924 lines
32 KiB
Rust
924 lines
32 KiB
Rust
// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
|
|
//
|
|
// ucd-generate property-values ucd-15.0.0 --include gc,script,scx,age,gcb,wb,sb
|
|
//
|
|
// Unicode version: 15.0.0.
|
|
//
|
|
// ucd-generate 0.2.14 is available on crates.io.
|
|
|
|
pub const PROPERTY_VALUES: &'static [(
|
|
&'static str,
|
|
&'static [(&'static str, &'static str)],
|
|
)] = &[
|
|
(
|
|
"Age",
|
|
&[
|
|
("1.1", "V1_1"),
|
|
("10.0", "V10_0"),
|
|
("11.0", "V11_0"),
|
|
("12.0", "V12_0"),
|
|
("12.1", "V12_1"),
|
|
("13.0", "V13_0"),
|
|
("14.0", "V14_0"),
|
|
("15.0", "V15_0"),
|
|
("2.0", "V2_0"),
|
|
("2.1", "V2_1"),
|
|
("3.0", "V3_0"),
|
|
("3.1", "V3_1"),
|
|
("3.2", "V3_2"),
|
|
("4.0", "V4_0"),
|
|
("4.1", "V4_1"),
|
|
("5.0", "V5_0"),
|
|
("5.1", "V5_1"),
|
|
("5.2", "V5_2"),
|
|
("6.0", "V6_0"),
|
|
("6.1", "V6_1"),
|
|
("6.2", "V6_2"),
|
|
("6.3", "V6_3"),
|
|
("7.0", "V7_0"),
|
|
("8.0", "V8_0"),
|
|
("9.0", "V9_0"),
|
|
("na", "Unassigned"),
|
|
("unassigned", "Unassigned"),
|
|
("v100", "V10_0"),
|
|
("v11", "V1_1"),
|
|
("v110", "V11_0"),
|
|
("v120", "V12_0"),
|
|
("v121", "V12_1"),
|
|
("v130", "V13_0"),
|
|
("v140", "V14_0"),
|
|
("v150", "V15_0"),
|
|
("v20", "V2_0"),
|
|
("v21", "V2_1"),
|
|
("v30", "V3_0"),
|
|
("v31", "V3_1"),
|
|
("v32", "V3_2"),
|
|
("v40", "V4_0"),
|
|
("v41", "V4_1"),
|
|
("v50", "V5_0"),
|
|
("v51", "V5_1"),
|
|
("v52", "V5_2"),
|
|
("v60", "V6_0"),
|
|
("v61", "V6_1"),
|
|
("v62", "V6_2"),
|
|
("v63", "V6_3"),
|
|
("v70", "V7_0"),
|
|
("v80", "V8_0"),
|
|
("v90", "V9_0"),
|
|
],
|
|
),
|
|
(
|
|
"General_Category",
|
|
&[
|
|
("c", "Other"),
|
|
("casedletter", "Cased_Letter"),
|
|
("cc", "Control"),
|
|
("cf", "Format"),
|
|
("closepunctuation", "Close_Punctuation"),
|
|
("cn", "Unassigned"),
|
|
("cntrl", "Control"),
|
|
("co", "Private_Use"),
|
|
("combiningmark", "Mark"),
|
|
("connectorpunctuation", "Connector_Punctuation"),
|
|
("control", "Control"),
|
|
("cs", "Surrogate"),
|
|
("currencysymbol", "Currency_Symbol"),
|
|
("dashpunctuation", "Dash_Punctuation"),
|
|
("decimalnumber", "Decimal_Number"),
|
|
("digit", "Decimal_Number"),
|
|
("enclosingmark", "Enclosing_Mark"),
|
|
("finalpunctuation", "Final_Punctuation"),
|
|
("format", "Format"),
|
|
("initialpunctuation", "Initial_Punctuation"),
|
|
("l", "Letter"),
|
|
("lc", "Cased_Letter"),
|
|
("letter", "Letter"),
|
|
("letternumber", "Letter_Number"),
|
|
("lineseparator", "Line_Separator"),
|
|
("ll", "Lowercase_Letter"),
|
|
("lm", "Modifier_Letter"),
|
|
("lo", "Other_Letter"),
|
|
("lowercaseletter", "Lowercase_Letter"),
|
|
("lt", "Titlecase_Letter"),
|
|
("lu", "Uppercase_Letter"),
|
|
("m", "Mark"),
|
|
("mark", "Mark"),
|
|
("mathsymbol", "Math_Symbol"),
|
|
("mc", "Spacing_Mark"),
|
|
("me", "Enclosing_Mark"),
|
|
("mn", "Nonspacing_Mark"),
|
|
("modifierletter", "Modifier_Letter"),
|
|
("modifiersymbol", "Modifier_Symbol"),
|
|
("n", "Number"),
|
|
("nd", "Decimal_Number"),
|
|
("nl", "Letter_Number"),
|
|
("no", "Other_Number"),
|
|
("nonspacingmark", "Nonspacing_Mark"),
|
|
("number", "Number"),
|
|
("openpunctuation", "Open_Punctuation"),
|
|
("other", "Other"),
|
|
("otherletter", "Other_Letter"),
|
|
