ISO 639-2: remove languages not spoken anymore

This commit is contained in:
Moritz Bunkus 2015-09-22 22:56:31 +02:00
parent 96599d3c68
commit c99f9c3f2e
2 changed files with 25 additions and 18 deletions

View File

@ -1,5 +1,9 @@
2015-09-22 Moritz Bunkus <moritz@bunkus.org>
* all: several ISO 639-2 codes of languages that are very old and
not spoken anymore have been removed (e.g. »English, Middle
(1100-1500)«).
* MKVToolNix GUI: enhancement: on Windows the drop down boxes were
elliding overlong text. This has been changed to making the open
combo boxes' scroll areas wide enough to contain the whole

View File

@ -107,10 +107,8 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Chinook jargon", "chn", std::string{}, std::string{} },
{ "Chipewyan; Dene Suline", "chp", std::string{}, std::string{} },
{ "Choctaw", "cho", std::string{}, std::string{} },
{ "Church Slavic; Old Slavonic; Church Slavonic; Old Bulgarian; Old Church Slavonic", "chu", "cu", std::string{} },
{ "Chuukese", "chk", std::string{}, std::string{} },
{ "Chuvash", "chv", "cv", std::string{} },
{ "Classical Newari; Old Newari; Classical Nepal Bhasa", "nwc", std::string{}, std::string{} },
{ "Classical Syriac", "syc", std::string{}, std::string{} },
{ "Coptic", "cop", std::string{}, std::string{} },
{ "Cornish", "cor", "kw", std::string{} },
@ -135,7 +133,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Dogrib", "dgr", std::string{}, std::string{} },
{ "Dravidian languages", "dra", std::string{}, std::string{} },
{ "Duala", "dua", std::string{}, std::string{} },
{ "Dutch, Middle (ca.1050-1350)", "dum", std::string{}, std::string{} },
{ "Dutch; Flemish", "dut", "nl", "nld" },
{ "Dyula", "dyu", std::string{}, std::string{} },
{ "Dzongkha", "dzo", "dz", std::string{} },
@ -145,8 +142,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Ekajuk", "eka", std::string{}, std::string{} },
{ "Elamite", "elx", std::string{}, std::string{} },
{ "English", "eng", "en", std::string{} },
{ "English, Middle (1100-1500)", "enm", std::string{}, std::string{} },
{ "English, Old (ca.450-1100)", "ang", std::string{}, std::string{} },
{ "Erzya", "myv", std::string{}, std::string{} },
{ "Esperanto", "epo", "eo", std::string{} },
{ "Estonian", "est", "et", std::string{} },
@ -161,8 +156,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Finno-Ugrian languages", "fiu", std::string{}, std::string{} },
{ "Fon", "fon", std::string{}, std::string{} },
{ "French", "fre", "fr", "fra" },
{ "French, Middle (ca.1400-1600)", "frm", std::string{}, std::string{} },
{ "French, Old (842-ca.1400)", "fro", std::string{}, std::string{} },
{ "Friulian", "fur", std::string{}, std::string{} },
{ "Fulah", "ful", "ff", std::string{} },
{ "Ga", "gaa", std::string{}, std::string{} },
@ -175,16 +168,13 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Geez", "gez", std::string{}, std::string{} },
{ "Georgian", "geo", "ka", "kat" },
{ "German", "ger", "de", "deu" },
{ "German, Middle High (ca.1050-1500)", "gmh", std::string{}, std::string{} },
{ "German, Old High (ca.750-1050)", "goh", std::string{}, std::string{} },
{ "Germanic languages", "gem", std::string{}, std::string{} },
{ "Gilbertese", "gil", std::string{}, std::string{} },
{ "Gondi", "gon", std::string{}, std::string{} },
{ "Gorontalo", "gor", std::string{}, std::string{} },
{ "Gothic", "got", std::string{}, std::string{} },
{ "Grebo", "grb", std::string{}, std::string{} },
{ "Greek, Ancient (to 1453)", "grc", std::string{}, std::string{} },
{ "Greek, Modern (1453-)", "gre", "el", "ell" },
{ "Greek", "gre", "el", "ell" },
{ "Guarani", "grn", "gn", std::string{} },
{ "Gujarati", "guj", "gu", std::string{} },
{ "Gwich'in", "gwi", std::string{}, std::string{} },
@ -219,8 +209,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Inupiaq", "ipk", "ik", std::string{} },
{ "Iranian languages", "ira", std::string{}, std::string{} },
{ "Irish", "gle", "ga", std::string{} },
{ "Irish, Middle (900-1200)", "mga", std::string{}, std::string{} },
{ "Irish, Old (to 900)", "sga", std::string{}, std::string{} },
