xapian-applications/omega/htdig2omega

   1 #!/usr/bin/perl -w
   2 # htdig2omega - dump an htdig database into a form suitable for indexing
   3 # into a Xapian database using scriptindex.
   4 #
   5 # Copyright 2002,2003,2004 Olly Betts
   6 #
   7 # This program is free software; you can redistribute it and/or
   8 # modify it under the terms of the GNU General Public License as
   9 # published by the Free Software Foundation; either version 2 of the
  10 # License, or (at your option) any later version.
  11 #
  12 # This program is distributed in the hope that it will be useful,
  13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with this program; if not, write to the Free Software
  19 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  20 # USA
  21
  22 use strict;
  23
  24 $#ARGV == 0 or die "Syntax: $0 HTDIGDIR\nTypical usage: $0 HTDIGDIR|scriptindex XAPIANDB htdig2omega.script\n";
  25
  26 my $dir = shift @ARGV;
  27
  28 # dump the document database (-w suppresses dumping the word database)
  29 system "htdump", "-w", $dir;
  30 open DOCS, "$dir/db.docs" or die $!;
  31 while (<DOCS>) {
  32     my ($id, @x) = split /\t/;
  33     my %f;
  34     for (@x) {
  35         unless (s/^([a-zA-Z])://) {
  36             print STDERR "Bad field: $_\n";
  37             next;
  38         }
  39         $f{$1} = $_;
  40     }
  41     print "url=$f{'u'}\ncaption=$f{'t'}\nlastmod=$f{'m'}\nsize=$f{'s'}\ntext=$f{'H'}\nmetadesc=$f{'h'}\n\n";
  42 }
  43 close DOCS;