| Filename | /mnt/catalyst/koha/C4/Languages.pm |
| Statements | Executed 17 statements in 2.74ms |
| Calls | P | F | Exclusive Time |
Inclusive Time |
Subroutine |
|---|---|---|---|---|---|
| 1 | 1 | 1 | 425µs | 438µs | C4::Languages::BEGIN@22 |
| 1 | 1 | 1 | 18µs | 20µs | C4::Languages::BEGIN@25 |
| 1 | 1 | 1 | 14µs | 14µs | C4::Languages::BEGIN@39 |
| 1 | 1 | 1 | 10µs | 41µs | C4::Languages::BEGIN@24 |
| 1 | 1 | 1 | 8µs | 73µs | C4::Languages::BEGIN@26 |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::_build_languages_arrayref |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::_get_language_dirs |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::_get_themes |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::accept_language |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::getAllLanguages |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::getFrameworkLanguages |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::getTranslatedLanguages |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::get_bidi |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::language_get_description |
| 0 | 0 | 0 | 0s | 0s | C4::Languages::regex_lang_subtags |
| Line | State ments |
Time on line |
Calls | Time in subs |
Code |
|---|---|---|---|---|---|
| 1 | package C4::Languages; | ||||
| 2 | |||||
| 3 | # Copyright 2006 (C) LibLime | ||||
| 4 | # Joshua Ferraro <jmf@liblime.com> | ||||
| 5 | # Portions Copyright 2009 Chris Cormack and the Koha Dev Team | ||||
| 6 | # This file is part of Koha. | ||||
| 7 | # | ||||
| 8 | # Koha is free software; you can redistribute it and/or modify it under the | ||||
| 9 | # terms of the GNU General Public License as published by the Free Software | ||||
| 10 | # Foundation; either version 2 of the License, or (at your option) any later | ||||
| 11 | # version. | ||||
| 12 | # | ||||
| 13 | # Koha is distributed in the hope that it will be useful, but WITHOUT ANY | ||||
| 14 | # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR | ||||
| 15 | # A PARTICULAR PURPOSE. See the GNU General Public License for more details. | ||||
| 16 | # | ||||
| 17 | # You should have received a copy of the GNU General Public License along | ||||
| 18 | # with Koha; if not, write to the Free Software Foundation, Inc., | ||||
| 19 | # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. | ||||
| 20 | |||||
| 21 | |||||
| 22 | 2 | 34µs | 2 | 451µs | # spent 438µs (425+13) within C4::Languages::BEGIN@22 which was called:
# once (425µs+13µs) by C4::Templates::BEGIN@35 at line 22 # spent 438µs making 1 call to C4::Languages::BEGIN@22
# spent 13µs making 1 call to strict::import |
| 23 | #use warnings; FIXME - Bug 2505 | ||||
| 24 | 2 | 23µs | 2 | 72µs | # spent 41µs (10+31) within C4::Languages::BEGIN@24 which was called:
# once (10µs+31µs) by C4::Templates::BEGIN@35 at line 24 # spent 41µs making 1 call to C4::Languages::BEGIN@24
# spent 31µs making 1 call to Exporter::import |
| 25 | 2 | 27µs | 2 | 23µs | # spent 20µs (18+3) within C4::Languages::BEGIN@25 which was called:
# once (18µs+3µs) by C4::Templates::BEGIN@35 at line 25 # spent 20µs making 1 call to C4::Languages::BEGIN@25
# spent 3µs making 1 call to C4::Context::import |
| 26 | 2 | 123µs | 2 | 138µs | # spent 73µs (8+65) within C4::Languages::BEGIN@26 which was called:
# once (8µs+65µs) by C4::Templates::BEGIN@35 at line 26 # spent 73µs making 1 call to C4::Languages::BEGIN@26
# spent 65µs making 1 call to vars::import |
| 27 | |||||
| 28 | 1 | 600ns | eval { | ||
| 29 | 1 | 7µs | 1 | 3µs | if (C4::Context->ismemcached) { # spent 3µs making 1 call to C4::Context::ismemcached |
| 30 | require Memoize::Memcached; | ||||
