bdinfo-rs-core 2.0.0

//! ISO-639 language-code -> English-name lookup.
//!
//! Each code maps to a display name; an unrecognized code maps to itself, so a
//! stream's language field is never lost — at worst the raw code is shown.
//!
//! The mapping is a `static` table plus a linear scan (the
//! same shape as [`crate::discovery`]'s small lookup tables) — deliberately not a
//! hash map: the result feeds the stream model's language name, an output-path
//! value whose ordering must stay deterministic (the house rule: never a hash
//! map in an output path). The table is stored sorted by code; the lookup is an
//! exact match on the code, so storage order is non-observable.

/// ISO-639 code -> English language name, sorted by code.
///
/// The ISO-639-2 bibliographic/terminological aliases (e.g. `alb`/`sqi` ->
/// `Albanian`, `ger`/`deu` -> `German`) are kept as separate entries mapping to
/// the same name.
static LANGUAGE_CODES: &[(&str, &str)] = &[
    ("aar", "Afar"),
    ("abk", "Abkhazian"),
    ("ace", "Achinese"),
    ("ach", "Acoli"),
    ("ada", "Adangme"),
    ("afa", "Afro-Asiatic (Other)"),
    ("afh", "Afrihili"),
    ("afr", "Afrikaans"),
    ("aka", "Akan"),
    ("akk", "Akkadian"),
    ("alb", "Albanian"),
    ("ale", "Aleut"),
    ("alg", "Algonquian languages"),
    ("amh", "Amharic"),
    ("ang", "English, Old (ca.450-1100)"),
    ("apa", "Apache languages"),
    ("ara", "Arabic"),
    ("arc", "Aramaic"),
    ("arm", "Armenian"),
    ("arn", "Araucanian"),
    ("arp", "Arapaho"),
    ("art", "Artificial (Other)"),
    ("arw", "Arawak"),
    ("asm", "Assamese"),
    ("ath", "Athapascan languages"),
    ("aus", "Australian languages"),
    ("ava", "Avaric"),
    ("ave", "Avestan"),
    ("awa", "Awadhi"),
    ("aym", "Aymara"),
    ("aze", "Azerbaijani"),
    ("bad", "Banda"),
    ("bai", "Bamileke languages"),
    ("bak", "Bashkir"),
    ("bal", "Baluchi"),
    ("bam", "Bambara"),
    ("ban", "Balinese"),
    ("baq", "Basque"),
    ("bas", "Basa"),
    ("bat", "Baltic (Other)"),
    ("bej", "Beja"),
    ("bel", "Belarusian"),
    ("bem", "Bemba"),
    ("ben", "Bengali"),
    ("ber", "Berber (Other)"),
    ("bho", "Bhojpuri"),
    ("bih", "Bihari"),
    ("bik", "Bikol"),
    ("bin", "Bini"),
    ("bis", "Bislama"),
    ("bla", "Siksika"),
    ("bnt", "Bantu (Other)"),
    ("bod", "Tibetan"),
    ("bos", "Bosnian"),
    ("bra", "Braj"),
    ("bre", "Breton"),
    ("btk", "Batak (Indonesia)"),
    ("bua", "Buriat"),
    ("bug", "Buginese"),
    ("bul", "Bulgarian"),
    ("bur", "Burmese"),
    ("cad", "Caddo"),
    ("cai", "Central American Indian (Other)"),
    ("car", "Carib"),
    ("cat", "Catalan"),
    ("cau", "Caucasian (Other)"),
    ("ceb", "Cebuano"),
    ("cel", "Celtic (Other)"),
    ("ces", "Czech"),
    ("cha", "Chamorro"),
    ("chb", "Chibcha"),
    ("che", "Chechen"),
    ("chg", "Chagatai"),
    ("chi", "Chinese"),
    ("chk", "Chuukese"),
    ("chm", "Mari"),
    ("chn", "Chinook jargon"),
    ("cho", "Choctaw"),
    ("chp", "Chipewyan"),
    ("chr", "Cherokee"),
    ("chu", "Church Slavic"),
    ("chv", "Chuvash"),
    ("chy", "Cheyenne"),
    ("cmc", "Chamic languages"),
    ("cop", "Coptic"),
    ("cor", "Cornish"),
