-
Notifications
You must be signed in to change notification settings - Fork 2
/
intltool-merge.in
1356 lines (1149 loc) · 34.4 KB
/
intltool-merge.in
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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!@INTLTOOL_PERL@ -w
# -*- Mode: perl; indent-tabs-mode: nil; c-basic-offset: 4 -*-
#
# The Intltool Message Merger
#
# Copyright (C) 2000, 2003 Free Software Foundation.
# Copyright (C) 2000, 2001 Eazel, Inc
#
# Intltool is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# version 2 published by the Free Software Foundation.
#
# Intltool 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., 675 Mass Ave, Cambridge, MA 02139, USA.
#
# As a special exception to the GNU General Public License, if you
# distribute this file as part of a program that contains a
# configuration script generated by Autoconf, you may include it under
# the same distribution terms that you use for the rest of that program.
#
# Authors: Maciej Stachowiak <mjs@noisehavoc.org>
# Kenneth Christiansen <kenneth@gnu.org>
# Darin Adler <darin@bentspoon.com>
#
# Proper XML UTF-8'ification written by Cyrille Chepelov <chepelov@calixo.net>
#
## Release information
my $PROGRAM = "intltool-merge";
my $PACKAGE = "intltool";
my $VERSION = "0.35.0";
## Loaded modules
use strict;
use Getopt::Long;
use Text::Wrap;
use File::Basename;
my $must_end_tag = -1;
my $last_depth = -1;
my $translation_depth = -1;
my @tag_stack = ();
my @entered_tag = ();
my @translation_strings = ();
my $leading_space = "";
## Scalars used by the option stuff
my $HELP_ARG = 0;
my $VERSION_ARG = 0;
my $BA_STYLE_ARG = 0;
my $XML_STYLE_ARG = 0;
my $KEYS_STYLE_ARG = 0;
my $DESKTOP_STYLE_ARG = 0;
my $SCHEMAS_STYLE_ARG = 0;
my $RFC822DEB_STYLE_ARG = 0;
my $QUIET_ARG = 0;
my $PASS_THROUGH_ARG = 0;
my $UTF8_ARG = 0;
my $MULTIPLE_OUTPUT = 0;
my $cache_file;
## Handle options
GetOptions
(
"help" => \$HELP_ARG,
"version" => \$VERSION_ARG,
"quiet|q" => \$QUIET_ARG,
"oaf-style|o" => \$BA_STYLE_ARG, ## for compatibility
"ba-style|b" => \$BA_STYLE_ARG,
"xml-style|x" => \$XML_STYLE_ARG,
"keys-style|k" => \$KEYS_STYLE_ARG,
"desktop-style|d" => \$DESKTOP_STYLE_ARG,
"schemas-style|s" => \$SCHEMAS_STYLE_ARG,
"rfc822deb-style|r" => \$RFC822DEB_STYLE_ARG,
"pass-through|p" => \$PASS_THROUGH_ARG,
"utf8|u" => \$UTF8_ARG,
"multiple-output|m" => \$MULTIPLE_OUTPUT,
"cache|c=s" => \$cache_file
) or &error;
my $PO_DIR;
my $FILE;
my $OUTFILE;
my %po_files_by_lang = ();
my %translations = ();
my $iconv = $ENV{"ICONV"} || $ENV{"INTLTOOL_ICONV"} || "@INTLTOOL_ICONV@";
my $devnull = ($^O eq 'MSWin32' ? 'NUL:' : '/dev/null');
# Use this instead of \w for XML files to handle more possible characters.
my $w = "[-A-Za-z0-9._:]";
# XML quoted string contents
my $q = "[^\\\"]*";
## Check for options.
if ($VERSION_ARG)
{
&print_version;
}
elsif ($HELP_ARG)
{
&print_help;
}
elsif ($BA_STYLE_ARG && @ARGV > 2)
{
&utf8_sanity_check;
&preparation;
&print_message;
&ba_merge_translations;
&finalize;
}
elsif ($XML_STYLE_ARG && @ARGV > 2)
{
&utf8_sanity_check;
&preparation;
&print_message;
&xml_merge_output;
&finalize;
}
elsif ($KEYS_STYLE_ARG && @ARGV > 2)
{
&utf8_sanity_check;
&preparation;
&print_message;
&keys_merge_translations;
&finalize;
}
elsif ($DESKTOP_STYLE_ARG && @ARGV > 2)
{
&utf8_sanity_check;
&preparation;
&print_message;
&desktop_merge_translations;
&finalize;
}
elsif ($SCHEMAS_STYLE_ARG && @ARGV > 2)
{
&utf8_sanity_check;
&preparation;
&print_message;
&schemas_merge_translations;
&finalize;
}
elsif ($RFC822DEB_STYLE_ARG && @ARGV > 2)
{
&preparation;
&print_message;
&rfc822deb_merge_translations;
&finalize;
}
else
{
&print_help;
}
exit;
## Sub for printing release information
sub print_version
{
print <<_EOF_;
${PROGRAM} (${PACKAGE}) ${VERSION}
Written by Maciej Stachowiak, Darin Adler and Kenneth Christiansen.
