2 # -*- Mode: perl; indent-tabs-mode: nil; c-basic-offset: 4 -*-
5 # The Intltool Message Extractor
7 # Copyright (C) 2000-2001, 2003 Free Software Foundation.
9 # Intltool is free software; you can redistribute it and/or
10 # modify it under the terms of the GNU General Public License as
11 # published by the Free Software Foundation; either version 2 of the
12 # License, or (at your option) any later version.
14 # Intltool is distributed in the hope that it will be useful,
15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 # General Public License for more details.
19 # You should have received a copy of the GNU General Public License
20 # along with this program; if not, write to the Free Software
21 # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
23 # As a special exception to the GNU General Public License, if you
24 # distribute this file as part of a program that contains a
25 # configuration script generated by Autoconf, you may include it under
26 # the same distribution terms that you use for the rest of that program.
28 # Authors: Kenneth Christiansen <kenneth@gnu.org>
29 # Darin Adler <darin@bentspoon.com>
32 ## Release information
33 my $PROGRAM = "intltool-extract";
34 my $PACKAGE = "intltool";
42 ## Scalars used by the option stuff
46 my $VERSION_ARG = "0";
53 my $gettext_type = "";
57 ## Use this instead of \w for XML files to handle more possible characters.
58 my $w = "[-A-Za-z0-9._:]";
65 "type=s" => \$TYPE_ARG,
66 "local|l" => \$LOCAL_ARG,
67 "help|h" => \$HELP_ARG,
68 "version|v" => \$VERSION_ARG,
69 "update" => \$UPDATE_ARG,
70 "quiet|q" => \$QUIET_ARG,
77 ## This section will check for the different options.
79 sub split_on_argument {
87 } elsif ($LOCAL_ARG) {
91 } elsif ($UPDATE_ARG) {
108 $OUTFILE = "$FILE.h";
112 $OUTFILE = fileparse($FILE, ());
114 system("mkdir tmp/");
116 $OUTFILE = "./tmp/$OUTFILE.h"
120 if ($TYPE_ARG =~ /^gettext\/(.*)/) {
125 ## Sub for printing release information
128 ${PROGRAM} (${PACKAGE}) $VERSION
129 Copyright (C) 2000, 2003 Free Software Foundation, Inc.
130 Written by Kenneth Christiansen, 2000.
132 This is free software; see the source for copying conditions. There is NO
133 warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
138 ## Sub for printing usage information
141 Usage: ${PROGRAM} [OPTION]... [FILENAME]
142 Generates a header file from an XML source file.
144 It grabs all strings between <_translatable_node> and its end tag in
145 XML files. Read manpage (man ${PROGRAM}) for more info.
147 --type=TYPE Specify the file type of FILENAME. Currently supports:
148 "gettext/glade", "gettext/ini", "gettext/keys"
149 "gettext/rfc822deb", "gettext/schemas",
150 "gettext/scheme", "gettext/xml"
151 -l, --local Writes output into current working directory
152 (conflicts with --update)
153 --update Writes output into the same directory the source file
154 reside (conflicts with --local)
155 -v, --version Output version information and exit
156 -h, --help Display this help and exit
157 -q, --quiet Quiet mode
159 Report bugs to http://bugzilla.gnome.org/ (product name "$PACKAGE")
160 or send email to <xml-i18n-tools\@gnome.org>.
