# # ISO 639-2 (T) # aar = aa abk = ab afr = af aka = ak sqi = sq amh = am ara = ar arg = an hye = hy asm = as ava = av ave = ae aym = ay aze = az bak = ba bam = bm eus = eu bel = be ben = bn bih = bh bis = bi bod = bo bos = bs bre = br bul = bg mya = my cat = ca ces = cs cha = ch che = ce zho = zh chu = cu chv = cv cor = kw cos = co cre = cr cym = cy dan = da deu = de div = dv nld = nl dzo = dz ell = el eng = en epo = eo est = et ewe = ee fao = fo fas = fa fij = fj fin = fi fra = fr fry = fy ful = ff kat = ka gla = gd gle = ga glg = gl glv = gv grn = gn guj = gu hat = ht hau = ha heb = he her = hz hin = hi hmo = ho hrv = hr hun = hu ibo = ig isl = is ido = io iii = ii iku = iu ile = ie ina = ia ind = id ipk = ik ita = it jav = jv jpn = ja kal = kl kan = kn kas = ks kau = kr kaz = kk khm = km kik = ki kin = rw kir = ky kom = kv kon = kg kor = ko kua = kj kur = ku lao = lo lat = la lav = lv lim = li lin = ln lit = lt ltz = lb lub = lu lug = lg mkd = mk mah = mh mal = ml mri = mi mar = mr msa = ms mlg = mg mlt = mt mon = mn nau = na nav = nv nbl = nr nde = nd ndo = ng nep = ne nno = nn nob = nb nor = no nya = ny oci = oc oji = oj ori = or orm = om oss = os pan = pa pli = pi pol = pl por = pt pus = ps que = qu roh = rm ron = ro run = rn rus = ru sag = sg san = sa sin = si slk = sk slv = sl sme = se smo = sm sna = sn snd = sd som = so sot = st spa = es srd = sc srp = sr ssw = ss sun = su swa = sw swe = sv tah = ty tam = ta tat = tt tel = te tgk = tg tgl = tl tha = th tir = ti ton = to tsn = tn tso = ts tuk = tk tur = tr twi = tw uig = ug ukr = uk urd = ur uzb = uz ven = ve vie = vi vol = vo wln = wa wol = wo xho = xh yid = yi yor = yo zha = za zul = zu # # ISO 639-2 (B) # alb = sq arm = hy baq = eu tib = bo bur = my cze = cs chi = zh wel = cy ger = de dut = nl gre = el per = fa fre = fr geo = ka ice = is mac = mk mao = mi may = ms rum = ro slo = sk #--------------------------------------------------------------------# $common = U+0020..U+007E # Basic Latin $common_marks = { # Combining Diacritical Marks (subset) U+0300..U+030C U+0323 # dot below U+0326..U+0328 # comma below, cedilla, ogonek } $apostrophes = { # Various apostrophe like letters, often used to indicate glottal stop. U+02B9 # ʹ U+02BB # ʻ U+02BC # ʼ U+2019 # ’ U+A78B..U+A78C # Ꞌꞌ } und = $common # undetermined (used by default) #--------------------------------------------------------------------# # # Languages covered by ISO-8859-1 # $iso_8859_1 = { $common $common_marks U+00A1..U+00AC # ¡¢£¤¥¦§¨©ª«¬ U+00AE..U+00AF # ®¯ U+00B0..U+00BF # °±²³´µ¶·¸¹º»¼½¾¿ U+00C0..U+00CF # ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ U+00D0..U+00DF # ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞß U+00E0..U+00EF # àáâãäåæçèéêëìíîï U+00F0..U+00FF # ðñòóôõö÷øùúûüýþÿ U+20AC # € (additional) } ace = $iso_8859_1 # Acehnese af = $iso_8859_1 # Afrikaans an = $iso_8859_1 # Aragonese ast = $iso_8859_1 # Asturian bcl = $iso_8859_1 # Central Bikol bej = $iso_8859_1 # Beja (also Arabic) bem = $iso_8859_1 # Bemba bi = $iso_8859_1 # Bislama br = $iso_8859_1 # Breton ca = $iso_8859_1 # Catalan (except two deprecated letters) car = $iso_8859_1 # Carib cbk = $iso_8859_1 # Chavacano ceb = $iso_8859_1 # Cebuano cgg = $iso_8859_1 # Kiga ch = $iso_8859_1 # Chamorro chk = $iso_8859_1 # Chuukese chy = $iso_8859_1 # Cheyenne co = $iso_8859_1 # Corsican eka = $iso_8859_1 # Ekajuk (assumed) en = $iso_8859_1 # English es = $iso_8859_1 # Spanish eu = $iso_8859_1 # Basque fil = $iso_8859_1 # Filipino fj = $iso_8859_1 # Fijian fo = $iso_8859_1 # Faroese frs = $iso_8859_1 # East Frisian Low Saxon fur = $iso_8859_1 # Friulian fy = $iso_8859_1 # West Frisian ga = $iso_8859_1 # Irish gd = $iso_8859_1 # Scottish Gaelic gil = $iso_8859_1 # Gilbertese gl = $iso_8859_1 # Galician gsw = $iso_8859_1 # Swiss German gv = $iso_8859_1 # Manx gwi = $iso_8859_1 # Gwich'in hil = $iso_8859_1 # Hiligaynon ho = $iso_8859_1 # Hiri Motu ht = $iso_8859_1 # Haitian Creole ia = $iso_8859_1 # Interlingua iba = $iso_8859_1 # Iban ibg = $iso_8859_1 # Ibanag id = $iso_8859_1 # Indonesian ie = $iso_8859_1 # Interlingue ilo = $iso_8859_1 # Ilocano io = $iso_8859_1 # Ido is = $iso_8859_1 # Icelandic it = $iso_8859_1 # Italian ivb = $iso_8859_1 # Ibatan ivv = $iso_8859_1 # Ivatan kha = $iso_8859_1 # Khasi ki = $iso_8859_1 # Kikuyu kl = $iso_8859_1 # Greenlandic kos = $iso_8859_1 # Kosraean kw = $iso_8859_1 # Cornish la = $iso_8859_1 # Latin lam = $iso_8859_1 # Lamba (assumed) lb = $iso_8859_1 # Luxembourgish li = $iso_8859_1 # Limburgish lld = $iso_8859_1 # Ladin loz = $iso_8859_1 # Lozi lu = $iso_8859_1 # Luba-Katanga (assumed) lua = $iso_8859_1 # Luba-Kasai lus = $iso_8859_1 # Lushai mdh = $iso_8859_1 # Maguindanao mic = $iso_8859_1 # Mi'kmaq mrw = $iso_8859_1 # Maranao mwl = $iso_8859_1 # Mirandese na = $iso_8859_1 # Nauru nap = $iso_8859_1 # Neapolitan nd = $iso_8859_1 # Northern Ndebele nds = $iso_8859_1 # Low German nia = $iso_8859_1 # Nias nr = $iso_8859_1 # Southern Ndebele nyn = $iso_8859_1 # Nkore nyo = $iso_8859_1 # Nyoro oc = $iso_8859_1 # Occitan pag = $iso_8859_1 # Pangasinan pam = $iso_8859_1 # Kapampangan pap = $iso_8859_1 # Papiamento pau = $iso_8859_1 # Palauan pon = $iso_8859_1 # Pohnpeian pt = $iso_8859_1 # Portuguese qu = $iso_8859_1 # Quechua rm = $iso_8859_1 # Romansh rn = $iso_8859_1 # Kirundi rup = $iso_8859_1 # Aromanian