1 | #!@XML_I18N_TOOLS_PERL@ -w |
---|
2 | |
---|
3 | # |
---|
4 | # The XML Translation Merge Tool |
---|
5 | # |
---|
6 | # Copyright (C) 2000 Free Software Foundation. |
---|
7 | # Copyright (C) 2000, 2001 Eazel, Inc |
---|
8 | # |
---|
9 | # This library 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. |
---|
13 | # |
---|
14 | # This script 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. |
---|
18 | # |
---|
19 | # You should have received a copy of the GNU General Public License |
---|
20 | # along with this library; if not, write to the Free Software |
---|
21 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. |
---|
22 | # |
---|
23 | # Authors: Maciej Stachowiak <mjs@eazel.com> |
---|
24 | # Kenneth Christiansen <kenneth@gnu.org> |
---|
25 | # Darin Adler <darin@eazel.com> |
---|
26 | # |
---|
27 | # Proper XML UTF-8ification written by Cyrille Chepelov <chepelov@calixo.net> |
---|
28 | # |
---|
29 | |
---|
30 | ## Release information |
---|
31 | my $PROGRAM = "xml-i18n-merge"; |
---|
32 | my $PACKAGE = "xml-i18n-tools"; |
---|
33 | my $VERSION = "0.9"; |
---|
34 | |
---|
35 | ## Script options - Enable by setting value to 1 |
---|
36 | my $ENABLE_XML = "1"; |
---|
37 | |
---|
38 | ## Loaded modules |
---|
39 | use strict; |
---|
40 | use File::Basename; |
---|
41 | use Getopt::Long; |
---|
42 | |
---|
43 | ## Scalars used by the option stuff |
---|
44 | my $HELP_ARG = "0"; |
---|
45 | my $VERSION_ARG = "0"; |
---|
46 | my $OAF_STYLE_ARG = "0"; |
---|
47 | my $XML_STYLE_ARG = "0"; |
---|
48 | my $KEYS_STYLE_ARG = "0"; |
---|
49 | my $DESKTOP_STYLE_ARG = "0"; |
---|
50 | my $QUIET_ARG = "0"; |
---|
51 | my $PASS_THROUGH_ARG = "0"; |
---|
52 | my $UTF8_ARG = "0"; |
---|
53 | |
---|
54 | ## Handle options |
---|
55 | GetOptions ( |
---|
56 | "help|h|?" => \$HELP_ARG, |
---|
57 | "version|v" => \$VERSION_ARG, |
---|
58 | "quiet|q" => \$QUIET_ARG, |
---|
59 | "oaf-style|o" => \$OAF_STYLE_ARG, |
---|
60 | "xml-style|x" => \$XML_STYLE_ARG, |
---|
61 | "keys-style|k" => \$KEYS_STYLE_ARG, |
---|
62 | "desktop-style|d" => \$DESKTOP_STYLE_ARG, |
---|
63 | "pass-through|p" => \$PASS_THROUGH_ARG, |
---|
64 | "utf8|u" => \$UTF8_ARG |
---|
65 | ) or &error; |
---|
66 | |
---|
67 | |
---|
68 | my $PO_DIR; |
---|
69 | my $FILE; |
---|
70 | my $OUTFILE; |
---|
71 | |
---|
72 | my @languages; |
---|
73 | my %po_files_by_lang = (); |
---|
74 | my %translations = (); |
---|
75 | |
---|
76 | # Use this instead of \w for XML files to handle more possible characters. |
---|
77 | my $w = "[-A-Za-z0-9._:]"; |
---|
78 | |
---|
79 | |
---|
80 | &split_on_argument; |
---|
81 | |
---|
82 | |
---|
83 | ## Check for options. |
---|
84 | ## This section will check for the different options. |
---|
85 | |
---|
86 | sub split_on_argument { |
---|
87 | |
---|
88 | if ($VERSION_ARG) { |
---|
89 | &version; |
---|
90 | } elsif ($HELP_ARG) { |
---|
91 | &help; |
---|
92 | } elsif ($OAF_STYLE_ARG && @ARGV > 2) { |
---|
93 | &place_normal; |
---|
94 | &message; |