| 31 | import Memoize::Memcached qw(memoize_memcached); | ||||
| 32 | |||||
| 33 | memoize_memcached('getTranslatedLanguages', memcached => C4::Context->memcached); | ||||
| 34 | memoize_memcached('getFrameworkLanguages' , memcached => C4::Context->memcached); | ||||
| 35 | memoize_memcached('getAllLanguages', memcached => C4::Context->memcached); | ||||
| 36 | } | ||||
| 37 | }; | ||||
| 38 | |||||
| 39 | # spent 14µs within C4::Languages::BEGIN@39 which was called:
# once (14µs+0s) by C4::Templates::BEGIN@35 at line 50 | ||||
| 40 | 1 | 900ns | $VERSION = 3.07.00.049; | ||
| 41 | 1 | 500ns | require Exporter; | ||
| 42 | 1 | 6µs | @ISA = qw(Exporter); | ||
| 43 | 1 | 600ns | @EXPORT = qw( | ||
| 44 | &getFrameworkLanguages | ||||
| 45 | &getTranslatedLanguages | ||||
| 46 | &getAllLanguages | ||||
| 47 | ); | ||||
| 48 | 1 | 3µs | @EXPORT_OK = qw(getFrameworkLanguages getTranslatedLanguages getAllLanguages get_bidi regex_lang_subtags language_get_description accept_language); | ||
| 49 | 1 | 5µs | $DEBUG = 0; | ||
| 50 | 1 | 2.51ms | 1 | 14µs | } # spent 14µs making 1 call to C4::Languages::BEGIN@39 |
| 51 | |||||
| 52 | =head1 NAME | ||||
| 53 | |||||
| 54 | C4::Languages - Perl Module containing language list functions for Koha | ||||
| 55 | |||||
| 56 | =head1 SYNOPSIS | ||||
| 57 | |||||
| 58 | use C4::Languages; | ||||
| 59 | |||||
| 60 | =head1 DESCRIPTION | ||||
| 61 | |||||
| 62 | =cut | ||||
| 63 | |||||
| 64 | =head1 FUNCTIONS | ||||
| 65 | |||||
| 66 | =head2 getFrameworkLanguages | ||||
| 67 | |||||
| 68 | Returns a reference to an array of hashes: | ||||
| 69 | |||||
| 70 | my $languages = getFrameworkLanguages(); | ||||
| 71 | for my $language(@$languages) { | ||||
| 72 | print "$language->{language_code}\n"; # language code in iso 639-2 | ||||
| 73 | print "$language->{language_name}\n"; # language name in native script | ||||
| 74 | print "$language->{language_locale_name}\n"; # language name in current locale | ||||
| 75 | } | ||||
| 76 | |||||
| 77 | =cut | ||||
| 78 | |||||
| 79 | sub getFrameworkLanguages { | ||||
| 80 | # get a hash with all language codes, names, and locale names | ||||
| 81 | my $all_languages = getAllLanguages(); | ||||
| 82 | my @languages; | ||||
| 83 | |||||
| 84 | # find the available directory names | ||||
| 85 | my $dir=C4::Context->config('intranetdir')."/installer/data/"; | ||||
| 86 | opendir (MYDIR,$dir); | ||||
| 87 | my @listdir= grep { !/^\.|CVS/ && -d "$dir/$_"} readdir(MYDIR); | ||||
| 88 | closedir MYDIR; | ||||
| 89 | |||||
| 90 | # pull out all data for the dir names that exist | ||||
| 91 | for my $dirname (@listdir) { | ||||
| 92 | for my $language_set (@$all_languages) { | ||||
| 93 | |||||
| 94 | if ($dirname eq $language_set->{language_code}) { | ||||
| 95 | push @languages, { | ||||
| 96 | 'language_code'=>$dirname, | ||||
| 97 | 'language_description'=>$language_set->{language_description}, | ||||
| 98 | 'native_descrition'=>$language_set->{language_native_description} } | ||||
| 99 | } | ||||
| 100 | } | ||||
| 101 | } | ||||
| 102 | return \@languages; | ||||
| 103 | } | ||||
| 104 | |||||
| 105 | =head2 getTranslatedLanguages | ||||
| 106 | |||||
| 107 | Returns a reference to an array of hashes: | ||||
| 108 | |||||
| 109 | my $languages = getTranslatedLanguages(); | ||||
| 110 | print "Available translated languages:\n"; | ||||
| 111 | for my $language(@$trlanguages) { | ||||
| 112 | print "$language->{language_code}\n"; # language code in iso 639-2 | ||||
| 113 | print "$language->{language_name}\n"; # language name in native script | ||||
| 114 | print "$language->{language_locale_name}\n"; # language name in current locale | ||||
| 115 | } | ||||
| 116 | |||||
| 117 | =cut | ||||