rw = $iso_8859_1 # Kinyarwanda sad = $iso_8859_1 # Sandawe sco = $iso_8859_1 # Scots sma = $iso_8859_1 # Southern Sami so = $iso_8859_1 # Somali (also Arabic) sq = $iso_8859_1 # Albanian srn = $iso_8859_1 # Sranan Tongo ss = $iso_8859_1 # Swazi/Swati stq = $iso_8859_1 # Saterland Frisian sv = $iso_8859_1 # Swedish sw = $iso_8859_1 # Swahili tdt = $iso_8859_1 # Tetum ter = $iso_8859_1 # Terêna tiv = $iso_8859_1 # Tiv tl = $iso_8859_1 # Tagalog tpi = $iso_8859_1 # Tok Pisin ts = $iso_8859_1 # Tsonga umb = $iso_8859_1 # Umbundu vo = $iso_8859_1 # Volapük wa = $iso_8859_1 # Walloon wal = $iso_8859_1 # Wolaitta war = $iso_8859_1 # Waray xh = $iso_8859_1 # Xhosa xsb = $iso_8859_1 # Sambal yap = $iso_8859_1 # Yapese yka = $iso_8859_1 # Yakan zap = $iso_8859_1 # Zapotec languages (assumed) zu = $iso_8859_1 # Zulu akl = $iso_8859_1 # Aklanon mlz = akl # Malaynon ay = $iso_8859_1 # Aymara ayc = ay # Southern Aymara ayr = ay # Central Aymara kck = $iso_8859_1 # Kalanga nmq = kck # Nambya kg = $iso_8859_1 # Kongo (assumed) kng = kg # Koongo ldi = kg # Laari kwy = kg # San Salvador Kongo yom = kg # Yombe kj = $iso_8859_1 # Kwanyama ng = $iso_8859_1 # Ndonga kwm = $iso_8859_1 # Kwambi lnb = $iso_8859_1 # Mbalanhu nne = $iso_8859_1 # Ngandjera mg = $iso_8859_1 # Malagasy xmv = mg # Antankarana bhr = mg # Bara buc = mg # Bushi msh = mg # Masikoro bmm = mg # Northern Betsimisaraka plt = mg # Plateau Malagasy skg = mg # Sakalava bzc = mg # Southern Betsimisaraka tdx = mg # Tandroy-Mafahaly txy = mg # Tanosy tkg = mg # Tesaka xmw = mg # Tsimihety ms = $iso_8859_1 # Malay kxd = ms # Brunei Malay zsm = ms # Standard Malay jax = ms # Jambi Malay meo = ms # Kedah Malay kvr = ms # Kerinci xmm = ms # Manado Malay min = ms # Minangkabau mui = ms # Musi zmi = ms # Negeri Sembilan max = ms # North Moluccan Malay coa = ms # Cocos Malay no = $iso_8859_1 # Norwegian nb = no # Norwegian Bokmål nn = no # Norwegian Nynorsk om = $iso_8859_1 # Oromo gax = om # Borana–Arsi–Guji–Wallaggaa-Shawaa Oromo hae = om # Eastern Oromo orc = om # Orma gaz = om # West Central Oromo ssn = om # Waata sc = $iso_8859_1 # Sardinian sro = sc # Campidanese Sardinian src = sc # Logudorese Sardinian seh = $iso_8859_1 # Mozambiquean Sena swk = seh # Malawian Sena bwg = seh # Barwe sg = $iso_8859_1 # Sango snj = sg # Riverain Sango sgd = $iso_8859_1 # Surigaonon tgn = sgd # Tandaganon sn = $iso_8859_1 # Shona twl = sn # Tavara (Korekore) mxc = sn # Manyika twx = sn # Tewe (Manyika) ndc = sn # Ndau toi = $iso_8859_1 # Tonga (Chitonga, assumed) dov = toi # Dombe za = $iso_8859_1 # Zhuang zch = za # Central Hongshuihe Zhuang zhd = za # Dai Zhuang (Wenma) zeh = za # Eastern Hongshuihe Zhuang zgb = za # Guibei Zhuang zgn = za # Guibian Zhuang zln = za # Lianshan Zhuang zlj = za # Liujiang Zhuang zlq = za # Liuqian Zhuang zgm = za # Minz Zhuang zhn = za # Nong Zhuang (Yanguang) zqe = za # Qiubei Zhuang zyg = za # Yang Zhuang (Dejing) zyb = za # Yongbei Zhuang zyn = za # Yongnan Zhuang zyj = za # Youjiang Zhuang zzj = za # Zuojiang Zhuang #--------------------------------------------------------------------# # # Languages covered by ISO-8859-1 except rare letters # da = { # Danish $iso_8859_1 U+01FE..U+01FF # Ǿǿ } jut = da # Jutlandic de = { # German $iso_8859_1 U+1E9E # ẞ } fr = { # French $iso_8859_1 U+0152..U+0153 # Œœ U+0178 # Ÿ } nl = { # Dutch $iso_8859_1 U+0132..U+0133 # IJij } $finnic_latin = { $iso_8859_1 U+010C..U+010D # Čč U+0160..U+0161 # Šš U+017D..U+017E # Žž $apostrophes } et = $finnic_latin # Estonian ekk = et # Standard Estonian vro = et # Võro fi = $finnic_latin # Finnish krl = $finnic_latin # Karelian vep = $finnic_latin # Veps vot = $finnic_latin # Votic #--------------------------------------------------------------------# # # Languages covered by ISO-8859-2 # $iso_8859_2 = { $common $common_marks U+00A4 # ¤ U+00A7..U+00A8 # §¨ U+00B0 # ° U+00B4 # ´ U+00B8 # ¸ U+00C1..U+00C2 # Á U+00C4 # Ä U+00C7 # Ç U+00C9 # É U+00CB # Ë U+00CD..U+00CE # ÍÎ U+00D3..U+00D4 # ÓÔ U+00D6..U+00D7 # Ö× U+00DA # Ú U+00DC..U+00DD # ÜÝ U+00DF # ß U+00E1..U+00E2 # áâ U+00E4 # ä U+00E7 # ç U+00E9 # é U+00EB # ë U+00ED..U+00EE # íî U+00F3..U+00F4 # óô U+00F6..U+00F7 # ö÷ U+00FA # ú U+00FC..U+00FD # üý U+0102..U+0107 # Ă㥹Ćć U+010C..U+010F # ČčĎď U+0110..U+0111 # Đđ U+0118..U+011B # ĘęĚě U+0139..U+013A # Ĺĺ U+013D..U+013E # Ľľ U+0141..U+0144 # ŁłŃń U+0147..U+0148 # Ňň U+0150..U+0151 # Őő U+0154..U+0155 # Ŕŕ U+0158..U+015B # ŘřŚś U+015E..U+015F # Şş U+0160..U+0165 # ŠšŢţŤť U+016E..U+016F # Ůů U+0170..U+0171 # Űű U+0179..U+017E # ŹźŻżŽž U+02C7 # ˇ U+02D8..U+02D9 # ˘˙ U+02DB # ˛ U+02DD # ˝ U+20AC # € (additional) } cs = $iso_8859_2 # Czech hr = $iso_8859_2 # Croatian hu = $iso_8859_2 # Hungarian pl = $iso_8859_2 # Polish sk = $iso_8859_2 # Slovak sl = $iso_8859_2 # Slovene hsb = $iso_8859_2 # Upper Sorbian dsb = $iso_8859_2 # Lower Sorbian #--------------------------------------------------------------------# # # Languages covered by ISO-8859-3 # $iso_8859_3 = { $common $common_marks U+00A3..U+00A4 # £¤ U+00A7..U+00A8 # §¨ U+00B0 # ° U+00B2..U+00B5 # ²³´µ U+00B7..U+00B8 # ·¸ U+00BD # ½ U+00C0..U+00C2 # ÀÁ U+00C4 # Ä U+00C7..U+00CF # ÇÈÉÊËÌÍÎÏ U+00D1..U+00D4 # ÑÒÓÔ U+00D6..U+00D7 # Ö× U+00D9..U+00DC # ÙÚÛÜ U+00DF # ß U+00E0..U+00E2 # àáâ U+00E4 # ä U+00E7..U+00EF # çèéêëìíîï U+00F1..U+00F4 # ñòóô U+00F6..U+00F7 # ö÷ U+00F9..U+00FC # ùúûü U+0108..U+010B # ĈĉĊċ U+011C..U+011F # ĜĝĞğ U+0120..U+0121 # Ġġ U+0124..U+0127 # ĤĥĦħ U+0130..U+0131 # İı U+0134..U+0135 # Ĵĵ U+015C..U+015F # ŜŝŞş U+016C..U+016D # Ŭŭ U+017B..U+017C # Żż U+02D8..U+02D9 # ˘˙ U+20AC # € (additional) } eo = $iso_8859_3 # Esperanto mt = $iso_8859_3 # Maltese #--------------------------------------------------------------------# # # Languages covered by ISO-8859-4 / ISO-8849-10 # $iso_8859_4_10 = { $common $common_marks U+00A4 # ¤ U+00A7..U+00A8 # §¨ U+00AF # ¯ U+00B0 # ° U+00B4 # ´ U+00B7 # · U+00B8 # ¸ U+00C1..U+00C6 # ÁÂÃÄÅÆ U+00C9 # É U+00CB # Ë U+00CD..U+00CF # ÍÎÏ U+00D0 # Ð U+00D3..U+00D8 # ÓÔÕÖ×Ø U+00DA..U+00DF # ÚÛÜÝÞß U+00E1..U+00E6 # áâãäåæ U+00E9 # é U+00EB # ë U+00ED..U+00EF # íîï U+00F0 # ð U+00F3..U+00F8 # óôõö÷ø U+00FA..U+00FE # úûüýþ U+0100..U+0101 # Āā U+0104..U+0105 # Ąą U+010C..U+010D # Čč U+0110..U+0113 # ĐđĒē U+0116..U+0119 # ĖėĘę U+0122..U+0123 # Ģģ U+0128..U+012B # ĨĩĪī U+012E..U+012F # Įį U+0136..U+0138 # Ķķĸ U+013B..U+013C # Ļļ U+0145..U+0146 # Ņņ U+014A..U+014D # ŊŋŌō U+0156..U+0157 # Ŗŗ U+0160..U+0161 # Šš U+0166..U+016B # ŦŧŨũŪū U+0172..U+0173 # Ųų U+017D..U+017E # Žž U+02C7 # ˇ U+02D9 # ˙ U+02DB # ˛ U+20AC # € (additional) } lv = $iso_8859_4_10 # Latvian lvs = lv # Standard Latvian language ltg = lv # Latgalian language lt = $iso_8859_4_10 # Lithuanian sgs = lt # Samogitian se = $iso_8859_4_10 # Northern Sami smj = $iso_8859_4_10 # Lule Sami smn = $iso_8859_4_10 # Inari Sami #--------------------------------------------------------------------# # # Languages using other Latin alphabets # # Europe csb = { # Kashubian $common $common_marks U+00C3 # à U+00C9 # É U+00CB # Ë U+00D2..U+00D4 # ÒÓÔ U+00D9 # Ù U+00E3 # ã U+00E9 # é U+00EB # ë U+00F2..U+00F4 # òóô U+00F9 # ù U+0104..U+0105 # Ąą U+0141..U+0144 # ŁłŃń U+017B..U+017C # Żż } cy = { # Welsh $iso_8859_1 U+0174..U+0178 # ŴŵŶŷŸ U+1E80..U+1E85 # ẀẁẂẃẄẅ U+1EF2..U+1EF3 # Ỳỳ } frr = { # North Frisian $iso_8859_1 U+0100..U+0101 # Āā U+0110..U+0113 # ĐđĒē } scn = { # Sicilian $iso_8859_1 U+00D0 # Ð U+0111 # đ U+1E0C..U+1E0D # Ḍḍ } sms = { # Skolt Sami $common $common_marks U+00C2 #  U+00C4..U+00C5 # ÄÅ U+00D5 # Õ U+00E2 # â U+00E4..U+00E5 # äå U+00F5 # õ U+010C..U+010D # Čč U+0110..U+0111 # Đđ U+014A..U+014B # Ŋŋ U+0160..U+0161 # Šš U+017D..U+017E # Žž U+01B7 # Ʒ U+01E4..U+01E9 # ǤǥǦǧǨǩ U+01EE..U+01EF # Ǯǯ U+0292 # ʒ $apostrophes U+02C8 # ˈ } szl = { # Silesian $common $common_marks U+00C3 # à U+00D4..U+00D5 # ÔÕ U+00E3 # ã U+00F4..U+00F5 # ôõ U+0106..U+0107 # Ćć U+010C..U+010D # Čč U+0141..U+0144 # ŁłŃń U+014C..U+014F # ŌōŎŏ U+0158..U+015B # ŘřŚś U+0160..U+0161 # Šš U+016E..U+016F # Ůů U+0179..U+017E # ŹźŻżŽž } # Asia $formosan_alphabets = { $common $common_marks U+00C9 # É U+00E9 # é U+0197 # Ɨ U+0268 # ɨ U+0244 # Ʉ U+0289 # ʉ U+1E5E..U+1E5F # Ṟṟ } ami = $formosan_alphabets # Amis tay = $formosan_alphabets # Atayal bnn = $formosan_alphabets # Bunun xnb = $formosan_alphabets # Kanakanavu ckv = $formosan_alphabets # Kavalan pwn = $formosan_alphabets # Paiwan pyu = $formosan_alphabets # Puyuma dru = $formosan_alphabets # Rukai sxr = $formosan_alphabets # Saaroa xsy = $formosan_alphabets # Saisiyat szy = $formosan_alphabets # Sakizaya trv = $formosan_alphabets # Seediq, Taroko ssf = $formosan_alphabets # Thao tsu = $formosan_alphabets # Tsou tao = $formosan_alphabets # Yami/Tao hak = { # Hakka $iso_8859_1 U+016E..U+016F # Ůů U+1E72..U+1E73 # Ṳṳ U+030D # combining vertical line above U+0324 # combining diaeresis below } krj = { # Karay-a $common U+00CB # Ë U+00EB # ë U+014A..U+014B # Ŋŋ U+018F # Ə U+0259 # ə } nan = { # Southern Min $iso_8859_1 U+0100..U+0101 # Āā U+0112..U+0113 # Ēē U+012A..U+012B # Īī U+0143..U+0144 # Ńń U+014C..U+014D # Ōō U+016A..U+016B # Ūū U+01F8..U+01F9 # Ǹǹ U+1E72..U+1E73 # Ṳṳ U+207F # ⁿ U+030D # combining vertical line above U+030E # combining double vertical line above U+0358 # combining dot above right } $turkic_latin = { $iso_8859_1 U+010C..U+010D # Čč U+0116..U+0117 # Ėė U+011E..U+011F # Ğğ U+0130..U+0131 # İı U+0143..U+0144 # Ńń U+014A..U+014B # Ŋŋ U+015A..U+015B # Śś U+015E..U+015F # Şş U+0160..U+0161 # Šš U+0162..U+0163 # Ţţ U+016A..U+016B # Ūū U+0179..U+017A # Źź U+017D..U+017E # Žž U+018F # Ə U+01F4..U+01F5 # Ǵǵ U+0259 # ə $apostrophes } tr = $turkic_latin # Turkish tsg = { # Tausug $common $common_marks U+0100..U+0101 # Āā U+0112..U+0113 # Ēē U+012A..U+012B # Īī U+014A..U+014B # Ŋŋ U+014C..U+014D # Ōō U+016A..U+016B # Ūū } vi = { # Vietnamese $iso_8859_1 U+0100..U+017F # Latin Extended-A U+0180..U+024F # Latin Extended-B U+1EA0..U+1EF9 # Latin Extended Additional (subset) U+0340..U+0341 # ◌̀◌́ U+1DC4 # ᷄ U+20AB # ₫ } zza = { # Zaza $common $common_marks U+00C7 # Ç U+00CA # Ê U+00CE # Î U+00DB # Û U+00E7 # ç U+00EA # ê U+00EE # î U+00FB # û U+011E..U+011F # Ğğ U+015E..U+015F # Şş } # Oceania $polynesian_latin = { $common $common_marks U+0100..U+0101 # Āā U+0112..U+0113 # Ēē U+012A..U+012B # Īī U+014A..U+014B # Ŋŋ U+014C..U+014D # Ōō U+016A..U+016B # Ūū U+0294 # ʔ $apostrophes } haw = $polynesian_latin # Hawaiian mi = $polynesian_latin # Maori niu = $polynesian_latin # Niuean pnh = $polynesian_latin # Tongareva rap = $polynesian_latin # Rapa Nui rar = $polynesian_latin # Cook Islands Maori rkh = $polynesian_latin # Rakahanga-Manihiki sm = $polynesian_latin # Samoan tkl = $polynesian_latin # Tokelauan to = $polynesian_latin # Tongan tvl = $polynesian_latin # Tuvaluan ty = $polynesian_latin # Tahitian mh = { # Marshallese $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+0100..U+0101 # Āā U+013B..U+013C # Ļļ U+0145..U+0146 # Ņņ U+014C..U+014D # Ōō U+016A..U+016B # Ūū U+1E36..U+1E37 # Ḷḷ U+1E42..U+1E43 # Ṃṃ U+1E46..U+1E47 # Ṇṇ U+1ECC..U+1ECD # Ọọ } # Africa $benin_alphabets = { $iso_8859_1 U+0100..U+0101 # Āā U+0112..U+0113 # Ēē U+011A..U+011B # Ěě U+0128..U+0129 # Ĩĩ U+012A..U+012B # Īī U+0143..U+0144 # Ńń U+0147..U+0148 # Ňň U+014A..U+014B # Ŋŋ U+014C..U+014D # Ōō U+0168..U+0169 # Ũũ U+016A..U+016B # Ūū U+0181 # Ɓ U+0186 # Ɔ U+0189..U+018A # ƉƊ U+018E..U+018F # ƎƏ U+0190..U+0192 # ƐƑƒ U+0194 # Ɣ U+0196 # Ɩ U+01B1..U+01B4 # ƱƲƳƴ U+01B7 # Ʒ U+01CD..U+01CF # ǍǎǏ U+01D0..U+01D4 # ǐǑǒǓǔ U+01DD # ǝ U+01F8..U+01F9 # Ǹǹ U+0253..U+0254 # ɓɔ U+0256..U+0257 # ɖɗ U+0259 # ə U+025B # ɛ U+0263 # ɣ U+0269 # ɩ U+028A..U+028B # ʊʋ U+0292 # ʒ U+0330 # combining tilde below U+1E1A..U+1E1B # Ḛḛ U+1E2C..U+1E2D # Ḭḭ U+1E3E..U+1E3F # Ḿḿ U+1E4C..U+1E4D # Ṍṍ U+1E74..U+1E75 # Ṵṵ U+1E78..U+1E79 # Ṹṹ U+1EBC..U+1EBD # Ẽẽ } ajg = $benin_alphabets # Aja bba = $benin_alphabets # Bariba beh = $benin_alphabets # Berba (Biali) blo = $benin_alphabets # Anii (Basila) bqc = $benin_alphabets # Boko, Boo ddn = $benin_alphabets # Dendi dop = $benin_alphabets # Lukpa fod = $benin_alphabets # Foodo fon = $benin_alphabets # Fon gej = $benin_alphabets # Gen mql = $benin_alphabets # Mbelime ntm = $benin_alphabets # Nateni pil = $benin_alphabets # Yom soy = $benin_alphabets # Yobe tbz = $benin_alphabets # Tammari wwa = $benin_alphabets # Waama xwe = $benin_alphabets # Xwela $ghana_alphabets = { $iso_8859_1 U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+0186 # Ɔ U+0189 # Ɖ U+018E # Ǝ U+0190..U+0192 # ƐƑƒ U+0194 # Ɣ U+0196 # Ɩ U+01B2..U+01B4 # ƲƳƴ U+01B7 # Ʒ U+01DD # ǝ U+0253..U+0254 # ɓɔ U+0256 # ɖ U+025B # ɛ U+0263 # ɣ U+0269 # ɩ U+028B # ʋ U+0292 # ʒ $apostrophes } ak = $ghana_alphabets # Akan tw = ak # Twi fat = ak # Fante dga = $ghana_alphabets # Southern Dagaare dgd = $ghana_alphabets # Dagaari Dioula dgi = $ghana_alphabets # Northern Dagara dag = $ghana_alphabets # Dagbani ada = $ghana_alphabets # Dangme ee = $ghana_alphabets # Ewe wci = ee # Waci kef = ee # Kpesi gur = $ghana_alphabets # Frafra gaa = $ghana_alphabets # Ga gjn = $ghana_alphabets # Gonja nzi = $ghana_alphabets # Nzema xsm = $ghana_alphabets # Kasem ach = { # Acholi $iso_8859_1 U+014A..U+014B # Ŋŋ } $balanta_alphabets = { $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+014A..U+014B # Ŋŋ U+0166..U+0167 # Ŧŧ U+0181 # Ɓ U+0253 # ɓ } ble = $balanta_alphabets # Balanta-Kentohe bjt = $balanta_alphabets # Balanta-Ganja bdm = { # Yedina (Buduma) $iso_8859_1 U+018F # Ə U+0259 # ə } bin = { # Bini, Edo $common $common_marks U+1EB8..U+1EB9 # Ẹẹ U+1ECC..U+1ECD # Ọọ } bsc = { # Bassari $iso_8859_1 U+0124..U+0125 # Ĥĥ U+014A..U+014B # Ŋŋ U+015C..U+015D # Ŝŝ U+0174..U+0177 # ŴŵŶŷ U+0181 # Ɓ U+0186 # Ɔ U+018A # Ɗ U+018E # Ǝ U+0190 # Ɛ U+019D # Ɲ U+01A9 # Ʃ U+01B3..U+01B4 # Ƴƴ U+01DD # ǝ U+0248..U+0249 # Ɉɉ U+0253..U+0254 # ɓɔ U+0257 # ɗ U+025B # ɛ U+0272 # ɲ U+0283 # ʃ U+1EF8..U+1EF9 # Ỹỹ } boo = { # Bozo $common U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+019D # Ɲ U+0254 # ɔ U+025B # ɛ U+0272 # ɲ } boz = boo bze = boo bzx = boo bmq = { # Bomu $common U+0181 # Ɓ U+0190 # Ɛ U+019D # Ɲ U+0253 # ɓ U+025B # ɛ U+0272 # ɲ $apostrophes } $chewa_tumbuka_latin = { $iso_8859_1 U+0174..U+0175 # Ŵŵ U+014A..U+014B # Ŋŋ } ny = $chewa_tumbuka_latin # Chewa (Nyanja) tum = $chewa_tumbuka_latin # Tumbuka cou = { # Wamey $common $common_marks U+00C1 # Á U+00CB # Ë U+00D1 # Ñ U+00E1 # á U+00EB # ë U+00F1 # ñ U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+018A # Ɗ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ U+1EF8..U+1EF9 # Ỹỹ } $dinka_nuer_alphabets = { $common $common_marks U+00C4 # Ä U+00CB # Ë U+00CF # Ï U+00D6 # Ö U+00E4 # ä U+00E9 # é U+00EB # ë U+00EF # ï U+00F3 # ó U+00F6 # ö U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+0194 # Ɣ U+0254 # ɔ U+025B # ɛ U+0263 # ɣ } din = $dinka_nuer_alphabets # Dinka dip = din # Northeastern (Padang) diw = din # Northwestern (Ruweng) dib = din # South Central (Agar) dks = din # Southeastern dik = din # Southwestern (Rek & Twic) nus = $dinka_nuer_alphabets # Nuer dje = { # Zarma $iso_8859_1 U+014A..U+014B # Ŋŋ U+019D # Ɲ U+0272 # ɲ U+0330 # combining tilde below U+1E1A..U+1E1B # Ḛḛ U+1E2C..U+1E2D # Ḭḭ U+1E74..U+1E75 # Ṵṵ # unofficial U+0128..U+0129 # Ĩĩ U+0168..U+0169 # Ũũ U+1EBC..U+1EBD # Ẽẽ } dsh = { $iso_8859_1 U+A7C7..U+A7C8 # Ꟈꟈ $apostrophes } dyo = { # Jola-Fonyi $iso_8859_1 U+014A..U+014B # Ŋŋ } efi = { # Efik $common $common_marks U+00D1 # Ñ U+00D6 # Ö U+00F1 # ñ U+00F6 # ö U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0254 # ɔ U+1EB8..U+1EB9 # Ẹẹ U+1ECA..U+1ECD # ỊịỌọ U+1EE4..U+1EE5 # Ụụ } ewo = { # Ewondo $common U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+018F # Ə U+0190 # Ɛ U+0254 # ɔ U+0259 # ə U+025B # ɛ } $fula_alphabets = { $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+018A # Ɗ U+0193 # Ɠ U+019D # Ɲ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ U+0260 # ɠ U+0272 # ɲ } ff = $fula_alphabets # Fula fuc = ff # Pulaar fuf = ff # Pular ffm = ff # Maasina Fulfulde fue = ff # Borgu