Changeset 2594 for branches/release-40/extlib/I18N/LangTags/List.pm

Timestamp:

06/18/08 02:03:47 (18 months ago)

Author:

fumiakiy

Message:

Updating I18N::LangTags to version 0.35 and Locale::MakeText to version 1.13 for better support of Perl 5.10. BugId:80126

Files:

• branches/release-40/extlib/I18N/LangTags/List.pm (modified) (47 diffs)

branches/release-40/extlib/I18N/LangTags/List.pm

@@ -2 +2 @@
 require 5;
 package I18N::LangTags::List;
-#  Time-stamp: "2002-02-02 20:13:58 MST"
+#  Time-stamp: "2004-10-06 23:26:21 ADT"
 use strict;
-use vars qw(%Name $Debug $VERSION);
-$VERSION = '0.25';
+use vars qw(%Name %Is_Disrec $Debug $VERSION);
+$VERSION = '0.35';
 # POD at the end.
 
@@ -13 +13 @@
   my $seeking = 1;
   my $count = 0;
-  my($tag,$name);
+  my($disrec,$tag,$name);
+  my $last_name = '';
   while(<I18N::LangTags::List::DATA>) {
     if($seeking) {
       $seeking = 0 if m/=for woohah/;
-    } else {
-      next unless ($tag, $name) =
-       m/\{([-0-9a-zA-Z]+)\}(?:\s*:)?\s*([^\[\]]+)/;
+    } elsif( ($disrec, $tag, $name) =
+          m/(\[?)\{([-0-9a-zA-Z]+)\}(?:\s*:)?\s*([^\[\]]+)/
+    ) {
       $name =~ s/\s*[;\.]*\s*$//g;
       next unless $name;
       ++$count;
       print "<$tag> <$name>\n" if $Debug;
-      $Name{$tag} = $name;
+      $last_name = $Name{$tag} = $name;
+      $Is_Disrec{$tag} = 1 if $disrec;
+    } elsif (m/[Ff]ormerly \"([-a-z0-9]+)\"/) {
+      $Name{$1} = "$last_name (old tag)" if $last_name;
+      $Is_Disrec{$1} = 1;
     }
   }
@@ -72 +77 @@
 }
 
+#--------------------------------------------------------------------------
+
+sub is_decent {
+  my $tag = lc($_[0] || return 0);
+  #require I18N::LangTags;
+
+  return 0 unless
+    $tag =~ 
+    /^(?:  # First subtag
+         [xi] | [a-z]{2,3}
+      )
+      (?:  # Subtags thereafter
+         -           # separator
+         [a-z0-9]{1,8}  # subtag  
+      )*
+    $/xs;
+
+  my @supers = ();
+  foreach my $bit (split('-', $tag)) {
+    push @supers, 
+      scalar(@supers) ? ($supers[-1] . '-' . $bit) : $bit;
+  }
+  return 0 unless @supers;
+  shift @supers if $supers[0] =~ m<^(i|x|sgn)$>s;
+  return 0 unless @supers;
+
+  foreach my $f ($tag, @supers) {
+    return 0 if $Is_Disrec{$f};
+    return 2 if $Name{$f};
+     # so that decent subforms of indecent tags are decent
+  }
+  return 2 if $Name{$tag}; # not only is it decent, it's known!
+  return 1;
+}
+
+#--------------------------------------------------------------------------
 1;
 
@@ -103 +144 @@
 
 The function I18N::LangTags::List::name(...) is not exported.
+
+This module also provides a function
+C<I18N::LangTags::List::is_decent( I<langtag> )> that returns true iff
+the language tag is syntactically valid and is for general use (like
+"fr" or "fr-ca", below).  That is, it returns false for tags that are
+syntactically invalid and for tags, like "aus", that are listed in
+brackets below.  This function is not exported.
 
 The map of tags-to-names that it uses is accessable as
@@ -196 +244 @@
 =item {ada} : Adangme
 
+=item {ady} : Adyghe
+
+eq Adygei
+
 =item {aa} : Afar
 
@@ -206 +258 @@
 =item [{afa} : Afro-Asiatic (Other)]
 
-=item {aka} : Akan
+=item {ak} : Akan
+
+(Formerly "aka".)
 
 =item {akk} : Akkadian
@@ -265 +319 @@
 =item {hy} : Armenian
 
+=item {an} : Aragonese
+
 =item [{art} : Artificial (Other)]
 
+=item {ast} : Asturian
+
+eq Bable.
+
 =item {as} : Assamese
 
@@ -277 +337 @@
 =item [{map} : Austronesian (Other)]
 
-=item {ava} : Avaric
+=item {av} : Avaric
+
+(Formerly "ava".)
 
 =item {ae} : Avestan
@@ -291 +353 @@
 eq Azeri
 
+Notable forms:
+{az-Arab} Azerbaijani in Arabic script;
+{az-Cyrl} Azerbaijani in Cyrillic script;
+{az-Latn} Azerbaijani in Latin script.
+
 =item {ban} : Balinese
 
@@ -297 +364 @@
 =item {bal} : Baluchi
 
-=item {bam} : Bambara
+=item {bm} : Bambara
+
+(Formerly "bam".)
 
