enumdata.py

# Copyright (C) 2021 The Qt Company Ltd.
# SPDX-License-Identifier: LicenseRef-Qt-Commercial OR GPL-3.0-only WITH Qt-GPL-exception-1.0

"""Assorted enumerations implicated in public API.

The numberings of these enumerations can only change at major
versions. When new CLDR data implies adding entries, the new ones must
go after all existing ones. See also zonedata.py for enumerations
related to timezones and CLDR, which can more freely be changed
between versions.

A run of cldr2qlocalexml.py will produce output reporting any
language, script and territory codes it sees, in data, for which it
can find a name (taken always from en.xml) that could potentially be
used. There is no point adding a mapping for such a code unless the
CLDR's common/main/ contains an XML file for at least one locale that
exercises it (and little point, even then, absent substantial data,
ignoring draft='unconfirmed' entries).

Each *_map reflects the current values of its enums in qlocale.h; if
new xml language files are available in CLDR, these languages and
territories need to be *appended* to this list (for compatibility
between versions). Include any spaces and dashes present in names
(they'll be squished out for the enum entries) in *_map, but use the
squished forms of names in the *_aliases mappings. The squishing also
turns the first letter of each word into a capital so you can safely
preserve the case of en.xml's name; but omit (or replace with space)
any punctuation aside from dashes and map any accented letters to
their un-accented plain ASCII. The two tables, for each enum, have
the forms:
* map { Numeric value: ("Proper name", "ISO code") }
* alias { "OldName": "CurrentName" }

TODO: add support for marking entries as deprecated from a specified
version. For aliases that merely deprecates the name. Where we have a
name for which CLDR offers no data, we may also want to deprecate
entries in the map - although they may be worth keeping for the
benefit of QLocaleSelector (see QTBUG-112765), if other
locale-specific resources might have use of them.

For a new major version (and only then), we can change the numbering,
so re-sort each list into alphabetic order (e.g. using sort -k2); but
keep the Any and C entries first. That's why those are offset with a
blank line, below. After doing that, regenerate locale data as usual;
this will cause a binary-incompatible change.

Note on 'macrolanguage' comments: see QTBUG-107781 and 'ISO 639
macrolanguage' on Wikipedia. A 'macrolanguage' is (loosely-speaking) a
group of languages so closely related to one another that they could
also be regarded as divergent dialects of the macrolanguage.  In some
cases this may mean a resource (such as translation or text-to-speech
data) may describe itself as pertaining to the macrolanguage, implying
its suitability for use in any of the languages within the
macrolanguage. For example, no_NO might be used for a generic
Norwegian resource, embracing both nb_NO and nn_NO.

"""

language_map = {
      0: ("AnyLanguage",                 "  "),
      1: ("C",                           "  "),

