Skip to content

Latest commit

 

History

History
649 lines (632 loc) · 21.3 KB

README.rst

File metadata and controls

649 lines (632 loc) · 21.3 KB
Raw

About

Provides transliteration functions between different scripts in use by different languages.

For example, this can provide conversions between Cyrillic and Latin. In order to provide consistent naming standard for language code/scripts/variants/territories, the iso_tools module is employed, with the format (2-letter <a href="https://en.wikipedia.org/wiki/ISO_639-1">ISO 639-1</a> code or 3-letter <a href="https://en.wikipedia.org/wiki/ISO_639-3">ISO 639-3</a> code)_(<a href="https://en.wikipedia.org/wiki/ISO_15924">ISO 15924</a> script code)-(ISO ???? territory code)|(other variant code, such as hex(adecimal), etc). Note that Zyyy is "Code for undetermined script" in ISO 15924.

It uses tables and engines from multiple sources:

  • ICU: ...
  • Korean: ...
  • Internal: My own engine

Install

Usage

>>> from multi_translit import MultiTranslit, translit, get_scripts_dict

>>> MultiTranslit.mapping_to_iso
???

>>> MultiTranslit.get_possible_conversions_list('ja_Latn', 'ja-Hira')
[(u'ja_Latn', u'ja-Hrkt'), (u'ja_Latn', u'ja-Hira'), (u'ja_Latn', u'ja-Kana'), ('Latn', u'Latn|ASCII')]

>>> MultiTranslit.get_best_conversion('ja', 'ja_Latn')
(u'ja', 'Latn')

>>> MultiTranslit.get_best_conversions_list('ja', 'ja_Latn')
[(u'ja', 'Latn')]

MultiTranslit.get_L_all_conversions('ja', 'ja_Latn')
MultiTranslit.translit('ja_Latn', 'ja-Hira', 'nihonngo')

