
-#       wheather.com popup reported in in AF #1640173.
-#
-#     Revision 1.38  2007/02/19 11:22:48  hal9
-#     Adding back the orginal filter content to offset problems found by Fabian.
-#
-#     Revision 1.37  2007/02/17 13:29:44  hal9
-#     Updates to the crude parental filter per Feature Requests item #1648657.
-#
-#     Revision 1.36  2007/02/05 16:47:31  fabiankeil
-#     - Let banners-by-link look for "advert".
-#     - Fix XML systax problems with banners-by-link
-#       and banners-by-size (AF#1651570).
-#
-#     Revision 1.35  2006/12/21 12:28:12  fabiankeil
-#     Escaping special characters in filter descriptions is no
-#     longer necessary, it's done by Privoxy now.
-#
-#     Revision 1.34  2006/12/12 17:32:23  fabiankeil
-#     Added id mbEnd to google filter, it's now and then
-#     used for the sponsored links.
-#
-#     Have js-annoyances try to prevent status bar
-#     modifications where the status bar text is
-#     inside another variable. Fixes 1605710.
-#
-#     Revision 1.33  2006/11/16 17:10:43  fabiankeil
-#     Removed webbugs debugging comment again.
-#     The apostrophe could break JavaScript and
-#     the comment itself could mess up existing
-#     comments.
-#
-#     Revision 1.32  2006/11/10 18:04:04  fabiankeil
-#     Have no-ping print the ping warning in red.
-#
-#     Modified yahoo to keep in sync with recent
-#     CSS changes and to suppress a useless horizontal
-#     scrollbar.
-#
-#     msn now makes sure that the continue-link boxes
-#     act as links (the original CSS just changes the cursor).
-#
-#     Changed fun filter regex to leave microsoft links alone.
-#     Fixes BR 1019996.
-#
-#     Revision 1.31  2006/10/21 13:12:28  fabiankeil
-#     Added no-ping and hide-tor-exit-notation.
-#
-#     Adjusted jumping-windows to break less.
-#     Fixes BR 1146134.
-#
-#     Revision 1.30  2006/10/18 12:36:50  fabiankeil
-#     google filter now cleans Google groups as well.
-#
-#     Revision 1.29  2006/10/11 14:03:17  fabiankeil
-#     Changed img-reorder regex to only move width
-#     attributes if they are following at least one
-#     whitespace. Fixes BR 1328455.
-#
-#     Revision 1.28  2006/10/11 13:31:13  fabiankeil
-#     Added Anduin Withers' js-annoyances fix
-#     for not messing up escaped quotes. Fixes BR 999765.
-#
-#     Improved blogspot filter to make it less likely that
-#     the blogspot banner at the top of the page is missed.
-#
-#     Revision 1.27  2006/10/08 17:00:51  fabiankeil
-#     Modified webbugs filter to create a comment around the offending
-#     image instead of removing it entirely.
-#
-#     Adjusted regex to only match if there's at least one whitespace
-#     before the width and height attributes. Makes it more likely that
-#     they are indeed attributes, and not part of the value of another attribute.
-#     Solves BR 1035587.
-#
-#     Thanks to Martin Thomas for diagnosing the cause of the problem.
-#
-#     Revision 1.26  2006/10/06 18:06:16  fabiankeil
-#     Added header filter x-httpd-php-to-html
-#     and reverted another img-reorder whitespace
-#     problem.
-#
-#     Revision 1.25  2006/10/06 15:26:09  fabiankeil
-#     Bumped copyright year.
-#
-#     Reverted parts of the last img-reorder change
-#     which were intended to remove superfluous whitespace
-#     but had the side effect to mess up some tags.
-#
-#     Modified banners-by-size and banners-by-link to
-#     use border value "0" instead of "\0". Fixes BR 1100065.
-#
-#     Revision 1.24  2006/10/06 11:25:31  fabiankeil
-#     Taught img-reorder not to break img tags
-#     with empty src attributes. Fixes BR 1089474.
-#     Thanks to Raphael Moll for reporting.
-#
-#     Revision 1.23  2006/10/05 14:46:28  fabiankeil
-#     Replaced "<" in img-reorder's description with "&lt;".
-#
-#     Modified msn filter to tag ads with classes instead
-#     of ids. There may be more than one ad per page,
-#     but ids are required to be unique.
-#
-#     Revision 1.22  2006/10/04 19:17:14  fabiankeil
-#     Incorportated Frédéric Crozat's ie-exploits
-#     modification to make it less trigger-happy.
-#
-#     Modified blogspot filter to make .post-body
-#     scrollable if necessary.
-#
-#     Revision 1.21  2006/10/02 16:21:14  fabiankeil
-#     Adjusted yahoo filter to hide .yschspns as well.
-#     Added header filters: html-to-xml and xml-to-html.
-#
-#     Revision 1.20  2006/10/01 21:00:22  fabiankeil
-#     New site-specific filters: google, yahoo, msn and blogspot.
-#
-#     Revision 1.19  2006/07/18 14:48:45  david__schmidt
-#     Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch)
-#     with what was really the latest development (the v_3_0_branch branch)
-#
-#     Revision 1.11.2.23  2004/02/17 13:34:01  oes
-#     - Beefed up the protection of the unsolicited-popups
-#       filter against matching in JavaScript string constants.
