Spaces:
Runtime error
Runtime error
| | |
| ## European Latin extensions | |
| # Vowels | |
| ::s Ä ::t Ae | |
| ::s Ö ::t Oe | |
| ::s Ü ::t Ue | |
| ::s Å ::t Aa | |
| ::s Æ ::t Ae | |
| ::s Ø ::t oe | |
| ::s Π::t Oe | |
| ::s ä ::t ae | |
| ::s ö ::t oe | |
| ::s ü ::t ue | |
| ::s å ::t aa | |
| ::s æ ::t ae | |
| ::s ø ::t oe | |
| ::s œ ::t oe | |
| # Consonants | |
| ::s Ç ::t S | |
| ::s ç ::t s | |
| ::s Ç ::t Ch ::lcode tur | |
| ::s ç ::t ch ::lcode tur | |
| ::s Ş ::t Sh | |
| ::s ş ::t sh | |
| ::s Ș ::t Sh | |
| ::s ș ::t sh | |
| ::s ß ::t ss | |
| ::s Ț ::t Ts | |
| ::s ț ::t ts | |
| # Miscellaneous | |
| ::s ə ::t e | |
| # English | |
| ::s chr ::t chr ::t-alt kr ::example chromosome, synchronize | |
| ::s Chr ::t Chr ::t-alt Kr ::example Christmas, Chrysler | |
| ::s eight ::t eight ::t-alt eit ::example eight, weight | |
| ::s Eight ::t Eight ::t-alt Eit ::example Eighteen | |
| ::s ight ::t ight ::t-alt ait ::example Knight | |
| ::s gh ::t gh ::t-alt f, ph, "" ::example laugh, daughter | |
| ::s high ::t high ::t-alt hai ::example highlight | |
| ::s High ::t High ::t-alt Hai ::example High School | |
| ::s Isle ::t Isle ::t-alt Ail ::use-only-at-start-of-word ::use-only-at-end-of-word ::example Isle | |
| ::s Island ::t Island ::t-alt Ailand ::use-only-at-start-of-word ::use-only-at-end-of-word ::example Island | |
| ::s kn ::t kn ::t-alt n ::use-only-at-start-of-word ::example knowledge | |
| ::s Kn ::t Kn ::t-alt N ::use-only-at-start-of-word ::example Knight | |
| ::s Mc ::t Mc ::t-alt Mac ::use-only-at-start-of-word ::example McNulty | |
| ::s mc ::t mc ::t-alt mac ::use-only-at-start-of-word | |
| ::s oo ::t oo ::t-alt u ::lcode eng ::example Brooklyn; Goose Bay | |
| ::s ph ::t ph ::t-alt f ::example alpha | |
| ::s Ph ::t Ph ::t-alt F ::example Philip | |
| ::s Thom ::t Thom ::t-alt Tom ::use-only-at-start-of-word ::example Thomas, Thompson | |
| ::s tion ::t tion ::t-alt shen ::example | |
| ::s Sean ::t Sean ::t-alt Shawn ::use-only-at-start-of-word ::use-only-at-end-of-word | |
| ::s ssion ::t ssion ::t-alt shen ::example Sessions | |
| ::s St ::t St ::t-alt Saint ::use-only-at-start-of-word ::use-only-at-end-of-word | |
| ::s St. ::t St. ::t-alt Saint ::use-only-at-start-of-word ::use-only-at-end-of-word | |
| ::s Wr ::t Wr ::t-alt R ::example Wren | |
| ::s wr ::t wr ::t-alt r ::example Cartwright | |
| ::s x ::t x ::t-alt ks ::example Mexico | |
| ::s x ::t x ::t-alt gz ::example example, anxiety, exhaust, exit | |
| # French | |
| ::s â ::t a ::t-alt as ::example pâte/paste, pastry | |
| ::s ê ::t e ::t-alt es ::example fête/feast | |
| ::s î ::t i ::t-alt is ::example île/isle | |
| ::s ô ::t o ::t-alt os ::example côte/coast | |
| ::s û ::t u ::t-alt us ::example août/August | |
| ::s eaux ::t eaux ::t-alt o ::example Bordeaux | |
| ::s eau ::t eau ::t-alt o ::example Chateau | |
| ::s auld ::t auld ::t-alt o ::use-only-at-end-of-word ::example Renauld | |
| ::s ault ::t ault ::t-alt o ::use-only-at-end-of-word ::example Renault | |
| ::s oux ::t oux ::t-alt u | |
| ::s ois ::t ois ::t-alt oa ::use-only-at-end-of-word ::example Dubois | |
| # German | |
| ::s Sch ::t Sch ::t-alt Sh | |
| ::s sch ::t sch ::t-alt sh | |
| ::s stein ::t stein ::t-alt shtain | |
| ::s dt ::t dt ::t-alt tt ::use-only-at-end-of-word ::example Schmidt | |
| # Dutch | |
| ::s ij ::t ij ::t-alt ai | |
| ::s Ij ::t Ij ::t-alt Ai | |
| # Greek | |
| ::s Ι ::t I | |
| ::s ι ::t i | |
| ::s ί ::t i | |
| ::s ἶ ::t i | |
| ::s Υ ::t Y | |
| ::s υ ::t y | |
| ::s Ρ ::t R | |
| ::s ρ ::t r | |
| ::s Ντ ::t D | |
| ::s ντ ::t nd ::t-alt d | |
| # ::s ντζ ::t ntz | |
| ::s Μπ ::t B | |
| ::s μπ ::t mb ::t-alt b | |
| ::s γγ ::t ng | |
| ::s γκ ::t ng ::t-alt g | |
| ::s ει ::t ei ::t-alt i | |
| ::s ου ::t ou ::t-alt u | |
| ::s χ ::t ch ::t-alt kh | |
| # Cyrillic | |
| ::s Г ::t G ::t-alt H | |
| ::s г ::t g ::t-alt h | |
| ::s Е ::t E ::t-alt Ye | |