("othernumber", "Other_Number"),
|
|
("otherpunctuation", "Other_Punctuation"),
|
|
("othersymbol", "Other_Symbol"),
|
|
("p", "Punctuation"),
|
|
("paragraphseparator", "Paragraph_Separator"),
|
|
("pc", "Connector_Punctuation"),
|
|
("pd", "Dash_Punctuation"),
|
|
("pe", "Close_Punctuation"),
|
|
("pf", "Final_Punctuation"),
|
|
("pi", "Initial_Punctuation"),
|
|
("po", "Other_Punctuation"),
|
|
("privateuse", "Private_Use"),
|
|
("ps", "Open_Punctuation"),
|
|
("punct", "Punctuation"),
|
|
("punctuation", "Punctuation"),
|
|
("s", "Symbol"),
|
|
("sc", "Currency_Symbol"),
|
|
("separator", "Separator"),
|
|
("sk", "Modifier_Symbol"),
|
|
("sm", "Math_Symbol"),
|
|
("so", "Other_Symbol"),
|
|
("spaceseparator", "Space_Separator"),
|
|
("spacingmark", "Spacing_Mark"),
|
|
("surrogate", "Surrogate"),
|
|
("symbol", "Symbol"),
|
|
("titlecaseletter", "Titlecase_Letter"),
|
|
("unassigned", "Unassigned"),
|
|
("uppercaseletter", "Uppercase_Letter"),
|
|
("z", "Separator"),
|
|
("zl", "Line_Separator"),
|
|
("zp", "Paragraph_Separator"),
|
|
("zs", "Space_Separator"),
|
|
],
|
|
),
|
|
(
|
|
"Grapheme_Cluster_Break",
|
|
&[
|
|
("cn", "Control"),
|
|
("control", "Control"),
|
|
("cr", "CR"),
|
|
("eb", "E_Base"),
|
|
("ebase", "E_Base"),
|
|
("ebasegaz", "E_Base_GAZ"),
|
|
("ebg", "E_Base_GAZ"),
|
|
("em", "E_Modifier"),
|
|
("emodifier", "E_Modifier"),
|
|
("ex", "Extend"),
|
|
("extend", "Extend"),
|
|
("gaz", "Glue_After_Zwj"),
|
|
("glueafterzwj", "Glue_After_Zwj"),
|
|
("l", "L"),
|
|
("lf", "LF"),
|
|
("lv", "LV"),
|
|
("lvt", "LVT"),
|
|
("other", "Other"),
|
|
("pp", "Prepend"),
|
|
("prepend", "Prepend"),
|
|
("regionalindicator", "Regional_Indicator"),
|
|
("ri", "Regional_Indicator"),
|
|
("sm", "SpacingMark"),
|
|
("spacingmark", "SpacingMark"),
|
|
("t", "T"),
|
|
("v", "V"),
|
|
("xx", "Other"),
|
|
("zwj", "ZWJ"),
|
|
],
|
|
),
|
|
(
|
|
"Script",
|
|
&[
|
|
("adlam", "Adlam"),
|
|
("adlm", "Adlam"),
|
|
("aghb", "Caucasian_Albanian"),
|
|
("ahom", "Ahom"),
|
|
("anatolianhieroglyphs", "Anatolian_Hieroglyphs"),
|
|
("arab", "Arabic"),
|
|
("arabic", "Arabic"),
|
|
("armenian", "Armenian"),
|
|
("armi", "Imperial_Aramaic"),
|
|
("armn", "Armenian"),
|
|
("avestan", "Avestan"),
|
|
("avst", "Avestan"),
|
|
("bali", "Balinese"),
|
|
("balinese", "Balinese"),
|
|
("bamu", "Bamum"),
|
|
("bamum", "Bamum"),
|
|
("bass", "Bassa_Vah"),
|
|
("bassavah", "Bassa_Vah"),
|
|
("batak", "Batak"),
|
|
("batk", "Batak"),
|
|
("beng", "Bengali"),
|
|
("bengali", "Bengali"),
|
|
("bhaiksuki", "Bhaiksuki"),
|
|
("bhks", "Bhaiksuki"),
|
|
("bopo", "Bopomofo"),
|
|
("bopomofo", "Bopomofo"),
|
|
("brah", "Brahmi"),
|
|
("brahmi", "Brahmi"),
|
|
("brai", "Braille"),
|
|
("braille", "Braille"),
|
|
("bugi", "Buginese"),
|
|
("buginese", "Buginese"),
|
|
("buhd", "Buhid"),
|
|
("buhid", "Buhid"),
|
|
("cakm", "Chakma"),
|
|
("canadianaboriginal", "Canadian_Aboriginal"),
|
|
("cans", "Canadian_Aboriginal"),
|
|
("cari", "Carian"),
|
|
("carian", "Carian"),
|
|
("caucasianalbanian", "Caucasian_Albanian"),
|
|
("chakma", "Chakma"),
|
|
("cham", "Cham"),
|
|
("cher", "Cherokee"),
|
|
("cherokee", "Cherokee"),
|
|
("chorasmian", "Chorasmian"),
|
|
("chrs", "Chorasmian"),
|
|