# Get all possible conversions, indexed by "from" (or source) script
>>> pprint(MultiTranslit.get_scripts_dict())
{u'Latn': [u'Latn|ASCII'],
 u'Latn|ASCII': [u'Latn'],
 u'Latn|FONIPA': [u'Latn|FONXSAMP'],
 u'Latn|FONXSAMP': [u'Latn|FONIPA', u'|FONIPA'],
 u'Latn|x-Accents': [u'Zyyy'],
 u'Latn|x-Fullwidth': [u'Latn|x-Halfwidth'],
 u'Latn|x-Halfwidth': [u'Latn|x-Fullwidth'],
 u'Zyyy': [u'Zyyy|Hex/C',
           u'Zyyy|Hex',
           u'Zyyy|Hex/XML10',
           u'Zyyy|x-Publishing',
           u'Zyyy|Title',
           u'Zyyy|FCD',
           u'Zyyy|Hex/Unicode',
           u'Zyyy|Upper',
           u'Zyyy|Name',
           u'Zyyy|Hex/XML',
           u'Latn|x-Accents',
           u'Latn|BGN',
           u'Zyyy|NFKD',
           u'Zyyy|FCC',
           u'Zyyy|NFKC',
           u'Zyyy|Hex/Perl',
           u'Latn|FONXSAMP',
           u'Zyyy',
           u'Latn',
           u'Zyyy|NFD',
           u'Zyyy|Hex/Java',
           u'Zyyy|Null',
           u'Zyyy|NFC',
           u'Zyyy|Remove',
           u'|FONIPA',
           u'Zyyy|Lower'],
 u'Zyyy|Any/C': [u'Zyyy|Hex'],
 u'Zyyy|Any/Java': [u'Zyyy|Hex'],
 u'Zyyy|Any/Perl': [u'Zyyy|Hex'],
 u'Zyyy|Any/Unicode': [u'Zyyy|Hex'],
 u'Zyyy|Any/XML': [u'Zyyy|Hex'],
 u'Zyyy|Any/XML10': [u'Zyyy|Hex'],
 u'Zyyy|Digit': [u'Zyyy|Tone'],
 u'Zyyy|FCC': [u'Zyyy'],
 u'Zyyy|FCD': [u'Zyyy'],
 u'Zyyy|Hex': [u'Zyyy|Any/Java',
               u'Zyyy|Any/C',
               u'Zyyy|Any/Perl',
               u'Zyyy|Any/XML',
               u'Zyyy|Any/XML10',
               u'Zyyy|Any/Unicode',
               u'Zyyy'],
 u'Zyyy|Hex/C': [u'Zyyy'],
 u'Zyyy|Hex/Java': [u'Zyyy'],
 u'Zyyy|Hex/Perl': [u'Zyyy'],
 u'Zyyy|Hex/Unicode': [u'Zyyy'],
 u'Zyyy|Hex/XML': [u'Zyyy'],
 u'Zyyy|Hex/XML10': [u'Zyyy'],
 u'Zyyy|Lower': [u'Zyyy'],
 u'Zyyy|NFC': [u'Zyyy'],
 u'Zyyy|NFD': [u'Zyyy'],
 u'Zyyy|NFKC': [u'Zyyy'],
 u'Zyyy|NFKD': [u'Zyyy'],
 u'Zyyy|Name': [u'Zyyy'],
 u'Zyyy|Null': [u'Zyyy'],
 u'Zyyy|Remove': [u'Zyyy'],
 u'Zyyy|Title': [u'Zyyy'],
 u'Zyyy|Tone': [u'Zyyy|Digit'],
 u'Zyyy|Upper': [u'Zyyy'],
 u'Zyyy|x-Publishing': [u'Zyyy'],
 u'am': [u'ar', u'am_Latn|BGN', u'am|FONIPA', u'fa'],
 u'am|FONIPA': [u'am'],
 u'ar': [u'ar|FONIPA',
         u'sk',
         u'ar_Latn|BGN',
         u'es|419',
         u'ar_Latn|UNGEGN',
         u'ro',
         u'pl',
         u'ar_Latn',
         u'cs',
         u'es'],
 u'ar_Latn': [u'ar'],
 u'ar_Latn|BGN': [u'ar'],
 u'ar_Latn|UNGEGN': [u'ar'],
 u'ar|Compatibility': [u'ar'],
 u'ar|FONIPA': [u'ar'],
 u'az': [u'az_Latn|BGN', u'az_Zyyy|Upper', u'az_Zyyy|Title', u'az_Zyyy|Lower'],