Copyright (C) 2000-2003 Free Software Foundation, Inc.
Copyright (C) 2000-2001 Eazel, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
_EOF_
exit;
}
## Sub for printing usage information
sub print_help
{
print <<_EOF_;
Usage: ${PROGRAM} [OPTION]... PO_DIRECTORY FILENAME OUTPUT_FILE
Generates an output file that includes some localized attributes from an
untranslated source file.
Mandatory options: (exactly one must be specified)
-b, --ba-style includes translations in the bonobo-activation style
-d, --desktop-style includes translations in the desktop style
-k, --keys-style includes translations in the keys style
-s, --schemas-style includes translations in the schemas style
-r, --rfc822deb-style includes translations in the RFC822 style
-x, --xml-style includes translations in the standard xml style
Other options:
-u, --utf8 convert all strings to UTF-8 before merging
(default for everything except RFC822 style)
-p, --pass-through deprecated, does nothing and issues a warning
-m, --multiple-output output one localized file per locale, instead of
a single file containing all localized elements
-c, --cache=FILE specify cache file name
(usually \$top_builddir/po/.intltool-merge-cache)
-q, --quiet suppress most messages
--help display this help and exit
--version output version information and exit
Report bugs to http://bugzilla.gnome.org/ (product name "$PACKAGE")
or send email to <xml-i18n-tools\@gnome.org>.
_EOF_
exit;
}
## Sub for printing error messages
sub print_error
{
print STDERR "Try `${PROGRAM} --help' for more information.\n";
exit;
}
sub print_message
{
print "Merging translations into $OUTFILE.\n" unless $QUIET_ARG;
}
sub preparation
{
$PO_DIR = $ARGV[0];
$FILE = $ARGV[1];
$OUTFILE = $ARGV[2];
&gather_po_files;
&get_translation_database;
}
# General-purpose code for looking up translations in .po files
sub po_file2lang
{
my ($tmp) = @_;
$tmp =~ s/^.*\/(.*)\.po$/$1/;
return $tmp;
}
sub gather_po_files
{
for my $po_file (glob "$PO_DIR/*.po") {
$po_files_by_lang{po_file2lang($po_file)} = $po_file;
}
}
sub get_local_charset
{
my ($encoding) = @_;
my $alias_file = $ENV{"G_CHARSET_ALIAS"} || "@INTLTOOL_LIBDIR@/charset.alias";
# seek character encoding aliases in charset.alias (glib)
if (open CHARSET_ALIAS, $alias_file)
{
while (<CHARSET_ALIAS>)
{
next if /^\#/;
return $1 if (/^\s*([-._a-zA-Z0-9]+)\s+$encoding\b/i)
}
close CHARSET_ALIAS;
}
# if not found, return input string
return $encoding;
}
sub get_po_encoding
{
my ($in_po_file) = @_;
my $encoding = "";
open IN_PO_FILE, $in_po_file or die;
while (<IN_PO_FILE>)
{
## example: "Content-Type: text/plain; charset=ISO-8859-1\n"
if (/Content-Type\:.*charset=([-a-zA-Z0-9]+)\\n/)
{
$encoding = $1;
last;
}
}
close IN_PO_FILE;
if (!$encoding)
{
print STDERR "Warning: no encoding found in $in_po_file. Assuming ISO-8859-1\n" unless $QUIET_ARG;
$encoding = "ISO-8859-1";
}
system ("$iconv -f $encoding -t UTF-8 <$devnull 2>$devnull");
if ($?) {
$encoding = get_local_charset($encoding);
}
return $encoding
}
sub utf8_sanity_check
{
print STDERR "Warning: option --pass-through has been removed.\n" if $PASS_THROUGH_ARG;
$UTF8_ARG = 1;
}
sub get_translation_database