---|
95 | &preparation; |
---|
96 | &oaf_merge_translations; |
---|
97 | } elsif ($XML_STYLE_ARG && @ARGV > 2) { |
---|
98 | &utf8_sanity_check; |
---|
99 | &place_normal; |
---|
100 | &message; |
---|
101 | &preparation; |
---|
102 | &xml_merge_translations; |
---|
103 | } elsif ($KEYS_STYLE_ARG && @ARGV > 2) { |
---|
104 | &utf8_sanity_check; |
---|
105 | &place_normal; |
---|
106 | &message; |
---|
107 | &preparation; |
---|
108 | &keys_merge_translations; |
---|
109 | } elsif ($DESKTOP_STYLE_ARG && @ARGV > 2) { |
---|
110 | &place_normal; |
---|
111 | &message; |
---|
112 | &preparation; |
---|
113 | &desktop_merge_translations; |
---|
114 | } else { |
---|
115 | &help; |
---|
116 | } |
---|
117 | } |
---|
118 | |
---|
119 | sub utf8_sanity_check { |
---|
120 | if (!$UTF8_ARG) { |
---|
121 | if (!$PASS_THROUGH_ARG) { |
---|
122 | print "****WARNING****: no default behavior to xml-i18n-merge (-p or -u) specified.\n"; |
---|
123 | print "Previous default was equivalent to -p, but generating broken \"XML\" files\n"; |
---|
124 | print "Please read the documentation and choose either -p or -u behavior\n"; |
---|
125 | print "For the moment, will assume -p, but this default may change in the future\n"; |
---|
126 | print "\n\n\n"; |
---|
127 | |
---|
128 | print "xml-i18n-merge will now sleep 5 seconds.\n"; |
---|
129 | sleep 5; |
---|
130 | $PASS_THROUGH_ARG="1"; |
---|
131 | } else { |
---|
132 | #print "xml-i18n-merge warning: \"XML\" with 8-bit pass-through is not likely to be \nreal XML.\n"; |
---|
133 | } |
---|
134 | } |
---|
135 | } |
---|
136 | |
---|
137 | sub place_normal { |
---|
138 | $PO_DIR = $ARGV[0]; |
---|
139 | $FILE = $ARGV[1]; |
---|
140 | $OUTFILE = $ARGV[2]; |
---|
141 | } |
---|
142 | |
---|
143 | |
---|
144 | ## Sub for printing release information |
---|
145 | sub version{ |
---|
146 | print "${PROGRAM} (${PACKAGE}) ${VERSION}\n"; |
---|
147 | print "Written by Maciej Stachowiak and Kenneth Christiansen, 2000.\n\n"; |
---|
148 | print "Copyright (C) 2000 Free Software Foundation, Inc.\n"; |
---|
149 | print "Copyright (C) 2000, 2001 Eazel, Inc.\n"; |
---|
150 | print "This is free software; see the source for copying conditions. There is NO\n"; |
---|
151 | print "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n"; |
---|
152 | exit; |
---|
153 | } |
---|
154 | |
---|
155 | ## Sub for printing usage information |
---|
156 | sub help{ |
---|
157 | print "Usage: ${PROGRAM} [OPTIONS] PO_DIRECTORY FILENAME OUTPUT_FILE\n"; |
---|
158 | print "Generates an xml file that includes translated versions of some attributes,\n"; |
---|
159 | print "from an untranslated source and a po directory that includes translations.\n"; |
---|
160 | print " -v, --version shows the version\n"; |
---|
161 | print " -h, --help shows this help page\n"; |
---|
162 | print " -q, --quiet quiet mode\n"; |
---|
163 | print " -o, --oaf-style includes translations in the oaf style\n"; |
---|
164 | print " -x, --xml-style includes translations in the xml style\n"; |