("common", "Common"),
|
|
("copt", "Coptic"),
|
|
("coptic", "Coptic"),
|
|
("cpmn", "Cypro_Minoan"),
|
|
("cprt", "Cypriot"),
|
|
("cuneiform", "Cuneiform"),
|
|
("cypriot", "Cypriot"),
|
|
("cyprominoan", "Cypro_Minoan"),
|
|
("cyrillic", "Cyrillic"),
|
|
("cyrl", "Cyrillic"),
|
|
("deseret", "Deseret"),
|
|
("deva", "Devanagari"),
|
|
("devanagari", "Devanagari"),
|
|
("diak", "Dives_Akuru"),
|
|
("divesakuru", "Dives_Akuru"),
|
|
("dogr", "Dogra"),
|
|
("dogra", "Dogra"),
|
|
("dsrt", "Deseret"),
|
|
("dupl", "Duployan"),
|
|
("duployan", "Duployan"),
|
|
("egyp", "Egyptian_Hieroglyphs"),
|
|
("egyptianhieroglyphs", "Egyptian_Hieroglyphs"),
|
|
("elba", "Elbasan"),
|
|
("elbasan", "Elbasan"),
|
|
("elym", "Elymaic"),
|
|
("elymaic", "Elymaic"),
|
|
("ethi", "Ethiopic"),
|
|
("ethiopic", "Ethiopic"),
|
|
("geor", "Georgian"),
|
|
("georgian", "Georgian"),
|
|
("glag", "Glagolitic"),
|
|
("glagolitic", "Glagolitic"),
|
|
("gong", "Gunjala_Gondi"),
|
|
("gonm", "Masaram_Gondi"),
|
|
("goth", "Gothic"),
|
|
("gothic", "Gothic"),
|
|
("gran", "Grantha"),
|
|
("grantha", "Grantha"),
|
|
("greek", "Greek"),
|
|
("grek", "Greek"),
|
|
("gujarati", "Gujarati"),
|
|
("gujr", "Gujarati"),
|
|
("gunjalagondi", "Gunjala_Gondi"),
|
|
("gurmukhi", "Gurmukhi"),
|
|
("guru", "Gurmukhi"),
|
|
("han", "Han"),
|
|
("hang", "Hangul"),
|
|
("hangul", "Hangul"),
|
|
("hani", "Han"),
|
|
("hanifirohingya", "Hanifi_Rohingya"),
|
|
("hano", "Hanunoo"),
|
|
("hanunoo", "Hanunoo"),
|
|
("hatr", "Hatran"),
|
|
("hatran", "Hatran"),
|
|
("hebr", "Hebrew"),
|
|
("hebrew", "Hebrew"),
|
|
("hira", "Hiragana"),
|
|
("hiragana", "Hiragana"),
|
|
("hluw", "Anatolian_Hieroglyphs"),
|
|
("hmng", "Pahawh_Hmong"),
|
|
("hmnp", "Nyiakeng_Puachue_Hmong"),
|
|
("hrkt", "Katakana_Or_Hiragana"),
|
|
("hung", "Old_Hungarian"),
|
|
("imperialaramaic", "Imperial_Aramaic"),
|
|
("inherited", "Inherited"),
|
|
("inscriptionalpahlavi", "Inscriptional_Pahlavi"),
|
|
("inscriptionalparthian", "Inscriptional_Parthian"),
|
|
("ital", "Old_Italic"),
|
|
("java", "Javanese"),
|
|
("javanese", "Javanese"),
|
|
("kaithi", "Kaithi"),
|
|
("kali", "Kayah_Li"),
|
|
("kana", "Katakana"),
|
|
("kannada", "Kannada"),
|
|
("katakana", "Katakana"),
|
|
("katakanaorhiragana", "Katakana_Or_Hiragana"),
|
|
("kawi", "Kawi"),
|
|
("kayahli", "Kayah_Li"),
|
|
("khar", "Kharoshthi"),
|
|
("kharoshthi", "Kharoshthi"),
|
|
("khitansmallscript", "Khitan_Small_Script"),
|
|
("khmer", "Khmer"),
|
|
("khmr", "Khmer"),
|
|
("khoj", "Khojki"),
|
|
("khojki", "Khojki"),
|
|
("khudawadi", "Khudawadi"),
|
|
("kits", "Khitan_Small_Script"),
|
|
("knda", "Kannada"),
|
|
("kthi", "Kaithi"),
|
|
("lana", "Tai_Tham"),
|
|
("lao", "Lao"),
|
|
("laoo", "Lao"),
|
|
("latin", "Latin"),
|
|
("latn", "Latin"),
|
|
("lepc", "Lepcha"),
|
|
("lepcha", "Lepcha"),
|
|
("limb", "Limbu"),
|
|
("limbu", "Limbu"),
|
|
("lina", "Linear_A"),
|
|
("linb", "Linear_B"),
|
|
("lineara", "Linear_A"),
|
|
("linearb", "Linear_B"),
|
|
("lisu", "Lisu"),
|
|
("lyci", "Lycian"),
|
|
("lycian", "Lycian"),
|
|
("lydi", "Lydian"),
|
|
("lydian", "Lydian"),
|
|
("mahajani", "Mahajani"),
|
|
("mahj", "Mahajani"),
|
|
("maka", "Makasar"),
|
|
("makasar", "Makasar"),
|
|