| ::s е ::t e ::t-alt ye | |
| ::s Ё ::t E ::t-alt Yo | |
| ::s ё ::t e ::t-alt yo | |
| ::s Х ::t Kh ::t-alt Ch, H ::comment Cyrillic capital ha | |
| ::s х ::t kh ::t-alt ch, h ::comment Cyrillic small ha | |
| ::s Щ ::t Shch ::t-alt Sh | |
| ::s щ ::t shch ::t-alt sh | |
| ::s Ъ ::t ::comment Cyrillic capital hard sign | |
| ::s ъ ::t ::comment Cyrillic small hard sign | |
| ::s Ы ::t Y ::comment Cyrillic capital yeru | |
| ::s ы ::t y ::comment Cyrillic small yeru | |
| ::s Ь ::t ::comment Cyrillic capital soft sign | |
| ::s ь ::t ::comment Cyrillic small soft sign | |
| ::s Ҥ ::t Ng ::comment Cyrillic capital ligature EN GHE | |
| ::s ҥ ::t ng ::comment Cyrillic small ligature EN GHE | |
| ::s Ә ::t e ::comment Cyrillic capital schwa | |
| ::s ә ::t e ::comment Cyrillic small schwa | |
| ::s Ӏ ::t ' ::comment Cyrillic palochka | |
| ::s Ҵ ::t TS ::comment Cyrillic capital ligature te tse, used in Abkhasian | |
| ::s ҵ ::t ts ::comment Cyrillic small ligature te tse, used in Abkhasian | |
| ::s Ӕ ::t AE ::comment Cyrillic capital ligature a ie | |
| ::s ӕ ::t ae ::comment Cyrillic small ligature a ie | |
| ::s Г ::t H ::lcode ukr ::comment Ukrainian capital letter he | |
| ::s г ::t h ::lcode ukr ::comment Ukrainian small letter he | |
| ::s Ґ ::t G ::lcode ukr ::comment Ukrainian capital letter ghe | |
| ::s ґ ::t g ::lcode ukr ::comment Ukrainian small letter ghe | |
| # Gothic | |
| ::s 𐌴 ::t e ::comment Gothic letter aihvus | |
| ::s 𐌹 ::t i ::comment Gothic letter eis | |
| ::s 𐍇 ::t x ::comment Gothic letter iggws | |
| # Georgian | |
| ::s ა ::t a ::comment Georgian letter an | |
| ::s ე ::t e ::comment Georgian letter en | |
| ::s ი ::t i ::comment Georgian letter in | |
| ::s ო ::t o ::comment Georgian letter on | |
| ::s უ ::t u ::comment Georgian letter un | |
| # Armenian | |
| ::s Ա ::t a ::comment Armenian capital letter ayb | |
| ::s ա ::t a ::comment Armenian small letter ayb | |
| ::s Ե ::t e ::comment Armenian capital letter ech | |
| ::s ե ::t e ::comment Armenian small letter ech | |
| ::s և ::t ev ::comment Armenian small ligature ech yiwn | |
| ::s Է ::t e ::comment Armenian capital letter eh | |
| ::s է ::t e ::comment Armenian small letter eh | |
| ::s Ի ::t i ::comment Armenian capital letter ini | |
| ::s ի ::t i ::comment Armenian small letter ini | |
| ::s Օ ::t o ::comment Armenian capital letter oh | |
| ::s օ ::t o ::comment Armenian small letter oh | |
| ## Japanese | |
| # Katakana | |
| ::s シ ::t shi | |
| ::s チ ::t chi | |
| ::s フ ::t fu | |
| ::s ジ ::t ji | |
| ::s ヂ ::t ji | |
| ::s ヅ ::t zu | |
| ::s シャ ::t sha | |
| ::s シュ ::t shu | |
| ::s ショ ::t sho | |
| ::s チャ ::t cha | |
| ::s チェ ::t che | |
| ::s チュ ::t chu | |
| ::s チョ ::t cho | |
| ::s ジャ ::t ja | |
| ::s ジュ ::t ju | |
| ::s ジョ ::t jo | |
| ::s ジェ ::t je | |
| ::s ヂャ ::t ja | |
| ::s ヂュ ::t ju | |
| ::s ヂョ ::t jo | |
| ::s フェ ::t fe | |
| ::s ヴェ ::t ve | |
| ::s フィ ::t fi | |
| ::s ウィ ::t wi | |
| ::s ヴィ ::t vi | |
| ::s ティ ::t ti | |
| ::s ディ ::t di | |
| ::s ッ ::t (__SOKUON__) ::comment katakana double following consonant | |
| ::s ー ::t (__CHOONPU__) ::comment katakana prolonged sound mark | |
| # Hiragana | |
| ::s し ::t shi | |
| ::s ち ::t chi | |
| ::s つ ::t tsu | |
| ::s ふ ::t fu | |
| ::s を ::t o | |
| ::s じ ::t ji | |
| ::s ぢ ::t ji | |
| ::s づ ::t zu | |
| ::s しゃ ::t sha | |
| ::s しゅ ::t shu | |
| ::s しょ ::t sho | |
| ::s ちゃ ::t cha | |
| ::s ちゅ ::t chu | |
| ::s ちょ ::t cho | |
| ::s じゃ ::t ja | |
| ::s じゅ ::t ju | |
| ::s じょ ::t jo | |
| ::s ぢゃ ::t ja | |
| ::s ぢゅ ::t ju | |
| ::s ぢょ ::t jo | |
| ::s っ ::t (__SOKUON__) ::comment hiragana double following consonant | |
| ::s 々 ::t ² ::comment ideographic iteration mark ::annotation repetition-sign | |
| ::s フ ::t fu ::t-alt f | |
| ::s キ ::t ki ::t-alt k | |
| ::s ク ::t ku ::t-alt k | |
| ::s ラ ::t ra ::t-alt la | |
| ::s リ ::t ri ::t-alt li | |
| ::s ル ::t ru ::t-alt lu, l, r | |
| ::s レ ::t re ::t-alt le | |