{ "Iroquoian languages", "iro", std::string{}, std::string{} },
{ "Italian", "ita", "it", std::string{} },
{ "Japanese", "jpn", "ja", std::string{} },
@ -337,7 +325,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Niuean", "niu", std::string{}, std::string{} },
{ "No linguistic content; Not applicable", "zxx", std::string{}, std::string{} },
{ "Nogai", "nog", std::string{}, std::string{} },
{ "Norse, Old", "non", std::string{}, std::string{} },
{ "North American Indian languages", "nai", std::string{}, std::string{} },
{ "Northern Frisian", "frr", std::string{}, std::string{} },
{ "Northern Sami", "sme", "se", std::string{} },
@ -349,7 +336,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Nyoro", "nyo", std::string{}, std::string{} },
{ "Nzima", "nzi", std::string{}, std::string{} },
{ "Occitan (post 1500)", "oci", "oc", std::string{} },
{ "Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)", "arc", std::string{}, std::string{} },
{ "Ojibwa", "oji", "oj", std::string{} },
{ "Oriya", "ori", "or", std::string{} },
{ "Oromo", "orm", "om", std::string{} },
@ -366,14 +352,12 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Papuan languages", "paa", std::string{}, std::string{} },
{ "Pedi; Sepedi; Northern Sotho", "nso", std::string{}, std::string{} },
{ "Persian", "per", "fa", "fas" },
{ "Persian, Old (ca.600-400 B.C.)", "peo", std::string{}, std::string{} },
{ "Philippine languages", "phi", std::string{}, std::string{} },
{ "Phoenician", "phn", std::string{}, std::string{} },
{ "Pohnpeian", "pon", std::string{}, std::string{} },
{ "Polish", "pol", "pl", std::string{} },
{ "Portuguese", "por", "pt", std::string{} },
{ "Prakrit languages", "pra", std::string{}, std::string{} },
{ "Provençal, Old (to 1500);Occitan, Old (to 1500)", "pro", std::string{}, std::string{} },
{ "Pushto; Pashto", "pus", "ps", std::string{} },
{ "Quechua", "que", "qu", std::string{} },
{ "Rajasthani", "raj", std::string{}, std::string{} },
@ -463,7 +447,6 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Tumbuka", "tum", std::string{}, std::string{} },
{ "Tupi languages", "tup", std::string{}, std::string{} },
{ "Turkish", "tur", "tr", std::string{} },
{ "Turkish, Ottoman (1500-1928)", "ota", std::string{}, std::string{} },
{ "Turkmen", "tuk", "tk", std::string{} },
{ "Tuvalu", "tvl", std::string{}, std::string{} },
{ "Tuvinian", "tyv", std::string{}, std::string{} },
@ -507,6 +490,26 @@ std::vector<iso639_language_t> const g_iso639_languages{
{ "Zuni", "zun", std::string{}, std::string{} },
};
std::vector<iso639_language_t> const s_old_iso639_languages{
{ "Church Slavic; Old Slavonic; Church Slavonic; Old Bulgarian; Old Church Slavonic", "chu", "cu", std::string{} },
{ "Classical Newari; Old Newari; Classical Nepal Bhasa", "nwc", std::string{}, std::string{} },
{ "Dutch, Middle (ca.1050-1350)", "dum", std::string{}, std::string{} },
{ "English, Middle (1100-1500)", "enm", std::string{}, std::string{} },
{ "English, Old (ca.450-1100)", "ang", std::string{}, std::string{} },
{ "French, Middle (ca.1400-1600)", "frm", std::string{}, std::string{} },
{ "French, Old (842-ca.1400)", "fro", std::string{}, std::string{} },
{ "German, Middle High (ca.1050-1500)", "gmh", std::string{}, std::string{} },
{ "German, Old High (ca.750-1050)", "goh", std::string{}, std::string{} },
{ "Greek, Ancient (to 1453)", "grc", std::string{}, std::string{} },
{ "Irish, Middle (900-1200)", "mga", std::string{}, std::string{} },
{ "Irish, Old (to 900)", "sga", std::string{}, std::string{} },
{ "Norse, Old", "non", std::string{}, std::string{} },
{ "Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)", "arc", std::string{}, std::string{} },
{ "Persian, Old (ca.600-400 B.C.)", "peo", std::string{}, std::string{} },
{ "Provençal, Old (to 1500);Occitan, Old (to 1500)", "pro", std::string{}, std::string{} },
{ "Turkish, Ottoman (1500-1928)", "ota", std::string{}, std::string{} },
};
static std::unordered_map<std::string, std::string> s_deprecated_1_and_2_codes{
// ISO 639-1
{ "iw", "he" },