2 # Convert Translation.gz files into Sleepycat db files for efficient usage of
5 # Copyright (C) 2006 Jeroen van Wolffelaar <jeroen@wolffelaar.nl>
6 # Copyright (C) 2007 Frank Lichtenheld <frank@lichtenheld.de>
7 # This program is free software; you can redistribute it and/or modify
8 # it under the terms of the GNU General Public License as published by
9 # the Free Software Foundation; either version 2 of the License, or
10 # (at your option) any later version.
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.
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 Street, Fifth Floor, Boston, MA 02110-1301 USA.
27 # max. distinct results for a given package postfix
28 my $MAX_PACKAGE_POSTFIXES = 100;
36 use Lingua::Stem v0.82;
38 use Packages::Config qw( $TOPDIR $DBDIR @DDTP_LANGUAGES );
39 &Packages::Config::init( './' );
40 my %descriptions = ();
44 -d $DBDIR || mkpath( $DBDIR );
46 my $fixja = Text::Iconv->new("EUC-JP", "UTF-8");
48 # FIXME: one database per dist
49 # http://lists.debian.org/4E42E104.90201@deb-support.de
50 # FIXME: unhardcode dists name
51 my @dists = ('sid', 'wheezy', 'squeeze', 'lenny');
53 foreach my $lang (@DDTP_LANGUAGES) {
54 (my $locale = $lang) =~ s/^([a-z]{2})-([a-z]{2})$/"$1_".uc($2)/e;
55 print "Reading Translations for $lang ($locale)...";
57 foreach my $dist (@dists) {
58 open PKG, "bzcat $TOPDIR/archive/*/$dist/*/i18n/Translation-$locale.bz2|";
65 while (/^(\S+):\s*(.*)\s*$/mg) {
66 my ($key, $value) = ($1, $2);
67 $value =~ s/\377/\n /g;
68 $key =~ tr [A-Z] [a-z];
71 # Skip double descriptions
72 next if exists($descriptions{$data{"description-md5"}}{$lang});
73 # some weirdnesses in the files
74 next unless defined $data{"description-".lc($locale)};
76 my $fixed = $fixja->convert($data{"description-ja"});
77 $data{"description-ja"} = $fixed if $fixed;
79 $descriptions{$data{"description-md5"}}{$lang} =
80 $data{"description-".lc($locale)};
88 print "Writing database (".scalar(keys %descriptions)." unique descriptions)...\n";
90 tie %descriptions_db, "DB_File", "$DBDIR/descriptions_translated.db.new",
91 O_RDWR|O_CREAT, 0666, $DB_BTREE
92 or die "Error creating DB: $!";
93 while (my ($md5, $v) = each(%descriptions)) {
95 while (my ($lang, $desc) = each %$v) {
96 unless ($lang && $desc) {
97 warn "MD5: $md5 LANG: $lang DESC: $desc\n";
100 $str .= "$lang\001$desc\000";
103 $descriptions_db{$md5} = $str;
105 untie %descriptions_db;
107 rename("$DBDIR/descriptions_translated.db.new",
108 "$DBDIR/descriptions_translated.db");