 =item [{bai} : Bamileke languages]
@@ -404 +473 @@
 
 Many forms are mutually un-intelligible in spoken media.
-Notable subforms:
+Notable forms:
+{zh-Hans} Chinese, in simplified script;
+{zh-Hant} Chinese, in traditional script;
+{zh-tw} Taiwan Chinese;
 {zh-cn} PRC Chinese;
+{zh-sg} Singapore Chinese;
+{zh-mo} Macau Chinese;
 {zh-hk} Hong Kong Chinese;
-{zh-mo} Macau Chinese;
-{zh-sg} Singapore Chinese;
-{zh-tw} Taiwan Chinese;
 {zh-guoyu} Mandarin [Putonghua/Guoyu];
-{zh-hakka} Hakka [formerly i-hakka];
+{zh-hakka} Hakka [formerly "i-hakka"];
 {zh-min} Hokkien;
 {zh-min-nan} Southern Hokkien;
@@ -448 +519 @@
 eq Corse.
 
-=item {cre} : Cree
-
-NOT Creek!
+=item {cr} : Cree
+
+NOT Creek!  (Formerly "cre".)
 
 =item {mus} : Creek
@@ -477 +548 @@
 
 =item {da} : Danish
+
+=item {dar} : Dargwa
 
 =item {day} : Dayak
@@ -492 +565 @@
 =item {din} : Dinka
 
-=item {div} : Divehi
+=item {dv} : Divehi
+
+eq Maldivian.  (Formerly "div".)
 
 =item {doi} : Dogri
@@ -556 +631 @@
 eq Anglo-Saxon.  (Historical)
 
+=item {i-enochian} : Enochian (Artificial)
+
+=item {myv} : Erzya
+
 =item {eo} : Esperanto
 
@@ -562 +641 @@
 =item {et} : Estonian
 
-=item {ewe} : Ewe
+=item {ee} : Ewe
+
+(Formerly "ewe".)
 
 =item {ewo} : Ewondo
@@ -604 +685 @@
 =item {fur} : Friulian
 
-=item {ful} : Fulah
+=item {ff} : Fulah
+
+(Formerly "ful".)
 
 =item {gaa} : Ga
@@ -616 +699 @@
 eq Galician
 
-=item {lug} : Ganda
+=item {lg} : Ganda
+
+(Formerly "lug".)
 
 =item {gay} : Gayo
@@ -680 +765 @@
 =item {hai} : Haida
 
+=item {ht} : Haitian
+
+eq Haitian Creole
+
 =item {ha} : Hausa
 
@@ -717 +806 @@
 =item {is} : Icelandic
 
-=item {ibo} : Igbo
+=item {io} : Ido
+
+(Artificial)
+
+=item {ig} : Igbo
+
+(Formerly "ibo".)
 
 =item {ijo} : Ijo
@@ -733 +828 @@
 =for etc
 {in} Indonesian (old tag)
+
+=item {inh} : Ingush
 
 =item {ia} : Interlingua (International Auxiliary Language Association)
@@ -774 +871 @@
 (NOT "jp"!)
 
-=item {jw} : Javanese
+=item {jv} : Javanese
+
+(Formerly "jw" because of a typo.)
 
 =item {jrb} : Judeo-Arabic
@@ -780 +879 @@
 =item {jpr} : Judeo-Persian
 
+=item {kbd} : Kabardian
+
 =item {kab} : Kabyle
 
@@ -788 +889 @@
 eq Greenlandic "Eskimo"
 
+=item {xal} : Kalmyk
+
 =item {kam} : Kamba
 
@@ -794 +897 @@
 eq Kanarese.  NOT Canadian!
 
-=item {kau} : Kanuri
+=item {kr} : Kanuri
+
+(Formerly "kau".)
+
+=item {krc} : Karachay-Balkar
 
 =item {kaa} : Kara-Kalpak
@@ -802 +909 @@
 =item {ks} : Kashmiri
 
+=item {csb} : Kashubian
+
+eq Kashub
+
 =item {kaw} : Kawi
 
@@ -830 +941 @@
 =item {kv} : Komi
 
-=item {kon} : Kongo
+=item {kg} : Kongo
+
+(Formerly "kon".)
 
 =item {kok} : Konkani
@@ -878 +991 @@
 =item {lb} : Letzeburgesch
 
-eq Luxemburgian, eq Luxemburger.  (Formerly i-lux.)
+eq Luxemburgian, eq Luxemburger.  (Formerly "i-lux".)
 
 =for etc
@@ -885 +998 @@
 =item {lez} : Lezghian
 
+=item {li} : Limburgish
+
+eq Limburger, eq Limburgan.  NOT Letzeburgesch!
+
 =item {ln} : Lingala
 
@@ -893 +1010 @@
 eq Low Saxon.  eq Low German.  eq Low Saxon.
 