| ::s ロ ::t ro ::t-alt lo | |
| ::s ム ::t mu ::t-alt m ::example キム = Kim | |
| ::s シ ::t shi ::t-alt si ::example メキシコ = meksiko (Mexico) | |
| ::s ス ::t su ::t-alt s | |
| ::s ト ::t to ::t-alt t | |
| ::s ツ ::t tsu ::t-alt tu, ts ::example シュルツ = Schultz | |
| # Chinese | |
| ::s 邦 ::t bang ::t-alt bon, bum, bun, pon | |
| ::s 鲍 ::t bao ::t-alt bow | |
| ::s 堡 ::t bao ::t-alt berg, burg, bourg, burgh | |
| ::s 贝 ::t bei ::t-alt ber | |
| ::s 本 ::t ben ::t-alt bern, bon, bourn, burn | |
| ::s 彼得 ::t bide ::t-alt peter, pet | |
| ::s 伯 ::t bo ::t-alt ber | |
| ::s 波 ::t bo ::t-alt po | |
| ::s 布 ::t bu ::t-alt b | |
| ::s 策 ::t ce ::t-alt tze, tzer | |
| ::s 曾 ::t ceng ::t-alt tzen, zen | |
| ::s 彻 ::t che ::t-alt tche | |
| ::s 茨 ::t ci ::t-alt ts, tz, z | |
| ::s 兹 ::t ci ::t-alt ds, dz, tz, z, zi | |
| ::s 蒂 ::t di ::t-alt ti, tti | |
| ::s 丁 ::t ding ::t-alt din, tin | |
| ::s 顿 ::t dun ::t-alt ton | |
| ::s 多 ::t duo ::t-alt do, dor, to | |
| ::s 尔 ::t er ::t-alt l, le, ll, r | |
| ::s 弗 ::t fu ::t-alt f, fer, pher, v, ver, vir | |
| ::s 夫 ::t fu ::t-alt f, v, v | |
| ::s 福 ::t fu ::t-alt faw, for, ford | |
| ::s 哥 ::t ge ::t-alt go, co | |
| ::s 戈 ::t ge ::t-alt go | |
| ::s 各 ::t ge ::t-alt go, co | |
| ::s 赫 ::t he ::t-alt ch, che, cher, ge | |
| ::s 华 ::t hua ::t-alt ver, wa, war, wer ::example Washington | |
| ::s 怀 ::t huai ::t-alt whi, wi, wy | |
| ::s 惠 ::t hui ::t-alt wha, whea | |
| ::s 基 ::t ji ::t-alt ki, chi | |
| ::s 吉 ::t ji ::t-alt gi, gui | |
| ::s 加 ::t jia ::t-alt ca, ga, ka ::example Canada | |
| ::s 杰 ::t jie ::t-alt ger | |
| ::s 金 ::t jin ::t-alt kin, gin | |
| ::s 斤 ::t jin ::t-alt zin | |
| ::s 康 ::t kang ::t-alt con, corn | |
| ::s 考 ::t kao ::t-alt cow, cour | |
| ::s 克 ::t ke ::t-alt k, che, cher | |
| ::s 科 ::t ke ::t-alt ko | |
| ::s 拉 ::t la ::t-alt ra ::example Tirana | |
| ::s 朗 ::t lang ::t-alt lon, ron | |
| ::s 赖 ::t lai ::t-alt ri | |
| ::s 劳 ::t lao ::t-alt low | |
| ::s 勒 ::t lei ::t-alt ler | |
| ::s 伦 ::t lun ::t-alt lon, ran, ron | |
| ::s 里 ::t li ::t-alt ri | |
| ::s 利 ::t li ::t-alt ri ::example Ferrari | |
| ::s 隆 ::t long ::t-alt lon, lum, lund | |
| ::s 罗 ::t luo ::t-alt l, lo, lu, ro, row, ru | |
| ::s 洛 ::t luo ::t-alt lo, low, ro | |
| ::s 默 ::t mo ::t-alt mer | |
| ::s 纳 ::t na ::t-alt ne, ner | |
| ::s 珀 ::t po ::t-alt per | |
| ::s 奇 ::t qi ::t-alt chi, dge, ge, tch | |
| ::s 齐 ::t qi ::t-alt tsi, zi | |
| ::s 乔 ::t qiao ::t-alt jo | |
| ::s 青 ::t qing ::t-alt tsing | |
| ::s 琼 ::t qiong ::t-alt jon, jum, jun | |
| ::s 瑟 ::t se ::t-alt the | |
| ::s 什 ::t shen ::t-alt sh | |
| ::s 圣 ::t sheng ::t-alt san, sao, saint | |
| ::s 斯 ::t si ::t-alt s, rth, th ::example Alaska | |
| ::s 索 ::t suo ::t-alt tho | |
| ::s 特 ::t te ::t-alt t | |
| ::s 翁 ::t weng ::t-alt on | |
| ::s 沃 ::t wo ::t-alt ver, vo, war, wer | |
| ::s 乌 ::t wu ::t-alt ou, u | |
| ::s 希 ::t xi ::t-alt chi, hi, shi | |
| ::s 西 ::t xi ::t-alt s, si | |
| ::s 锡 ::t xi ::t-alt ci, si, thi, zi | |
| ::s 夏 ::t xia ::t-alt ha, cha, cia, sha, tia | |
| ::s 香 ::t xiang ::t-alt chan, cham | |
| ::s 歇 ::t xie ::t-alt she | |
| ::s 谢 ::t xie ::t-alt che, she | |
| ::s 辛 ::t xin ::t-alt cin, sen, sin, sing, sun, zen | |
| ::s 欣 ::t xin ::t-alt hin, shin | |
| ::s 休 ::t xiu ::t-alt hu, hue | |
| ::s 修 ::t xiu ::t-alt ciu, siu, thew, tiu | |
| ::s 许 ::t xu ::t-alt hue, schue | |
| ::s 逊 ::t xun ::t-alt son | |
| ::s 耶 ::t ye ::t-alt yer, ier | |
| ::s 泽 ::t ze ::t-alt ser | |
| ::s 扎 ::t zha ::t-alt za | |
| ::s 詹 ::t zhan ::t-alt ja, jam, jan, jen, jon | |
| ::s 治 ::t zhi ::t-alt ge ::example George | |
| ## Numbers | |
| # Chinese and Japanese numbers | |
| ::s 零 ::num 0 | |
| ::s 〇 ::num 0 | |
| ::s 一 ::num 1 | |
| ::s 二 ::num 2 | |
| ::s 三 ::num 3 | |
| ::s 四 ::num 4 | |
| ::s 五 ::num 5 | |
| ::s 六 ::num 6 | |
| ::s 七 ::num 7 | |
| ::s 八 ::num 8 | |
| ::s 九 ::num 9 | |
| ::s 十 ::num 10 | |
| ::s 百 ::num 100 | |
| ::s 千 ::num 1000 | |
