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
|
#!/usr/bin/perl -w
#
# The Intltool Message Merger
#
# Copyright (C) 2000 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 Library General Public License as
# published by the Free Software Foundation; either version 2 of the
# License, or (at your option) any later version.
#
# 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
# Library General Public License for more details.
#
# You should have received a copy of the GNU Library General Public
# License along with the Gnome Library; see the file COPYING.LIB. If not,
# write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
# Boston, MA 02111-1307, USA.
#
# Authors: Maciej Stachowiak <mjs@eazel.com>
# Kenneth Christiansen <kenneth@gnu.org>
# Darin Adler <darin@bentspoon.com>
#
# Proper XML UTF-8ification written by Cyrille Chepelov <chepelov@calixo.net>
#
## Release information
my $PROGRAM = "intltool-merge";
my $PACKAGE = "intltool";
my $VERSION = "0.9.6";
## Script options - Enable by setting value to 1
my $ENABLE_XML = "1";
## Loaded modules
use strict;
use File::Basename;
use Getopt::Long;
## Scalars used by the option stuff
my $HELP_ARG = "0";
my $VERSION_ARG = "0";
my $OAF_STYLE_ARG = "0";
my $XML_STYLE_ARG = "0";
my $KEYS_STYLE_ARG = "0";
my $DESKTOP_STYLE_ARG = "0";
my $QUIET_ARG = "0";
my $PASS_THROUGH_ARG = "0";
my $UTF8_ARG = "0";
## Handle options
GetOptions (
"help|h" => \$HELP_ARG,
"version|v" => \$VERSION_ARG,
"quiet|q" => \$QUIET_ARG,
"oaf-style|o" => \$OAF_STYLE_ARG,
"xml-style|x" => \$XML_STYLE_ARG,
"keys-style|k" => \$KEYS_STYLE_ARG,
"desktop-style|d" => \$DESKTOP_STYLE_ARG,
"pass-through|p" => \$PASS_THROUGH_ARG,
"utf8|u" => \$UTF8_ARG
) or &error;
my $PO_DIR;
my $FILE;
my $OUTFILE;
my @languages;
my %po_files_by_lang = ();
my %translations = ();
# Use this instead of \w for XML files to handle more possible characters.
my $w = "[-A-Za-z0-9._:]";
&split_on_argument;
## Check for options.
## This section will check for the different options.
sub split_on_argument {
if ($VERSION_ARG) {
&version;
} elsif ($HELP_ARG) {
&help;
} elsif ($OAF_STYLE_ARG && @ARGV > 2) {
&place_normal;
&message;
&preparation;
&oaf_merge_translations;
} elsif ($XML_STYLE_ARG && @ARGV > 2) {
&utf8_sanity_check;
&place_normal;
&message;
&preparation;
&xml_merge_translations;
} elsif ($KEYS_STYLE_ARG && @ARGV > 2) {
&utf8_sanity_check;
&place_normal;
&message;
&preparation;
&keys_merge_translations;
} elsif ($DESKTOP_STYLE_ARG && @ARGV > 2) {
&place_normal;
&message;
&preparation;
&desktop_merge_translations;
} else {
&help;
}
}
sub utf8_sanity_check {
if (!$UTF8_ARG) {
if (!$PASS_THROUGH_ARG) {
$PASS_THROUGH_ARG="1";
}
}
}
sub place_normal {
$PO_DIR = $ARGV[0];
$FILE = $ARGV[1];
$OUTFILE = $ARGV[2];
}
## Sub for printing release information
sub version{
print "${PROGRAM} (${PACKAGE}) ${VERSION}\n";
print "Written by Maciej Stachowiak and Kenneth Christiansen, 2000.\n\n";
print "Copyright (C) 2000 Free Software Foundation, Inc.\n";
print "Copyright (C) 2000, 2001 Eazel, Inc.\n";
print "This is free software; see the source for copying conditions. There is NO\n";
print "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n";
exit;
}
## Sub for printing usage information
sub help{
print "Usage: ${PROGRAM} [OPTIONS] PO_DIRECTORY FILENAME OUTPUT_FILE\n";
print "Generates an xml file that includes translated versions of some attributes,\n";
print "from an untranslated source and a po directory that includes translations.\n";
print " -v, --version shows the version\n";
print " -h, --help shows this help page\n";
print " -q, --quiet quiet mode\n";