      2: ("Abkhazian",                   "ab"),
      3: ("Afar",                        "aa"),
      4: ("Afrikaans",                   "af"),
      5: ("Aghem",                       "agq"),
      6: ("Akan",                        "ak"), # macrolanguage
      7: ("Akkadian",                    "akk"),
      8: ("Akoose",                      "bss"),
      9: ("Albanian",                    "sq"), # macrolanguage
     10: ("American Sign Language",      "ase"),
     11: ("Amharic",                     "am"),
     12: ("Ancient Egyptian",            "egy"),
     13: ("Ancient Greek",               "grc"),
     14: ("Arabic",                      "ar"), # macrolanguage
     15: ("Aragonese",                   "an"),
     16: ("Aramaic",                     "arc"),
     17: ("Armenian",                    "hy"),
     18: ("Assamese",                    "as"),
     19: ("Asturian",                    "ast"),
     20: ("Asu",                         "asa"),
     21: ("Atsam",                       "cch"),
     22: ("Avaric",                      "av"),
     23: ("Avestan",                     "ae"),
     24: ("Aymara",                      "ay"), # macrolanguage
     25: ("Azerbaijani",                 "az"), # macrolanguage
     26: ("Bafia",                       "ksf"),
     27: ("Balinese",                    "ban"),
     28: ("Bambara",                     "bm"),
     29: ("Bamun",                       "bax"),
     30: ("Bangla",                      "bn"),
     31: ("Basaa",                       "bas"),
     32: ("Bashkir",                     "ba"),
     33: ("Basque",                      "eu"),
     34: ("Batak Toba",                  "bbc"),
     35: ("Belarusian",                  "be"),
     36: ("Bemba",                       "bem"),
     37: ("Bena",                        "bez"),
     38: ("Bhojpuri",                    "bho"),
     39: ("Bislama",                     "bi"),
     40: ("Blin",                        "byn"),
     41: ("Bodo",                        "brx"),
     42: ("Bosnian",                     "bs"),
     43: ("Breton",                      "br"),
     44: ("Buginese",                    "bug"),
     45: ("Bulgarian",                   "bg"),
     46: ("Burmese",                     "my"),
     47: ("Cantonese",                   "yue"),
     48: ("Catalan",                     "ca"),
     49: ("Cebuano",                     "ceb"),
     50: ("Central Atlas Tamazight",     "tzm"),
     51: ("Central Kurdish",             "ckb"),
     52: ("Chakma",                      "ccp"),
     53: ("Chamorro",                    "ch"),
     54: ("Chechen",                     "ce"),
     55: ("Cherokee",                    "chr"),
     56: ("Chickasaw",                   "cic"),
     57: ("Chiga",                       "cgg"),
     58: ("Chinese",                     "zh"), # macrolanguage
     59: ("Church",                      "cu"), # macrolanguage
     60: ("Chuvash",                     "cv"),
     61: ("Colognian",                   "ksh"),
     62: ("Coptic",                      "cop"),
     63: ("Cornish",                     "kw"),
     64: ("Corsican",                    "co"),
     65: ("Cree",                        "cr"), # macrolanguage
     66: ("Croatian",                    "hr"),
     67: ("Czech",                       "cs"),
     68: ("Danish",                      "da"),
     69: ("Divehi",                      "dv"),
     70: ("Dogri",                       "doi"), # macrolanguage
     71: ("Duala",                       "dua"),
     72: ("Dutch",                       "nl"),
     73: ("Dzongkha",                    "dz"),
     74: ("Embu",                        "ebu"),
     75: ("English",                     "en"),
     76: ("Erzya",                       "myv"),
     77: ("Esperanto",                   "eo"),
     78: ("Estonian",                    "et"), # macrolanguage
     79: ("Ewe",                         "ee" ),
     80: ("Ewondo",                      "ewo"),
     81: ("Faroese",                     "fo"),
     82: ("Fijian",                      "fj"),
     83: ("Filipino",                    "fil"),
     84: ("Finnish",                     "fi"),
     85: ("French",                      "fr"),
     86: ("Friulian",                    "fur"),
     87: ("Fulah",                       "ff"), # macrolanguage
     88: ("Gaelic",                      "gd"),
     89: ("Ga",                          "gaa"),
     90: ("Galician",                    "gl"),
     91: ("Ganda",                       "lg"),
     92: ("Geez",                        "gez"),
     93: ("Georgian",                    "ka"),
     94: ("German",                      "de"),
     95: ("Gothic",                      "got"),
     96: ("Greek",                       "el"),
     97: ("Guarani",                     "gn"), # macrolanguage
     98: ("Gujarati",                    "gu"),
     99: ("Gusii",                       "guz"),
    100: ("Haitian",                     "ht"),
    101: ("Hausa",                       "ha"),
    102: ("Hawaiian",                    "haw"),
    103: ("Hebrew",                      "he"),
    104: ("Herero",                      "hz"),
    105: ("Hindi",                       "hi"),
    106: ("Hiri Motu",                   "ho"),
    107: ("Hungarian",                   "hu"),
    108: ("Icelandic",                   "is"),
    109: ("Ido",                         "io"),
    110: ("Igbo",                        "ig" ),
    111: ("Inari Sami",                  "smn"),
    112: ("Indonesian",                  "id"),
    113: ("Ingush",                      "inh"),
    114: ("Interlingua",                 "ia"),
    115: ("Interlingue",                 "ie"),
    116: ("Inuktitut",                   "iu"), # macrolanguage
    117: ("Inupiaq",                     "ik"), # macrolanguage
