src/store/id_rewriters/file/storeid_file_rewrite.pl.in

   1 #!@PERL@
   2
   3 use strict;
   4 use warnings;
   5 use Pod::Usage;
   6
   7 =pod
   8
   9 =head1 NAME
  10
  11  storeid_file_rewrite - File based Store-ID helper for Squid
  12
  13 =head1 SYNOPSIS
  14
  15  storeid_file_rewrite filepath
  16
  17 =head1 DESCRIPTION
  18
  19 This program acts as a store_id helper program, rewriting URLs passed
  20 by Squid into storage-ids that can be used to achieve better caching
  21 for websites that use different URLs for the same content.
  22
  23 It takes a text file with two tab separated columns.
  24 Column 1: Regular expression to match against the URL
  25 Column 2: Rewrite rule to generate a Store-ID
  26 Eg:
  27 ^http:\/\/[^\.]+\.dl\.sourceforge\.net\/(.*)    http://dl.sourceforge.net.squid.internal/$1
  28
  29 Rewrite rules are matched in the same order as they appear in the rules file.
  30 So for best performance, sort it in order of frequency of occurrence.
  31
  32 This program will automatically detect the existence of a concurrency channel-ID and adjust appropriately.
  33 It may be used with any value 0 or above for the store_id_children concurrency= parameter.
  34
  35 =head1 OPTIONS
  36
  37 The only command line parameter this helper takes is the regex rules file name.
  38
  39 =head1 AUTHOR
  40
  41 This program and documentation was written by I<Alan Mizrahi <alan@mizrahi.com.ve>>
  42
  43 Based on prior work by I<Eliezer Croitoru <eliezer@ngtech.co.il>>
  44
  45 =head1 COPYRIGHT
  46
  47  * Copyright (C) 1996-2021 The Squid Software Foundation and contributors
  48  *
  49  * Squid software is distributed under GPLv2+ license and includes
  50  * contributions from numerous individuals and organizations.
  51  * Please see the COPYING and CONTRIBUTORS files for details.
  52
  53  Copyright (C) 2013 Alan Mizrahi <alan@mizrahi.com.ve>
  54  Based on code from Eliezer Croitoru <eliezer@ngtech.co.il>
  55
  56  This program is free software; you can redistribute it and/or modify
  57  it under the terms of the GNU General Public License as published by
  58  the Free Software Foundation; either version 2 of the License, or
  59  (at your option) any later version.
  60
  61  This program is distributed in the hope that it will be useful,
  62  but WITHOUT ANY WARRANTY; without even the implied warranty of
  63  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  64  GNU General Public License for more details.
  65
  66  You should have received a copy of the GNU General Public License
  67  along with this program; if not, write to the Free Software
  68  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307, USA.
  69
  70 =head1 QUESTIONS
  71
  72 Questions on the usage of this program can be sent to the I<Squid Users mailing list <squid-users@lists.squid-cache.org>>
  73
  74 =head1 REPORTING BUGS
  75
  76 Bug reports need to be made in English.
  77 See http://wiki.squid-cache.org/SquidFaq/BugReporting for details of what you need to include with your bug report.
  78
  79 Report bugs or bug fixes using http://bugs.squid-cache.org/
  80
  81 Report serious security bugs to I<Squid Bugs <squid-bugs@lists.squid-cache.org>>
  82
  83 Report ideas for new improvements to the I<Squid Developers mailing list <squid-dev@lists.squid-cache.org>>
  84
  85 =head1 SEE ALSO
  86
  87 squid (8), GPL (7),
  88
  89 The Squid wiki http://wiki.squid-cache.org/Features/StoreID
  90
  91 The Squid Configuration Manual http://www.squid-cache.org/Doc/config/
  92
  93 =cut
  94
  95 my @rules; # array of [regex, replacement string]
  96
  97 die "Usage: $0 <rewrite-file>\n" unless $#ARGV == 0;
  98
  99 # read config file
 100 open RULES, $ARGV[0] or die "Error opening $ARGV[0]: $!";
 101 while (<RULES>) {
 102     chomp;
 103     next if /^\s*#?$/;
 104     if (/^\s*([^\t]+?)\s*\t+\s*([^\t]+?)\s*$/) {
 105         push(@rules, [qr/$1/, $2]);
 106     } else {
 107         print STDERR "$0: Parse error in $ARGV[0] (line $.)\n";
 108     }
 109 }
 110 close RULES;
 111
 112 $|=1;
 113 # read urls from squid and do the replacement
 114 URL: while (<STDIN>) {
 115     chomp;
 116     last if $_ eq 'quit';
 117
 118     my $channel = "";
 119     if (s/^(\d+\s+)//o) {
 120         $channel = $1;
 121     }
 122
 123     foreach my $rule (@rules) {
 124         if (my @match = /$rule->[0]/) {
 125             $_ = $rule->[1];
 126
 127             for (my $i=1; $i<=scalar(@match); $i++) {
 128                 s/\$$i/$match[$i-1]/g;
 129             }
 130             print $channel, "OK store-id=$_\n";
 131             next URL;
 132         }
 133     }
 134     print $channel, "ERR\n";
 135 }