 u'az-IR': [u'az'],
 u'az_Cyrl': [u'az_Latn|AllWorth', u'az_Latn|ALA-LC', u'az_Latn|ISO 9'],
 u'az_Latn|ALA-LC': [u'az_Cyrl'],
 u'az_Latn|AllWorth': [u'az_Cyrl'],
 u'az_Latn|ISO 9': [u'az_Cyrl'],
 u'az_Zyyy': [u'az_Latn|BGN'],
 u'be': [u'be_Latn|BGN/PCGN',
         u'be_Latn|UNGEGN',
         u'be_Latn|\u0141acinka',
         u'be_Latn|ALA-LC',
         u'be_Latn|Official',
         u'be_Latn|BGN'],
 u'be_Latn|ALA-LC': [u'be'],
 u'be_Latn|BGN/PCGN': [u'be'],
 u'be_Latn|Official': [u'be'],
 u'be_Latn|UNGEGN': [u'be'],
 u'be_Latn|\u0141acinka': [u'be'],
 u'be_Zyyy': [u'be_Latn|BGN'],
 u'bg': [u'bg_Latn|ALA-LC',
         u'bg_Latn|BGN',
         u'bg_Latn|ISO 9',
         u'bg_Latn|UNGEGN',
         u'bg_Latn|BGN/PCGN'],
 u'bg_Latn|ALA-LC': [u'bg'],
 u'bg_Latn|BGN/PCGN': [u'bg'],
 u'bg_Latn|ISO 9': [u'bg'],
 u'bg_Latn|UNGEGN': [u'bg'],
 u'bg_Zyyy': [u'bg_Latn|BGN'],
 u'bn': [u'kn',
         u'gu',
         u'ta',
         u'hi',
         u'ml',
         u'ar',
         u'te',
         u'bn_Latn',
         u'pa',
         u'or'],
 u'bn_Latn': [u'bn'],
 u'bn_Zyyy': [u'bn'],
 u'chr': [u'chr_Latn'],
 u'chr_Latn': [u'chr'],
 u'cs': [u'cs|FONIPA', u'fa', u'am', u'ja-Kana', u'ko', u'ar'],
 u'cs|FONIPA': [u'ja-Kana', u'ko'],
 u'dv': [u'dv_Latn|BGN'],
 u'el': [u'el_Zyyy|Upper',
         u'el_Latn',
         u'el_Latn|BGN',
         u'el_Zyyy|Title',
         u'el_Latn|UNGEGN',
         u'el_Zyyy|Lower'],
 u'el_Latn': [u'el|UNGEGN', u'el'],
 u'el_Latn|BGN': [u'el'],
 u'el_Latn|UNGEGN': [u'el'],
 u'el|UNGEGN': [u'el_Latn'],
 u'en|CMU Pron': [u'en|FONIPA'],
 u'en|FONIPA': [u'en|CMU Pron', u'ja-Kana'],
 u'es': [u'am', 'zh', u'es|FONIPA', u'ar', u'ja-Kana', u'fa'],
 u'es|419': [u'ja-Kana', u'am', u'ar', u'fa', 'zh'],
 u'es|FONIPA': [u'es|419-FONIPA', u'ja-Kana', 'zh', u'am'],
 u'fa': [u'es|419',
         u'fa_Latn|BGN',
         u'pl',
         u'es',
         u'cs',
         u'ro',
         u'fa|FONIPA',
         u'sk'],
 u'fa_Zyyy': [u'fa', u'fa_Latn|BGN'],
 u'fa|FONIPA': [u'fa'],
 u'gu': [u'pa',
         u'kn',
         u'bn',
         u'ta',
         u'or',
         u'gu_Latn',
         u'te',
         u'hi',
         u'ar',
         u'ml'],
 u'gu_Latn': [u'gu'],
 u'gu_Zyyy': [u'gu'],
 u'hak': [u'hak_Latn|Guangdong'],
 u'he': [u'he_Latn', u'he_Latn|BGN'],
 u'he_Latn': [u'he'],
 u'he_Latn|BGN': [u'he'],
 u'he_Latn|UNGEGN': [u'he'],
 u'hi': [u'bn',
         u'kn',
         u'or',
         u'hi_Latn',
         u'te',
         u'ar',
         u'gu',
         u'ta',
         u'ml',
         u'pa'],
 u'hi_Latn': [u'hi'],