| 118 | |||||
| 119 | sub getTranslatedLanguages { | ||||
| 120 | my ($interface, $theme, $current_language, $which) = @_; | ||||
| 121 | my $htdocs; | ||||
| 122 | my @languages; | ||||
| 123 | my @enabled_languages; | ||||
| 124 | |||||
| 125 | if ($interface && $interface eq 'opac' ) { | ||||
| 126 | @enabled_languages = split ",", C4::Context->preference('opaclanguages'); | ||||
| 127 | $htdocs = C4::Context->config('opachtdocs'); | ||||
| 128 | if ( $theme and -d "$htdocs/$theme" ) { | ||||
| 129 | (@languages) = _get_language_dirs($htdocs,$theme); | ||||
| 130 | } | ||||
| 131 | else { | ||||
| 132 | for my $theme ( _get_themes('opac') ) { | ||||
| 133 | push @languages, _get_language_dirs($htdocs,$theme); | ||||
| 134 | } | ||||
| 135 | } | ||||
| 136 | } | ||||
| 137 | elsif ($interface && $interface eq 'intranet' ) { | ||||
| 138 | @enabled_languages = split ",", C4::Context->preference('language'); | ||||
| 139 | $htdocs = C4::Context->config('intrahtdocs'); | ||||
| 140 | if ( $theme and -d "$htdocs/$theme" ) { | ||||
| 141 | @languages = _get_language_dirs($htdocs,$theme); | ||||
| 142 | } | ||||
| 143 | else { | ||||
| 144 | foreach my $theme ( _get_themes('intranet') ) { | ||||
| 145 | push @languages, _get_language_dirs($htdocs,$theme); | ||||
| 146 | } | ||||
| 147 | } | ||||
| 148 | } | ||||
| 149 | else { | ||||
| 150 | @enabled_languages = split ",", C4::Context->preference('opaclanguages'); | ||||
| 151 | my $htdocs = C4::Context->config('intrahtdocs'); | ||||
| 152 | foreach my $theme ( _get_themes('intranet') ) { | ||||
| 153 | push @languages, _get_language_dirs($htdocs,$theme); | ||||
| 154 | } | ||||
| 155 | $htdocs = C4::Context->config('opachtdocs'); | ||||
| 156 | foreach my $theme ( _get_themes('opac') ) { | ||||
| 157 | push @languages, _get_language_dirs($htdocs,$theme); | ||||
| 158 | } | ||||
| 159 | my %seen; | ||||
| 160 | $seen{$_}++ for @languages; | ||||
| 161 | @languages = keys %seen; | ||||
| 162 | } | ||||
| 163 | return _build_languages_arrayref(\@languages,$current_language,\@enabled_languages); | ||||
| 164 | } | ||||
| 165 | |||||
| 166 | =head2 getAllLanguages | ||||
| 167 | |||||
| 168 | Returns a reference to an array of hashes: | ||||
| 169 | |||||
| 170 | my $alllanguages = getAllLanguages(); | ||||
| 171 | print "Available translated languages:\n"; | ||||
| 172 | for my $language(@$alllanguages) { | ||||
| 173 | print "$language->{language_code}\n"; | ||||
| 174 | print "$language->{language_name}\n"; | ||||
| 175 | print "$language->{language_locale_name}\n"; | ||||
| 176 | } | ||||
| 177 | |||||
| 178 | =cut | ||||
| 179 | |||||
| 180 | sub getAllLanguages { | ||||
| 181 | my $lang = shift; | ||||
| 182 | # if no parameter is passed to the function, it returns english languages names | ||||
| 183 | # if a $lang parameter conforming to RFC4646 syntax is passed, the function returns languages names translated in $lang | ||||
| 184 | # if a language name is not translated in $lang in database, the function returns english language name | ||||
| 185 | my @languages_loop; | ||||
| 186 | my $dbh=C4::Context->dbh; | ||||
| 187 | my $default_language = 'en'; | ||||
| 188 | my $current_language = $default_language; | ||||
| 189 | if ($lang) { | ||||
| 190 | $current_language = regex_lang_subtags($lang)->{'language'}; | ||||
| 191 | } | ||||
| 192 | my $sth = $dbh->prepare('SELECT * FROM language_subtag_registry WHERE type=\'language\''); | ||||
| 193 | $sth->execute(); | ||||
| 194 | while (my $language_subtag_registry = $sth->fetchrow_hashref) { | ||||
| 195 | my $desc; | ||||
| 196 | # check if language name is stored in current language | ||||