    ("cos", "Corsican"),
    ("cpe", "Creoles and pidgins,"),
    ("cpf", "Creoles and pidgins,"),
    ("cpp", "Creoles and pidgins,"),
    ("cre", "Cree"),
    ("crp", "Creoles and pidgins (Other)"),
    ("cus", "Cushitic (Other)"),
    ("cym", "Welsh"),
    ("cze", "Czech"),
    ("dak", "Dakota"),
    ("dan", "Danish"),
    ("day", "Dayak"),
    ("del", "Delaware"),
    ("den", "Slave (Athapascan)"),
    ("deu", "German"),
    ("dgr", "Dogrib"),
    ("din", "Dinka"),
    ("div", "Divehi"),
    ("doi", "Dogri"),
    ("dra", "Dravidian (Other)"),
    ("dua", "Duala"),
    ("dum", "Dutch, Middle (ca. 1050-1350)"),
    ("dut", "Dutch"),
    ("dyu", "Dyula"),
    ("dzo", "Dzongkha"),
    ("efi", "Efik"),
    ("egy", "Egyptian (Ancient)"),
    ("eka", "Ekajuk"),
    ("ell", "Greek"),
    ("elx", "Elamite"),
    ("eng", "English"),
    ("enm", "English, Middle (1100-1500)"),
    ("epo", "Esperanto"),
    ("est", "Estonian"),
    ("eus", "Basque"),
    ("ewe", "Ewe"),
    ("ewo", "Ewondo"),
    ("fan", "Fang"),
    ("fao", "Faroese"),
    ("fas", "Persian"),
    ("fat", "Fanti"),
    ("fij", "Fijian"),
    ("fin", "Finnish"),
    ("fiu", "Finno-Ugrian (Other)"),
    ("fon", "Fon"),
    ("fra", "French"),
    ("fre", "French"),
    ("frm", "French, Middle (ca.1400-1600)"),
    ("fro", "French, Old (842-ca.1400)"),
    ("fry", "Frisian"),
    ("ful", "Fulah"),
    ("fur", "Friulian"),
    ("gaa", "Ga"),
    ("gay", "Gayo"),
    ("gba", "Gbaya"),
    ("gem", "Germanic (Other)"),
    ("geo", "Georgian"),
    ("ger", "German"),
    ("gez", "Geez"),
    ("gil", "Gilbertese"),
    ("gla", "Gaelic"),
    ("gle", "Irish"),
    ("glg", "Gallegan"),
    ("glv", "Manx"),
    ("gmh", "German, Middle High (ca.1050-1500)"),
    ("goh", "German, Old High (ca.750-1050)"),
    ("gon", "Gondi"),
    ("gor", "Gorontalo"),
    ("got", "Gothic"),
    ("grb", "Grebo"),
    ("grc", "Greek, Ancient (to 1453)"),
    ("gre", "Greek"),
    ("grn", "Guarani"),
    ("guj", "Gujarati"),
    ("gwi", "Gwich´in"),
    ("hai", "Haida"),
    ("hau", "Hausa"),
    ("haw", "Hawaiian"),
    ("heb", "Hebrew"),
    ("her", "Herero"),
    ("hil", "Hiligaynon"),
    ("him", "Himachali"),
    ("hin", "Hindi"),
    ("hit", "Hittite"),
    ("hmn", "Hmong"),
    ("hmo", "Hiri Motu"),
    ("hrv", "Croatian"),
    ("hun", "Hungarian"),
    ("hup", "Hupa"),
    ("hye", "Armenian"),
    ("iba", "Iban"),
    ("ibo", "Igbo"),
    ("ice", "Icelandic"),
    ("ijo", "Ijo"),
    ("iku", "Inuktitut"),
    ("ile", "Interlingue"),
    ("ilo", "Iloko"),
    ("ina", "Interlingua (International"),
    ("inc", "Indic (Other)"),
    ("ind", "Indonesian"),
    ("ine", "Indo-European (Other)"),
    ("ipk", "Inupiaq"),
    ("ira", "Iranian (Other)"),
    ("iro", "Iroquoian languages"),
    ("isl", "Icelandic"),
    ("ita", "Italian"),
    ("jav", "Javanese"),
    ("jpn", "Japanese"),
    ("jpr", "Judeo-Persian"),
    ("jrb", "Judeo-Arabic"),
    ("kaa", "Kara-Kalpak"),
    ("kab", "Kabyle"),
    ("kac", "Kachin"),
    ("kal", "Kalaallisut"),
    ("kam", "Kamba"),
    ("kan", "Kannada"),
    ("kar", "Karen"),
    ("kas", "Kashmiri"),
    ("kat", "Georgian"),
    ("kau", "Kanuri"),
    ("kaw", "Kawi"),
    ("kaz", "Kazakh"),
    ("kha", "Khasi"),