 u'hi_Zyyy': [u'hi'],
 u'hy': [u'am', u'hy_Latn', u'hy|FONIPA', u'fa', u'hy_Latn|BGN', u'ar'],
 u'hy_Armn|Western': [u'ar', u'fa', u'am', u'hy_Armn|Western-FONIPA'],
 u'hy_Latn': [u'hy'],
 u'hy_Latn|BGN': [u'hy'],
 u'hy_Latn|BGN/PCGN': [u'hy|Western'],
 u'hy|Western': [u'hy_Latn|BGN/PCGN'],
 u'ii': [u'ii_Latn'],
 u'ii_Latn': [u'ii'],
 u'it': [u'ja-Kana', u'am'],
 u'ja': [u'ja_Latn|FONIPA', 'ja-Hira', u'ja_Cyrl', 'Latn', 'ja-Kana'],
 u'ja_Cyrl': [u'ja-Kana', u'ja-Hira'],
 u'ja-Hira': [u'ja-Kana',
              u'ja_Latn',
              u'ja_Latn|FONIPA',
              u'ja-Hrkt',
              u'ja_Cyrl'],
 'ja-Hrkt': [u'ja-Hrkt',
             u'ja_Cyrl',
             u'ja_Latn',
             u'ja-Kana',
             u'ja_Latn|FONIPA',
             u'ja-Hira'],
 u'ja-Kana': ['ja-Hrkt',
              u'ja_Cyrl',
              u'es',
              u'cs|FONIPA',
              u'it',
              u'ro|FONIPA',
              u'ja_Latn|BGN',
              u'sk',
              u'ja_Latn|FONIPA',
              u'cs',
              u'pl|FONIPA',
              u'ro',
              u'es|FONIPA',
              u'ja_Latn',
              u'pl',
              u'ja-Hira',
              u'sk|FONIPA',
              u'es|419'],
 u'ja_Latn': [u'ja-Hrkt', u'ja-Hira', u'ja-Kana'],
 u'ja_Latn|BGN': [u'ja-Kana'],
 u'ja_Latn|ICU Romaji': [u'ru', u'ko'],
 u'ka': [u'ka_Latn|ALA-LC',
         u'ka_Latn|TITUS',
         u'ka_Latn|KNAB',
         u'ka_Latn|BGN 1981',
         u'ka_Latn|IKE',
         u'ka_Latn|National',
         u'ka_Latn|BGN',
         u'ka_Latn|BGN/PCGN',
         u'ka_Latn',
         u'ka_Latn|ISO 9984'],
 u'ka_Latn': [u'ka'],
 u'ka_Latn|ALA-LC': [u'ka'],
 u'ka_Latn|BGN': [u'ka'],
 u'ka_Latn|BGN 1981': [u'ka'],
 u'ka_Latn|BGN/PCGN': [u'ka'],
 u'ka_Latn|IKE': [u'ka'],
 u'ka_Latn|ISO 9984': [u'ka'],
 u'ka_Latn|KNAB': [u'ka'],
 u'ka_Latn|National': [u'ka'],
 u'ka_Latn|TITUS': [u'ka'],
 u'kk': [u'am',
         u'kk_Latn|ALA-LC',
         u'kk|FONIPA',
         u'kk_Latn|BGN',
         u'ar',
         u'fa',
         u'kk_Latn|ISO 9',
         u'kk_Latn|BGN/PCGN',
         u'kk_Latn|Allworth',
         u'kk_Latn|KNAB'],
 u'kk_Latn|ALA-LC': [u'kk'],
 u'kk_Latn|Allworth': [u'kk'],
 u'kk_Latn|BGN/PCGN': [u'kk'],
 u'kk_Latn|ISO 9': [u'kk'],
 u'kk_Latn|KNAB': [u'kk'],
 u'kk_Zyyy': [u'kk|FONIPA', u'kk_Latn|BGN'],
 u'kn': [u'te',
         u'ml',
         u'or',
         u'pa',
         u'ta',
         u'hi',
         u'bn',
         u'gu',
         u'ar',
         u'kn_Latn'],
 u'kn_Latn': [u'kn'],
 u'kn_Zyyy': [u'kn'],
 'ko': ['ko_Latn|MRR',