---|
165 | print " -k, --keys-style includes translations in the keys style\n"; |
---|
166 | print " -d, --desktop-style includes translations in the desktop style\n"; |
---|
167 | print " -u, --utf8 convert all strings to UTF-8 before merging\n"; |
---|
168 | print " -p, --pass-through use strings as found in .po files, without\n"; |
---|
169 | print " conversion (STRONGLY unrecommended with -x)\n"; |
---|
170 | print "\nReport bugs to bugzilla.eazel.com, module xml-i18n-tools or <mjs\@eazel.com>\n"; |
---|
171 | exit; |
---|
172 | } |
---|
173 | |
---|
174 | |
---|
175 | ## Sub for printing error messages |
---|
176 | sub error{ |
---|
177 | # print "xml-i18n-merge: invalid option @ARGV\n"; |
---|
178 | print "Try `${PROGRAM} --help' for more information.\n"; |
---|
179 | exit; |
---|
180 | } |
---|
181 | |
---|
182 | |
---|
183 | sub message { |
---|
184 | print "Merging translations into $OUTFILE.\n" unless $QUIET_ARG; |
---|
185 | } |
---|
186 | |
---|
187 | |
---|
188 | sub preparation { |
---|
189 | &gather_po_files; |
---|
190 | &create_translation_database; |
---|
191 | } |
---|
192 | |
---|
193 | |
---|
194 | |
---|
195 | # General-purpose code for looking up translations in .po files |
---|
196 | |
---|
197 | sub gather_po_files |
---|
198 | { |
---|
199 | my @po_files = glob("${PO_DIR}/*.po"); |
---|
200 | |
---|
201 | @languages = map (&po_file2lang, @po_files); |
---|
202 | |
---|
203 | foreach my $lang (@languages) { |
---|
204 | $po_files_by_lang{$lang} = shift (@po_files); |
---|
205 | } |
---|
206 | } |
---|
207 | |
---|
208 | sub po_file2lang |
---|
209 | { |
---|
210 | my $tmp = $_; |
---|
211 | $tmp =~ s/^.*\/(.*)\.po$/$1/; |
---|
212 | return $tmp; |
---|
213 | } |
---|
214 | |
---|
215 | sub get_po_encoding |
---|
216 | { |
---|
217 | my ($in_po_file) = @_; |
---|
218 | my $encoding = ""; |
---|
219 | |
---|
220 | open IN_PO_FILE, $in_po_file; |
---|
221 | |
---|
222 | while (<IN_PO_FILE>) { |
---|
223 | ## example: "Content-Type: text/plain; charset=ISO-8859-1\n" |
---|
224 | if (/Content-Type\:.*charset=([-a-zA-Z0-9]+)\\n/) { |
---|
225 | $encoding = $1; |
---|
226 | last; |
---|
227 | } |
---|
228 | } |
---|
229 | close IN_PO_FILE; |
---|
230 | |
---|
231 | if (!$encoding) { |
---|
232 | print ("Warning: no encoding found in $in_po_file. Assuming ISO-8859-1\n"); |
---|
233 | $encoding = "ISO-8859-1"; |
---|
234 | } |
---|
235 | return $encoding |
---|
236 | } |
---|
237 | |
---|
238 | sub create_translation_database |
---|
239 | { |
---|
240 | foreach my $lang (@languages) { |
---|
241 | |
---|
242 | my $po_file = $po_files_by_lang{$lang}; |
---|
243 | |
---|
244 | if ($UTF8_ARG) { |
---|
245 | my $encoding = get_po_encoding($po_file); |
---|
246 | open PO_FILE, "iconv -f $encoding -t UTF-8 $po_file|"; |
---|
247 | } else { |
---|
248 | open PO_FILE, "<$po_file"; |
---|
249 | } |
---|
250 | |
---|
251 | while (<PO_FILE>) { |
---|
252 | if (/^#,.*fuzzy/) { |
---|
253 | $_ = <PO_FILE>; next; |