| 197 | my $sth4= $dbh->prepare("SELECT description FROM language_descriptions WHERE type='language' AND subtag =? AND lang = ?"); | ||||
| 198 | $sth4->execute($language_subtag_registry->{subtag},$current_language); | ||||
| 199 | while (my $language_desc = $sth4->fetchrow_hashref) { | ||||
| 200 | $desc=$language_desc->{description}; | ||||
| 201 | } | ||||
| 202 | my $sth2= $dbh->prepare("SELECT * FROM language_descriptions LEFT JOIN language_rfc4646_to_iso639 on language_rfc4646_to_iso639.rfc4646_subtag = language_descriptions.subtag WHERE type='language' AND subtag =? AND language_descriptions.lang = ?"); | ||||
| 203 | if ($desc) { | ||||
| 204 | $sth2->execute($language_subtag_registry->{subtag},$current_language); | ||||
| 205 | } | ||||
| 206 | else { | ||||
| 207 | $sth2->execute($language_subtag_registry->{subtag},$default_language); | ||||
| 208 | } | ||||
| 209 | my $sth3 = $dbh->prepare("SELECT description FROM language_descriptions WHERE type='language' AND subtag=? AND lang=?"); | ||||
| 210 | # add the correct description info | ||||
| 211 | while (my $language_descriptions = $sth2->fetchrow_hashref) { | ||||
| 212 | $sth3->execute($language_subtag_registry->{subtag},$language_subtag_registry->{subtag}); | ||||
| 213 | my $native_description; | ||||
| 214 | while (my $description = $sth3->fetchrow_hashref) { | ||||
| 215 | $native_description = $description->{description}; | ||||
| 216 | } | ||||
| 217 | |||||
| 218 | # fill in the ISO6329 code | ||||
| 219 | $language_subtag_registry->{iso639_2_code} = $language_descriptions->{iso639_2_code}; | ||||
| 220 | # fill in the native description of the language, as well as the current language's translation of that if it exists | ||||
| 221 | if ($native_description) { | ||||
| 222 | $language_subtag_registry->{language_description} = $native_description; | ||||
| 223 | $language_subtag_registry->{language_description}.=" ($language_descriptions->{description})" if $language_descriptions->{description}; | ||||
| 224 | } | ||||
| 225 | else { | ||||
| 226 | $language_subtag_registry->{language_description} = $language_descriptions->{description}; | ||||
| 227 | } | ||||
| 228 | } | ||||
| 229 | push @languages_loop, $language_subtag_registry; | ||||
| 230 | } | ||||
| 231 | return \@languages_loop; | ||||
| 232 | } | ||||
| 233 | |||||
| 234 | =head2 _get_themes | ||||
| 235 | |||||
| 236 | Internal function, returns an array of all available themes. | ||||
| 237 | |||||
| 238 | (@themes) = &_get_themes('opac'); | ||||
| 239 | (@themes) = &_get_themes('intranet'); | ||||
| 240 | |||||
| 241 | =cut | ||||
| 242 | |||||
| 243 | sub _get_themes { | ||||
| 244 | my $interface = shift; | ||||
| 245 | my $htdocs; | ||||
| 246 | my @themes; | ||||
| 247 | if ( $interface eq 'intranet' ) { | ||||
| 248 | $htdocs = C4::Context->config('intrahtdocs'); | ||||
| 249 | } | ||||
| 250 | else { | ||||
| 251 | $htdocs = C4::Context->config('opachtdocs'); | ||||
| 252 | } | ||||
| 253 | opendir D, "$htdocs"; | ||||
| 254 | my @dirlist = readdir D; | ||||
| 255 | foreach my $directory (@dirlist) { | ||||
| 256 | # if there's an en dir, it's a valid theme | ||||
| 257 | -d "$htdocs/$directory/en" and push @themes, $directory; | ||||
| 258 | } | ||||
| 259 | return @themes; | ||||
| 260 | } | ||||
| 261 | |||||
| 262 | =head2 _get_language_dirs | ||||
| 263 | |||||
| 264 | Internal function, returns an array of directory names, excluding non-language directories | ||||
| 265 | |||||
| 266 | =cut | ||||
| 267 | |||||
| 268 | sub _get_language_dirs { | ||||
| 269 | my ($htdocs,$theme) = @_; | ||||
| 270 | my @lang_strings; | ||||
| 271 | opendir D, "$htdocs/$theme"; | ||||
| 272 | for my $lang_string ( readdir D ) { | ||||
| 273 | next if $lang_string =~/^\./; | ||||