| ::s 万 ::num 10000 | |
| ::s 萬 ::num 10000 | |
| ::s 亿 ::num 100000000 | |
| ::s 億 ::num 100000000 | |
| ::s 兆 ::num 1000000000000 | |
| ::s 京 ::num 10000000000000000 | |
| ::s 北京 ::t beijing | |
| ::s 京都 ::t jingdou | |
| ::s 东京 ::t dongjing | |
| ::s 京胡 ::t jinghu | |
| ::s 南京 ::t nangjing | |
| ::s 普京 ::t pujing ::comment Putin | |
| ::s 東京 ::t dongjing ::comment Tokyo | |
| ::s 京兆 ::t jingzhao | |
| ::s ㎢ ::t km² | |
| ::s ㎥ ::t m³ | |
| ::s ㎝ ::t cm | |
| ## Indian | |
| # see mostly under UnicodeDataOverwrite.txt | |
| # Malayalam | |
| ::s ൗ ::t au ::comment MALAYALAM AU LENGTH MARK | |
| # Tamil | |
| ::s ட ::t d ::comment most commonly d, but t when word-initial or in a doubled consonant | |
| ::s ஃப ::t f ::comment h+p=f | |
| ::s ஃஜ ::t z ::comment h+j=z | |
| # Myanmar/Burmese | |
| # ::s ့ ::t ::comment dot below, denotes creaky tone | |
| # ::s း ::t ::comment visarga, denotes high tone | |
| ::s ၌ ::t -nai ::comment locative | |
| ::s ၍ ::t -jwe ::comment completed | |
| ::s ၎ ::t legau ::comment aforementioned | |
| ::s ၏ ::t -i ::comment genetive | |
| # Lao | |
| ::s ັ ::t a ::comment vowel sign mai kan | |
| ::s ົ ::t o ::comment vowel sign mai kon | |
| ::s ູ ::t uu ::comment vowel sign uu | |
| ::s ຽ ::t y ::comment semivowel sign nyo | |
| ::s ຼ ::t l ::comment semivowel sign lo | |
| ::s ລ ::t l ::comment lo loot | |
| ::s ຣ ::t l ::comment lo ling | |
| ::s ໝ ::t m ::comment ho mo | |
| ::s ໜ ::n ::comment ho no | |
| ::s ຢ ::t y ::comment yo | |
| ::s ໍ ::t oo ::comment niggahita (possibly also nasal -m in final position) | |
| ::s ໆ ::t ² ::comment Lao ko la ::annotation repetition-sign | |
| ::s ຯ ::t ... ::comment Lao ellipsis | |
| # Thai | |
| ::s ออ ::t o | |
| ::s อั ::t a | |
| ::s อิ ::t i | |
| ::s ๆ ::t ² ::comment Thai character maiyamok ::annotation repetition-sign | |
| # Khmer | |
| ::s ័ ::t "" ::comment Khmer samyok sannya: indicates deviation from the general rules of pronunciation | |
| ::s ៏ ::t "" ::comment Khmer sign ahsda: denotes stressed intonation in some single-consonant words | |
| ::s ៍ ::t "" ::comment Khmer sign toandakhiat: indicates that the base character is not pronounced | |
| ::s ៌ ::t "" ::comment Khmer sign robat: a diacritic historically corresponding to the repha form of ra in Devanagari | |
| ::s ប៉ ::t pa ::comment Khmer ba + musĕkâtônd -> pa | |
| ::s ៗ ::t ² ::comment Khmer sign lek too ::annotation repetition-sign | |
| ## Semitic languages | |
| # Arabic | |
| ::s و ::t w ::comment Arabic letter waw ::t-alt o, u ::lcode ara | |
| ::s ء ::t ' ::comment hamza | |
| ::s ٔ ::t ' ::comment hamza above | |
| ::s ٕ ::t ' ::comment hamza below | |
| ::s ع ::t ' ::comment ain | |
| ::s آ ::t a ::comment alef madda | |
| ::s ٓا ::t a ::comment Arabic maddah above plus alef (presumably an ill-formed version of آ; found 1 instance in Urdu text) | |
| ::s إ ::t i ::comment alef with hamza below | |
| ::s ٱ ::t a ::comment alef wasla ::comment typically indicates liaison with preceding word | |
| ::s ة ::t a ::comment teh marbuta | |
| ::s ۃ ::t a ::comment teh marbuta goal ::comment Used in Punjabi, Sindhi. Different from plain 'teh marbuta'? | |
| ::s ي ::t y ::comment Arabic yeh | |
| ::s ى ::t a ::comment alef maksura | |
| ::s ﻯ ::t a ::comment alef maksura isolated form | |
| ::s ﻰ ::t a ::comment alef maksura final form | |
| ::s ﯨ ::t a ::comment Uighur Kazach Kirghiz alef maksura initial form | |
| ::s ﯩ ::t a ::comment Uighur Kazach Kirghiz alef maksura medial form | |
| ::s ٰ ::t a ::comment Arabic letter superscript alef | |
| ::s ـ ::t ::comment tatweel (filler) | |
| ::s َ ::t a ::comment fatha ("-a") | |
| ::s ُ ::t u ::comment damma ("-u") | |
| ::s ِ ::t i ::comment kasra ("-i") | |
| ::s ْ ::t ::comment sukun (no vowel) | |
| ::s ۡ ::t ::comment small high dotless head of khah; like sukun (no vowel); used in Kashmiri, Assamese | |
| ::s ً ::t ::comment fathatan ("-an") | |