print " -o, --oaf-style includes translations in the oaf style\n";
print " -x, --xml-style includes translations in the xml style\n";
print " -k, --keys-style includes translations in the keys style\n";
print " -d, --desktop-style includes translations in the desktop style\n";
print " -u, --utf8 convert all strings to UTF-8 before merging\n";
print " -p, --pass-through use strings as found in .po files, without\n";
print " conversion (STRONGLY unrecommended with -x)\n";
print "\nReport bugs to bugzilla.gnome.org, module xml-i18n-tools or xml-i18n-tools-list\@gnome.org>\n";
exit;
}
## Sub for printing error messages
sub error{
print "Try `${PROGRAM} --help' for more information.\n";
exit;
}
sub message {
print "Merging translations into $OUTFILE.\n" unless $QUIET_ARG;
}
sub preparation {
&gather_po_files;
&create_translation_database;
}
# General-purpose code for looking up translations in .po files
sub gather_po_files
{
my @po_files = glob("${PO_DIR}/*.po");
@languages = map (&po_file2lang, @po_files);
foreach my $lang (@languages) {
$po_files_by_lang{$lang} = shift (@po_files);
}
}
sub po_file2lang
{
my $tmp = $_;
$tmp =~ s/^.*\/(.*)\.po$/$1/;
return $tmp;
}
sub get_po_encoding
{
my ($in_po_file) = @_;
my $encoding = "";
open IN_PO_FILE, $in_po_file;
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 ("Warning: no encoding found in $in_po_file. Assuming ISO-8859-1\n");
$encoding = "ISO-8859-1";
}
return $encoding
}
sub create_translation_database
{
foreach my $lang (@languages) {
my $po_file = $po_files_by_lang{$lang};
if ($UTF8_ARG) {
my $encoding = get_po_encoding($po_file);
open PO_FILE, "iconv -f $encoding -t UTF-8 $po_file|";
} else {
open PO_FILE, "<$po_file";
}
while (<PO_FILE>) {
if (/^#,.*fuzzy/) {
$_ = <PO_FILE>; next;
}
if (/^msgid "(.*)"/ ) {
my $msgid = unescape_po_string($1);
$_ = <PO_FILE>;
if (/^msgstr "(.+)"/) {
my $msgstr = unescape_po_string($1);
$translations{$lang . "|" . $msgid} = $msgstr;
# print "[$lang]$msgstr\n";
}
}
}
}
}
sub unescape_one_sequence
{
my ($sequence) = @_;
return "\\" if $sequence eq "\\\\";
return "\"" if $sequence eq "\\\"";
# gettext also handles \n, \t, \b, \r, \f, \v, \a, \xxx (octal),
# \xXX (hex) and has a comment saying they want to handle \u and \U.
return $sequence;
}
sub unescape_po_string
{
my ($string) = @_;
$string =~ s/(\\.)/unescape_one_sequence($1)/eg;
return $string;
}
sub lookup_translations
{
my ($value) = @_;
my %transmap = ();
foreach my $lang (@languages) {
my $translation = lookup_translation ($value, $lang);
if ($translation) {
$transmap{$lang} = $translation;
}
}
return %transmap;
}
sub lookup_translation
{
my ($string, $lang) = @_;
$string =~ s/\+/\\+/g;
my $salt = "$lang|$string";
if ($translations{$salt}) {
return $translations{$salt};
}
return "";
}
sub entity_encode_translations
{
my %transmap = @_;
foreach my $key (keys %transmap) {
$transmap{$key} = entity_encode ($transmap{$key});
}
return %transmap;
}
sub entity_encode
{
my ($pre_encoded) = @_;
my @list_of_chars = unpack ('C*', $pre_encoded);
if ($PASS_THROUGH_ARG) {
return join ('', map (&entity_encode_int_even_high_bit, @list_of_chars));
} else {
return join ('', map (&entity_encode_int_minimalist, @list_of_chars));
}
}
sub entity_encode_int_minimalist
{
if ($_ == 34) { return """ }
elsif ($_ == 38) { return "&" }
elsif ($_ == 39) { return "'" }
elsif ($_ == 60) { return "<" }
elsif ($_ == 62) { return ">" }
return chr $_;
}
sub entity_encode_int_even_high_bit
{
if ($_ > 127 || $_ == 34 || $_ == 38 || $_ == 39 || $_ == 60 || $_ == 62) {
# the ($_ > 127) should probably be removed
return "&#" . $_ . ";";