| 274 | next if $lang_string eq 'all'; | ||||
| 275 | next if $lang_string =~/png$/; | ||||
| 276 | next if $lang_string =~/js$/; | ||||
| 277 | next if $lang_string =~/css$/; | ||||
| 278 | next if $lang_string =~/CVS$/; | ||||
| 279 | next if $lang_string =~/\.txt$/i; #Don't read the readme.txt ! | ||||
| 280 | next if $lang_string =~/img|images|famfam|js|less|lib|sound|pdf/; | ||||
| 281 | push @lang_strings, $lang_string; | ||||
| 282 | } | ||||
| 283 | return (@lang_strings); | ||||
| 284 | } | ||||
| 285 | |||||
| 286 | =head2 _build_languages_arrayref | ||||
| 287 | |||||
| 288 | Internal function for building the ref to array of hashes | ||||
| 289 | |||||
| 290 | FIXME: this could be rewritten and simplified using map | ||||
| 291 | |||||
| 292 | =cut | ||||
| 293 | |||||
| 294 | sub _build_languages_arrayref { | ||||
| 295 | my ($translated_languages,$current_language,$enabled_languages) = @_; | ||||
| 296 | my @translated_languages = @$translated_languages; | ||||
| 297 | my @languages_loop; # the final reference to an array of hashrefs | ||||
| 298 | my @enabled_languages = @$enabled_languages; | ||||
| 299 | # how many languages are enabled, if one, take note, some contexts won't need to display it | ||||
| 300 | my %seen_languages; # the language tags we've seen | ||||
| 301 | my %found_languages; | ||||
| 302 | my $language_groups; | ||||
| 303 | my $track_language_groups; | ||||
| 304 | my $current_language_regex = regex_lang_subtags($current_language); | ||||
| 305 | # Loop through the translated languages | ||||
| 306 | for my $translated_language (@translated_languages) { | ||||
| 307 | # separate the language string into its subtag types | ||||
| 308 | my $language_subtags_hashref = regex_lang_subtags($translated_language); | ||||
| 309 | |||||
| 310 | # is this language string 'enabled'? | ||||
| 311 | for my $enabled_language (@enabled_languages) { | ||||
| 312 | #warn "Checking out if $translated_language eq $enabled_language"; | ||||
| 313 | $language_subtags_hashref->{'enabled'} = 1 if $translated_language eq $enabled_language; | ||||
| 314 | } | ||||
| 315 | |||||
| 316 | # group this language, key by langtag | ||||
| 317 | $language_subtags_hashref->{'sublanguage_current'} = 1 if $translated_language eq $current_language; | ||||
| 318 | $language_subtags_hashref->{'rfc4646_subtag'} = $translated_language; | ||||
| 319 | $language_subtags_hashref->{'native_description'} = language_get_description($language_subtags_hashref->{language},$language_subtags_hashref->{language},'language'); | ||||
| 320 | $language_subtags_hashref->{'script_description'} = language_get_description($language_subtags_hashref->{script},$language_subtags_hashref->{'language'},'script'); | ||||
| 321 | $language_subtags_hashref->{'region_description'} = language_get_description($language_subtags_hashref->{region},$language_subtags_hashref->{'language'},'region'); | ||||
| 322 | $language_subtags_hashref->{'variant_description'} = language_get_description($language_subtags_hashref->{variant},$language_subtags_hashref->{'language'},'variant'); | ||||
| 323 | $track_language_groups->{$language_subtags_hashref->{'language'}}++; | ||||
| 324 | push ( @{ $language_groups->{$language_subtags_hashref->{language}} }, $language_subtags_hashref ); | ||||
| 325 | } | ||||
| 326 | # $key is a language subtag like 'en' | ||||
| 327 | while( my ($key, $value) = each %$language_groups) { | ||||
| 328 | |||||
| 329 | # is this language group enabled? are any of the languages within it enabled? | ||||
| 330 | my $enabled; | ||||
| 331 | for my $enabled_language (@enabled_languages) { | ||||
| 332 | my $regex_enabled_language = regex_lang_subtags($enabled_language); | ||||