-#     - Extended the fun filter with a German joke
-#     - Extended the site-specifics filter with a convenience
-#       reeplacement for managing mailing lists at SourceForge
-#
-#     Revision 1.11.2.22  2004/01/30 15:29:29  oes
-#     Updated the copyright note
-#
-#     Revision 1.11.2.21  2004/01/20 15:15:01  oes
-#     Detail enhancement in all-popups
-#
-#     Revision 1.11.2.20  2004/01/06 16:46:14  oes
-#     Fixed a JS syntax problem in jumping-windows
-#
-#     Revision 1.11.2.19  2003/12/17 17:09:25  oes
-#     Added remedy against IE address bar spoofing
-#
-#     Revision 1.11.2.18  2003/12/02 11:25:27  oes
-#     Fixed a line trashed in previous commit
-#
-#     Revision 1.11.2.17  2003/12/01 21:58:46  oes
-#     Assorted tuning:
-#
-#      - unsolicited-popups no longer matches at start or end of quoted
-#        strings, and is now activated earlier and deactivated later in
-#        the page.
-#      - replacement images in banners-by-* now without border
-#      - more effective shockwave flash flattening
-#      - Custom annoyance filtering for Yahoo Groups, Monster.com, NY Times.
-#
-#     Revision 1.11.2.16  2003/05/08 09:44:56  oes
-#     Allow extra parameters in blink,marquee tags. Fixes bug #734012
-#
-#     Revision 1.11.2.15  2003/03/30 13:57:08  oes
-#     Making unsolicited-popups safe for use on <html> tags enclosed in JS strings
-#
-#     Revision 1.11.2.14  2003/03/19 13:17:50  oes
-#     - Added filter "site-specifics" to address site specific problems
-#     - Fixed a small problem in the img-reorder filter
-#
-#     Revision 1.11.2.13  2003/03/18 19:28:59  oes
-#     Fixed a minor problem in the img-reorder filter
-#
-#     Revision 1.11.2.12  2003/03/15 14:06:58  oes
-#      - Assorted refinements, optimizations and fixes in the js-annoyances,
-#        img-reorder, banners-by-size, banners-by-link, webbugs, refresh-tags,
-#        html-annoyances, content-cookies and fun filters
-#      - Replaced filter "popups" by choice between two modes:
-#        - "unsolicited-popups" tries to catch only the unsolicited ones
-#        - "all-popups" tries to kill them all (as before)
-#      - New filter "tiny-textforms" Help those tiny or hard-wrap textareas.
-#      - New filter "jumping-windows" that prevents windows from resizing
-#        and moving themselves
-#      - Replaced "nimda" with more general "ie-exploits" filter in which
-#        all filters for exploits shall be collected
-#
-#     Revision 1.11.2.11  2002/11/12 16:14:43  oes
-#     Exchanged js-annoyance filter against status bar rewrites with improved version by Don Libes
-#
-#     Revision 1.11.2.10  2002/11/11 13:39:47  oes
-#     Make refresh-tags filter work even on incorrect refresh tags like found on usatoday.com
-#
-#     Revision 1.11.2.9  2002/11/08 16:39:17  oes
-#     Made img-reorder more cautious. Fixes bug #632715
-#
-#     Revision 1.11.2.8  2002/10/13 21:56:52  hal9
-#     Adding demoronizer filter. This should include all the common abuses. I have
-#     left a few of the rare cases commented out (never found these in the wild).
-#
-#     Revision 1.11.2.7  2002/09/25 15:09:39  oes
-#     Preserve original quoting style in <img> tags wherever possible. Fixes Bug #605956
-#
-#     Revision 1.11.2.6  2002/08/23 14:12:26  oes
-#     Proofed frameset-borders against "fremaborder=0 border=0"
-#
-#     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)
-#
-#     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)
-#
-#     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 :-(
-#
-#     Revision 1.11.2.2  2002/08/01 11:20:13  oes
-#     Fixed bugs 587802, 577802 and an unreported one
-#
-#     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
-#
-#     Revision 1.11  2002/05/24 00:57:18  oes
-#     Made WeBugs job ungreedy; Fixes bug 559190
-#
-#     Revision 1.10  2002/04/18 10:14:19  oes
-#     renamed some filters
-#
-#     Revision 1.9  2002/04/11 07:36:35  oes
-#     Generalized js-popup filter
-#
-#     Revision 1.8  2002/04/10 17:07:21  oes
-#     Fixed potentially desctructive jobs, added noflash filter
-#
-#     Revision 1.7  2002/04/09 18:34:51  oes
-#     Fixed HTML syntax in replacements
-#
-#     Revision 1.6  2002/04/03 19:49:52  swa
-#     name change
-#
-#     Revision 1.5  2002/03/27 15:30:26  swa
-#     have a consistent appearance
-#
-#     Revision 1.4  2002/03/26 22:29:54  swa
-#     we have a new homepage!
-#
-#     Revision 1.3  2002/03/24 16:08:03  jongfoster
-#     Fixing banners-by-size for new config URLs
-#
-#     Revision 1.2  2002/03/24 13:02:18  swa
-#     name change related issues.
-#
-#     Revision 1.1  2002/03/24 11:37:39  jongfoster
-#     Name change
-#
-#     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)
-#
-#     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
-#
-#     Revision 1.18  2002/03/08 17:14:12  oes
-#     PNG -> image in comments
+s@^Accept:\s*text/css.*@CSS-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