    118: ("Irish",                       "ga"),
    119: ("Italian",                     "it"),
    120: ("Japanese",                    "ja"),
    121: ("Javanese",                    "jv"),
    122: ("Jju",                         "kaj"),
    123: ("Jola-Fonyi",                  "dyo"),
    124: ("Kabuverdianu",                "kea"),
    125: ("Kabyle",                      "kab"),
    126: ("Kako",                        "kkj"),
    127: ("Kalaallisut",                 "kl"),
    128: ("Kalenjin",                    "kln"),
    129: ("Kamba",                       "kam"),
    130: ("Kannada",                     "kn"),
    131: ("Kanuri",                      "kr"), # macrolanguage
    132: ("Kashmiri",                    "ks"),
    133: ("Kazakh",                      "kk"),
    134: ("Kenyang",                     "ken"),
    135: ("Khmer",                       "km"),
    136: ("Kiche",                       "quc"),
    137: ("Kikuyu",                      "ki"),
    138: ("Kinyarwanda",                 "rw"),
    139: ("Komi",                        "kv"), # macrolanguage
    140: ("Kongo",                       "kg"), # macrolanguage
    141: ("Konkani",                     "kok"),
    142: ("Korean",                      "ko"),
    143: ("Koro",                        "kfo"),
    144: ("Koyraboro Senni",             "ses"),
    145: ("Koyra Chiini",                "khq"),
    146: ("Kpelle",                      "kpe"),
    147: ("Kuanyama",                    "kj"),
    148: ("Kurdish",                     "ku"), # macrolanguage
    149: ("Kwasio",                      "nmg"),
    150: ("Kyrgyz",                      "ky"),
    151: ("Lakota",                      "lkt"),
    152: ("Langi",                       "lag"),
    153: ("Lao",                         "lo"),
    154: ("Latin",                       "la"),
    155: ("Latvian",                     "lv"), # macrolanguage
    156: ("Lezghian",                    "lez"),
    157: ("Limburgish",                  "li"),
    158: ("Lingala",                     "ln"),
    159: ("Literary Chinese",            "lzh"),
    160: ("Lithuanian",                  "lt"),
    161: ("Lojban",                      "jbo"),
    162: ("Lower Sorbian",               "dsb"),
    163: ("Low German",                  "nds"),
    164: ("Luba-Katanga",                "lu"),
    165: ("Lule Sami",                   "smj"),
    166: ("Luo",                         "luo"),
    167: ("Luxembourgish",               "lb"),
    168: ("Luyia",                       "luy"),
    169: ("Macedonian",                  "mk"),
    170: ("Machame",                     "jmc"),
    171: ("Maithili",                    "mai"),
    172: ("Makhuwa-Meetto",              "mgh"),
    173: ("Makonde",                     "kde"),
    174: ("Malagasy",                    "mg"), # macrolanguage
    175: ("Malayalam",                   "ml"),
    176: ("Malay",                       "ms"), # macrolanguage
    177: ("Maltese",                     "mt"),
    178: ("Mandingo",                    "man"), # macrolanguage
    179: ("Manipuri",                    "mni"),
    180: ("Manx",                        "gv"),
    181: ("Maori",                       "mi"),
    182: ("Mapuche",                     "arn"),
    183: ("Marathi",                     "mr"),
    184: ("Marshallese",                 "mh"),
    185: ("Masai",                       "mas"),
    186: ("Mazanderani",                 "mzn"),
    187: ("Mende",                       "men"),
    188: ("Meru",                        "mer"),
    189: ("Meta",                        "mgo"),
    190: ("Mohawk",                      "moh"),
    191: ("Mongolian",                   "mn"), # macrolanguage
    192: ("Morisyen",                    "mfe"),
    193: ("Mundang",                     "mua"),
    194: ("Muscogee",                    "mus"),
    195: ("Nama",                        "naq"),
    196: ("Nauru",                       "na"),
    197: ("Navajo",                      "nv"),
    198: ("Ndonga",                      "ng"),
    199: ("Nepali",                      "ne"), # macrolanguage
    200: ("Newari",                      "new"),
    201: ("Ngiemboon",                   "nnh"),
    202: ("Ngomba",                      "jgo"),
    203: ("Nigerian Pidgin",             "pcm"),
    204: ("Nko",                         "nqo"),
    205: ("Northern Luri",               "lrc"),
    206: ("Northern Sami",               "se" ),
    207: ("Northern Sotho",              "nso"),
    208: ("North Ndebele",               "nd"),
    209: ("Norwegian Bokmal",            "nb"),
    210: ("Norwegian Nynorsk",           "nn"),
    211: ("Nuer",                        "nus"),
    212: ("Nyanja",                      "ny" ),
    213: ("Nyankole",                    "nyn"),
    214: ("Occitan",                     "oc"),
    215: ("Odia",                        "or"), # macrolanguage
    216: ("Ojibwa",                      "oj"), # macrolanguage
    217: ("Old Irish",                   "sga"),
    218: ("Old Norse",                   "non"),
    219: ("Old Persian",                 "peo"),
    220: ("Oromo",                       "om"), # macrolanguage
    221: ("Osage",                       "osa"),
    222: ("Ossetic",                     "os"),
    223: ("Pahlavi",                     "pal"),
    224: ("Palauan",                     "pau"),
    225: ("Pali",                        "pi"), # macrolanguage
    226: ("Papiamento",                  "pap"),
    227: ("Pashto",                      "ps"), # macrolanguage
    228: ("Persian",                     "fa"), # macrolanguage
    229: ("Phoenician",                  "phn"),
    230: ("Polish",                      "pl"),
    231: ("Portuguese",                  "pt"),
    232: ("Prussian",                    "prg"),