| 333 | $enabled = 1 if $key eq $regex_enabled_language->{language}; | ||||
| 334 | } | ||||
| 335 | push @languages_loop, { | ||||
| 336 | # this is only use if there is one | ||||
| 337 | rfc4646_subtag => @$value[0]->{rfc4646_subtag}, | ||||
| 338 | native_description => language_get_description($key,$key,'language'), | ||||
| 339 | language => $key, | ||||
| 340 | sublanguages_loop => $value, | ||||
| 341 | plural => $track_language_groups->{$key} >1 ? 1 : 0, | ||||
| 342 | current => $current_language_regex->{language} eq $key ? 1 : 0, | ||||
| 343 | group_enabled => $enabled, | ||||
| 344 | }; | ||||
| 345 | } | ||||
| 346 | return \@languages_loop; | ||||
| 347 | } | ||||
| 348 | |||||
| 349 | sub language_get_description { | ||||
| 350 | my ($script,$lang,$type) = @_; | ||||
| 351 | my $dbh = C4::Context->dbh; | ||||
| 352 | my $desc; | ||||
| 353 | my $sth = $dbh->prepare("SELECT description FROM language_descriptions WHERE subtag=? AND lang=? AND type=?"); | ||||
| 354 | #warn "QUERY: SELECT description FROM language_descriptions WHERE subtag=$script AND lang=$lang AND type=$type"; | ||||
| 355 | $sth->execute($script,$lang,$type); | ||||
| 356 | while (my $descriptions = $sth->fetchrow_hashref) { | ||||
| 357 | $desc = $descriptions->{'description'}; | ||||
| 358 | } | ||||
| 359 | unless ($desc) { | ||||
| 360 | $sth = $dbh->prepare("SELECT description FROM language_descriptions WHERE subtag=? AND lang=? AND type=?"); | ||||
| 361 | $sth->execute($script,'en',$type); | ||||
| 362 | while (my $descriptions = $sth->fetchrow_hashref) { | ||||
| 363 | $desc = $descriptions->{'description'}; | ||||
| 364 | } | ||||
| 365 | } | ||||
| 366 | return $desc; | ||||
| 367 | } | ||||
| 368 | =head2 regex_lang_subtags | ||||
| 369 | |||||
| 370 | This internal sub takes a string composed according to RFC 4646 as | ||||
| 371 | an input and returns a reference to a hash containing keys and values | ||||
| 372 | for ( language, script, region, variant, extension, privateuse ) | ||||
| 373 | |||||
| 374 | =cut | ||||
| 375 | |||||
| 376 | sub regex_lang_subtags { | ||||
| 377 | my $string = shift; | ||||
| 378 | |||||
| 379 | # Regex for recognizing RFC 4646 well-formed tags | ||||
| 380 | # http://www.rfc-editor.org/rfc/rfc4646.txt | ||||
| 381 | |||||
| 382 | # regexes based on : http://unicode.org/cldr/data/tools/java/org/unicode/cldr/util/data/langtagRegex.txt | ||||
| 383 | # The structure requires no forward references, so it reverses the order. | ||||
| 384 | # The uppercase comments are fragments copied from RFC 4646 | ||||
| 385 | # | ||||
| 386 | # Note: the tool requires that any real "=" or "#" or ";" in the regex be escaped. | ||||
| 387 | |||||
| 388 | my $alpha = qr/[a-zA-Z]/ ; # ALPHA | ||||
| 389 | my $digit = qr/[0-9]/ ; # DIGIT | ||||
| 390 | my $alphanum = qr/[a-zA-Z0-9]/ ; # ALPHA / DIGIT | ||||
| 391 | my $x = qr/[xX]/ ; # private use singleton | ||||
| 392 | my $singleton = qr/[a-w y-z A-W Y-Z]/ ; # other singleton | ||||
| 393 | my $s = qr/[-]/ ; # separator -- lenient parsers will use [-_] | ||||
| 394 | |||||
| 395 | # Now do the components. The structure is slightly different to allow for capturing the right components. | ||||
| 396 | # The notation (?:....) is a non-capturing version of (...): so the "?:" can be deleted if someone doesn't care about capturing. | ||||
| 397 | |||||
| 398 | my $extlang = qr{(?: $s $alpha{3} )}x ; # *3("-" 3ALPHA) | ||||
| 399 | my $language = qr{(?: $alpha{2,3} | $alpha{4,8} )}x ; | ||||
| 400 | #my $language = qr{(?: $alpha{2,3}$extlang{0,3} | $alpha{4,8} )}x ; # (2*3ALPHA [ extlang ]) / 4ALPHA / 5*8ALPHA | ||||
| 401 | |||||