| ::s اً ::t an ::comment alef + fathatan | |
| ::s ٌ ::t ::comment dammatan ("-un") | |
| ::s ٍ ::t ::comment kasratan ("-in") | |
| ::s ّ ::t ::comment shadda (consonant doubler) | |
| ::s ڃ ::t ny ::comment Arabic letter nyeh U+0683 (used in Sindhi (snd)) | |
| ::s ڄ ::t dy ::comment Arabic letter dyeh U+0684 (used in Sindhi (snd)) | |
| ::s ۾ ::t men ::comment Sindhi postposition men | |
| ::s ؑ ::t alayhe wasallam ::comment "upon him be peace" | |
| ::s ﷴ ::t mohammad ::comment "Mohammad" | |
| ::s ﷸ ::t wasallam ::comment "and peace" | |
| ::s ﷺ ::t sallallahou alayhe wasallam ::comment "prayer of God be upon him and his family and peace" | |
| # Farsi | |
| ::s ی ::t i ::t-alt y ::comment Contributed by Nima | |
| ::s ای ::t i ::t-alt ai ::use-only-at-start-of-word ::comment Contributed by Nima | |
| ::s هٔ ::t eye ::use-only-at-end-of-word ::lcode fas ::comment Contributed by Nima | |
| ::s و ::t v ::t-alt o, u ::lcode fas ::comment Arabic letter waw | |
| ::s ض ::t z ::t-alt d ::lcode fas ::comment Contributed by Marjan | |
| ::s ث ::t s ::t-alt th ::lcode fas ::comment Contributed by Marjan | |
| ::s ذ ::t z ::t-alt th ::lcode fas ::comment Contributed by Nima | |
| ::s ع ::t a ::t-alt ' ::lcode fas ::comment Contributed by Nima | |
| ::s عا ::t a ::lcode fas ::comment Contributed by Nima | |
| ::s عی ::t i ::t-alt iy ::lcode fas ::comment Contributed by Nima | |
| ::s عو ::t u ::t-alt o, av ::lcode fas ::comment Contributed by Nima | |
| ::s چ ::t ch ::t-alt tch, tsh ::lcode fas ::comment Contributed by Nima | |
| ::s ه ::t e ::t-alt h ::use-only-at-end-of-word ::lcode fas ::comment Contributed by Nima | |
| ::s ::t "" ::t-alt " " ::lcode fas ::comment source is character "zero-width non-joiner" (U+200C); Contributed by Nima | |
| ::s غ ::t gh ::t-alt g ::lcode fas | |
| ::s آئی ::t ai ::t-alt ae ::lcode fas | |
| ::s ائی ::t ai ::t-alt ae ::lcode fas | |
| ::s آئو ::t au ::t-alt ao ::lcode fas | |
| ::s ائو ::t au ::t-alt ao ::lcode fas | |
| # Kashmiri (so far: educated guesses) | |
| ::s ٖ ::t a ::comment Arabic subscript alef U+0656 | |
| ::s ٗ ::t u ::comment Arabic inverted damma U+0657 | |
| ::s ۚ ::t j ::comment Arabic small high jeem U+06DA | |
| ::s ۪ ::t ::comment Arabic emtpy centre low stop U+06EA | |
| ::s ۬ ::t ::comment Arabic rounded high stop with filled center U+06EC | |
| # Pashto | |
| ::s ٙ ::t e | |
| # Hebrew | |
| ::s ב ::t v ::comment Hebrew letter bet ::t-alt b | |
| ::s כ ::t k ::comment Hebrew letter kaf ::t-alt kh | |
| ::s ך ::t k ::comment Hebrew letter kaf ::t-alt kh | |
| ::s פ ::t f ::comment Hebrew letter pe ::t-alt p | |
| ::s ש ::t sh ::comment Hebrew letter shin ::t-alt s | |
| ::s ו ::t v ::comment Hebrew letter vav ::t-alt o, u | |
| ::s ח ::t ch ::comment Hebrew letter het ::t-alt h ::use-alt-in-pointed | |
| ::s ק ::t q ::t-alt k ::use-alt-in-pointed | |
| ::s וֹ ::t o | |
| ::s וּ ::t u | |
| ::s קְוָ ::t qva ::t-alt kva ::use-alt-in-pointed | |
| ::s י ::t y | |
| ::s יּ ::t y | |
| ::s יָּ ::t ya | |
| ::s ע ::t ' | |
| ::s ִי ::t i ::t-alt iy ::use-alt-in-pointed | |
| ::s ֵי ::t e | |
| ::s ִיּ ::t iy | |
| ::s ִיָּ ::t iya | |
| ::s ױ ::t oy | |
| ::s א ::t a ::t-alt ' | |
| ::s אָ ::t a | |
| ::s ֹא ::t o | |
| ::s אַ ::t 'a | |
| ::s אֲ ::t 'a | |
| ::s אֶ ::t e | |
| ::s אֱ ::t e | |
| ::s פ ::t f | |
| ::s פּ ::t p | |
| ::s פַּ ::t pa | |
| ::s פְּ ::t pe ::t-alt p ::use-alt-in-pointed | |
| ::s שׁ ::t sh | |
| ::s שָׁ ::t sha | |
| ::s שָּׁ ::t sha ::comment ? | |
| ::s שְׁ ::t she ::t-alt sh ::use-alt-in-pointed | |
| ::s שֶׁ ::t she | |
| ::s שִׁ ::t shi | |
| ::s שֻׁ ::t shu | |
| ::s שׂ ::t s | |
| ::s שָׂ ::t sa | |
| ::s שְׂ ::t s ::t-alt se ::use-alt-in-pointed | |
| ::s כּ ::t k | |
| ::s כֶּ ::t ke | |
| ::s כֹּ ::t ko | |
| ::s בּ ::t b | |
| ::s בַּ ::t ba | |
| ::s בָּ ::t ba | |
| ::s בְּ ::t be ::t-alt b ::use-alt-in-pointed | |
| ::s בֶּ ::t be | |
| ::s תּ ::t t | |
| ::s תַּ ::t ta | |