{
if ($cache_file) {
&get_cached_translation_database;
} else {
&create_translation_database;
}
}
sub get_newest_po_age
{
my $newest_age;
foreach my $file (values %po_files_by_lang)
{
my $file_age = -M $file;
$newest_age = $file_age if !$newest_age || $file_age < $newest_age;
}
$newest_age = 0 if !$newest_age;
return $newest_age;
}
sub create_cache
{
print "Generating and caching the translation database\n" unless $QUIET_ARG;
&create_translation_database;
open CACHE, ">$cache_file" || die;
print CACHE join "\x01", %translations;
close CACHE;
}
sub load_cache
{
print "Found cached translation database\n" unless $QUIET_ARG;
my $contents;
open CACHE, "<$cache_file" || die;
{
local $/;
$contents = <CACHE>;
}
close CACHE;
%translations = split "\x01", $contents;
}
sub get_cached_translation_database
{
my $cache_file_age = -M $cache_file;
if (defined $cache_file_age)
{
if ($cache_file_age <= &get_newest_po_age)
{
&load_cache;
return;
}
print "Found too-old cached translation database\n" unless $QUIET_ARG;
}
&create_cache;
}
sub create_translation_database
{
for my $lang (keys %po_files_by_lang)
{
my $po_file = $po_files_by_lang{$lang};
if ($UTF8_ARG)
{
my $encoding = get_po_encoding ($po_file);
if (lc $encoding eq "utf-8")
{
open PO_FILE, "<$po_file";
}
else
{
print "NOTICE: $po_file is not in UTF-8 but $encoding, converting...\n" unless $QUIET_ARG;;
open PO_FILE, "$iconv -f $encoding -t UTF-8 $po_file|";
}
}
else
{
open PO_FILE, "<$po_file";
}
my $nextfuzzy = 0;
my $inmsgid = 0;
my $inmsgstr = 0;
my $msgid = "";
my $msgstr = "";
while (<PO_FILE>)
{
$nextfuzzy = 1 if /^#, fuzzy/;
if (/^msgid "((\\.|[^\\])*)"/ )
{
$translations{$lang, $msgid} = $msgstr if $inmsgstr && $msgid && $msgstr;
$msgid = "";
$msgstr = "";
if ($nextfuzzy) {
$inmsgid = 0;
} else {
$msgid = unescape_po_string($1);
$inmsgid = 1;
}
$inmsgstr = 0;
$nextfuzzy = 0;
}
if (/^msgstr "((\\.|[^\\])*)"/)
{
$msgstr = unescape_po_string($1);
$inmsgstr = 1;
$inmsgid = 0;
}
if (/^"((\\.|[^\\])*)"/)
{
$msgid .= unescape_po_string($1) if $inmsgid;
$msgstr .= unescape_po_string($1) if $inmsgstr;
}
}
$translations{$lang, $msgid} = $msgstr if $inmsgstr && $msgid && $msgstr;
}
}
sub finalize
{
}
sub unescape_one_sequence
{
my ($sequence) = @_;
return "\\" if $sequence eq "\\\\";
return "\"" if $sequence eq "\\\"";
return "\n" if $sequence eq "\\n";
return "\r" if $sequence eq "\\r";
return "\t" if $sequence eq "\\t";
return "\b" if $sequence eq "\\b";
return "\f" if $sequence eq "\\f";
return "\a" if $sequence eq "\\a";
return chr(11) if $sequence eq "\\v"; # vertical tab, see ascii(7)
return chr(hex($1)) if ($sequence =~ /\\x([0-9a-fA-F]{2})/);
return chr(oct($1)) if ($sequence =~ /\\([0-7]{3})/);
# FIXME: Is \0 supported as well? Kenneth and Rodney don't want it, see bug #48489
return $sequence;
}
sub unescape_po_string
{
my ($string) = @_;
$string =~ s/(\\x[0-9a-fA-F]{2}|\\[0-7]{3}|\\.)/unescape_one_sequence($1)/eg;
return $string;
}
## NOTE: deal with < - < but not > - > because it seems its ok to have
## > in the entity. For further info please look at #84738.
sub entity_decode
{
local ($_) = @_;
s/'/'/g; # '
s/"/"/g; # "
s/&/&/g;
s/</</g;
return $_;