| 402 | my $script = qr{(?: $alpha{4} )}x ; # 4ALPHA | ||||
| 403 | |||||
| 404 | my $region = qr{(?: $alpha{2} | $digit{3} )}x ; # 2ALPHA / 3DIGIT | ||||
| 405 | |||||
| 406 | my $variantSub = qr{(?: $digit$alphanum{3} | $alphanum{5,8} )}x ; # *("-" variant), 5*8alphanum / (DIGIT 3alphanum) | ||||
| 407 | my $variant = qr{(?: $variantSub (?: $s$variantSub )* )}x ; # *("-" variant), 5*8alphanum / (DIGIT 3alphanum) | ||||
| 408 | |||||
| 409 | my $extensionSub = qr{(?: $singleton (?: $s$alphanum{2,8} )+ )}x ; # singleton 1*("-" (2*8alphanum)) | ||||
| 410 | my $extension = qr{(?: $extensionSub (?: $s$extensionSub )* )}x ; # singleton 1*("-" (2*8alphanum)) | ||||
| 411 | |||||
| 412 | my $privateuse = qr{(?: $x (?: $s$alphanum{1,8} )+ )}x ; # ("x"/"X") 1*("-" (1*8alphanum)) | ||||
| 413 | |||||
| 414 | # Define certain grandfathered codes, since otherwise the regex is pretty useless. | ||||
| 415 | # Since these are limited, this is safe even later changes to the registry -- | ||||
| 416 | # the only oddity is that it might change the type of the tag, and thus | ||||
| 417 | # the results from the capturing groups. | ||||
| 418 | # http://www.iana.org/assignments/language-subtag-registry | ||||
| 419 | # Note that these have to be compared case insensitively, requiring (?i) below. | ||||
| 420 | |||||
| 421 | my $grandfathered = qr{(?: (?i) | ||||
| 422 | en $s GB $s oed | ||||
| 423 | | i $s (?: ami | bnn | default | enochian | hak | klingon | lux | mingo | navajo | pwn | tao | tay | tsu ) | ||||
| 424 | | sgn $s (?: BE $s fr | BE $s nl | CH $s de) | ||||
| 425 | )}x; | ||||
| 426 | |||||
| 427 | # For well-formedness, we don't need the ones that would otherwise pass, so they are commented out here | ||||
| 428 | |||||
| 429 | # | art $s lojban | ||||
| 430 | # | cel $s gaulish | ||||
| 431 | # | en $s (?: boont | GB $s oed | scouse ) | ||||
| 432 | # | no $s (?: bok | nyn) | ||||
| 433 | # | zh $s (?: cmn | cmn $s Hans | cmn $s Hant | gan | guoyu | hakka | min | min $s nan | wuu | xiang | yue) | ||||
| 434 | |||||
| 435 | # Here is the final breakdown, with capturing groups for each of these components | ||||
| 436 | # The language, variants, extensions, grandfathered, and private-use may have interior '-' | ||||
| 437 | |||||
| 438 | #my $root = qr{(?: ($language) (?: $s ($script) )? 40% (?: $s ($region) )? 40% (?: $s ($variant) )? 10% (?: $s ($extension) )? 5% (?: $s ($privateuse) )? 5% ) 90% | ($grandfathered) 5% | ($privateuse) 5% }; | ||||
| 439 | |||||
| 440 | $string =~ qr{^ (?:($language)) (?:$s($script))? (?:$s($region))? (?:$s($variant))? (?:$s($extension))? (?:$s($privateuse))? $}xi; # |($grandfathered) | ($privateuse) $}xi; | ||||
| 441 | my %subtag = ( | ||||
| 442 | 'rfc4646_subtag' => $string, | ||||
| 443 | 'language' => $1, | ||||
| 444 | 'script' => $2, | ||||
| 445 | 'region' => $3, | ||||
| 446 | 'variant' => $4, | ||||
| 447 | 'extension' => $5, | ||||
| 448 | 'privateuse' => $6, | ||||
| 449 | ); | ||||
| 450 | return \%subtag; | ||||
| 451 | } | ||||
| 452 | |||||
| 453 | # Script Direction Resources: | ||||
| 454 | # http://www.w3.org/International/questions/qa-scripts | ||||
| 455 | sub get_bidi { | ||||
| 456 | my ($language_script)= @_; | ||||
| 457 | my $dbh = C4::Context->dbh; | ||||
| 458 | my $bidi; | ||||
| 459 | my $sth = $dbh->prepare('SELECT bidi FROM language_script_bidi WHERE rfc4646_subtag=?'); | ||||
| 460 | $sth->execute($language_script); | ||||
| 461 | while (my $result = $sth->fetchrow_hashref) { | ||||
| 462 | $bidi = $result->{'bidi'}; | ||||
| 463 | } | ||||
| 464 | return $bidi; | ||||
| 465 | }; | ||||
| 466 | |||||
| 467 | sub accept_language { | ||||
| 468 | # referenced http://search.cpan.org/src/CGILMORE/I18N-AcceptLanguage-1.04/lib/I18N/AcceptLanguage.pm | ||||
