2
# -*- Mode: perl; indent-tabs-mode: nil; c-basic-offset: 4 -*-
5
# The Intltool Message Extractor
7
# Copyright (C) 2000-2001 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 ($TYPE_ARG =~ /^gettext\/(.*)/) {
125
## Sub for printing release information
127
print "${PROGRAM} (${PACKAGE}) $VERSION\n";
128
print "Copyright (C) 2000 Free Software Foundation, Inc.\n";
129
print "Written by Kenneth Christiansen, 2000.\n\n";
130
print "This is free software; see the source for copying conditions. There is NO\n";
131
print "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n";
135
## Sub for printing usage information
137
print "Usage: ${PROGRAM} [FILENAME] [OPTIONS] ...\n";
138
print "Generates a header file from an xml source file.\n\nGrabs all strings ";
139
print "between <_translatable_node> and it's end tag,\nwhere tag are all allowed ";
140
print "xml tags. Read the docs for more info.\n\n";
141
print " -v, --version shows the version\n";
142
print " -h, --help shows this help page\n";
143
print " -q, --quiet quiet mode\n";
144
print "\nReport bugs to <kenneth\@gnu.org>.\n";
148
## Sub for printing error messages
150
print "Try `${PROGRAM} --help' for more information.\n";
155
print "Generating C format header file for translation.\n";
163
open OUT, ">$OUTFILE";
167
print "Wrote $OUTFILE\n" unless $QUIET_ARG;
175
local $/; #slurp mode
176
open (IN, "<$FILE") || die "can't open $FILE: $!";
180
&type_ini if $gettext_type eq "ini";
181
&type_keys if $gettext_type eq "keys";
182
&type_xml if $gettext_type eq "xml";
183
&type_glade if $gettext_type eq "glade";
184
&type_scheme if $gettext_type eq "scheme";
185
&type_schemas if $gettext_type eq "schemas";
186
&type_rfc822deb if $gettext_type eq "rfc822deb";
189
sub entity_decode_minimal
215
return '\"' if $_ eq '"';
216
return '\n' if $_ eq "\n";
217
return '\\' if $_ eq '\\';
225
return join "", map &escape_char, split //, $string;
229
### For generic translatable desktop files ###
230
while ($input =~ /^_.*=(.*)$/mg) {
236
### For generic translatable mime/keys files ###
237
while ($input =~ /^\s*_\w+=(.*)$/mg) {
243
### For generic translatable XML files ###
245
while ($input =~ /\s_$w+=\"([^"]+)\"/sg) { # "
246
$messages{entity_decode_minimal($1)} = [];
249
while ($input =~ /<_($w+)(?: xml:space="($w+)")?>(.+?)<\/_\1>/sg) {
251
if (!defined($2) || $2 ne "preserve") {
256
$messages{entity_decode_minimal($_)} = [];
261
### For schemas XML files ###
263
# FIXME: We should handle escaped < (less than)
265
<locale\ name="C">\s*
266
(<default>\s*(.*?)\s*<\/default>\s*)?
267
(<short>\s*(.*?)\s*<\/short>\s*)?
268
(<long>\s*(.*?)\s*<\/long>\s*)?
271
my @totranslate = ($2,$4,$6);
272
foreach (@totranslate) {
275
$messages{entity_decode_minimal($_)} = [];
281
### For rfc822-style Debian configuration files ###
283
while ($input =~ /(?:^|\n)_[^:]+:\s*(.*?)(?=\n\S|$)/sg) {
284
my @str_list = rfc822deb_split($1);
285
for my $str (@str_list) {
286
# As rfc822deb is for configuration files, duplicates
287
# should never happen. Developers must use the
288
# [] construct to make msgid unique, see also intltool-merge
289
print STDERR "Warning: msgid multiply defined:\n $str\n"
290
if defined($messages{$str});
291
$messages{$str} = [];
296
sub rfc822deb_split {
297
# Debian defines a special way to deal with rfc822-style files:
298
# when a value contain newlines, it consists of
299
# 1. a short form (first line)
300
# 2. a long description, all lines begin with a space,
301
# and paragraphs are separated by a single dot on a line
302
# This routine returns an array of all paragraphs, and reformat
306
return ($text) if $text !~ /\n/;
308
$text =~ s/([^\n]*)\n//;
311
for my $line (split (/\n/, $text)) {
314
if ($line =~ /^\.$/) {
319
} elsif ($line =~ /^\s/) {
320
# Line which must not be reformatted
321
$str .= "\n" if length ($str) && $str !~ /\n$/;
324
# Continuation line, remove newline
325
$str .= " " if length ($str) && $str !~ /[\n ]$/;
330
push(@list, $str) if length ($str);
335
### For translatable Glade XML files ###
337
my $tags = "label|title|text|format|copyright|comments|preview_text|tooltip|message";
339
while ($input =~ /<($tags)>([^<]+)<\/($tags)>/sg) {
340
# Glade sometimes uses tags that normally mark translatable things for
341
# little bits of non-translatable content. We work around this by not
342
# translating strings that only includes something like label4 or window1.
343
$messages{entity_decode($2)} = [] unless $2 =~ /^(window|label)[0-9]+$/;
346
while ($input =~ /<items>(..[^<]*)<\/items>/sg) {
347
for my $item (split (/\n/, $1)) {
348
$messages{entity_decode($item)} = [];
352
## handle new glade files
353
while ($input =~ /<(property|atkproperty)\s+[^>]*translatable\s*=\s*"yes"[^>]*>([^<]+)<\/\1>/sg) {
354
$messages{entity_decode($2)} = [] unless $2 =~ /^(window|label)[0-9]+$/;
356
while ($input =~ /<atkaction\s+action_name="([^>]*)"\s+description="([^>]+)"\/>/sg) {
357
$messages{entity_decode_minimal($2)} = [];
362
while ($input =~ /_\(?"((?:[^"\\]+|\\.)*)"\)?/sg) {
368
for my $message (sort keys %messages) {
369
print OUT "/* xgettext:no-c-format */\n" if $message =~ /%/;
371
my @lines = split (/\n/, $message, -1);
372
for (my $n = 0; $n < @lines; $n++) {
374
print OUT "char *s = N_(\"";
379
print OUT escape($lines[$n]);
381
if ($n < @lines - 1) {