("malayalam", "Malayalam"),
|
|
("mand", "Mandaic"),
|
|
("mandaic", "Mandaic"),
|
|
("mani", "Manichaean"),
|
|
("manichaean", "Manichaean"),
|
|
("marc", "Marchen"),
|
|
("marchen", "Marchen"),
|
|
("masaramgondi", "Masaram_Gondi"),
|
|
("medefaidrin", "Medefaidrin"),
|
|
("medf", "Medefaidrin"),
|
|
("meeteimayek", "Meetei_Mayek"),
|
|
("mend", "Mende_Kikakui"),
|
|
("mendekikakui", "Mende_Kikakui"),
|
|
("merc", "Meroitic_Cursive"),
|
|
("mero", "Meroitic_Hieroglyphs"),
|
|
("meroiticcursive", "Meroitic_Cursive"),
|
|
("meroitichieroglyphs", "Meroitic_Hieroglyphs"),
|
|
("miao", "Miao"),
|
|
("mlym", "Malayalam"),
|
|
("modi", "Modi"),
|
|
("mong", "Mongolian"),
|
|
("mongolian", "Mongolian"),
|
|
("mro", "Mro"),
|
|
("mroo", "Mro"),
|
|
("mtei", "Meetei_Mayek"),
|
|
("mult", "Multani"),
|
|
("multani", "Multani"),
|
|
("myanmar", "Myanmar"),
|
|
("mymr", "Myanmar"),
|
|
("nabataean", "Nabataean"),
|
|
("nagm", "Nag_Mundari"),
|
|
("nagmundari", "Nag_Mundari"),
|
|
("nand", "Nandinagari"),
|
|
("nandinagari", "Nandinagari"),
|
|
("narb", "Old_North_Arabian"),
|
|
("nbat", "Nabataean"),
|
|
("newa", "Newa"),
|
|
("newtailue", "New_Tai_Lue"),
|
|
("nko", "Nko"),
|
|
("nkoo", "Nko"),
|
|
("nshu", "Nushu"),
|
|
("nushu", "Nushu"),
|
|
("nyiakengpuachuehmong", "Nyiakeng_Puachue_Hmong"),
|
|
("ogam", "Ogham"),
|
|
("ogham", "Ogham"),
|
|
("olchiki", "Ol_Chiki"),
|
|
("olck", "Ol_Chiki"),
|
|
("oldhungarian", "Old_Hungarian"),
|
|
("olditalic", "Old_Italic"),
|
|
("oldnortharabian", "Old_North_Arabian"),
|
|
("oldpermic", "Old_Permic"),
|
|
("oldpersian", "Old_Persian"),
|
|
("oldsogdian", "Old_Sogdian"),
|
|
("oldsoutharabian", "Old_South_Arabian"),
|
|
("oldturkic", "Old_Turkic"),
|
|
("olduyghur", "Old_Uyghur"),
|
|
("oriya", "Oriya"),
|
|
("orkh", "Old_Turkic"),
|
|
("orya", "Oriya"),
|
|
("osage", "Osage"),
|
|
("osge", "Osage"),
|
|
("osma", "Osmanya"),
|
|
("osmanya", "Osmanya"),
|
|
("ougr", "Old_Uyghur"),
|
|
("pahawhhmong", "Pahawh_Hmong"),
|
|
("palm", "Palmyrene"),
|
|
("palmyrene", "Palmyrene"),
|
|
("pauc", "Pau_Cin_Hau"),
|
|
("paucinhau", "Pau_Cin_Hau"),
|
|
("perm", "Old_Permic"),
|
|
("phag", "Phags_Pa"),
|
|
("phagspa", "Phags_Pa"),
|
|
("phli", "Inscriptional_Pahlavi"),
|
|
("phlp", "Psalter_Pahlavi"),
|
|
("phnx", "Phoenician"),
|
|
("phoenician", "Phoenician"),
|
|
("plrd", "Miao"),
|
|
("prti", "Inscriptional_Parthian"),
|
|
("psalterpahlavi", "Psalter_Pahlavi"),
|
|
("qaac", "Coptic"),
|
|
("qaai", "Inherited"),
|
|
("rejang", "Rejang"),
|
|
("rjng", "Rejang"),
|
|
("rohg", "Hanifi_Rohingya"),
|
|
("runic", "Runic"),
|
|
("runr", "Runic"),
|
|
("samaritan", "Samaritan"),
|
|
("samr", "Samaritan"),
|
|
("sarb", "Old_South_Arabian"),
|
|
("saur", "Saurashtra"),
|
|
("saurashtra", "Saurashtra"),
|
|
("sgnw", "SignWriting"),
|
|
("sharada", "Sharada"),
|
|
("shavian", "Shavian"),
|
|
("shaw", "Shavian"),
|
|
("shrd", "Sharada"),
|
|
("sidd", "Siddham"),
|
|
("siddham", "Siddham"),
|
|
("signwriting", "SignWriting"),
|
|
("sind", "Khudawadi"),
|
|
("sinh", "Sinhala"),
|
|
("sinhala", "Sinhala"),
|
|
("sogd", "Sogdian"),
|
|
("sogdian", "Sogdian"),
|
|
("sogo", "Old_Sogdian"),
|
|
("sora", "Sora_Sompeng"),
|
|
("sorasompeng", "Sora_Sompeng"),
|
|
