#       connections.  These performance issues only matter if your server
#       CPU is getting overloaded.  Also, these only matter when retrieving
#       HTML, because it's the HTML modification that takes all the time.
#     If you can, use mod_perl.  Starting with version 1.3.1, this should
#       work under mod_perl, which requires Perl 5.004 or later.  If you use
#       mod_perl, be careful to install this as an NPH script, i.e. set the
#       "PerlSendHeader Off" configuration directive.  For more info, see the
#       mod_perl documentation.
#     If you use mod_perl and modify this script, see the note near the
#       "reset 'a-z'" line below, regarding UPPER_CASE and lower_case
#       variables.
#
#
#   TO DO:
#     What I want to hear about:
#       . Any HTML tags not being converted here.
#       . Any method of introducing JavaScript or other script, that's not
#           being handled here.
#       . Any script MIME types other than those already in @SCRIPT_MIME_TYPES.
#       . Any MIME types other than text/html that have links that need to
#           be converted.
#     plug any other script holes (e.g. MSIE-proprietary, other MIME types?)
#     This could use cleaner URL-encoding all over ($base_url, etc.)
#     more error checking?
#     find a simple encryption technique for proxy_encode()
#     support more protocols, like mailto: or gopher:
#     For ad filtering, add option to disable images from servers other than
#       that of the containing HTML page?  Is it worth it?
#
#
#   BUGS:
#     Anonymity may not not perfect.  In particular, there may be some remaining
#       JavaScript holes.  Please let me know if you find any.
#     Since ALL of your cookies are sent to this script (which then chooses
#       the relevant ones), some cookies could conceivably be dropped if
#       you accumulate a whole lot.  I haven't seen this happen yet.
#
#
#   I first wrote this in 1996 as an experiment to allow indirect browsing.
#     The original seed was a program I wrote for Rich Morin's article
#     in the June 1996 issue of Unix Review, online at
#     http://www.cfcl.com/tin/P/199606.shtml.
#
#   Confession: I didn't originally write this with the spec for HTTP
#     proxies in mind, and there are probably some violations of the protocol
#     (at least for proxies).  This whole thing is one big violation of the
#     proxy model anyway, so I hereby rationalize that the spec can be widely
#     interpreted here.  If there is demand, I can make it more conformant.
#     The HTTP client and server components should be fine; it's just the
#     special requirements for proxies that may not be followed.
#
#--------------------------------------------------------------------------

use strict ;
use Socket ;

# First block below is config variables, second block is sort-of config
#   variables, third block is persistent constants, fourth block is would-be
#   persistent constants (not set until needed), fifth block is constants for
#   JavaScript processing (mostly regular expressions), and last block is
#   variables.
# Removed $RE_JS_STRING_LITERAL to help with Perl's long-literal-string bug,
#   but can replace it later if/when that is fixed.  Added
#   $RE_JS_STRING_LITERAL_START, $RE_JS_STRING_REMAINDER_1, and
#   $RE_JS_STRING_REMAINDER_2 as part of the workaround.
use vars qw(
   $TEXT_ONLY
   $REMOVE_COOKIES  $REMOVE_SCRIPTS  $FILTER_ADS  $HIDE_REFERER
   $INSERT_ENTRY_FORM  $ALLOW_USER_CONFIG
   @ALLOWED_SERVERS  @BANNED_SERVERS  @BANNED_NETWORKS
   $NO_COOKIE_WITH_IMAGE  @ALLOWED_COOKIE_SERVERS  @BANNED_COOKIE_SERVERS
   @ALLOWED_SCRIPT_SERVERS  @BANNED_SCRIPT_SERVERS
   @BANNED_IMAGE_URL_PATTERNS  $RETURN_EMPTY_GIF
   $USER_IP_ADDRESS_TEST  $DESTINATION_SERVER_TEST
   $INSERT_HTML  $INSERT_FILE  $ANONYMIZE_INSERTION  $FORM_AFTER_INSERTION
   $INSERTION_FRAME_HEIGHT
   $RUNNING_ON_SSL_SERVER  $NOT_RUNNING_AS_NPH
   $HTTP_PROXY  $SSL_PROXY  $NO_PROXY  $PROXY_AUTH  $SSL_PROXY_AUTH
   $MINIMIZE_CACHING
   $SESSION_COOKIES_ONLY  $COOKIE_PATH_FOLLOWS_SPEC  $RESPECT_THREE_DOT_RULE
   @PROXY_GROUP
   $USER_AGENT  $USE_PASSIVE_FTP_MODE  $SHOW_FTP_WELCOME
   $PROXIFY_SCRIPTS  $ALLOW_UNPROXIFIED_SCRIPTS  $PROXIFY_COMMENTS
   $ENCODE_DECODE_BLOCK_IN_JS
   $USE_POST_ON_START  $ENCODE_URL_INPUT
   $REMOVE_TITLES  $NO_BROWSE_THROUGH_SELF  $NO_LINK_TO_START  $MAX_REQUEST_SIZE
   @TRANSMIT_HTML_IN_PARTS_URLS
   $QUIETLY_EXIT_PROXY_SESSION
   $OVERRIDE_SECURITY

   @SCRIPT_MIME_TYPES  @OTHER_TYPES_TO_REGISTER  @TYPES_TO_HANDLE
   $NON_TEXT_EXTENSIONS
   $PROXY_VERSION

   @MONTH  @WEEKDAY  %UN_MONTH
   @BANNED_NETWORK_ADDRS
   $USER_IP_ADDRESS_TEST_H  $DESTINATION_SERVER_TEST_H
   $RUNNING_ON_IIS
   @NO_PROXY
   $NO_CACHE_HEADERS