} else {
return chr $_;
}
}
## XML/OAF-specific merge code
sub oaf_merge_translations
{
my $xml_source; {
local (*INPUT);
local $/; # slurp mode
open INPUT, "<$FILE" or die "can't open $FILE: $!";
$xml_source = <INPUT>;
close INPUT;
}
open OUTPUT, ">$OUTFILE";
while ($xml_source =~ /[ \t]*<[^<]*\s_$w+="[^"]*"[^<]*>/m) { #"
print OUTPUT $`; #`
my $orig_node = $&;
$xml_source = $'; #'
my $non_translated_line = $orig_node;
$non_translated_line =~ s/_($w+)="/$1="/;
my $new_node = $non_translated_line;
my $value_str = $orig_node;
$value_str =~ s/.*_$w+="([^"]*)".*/$1/s; #"
if ($value_str) {
my %value_translation_map = entity_encode_translations
(lookup_translations ($value_str));
foreach my $key (sort keys %value_translation_map) {
my $translation = $value_translation_map{$key};
my $translated_line = $orig_node;
$translated_line =~ s/name="([^"]*)"/name="$1-$key"/;
$translated_line =~ s/(\s*)_($w+)="[^"]*"/$1$2="$translation"/;
$new_node .= "\n$translated_line";
}
}
$xml_source = $new_node . $xml_source;
}
print OUTPUT $xml_source;
close OUTPUT;
}
## XML (non-OAF) merge code
sub xml_merge_translations
{
my $xml_source; {
local (*INPUT);
local $/; # slurp mode
open INPUT, "<$FILE" or die "can't open $FILE: $!";
$xml_source = <INPUT>;
close INPUT;
}
open OUTPUT, ">$OUTFILE";
# FIXME: support attribute translations
# First just unmark for translation all empty nodes
# for example <_foo/> is just replaced by <foo/>
$xml_source =~ s/<_($w+)\/>/<$1\/>/mg;
# Support for XML <_foo>blah</_foo> style translations
while ($xml_source =~ /([ \t]*)<_($w+)>([^<]+)<\/_\2>/m) {
print OUTPUT $`;
$xml_source = $'; #'
my $spaces = $1;
my $tag_name = $2;
my $value_str = $3;
my $non_translated_line = "$spaces<$tag_name>$value_str</$tag_name>";
my $new_node = $non_translated_line;
if ($value_str) {
my %value_translation_map = entity_encode_translations
(lookup_translations ($value_str));
foreach my $key (sort keys %value_translation_map) {
my $translation = $value_translation_map{$key};
$new_node .= "\n$spaces<$tag_name xml:lang=\"$key\">$translation</$tag_name>";
}
}
$xml_source = $new_node . $xml_source;
}
print OUTPUT $xml_source;
close OUTPUT;
}
sub keys_merge_translations
{
open INPUT, "<${FILE}";
open OUTPUT, ">${OUTFILE}";
while (<INPUT>) {
chomp;
if (/^\s*_\w+=.*/) {
my $orig_line = $_;
my $non_translated_line = $orig_line;
$non_translated_line =~ s/_([^="]*)=/$1=/;
print OUTPUT "${non_translated_line}\n";
my $value_str = $orig_line;
$value_str =~ s/.*_\w+=(.*)/$1/;
if ($value_str) {
my %value_translation_map = lookup_translations ($value_str);
foreach my $key (sort keys %value_translation_map) {
my $translation = $value_translation_map{$key};
my $translated_line = $orig_line;
$translated_line =~ s/_([^="]*)=([^\n]*)/\[$key]$1=$translation/;
print OUTPUT "$translated_line\n";
}
}
} else {
print OUTPUT "$_\n";
}
}
close OUTPUT;
close INPUT;
}
sub desktop_merge_translations
{
open INPUT, "<${FILE}";
open OUTPUT, ">${OUTFILE}";
while (<INPUT>) {
chomp;
if (/^\s*_\w+=.*/) {
my $orig_line = $_;
my $non_translated_line = $orig_line;
$non_translated_line =~ s/_([^="]*)=/$1=/;
print OUTPUT "${non_translated_line}\n";
my $value_str = $orig_line;
$value_str =~ s/.*_\w+=(.*)/$1/;
if ($value_str) {
my %value_translation_map = lookup_translations ($value_str);
foreach my $key (sort keys %value_translation_map) {
my $translation = $value_translation_map{$key};
my $translated_line = $orig_line;
$translated_line =~ s/^_([^="]*)=([^\n]*)/$1\[$key]=$translation/;
print OUTPUT "$translated_line\n";
}
}
} else {
print OUTPUT "$_\n";
}
}
close OUTPUT;
close INPUT;
}
|