        u'cs|FONIPA',
        'ko_Latn|SKR 1984',
        'ko_Latn|SKATS',
        u'cs',
        'ko_Latn|SKR 1959',
        'ko_Latn|Yale',
        'ko_Latn|HSR',
        u'ko_Latn|BGN',
        'ko_Latn|NKR 1992',
        'ko_Latn|SKR 2000',
        'ko_Latn|ISO TS 11941',
        u'ko_Latn'],
 u'ko_Hani|Hanja': [u'ko_Hang', u'ko_Latn|Yale'],
 u'ko_Latn': [u'ko', u'ko|Jamo'],
 'ko_Latn|HSR': ['ko'],
 'ko_Latn|ISO TS 11941': ['ko'],
 'ko_Latn|MRR': ['ko'],
 'ko_Latn|NKR 1992': ['ko'],
 'ko_Latn|SKATS': ['ko'],
 'ko_Latn|SKR 1959': ['ko'],
 'ko_Latn|SKR 1984': ['ko'],
 'ko_Latn|SKR 2000': ['ko'],
 'ko_Latn|Yale': ['ko'],
 u'ko|Jamo': [u'ko_Latn'],
 u'ky': [u'fa',
         u'ky_Latn|Allworth',
         u'ky_Latn|ALA-LC',
         u'ky_Latn|KNAB',
         u'am',
         u'ky|FONIPA',
         u'ky_Latn|WWS',
         u'ky_Latn|BGN/PCGN',
         u'ky_Latn|ISO 9',
         u'ar',
         u'ky_Latn|BGN'],
 u'ky_Latn|ALA-LC': [u'ky'],
 u'ky_Latn|Allworth': [u'ky'],
 u'ky_Latn|BGN/PCGN': [u'ky'],
 u'ky_Latn|ISO 9': [u'ky'],
 u'ky_Latn|KNAB': [u'ky'],
 u'ky_Latn|WWS': [u'ky'],
 u'ky_Zyyy': [u'ky|FONIPA', u'ky_Latn|BGN'],
 u'lt_Latn': [u'lt_Zyyy|Title', u'lt_Zyyy|Upper', u'lt_Zyyy|Lower'],
 u'ltc': [u'ltc_Latn'],
 u'mk': [u'mk_Latn|ISO 9',
         u'mk_Latn|BGN',
         u'mk_Latn|UN',
         u'mk_Latn|ALA-LC',
         u'mk_Latn|UNGEGN'],
 u'mk_Latn|ALA-LC': [u'mk'],
 u'mk_Latn|ISO 9': [u'mk'],
 u'mk_Latn|UN': [u'mk'],
 u'mk_Latn|UNGEGN': [u'mk'],
 u'mk_Zyyy': [u'mk_Latn|BGN'],
 u'ml': [u'te',
         u'pa',
         u'ar',
         u'bn',
         u'hi',
         u'or',
         u'gu',
         u'kn',
         u'ml_Latn',
         u'ta'],
 u'ml_Latn': [u'ml'],
 u'ml_Zyyy': [u'ml'],
 u'mn': [u'mn_Latn|ALA-LC',
         u'mn_Latn|ISO 9',
         u'mn_Latn|MNS',
         u'mn_Latn|BGN',
         u'mn_Latn|BGN/PCGN',
         u'mn_Latn|KNAB'],
 u'mn_Latn|ALA-LC': [u'mn'],
 u'mn_Latn|BGN/PCGN': [u'mn'],
 u'mn_Latn|ISO 9': [u'mn'],
 u'mn_Latn|KNAB': [u'mn'],
 u'mn_Latn|MNS': [u'mn'],
 u'mn_Zyyy': [u'mn_Latn|MNS', u'mn_Latn|BGN'],
 u'my': [u'my|FONIPA', u'am', u'fa', u'ar'],
 u'my_Zyyy': [u'my', u'my|FONIPA'],
 u'nl': [u'nl_Zyyy|Title'],
 u'or': [u'or_Latn',
         u'gu',
         u'hi',
         u'ml',
         u'ta',
         u'ar',
         u'pa',
         u'kn',
         u'bn',
         u'te'],
 u'or_Latn': [u'or'],
 u'or_Zyyy': [u'or'],
 u'pa': [u'kn',
         u'or',
         u'pa_Latn',
         u'hi',
         u'ar',
         u'te',
         u'bn',
         u'ml',
         u'gu',
         u'ta'],