Fulfulde fuh = ff # Western Niger fuq = ff # Central–Eastern Niger fuv = ff # Nigerian Fulfulde fub = ff # Adamawa Fulfulde fui = ff # Bagirmi Fulfulde ha = { # Hausa $common U+0181 # Ɓ U+018A # Ɗ U+0198..U+0199 # Ƙƙ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ $apostrophes } hz = { # Herero $common U+1E12..U+1E13 # Ḓḓ U+1E4A..U+1E4B # Ṋṋ U+1E70..U+1E71 # Ṱṱ U+032D # combining circumflex accent below } ig = { # Igbo $common $common_marks U+1E44..U+1E45 # Ṅṅ U+1ECA..U+1ECD # ỊịỌọ U+1EE4..U+1EE5 # Ụụ } kbp = { # Kabiye $common $common_marks U+00D1 # Ñ U+00E0..U+00E1 # àá U+00F1 # ñ U+00F9 # ù U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0189 # Ɖ U+0190 # Ɛ U+0194 # Ɣ U+0196 # Ɩ U+01B2 # Ʋ U+0251 # ɑ U+0254 # ɔ U+0256 # ɖ U+025B # ɛ U+0263 # ɣ U+0269 # ɩ U+028B # ʋ } knf = { # Mankanya $common $common_marks U+00CB # Ë U+00D1 # Ñ U+00EB # ë U+00F1 # ñ U+014A..U+014B # Ŋŋ U+015E..U+015F # Şş U+0162..U+0163 # Ţţ U+0166..U+0167 # Ŧŧ } $kpelle_alphabets = { $iso_8859_1 U+0128..U+0129 # Ĩĩ U+014A..U+014B # Ŋŋ U+0168..U+0169 # Ũũ U+0181 # Ɓ U+0186 # Ɔ U+018F # Ə U+0190 # Ɛ U+0193..U+0194 # ƓƔ U+0194 # Ɣ U+019D # Ɲ U+0253..U+0254 # ɓɔ U+0259 # ə U+025B # ɛ U+0260 # ɠ U+0263 # ɣ U+0272 # ɲ } kpe = $kpelle_alphabets # Kpelle gkp = $kpelle_alphabets # Guinea Kpelle xpe = $kpelle_alphabets # Liberia Kpelle knu = $kpelle_alphabets # Kono kr = { # Kanuri $iso_8859_1 U+018E..U+018F # ƎƏ U+01CD..U+01CE # Ǎǎ U+01D1..U+01D4 # ǑǒǓǔ U+01DD # ǝ U+024C..U+024D # Ɍɍ U+0259 # ə U+02C6 # ˆ U+0314 # ̔ } knc = kr # Central Kanuri kby = kr # Manga Kanuri krt = kr # Tumari Kanuri bms = kr # Bilma Kanuri kbl = kr # Kanembu kri = { # Krio $iso_8859_1 U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+0254 # ɔ U+025B # ɛ } lg = { # Luganda $common U+014A..U+014B # Ŋŋ } ln = { # Lingala $iso_8859_1 U+011A..U+011B # Ěě U+0186 # Ɔ U+0190 # Ɛ U+01CD..U+01CF # ǍǎǏ U+01D0..U+01D2 # ǐǑǒ U+0254 # ɔ U+025B # ɛ } lom = { # Loma $iso_8859_1 U+014A..U+014B # Ŋŋ U+0168..U+0169 # Ũũ U+0181 # Ɓ U+0186 # Ɔ U+0190 # Ɛ U+0194 # Ɣ U+01B2 # Ʋ U+0253..U+0254 # ɓɔ U+025B # ɛ U+0263 # ɣ U+028B # ʋ } tod = lom # Toma mas = { # Masai $iso_8859_1 U+0100..U+0101 # Āā U+0112..U+0113 # Ēē U+012A..U+012B # Īī U+014A..U+014B # Ŋŋ U+014C..U+014D # Ōō U+016A..U+016B # Ūū U+0186 # Ɔ U+0190 # Ɛ U+0197 # Ɨ U+0244 # Ʉ U+0254 # ɔ U+025B # ɛ U+0268 # ɨ U+0289 # ʉ U+0294 # ʔ } men = { # Mende $iso_8859_1 U+0102..U+0103 # Ăă U+0114..U+0115 # Ĕĕ U+012C..U+012D # Ĭĭ U+014A..U+014B # Ŋŋ U+014E..U+014F # Ŏŏ U+016C..U+016D # Ŭŭ U+0186 # Ɔ U+0190 # Ɛ U+0254 # ɔ U+025B # ɛ } mfv = { # Manjak $common $common_marks U+00CB # Ë U+00D1 # Ñ U+00EB # ë U+00F1 # ñ U+014A..U+014B # Ŋŋ U+015C..U+015D # Ŝŝ U+0162..U+0163 # Ţţ } mur = { # Murle $common $common_marks U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+0254 # ɔ U+025B # ɛ U+1E0E..U+1E0F # Ḏḏ U+1E6E..U+1E6F # Ṯṯ } myk = { # Minyanka $common U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+019D # Ɲ U+0254 # ɔ U+025B # ɛ U+0272 # ɲ } mos = { # Mossi $iso_8859_1 U+0190 # Ɛ U+0196 # Ɩ U+01B2 # Ʋ U+025B # ɛ U+0269 # ɩ U+028B # ʋ $apostrophes } sav = { # Safene $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+018A # Ɗ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ $apostrophes } seq = { # Senara $common U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+019D # Ɲ U+0254 # ɔ U+025B # ɛ U+0272 # ɲ } shz = seq # Syenara snf = { # Noon $iso_8859_1 U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+018A # Ɗ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ $apostrophes } snk = { # Soninke $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+014A..U+014B # Ŋŋ $apostrophes } $sotho_tswana_latin = { $iso_8859_1 U+0160..U+0161 # Šš } st = $sotho_tswana_latin # Sotho tn = $sotho_tswana_latin # Tswana nso = $sotho_tswana_latin # Northern Sotho srr = { # Serer $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+014A..U+014B # Ŋŋ U+0181 # Ɓ U+0187..U+0188 # Ƈƈ U+018A # Ɗ U+01A4..U+01A5 # Ƥƥ U+01AC..U+01AD # Ƭƭ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ $apostrophes } sus = { # Susu $iso_8859_1 U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+019D # Ɲ U+0254 # ɔ U+025B # ɛ U+0272 # ɲ } suq = { # Suri $common U+0186 # Ɔ U+0190 # Ɛ U+0254 # ɔ U+025B # ɛ } tem = { # Temne $common U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+018F # Ə U+0190 # Ɛ U+0226..U+0227 # Ȧȧ U+0245 # Ʌ U+0254 # ɔ U+0259 # ə U+025B # ɛ U+028C # ʌ } tnr = { # Bedik $common $common_marks U+00C8..U+00C9 # ÈÉ U+00CB # Ë U+00D1 # Ñ U+00E8..U+00E9 # èé U+00EB # ë U+00F1 # ñ U+014A..U+014B # Ŋŋ U+015C..U+015D # Ŝŝ U+0181 # Ɓ U+018A # Ɗ U+01B3..U+01B4 # Ƴƴ U+0253 # ɓ U+0257 # ɗ } udu = { # Uduk $common $common_marks U+014A..U+014B # Ŋŋ U+1E34..U+1E35 # Ḵḵ U+1E6E..U+1E6F # Ṯṯ U+0320 # combining minus sign below U+0331..U+0332 # macron below, low line $apostrophes } ve = { # Venda $common $common_marks U+1E12..U+1E13 # Ḓḓ U+1E3C..U+1E3D # Ḽḽ U+1E44..U+1E45 # Ṅṅ U+1E4A..U+1E4B # Ṋṋ U+1E70..U+1E71 # Ṱṱ U+032D # combining circumflex accent below } wo = { # Wolof $iso_8859_1 U+014A..U+014B # Ŋŋ } wof = wo # Gambian Wolof yao = { # Yao $common $common_marks U+0174..U+0175 # Ŵŵ } yo = { # Yoruba $common $common_marks # Nigeria U+1E62..U+1E63 # Ṣṣ U+1EB8..U+1EB9 # Ẹẹ U+1ECC..U+1ECD # Ọọ # Benin U+0186 # Ɔ U+0190 # Ɛ U+0254 # ɔ U+025B # ɛ } # America arn = { # Mapudungun $iso_8859_1 U+1E3A..U+1E3B # Ḻḻ U+1E48..U+1E49 # Ṉṉ U+1E6E..U+1E6F # Ṯṯ } arp = { # Arapaho $iso_8859_1 U+010C..U+010D # Čč U+0294 # ʔ U+0398 # Θ U+03B8 # θ $apostrophes } cad = { # Caddo $common U+0294 # ʔ $apostrophes } chn = { # Chinook jargon $common $common_marks U+018F # Ə U+0259 # ə U+026C # ɬ U+0294 # ʔ U+02B0 # ʰ U+A7AD # Ɬ $apostrophes } cho = { # Choctaw $common $common_marks U+0100..U+0101 # Āā U+0104..U+0105 # Ąą U+010C..U+010D # Čč U+012A..U+012B # Īī U+012E..U+012F # Įį U+0141..U+0142 # Łł U+014C..U+014D # Ōō U+0160..U+0161 # Šš U+01B2 # Ʋ U+01EA..U+01EB # Ǫǫ U+028B # ʋ U+1EA0..U+1EA1 # Ạạ U+207F # ⁿ } $sioux_alphabets = { $iso_8859_1 U+0104..U+0107 # ĄąĆć U+010A..U+010D # ĊċČč U+0120..U+0121 # Ġġ U+0126..U+0127 # Ħħ U+012E..U+012F # Įį U+0136..U+0137 # Ķķ U+0147..U+0148 # Ňň U+014A..U+014B # Ŋŋ U+015A..U+015B # Śś U+0160..U+0163 # ŠšŢţ U+0172..U+0173 # Ųų U+0179..U+017E # ŹźŻżŽž U+01E4..U+01E7 # ǤǥǦǧ U+0218..U+0219 # Șș U+021E..U+021F # Ȟȟ U+02BC..U+02BF # ʼʽʾʿ U+0314 # ̔ U+0397 # Η U+03B7 # η U+1E22..U+1E23 # Ḣḣ U+1E32..U+1E33 # Ḳḳ U+1E56..U+1E57 # Ṗṗ U+1E60..U+1E61 # Ṡṡ U+1E6A..U+1E6D # ṪṫṬṭ $apostrophes } dak = $sioux_alphabets # Dakota lkt = $sioux_alphabets # Lakota dgr = { # Dogrib $common $common_marks U+00C0 # À U+00C8 # È U+00CC # Ì U+00D2 # Ò U+00D9 # Ù U+00E0 # à U+00E8 # è U+00EC # ì U+00F2 # ò U+00F9 # ù U+0104..U+0105 # Ąą U+0118..U+0119 # Ęę U+012E..U+012F # Įį U+0131 # ı U+0141..U+0142 # Łł U+0172..U+0173 # Ųų U+01EA..U+01EB # Ǫǫ $apostrophes } gn = { # Guarani $common $common_marks U+00C3 # à U+00D1 # Ñ U+00D5 # Õ U+00E3 # ã U+00F1 # ñ U+00F5 # õ U+0128..U+0129 # Ĩĩ U+0168..U+0169 # Ũũ U+1EBC..U+1EBD # Ẽẽ U+1EF8..U+1EF9 # Ỹỹ $apostrophes } ik = { # Inupiaq $common $common_marks U+00D1 # Ñ U+00F1 # ñ U+0120..U+0121 # Ġġ U+0141..U+0142 # Łł U+014A..U+014B # Ŋŋ U+1E36..U+1E37 # Ḷḷ $apostrophes } esi = ik # North Alaskan Inupiatun esk = ik # Northwest Alaska Inupiatun kut = { # Kutenai $common $common_marks U+00B7 # · U+023B..U+023C # Ȼȼ U+0294 # ʔ U+0313 # ̓ U+0315 # ̕ U+2C60..U+2C61 # Ⱡⱡ } moh = { # Mohawk $iso_8859_1 U+1E48..U+1E49 # Ṉṉ U+A789 # ꞉ $apostrophes } mus = { # Muscogee (Creek) $common $common_marks U+0112..U+0113 # Ēē } nv = { # Navajo $common $common_marks U+00C1 # Á U+00C9 # É U+00CD # Í U+00D3 # Ó U+00E1 # á U+00E9 # é U+00ED # í U+00F3 # ó U+0104..U+0105 # Ąą U+0118..U+0119 # Ęę U+012E..U+012F # Įį U+0141..U+0142 # Łł U+01EA..U+01EB # Ǫǫ $apostrophes } tli = { # Tlingit $iso_8859_1 U+0141..U+0142 # Łł U+0178 # Ÿ U+0320 # combining minus sign below U+0331..U+0332 # macron below, low line U+1E34..U+1E35 # Ḵḵ $apostrophes } was = { # Washo $common $common_marks U+00C1 # Á U+00C9 # É U+00CD # Í U+00D3 # Ó U+00DA # Ú U+00E1 # á U+00E9 # é U+00ED # í U+00F3 # ó U+00FA # ú U+0106..U+0107 # Ćć U+014A..U+014B # Ŋŋ U+0160..U+0161 # Šš U+0197 # Ɨ U+0268 # ɨ U+0294 # ʔ U+A789 # ꞉ $apostrophes } zun = { # Zuni $common U+0141..U+0142 # Łł U+A789 # ꞉ $apostrophes } #--------------------------------------------------------------------# # # Languages using Greek script # $greek = $common U+0370..U+03E1 U+03F0..U+03FF el = $greek # Greek #--------------------------------------------------------------------# # # Languages using Cyrillic script # $cyrillic = { $common $common_marks $apostrophes U+00AB U+00BB # «» U+0400..U+040F # Cyrillic extensions U+0410..U+044F # Basic Cyrillic U+0450..U+045F # Cyrillic extensions U+048A..U+04F9 # Extended Cyrillic U+2018..U+201F # punctuation U+20BD # ₽ } # East Slavic languages: ru = $cyrillic # Russian be = $cyrillic # Belarusian uk = $cyrillic # Ukrainian rue = $cyrillic # Rusyn # South Slavic languages: bg = $cyrillic # Bulgarian mk = $cyrillic # Macedonian # Bosnian (below) # Serbian (below) # Montenegrin (below) # Uralic languages: sjd = $cyrillic # Kildin Sami kv = $cyrillic # Komi koi = $cyrillic # Permyak udm = $cyrillic # Udmurt # Khanty (below) mns = $cyrillic # Mansi # Enets (below) # Nenets (missing codes) nio = $cyrillic # Nganasan sel = $cyrillic # Selkup chm = $cyrillic # Mari myv = $cyrillic # Erzya (Mordvin) mdf = $cyrillic # Moksha (Mordvin) # Non-Slavic Indo-European languages: # Kurdish (below) os = $cyrillic # Ossetian tg = $cyrillic # Tajik sgh = $cyrillic # Shughni # Tat (below) # Judeo-tat/Juhuri (below) # Yaghnobi (below) # Yazghulami (below) # Romance languages: # Moldovan (below) # Indo-Aryan languages: # Romani (below) # Mongolian languages: mn = $cyrillic # Mongolian khk = $cyrillic # Khalkha bua = $cyrillic # Buryat xal = $cyrillic # Kalmyk # Northwest Caucasian languages: abq = $cyrillic # Abaza ady = $cyrillic # Adyghe kbd = $cyrillic # Kabardian uby = $cyrillic # Ubykh # Northeast Caucasian languages: av = $cyrillic # Avar lez = $cyrillic # Lezgin ce = $cyrillic # Chechen dar = $cyrillic # Dargwa lbe = $cyrillic # Lak tab = $cyrillic # Tabassaran inh = $cyrillic # Ingush aqc = $cyrillic # Archi agx = $cyrillic # Aghul rut = $cyrillic # Rutul # Turkic languages: # Azerbaijani (below) ba = $cyrillic # Bashkir cv = $cyrillic # Chuvash # Kazakh (below) ky = $cyrillic # Kyrgyz (some Arabic) tt = $cyrillic # Tatar (some Arabic) # Uzbek (below) alt = $cyrillic # Altay krc = $cyrillic # Karachay-Balkar # Crimean Tatar (below) # Gagauz (below) # Karakalpak (below) # Karaim (below) kjh = $cyrillic # Khakas kum = $cyrillic # Kumyk