---|
254 | } |
---|
255 | if (/^msgid "(.*)"/ ) { |
---|
256 | my $msgid = unescape_po_string($1); |
---|
257 | $_ = <PO_FILE>; |
---|
258 | |
---|
259 | if (/^msgstr "(.+)"/) { |
---|
260 | my $msgstr = unescape_po_string($1); |
---|
261 | $translations{$lang . "|" . $msgid} = $msgstr; |
---|
262 | # print "[$lang]$msgstr\n"; |
---|
263 | } |
---|
264 | } |
---|
265 | } |
---|
266 | } |
---|
267 | } |
---|
268 | |
---|
269 | sub unescape_po_string |
---|
270 | { |
---|
271 | my ($value) = @_; |
---|
272 | |
---|
273 | # this is likely to be quite incomplete. |
---|
274 | # I suck at encoding thought as perl noi^W. -- CC |
---|
275 | my $retval = $value; |
---|
276 | $retval =~ s/\\([n\"\\])/$1/g; |
---|
277 | |
---|
278 | return $retval; |
---|
279 | } |
---|
280 | |
---|
281 | sub lookup_translations |
---|
282 | { |
---|
283 | my ($value) = @_; |
---|
284 | |
---|
285 | my %transmap = (); |
---|
286 | |
---|
287 | foreach my $lang (@languages) { |
---|
288 | my $translation = lookup_translation ($value, $lang); |
---|
289 | |
---|
290 | if ($translation) { |
---|
291 | $transmap{$lang} = $translation; |
---|
292 | } |
---|
293 | } |
---|
294 | |
---|
295 | return %transmap; |
---|
296 | } |
---|
297 | |
---|
298 | |
---|
299 | sub lookup_translation |
---|
300 | { |
---|
301 | my ($string, $lang) = @_; |
---|
302 | $string =~ s/\+/\\+/g; |
---|
303 | |
---|
304 | my $salt = "$lang|$string"; |
---|
305 | |
---|
306 | if ($translations{$salt}) { |
---|
307 | return $translations{$salt}; |
---|
308 | } |
---|
309 | |
---|
310 | return ""; |
---|
311 | } |
---|
312 | |
---|
313 | |
---|
314 | sub entity_encode_translations |
---|
315 | { |
---|
316 | my %transmap = @_; |
---|
317 | |
---|
318 | foreach my $key (keys %transmap) { |
---|
319 | $transmap{$key} = entity_encode ($transmap{$key}); |
---|
320 | } |
---|
321 | |
---|
322 | return %transmap; |
---|
323 | } |
---|
324 | |
---|
325 | |
---|
326 | sub entity_encode |
---|
327 | { |
---|
328 | my ($pre_encoded) = @_; |
---|
329 | |
---|
330 | my @list_of_chars = unpack ('C*', $pre_encoded); |
---|
331 | |
---|
332 | if ($PASS_THROUGH_ARG) { |
---|
333 | return join ('', map (&entity_encode_int_even_high_bit, @list_of_chars)); |
---|
334 | } else { |
---|
335 | return join ('', map (&entity_encode_int_minimalist, @list_of_chars)); |
---|
336 | } |
---|
337 | } |
---|
338 | |
---|
339 | sub entity_encode_int_minimalist |
---|
340 | { |
---|
341 | if ($_ == 34) { return """ } |
---|
342 | elsif ($_ == 38) { return "&" } |
---|
343 | elsif ($_ == 39) { return "'" } |
---|
344 | elsif ($_ == 60) { return "<" } |
---|
345 | elsif ($_ == 62) { return ">" } |
---|
346 | return chr $_; |
---|
347 | } |
---|
348 | |
---|
349 | sub entity_encode_int_even_high_bit |
---|
350 | { |
---|
351 | if ($_ > 127 || $_ == 34 || $_ == 38 || $_ == 39 || $_ == 60 || $_ == 62) { |
---|
352 | # the ($_ > 127) should probably be removed |
---|
353 | return "&#" . $_ . ";"; |
---|
354 | } else { |
---|