| ::s תֵּ ::t te | |
| ::s תִּ ::t ti | |
| ::s דָּ ::t da | |
| ::s דְּ ::t de ::t-alt d ::use-alt-in-pointed | |
| ::s גּ ::t g | |
| ::s לֵּ ::t le | |
| ::s ד׳ ::t dh | |
| ::s ג׳ ::t j | |
| ::s ת׳ ::t th | |
| ::s ז׳ ::t zh | |
| ::s חַ ::t ach ::comment furtive patah ::use-only-at-end-of-word | |
| ::s עַ ::t a' ::comment furtive patah ::use-only-at-end-of-word | |
| ::s הַּ ::t ah ::comment furtive patah ::use-only-at-end-of-word | |
| ::s ַ ::t a ::comment Hebrew point patah | |
| ::s ֲ ::t a ::comment Hebrew point hataf patah (hataf = reduced) | |
| ::s ֳ ::t o ::comment Hebrew point hataf qamats | |
| ::s ָ ::t a ::comment Hebrew point qamats ::t-alt o ::use-alt-in-pointed | |
| ::s ֶ ::t e ::comment Hebrew point segol | |
| ::s ֱ ::t e ::comment Hebrew point hataf segol (hataf = reduced) | |
| ::s ְ ::t e ::comment Hebrew point sheva ::t-alt "" ::use-alt-in-pointed | |
| ::s ֵ ::t e ::comment Hebrew point tsere | |
| ::s ִ ::t i ::comment Hebrew point hiriq | |
| ::s ֹ ::t o ::comment Hebrew point holam | |
| ::s ֻ ::t u ::comment Hebrew point qubuts | |
| # ::s ּ ::t "" ::comment Hebrew point dagesh or mapiq | |
| # Yiddish | |
| ::s א ::t a ::lcode yid ::comment called "silent" alef | |
| ::s אי ::t y ::lcode yid | |
| ::s איי ::t ey ::lcode yid | |
| ::s או ::t u ::lcode yid | |
| ::s אוי ::t oy ::lcode yid | |
| ::s אַ ::t a ::lcode yid | |
| ::s אָ ::t o ::lcode yid | |
| ::s ב ::t b ::lcode yid | |
| ::s בֿ ::t v ::lcode yid | |
| ::s דזש ::t dzh ::lcode yid | |
| ::s ו ::t u ::lcode yid | |
| ::s וּ ::t u ::lcode yid | |
| ::s וֹ ::t o ::lcode yid | |
| ::s װ ::t v ::lcode yid | |
| ::s ווא ::t wa ::lcode yid | |
| ::s וואַ ::t wa ::lcode yid | |
| ::s ווע ::t we ::lcode yid | |
| ::s ווי ::t wi ::lcode yid | |
| ::s וואוי ::t wo ::lcode yid | |
| ::s וי ::t oy ::lcode yid | |
| ::s זש ::t zh ::lcode yid | |
| ::s ח ::t ch ::lcode yid | |
| ::s טש ::t tsh ::lcode yid | |
| ::s יִ::t i ::lcode yid | |
| ::s יי ::t ey ::lcode yid ::comment maybe "yi" at beginning of word | |
| ::s ײַ ::t ay ::lcode yid | |
| ::s כּ ::t k ::lcode yid | |
| ::s כ ::t ch ::lcode yid | |
| ::s ך ::t ch ::lcode yid | |
| ::s ע ::t e ::lcode yid | |
| ::s פּ ::t p ::lcode yid | |
| ::s פֿ ::t f ::lcode yid | |
| ::s ף ::t f ::lcode yid ::comment sometimes p | |
| ::s ק ::t k ::lcode yid | |
| ::s ת ::t s ::lcode yid | |
| # Syriac/Aramaic (should be vetted by expert) | |
| ::s ܰ ::t a ::comment Syriac pthaha above | |
| ::s ܲ ::t a ::comment Syriac pthaha dotted | |
| ::s ܳ ::t aa ::comment Syriac zqapha above | |
| ::s ܴ ::t aa ::comment Syriac zqapha below | |
| ::s ܵ ::t aa ::comment Syriac zqapha dotted | |
| ::s ܶ ::t e ::comment Syriac rbasa above | |
| ::s ܷ ::t e ::comment Syriac rbasa below | |
| ::s ܿ ::t o ::comment Syriac rwaha | |
| ::s ܸ ::t e ::comment Syriac dotted zlama horizontal | |
| ::s ܹ ::t e ::comment Syriac dotted zlama angular | |
| ::s ܺ ::t i ::comment Syriac hbasa above | |
| ::s ܝܺ ::t i ::comment Syriac yudh + hbasa above | |
| ::s ܼ ::t u ::comment Syriac hbasa-esasa dotted | |
| ::s ܽ ::t o ::comment Syriac esasa above | |
| ::s ܾ ::t u ::comment Syriac esasa below | |
| ::s ݇ ::t "" ::comment Syriac oblique line above; indication of a silent letter | |
| ::s ܖ ::t d ::comment Syriac letter dotless dalath rish; ambiguous form for undifferentiated early dalath/rish | |
| ::s ܜ ::t t ::comment Syriac letter teth garshuni; used in Garshuni documents | |
| ::s ܒ݂ ::t v ::comment Syriac beth + rukkakha | |
| ::s ܒ̥ ::t v ::comment Syriac beth + ring-below | |
| ::s ܓ݂ ::t g ::comment Syriac gammal + rukkakha [IPA: ɣ] | |
| ::s ܓ̥ ::t g ::comment Syriac gammal + ring-below [IPA: ɣ] | |
| ::s ܕ݂ ::t d ::comment Syriac dalath + rukkakha [IPA: ð] | |
| ::s ܕ̥ ::t d ::comment Syriac dalath + ring-below [IPA: ð] | |
| ::s ܟ݂ ::t kh ::comment Syriac kaph + rukkakha [IPA: x] | |
| ::s ܟ̥ ::t kh ::comment Syriac kaph + ring-below [IPA: x] | |