    ("khi", "Khoisan (Other)"),
    ("khm", "Khmer"),
    ("kho", "Khotanese"),
    ("kik", "Kikuyu"),
    ("kin", "Kinyarwanda"),
    ("kir", "Kirghiz"),
    ("kmb", "Kimbundu"),
    ("kok", "Konkani"),
    ("kom", "Komi"),
    ("kon", "Kongo"),
    ("kor", "Korean"),
    ("kos", "Kosraean"),
    ("kpe", "Kpelle"),
    ("kro", "Kru"),
    ("kru", "Kurukh"),
    ("kua", "Kuanyama"),
    ("kum", "Kumyk"),
    ("kur", "Kurdish"),
    ("kut", "Kutenai"),
    ("lad", "Ladino"),
    ("lah", "Lahnda"),
    ("lam", "Lamba"),
    ("lao", "Lao"),
    ("lat", "Latin"),
    ("lav", "Latvian"),
    ("lez", "Lezghian"),
    ("lin", "Lingala"),
    ("lit", "Lithuanian"),
    ("lol", "Mongo"),
    ("loz", "Lozi"),
    ("ltz", "Letzeburgesch"),
    ("lua", "Luba-Lulua"),
    ("lub", "Luba-Katanga"),
    ("lug", "Ganda"),
    ("lui", "Luiseno"),
    ("lun", "Lunda"),
    ("luo", "Luo (Kenya and Tanzania)"),
    ("lus", "Lushai"),
    ("mac", "Macedonian"),
    ("mad", "Madurese"),
    ("mag", "Magahi"),
    ("mah", "Marshall"),
    ("mai", "Maithili"),
    ("mak", "Makasar"),
    ("mal", "Malayalam"),
    ("man", "Mandingo"),
    ("mao", "Maori"),
    ("map", "Austronesian (Other)"),
    ("mar", "Marathi"),
    ("mas", "Masai"),
    ("may", "Malay"),
    ("mdr", "Mandar"),
    ("men", "Mende"),
    ("mga", "Irish, Middle (900-1200)"),
    ("mic", "Micmac"),
    ("min", "Minangkabau"),
    ("mis", "Miscellaneous languages"),
    ("mkd", "Macedonian"),
    ("mkh", "Mon-Khmer (Other)"),
    ("mlg", "Malagasy"),
    ("mlt", "Maltese"),
    ("mnc", "Manchu"),
    ("mni", "Manipuri"),
    ("mno", "Manobo languages"),
    ("moh", "Mohawk"),
    ("mol", "Moldavian"),
    ("mon", "Mongolian"),
    ("mos", "Mossi"),
    ("mri", "Maori"),
    ("msa", "Malay"),
    ("mul", "Multiple languages"),
    ("mun", "Munda languages"),
    ("mus", "Creek"),
    ("mwr", "Marwari"),
    ("mya", "Burmese"),
    ("myn", "Mayan languages"),
    ("nah", "Nahuatl"),
    ("nai", "North American Indian (Other)"),
    ("nau", "Nauru"),
    ("nav", "Navajo"),
    ("nbl", "Ndebele, South"),
    ("nde", "Ndebele, North"),
    ("ndo", "Ndonga"),
    ("nds", "Saxon"),
    ("nep", "Nepali"),
    ("new", "Newari"),
    ("nia", "Nias"),
    ("nic", "Niger-Kordofanian (Other)"),
    ("niu", "Niuean"),
    ("nld", "Dutch"),
    ("nno", "Norwegian Nynorsk"),
    ("nob", "Norwegian Bokmål"),
    ("non", "Norse, Old"),
    ("nor", "Norwegian"),
    ("nso", "Sotho, Northern"),
    ("nub", "Nubian languages"),
    ("nya", "Nyanja"),
    ("nym", "Nyamwezi"),
    ("nyn", "Nyankole"),
    ("nyo", "Nyoro"),
    ("nzi", "Nzima"),
    ("oci", "Occitan"),
    ("oji", "Ojibwa"),
    ("ori", "Oriya"),
    ("orm", "Oromo"),
    ("osa", "Osage"),
    ("oss", "Ossetian"),
    ("ota", "Turkish, Ottoman (1500-1928)"),
    ("oto", "Otomian languages"),
    ("paa", "Papuan (Other)"),
    ("pag", "Pangasinan"),
    ("pal", "Pahlavi"),
    ("pam", "Pampanga"),
    ("pan", "Panjabi"),
    ("pap", "Papiamento"),
    ("pau", "Palauan"),
    ("peo", "Persian, Old (ca.600-400 B.C.)"),
    ("per", "Persian"),
    ("phi", "Philippine (Other)"),
    ("phn", "Phoenician"),
    ("pli", "Pali"),
    ("pol", "Polish"),
    ("pon", "Pohnpeian"),