    233: ("Punjabi",                     "pa"),
    234: ("Quechua",                     "qu"), # macrolanguage
    235: ("Romanian",                    "ro"),
    236: ("Romansh",                     "rm"),
    237: ("Rombo",                       "rof"),
    238: ("Rundi",                       "rn"),
    239: ("Russian",                     "ru"),
    240: ("Rwa",                         "rwk"),
    241: ("Saho",                        "ssy"),
    242: ("Sakha",                       "sah"),
    243: ("Samburu",                     "saq"),
    244: ("Samoan",                      "sm"),
    245: ("Sango",                       "sg"),
    246: ("Sangu",                       "sbp"),
    247: ("Sanskrit",                    "sa"),
    248: ("Santali",                     "sat"),
    249: ("Sardinian",                   "sc"), # macrolanguage
    250: ("Saurashtra",                  "saz"),
    251: ("Sena",                        "seh"),
    252: ("Serbian",                     "sr"),
    253: ("Shambala",                    "ksb"),
    254: ("Shona",                       "sn"),
    255: ("Sichuan Yi",                  "ii" ),
    256: ("Sicilian",                    "scn"),
    257: ("Sidamo",                      "sid"),
    258: ("Silesian",                    "szl"),
    259: ("Sindhi",                      "sd"),
    260: ("Sinhala",                     "si"),
    261: ("Skolt Sami",                  "sms"),
    262: ("Slovak",                      "sk"),
    263: ("Slovenian",                   "sl"),
    264: ("Soga",                        "xog"),
    265: ("Somali",                      "so"),
    266: ("Southern Kurdish",            "sdh"),
    267: ("Southern Sami",               "sma"),
    268: ("Southern Sotho",              "st"),
    269: ("South Ndebele",               "nr" ),
    270: ("Spanish",                     "es"),
    271: ("Standard Moroccan Tamazight", "zgh"),
    272: ("Sundanese",                   "su"),
    273: ("Swahili",                     "sw"), # macrolanguage
    274: ("Swati",                       "ss"),
    275: ("Swedish",                     "sv"),
    276: ("Swiss German",                "gsw"),
    277: ("Syriac",                      "syr"),
    278: ("Tachelhit",                   "shi"),
    279: ("Tahitian",                    "ty"),
    280: ("Tai Dam",                     "blt"),
    281: ("Taita",                       "dav"),
    282: ("Tajik",                       "tg"),
    283: ("Tamil",                       "ta"),
    284: ("Taroko",                      "trv"),
    285: ("Tasawaq",                     "twq"),
    286: ("Tatar",                       "tt"),
    287: ("Telugu",                      "te"),
    288: ("Teso",                        "teo"),
    289: ("Thai",                        "th"),
    290: ("Tibetan",                     "bo"),
    291: ("Tigre",                       "tig"),
    292: ("Tigrinya",                    "ti"),
    293: ("Tokelau",                     "tkl"),
    294: ("Tok Pisin",                   "tpi"),
    295: ("Tongan",                      "to"),
    296: ("Tsonga",                      "ts"),
    297: ("Tswana",                      "tn"),
    298: ("Turkish",                     "tr"),
    299: ("Turkmen",                     "tk"),
    300: ("Tuvalu",                      "tvl"),
    301: ("Tyap",                        "kcg"),
    302: ("Ugaritic",                    "uga"),
    303: ("Ukrainian",                   "uk"),
    304: ("Upper Sorbian",               "hsb"),
    305: ("Urdu",                        "ur"),
    306: ("Uyghur",                      "ug"),
    307: ("Uzbek",                       "uz"), # macrolanguage
    308: ("Vai",                         "vai"),
    309: ("Venda",                       "ve" ),
    310: ("Vietnamese",                  "vi"),
    311: ("Volapuk",                     "vo"),
    312: ("Vunjo",                       "vun"),
    313: ("Walloon",                     "wa"),
    314: ("Walser",                      "wae"),
    315: ("Warlpiri",                    "wbp"),
    316: ("Welsh",                       "cy"),
    317: ("Western Balochi",             "bgn"),
    318: ("Western Frisian",             "fy"),
    319: ("Wolaytta",                    "wal"),
    320: ("Wolof",                       "wo"),
    321: ("Xhosa",                       "xh"),
    322: ("Yangben",                     "yav"),
    323: ("Yiddish",                     "yi"), # macrolanguage
    324: ("Yoruba",                      "yo"),
    325: ("Zarma",                       "dje"),
    326: ("Zhuang",                      "za"), # macrolanguage
    327: ("Zulu",                        "zu"),
    # added in CLDR v40
    328: ("Kaingang",                    "kgp"),
    329: ("Nheengatu",                   "yrl"),
    # added in CLDR v42
    330: ("Haryanvi",                    "bgc"),
    331: ("Northern Frisian",            "frr"),
    332: ("Rajasthani",                  "raj"),
    333: ("Moksha",                      "mdf"),
    334: ("Toki Pona",                   "tok"),
    335: ("Pijin",                       "pis"),
    336: ("Obolo",                       "ann"),
    # added in CLDR v43
    337: ("Baluchi",                     "bal"),
    338: ("Ligurian",                    "lij"),
    339: ("Rohingya",                    "rhg"),
    340: ("Torwali",                     "trw"),
    # added in CLDR v44
    341: ("Anii",                        "blo"),
    342: ("Kangri",                      "xnr"),
    343: ("Venetian",                    "vec"),
}
# Don't add languages just because they exist; check CLDR does provide
# substantial data for locales using it; and check, once added, they
# don't show up in cldr2qlocalexmo.py's unused listing. Do also check
# the data's draft status; if it's (nearly) all unconfirmed, leave it.