| 469 | my ($clientPreferences,$supportedLanguages) = @_; | ||||
| 470 | my @languages = (); | ||||
| 471 | if ($clientPreferences) { | ||||
| 472 | # There should be no whitespace anways, but a cleanliness/sanity check | ||||
| 473 | $clientPreferences =~ s/\s//g; | ||||
| 474 | # Prepare the list of client-acceptable languages | ||||
| 475 | foreach my $tag (split(/,/, $clientPreferences)) { | ||||
| 476 | my ($language, $quality) = split(/\;/, $tag); | ||||
| 477 | $quality =~ s/^q=//i if $quality; | ||||
| 478 | $quality = 1 unless $quality; | ||||
| 479 | next if $quality <= 0; | ||||
| 480 | # We want to force the wildcard to be last | ||||
| 481 | $quality = 0 if ($language eq '*'); | ||||
| 482 | # Pushing lowercase language here saves processing later | ||||
| 483 | push(@languages, { quality => $quality, | ||||
| 484 | language => $language, | ||||
| 485 | lclanguage => lc($language) }); | ||||
| 486 | } | ||||
| 487 | } else { | ||||
| 488 | carp "accept_language(x,y) called with no clientPreferences (x)."; | ||||
| 489 | } | ||||
| 490 | # Prepare the list of server-supported languages | ||||
| 491 | my %supportedLanguages = (); | ||||
| 492 | my %secondaryLanguages = (); | ||||
| 493 | foreach my $language (@$supportedLanguages) { | ||||
| 494 | # warn "Language supported: " . $language->{language}; | ||||
| 495 | my $subtag = $language->{rfc4646_subtag}; | ||||
| 496 | $supportedLanguages{lc($subtag)} = $subtag; | ||||
| 497 | if ( $subtag =~ /^([^-]+)-?/ ) { | ||||
| 498 | $secondaryLanguages{lc($1)} = $subtag; | ||||
| 499 | } | ||||
| 500 | } | ||||
| 501 | |||||
| 502 | # Reverse sort the list, making best quality at the front of the array | ||||
| 503 | @languages = sort { $b->{quality} <=> $a->{quality} } @languages; | ||||
| 504 | my $secondaryMatch = ''; | ||||
| 505 | foreach my $tag (@languages) { | ||||
| 506 | if (exists($supportedLanguages{$tag->{lclanguage}})) { | ||||
| 507 | # Client en-us eq server en-us | ||||
| 508 | return $supportedLanguages{$tag->{language}} if exists($supportedLanguages{$tag->{language}}); | ||||
| 509 | return $supportedLanguages{$tag->{lclanguage}}; | ||||
| 510 | } elsif (exists($secondaryLanguages{$tag->{lclanguage}})) { | ||||
| 511 | # Client en eq server en-us | ||||
| 512 | return $secondaryLanguages{$tag->{language}} if exists($secondaryLanguages{$tag->{language}}); | ||||
| 513 | return $supportedLanguages{$tag->{lclanguage}}; | ||||
| 514 | } elsif ($tag->{lclanguage} =~ /^([^-]+)-/ && exists($secondaryLanguages{$1}) && $secondaryMatch eq '') { | ||||
| 515 | # Client en-gb eq server en-us | ||||
| 516 | $secondaryMatch = $secondaryLanguages{$1}; | ||||
| 517 | } elsif ($tag->{lclanguage} =~ /^([^-]+)-/ && exists($secondaryLanguages{$1}) && $secondaryMatch eq '') { | ||||
| 518 | # FIXME: We just checked the exact same conditional! | ||||
| 519 | # Client en-us eq server en | ||||
| 520 | $secondaryMatch = $supportedLanguages{$1}; | ||||
| 521 | } elsif ($tag->{lclanguage} eq '*') { | ||||
| 522 | # * matches every language not already specified. | ||||
| 523 | # It doesn't care which we pick, so let's pick the default, | ||||
| 524 | # if available, then the first in the array. | ||||
| 525 | #return $acceptor->defaultLanguage() if $acceptor->defaultLanguage(); | ||||
| 526 | return $supportedLanguages->[0]; | ||||
| 527 | } | ||||
| 528 | } | ||||
| 529 | # No primary matches. Secondary? (ie, en-us requested and en supported) | ||||
| 530 | return $secondaryMatch if $secondaryMatch; | ||||
| 531 | return undef; # else, we got nothing. | ||||
| 532 | } | ||||
| 533 | 1 | 6µs | 1; | ||
| 534 | |||||
| 535 | __END__ |