/usr/bin/dl10n-html is in dl10n 3.00.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | #!/usr/bin/perl -w
eval 'exec /usr/bin/perl -w -S $0 ${1+"$@"}'
if 0; # not running under some shell
use strict;
use utf8;
=head1 NAME
dl10n-spider -- crawl translator mailing lists (and BTS) for status updates
=head1 SYNOPSIS
dl10n-spider [options] lang+
=head1 DESCRIPTION
This script parses the debian-l10n-E<lt>languageE<gt> mailing list
archives. It looks for emails which title follow a specific format
indicating what the author intend to translate, or the current status of
his work on this translation.
Those informations are saved to a dl10n database which can then be used to
build a l10n coordination page or any other useless statistics.
=cut
use Getopt::Long; #to parse the args
use LWP::UserAgent;
use Debian::L10n::Html;
use File::Path;
use POSIX qw(strftime);
my $progname = $0;
$progname = $1 if $progname =~ m,([^/])+$,;
my $VERSION = "4.0"; # External Version Number
my $BANNER = "Debian l10n infrastructure -- mailing list spider v$VERSION"; # Version Banner - text form
my $cmdline_year = undef;
my $cmdline_month = undef;
my $cmdline_msg = undef;
my $cmdline_file = undef;
my %Language = (
ar => 'arabic',
ca => 'catalan',
cs => 'czech',
de => 'german',
en => 'english',
es => 'spanish',
fr => 'french',
gl => 'galician',
nl => 'dutch',
# pt => 'portuguese',
pt_BR => 'brazilian',
ro => 'romanian',
ru => 'russian',
sk => 'slovak',
sv => 'swedish',
tr => 'turkish',
all => 'all',
);
=head1 Command line option parsing
=over
=item General options:
=over
=item -h, --help
display short help text
=item -V, --version
display version and exit
=back
=item Begin point of the crawling:
=over
=item --year=YYYY
=item --month=MM
=item --message=msg
=back
if not specified, will crawl for new messages.
=item Database to fill:
=over
=item --sdb=STATUS_FILE
use STATUS_FILE as status file (instead of $STATUS_FILE)
=back
=back
=cut
# This is put into a block to avoid main namespace pollution
{
sub syntax_msg {
my $message = shift;
if (defined $message) {
print "$progname: $message\n";
} else {
print "$BANNER\n";
}
print <<EOF
Syntax: $0 [options] [lang]+
General options:
-h, --help display short help text
-V, --version display version and exit
Database to fill:
--sdb=STATUS_FILE use STATUS_FILE as status file
EOF
;
if (defined $message) {
exit 1;
} else {
exit 0;
}
}
# Display Version Banner
# Options: -V|--version, --print-version
sub banner {
if ($_[0] eq 'print-version') {
print "$VERSION\n";
} else {
print "$BANNER\n";
}
exit 0;
}
# Hash used to process commandline options
my %opthash = (
# ------------------ general options
"help|h" => \&syntax_msg,
"version|V" => \&banner,
# ------------------ configuration options
"sdb=s" => \$cmdline_file,
);
# init commandline parser
Getopt::Long::config('bundling', 'no_getopt_compat', 'no_auto_abbrev');
# process commandline options
GetOptions(%opthash)
or syntax_msg("error parsing options");
}
my $lang = $ARGV[0];
my $language = $Language{$lang};
Html::html($cmdline_file, $lang);
{
my $head = <<EOF
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="$lang" lang="$lang">
<head>
<title>Coordination of debian-l10n-$language</title>
<link href="../l10n.css" rel="stylesheet" />
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-15" />
<meta name="Copyright" content="Copyright (C) 2004 Nicolas Bertolissio" />
</head>
<body>
<p style="text-align:center;">
<a href="http://www.debian.org/"><img src="http://www.debian.org/logos/openlogo-nd-50.png" style="border:0; width:50px; height:61px;" alt="" /></a>
<a href="http://www.debian.org/"><img src="http://www.debian.org/Pics/debian.jpg" style="border:0; width:179px; height:61px;" alt="Debian Project" /></a>
</p>
<h1>Coordination of debian-l10n-$language</h1>
<p>
This page is made to aid the coordination of translating debian related text to
$language. As documented <a href='http://i18n.debian.net/debian-l10n/docs/robot/pseudo-urls.html'>here</a>, translators and
reviewers use pseudo-urls in the subject of e-mails to the debian-l10n-$language
list for coordination.
</p>
<p>
A program parses these pseudo-urls and collects the relevant data, which are
then displayed below.
</p>
EOF
;
my $date = strftime('%a, %d %b %Y %H:%M:%S %z', gmtime);
my $tail = <<EOF
<hr />
<p>
<small>Comments:
<a href='mailto:debian-l10n-devel\@lists.alioth.debian.org'>Debian L10N
Development Team</a></small>
</p>
<p>
<small>Generated on $date</small>
</p>
</body>
</html>
EOF
;
opendir D, './include' or die "Cannot open .: $!";
my @files = readdir D;
closedir D;
mkpath ("html/include", 02775) or die "Cannot create include directory\n" unless (-d "html/include");
mkpath ("html/$Language{$lang}", 02775) or die "Cannot create $Language{$lang} directory\n" unless (-d "html/$Language{$lang}");
foreach (grep (/^$lang\./, @files)) {
next unless /\.inc$/;
s/\.inc$//;
open I, "<include/$_.inc" or die "Cannot open $_.inc: $!";
my @inc = <I>;
close I;
open I, ">html/include/$_.inc" or die "Cannot open $_.inc $_";
print I @inc;
close I;
open H, ">html/$Language{$lang}/$_.html" or die "Cannot open $_.html: $_";
print H $head;
print H @inc;
print H $tail;
close H;
}
}
=head1 LICENSE
This program is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation; either version 2 of the License, or (at your option) any later
version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
PARTICULAR PURPOSE. See the GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation, Inc.,
59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
=head1 COPYRIGHT (C)
2003,2004 Tim Dijkstra
2004 Nicolas Bertolissio
2004 Martin Quinson
=cut
1;
|