    ("por", "Portuguese"),
    ("pra", "Prakrit languages"),
    ("pro", "Provençal"),
    ("pus", "Pushto"),
    ("que", "Quechua"),
    ("raj", "Rajasthani"),
    ("rap", "Rapanui"),
    ("rar", "Rarotongan"),
    ("roa", "Romance (Other)"),
    ("roh", "Raeto-Romance"),
    ("rom", "Romany"),
    ("ron", "Romanian"),
    ("rum", "Romanian"),
    ("run", "Rundi"),
    ("rus", "Russian"),
    ("sad", "Sandawe"),
    ("sag", "Sango"),
    ("sah", "Yakut"),
    ("sai", "South American Indian (Other)"),
    ("sal", "Salishan languages"),
    ("sam", "Samaritan Aramaic"),
    ("san", "Sanskrit"),
    ("sas", "Sasak"),
    ("sat", "Santali"),
    ("scc", "Serbian"),
    ("sco", "Scots"),
    ("scr", "Croatian"),
    ("sel", "Selkup"),
    ("sem", "Semitic (Other)"),
    ("sga", "Irish, Old (to 900)"),
    ("sgn", "Sign languages"),
    ("shn", "Shan"),
    ("sid", "Sidamo"),
    ("sin", "Sinhalese"),
    ("sio", "Siouan languages"),
    ("sit", "Sino-Tibetan (Other)"),
    ("sla", "Slavic (Other)"),
    ("slk", "Slovak"),
    ("slo", "Slovak"),
    ("slv", "Slovenian"),
    ("sme", "Northern Sami"),
    ("smi", "Sami languages (Other)"),
    ("smo", "Samoan"),
    ("sna", "Shona"),
    ("snd", "Sindhi"),
    ("snk", "Soninke"),
    ("sog", "Sogdian"),
    ("som", "Somali"),
    ("son", "Songhai"),
    ("sot", "Sotho, Southern"),
    ("spa", "Spanish"),
    ("sqi", "Albanian"),
    ("srd", "Sardinian"),
    ("srp", "Serbian"),
    ("srr", "Serer"),
    ("ssa", "Nilo-Saharan (Other)"),
    ("ssw", "Swati"),
    ("suk", "Sukuma"),
    ("sun", "Sundanese"),
    ("sus", "Susu"),
    ("sux", "Sumerian"),
    ("swa", "Swahili"),
    ("swe", "Swedish"),
    ("syr", "Syriac"),
    ("tah", "Tahitian"),
    ("tai", "Tai (Other)"),
    ("tam", "Tamil"),
    ("tat", "Tatar"),
    ("tel", "Telugu"),
    ("tem", "Timne"),
    ("ter", "Tereno"),
    ("tet", "Tetum"),
    ("tgk", "Tajik"),
    ("tgl", "Tagalog"),
    ("tha", "Thai"),
    ("tib", "Tibetan"),
    ("tig", "Tigre"),
    ("tir", "Tigrinya"),
    ("tiv", "Tiv"),
    ("tkl", "Tokelau"),
    ("tli", "Tlingit"),
    ("tmh", "Tamashek"),
    ("tog", "Tonga (Nyasa)"),
    ("ton", "Tonga (Tonga Islands)"),
    ("tpi", "Tok Pisin"),
    ("tsi", "Tsimshian"),
    ("tsn", "Tswana"),
    ("tso", "Tsonga"),
    ("tuk", "Turkmen"),
    ("tum", "Tumbuka"),
    ("tur", "Turkish"),
    ("tut", "Altaic (Other)"),
    ("tvl", "Tuvalu"),
    ("twi", "Twi"),
    ("tyv", "Tuvinian"),
    ("uga", "Ugaritic"),
    ("uig", "Uighur"),
    ("ukr", "Ukrainian"),
    ("umb", "Umbundu"),
    ("und", "Undetermined"),
    ("urd", "Urdu"),
    ("uzb", "Uzbek"),
    ("vai", "Vai"),
    ("ven", "Venda"),
    ("vie", "Vietnamese"),
    ("vol", "Volapük"),
    ("vot", "Votic"),
    ("wak", "Wakashan languages"),
    ("wal", "Walamo"),
    ("war", "Waray"),
    ("was", "Washo"),
    ("wel", "Welsh"),
    ("wen", "Sorbian languages"),
    ("wol", "Wolof"),
    ("xho", "Xhosa"),
    ("yao", "Yao"),
    ("yap", "Yapese"),
    ("yid", "Yiddish"),
    ("yor", "Yoruba"),
    ("ypk", "Yupik languages"),
    ("zap", "Zapotec"),
    ("zen", "Zenaga"),
    ("zha", "Zhuang"),
    ("zho", "Chinese"),
    ("znd", "Zande"),
    ("zul", "Zulu"),
    ("zun", "Zuni"),
];