 u'pa_Latn': [u'pa'],
 u'pa_Zyyy': [u'pa'],
 u'pl': [u'ja-Kana', u'fa', u'am', u'pl|FONIPA', u'ar'],
 u'pl|FONIPA': [u'ja-Kana'],
 u'ps': [u'ps_Latn|BGN'],
 u'ps_Zyyy': [u'ps_Latn|BGN'],
 u'ro': [u'fa', u'ar', u'ja-Kana', u'ro|FONIPA', u'am'],
 u'ro_Cyrl': [u'ro_Latn|ALA-LC',
              u'ro_Latn|ISO 9',
              u'ro_Latn|WWS',
              u'ro_Latn|Official'],
 u'ro_Latn|ALA-LC': [u'ro_Cyrl'],
 u'ro_Latn|ISO 9': [u'ro_Cyrl'],
 u'ro_Latn|Official': [u'ro_Cyrl'],
 u'ro_Latn|WWS': [u'ro_Cyrl'],
 u'ro|FONIPA': [u'ja-Kana'],
 u'ru': [u'ru_Latn|ISO 9',
         u'ru_Latn|BGN/PCGN',
         u'ru_Latn|ALA-LC',
         u'ja-Kana',
         u'zh_Latn-x-Pinyin',
         u'ru_Latn|ISO 9 R',
         u'ru_Latn',
         u'ru_Latn|Official',
         'zh',
         u'ru_Latn|BGN'],
 u'ru_Latn': [u'ru_Latn|BGN', u'ru'],
 u'ru_Latn|ALA-LC': [u'ru'],
 u'ru_Latn|BGN': [u'ru_Latn', u'ru'],
 u'ru_Latn|BGN/PCGN': [u'ru'],
 u'ru_Latn|ISO 9': [u'ru'],
 u'ru_Latn|ISO 9 R': [u'ru'],
 u'ru_Latn|Official': [u'ru'],
 u'sk': [u'ja-Kana', u'ar', u'fa', u'am', u'sk|FONIPA'],
 u'sk|FONIPA': [u'ja-Kana'],
 u'sr': [u'sr_Latn|ISO 9', u'sr_Latn', u'sr_Latn|ALA-LC', u'sr_Latn|BGN'],
 u'sr_Latn': [u'sr'],
 u'sr_Latn|ALA-LC': [u'sr'],
 u'sr_Latn|ISO 9': [u'sr'],
 u'sr_Zyyy': [u'sr_Latn|BGN'],
 u'ta': [u'or',
         u'ta_Latn',
         u'ar',
         u'te',
         u'kn',
         u'pa',
         u'ml',
         u'ta|FONIPA',
         u'bn',
         u'hi',
         u'gu'],
 u'ta_Latn': [u'ta'],
 u'ta_Zyyy': [u'ta', u'ta|FONIPA'],
 u'te': [u'hi',
         u'ta',
         u'ar',
         u'pa',
         u'gu',
         u'te_Latn',
         u'kn',
         u'bn',
         u'ml',
         u'or'],
 u'te_Latn': [u'te'],
 u'te_Zyyy': [u'te'],
 u'tg': [u'tg_Latn|WWS',
         u'tg_Latn|BGN/PCGN',
         u'tg_Latn|KNAB',
         u'tg_Latn|Allworth',
         u'tg_Latn|ALA-LC',
         u'tg_Latn|ISO 9'],
 u'tg_Latn|ALA-LC': [u'tg'],
 u'tg_Latn|Allworth': [u'tg'],
 u'tg_Latn|BGN/PCGN': [u'tg'],
 u'tg_Latn|ISO 9': [u'tg'],
 u'tg_Latn|KNAB': [u'tg'],
 u'tg_Latn|WWS': [u'tg'],
 u'th': [u'th_Latn'],
 u'th_Latn': [u'th'],
 u'tk': [u'tk_Latn|BGN'],
 u'tk_Cyrl': [u'tk_Latn|Official WWS',
              u'tk_Latn|ALA-LC',
              u'tk_Latn|Allworth',
              u'tk_Latn|BGN/PCGN',
              u'tk_Latn|Official TDS 565',
              u'tk_Latn|Old Official',
              u'tk_Latn|ISO 9'],
 u'tk_Latn|ALA-LC': [u'tk_Cyrl'],
 u'tk_Latn|Allworth': [u'tk_Cyrl'],
 u'tk_Latn|BGN/PCGN': [u'tk_Cyrl'],
 u'tk_Latn|ISO 9': [u'tk_Cyrl'],