nog = $cyrillic # Nogai tyv = $cyrillic # Tuvan # Uyghur (below) sah = $cyrillic # Yakut dlg = $cyrillic # Dolgan bgx = $cyrillic # Balkan Gagauz Turkish uum = $cyrillic # Urum # Siberian Tatar (below) # Sinitic: dng = $cyrillic # Dungan # Tungusic languages: eve = $cyrillic # Even evn = $cyrillic # Evenki gld = $cyrillic # Nanai ude = $cyrillic # Udege # Orok (below) ulc = $cyrillic # Ulch # Chukotko-Kamchatkan languages: # Chukchi (below) kpy = $cyrillic # Koryak # Itelmen (below) alr = $cyrillic # Alyutor # Eskimo-Aleut languages: # Aleut (below) ynk = $cyrillic # Naukan Yupik ess = $cyrillic # Central Siberian Yupik # Yukaghir languages: # Tundra Yukaghir (below) # Southern Yukaghir (below) # Other languages: ket = $cyrillic # Ket # Nivkh (below) #--------------------------------------------------------------------# # # Languages requiring chars outside main Cyrillic range # ab = { # Abkhazian $cyrillic U+0524..U+0525 # Ԥԥ } oaa = { # Orok $cyrillic U+0528..U+0529 # Ԩԩ } niv = { # Nivkh $cyrillic U+04FA..U+04FF # Additions for Nivkh } $khanty_enets_itelmen = { $cyrillic U+0510..U+0511 # Ԑԑ U+0512..U+0513 # Ԓԓ U+052E..U+052F # Ԯԯ } kca = $khanty_enets_itelmen # Khanty enf = $khanty_enets_itelmen # Forest Enets enh = $khanty_enets_itelmen # Tundra Enets ckt = $khanty_enets_itelmen # Chukchi itl = $khanty_enets_itelmen # Itelmen $cyrillic_we = { $cyrillic U+051C..U+051D # Ԝԝ } ykg = $cyrillic_we # Tundra Yukaghir yux = $cyrillic_we # Southern Yukaghir #--------------------------------------------------------------------# # # Languages with both Latin and Cyrillic alphabets # bs = $iso_8859_2 $cyrillic # Bosnian sr = $iso_8859_2 $cyrillic # Serbian cnr = $iso_8859_2 $cyrillic # Montenegrin tk = $iso_8859_2 $cyrillic # Turkmen (also Arabic) $kurdish_latin = { $iso_8859_1 U+0141..U+0142 # Łł U+0147..U+0148 # Ňň U+0158..U+0159 # Řř U+015E..U+015F # Şş U+051A..U+051D # ԚԛԜԝ } ku = $kurdish_latin $cyrillic # Kurdish kmr = ku # Kurmanji ro = { # Romanian/Moldovan $iso_8859_1 U+0102..U+0103 # Ăă U+015E..U+015F # Şş U+0162..U+0163 # Ţţ U+0218..U+021B # ȘșȚț $cyrillic } az = $turkic_latin $cyrillic # Azerbaijani (also Perso-Arabic) azj = az # North Azerbaijani kk = $turkic_latin $cyrillic # Kazakh (also Arabic) uz = $turkic_latin $cyrillic # Uzbek (some Arabic) crh = $turkic_latin $cyrillic # Crimean Tatar gag = $turkic_latin $cyrillic # Gagauz kaa = $turkic_latin $cyrillic # Karakalpak kdr = $turkic_latin $cyrillic # Karaim sty = $turkic_latin $cyrillic # Siberian Tatar ug = { # Uyghur (also Arabic) $iso_8859_1 # Uyghur New Script U+018F # Ə U+019F # Ɵ U+01A2..U+01A3 # Ƣƣ U+0259 # ə U+0275 # ɵ U+2C67..U+2C6C # ⱧⱨⱩⱪⱫⱬ $cyrillic } ttt = { # Tat $iso_8859_1 U+011E..U+011F # Ğğ U+0130..U+0131 # İı U+015E..U+015F # Şş U+018F # Ə U+0259 # ə $cyrillic U+0526..U+0527 # Ԧԧ } ale = { # Aleut $iso_8859_1 U+011C..U+011D # Ĝĝ $cyrillic U+04FC..U+04FD # Ӽӽ } rom = { # Romani $common $common_marks U+00C4 # Ä U+00C4..U+00C5 # ÄÅ U+00C7 # Ç U+00D6 # Ö U+00E4..U+00E5 # äå U+00E7 # ç U+00F6 # ö U+0102..U+0103 # Ăă U+0106..U+0107 # Ćć U+010C..U+010D # Čč U+014E..U+014F # Ŏŏ U+015A..U+015B # Śś U+0160..U+0161 # Šš U+0179..U+017A # Źź U+017D..U+017E # Žž U+01B7 # Ʒ U+01F4..U+01F5 # Ǵǵ U+021E..U+021F # Ȟȟ U+0292 # ʒ U+0398 # Θ U+03B8 # θ $cyrillic } tkr = { # Tsakhur $cyrillic $iso_8859_1 U+011E..U+011F # Ğğ U+0130..U+0131 # İı U+015E..U+015F # Şş U+0361 # combining double inverted breve $apostrophes } yah = { # Yazghulami $cyrillic_we U+0100..U+0101 # Āā U+010C..U+010D # Čč U+0394 # Δ U+03B4 # δ U+018F # Ə U+0259 # ə U+01F4..U+01F5 # Ǵǵ U+0263..U+0264 # ɣɤ U+03B3 # γ U+01F0 # ǰ U+1E30..U+1E31 # Ḱḱ U+0160..U+0161 # Šš U+0398 # Θ U+03B8 # θ U+03D1 # ϑ U+016F # Ů U+016F # ů U+017D..U+017E # Žž U+02DA # ˚ } yai = { # Yaghnobi $cyrillic_we $iso_8859_1 U+010C..U+010D # Čč U+012A..U+012B # Īī U+0160..U+0161 # Šš U+016A..U+016B # Ūū U+017D..U+017E # Žž U+0194 # Ɣ U+01F0 # ǰ U+0263 # ɣ U+028F # ʏ U+1E24..U+1E25 # Ḥḥ } #--------------------------------------------------------------------# # # Languages using Armenian script # $armenian = { $common U+0530..U+058F # Armenian Unicode block U+FB13..U+FB17 # Armenian ligatures U+058F # ֏ } hy = $armenian # Armenian hyw = hy # Western Armenian #--------------------------------------------------------------------# # # Languages using Hebrew script # $hebrew = { $common U+0590..U+05FF # Hebrew Unicode block U+FB1D..U+FB4F # Hebrew ligatures } he = $hebrew # Hebrew yi = $hebrew # Yiddish ydd = yi # Eastern Yiddish yih = yi # Western Yiddish apc = $hebrew # North Levantine (also Arabic) ajp = $hebrew # South Levantine (also Arabic) jpr = $hebrew # Judeo-Persian jrb = $hebrew # Judeo-Arabic lad = $hebrew # Judeo-Spanish (also other scripts) jdt = { # Judeo-Tat/Juhuri ttt # Latin, Cyrillic U+0126..U+0127 # Ħħ U+1E28..U+1E29 # Ḩḩ $hebrew } #--------------------------------------------------------------------# # Embedding a single glyph per code point won't work for Arabic script. # Embedding a single glyph per code point won't work for Syriac script. #--------------------------------------------------------------------# # # Languages using Thaana script # $thaana = $common U+0780..U+07BF dv = $thaana # Divehi #--------------------------------------------------------------------# # # Languages using NKo script (probably) # $nko = $common