/// Returns the English name for an ISO-639 language `code`, or `code` itself when
/// it is not in the table.
///
/// The match is exact and case-sensitive; anything unrecognized falls back to
/// the identity mapping, so the caller always gets a printable value.
#[must_use]
pub fn get_name(code: &str) -> String {
    LANGUAGE_CODES
        .iter()
        .find(|&&(candidate, _)| candidate == code)
        .map_or_else(|| code.to_owned(), |&(_, name)| name.to_owned())
}

#[cfg(test)]
mod tests {
    use proptest::prelude::{prop_assert_eq, proptest};

    use super::{LANGUAGE_CODES, get_name};

    #[test]
    fn known_codes_map_to_their_names() {
        assert_eq!(get_name("eng"), "English");
        assert_eq!(get_name("jpn"), "Japanese");
        assert_eq!(get_name("fra"), "French");
        assert_eq!(get_name("aar"), "Afar"); // first by code
        assert_eq!(get_name("zun"), "Zuni"); // last by code
    }

    #[test]
    fn iso_639_b_and_t_aliases_share_a_name() {
        // Both ISO-639-2 variants resolve to the same English name.
        assert_eq!(get_name("ger"), "German");
        assert_eq!(get_name("deu"), "German");
        assert_eq!(get_name("alb"), "Albanian");
        assert_eq!(get_name("sqi"), "Albanian");
    }

    #[test]
    fn non_ascii_names_are_preserved_verbatim() {
        // The report emits these exact UTF-8 bytes; keep them byte-for-byte.
        assert_eq!(get_name("gwi"), "Gwich\u{00B4}in");
        assert_eq!(get_name("nob"), "Norwegian Bokm\u{00E5}l");
        assert_eq!(get_name("pro"), "Proven\u{00E7}al");
        assert_eq!(get_name("vol"), "Volap\u{00FC}k");
    }

    #[test]
    fn unknown_code_returns_itself() {
        // The identity fallback: an unrecognized code maps to itself.
        assert_eq!(get_name("xyz"), "xyz");
        assert_eq!(get_name(""), "");
    }

    #[test]
    fn lookup_is_case_sensitive() {
        // The table matches the lowercase code exactly; uppercase falls
        // through to the identity fallback.
        assert_eq!(get_name("ENG"), "ENG");
        assert_eq!(get_name("Eng"), "Eng");
    }

    #[test]
    fn table_is_sorted_by_code_without_duplicates() {
        // Strictly ascending => sorted (the doc claim) and no duplicate codes.
        assert!(LANGUAGE_CODES.is_sorted_by(|a, b| a.0 < b.0));
    }

    #[test]
    fn every_table_entry_round_trips() {
        // Every code resolves to its own name, exercising the scan at all
        // positions (first, last, and everything between).
        for &(code, name) in LANGUAGE_CODES {
            assert_eq!(get_name(code), name);
        }
    }

    proptest! {
        #[test]
        fn uppercase_codes_are_never_found(code in "[A-Z]{3}") {
            // The table holds only lowercase codes, so any uppercase triple hits
            // the identity fallback.
            prop_assert_eq!(get_name(&code), code);
        }
    }
}