language_aliases = {
    # Renamings prior to Qt 6.0 (CLDR v37):
    'Afan': 'Oromo',
    'Byelorussian': 'Belarusian',
    'Bhutani': 'Dzongkha',
    'Cambodian': 'Khmer',
    'Kurundi': 'Rundi',
    'RhaetoRomance': 'Romansh',
    'Chewa': 'Nyanja',
    'Frisian': 'WesternFrisian',
    'Uigur': 'Uyghur',
    # Renamings:
    'Uighur': 'Uyghur',
    'Kwanyama': 'Kuanyama',
    'Inupiak': 'Inupiaq',
    'Bengali': 'Bangla',
    'CentralMoroccoTamazight': 'CentralAtlasTamazight',
    'Greenlandic': 'Kalaallisut',
    'Walamo': 'Wolaytta',
    'Navaho': 'Navajo',
    'Oriya': 'Odia',
    'Kirghiz': 'Kyrgyz'
    }

territory_map = {
      0: ("AnyTerritory",                                 "ZZ"),

      1: ("Afghanistan",                                  "AF"),
      2: ("Aland Islands",                                "AX"),
      3: ("Albania",                                      "AL"),
      4: ("Algeria",                                      "DZ"),
      5: ("American Samoa",                               "AS"),
      6: ("Andorra",                                      "AD"),
      7: ("Angola",                                       "AO"),
      8: ("Anguilla",                                     "AI"),
      9: ("Antarctica",                                   "AQ"),
     10: ("Antigua and Barbuda",                          "AG"),
     11: ("Argentina",                                    "AR"),
     12: ("Armenia",                                      "AM"),
     13: ("Aruba",                                        "AW"),
     14: ("Ascension Island",                             "AC"),
     15: ("Australia",                                    "AU"),
     16: ("Austria",                                      "AT"),
     17: ("Azerbaijan",                                   "AZ"),
     18: ("Bahamas",                                      "BS"),
     19: ("Bahrain",                                      "BH"),
     20: ("Bangladesh",                                   "BD"),
     21: ("Barbados",                                     "BB"),
     22: ("Belarus",                                      "BY"),
     23: ("Belgium",                                      "BE"),
     24: ("Belize",                                       "BZ"),
     25: ("Benin",                                        "BJ"),
     26: ("Bermuda",                                      "BM"),
     27: ("Bhutan",                                       "BT"),
     28: ("Bolivia",                                      "BO"),
     29: ("Bosnia and Herzegovina",                       "BA"),
     30: ("Botswana",                                     "BW"),
     31: ("Bouvet Island",                                "BV"),
     32: ("Brazil",                                       "BR"),
     33: ("British Indian Ocean Territory",               "IO"),
     34: ("British Virgin Islands",                       "VG"),
     35: ("Brunei",                                       "BN"),
     36: ("Bulgaria",                                     "BG"),
     37: ("Burkina Faso",                                 "BF"),
     38: ("Burundi",                                      "BI"),
     39: ("Cambodia",                                     "KH"),
     40: ("Cameroon",                                     "CM"),
     41: ("Canada",                                       "CA"),
     42: ("Canary Islands",                               "IC"),
     43: ("Cape Verde",                                   "CV"),
     44: ("Caribbean Netherlands",                        "BQ"),
     45: ("Cayman Islands",                               "KY"),
     46: ("Central African Republic",                     "CF"),
     47: ("Ceuta and Melilla",                            "EA"),
     48: ("Chad",                                         "TD"),
     49: ("Chile",                                        "CL"),
     50: ("China",                                        "CN"),
     51: ("Christmas Island",                             "CX"),
     52: ("Clipperton Island",                            "CP"),
     53: ("Cocos Islands",                                "CC"),
     54: ("Colombia",                                     "CO"),
     55: ("Comoros",                                      "KM"),
     56: ("Congo - Brazzaville",                          "CG"),
     57: ("Congo - Kinshasa",                             "CD"),
     58: ("Cook Islands",                                 "CK"),
     59: ("Costa Rica",                                   "CR"),
     60: ("Croatia",                                      "HR"),
     61: ("Cuba",                                         "CU"),
     62: ("Curacao",                                      "CW"),
     63: ("Cyprus",                                       "CY"),
     64: ("Czechia",                                      "CZ"),
     65: ("Denmark",                                      "DK"),
     66: ("Diego Garcia",                                 "DG"),
     67: ("Djibouti",                                     "DJ"),
     68: ("Dominica",                                     "DM"),
     69: ("Dominican Republic",                           "DO"),
     70: ("Ecuador",                                      "EC"),
     71: ("Egypt",                                        "EG"),
     72: ("El Salvador",                                  "SV"),
     73: ("Equatorial Guinea",                            "GQ"),
     74: ("Eritrea",                                      "ER"),
     75: ("Estonia",                                      "EE"),
     76: ("Eswatini",                                     "SZ"),
     77: ("Ethiopia",                                     "ET"),
     78: ("Europe",                                       "150"),
     79: ("European Union",                               "EU"),
     80: ("Falkland Islands",                             "FK"),
     81: ("Faroe Islands",                                "FO"),
     82: ("Fiji",                                         "FJ"),
     83: ("Finland",                                      "FI"),
     84: ("France",                                       "FR"),
     85: ("French Guiana",                                "GF"),
     86: ("French Polynesia",                             "PF"),
     87: ("French Southern Territories",                  "TF"),
     88: ("Gabon",                                        "GA"),
     89: ("Gambia",                                       "GM"),
     90: ("Georgia",                                      "GE"),
     91: ("Germany",                                      "DE"),
     92: ("Ghana",                                        "GH"),
     93: ("Gibraltar",                                    "GI"),
     94: ("Greece",                                       "GR"),
     95: ("Greenland",                                    "GL"),
     96: ("Grenada",                                      "GD"),
     97: ("Guadeloupe",                                   "GP"),
     98: ("Guam",                                         "GU"),
     99: ("Guatemala",                                    "GT"),
    100: ("Guernsey",                                     "GG"),
    101: ("Guinea-Bissau",                                "GW"),
    102: ("Guinea",                                       "GN"),
    103: ("Guyana",                                       "GY"),
    104: ("Haiti",                                        "HT"),
    105: ("Heard and McDonald Islands",                   "HM"),
    106: ("Honduras",                                     "HN"),
    107: ("Hong Kong",                                    "HK"),
    108: ("Hungary",                                      "HU"),
    109: ("Iceland",                                      "IS"),
    110: ("India",                                        "IN"),
    111: ("Indonesia",                                    "ID"),
    112: ("Iran",                                         "IR"),
    113: ("Iraq",                                         "IQ"),
    114: ("Ireland",                                      "IE"),
    115: ("Isle of Man",                                  "IM"),
    116: ("Israel",                                       "IL"),
    117: ("Italy",                                        "IT"),
    # Officially Côte d’Ivoire, which we'd need to map to CotedIvoire
    # or CoteDIvoire, either failing to make the d' separate from Cote
    # or messing with its case. So stick with Ivory Coast:
    118: ("Ivory Coast",                                  "CI"),
    119: ("Jamaica",                                      "JM"),
    120: ("Japan",                                        "JP"),
    121: ("Jersey",                                       "JE"),
    122: ("Jordan",                                       "JO"),
    123: ("Kazakhstan",                                   "KZ"),
    124: ("Kenya",                                        "KE"),