("soyo", "Soyombo"),
|
|
("soyombo", "Soyombo"),
|
|
("sund", "Sundanese"),
|
|
("sundanese", "Sundanese"),
|
|
("sylo", "Syloti_Nagri"),
|
|
("sylotinagri", "Syloti_Nagri"),
|
|
("syrc", "Syriac"),
|
|
("syriac", "Syriac"),
|
|
("tagalog", "Tagalog"),
|
|
("tagb", "Tagbanwa"),
|
|
("tagbanwa", "Tagbanwa"),
|
|
("taile", "Tai_Le"),
|
|
("taitham", "Tai_Tham"),
|
|
("taiviet", "Tai_Viet"),
|
|
("takr", "Takri"),
|
|
("takri", "Takri"),
|
|
("tale", "Tai_Le"),
|
|
("talu", "New_Tai_Lue"),
|
|
("tamil", "Tamil"),
|
|
("taml", "Tamil"),
|
|
("tang", "Tangut"),
|
|
("tangsa", "Tangsa"),
|
|
("tangut", "Tangut"),
|
|
("tavt", "Tai_Viet"),
|
|
("telu", "Telugu"),
|
|
("telugu", "Telugu"),
|
|
("tfng", "Tifinagh"),
|
|
("tglg", "Tagalog"),
|
|
("thaa", "Thaana"),
|
|
("thaana", "Thaana"),
|
|
("thai", "Thai"),
|
|
("tibetan", "Tibetan"),
|
|
("tibt", "Tibetan"),
|
|
("tifinagh", "Tifinagh"),
|
|
("tirh", "Tirhuta"),
|
|
("tirhuta", "Tirhuta"),
|
|
("tnsa", "Tangsa"),
|
|
("toto", "Toto"),
|
|
("ugar", "Ugaritic"),
|
|
("ugaritic", "Ugaritic"),
|
|
("unknown", "Unknown"),
|
|
("vai", "Vai"),
|
|
("vaii", "Vai"),
|
|
("vith", "Vithkuqi"),
|
|
("vithkuqi", "Vithkuqi"),
|
|
("wancho", "Wancho"),
|
|
("wara", "Warang_Citi"),
|
|
("warangciti", "Warang_Citi"),
|
|
("wcho", "Wancho"),
|
|
("xpeo", "Old_Persian"),
|
|
("xsux", "Cuneiform"),
|
|
("yezi", "Yezidi"),
|
|
("yezidi", "Yezidi"),
|
|
("yi", "Yi"),
|
|
("yiii", "Yi"),
|
|
("zanabazarsquare", "Zanabazar_Square"),
|
|
("zanb", "Zanabazar_Square"),
|
|
("zinh", "Inherited"),
|
|
("zyyy", "Common"),
|
|
("zzzz", "Unknown"),
|
|
],
|
|
),
|
|
(
|
|
"Script_Extensions",
|
|
&[
|
|
("adlam", "Adlam"),
|
|
("adlm", "Adlam"),
|
|
("aghb", "Caucasian_Albanian"),
|
|
("ahom", "Ahom"),
|
|
("anatolianhieroglyphs", "Anatolian_Hieroglyphs"),
|
|
("arab", "Arabic"),
|
|
("arabic", "Arabic"),
|
|
("armenian", "Armenian"),
|
|
("armi", "Imperial_Aramaic"),
|
|
("armn", "Armenian"),
|
|
("avestan", "Avestan"),
|
|
("avst", "Avestan"),
|
|
("bali", "Balinese"),
|
|
("balinese", "Balinese"),
|
|
("bamu", "Bamum"),
|
|
("bamum", "Bamum"),
|
|
("bass", "Bassa_Vah"),
|
|
("bassavah", "Bassa_Vah"),
|
|
("batak", "Batak"),
|
|
("batk", "Batak"),
|
|
("beng", "Bengali"),
|
|
("bengali", "Bengali"),
|
|
("bhaiksuki", "Bhaiksuki"),
|
|
("bhks", "Bhaiksuki"),
|
|
("bopo", "Bopomofo"),
|
|
("bopomofo", "Bopomofo"),
|
|
("brah", "Brahmi"),
|
|
("brahmi", "Brahmi"),
|
|
("brai", "Braille"),
|
|
("braille", "Braille"),
|
|
("bugi", "Buginese"),
|
|
("buginese", "Buginese"),
|
|
("buhd", "Buhid"),
|
|
("buhid", "Buhid"),
|
|
("cakm", "Chakma"),
|
|
("canadianaboriginal", "Canadian_Aboriginal"),
|
|
("cans", "Canadian_Aboriginal"),
|
|
("cari", "Carian"),
|
|
("carian", "Carian"),
|
|
("caucasianalbanian", "Caucasian_Albanian"),
|
|
("chakma", "Chakma"),
|
|
("cham", "Cham"),
|
|
("cher", "Cherokee"),
|
|
("cherokee", "Cherokee"),
|
|
("chorasmian", "Chorasmian"),
|
|
("chrs", "Chorasmian"),
|
|
("common", "Common"),
|
|
("copt", "Coptic"),
|
|
("coptic", "Coptic"),
|
|
("cpmn", "Cypro_Minoan"),
|
|
("cprt", "Cypriot"),
|
|
("cuneiform", "Cuneiform"),
|
|
("cypriot", "Cypriot"),
|
|
("cyprominoan", "Cypro_Minoan"),
|
|
("cyrillic", "Cyrillic"),
|
|
