tests/phpunit/includes/GlobalFunctions/wfBCP47Test.php

   1 <?php
   2 /**
   3  * Tests for wfBCP47()
   4  */
   5 class WfBCP47Test extends MediaWikiTestCase {
   6         /**
   7          * test @see wfBCP47().
   8          * Please note the BCP explicitly state that language codes are case
   9          * insensitive, there are some exceptions to the rule :)
  10          * This test is used to verify our formatting against all lower and
  11          * all upper cases language code.
  12          *
  13          * @see http://tools.ietf.org/html/bcp47
  14          * @dataProvider provideLanguageCodes()
  15          */
  16         function testBCP47( $code, $expected ) {
  17                 $code = strtolower( $code );
  18                 $this->assertEquals( $expected, wfBCP47( $code ),
  19                         "Applying BCP47 standard to lower case '$code'"
  20                 );
  21
  22                 $code = strtoupper( $code );
  23                 $this->assertEquals( $expected, wfBCP47( $code ),
  24                         "Applying BCP47 standard to upper case '$code'"
  25                 );
  26         }
  27
  28         /**
  29          * Array format is ($code, $expected)
  30          */
  31         public static function provideLanguageCodes() {
  32                 return array(
  33                         // Extracted from BCP47 (list not exhaustive)
  34                         # 2.1.1
  35                         array( 'en-ca-x-ca', 'en-CA-x-ca' ),
  36                         array( 'sgn-be-fr', 'sgn-BE-FR' ),
  37                         array( 'az-latn-x-latn', 'az-Latn-x-latn' ),
  38                         # 2.2
  39                         array( 'sr-Latn-RS', 'sr-Latn-RS' ),
  40                         array( 'az-arab-ir', 'az-Arab-IR' ),
  41
  42                         # 2.2.5
  43                         array( 'sl-nedis', 'sl-nedis' ),
  44                         array( 'de-ch-1996', 'de-CH-1996' ),
  45
  46                         # 2.2.6
  47                         array(
  48                                 'en-latn-gb-boont-r-extended-sequence-x-private',
  49                                 'en-Latn-GB-boont-r-extended-sequence-x-private'
  50                         ),
  51
  52                         // Examples from BCP47 Appendix A
  53                         # Simple language subtag:
  54                         array( 'DE', 'de' ),
  55                         array( 'fR', 'fr' ),
  56                         array( 'ja', 'ja' ),
  57
  58                         # Language subtag plus script subtag:
  59                         array( 'zh-hans', 'zh-Hans' ),
  60                         array( 'sr-cyrl', 'sr-Cyrl' ),
  61                         array( 'sr-latn', 'sr-Latn' ),
  62
  63                         # Extended language subtags and their primary language subtag
  64                         # counterparts:
  65                         array( 'zh-cmn-hans-cn', 'zh-cmn-Hans-CN' ),
  66                         array( 'cmn-hans-cn', 'cmn-Hans-CN' ),
  67                         array( 'zh-yue-hk', 'zh-yue-HK' ),
  68                         array( 'yue-hk', 'yue-HK' ),
  69
  70                         # Language-Script-Region:
  71                         array( 'zh-hans-cn', 'zh-Hans-CN' ),
  72                         array( 'sr-latn-RS', 'sr-Latn-RS' ),
  73
  74                         # Language-Variant:
  75                         array( 'sl-rozaj', 'sl-rozaj' ),
  76                         array( 'sl-rozaj-biske', 'sl-rozaj-biske' ),
  77                         array( 'sl-nedis', 'sl-nedis' ),
  78
  79                         # Language-Region-Variant:
  80                         array( 'de-ch-1901', 'de-CH-1901' ),
  81                         array( 'sl-it-nedis', 'sl-IT-nedis' ),
  82
  83                         # Language-Script-Region-Variant:
  84                         array( 'hy-latn-it-arevela', 'hy-Latn-IT-arevela' ),
  85
  86                         # Language-Region:
  87                         array( 'de-de', 'de-DE' ),
  88                         array( 'en-us', 'en-US' ),
  89                         array( 'es-419', 'es-419' ),
  90
  91                         # Private use subtags:
  92                         array( 'de-ch-x-phonebk', 'de-CH-x-phonebk' ),
  93                         array( 'az-arab-x-aze-derbend', 'az-Arab-x-aze-derbend' ),
  94                         /**
  95                          * Previous test does not reflect the BCP which states:
  96                          *  az-Arab-x-AZE-derbend
  97                          * AZE being private, it should be lower case, hence the test above
  98                          * should probably be:
  99                         #array( 'az-arab-x-aze-derbend', 'az-Arab-x-AZE-derbend' ),
 100                          */
 101
 102                         # Private use registry values:
 103                         array( 'x-whatever', 'x-whatever' ),
 104                         array( 'qaa-qaaa-qm-x-southern', 'qaa-Qaaa-QM-x-southern' ),
 105                         array( 'de-qaaa', 'de-Qaaa' ),
 106                         array( 'sr-latn-qm', 'sr-Latn-QM' ),
 107                         array( 'sr-qaaa-rs', 'sr-Qaaa-RS' ),
 108
 109                         # Tags that use extensions
 110                         array( 'en-us-u-islamcal', 'en-US-u-islamcal' ),
 111                         array( 'zh-cn-a-myext-x-private', 'zh-CN-a-myext-x-private' ),
 112                         array( 'en-a-myext-b-another', 'en-a-myext-b-another' ),
 113
 114                         # Invalid:
 115                         // de-419-DE
 116                         // a-DE
 117                         // ar-a-aaa-b-bbb-a-ccc
 118
 119                         /*
 120                         // ISO 15924 :
 121                         array( 'sr-Cyrl', 'sr-Cyrl' ),
 122                         # @todo FIXME: Fix our function?
 123                         array( 'SR-lATN', 'sr-Latn' ),
 124                         array( 'fr-latn', 'fr-Latn' ),
 125                         // Use lowercase for single segment
 126                         // ISO 3166-1-alpha-2 code
 127                         array( 'US', 'us' ),  # USA
 128                         array( 'uS', 'us' ),  # USA
 129                         array( 'Fr', 'fr' ),  # France
 130                         array( 'va', 'va' ),  # Holy See (Vatican City State)
 131                          */
 132                 );
 133         }
 134 }