}
# entity_encode: (string)
#
# Encode the given string to XML format (encode '<' etc).
sub entity_encode
{
my ($pre_encoded) = @_;
my @list_of_chars = unpack ('C*', $pre_encoded);
# with UTF-8 we only encode minimalistic
return join ('', map (&entity_encode_int_minimalist, @list_of_chars));
}
sub entity_encode_int_minimalist
{
return """ if $_ == 34;
return "&" if $_ == 38;
return "'" if $_ == 39;
return "<" if $_ == 60;
return chr $_;
}
sub entity_encoded_translation
{
my ($lang, $string) = @_;
my $translation = $translations{$lang, $string};
return $string if !$translation;
return entity_encode ($translation);
}
## XML (bonobo-activation specific) merge code
sub ba_merge_translations
{
my $source;
{
local $/; # slurp mode
open INPUT, "<$FILE" or die "can't open $FILE: $!";
$source = <INPUT>;
close INPUT;
}
open OUTPUT, ">$OUTFILE" or die "can't open $OUTFILE: $!";
# Binmode so that selftest works ok if using a native Win32 Perl...
binmode (OUTPUT) if $^O eq 'MSWin32';
while ($source =~ s|^(.*?)([ \t]*<\s*$w+\s+($w+\s*=\s*"$q"\s*)+/?>)([ \t]*\n)?||s)
{
print OUTPUT $1;
my $node = $2 . "\n";
my @strings = ();
$_ = $node;
while (s/(\s)_($w+\s*=\s*"($q)")/$1$2/s) {
push @strings, entity_decode($3);
}
print OUTPUT;
my %langs;
for my $string (@strings)
{
for my $lang (keys %po_files_by_lang)
{
$langs{$lang} = 1 if $translations{$lang, $string};
}
}
for my $lang (sort keys %langs)
{
$_ = $node;
s/(\sname\s*=\s*)"($q)"/$1"$2-$lang"/s;
s/(\s)_($w+\s*=\s*")($q)"/$1 . $2 . entity_encoded_translation($lang, $3) . '"'/seg;
print OUTPUT;
}
}
print OUTPUT $source;
close OUTPUT;
}
## XML (non-bonobo-activation) merge code
# Process tag attributes
# Only parameter is a HASH containing attributes -> values mapping
sub getAttributeString
{
my $sub = shift;
my $do_translate = shift || 0;
my $language = shift || "";
my $result = "";
my $translate = shift;
foreach my $e (reverse(sort(keys %{ $sub }))) {
my $key = $e;
my $string = $sub->{$e};
my $quote = '"';
$string =~ s/^[\s]+//;
$string =~ s/[\s]+$//;
if ($string =~ /^'.*'$/)
{
$quote = "'";
}
$string =~ s/^['"]//g;
$string =~ s/['"]$//g;
if ($do_translate && $key =~ /^_/) {
$key =~ s|^_||g;
if ($language) {
# Handle translation
my $decode_string = entity_decode($string);
my $translation = $translations{$language, $decode_string};
if ($translation) {
$translation = entity_encode($translation);
$string = $translation;
}
$$translate = 2;
} else {
$$translate = 2 if ($translate && (!$$translate)); # watch not to "overwrite" $translate
}
}
$result .= " $key=$quote$string$quote";
}
return $result;
}
# Returns a translatable string from XML node, it works on contents of every node in XML::Parser tree
sub getXMLstring
{
my $ref = shift;
my $spacepreserve = shift || 0;
my @list = @{ $ref };
my $result = "";
my $count = scalar(@list);
my $attrs = $list[0];
my $index = 1;
$spacepreserve = 1 if ((exists $attrs->{"xml:space"}) && ($attrs->{"xml:space"} =~ /^["']?preserve["']?$/));
$spacepreserve = 0 if ((exists $attrs->{"xml:space"}) && ($attrs->{"xml:space"} =~ /^["']?default["']?$/));
while ($index < $count) {
my $type = $list[$index];
my $content = $list[$index+1];
if (! $type ) {
# We've got CDATA
if ($content) {
# lets strip the whitespace here, and *ONLY* here
$content =~ s/\s+/ /gs if (!$spacepreserve);
$result .= $content;
}
} elsif ( "$type" ne "1" ) {
# We've got another element
$result .= "<$type";
$result .= getAttributeString(@{$content}[0], 0); # no nested translatable elements
if ($content) {
my $subresult = getXMLstring($content, $spacepreserve);
if ($subresult) {
$result .= ">".$subresult . "</$type>";
} else {
$result .= "/>";
}
} else {
$result .= "/>";
}
}
$index += 2;
}
return $result;
}
# Translate list of nodes if necessary
sub translate_subnodes
{
my $fh = shift;
my $content = shift;
my $language = shift || "";
my $singlelang = shift || 0;
my $spacepreserve = shift || 0;
my @nodes = @{ $content };
