xapian-applications/omega/mbox2omega

   1 #!/usr/bin/perl -w
   2 # Copyright (C) 2004,2005,2007 Olly Betts
   3 #
   4 # This program is free software; you can redistribute it and/or
   5 # modify it under the terms of the GNU General Public License as
   6 # published by the Free Software Foundation; either version 2 of the
   7 # License, or (at your option) any later version.
   8 #
   9 # This program is distributed in the hope that it will be useful,
  10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12 # GNU General Public License for more details.
  13 #
  14 # You should have received a copy of the GNU General Public License
  15 # along with this program; if not, write to the Free Software
  16 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  17 # USA
  18
  19 use strict;
  20
  21 if (grep {$_ eq '--help'} @ARGV) {
  22     die <<EOT;
  23 Syntax: $0 [MBOX...]
  24
  25 Run this script with one or more mailbox filenames on the command line (or
  26 pipe a mailbox in on stdin).  It produces output suitable for feeding to
  27 scriptindex using the mbox2omega.script index script.  For example:
  28
  29   $0 *.mbox | scriptindex /path/to/database mbox2omega.script
  30
  31 The index script tells scriptindex how to process the dump file, so you can
  32 customise that to change how the indexing is done.
  33
  34 Note that this script is mainly intended as a simple example of how you might
  35 generate scriptindex dump files from a data source, and its handling of mail
  36 messages is quite primitive - e.g. it doesn't handle MIME or character sets.
  37 EOT
  38 }
  39
  40 my $hdr = 1;
  41 line: while (<>) {
  42     if ($hdr) {
  43         chomp;
  44         while (1) {
  45             if (/^$/) {
  46                 print "body=\n";
  47                 $hdr = 0;
  48                 next line;
  49             }
  50             # Handle continuation lines
  51             my $line = $_;
  52             while (<>) {
  53                 chomp;
  54                 last unless /^[ \t]/;
  55                 $line .= $_;
  56             }
  57             if ($line =~ s/^Message-ID:\s*<?(.*?)>?\s*$/$1/i) {
  58                 print "id=$line\n" if length $line;
  59             } elsif ($line =~ s/^Subject:\s*(.*?)\s*$/$1/i) {
  60                 print "title=$line\n" if length $line;
  61             }
  62         }
  63     }
  64
  65     if (/^From /) {
  66         print "\n";
  67         $hdr = 1;
  68         next;
  69     }
  70     if ($_ !~ /^\s+$/) {
  71         print "=$_";
  72     }
  73 }