("cyrl", "Cyrillic"),
|
|
("deseret", "Deseret"),
|
|
("deva", "Devanagari"),
|
|
("devanagari", "Devanagari"),
|
|
("diak", "Dives_Akuru"),
|
|
("divesakuru", "Dives_Akuru"),
|
|
("dogr", "Dogra"),
|
|
("dogra", "Dogra"),
|
|
("dsrt", "Deseret"),
|
|
("dupl", "Duployan"),
|
|
("duployan", "Duployan"),
|
|
("egyp", "Egyptian_Hieroglyphs"),
|
|
("egyptianhieroglyphs", "Egyptian_Hieroglyphs"),
|
|
("elba", "Elbasan"),
|
|
("elbasan", "Elbasan"),
|
|
("elym", "Elymaic"),
|
|
("elymaic", "Elymaic"),
|
|
("ethi", "Ethiopic"),
|
|
("ethiopic", "Ethiopic"),
|
|
("geor", "Georgian"),
|
|
("georgian", "Georgian"),
|
|
("glag", "Glagolitic"),
|
|
("glagolitic", "Glagolitic"),
|
|
("gong", "Gunjala_Gondi"),
|
|
("gonm", "Masaram_Gondi"),
|
|
("goth", "Gothic"),
|
|
("gothic", "Gothic"),
|
|
("gran", "Grantha"),
|
|
("grantha", "Grantha"),
|
|
("greek", "Greek"),
|
|
("grek", "Greek"),
|
|
("gujarati", "Gujarati"),
|
|
("gujr", "Gujarati"),
|
|
("gunjalagondi", "Gunjala_Gondi"),
|
|
("gurmukhi", "Gurmukhi"),
|
|
("guru", "Gurmukhi"),
|
|
("han", "Han"),
|
|
("hang", "Hangul"),
|
|
("hangul", "Hangul"),
|
|
("hani", "Han"),
|
|
("hanifirohingya", "Hanifi_Rohingya"),
|
|
("hano", "Hanunoo"),
|
|
("hanunoo", "Hanunoo"),
|
|
("hatr", "Hatran"),
|
|
("hatran", "Hatran"),
|
|
("hebr", "Hebrew"),
|
|
("hebrew", "Hebrew"),
|
|
("hira", "Hiragana"),
|
|
("hiragana", "Hiragana"),
|
|
("hluw", "Anatolian_Hieroglyphs"),
|
|
("hmng", "Pahawh_Hmong"),
|
|
("hmnp", "Nyiakeng_Puachue_Hmong"),
|
|
("hrkt", "Katakana_Or_Hiragana"),
|
|
("hung", "Old_Hungarian"),
|
|
("imperialaramaic", "Imperial_Aramaic"),
|
|
("inherited", "Inherited"),
|
|
("inscriptionalpahlavi", "Inscriptional_Pahlavi"),
|
|
("inscriptionalparthian", "Inscriptional_Parthian"),
|
|
("ital", "Old_Italic"),
|
|
("java", "Javanese"),
|
|
("javanese", "Javanese"),
|
|
("kaithi", "Kaithi"),
|
|
("kali", "Kayah_Li"),
|
|
("kana", "Katakana"),
|
|
("kannada", "Kannada"),
|
|
("katakana", "Katakana"),
|
|
("katakanaorhiragana", "Katakana_Or_Hiragana"),
|
|
("kawi", "Kawi"),
|
|
("kayahli", "Kayah_Li"),
|
|
("khar", "Kharoshthi"),
|
|
("kharoshthi", "Kharoshthi"),
|
|
("khitansmallscript", "Khitan_Small_Script"),
|
|
("khmer", "Khmer"),
|
|
("khmr", "Khmer"),
|
|
("khoj", "Khojki"),
|
|
("khojki", "Khojki"),
|
|
("khudawadi", "Khudawadi"),
|
|
("kits", "Khitan_Small_Script"),
|
|
("knda", "Kannada"),
|
|
("kthi", "Kaithi"),
|
|
("lana", "Tai_Tham"),
|
|
("lao", "Lao"),
|
|
("laoo", "Lao"),
|
|
("latin", "Latin"),
|
|
("latn", "Latin"),
|
|
("lepc", "Lepcha"),
|
|
("lepcha", "Lepcha"),
|
|
("limb", "Limbu"),
|
|
("limbu", "Limbu"),
|
|
("lina", "Linear_A"),
|
|
("linb", "Linear_B"),
|
|
("lineara", "Linear_A"),
|
|
("linearb", "Linear_B"),
|
|
("lisu", "Lisu"),
|
|
("lyci", "Lycian"),
|
|
("lycian", "Lycian"),
|
|
("lydi", "Lydian"),
|
|
("lydian", "Lydian"),
|
|
("mahajani", "Mahajani"),
|
|
("mahj", "Mahajani"),
|
|
("maka", "Makasar"),
|
|
("makasar", "Makasar"),
|
|
("malayalam", "Malayalam"),
|
|
("mand", "Mandaic"),
|
|
("mandaic", "Mandaic"),
|
|
("mani", "Manichaean"),
|
|
("manichaean", "Manichaean"),
|
|
("marc", "Marchen"),
|
|
("marchen", "Marchen"),
|
|
("masaramgondi", "Masaram_Gondi"),
|
|
("medefaidrin", "Medefaidrin"),