355 | return chr $_; |
---|
356 | } |
---|
357 | } |
---|
358 | |
---|
359 | |
---|
360 | ## XML/OAF-specific merge code |
---|
361 | |
---|
362 | sub oaf_merge_translations |
---|
363 | { |
---|
364 | my $xml_source; { |
---|
365 | local (*INPUT); |
---|
366 | local $/; # slurp mode |
---|
367 | open INPUT, "<$FILE" or die "can't open $FILE: $!"; |
---|
368 | $xml_source = <INPUT>; |
---|
369 | close INPUT; |
---|
370 | } |
---|
371 | |
---|
372 | open OUTPUT, ">$OUTFILE"; |
---|
373 | |
---|
374 | while ($xml_source =~ /[ \t]*<[^<]*\s_$w+="[^"]*"[^<]*>/m) { #" |
---|
375 | print OUTPUT $`; #` |
---|
376 | my $orig_node = $&; |
---|
377 | $xml_source = $'; #' |
---|
378 | |
---|
379 | my $non_translated_line = $orig_node; |
---|
380 | $non_translated_line =~ s/_($w+)="/$1="/; |
---|
381 | |
---|
382 | my $new_node = $non_translated_line; |
---|
383 | |
---|
384 | my $value_str = $orig_node; |
---|
385 | $value_str =~ s/.*_$w+="([^"]*)".*/$1/s; #" |
---|
386 | |
---|
387 | if ($value_str) { |
---|
388 | my %value_translation_map = entity_encode_translations |
---|
389 | (lookup_translations ($value_str)); |
---|
390 | |
---|
391 | foreach my $key (sort keys %value_translation_map) { |
---|
392 | my $translation = $value_translation_map{$key}; |
---|
393 | |
---|
394 | my $translated_line = $orig_node; |
---|
395 | $translated_line =~ s/name="([^"]*)"/name="$1-$key"/; |
---|
396 | $translated_line =~ s/(\s*)_($w+)="[^"]*"/$1$2="$translation"/; |
---|
397 | |
---|
398 | $new_node .= "\n$translated_line"; |
---|
399 | } |
---|
400 | } |
---|
401 | |
---|
402 | $xml_source = $new_node . $xml_source; |
---|
403 | } |
---|
404 | |
---|
405 | print OUTPUT $xml_source; |
---|
406 | |
---|
407 | close OUTPUT; |
---|
408 | } |
---|
409 | |
---|
410 | |
---|
411 | ## XML (non-OAF) merge code |
---|
412 | |
---|
413 | sub xml_merge_translations |
---|
414 | { |
---|
415 | my $xml_source; { |
---|
416 | local (*INPUT); |
---|
417 | local $/; # slurp mode |
---|
418 | open INPUT, "<$FILE" or die "can't open $FILE: $!"; |
---|
419 | $xml_source = <INPUT>; |
---|
420 | close INPUT; |
---|
421 | } |
---|
422 | |
---|
423 | open OUTPUT, ">$OUTFILE"; |
---|
424 | |
---|
425 | # FIXME: support attribute translations |
---|
426 | |
---|
427 | # First just unmark for translation all empty nodes |
---|
428 | # for example <_foo/> is just replaced by <foo/> |
---|
429 | $xml_source =~ s/<_($w+)\/>/<$1\/>/mg; |
---|
430 | |
---|
431 | # Support for XML <_foo>blah</_foo> style translations |
---|
432 | while ($xml_source =~ /([ \t]*)<_($w+)>([^<]+)<\/_\2>/m) { |
---|
433 | print OUTPUT $`; |
---|
434 | $xml_source = $'; #' |
---|
435 | |
---|
436 | my $spaces = $1; |
---|
437 | my $tag_name = $2; |
---|
438 | my $value_str = $3; |
---|
439 | |
---|
440 | my $non_translated_line = "$spaces<$tag_name>$value_str</$tag_name>"; |
---|
441 | |
---|
442 | my $new_node = $non_translated_line; |
---|
443 | |
---|
444 | if ($value_str) { |
---|
445 | my %value_translation_map = entity_encode_translations |