165 ## Sub for printing error messages
167 print STDERR "Try `${PROGRAM} --help' for more information.\n";
172 print "Generating C format header file for translation.\n" unless $QUIET_ARG;
180 open OUT, ">$OUTFILE";
184 print "Wrote $OUTFILE\n" unless $QUIET_ARG;
192 local $/; #slurp mode
193 open (IN, "<$FILE") || die "can't open $FILE: $!";
197 &type_ini if $gettext_type eq "ini";
198 &type_keys if $gettext_type eq "keys";
199 &type_xml if $gettext_type eq "xml";
200 &type_glade if $gettext_type eq "glade";
201 &type_scheme if $gettext_type eq "scheme";
202 &type_schemas if $gettext_type eq "schemas";
203 &type_rfc822deb if $gettext_type eq "rfc822deb";
206 sub entity_decode_minimal
232 return '\"' if $_ eq '"';
233 return '\n' if $_ eq "\n";
234 return '\\' if $_ eq '\\';
242 return join "", map &escape_char, split //, $string;
246 ### For generic translatable desktop files ###
247 while ($input =~ /^_.*=(.*)$/mg) {
253 ### For generic translatable mime/keys files ###
254 while ($input =~ /^\s*_\w+=(.*)$/mg) {
260 ### For generic translatable XML files ###
262 while ($input =~ /\s_$w+\s*=\s*\"([^"]+)\"/sg) { # "
263 $messages{entity_decode_minimal($1)} = [];
266 while ($input =~ /<_($w+)(?: xml:space="($w+)")?>(.+?)<\/_\1>/sg) {
268 if (!defined($2) || $2 ne "preserve") {
273 $messages{entity_decode_minimal($_)} = [];
278 ### For schemas XML files ###
280 # FIXME: We should handle escaped < (less than)
282 <locale\ name="C">\s*
283 (<default>\s*(.*?)\s*<\/default>\s*)?
284 (<short>\s*(.*?)\s*<\/short>\s*)?
285 (<long>\s*(.*?)\s*<\/long>\s*)?
288 my @totranslate = ($2,$4,$6);
289 foreach (@totranslate) {
292 $messages{entity_decode_minimal($_)} = [];
298 ### For rfc822-style Debian configuration files ###
300 while ($input =~ /(?:^|\n)_[^:]+:\s*(.*?)(?=\n\S|$)/sg) {
301 my @str_list = rfc822deb_split($1);
302 for my $str (@str_list) {
303 # As rfc822deb is for configuration files, duplicates
304 # should never happen. Developers must use the
305 # [] construct to make msgid unique, see also intltool-merge
306 print STDERR "Warning: msgid multiply defined:\n $str\n"
307 if defined($messages{$str});
308 $messages{$str} = [];
313 sub rfc822deb_split {
314 # Debian defines a special way to deal with rfc822-style files:
315 # when a value contain newlines, it consists of
316 # 1. a short form (first line)
317 # 2. a long description, all lines begin with a space,
318 # and paragraphs are separated by a single dot on a line
319 # This routine returns an array of all paragraphs, and reformat
323 return ($text) if $text !~ /\n/;
325 $text =~ s/([^\n]*)\n//;
328 for my $line (split (/\n/, $text)) {
331 if ($line =~ /^\.$/) {
336 } elsif ($line =~ /^\s/) {
337 # Line which must not be reformatted
338 $str .= "\n" if length ($str) && $str !~ /\n$/;
341 # Continuation line, remove newline
342 $str .= " " if length ($str) && $str !~ /[\n ]$/;
347 push(@list, $str) if length ($str);
352 ### For translatable Glade XML files ###
354 my $tags = "label|title|text|format|copyright|comments|preview_text|tooltip|message";
356 while ($input =~ /<($tags)>([^<]+)<\/($tags)>/sg) {
357 # Glade sometimes uses tags that normally mark translatable things for
358 # little bits of non-translatable content. We work around this by not
359 # translating strings that only includes something like label4 or window1.
360 $messages{entity_decode($2)} = [] unless $2 =~ /^(window|label)[0-9]+$/;
363 while ($input =~ /<items>(..[^<]*)<\/items>/sg) {
364 for my $item (split (/\n/, $1)) {
365 $messages{entity_decode($item)} = [];
369 ## handle new glade files
370 while ($input =~ /<(property|atkproperty)\s+[^>]*translatable\s*=\s*"yes"[^>]*>([^<]+)<\/\1>/sg) {
371 $messages{entity_decode($2)} = [] unless $2 =~ /^(window|label)[0-9]+$/;
373 while ($input =~ /<atkaction\s+action_name="([^>]*)"\s+description="([^>]+)"\/>/sg) {
374 $messages{entity_decode_minimal($2)} = [];
379 while ($input =~ /_\w*\(?"((?:[^"\\]+|\\.)*)"\)?/sg) {
385 for my $message (sort keys %messages) {
386 print OUT "/* xgettext:no-c-format */\n" if $message =~ /%/;
388 my @lines = split (/\n/, $message, -1);
389 for (my $n = 0; $n < @lines; $n++) {
391 print OUT "char *s = N_(\"";
396 print OUT escape($lines[$n]);
398 if ($n < @lines - 1) {