 u'tk_Latn|Official TDS 565': [u'tk_Cyrl'],
 u'tk_Latn|Official WWS': [u'tk_Cyrl'],
 u'tk_Latn|Old Official': [u'tk_Cyrl'],
 u'tk_Zyyy': [u'tk_Latn|BGN'],
 u'tr': [u'tr_Zyyy|Title', u'tr_Zyyy|Lower', u'tr_Zyyy|Upper'],
 u'tt': [u'tt_Latn|ALA-LC',
         u'tt_Latn|KNAB',
         u'tt_Latn|Roman Official',
         u'tt_Latn|WWS',
         u'tt_Latn|ISO 9'],
 u'tt_Latn|ALA-LC': [u'tt'],
 u'tt_Latn|ISO 9': [u'tt'],
 u'tt_Latn|KNAB': [u'tt'],
 u'tt_Latn|Roman Official': [u'tt'],
 u'tt_Latn|WWS': [u'tt'],
 u'uk': [u'uk_Latn|BGN',
         u'uk_Latn|ISO 9',
         u'uk_Latn|ALA-LC',
         u'uk_Latn|Official',
         u'uk_Latn|WWS',
         u'uk_Latn|BGN/PCGN'],
 u'uk_Latn|ALA-LC': [u'uk'],
 u'uk_Latn|BGN/PCGN': [u'uk'],
 u'uk_Latn|ISO 9': [u'uk'],
 u'uk_Latn|Official': [u'uk'],
 u'uk_Latn|WWS': [u'uk'],
 u'uk_Zyyy': [u'uk_Latn|BGN'],
 u'uz': [u'uz_Latn|BGN',
         u'uz_Latn|ISO 9',
         u'uz_Latn|ALA-LC',
         u'uz_Latn|Official',
         u'uz_Latn',
         u'uz_Latn|BGN/PCGN',
         u'uz_Latn|WWS',
         u'uz_Latn|Former Official'],
 u'uz_Latn': [u'uz'],
 u'uz_Latn|ALA-LC': [u'uz'],
 u'uz_Latn|BGN/PCGN': [u'uz'],
 u'uz_Latn|Former Official': [u'uz'],
 u'uz_Latn|ISO 9': [u'uz'],
 u'uz_Latn|Official': [u'uz'],
 u'uz_Latn|WWS': [u'uz'],
 u'uz_Zyyy': [u'uz', u'uz_Latn', u'uz_Latn|BGN'],
 u'vi_Hani': [u'vi'],
 u'yue': [u'yue_Latn|Jyutping'],
 u'yue_Latn|Jyutping': [u'yue_Latn|Yale'],
 u'yue_Latn|Yale': [u'yue_Latn|Jyutping'],
 u'zh': [u'zh-Latn-x-NumericPinyin',
         'zh_Latn-x-Pinyin',
         u'es',
         u'zh_Hant',
         u'es|FONIPA',
         u'es|419',
         u'zh_Latn|Names'],
 u'zh_Bopo': [u'zh_Latn|Yale',
              u'zh_Latn|French',
              u'zh_Latn|x-GwoyeuRomatzyh',
              'zh_Latn-x-Pinyin',
              u'zh_Latn|GuoinII',
              u'zh_Latn|Tongyong',
              u'zh_Latn-x-NumericPinyin',
              u'zh_Latn|Wade-Giles'],
 u'zh_Hant': [u'zh'],
 u'zh_Latn|French': [u'zh_Bopo',
                     u'zh_Latn-x-Pinyin',
                     u'zh_Latn-x-NumericPinyin',
                     u'zh_Latn|Tongyong',
                     u'zh_Latn|Wade-Giles',
                     u'zh_Latn|GuoinII',
                     u'zh_Latn|Yale',
                     u'zh_Latn|x-GwoyeuRomatzyh'],
 u'zh_Latn|GuoinII': [u'zh_Latn-x-Pinyin',
                      u'zh_Latn-x-NumericPinyin',
                      u'zh_Latn|French',
                      u'zh_Bopo',
                      u'zh_Latn|Tongyong',
                      u'zh_Latn|Wade-Giles',