---|
446 | (lookup_translations ($value_str)); |
---|
447 | |
---|
448 | foreach my $key (sort keys %value_translation_map) { |
---|
449 | my $translation = $value_translation_map{$key}; |
---|
450 | |
---|
451 | $new_node .= "\n$spaces<$tag_name xml:lang=\"$key\">$translation</$tag_name>"; |
---|
452 | } |
---|
453 | } |
---|
454 | |
---|
455 | $xml_source = $new_node . $xml_source; |
---|
456 | } |
---|
457 | |
---|
458 | print OUTPUT $xml_source; |
---|
459 | |
---|
460 | close OUTPUT; |
---|
461 | } |
---|
462 | |
---|
463 | sub keys_merge_translations |
---|
464 | { |
---|
465 | open INPUT, "<${FILE}"; |
---|
466 | |
---|
467 | open OUTPUT, ">${OUTFILE}"; |
---|
468 | |
---|
469 | while (<INPUT>) { |
---|
470 | chomp; |
---|
471 | if (/^\s*_\w+=.*/) { |
---|
472 | my $orig_line = $_; |
---|
473 | |
---|
474 | my $non_translated_line = $orig_line; |
---|
475 | $non_translated_line =~ s/_([^="]*)=/$1=/; |
---|
476 | |
---|
477 | print OUTPUT "${non_translated_line}\n"; |
---|
478 | |
---|
479 | my $value_str = $orig_line; |
---|
480 | $value_str =~ s/.*_\w+=(.*)/$1/; |
---|
481 | |
---|
482 | if ($value_str) { |
---|
483 | my %value_translation_map = lookup_translations ($value_str); |
---|
484 | |
---|
485 | foreach my $key (sort keys %value_translation_map) { |
---|
486 | my $translation = $value_translation_map{$key}; |
---|
487 | |
---|
488 | my $translated_line = $orig_line; |
---|
489 | $translated_line =~ s/_([^="]*)=([^\n]*)/\[$key]$1=$translation/; |
---|
490 | print OUTPUT "$translated_line\n"; |
---|
491 | } |
---|
492 | } |
---|
493 | } else { |
---|
494 | print OUTPUT "$_\n"; |
---|
495 | } |
---|
496 | } |
---|
497 | |
---|
498 | close OUTPUT; |
---|
499 | close INPUT; |
---|
500 | } |
---|
501 | |
---|
502 | sub desktop_merge_translations |
---|
503 | { |
---|
504 | open INPUT, "<${FILE}"; |
---|
505 | |
---|
506 | open OUTPUT, ">${OUTFILE}"; |
---|
507 | |
---|
508 | while (<INPUT>) { |
---|
509 | chomp; |
---|
510 | if (/^\s*_\w+=.*/) { |
---|
511 | my $orig_line = $_; |
---|
512 | |
---|
513 | my $non_translated_line = $orig_line; |
---|
514 | $non_translated_line =~ s/_([^="]*)=/$1=/; |
---|
515 | |
---|
516 | print OUTPUT "${non_translated_line}\n"; |
---|
517 | |
---|
518 | my $value_str = $orig_line; |
---|
519 | $value_str =~ s/.*_\w+=(.*)/$1/; |
---|
520 | |
---|
521 | if ($value_str) { |
---|
522 | my %value_translation_map = lookup_translations ($value_str); |
---|
523 | |
---|
524 | foreach my $key (sort keys %value_translation_map) { |
---|
525 | my $translation = $value_translation_map{$key}; |
---|
526 | |
---|
527 | my $translated_line = $orig_line; |
---|
528 | $translated_line =~ s/^_([^="]*)=([^\n]*)/$1\[$key]=$translation/; |
---|
529 | print OUTPUT "$translated_line\n"; |
---|
530 | } |
---|
531 | } |
---|
532 | } else { |
---|
533 | print OUTPUT "$_\n"; |
---|
534 | } |
---|
535 | } |
---|
536 | |
---|
537 | close OUTPUT; |
---|
538 | close INPUT; |
---|
539 | |
---|
540 | } |
---|