my $count = scalar(@nodes);
my $index = 0;
while ($index < $count) {
my $type = $nodes[$index];
my $rest = $nodes[$index+1];
if ($singlelang) {
my $oldMO = $MULTIPLE_OUTPUT;
$MULTIPLE_OUTPUT = 1;
traverse($fh, $type, $rest, $language, $spacepreserve);
$MULTIPLE_OUTPUT = $oldMO;
} else {
traverse($fh, $type, $rest, $language, $spacepreserve);
}
$index += 2;
}
}
sub isWellFormedXmlFragment
{
my $ret = eval 'require XML::Parser';
if(!$ret) {
die "You must have XML::Parser installed to run $0\n\n";
}
my $fragment = shift;
return 0 if (!$fragment);
$fragment = "<root>$fragment</root>";
my $xp = new XML::Parser(Style => 'Tree');
my $tree = 0;
eval { $tree = $xp->parse($fragment); };
return $tree;
}
sub traverse
{
my $fh = shift;
my $nodename = shift;
my $content = shift;
my $language = shift || "";
my $spacepreserve = shift || 0;
if (!$nodename) {
if ($content =~ /^[\s]*$/) {
$leading_space .= $content;
}
print $fh $content;
} else {
# element
my @all = @{ $content };
my $attrs = shift @all;
my $translate = 0;
my $outattr = getAttributeString($attrs, 1, $language, \$translate);
if ($nodename =~ /^_/) {
$translate = 1;
$nodename =~ s/^_//;
}
my $lookup = '';
$spacepreserve = 0 if ((exists $attrs->{"xml:space"}) && ($attrs->{"xml:space"} =~ /^["']?default["']?$/));
$spacepreserve = 1 if ((exists $attrs->{"xml:space"}) && ($attrs->{"xml:space"} =~ /^["']?preserve["']?$/));
print $fh "<$nodename", $outattr;
if ($translate) {
$lookup = getXMLstring($content, $spacepreserve);
if (!$spacepreserve) {
$lookup =~ s/^\s+//s;
$lookup =~ s/\s+$//s;
}
if ($lookup || $translate == 2) {
my $translation = $translations{$language, $lookup} if isWellFormedXmlFragment($translations{$language, $lookup});
if ($MULTIPLE_OUTPUT && ($translation || $translate == 2)) {
$translation = $lookup if (!$translation);
print $fh " xml:lang=\"", $language, "\"" if $language;
print $fh ">";
if ($translate == 2) {
translate_subnodes($fh, \@all, $language, 1, $spacepreserve);
} else {
print $fh $translation;
}
print $fh "</$nodename>";
return; # this means there will be no same translation with xml:lang="$language"...
# if we want them both, just remove this "return"
} else {
print $fh ">";
if ($translate == 2) {
translate_subnodes($fh, \@all, $language, 1, $spacepreserve);
} else {
print $fh $lookup;
}
print $fh "</$nodename>";
}
} else {
print $fh "/>";
}
for my $lang (sort keys %po_files_by_lang) {
if ($MULTIPLE_OUTPUT && $lang ne "$language") {
next;
}
if ($lang) {
# Handle translation
#
my $translate = 0;
my $localattrs = getAttributeString($attrs, 1, $lang, \$translate);
my $translation = $translations{$lang, $lookup} if isWellFormedXmlFragment($translations{$lang, $lookup});
if ($translate && !$translation) {
$translation = $lookup;
}
if ($translation || $translate) {
print $fh "\n";
$leading_space =~ s/.*\n//g;
print $fh $leading_space;
print $fh "<", $nodename, " xml:lang=\"", $lang, "\"", $localattrs, ">";
if ($translate == 2) {
translate_subnodes($fh, \@all, $lang, 1, $spacepreserve);
} else {
print $fh $translation;
}
print $fh "</$nodename>";
}
}
}
} else {
my $count = scalar(@all);
if ($count > 0) {
print $fh ">";
my $index = 0;
while ($index < $count) {
my $type = $all[$index];
my $rest = $all[$index+1];
traverse($fh, $type, $rest, $language, $spacepreserve);
$index += 2;
}
print $fh "</$nodename>";
} else {
print $fh "/>";
}
}
}
}
sub intltool_tree_comment
{
my $expat = shift;
my $data = shift;
my $clist = $expat->{Curlist};
my $pos = $#$clist;
push @$clist, 1 => $data;
}
sub intltool_tree_cdatastart
{
my $expat = shift;
my $clist = $expat->{Curlist};
my $pos = $#$clist;
push @$clist, 0 => $expat->original_string();
}
sub intltool_tree_cdataend
{
my $expat = shift;
my $clist = $expat->{Curlist};
my $pos = $#$clist;
$clist->[$pos] .= $expat->original_string();
}
sub intltool_tree_char
{
my $expat = shift;
my $text = shift;
my $clist = $expat->{Curlist};
my $pos = $#$clist;