    125: ("Kiribati",                                     "KI"),
    126: ("Kosovo",                                       "XK"),
    127: ("Kuwait",                                       "KW"),
    128: ("Kyrgyzstan",                                   "KG"),
    129: ("Laos",                                         "LA"),
    130: ("Latin America",                                "419"),
    131: ("Latvia",                                       "LV"),
    132: ("Lebanon",                                      "LB"),
    133: ("Lesotho",                                      "LS"),
    134: ("Liberia",                                      "LR"),
    135: ("Libya",                                        "LY"),
    136: ("Liechtenstein",                                "LI"),
    137: ("Lithuania",                                    "LT"),
    138: ("Luxembourg",                                   "LU"),
    139: ("Macao",                                        "MO"),
    140: ("Macedonia",                                    "MK"),
    141: ("Madagascar",                                   "MG"),
    142: ("Malawi",                                       "MW"),
    143: ("Malaysia",                                     "MY"),
    144: ("Maldives",                                     "MV"),
    145: ("Mali",                                         "ML"),
    146: ("Malta",                                        "MT"),
    147: ("Marshall Islands",                             "MH"),
    148: ("Martinique",                                   "MQ"),
    149: ("Mauritania",                                   "MR"),
    150: ("Mauritius",                                    "MU"),
    151: ("Mayotte",                                      "YT"),
    152: ("Mexico",                                       "MX"),
    153: ("Micronesia",                                   "FM"),
    154: ("Moldova",                                      "MD"),
    155: ("Monaco",                                       "MC"),
    156: ("Mongolia",                                     "MN"),
    157: ("Montenegro",                                   "ME"),
    158: ("Montserrat",                                   "MS"),
    159: ("Morocco",                                      "MA"),
    160: ("Mozambique",                                   "MZ"),
    161: ("Myanmar",                                      "MM"),
    162: ("Namibia",                                      "NA"),
    163: ("Nauru",                                        "NR"),
    164: ("Nepal",                                        "NP"),
    165: ("Netherlands",                                  "NL"),
    166: ("New Caledonia",                                "NC"),
    167: ("New Zealand",                                  "NZ"),
    168: ("Nicaragua",                                    "NI"),
    169: ("Nigeria",                                      "NG"),
    170: ("Niger",                                        "NE"),
    171: ("Niue",                                         "NU"),
    172: ("Norfolk Island",                               "NF"),
    173: ("Northern Mariana Islands",                     "MP"),
    174: ("North Korea",                                  "KP"),
    175: ("Norway",                                       "NO"),
    176: ("Oman",                                         "OM"),
    177: ("Outlying Oceania",                             "QO"),
    178: ("Pakistan",                                     "PK"),
    179: ("Palau",                                        "PW"),
    180: ("Palestinian Territories",                      "PS"),
    181: ("Panama",                                       "PA"),
    182: ("Papua New Guinea",                             "PG"),
    183: ("Paraguay",                                     "PY"),
    184: ("Peru",                                         "PE"),
    185: ("Philippines",                                  "PH"),
    186: ("Pitcairn",                                     "PN"),
    187: ("Poland",                                       "PL"),
    188: ("Portugal",                                     "PT"),
    189: ("Puerto Rico",                                  "PR"),
    190: ("Qatar",                                        "QA"),
    191: ("Reunion",                                      "RE"),
    192: ("Romania",                                      "RO"),
    193: ("Russia",                                       "RU"),
    194: ("Rwanda",                                       "RW"),
    195: ("Saint Barthelemy",                             "BL"),
    196: ("Saint Helena",                                 "SH"),
    197: ("Saint Kitts and Nevis",                        "KN"),
    198: ("Saint Lucia",                                  "LC"),
    199: ("Saint Martin",                                 "MF"),
    200: ("Saint Pierre and Miquelon",                    "PM"),
    201: ("Saint Vincent and Grenadines",                 "VC"),
    202: ("Samoa",                                        "WS"),
    203: ("San Marino",                                   "SM"),
    204: ("Sao Tome and Principe",                        "ST"),
    205: ("Saudi Arabia",                                 "SA"),
    206: ("Senegal",                                      "SN"),
    207: ("Serbia",                                       "RS"),
    208: ("Seychelles",                                   "SC"),
    209: ("Sierra Leone",                                 "SL"),
    210: ("Singapore",                                    "SG"),
    211: ("Sint Maarten",                                 "SX"),
    212: ("Slovakia",                                     "SK"),
    213: ("Slovenia",                                     "SI"),
    214: ("Solomon Islands",                              "SB"),
    215: ("Somalia",                                      "SO"),
    216: ("South Africa",                                 "ZA"),
    217: ("South Georgia and South Sandwich Islands",     "GS"),
    218: ("South Korea",                                  "KR"),
    219: ("South Sudan",                                  "SS"),
    220: ("Spain",                                        "ES"),
    221: ("Sri Lanka",                                    "LK"),
    222: ("Sudan",                                        "SD"),
    223: ("Suriname",                                     "SR"),
    224: ("Svalbard and Jan Mayen",                       "SJ"),
    225: ("Sweden",                                       "SE"),
    226: ("Switzerland",                                  "CH"),
    227: ("Syria",                                        "SY"),
    228: ("Taiwan",                                       "TW"),
    229: ("Tajikistan",                                   "TJ"),
    230: ("Tanzania",                                     "TZ"),
    231: ("Thailand",                                     "TH"),
    232: ("Timor-Leste",                                  "TL"),
    233: ("Togo",                                         "TG"),
    234: ("Tokelau",                                      "TK"),
    235: ("Tonga",                                        "TO"),
    236: ("Trinidad and Tobago",                          "TT"),
    237: ("Tristan da Cunha",                             "TA"),
    238: ("Tunisia",                                      "TN"),
    239: ("Turkey",                                       "TR"),
    240: ("Turkmenistan",                                 "TM"),
    241: ("Turks and Caicos Islands",                     "TC"),
    242: ("Tuvalu",                                       "TV"),
    243: ("Uganda",                                       "UG"),
    244: ("Ukraine",                                      "UA"),
    245: ("United Arab Emirates",                         "AE"),
    246: ("United Kingdom",                               "GB"),
    247: ("United States Outlying Islands",               "UM"),
    248: ("United States",                                "US"),
    249: ("United States Virgin Islands",                 "VI"),
    250: ("Uruguay",                                      "UY"),
    251: ("Uzbekistan",                                   "UZ"),
    252: ("Vanuatu",                                      "VU"),
    253: ("Vatican City",                                 "VA"),
    254: ("Venezuela",                                    "VE"),
    255: ("Vietnam",                                      "VN"),
    256: ("Wallis and Futuna",                            "WF"),
    257: ("Western Sahara",                               "EH"),
    258: ("world",                                        "001"),
    259: ("Yemen",                                        "YE"),
    260: ("Zambia",                                       "ZM"),
    261: ("Zimbabwe",                                     "ZW"),
}