                      u'zh_Latn|Yale',
                      u'zh_Latn|x-GwoyeuRomatzyh'],
 u'zh_Latn|x-GwoyeuRomatzyh': [u'zh_Latn-x-NumericPinyin',
                              u'zh_Latn|French',
                              u'zh_Bopo',
                              u'zh_Latn|Wade-Giles',
                              u'zh_Latn|Yale',
                              u'zh_Latn-x-Pinyin',
                              u'zh_Latn|GuoinII',
                              u'zh_Latn|Tongyong'],
 u'zh_Latn-x-NumericPinyin': ['zh_Latn-x-Pinyin',
                             u'zh_Latn|Numeric Segmented Pinyin',
                             u'zh_Bopo',
                             u'zh_Latn|Tongyong',
                             u'zh_Latn|x-GwoyeuRomatzyh',
                             u'zh_Latn|FONIPA',
                             u'zh_Latn|Yale',
                             u'zh_Latn|GuoinII',
                             u'zh_Latn|French',
                             u'zh_Latn|Wade-Giles'],
 u'zh_Latn|Pinyin U Unaccented': [u'zh_Latn|Pinyin U Accented'],
 u'zh_Latn|Tongyong': [u'zh_Latn|French',
                       u'zh_Bopo',
                       u'zh_Latn|GuoinII',
                       u'zh_Latn|x-GwoyeuRomatzyh',
                       u'zh_Latn|Yale',
                       u'zh_Latn-x-Pinyin',
                       u'zh_Latn-x-NumericPinyin',
                       u'zh_Latn|Wade-Giles'],
 u'zh_Latn|Wade-Giles': [u'zh_Bopo',
                         u'zh_Latn-x-NumericPinyin',
                         u'zh_Latn|Tongyong',
                         u'zh_Latn-x-Pinyin',
                         u'zh_Latn|GuoinII',
                         u'zh_Latn|Yale',
                         u'zh_Latn|French',
                         u'zh_Latn|x-GwoyeuRomatzyh'],
 u'zh_Latn|Yale': [u'zh_Latn|Tongyong',
                   u'zh_Latn|x-GwoyeuRomatzyh',
                   u'zh_Latn-x-Pinyin',
                   u'zh_Latn|French',
                   u'zh_Latn|GuoinII',
                   u'zh_Latn|Wade-Giles',
                   u'zh_Bopo',
                   u'zh_Latn-x-NumericPinyin'],
 u'zh_Latn-x-Pinyin': [u'zh_Latn|French',
                       u'zh_Latn|GuoinII',
                       'zh',
                       u'zh_Bopo',
                       u'zh_Latn|x-GwoyeuRomatzyh',
                       u'ru',
                       u'zh_Latn-x-NumericPinyin',
                       u'zh_Latn|Wade-Giles',
                       u'zh_Latn|Yale',
                       u'zh_Latn|Tongyong'],
 u'|FONIPA': [u'Latn|FONXSAMP']}