| ::s ܦ݂ ::t f ::comment Syriac pe + rukkakha | |
| ::s ܦ̥ ::t f ::comment Syriac pe + ring-below | |
| ::s ܦ݁ ::t p ::comment Syriac pe + qushshaya | |
| ::s ܬ݂ ::t th ::comment Syriac taw + rukkakha [IPA: θ] | |
| ::s ܬ̥ ::t th ::comment Syriac taw + ring-below [IPA: θ] | |
| ::s ܄ ::t : ::comment Syriac sublinear colon; used at the end of verses of supplicationscolon skewed left | |
| ::s ܆ ::t , ::comment Syriac colon skewed left; marks a dependent clause | |
| ::s ܇ ::t , ::comment Syriac colon skewed right; marks the end of a subdivision of the apodosis, or latter part of a Biblical verse | |
| # Uzbek | |
| ::s ʻ ::t ' ::comment modifies pronunciation of preceding "o" and "g" | |
| ::s ʼ ::t ' ::comment glottal stop (tutuq belgisi) | |
| # Uyghur | |
| ::s ئا ::t a ::lcode uig | |
| ::s ە ::t e ::lcode uig | |
| ::s ئې ::t e ::lcode uig ::latinplus ë | |
| ::s ې ::t e ::lcode uig ::latinplus ë | |
| ::s ئە ::t e ::lcode uig | |
| ::s يە ::t e ::lcode uig | |
| ::s ئى ::t i ::lcode uig | |
| ::s ى ::t i ::lcode uig | |
| ::s ئو ::t o ::lcode uig | |
| ::s و ::t o ::lcode uig | |
| ::s ئۇ ::t u ::lcode uig | |
| ::s ۇ ::t u ::lcode uig | |
| ::s چ ::t ch ::t-alt q ::lcode uig | |
| ::s خ ::t x ::lcode uig | |
| ::s ژ ::t zh ::lcode uig | |
| ::s ئۆ ::t oe ::t-alt o ::lcode uig ::latinplus ö | |
| ::s ۆ ::t oe ::t-alt o ::lcode uig ::latinplus ö | |
| ::s ئۈ ::t ue ::t-alt u ::lcode uig ::latinplus ü | |
| ::s ۈ ::t ue ::t-alt u ::lcode uig ::latinplus ü | |
| ::s ۋ ::t w ::lcode uig | |
| # Maldivian | |
| ::s ް ::t ::comment thaana sukun | |
| ::s ަ ::t a ::comment thaana abafili | |
| ::s ާ ::t aa ::comment thaana aabaafili | |
| ::s ި ::t i ::comment thaana ibifili | |
| ::s ީ ::t ee ::comment thaana eebeefili | |
| ::s ު ::t u ::comment thaana ubufili | |
| ::s ޫ ::t oo ::comment thaana ooboofili | |
| ::s ެ ::t e ::comment thaana ebefili | |
| ::s ޭ ::t ey ::comment thaana eybeyfili | |
| ::s ޮ ::t o ::comment thaana obofili | |
| ::s ޯ ::t oa ::comment thaana oaboafili | |
| # Canadian syllabics (Inuktitut) | |
| ::s ᑊ ::t p ::comment syllable final | |
| ::s ᐟ ::t t ::comment syllable final | |
| ::s ᐠ ::t k ::comment syllable final | |
| ::s ᐨ ::t c ::comment syllable final | |
| ::s ᒼ ::t m ::comment syllable final | |
| ::s ᐣ ::t n ::comment syllable final | |
| ::s ᐢ ::t s ::comment syllable final | |
| ::s ᐧ ::t y ::comment syllable final | |
| ::s ᐤ ::t w ::comment syllable final | |
| ::s ᐦ ::t h ::comment syllable final | |
| ::s ᕽ ::t hk ::comment syllable final | |
| ::s ᓫ ::t l ::comment syllable final | |
| ::s ᕑ ::t r ::comment syllable final | |
| ## Punctuation | |
| # delete | |
| ::s ¿ ::t "" ::comment inverted question mark | |
| ::s ¡ ::t "" ::comment inverted exclamation mark | |
| # preserve | |
| ::s ′ ::t ′ | |
| # Cyrillic | |
| ::s ⁙ ::t . ::comment five dot punctuation | |
| # Amharic/Ethiopian | |
| ::s ። ::t . | |
| ::s ፣ ::t , | |
| ::s ፤ ::t ; | |
| ::s ፥ ::t : | |
| ::s ፡ ::t " " ::comment Ethiopic wordspace | |
| ::s ፦ ::t : ::comment Ethiopic preface colon | |
| ::s ቸ ::t cha ::comment Ethiopic syllable ca | |
| ::s ቹ ::t chu ::comment Ethiopic syllable cu | |
| ::s ቺ ::t chi ::comment Ethiopic syllable ci | |
| ::s ቻ ::t chaa ::comment Ethiopic syllable caa | |
| ::s ቼ ::t chee ::comment Ethiopic syllable cee | |
| ::s ች ::t che ::comment Ethiopic syllable ce | |
| ::s ቾ ::t cho ::comment Ethiopic syllable co | |
| ::s ሠ ::t sa ::comment Ethiopic syllable sza | |
| ::s ሡ ::t su ::comment Ethiopic syllable szu | |
| ::s ሢ ::t si ::comment Ethiopic syllable szi | |
| ::s ሣ ::t saa ::comment Ethiopic syllable szaa | |
| ::s ሤ ::t see::comment Ethiopic syllable szee | |
| ::s ሥ ::t se ::comment Ethiopic syllable sze | |
| ::s ሦ ::t so ::comment Ethiopic syllable szo | |
| ::s ጠ ::t te ::comment Ethiopic syllable the with ejective 't' | |
| ::s ጡ ::t tu ::comment Ethiopic syllable thu with ejective 't' | |