# Use original_string so that we retain escaped entities
# in CDATA sections.
#
if ($pos > 0 and $clist->[$pos - 1] eq '0') {
$clist->[$pos] .= $expat->original_string();
} else {
push @$clist, 0 => $expat->original_string();
}
}
sub intltool_tree_start
{
my $expat = shift;
my $tag = shift;
my @origlist = ();
# Use original_string so that we retain escaped entities
# in attribute values. We must convert the string to an
# @origlist array to conform to the structure of the Tree
# Style.
#
my @original_array = split /\x/, $expat->original_string();
my $source = $expat->original_string();
# Remove leading tag.
#
$source =~ s|^\s*<\s*(\S+)||s;
# Grab attribute key/value pairs and push onto @origlist array.
#
while ($source)
{
if ($source =~ /^\s*([\w:-]+)\s*[=]\s*["]/)
{
$source =~ s|^\s*([\w:-]+)\s*[=]\s*["]([^"]*)["]||s;
push @origlist, $1;
push @origlist, '"' . $2 . '"';
}
elsif ($source =~ /^\s*([\w:-]+)\s*[=]\s*[']/)
{
$source =~ s|^\s*([\w:-]+)\s*[=]\s*[']([^']*)[']||s;
push @origlist, $1;
push @origlist, "'" . $2 . "'";
}
else
{
last;
}
}
my $ol = [ { @origlist } ];
push @{ $expat->{Lists} }, $expat->{Curlist};
push @{ $expat->{Curlist} }, $tag => $ol;
$expat->{Curlist} = $ol;
}
sub readXml
{
my $filename = shift || return;
if(!-f $filename) {
die "ERROR Cannot find filename: $filename\n";
}
my $ret = eval 'require XML::Parser';
if(!$ret) {
die "You must have XML::Parser installed to run $0\n\n";
}
my $xp = new XML::Parser(Style => 'Tree');
$xp->setHandlers(Char => \&intltool_tree_char);
$xp->setHandlers(Start => \&intltool_tree_start);
$xp->setHandlers(CdataStart => \&intltool_tree_cdatastart);
$xp->setHandlers(CdataEnd => \&intltool_tree_cdataend);
my $tree = $xp->parsefile($filename);
# <foo><head id="a">Hello <em>there</em></head><bar>Howdy<ref/></bar>do</foo>
# would be:
# [foo, [{}, head, [{id => "a"}, 0, "Hello ", em, [{}, 0, "there"]], bar, [{},
# 0, "Howdy", ref, [{}]], 0, "do" ] ]
return $tree;
}
sub print_header
{
my $infile = shift;
my $fh = shift;
my $source;
if(!-f $infile) {
die "ERROR Cannot find filename: $infile\n";
}
print $fh qq{<?xml version="1.0" encoding="UTF-8"?>\n};
{
local $/;
open DOCINPUT, "<${FILE}" or die;
$source = <DOCINPUT>;
close DOCINPUT;
}
if ($source =~ /(<!DOCTYPE.*\[.*\]\s*>)/s)
{
print $fh "$1\n";
}
elsif ($source =~ /(<!DOCTYPE[^>]*>)/s)
{
print $fh "$1\n";
}
}
sub parseTree
{
my $fh = shift;
my $ref = shift;
my $language = shift || "";
my $name = shift @{ $ref };
my $cont = shift @{ $ref };
while (!$name || "$name" eq "1") {
$name = shift @{ $ref };
$cont = shift @{ $ref };
}
my $spacepreserve = 0;
my $attrs = @{$cont}[0];
$spacepreserve = 1 if ((exists $attrs->{"xml:space"}) && ($attrs->{"xml:space"} =~ /^["']?preserve["']?$/));
traverse($fh, $name, $cont, $language, $spacepreserve);