territory_aliases = {
    # Renamings prior to Qt 6.0 (CLDR v37):
    'DemocraticRepublicOfCongo': 'CongoKinshasa',
    'PeoplesRepublicOfCongo': 'CongoBrazzaville',
    'DemocraticRepublicOfKorea': 'NorthKorea',
    'RepublicOfKorea': 'SouthKorea',
    'RussianFederation': 'Russia',
    'SyrianArabRepublic': 'Syria',
    'LatinAmericaAndTheCaribbean': 'LatinAmerica',
    # Renamings:
    'EastTimor': 'TimorLeste',
    'Bonaire': 'CaribbeanNetherlands',
    'Macau': 'Macao',
    'SouthGeorgiaAndTheSouthSandwichIslands': 'SouthGeorgiaAndSouthSandwichIslands',
    'WallisAndFutunaIslands': 'WallisAndFutuna',
    'SaintVincentAndTheGrenadines': 'SaintVincentAndGrenadines',
    'BosniaAndHerzegowina': 'BosniaAndHerzegovina',
    'SvalbardAndJanMayenIslands': 'SvalbardAndJanMayen',
    'VaticanCityState': 'VaticanCity',
    'Swaziland': 'Eswatini',
    'UnitedStatesMinorOutlyingIslands': 'UnitedStatesOutlyingIslands',
    'CuraSao': 'Curacao',
    'CzechRepublic': 'Czechia',