|
|
("medf", "Medefaidrin"),
|
|
("meeteimayek", "Meetei_Mayek"),
|
|
("mend", "Mende_Kikakui"),
|
|
("mendekikakui", "Mende_Kikakui"),
|
|
("merc", "Meroitic_Cursive"),
|
|
("mero", "Meroitic_Hieroglyphs"),
|
|
("meroiticcursive", "Meroitic_Cursive"),
|
|
("meroitichieroglyphs", "Meroitic_Hieroglyphs"),
|
|
("miao", "Miao"),
|
|
("mlym", "Malayalam"),
|
|
("modi", "Modi"),
|
|
("mong", "Mongolian"),
|
|
("mongolian", "Mongolian"),
|
|
("mro", "Mro"),
|
|
("mroo", "Mro"),
|
|
("mtei", "Meetei_Mayek"),
|
|
("mult", "Multani"),
|
|
("multani", "Multani"),
|
|
("myanmar", "Myanmar"),
|
|
("mymr", "Myanmar"),
|
|
("nabataean", "Nabataean"),
|
|
("nagm", "Nag_Mundari"),
|
|
("nagmundari", "Nag_Mundari"),
|
|
("nand", "Nandinagari"),
|
|
("nandinagari", "Nandinagari"),
|
|
("narb", "Old_North_Arabian"),
|
|
("nbat", "Nabataean"),
|
|
("newa", "Newa"),
|
|
("newtailue", "New_Tai_Lue"),
|
|
("nko", "Nko"),
|
|
("nkoo", "Nko"),
|
|
("nshu", "Nushu"),
|
|
("nushu", "Nushu"),
|
|
("nyiakengpuachuehmong", "Nyiakeng_Puachue_Hmong"),
|
|
("ogam", "Ogham"),
|
|
("ogham", "Ogham"),
|
|
("olchiki", "Ol_Chiki"),
|
|
("olck", "Ol_Chiki"),
|
|
("oldhungarian", "Old_Hungarian"),
|
|
("olditalic", "Old_Italic"),
|
|
("oldnortharabian", "Old_North_Arabian"),
|
|
("oldpermic", "Old_Permic"),
|
|
("oldpersian", "Old_Persian"),
|
|
("oldsogdian", "Old_Sogdian"),
|
|
("oldsoutharabian", "Old_South_Arabian"),
|
|
("oldturkic", "Old_Turkic"),
|
|
("olduyghur", "Old_Uyghur"),
|
|
("oriya", "Oriya"),
|
|
("orkh", "Old_Turkic"),
|
|
("orya", "Oriya"),
|
|
("osage", "Osage"),
|
|
("osge", "Osage"),
|
|
("osma", "Osmanya"),
|
|
("osmanya", "Osmanya"),
|
|
("ougr", "Old_Uyghur"),
|
|
("pahawhhmong", "Pahawh_Hmong"),
|
|
("palm", "Palmyrene"),
|
|
("palmyrene", "Palmyrene"),
|
|
("pauc", "Pau_Cin_Hau"),
|
|
("paucinhau", "Pau_Cin_Hau"),
|
|
("perm", "Old_Permic"),
|
|
("phag", "Phags_Pa"),
|
|
("phagspa", "Phags_Pa"),
|
|
("phli", "Inscriptional_Pahlavi"),
|
|
("phlp", "Psalter_Pahlavi"),
|
|
("phnx", "Phoenician"),
|
|
("phoenician", "Phoenician"),
|
|
("plrd", "Miao"),
|
|
("prti", "Inscriptional_Parthian"),
|
|
("psalterpahlavi", "Psalter_Pahlavi"),
|
|
("qaac", "Coptic"),
|
|
("qaai", "Inherited"),
|
|
("rejang", "Rejang"),
|
|
("rjng", "Rejang"),
|
|
("rohg", "Hanifi_Rohingya"),
|
|
("runic", "Runic"),
|
|
("runr", "Runic"),
|
|
("samaritan", "Samaritan"),
|
|
("samr", "Samaritan"),
|
|
("sarb", "Old_South_Arabian"),
|
|
("saur", "Saurashtra"),
|
|
("saurashtra", "Saurashtra"),
|
|
("sgnw", "SignWriting"),
|
|
("sharada", "Sharada"),
|
|
("shavian", "Shavian"),
|
|
("shaw", "Shavian"),
|
|
("shrd", "Sharada"),
|
|
("sidd", "Siddham"),
|
|
("siddham", "Siddham"),
|
|
("signwriting", "SignWriting"),
|
|
("sind", "Khudawadi"),
|
|
("sinh", "Sinhala"),
|
|
("sinhala", "Sinhala"),
|
|
("sogd", "Sogdian"),
|
|
("sogdian", "Sogdian"),
|
|
("sogo", "Old_Sogdian"),
|
|
("sora", "Sora_Sompeng"),
|
|
("sorasompeng", "Sora_Sompeng"),
|
|
("soyo", "Soyombo"),
|
|
("soyombo", "Soyombo"),
|
|
("sund", "Sundanese"),
|
|
("sundanese", "Sundanese"),
|
|
("sylo", "Syloti_Nagri"),
|
|
("sylotinagri", "Syloti_Nagri"),
|
|
("syrc", "Syriac"),
|
|
("syriac", "Syriac"),
|
|
("tagalog", "Tagalog"),
|
|