+=item {art-lojban} : Lojban (Artificial)
+
 =item {loz} : Lozi
 
-=item {lub} : Luba-Katanga
+=item {lu} : Luba-Katanga
+
+(Formerly "lub".)
 
 =item {lua} : Luba-Lulua
@@ -986 +1107 @@
 =item {moh} : Mohawk
 
+=item {mdf} : Moksha
+
 =item {mo} : Moldavian
 
@@ -1008 +1131 @@
 =item {nah} : Nahuatl
 
+=item {nap} : Neapolitan
+
 =item {na} : Nauru
 
 =item {nv} : Navajo
 
-eq Navaho.  (Formerly i-navajo.)
+eq Navaho.  (Formerly "i-navajo".)
 
 =for etc
@@ -1039 +1164 @@
 =item {niu} : Niuean
 
+=item {nog} : Nogai
+
 =item {non} : Old Norse
 
@@ -1047 +1174 @@
 Do not use this.
 
-=item {se} : Northern Sami
-
-eq Lappish.  eq Lapp.  eq (Northern) Saami.
-
 =item {no} : Norwegian
 
@@ -1057 +1180 @@
 =item {nb} : Norwegian Bokmal
 
-eq BokmE<aring>l, (A form of Norwegian.)  (Formerly no-bok.)
+eq BokmE<aring>l, (A form of Norwegian.)  (Formerly "no-bok".)
 
 =for etc
@@ -1064 +1187 @@
 =item {nn} : Norwegian Nynorsk
 
-(A form of Norwegian.)  (Formerly no-nyn.)
+(A form of Norwegian.)  (Formerly "no-nyn".)
 
 =for etc
@@ -1083 +1206 @@
 eq ProvenE<ccedil>al, eq Provencal
 
-=item {oji} : Ojibwa
-
-eq Ojibwe.
+=item {oj} : Ojibwa
+
+eq Ojibwe.  (Formerly "oji".)
 
 =item {or} : Oriya
@@ -1203 +1326 @@
 NOT Aramaic!
 
+=item {se} : Northern Sami
+
+eq Lappish.  eq Lapp.  eq (Northern) Saami.
+
+=item {sma} : Southern Sami
+
+=item {smn} : Inari Sami
+
+=item {smj} : Lule Sami
+
+=item {sms} : Skolt Sami
+
 =item [{smi} : Sami languages (Other)]
 
@@ -1234 +1369 @@
 
 eq Serb.  NOT Sorbian.
+
+Notable forms:
+{sr-Cyrl} : Serbian in Cyrillic script;
+{sr-Latn} : Serbian in Latin script.
 
 =item {srr} : Serer
@@ -1250 +1389 @@
 {sgn-ni} Nicaraguan Sign Language (ISN);
 {sgn-us} American Sign Language (ASL).
+
+(And so on with other country codes as the subtag.)
 
 =item {bla} : Siksika
@@ -1423 +1564 @@
 =item {tum} : Tumbuka
 
+=item [{tup} : Tupi languages]
+
 =item {tr} : Turkish
 
@@ -1431 +1574 @@
 (Typically in Arabic script)  (Historical)
 
+=item {crh} : Crimean Turkish
+
+eq Crimean Tatar
+
 =item {tk} : Turkmen
 
@@ -1443 +1590 @@
 =item {tw} : Twi
 
+=item {udm} : Udmurt
+
 =item {uga} : Ugaritic
 
@@ -1463 +1612 @@
 eq E<Ouml>zbek
 
+Notable forms:
+{uz-Cyrl} Uzbek in Cyrillic script;
+{uz-Latn} Uzbek in Latin script.
+
 =item {vai} : Vai
 
-=item {ven} : Venda
-
-NOT Wendish!  NOT Wend!  NOT Avestan!
+=item {ve} : Venda
+
+NOT Wendish!  NOT Wend!  NOT Avestan!  (Formerly "ven".)
 
 =item {vi} : Vietnamese
@@ -1482 +1635 @@
 
 =item [{wak} : Wakashan languages]
+
+=item {wa} : Walloon
 
 =item {wal} : Walamo
@@ -1518 +1673 @@
 eq Yap
 
+=item {ii} : Sichuan Yi
+
 =item {yi} : Yiddish
 
-Formerly "ji".  Sometimes in Roman script, sometimes in Hebrew script.
-
-=for etc
-{ji} Yiddish (old tag)
+Formerly "ji".  Usually in Hebrew script.
+
+Notable forms:
+{yi-latn} Yiddish in Latin script
 
 =item {yo} : Yoruba
@@ -1559 +1716 @@
 =head1 COPYRIGHT AND DISCLAIMER
 
-Copyright (c) 2001,2002 Sean M. Burke. All rights reserved.
+Copyright (c) 2001+ Sean M. Burke. All rights reserved.
 
 You can redistribute and/or