    # Backwards compatibility with old Country enum, prior to Qt 6.2:
    'AnyCountry': 'AnyTerritory',
    'NauruCountry': 'NauruTerritory',
    'TokelauCountry': 'TokelauTerritory',
    'TuvaluCountry': 'TuvaluTerritory',
}

script_map = {
      0: ("AnyScript",              "Zzzz"),

      1: ("Adlam",                  "Adlm"),
      2: ("Ahom",                   "Ahom"),
      3: ("Anatolian Hieroglyphs",  "Hluw"),
      4: ("Arabic",                 "Arab"),
      5: ("Armenian",               "Armn"),
      6: ("Avestan",                "Avst"),
      7: ("Balinese",               "Bali"),
      8: ("Bamum",                  "Bamu"),
      9: ("Bangla",                 "Beng"),
     10: ("Bassa Vah",              "Bass"),
     11: ("Batak",                  "Batk"),
     12: ("Bhaiksuki",              "Bhks"),
     13: ("Bopomofo",               "Bopo"),
     14: ("Brahmi",                 "Brah"),
     15: ("Braille",                "Brai"),
     16: ("Buginese",               "Bugi"),
     17: ("Buhid",                  "Buhd"),
     18: ("Canadian Aboriginal",    "Cans"),
     19: ("Carian",                 "Cari"),
     20: ("Caucasian Albanian",     "Aghb"),
     21: ("Chakma",                 "Cakm"),
     22: ("Cham",                   "Cham"),
     23: ("Cherokee",               "Cher"),
     24: ("Coptic",                 "Copt"),
     25: ("Cuneiform",              "Xsux"),
     26: ("Cypriot",                "Cprt"),
     27: ("Cyrillic",               "Cyrl"),
     28: ("Deseret",                "Dsrt"),
     29: ("Devanagari",             "Deva"),
     30: ("Duployan",               "Dupl"),
     31: ("Egyptian hieroglyphs",   "Egyp"),
     32: ("Elbasan",                "Elba"),
     33: ("Ethiopic",               "Ethi"),
     34: ("Fraser",                 "Lisu"),
     35: ("Georgian",               "Geor"),
     36: ("Glagolitic",             "Glag"),
     37: ("Gothic",                 "Goth"),
     38: ("Grantha",                "Gran"),
     39: ("Greek",                  "Grek"),
     40: ("Gujarati",               "Gujr"),
     41: ("Gurmukhi",               "Guru"),
     42: ("Hangul",                 "Hang"),
     43: ("Han",                    "Hani"),
     44: ("Hanunoo",                "Hano"),
     45: ("Han with Bopomofo",      "Hanb"),
     46: ("Hatran",                 "Hatr"),
     47: ("Hebrew",                 "Hebr"),
     48: ("Hiragana",               "Hira"),
     49: ("Imperial Aramaic",       "Armi"),
     50: ("Inscriptional Pahlavi",  "Phli"),
     51: ("Inscriptional Parthian", "Prti"),
     52: ("Jamo",                   "Jamo"),
     53: ("Japanese",               "Jpan"),
     54: ("Javanese",               "Java"),
     55: ("Kaithi",                 "Kthi"),
     56: ("Kannada",                "Knda"),
     57: ("Katakana",               "Kana"),
     58: ("Kayah Li",               "Kali"),
     59: ("Kharoshthi",             "Khar"),
     60: ("Khmer",                  "Khmr"),
     61: ("Khojki",                 "Khoj"),
     62: ("Khudawadi",              "Sind"),
     63: ("Korean",                 "Kore"),
     64: ("Lanna",                  "Lana"),
     65: ("Lao",                    "Laoo"),
     66: ("Latin",                  "Latn"),
     67: ("Lepcha",                 "Lepc"),
     68: ("Limbu",                  "Limb"),
     69: ("Linear A",               "Lina"),
     70: ("Linear B",               "Linb"),
     71: ("Lycian",                 "Lyci"),
     72: ("Lydian",                 "Lydi"),
     73: ("Mahajani",               "Mahj"),
     74: ("Malayalam",              "Mlym"),
     75: ("Mandaean",               "Mand"),
     76: ("Manichaean",             "Mani"),
     77: ("Marchen",                "Marc"),
     78: ("Meitei Mayek",           "Mtei"),
     79: ("Mende",                  "Mend"),
     80: ("Meroitic Cursive",       "Merc"),
     81: ("Meroitic",               "Mero"),
     82: ("Modi",                   "Modi"),
     83: ("Mongolian",              "Mong"),
     84: ("Mro",                    "Mroo"),
     85: ("Multani",                "Mult"),
     86: ("Myanmar",                "Mymr"),
     87: ("Nabataean",              "Nbat"),
     88: ("Newa",                   "Newa"),
     89: ("New Tai Lue",            "Talu"),
     90: ("Nko",                    "Nkoo"),
     91: ("Odia",                   "Orya"),
     92: ("Ogham",                  "Ogam"),
     93: ("Ol Chiki",               "Olck"),
     94: ("Old Hungarian",          "Hung"),
     95: ("Old Italic",             "Ital"),
     96: ("Old North Arabian",      "Narb"),
     97: ("Old Permic",             "Perm"),
     98: ("Old Persian",            "Xpeo"),
     99: ("Old South Arabian",      "Sarb"),
    100: ("Orkhon",                 "Orkh"),
    101: ("Osage",                  "Osge"),
    102: ("Osmanya",                "Osma"),
    103: ("Pahawh Hmong",           "Hmng"),
    104: ("Palmyrene",              "Palm"),
    105: ("Pau Cin Hau",            "Pauc"),
    106: ("Phags-pa",               "Phag"),
    107: ("Phoenician",             "Phnx"),
    108: ("Pollard Phonetic",       "Plrd"),
    109: ("Psalter Pahlavi",        "Phlp"),
    110: ("Rejang",                 "Rjng"),
    111: ("Runic",                  "Runr"),
    112: ("Samaritan",              "Samr"),
    113: ("Saurashtra",             "Saur"),
    114: ("Sharada",                "Shrd"),
    115: ("Shavian",                "Shaw"),
    116: ("Siddham",                "Sidd"),
    117: ("SignWriting",            "Sgnw"), # Oddly, en.xml leaves no space in it.
    118: ("Simplified Han",         "Hans"),
    119: ("Sinhala",                "Sinh"),
    120: ("Sora Sompeng",           "Sora"),
    121: ("Sundanese",              "Sund"),
    122: ("Syloti Nagri",           "Sylo"),
    123: ("Syriac",                 "Syrc"),
    124: ("Tagalog",                "Tglg"),
    125: ("Tagbanwa",               "Tagb"),
    126: ("Tai Le",                 "Tale"),
    127: ("Tai Viet",               "Tavt"),
    128: ("Takri",                  "Takr"),
    129: ("Tamil",                  "Taml"),
    130: ("Tangut",                 "Tang"),
    131: ("Telugu",                 "Telu"),
    132: ("Thaana",                 "Thaa"),
    133: ("Thai",                   "Thai"),
    134: ("Tibetan",                "Tibt"),
    135: ("Tifinagh",               "Tfng"),
    136: ("Tirhuta",                "Tirh"),
    137: ("Traditional Han",        "Hant"),
    138: ("Ugaritic",               "Ugar"),
    139: ("Vai",                    "Vaii"),
    140: ("Varang Kshiti",          "Wara"),
    141: ("Yi",                     "Yiii"),
    # Added at CLDR v43
    142: ("Hanifi",                 "Rohg"), # Used for Rohingya
}

script_aliases = {
    # Renamings prior to Qt 6.0 (CLDR v37):
    'SimplifiedChineseScript': 'SimplifiedHanScript',
    'TraditionalChineseScript': 'TraditionalHanScript',
    # Renamings:
    'OriyaScript': 'OdiaScript',
    'MendeKikakuiScript': 'MendeScript',
    'BengaliScript': 'BanglaScript',
}