| ::s ጢ ::t ti ::comment Ethiopic syllable thi with ejective 't' | |
| ::s ጣ ::t taa ::comment Ethiopic syllable thaa with ejective 't' | |
| ::s ጤ ::t tee ::comment Ethiopic syllable thee with ejective 't' | |
| ::s ጥ ::t te ::comment Ethiopic syllable the with ejective 't' | |
| ::s ጦ ::t to ::comment Ethiopic syllable tho with ejective 't' | |
| # Devanagari (Hindi etc.) | |
| ::s । ::t . ::comment danda | |
| ::s ॥ ::t . ::comment double danda | |
| ::s ৷ ::t . ::comment Bengali currency numerator four; used as danda | |
| ::s ॰ ::t . ::comment Devanagari abbreviation sign | |
| # Oriya/Odia (India) | |
| ::s ::t . ::comment danda (deprecated, should use Devanagari danda ।) | |
| ::s ::t . ::comment double danda (deprecated, should use Devanagari double danda ॥) | |
| # Tibetan | |
| ::s ། ::t , | |
| ::s །: ::t : | |
| ::s ༏ ::t ; | |
| ::s ༎ ::t . | |
| ::s ༑ ::t , ::comment Tibetan mark run chen spungs shad | |
| ::s ༼ ::t ( ::comment Tibetan open roof punctuation | |
| ::s ༽ ::t ) ::comment Tibetan close roof punctuation | |
| ::s ༈ ::t "" ::comment Tibetan mark srbul shad | |
| ::s 【 ::t [ ::comment left black lenticular bracket | |
| ::s 】 ::t ] ::comment right black lenticular bracket | |
| ::s ༄ ::t "" ::comment Tibetan head mark | |
| ::s ༄༅ ::t "" ::comment Tibetan head mark | |
| ::s ༆ ::t "" ::comment Tibetan head mark | |
| # Myanmar/Burmese | |
| ::s ၊ ::t , | |
| ::s ။ ::t . | |
| Khmer | |
| ::s ៖ ::t ; ::comment Khmer sign camnuc pii kuuh | |
| ::s ។ ::t . ::comment Khmer sign khan | |
| # Arabic | |
| ::s ، ::t , | |
| ::s ؛ ::t ; | |
| ::s ٬ ::t , | |
| ::s ۔ ::t . | |
| ::s ؟ ::t ? | |
| ::s ٪ ::t % | |
| ::s ٫ ::t , ::comment Arabic decimal separator | |
| ::s ۽ ::t & ::comment Arabic sign Sindhi ampersand | |
| # Aramaic | |
| ::s ܀ ::t . | |
| ::s ܂ ::t . | |
| # Hebrew | |
| ::s ־ ::t - ::comment maqaf | |
| # Armenian | |
| ::s ։ ::t . | |
| ::s ՝ ::t , ::comment Armenian comma | |
| # Chinese | |
| ::s ， ::t ", " | |
| ::s 、 ::t ", " | |
| ::s 。 ::t ". " | |
| ::s ！ ::t "! " | |
| ::s ？ ::t "? " | |
| ::s 「 ::t ' "' | |
| ::s 」 ::t '" ' | |
| ::s 《 ::t ' "' | |
| ::s 》 ::t '" ' | |
| ::s （ ::t " (" | |
| ::s ） ::t ") " | |
| ::s ； ::t ; | |
| ::s ： ::t ": " | |
| ::s ︰ ::t ": " | |
| ::s － ::t - | |
| ::s ／ ::t / | |
| ::s ＝ ::t = | |
| ::s ～ ::t ~ | |
| ::s ＆ ::t & | |
| ::s ＜ ::t < | |
| ::s ＞ ::t > | |
| ::s ％ ::t % | |
| ::s ::t " " ::comment ideographic space | |
| # Japanese | |
| ::s 『 ::t ' "' | |
| ::s 』 ::t '" ' | |
| ::s ・ ::t " " ::comment Katakana middle dot; separates name elements such as first and last name | |
| # Symbols | |
| ::s ∞ ::t ∞ ::comment infinity | |
| ::s ::t ::comment soft hyphen; used to indicate preferred line breaks; remove | |
| ::s ֊ ::t - ::comment Armenian hyphen; map to regular hyphen-minus | |
| ::s ᐩ ::t + ::comment Canadian syllabics final plus; map to regular plus | |
| ::s ﹐ ::t , ::comment small comma; map to regular comma | |
| ::s ˚ ::t ° ::comment ring above; map to degree sign | |
| ::s ⇒ ::t ⇒ ::comment rightwards double arrow | |
| ::s † ::t † ::comment dagger | |
| ::s • ::t • ::comment bullet | |
| ::s ℃ ::t °C ::comment degree Celsius; split into 2 characters | |
| ::s ℉ ::t °F ::comment degree Fahrenheit; split into 2 characters | |
| ::s ― ::t ― ::comment horizontal bar | |
| ::s ˇ ::t ˇ ::comment caron (sometimes apparently used for "Arabic vowel sign small v above" U+065A, e.g. in Gilaki language (glk)) | |
| ::s ″ ::t ″ ::comment double prime | |
| ::s ﴾ ::t ( ::comment ornate left parenthesis | |
| ::s ﴿ ::t ) ::comment ornate right parenthesis | |
| ::s 〔 ::t [ ::comment left tortoise shell bracket | |
| ::s 〕 ::t ] ::comment right tortoise shell bracket | |
| ::s ﹝ ::t ( ::comment small left tortoise shell bracket | |
| ::s ﹞ ::t ) ::comment small left tortoise shell bracket | |
| ::s ♄ ::t ♄ ::comment Saturn | |
| ::s ♆ ::t ♆ ::comment Neptune | |
| ::s ♋ ::t ♋ ::comment Cancer | |