("tagb", "Tagbanwa"),
|
|
("tagbanwa", "Tagbanwa"),
|
|
("taile", "Tai_Le"),
|
|
("taitham", "Tai_Tham"),
|
|
("taiviet", "Tai_Viet"),
|
|
("takr", "Takri"),
|
|
("takri", "Takri"),
|
|
("tale", "Tai_Le"),
|
|
("talu", "New_Tai_Lue"),
|
|
("tamil", "Tamil"),
|
|
("taml", "Tamil"),
|
|
("tang", "Tangut"),
|
|
("tangsa", "Tangsa"),
|
|
("tangut", "Tangut"),
|
|
("tavt", "Tai_Viet"),
|
|
("telu", "Telugu"),
|
|
("telugu", "Telugu"),
|
|
("tfng", "Tifinagh"),
|
|
("tglg", "Tagalog"),
|
|
("thaa", "Thaana"),
|
|
("thaana", "Thaana"),
|
|
("thai", "Thai"),
|
|
("tibetan", "Tibetan"),
|
|
("tibt", "Tibetan"),
|
|
("tifinagh", "Tifinagh"),
|
|
("tirh", "Tirhuta"),
|
|
("tirhuta", "Tirhuta"),
|
|
("tnsa", "Tangsa"),
|
|
("toto", "Toto"),
|
|
("ugar", "Ugaritic"),
|
|
("ugaritic", "Ugaritic"),
|
|
("unknown", "Unknown"),
|
|
("vai", "Vai"),
|
|
("vaii", "Vai"),
|
|
("vith", "Vithkuqi"),
|
|
("vithkuqi", "Vithkuqi"),
|
|
("wancho", "Wancho"),
|
|
("wara", "Warang_Citi"),
|
|
("warangciti", "Warang_Citi"),
|
|
("wcho", "Wancho"),
|
|
("xpeo", "Old_Persian"),
|
|
("xsux", "Cuneiform"),
|
|
("yezi", "Yezidi"),
|
|
("yezidi", "Yezidi"),
|
|
("yi", "Yi"),
|
|
("yiii", "Yi"),
|
|
("zanabazarsquare", "Zanabazar_Square"),
|
|
("zanb", "Zanabazar_Square"),
|
|
("zinh", "Inherited"),
|
|
("zyyy", "Common"),
|
|
("zzzz", "Unknown"),
|
|
],
|
|
),
|
|
(
|
|
"Sentence_Break",
|
|
&[
|
|
("at", "ATerm"),
|
|
("aterm", "ATerm"),
|
|
("cl", "Close"),
|
|
("close", "Close"),
|
|
("cr", "CR"),
|
|
("ex", "Extend"),
|
|
("extend", "Extend"),
|
|
("fo", "Format"),
|
|
("format", "Format"),
|
|
("le", "OLetter"),
|
|
("lf", "LF"),
|
|
("lo", "Lower"),
|
|
("lower", "Lower"),
|
|
("nu", "Numeric"),
|
|
("numeric", "Numeric"),
|
|
("oletter", "OLetter"),
|
|
("other", "Other"),
|
|
("sc", "SContinue"),
|
|
("scontinue", "SContinue"),
|
|
("se", "Sep"),
|
|
("sep", "Sep"),
|
|
("sp", "Sp"),
|
|
("st", "STerm"),
|
|
("sterm", "STerm"),
|
|
("up", "Upper"),
|
|
("upper", "Upper"),
|
|
("xx", "Other"),
|
|
],
|
|
),
|
|
(
|
|
"Word_Break",
|
|
&[
|
|
("aletter", "ALetter"),
|
|
("cr", "CR"),
|
|
("doublequote", "Double_Quote"),
|
|
("dq", "Double_Quote"),
|
|
("eb", "E_Base"),
|
|
("ebase", "E_Base"),
|
|
("ebasegaz", "E_Base_GAZ"),
|
|
("ebg", "E_Base_GAZ"),
|
|
("em", "E_Modifier"),
|
|
("emodifier", "E_Modifier"),
|
|
("ex", "ExtendNumLet"),
|
|
("extend", "Extend"),
|
|
("extendnumlet", "ExtendNumLet"),
|
|
("fo", "Format"),
|
|
("format", "Format"),
|
|
("gaz", "Glue_After_Zwj"),
|
|
("glueafterzwj", "Glue_After_Zwj"),
|
|
("hebrewletter", "Hebrew_Letter"),
|
|
("hl", "Hebrew_Letter"),
|
|
("ka", "Katakana"),
|
|
("katakana", "Katakana"),
|
|
("le", "ALetter"),
|
|
("lf", "LF"),
|
|
("mb", "MidNumLet"),
|
|
("midletter", "MidLetter"),
|
|
("midnum", "MidNum"),
|
|
("midnumlet", "MidNumLet"),
|
|
("ml", "MidLetter"),
|
|
("mn", "MidNum"),
|
|
("newline", "Newline"),
|
|
("nl", "Newline"),
|
|
("nu", "Numeric"),
|
|
("numeric", "Numeric"),
|
|
("other", "Other"),
|
|
("regionalindicator", "Regional_Indicator"),
|
|
("ri", "Regional_Indicator"),
|
|
("singlequote", "Single_Quote"),
|
|
("sq", "Single_Quote"),
|
|
("wsegspace", "WSegSpace"),
|
|
("xx", "Other"),
|
|
("zwj", "ZWJ"),
|
|
],
|
|
),
|
|
];
|