U+07C0..U+07FF $nko_and_latin = { $nko U+014A..U+014B # Ŋŋ U+0186 # Ɔ U+0190 # Ɛ U+019D # Ɲ U+0254 # ɔ U+025B # ɛ U+0272 # ɲ } nqo = $nko # N'Ko man = $nko_and_latin # Manding # Manding-East: bm = $nko_and_latin # Bambara bof = $nko_and_latin # Bolon dyu = $nko_and_latin # Dyula rkm = $nko_and_latin # Marka # Manding-West: jad = $nko_and_latin # Jahanka kao = $nko_and_latin # Kassonke mlq = $nko_and_latin # Western Malinke mnk = $nko_and_latin # Mandinka mku = $nko_and_latin # Konyanka emk = $nko_and_latin # Eastern Maninkaka msc = $nko_and_latin # Sankaran Maninkaka mzj = $nko_and_latin # Manya jod = $nko_and_latin # Wojenaka jud = $nko_and_latin # Worodougou kfo = $nko_and_latin # Koro kga = $nko_and_latin # Koyaga mxx = $nko_and_latin # Mahou mwk = $nko_and_latin # Kita Maninka xkg = $nko_and_latin # Kagoro # Unclear: skq = $nko_and_latin # Sininkere #--------------------------------------------------------------------# # # Languages using Samaritan script # $samaritan = $common U+0800..U+083F smp = $samaritan # Samaritan Hebrew sam = $samaritan # Samaritan Aramaic #--------------------------------------------------------------------# # # Languages using Mandaic script # $mandaic = $common U+0840..U+085F mid = $mandaic # Mandaic myz = $mandaic # Classical Mandaic #--------------------------------------------------------------------# # Embedding a single glyph per code point won't work for Indic scripts: # Devanagari # Bengali # Gurmukhi # Gujarati # Oriya # Tamil # Telugu # Kannada # Malayalam # Sinhala #--------------------------------------------------------------------# # # Languages using Thai script # $thai = $common U+0E00..U+0E7F th = $thai # Thai sou = $thai # Southern Thai # Northern Thai (below) # Isan (below) mfa = $thai # Kelantan-Pattani Malay (also Latin) #--------------------------------------------------------------------# # # Languages using Lao script # $lao = $common U+0E80..U+0EFF lo = $lao # Lao kjg = $lao # Khmu khf = $lao # Buddhist Kmhmu #--------------------------------------------------------------------# # # Languages using Tibetan script (possibly) # $tibetan = $common U+0F00..U+0FFF # Central Tibetan: bo = $tibetan # Lhasa Tibetan / Standard Tibetan dre = $tibetan # Dolpo hut = $tibetan # Humla, Limi lhm = $tibetan # Lhomi (Shing Saapa) muk = $tibetan # Mugom (Mugu) ola = $tibetan # Walungge (Gola) loy = $tibetan # Lowa/Loke (Mustang) tcn = $tibetan # Tichurong # Amdo: adx = $tibetan # Amdo Tibetan # Gserpa (missing code) # Khalong (missing code) # Kham (Eastern): khg = $tibetan # Khams kbg = khg # Khamba tsk = khg # Tseku bqh = $tibetan # Baima cda = $tibetan # Choni # Zhongu (missing code) # Dongwang (missing code) # Drugchu (missing code) # Zitsadegu (missing code) # Southern: sip = $tibetan # Sikkimese dz = $tibetan # Dzongkha (Bhutanese) lya = dz # Laya luk = dz # Lunana adp = dz # Adap gro = $tibetan # Groma bro = $tibetan # Brokkat sgt = $tibetan # Brokpa cgk = $tibetan # Chochangachakha lkh = $tibetan # Lakha nao = $tibetan # Naapa # Ladakhi-Balti: lbj = $tibetan # Ladakhi zau = $tibetan # Zangskari cna = $tibetan # Changthang bft = $tibetan # Balti (mainly Perso-Arabic) prx = $tibetan # Purgi (also Perso-Arabic) # Lahuli-Spiti: sbu = $tibetan # Lahuli (Stod Bhoti) spt = $tibetan # Spiti Bhoti nes = $tibetan # Bhoti Kinnauri / Nyamkat tqp = $tibetan # Tukpa # Sherpa-Jirel: xsr = $tibetan # Sherpa jul = $tibetan # Jirel # Kyirong–Kagate: kgy = $tibetan # Kyirong syw = $tibetan # Kagate ttz = $tibetan # Tsum scp = $tibetan # Yolmo kte = $tibetan # Nubri gyo = $tibetan # Gyalsumdo # Tshangla: tsj = $tibetan # Tshangla kkf = $tibetan # Kalaktang Monpa # East Bodish: dka = $tibetan # Dakpa twm = $tibetan # Tawang Monpa dzl = $tibetan # Dzala neh = $tibetan # Nyen tgf = $tibetan # Chali kjz = $tibetan # Bumthang xkf = $tibetan # Kheng xkz = $tibetan # Kurtöp npb = $tibetan # Nupbi ole = $tibetan # 'Ole # Basum: # Basum (missing code) # Tamangic: taj = $tibetan # Eastern Tamang tdg = $tibetan # Western Tamang tmk = $tibetan # Northwestern Tamang tge = $tibetan # Eastern Gorkha Tamang gvr = $tibetan # Gurung ths = $tibetan # Thakali skj = $tibetan # Seke nmm = $tibetan # Manang chx = $tibetan # Chantyal ghh = $tibetan # Northern Ghale ghe = $tibetan # Southern Ghale ght = $tibetan # Kutang kzq = $tibetan # Kaike #--------------------------------------------------------------------# # # Languages using scripts in the Myanmar block # $myanmar = $common U+1000..U+109F my = $myanmar # Burmese int = my # Intha dnv = my # Danu tvn = my # Tavoyan dialects tco = my # Taungyo dialects rki = my # Rakhine language rmz = my # Marma shn = $myanmar # Shan kar = $myanmar # Karen (many more) pdu = $myanmar # Padaung kac = $myanmar # Jingpho sgp = $myanmar # Singpho tcl = $myanmar # Taman mnw = $myanmar # Modern Mon omx = $myanmar # Old Mon #--------------------------------------------------------------------# # # Languages using Georgian script # $georgian = { $common U+10A0..U+10FF # Georgian Unicode block U+2D00..U+2D2F # Georgian Supplement U+1C90..U+1CBF # Georgian Extended U+20BE # ₾ } ka = $georgian # Georgian #--------------------------------------------------------------------# # # Languages using Hangul script # $hangul = { $common U+1100..U+11FF # Hangul Jamo U+3130..U+318F # Hangul Compatibility Jamo U+AC00..U+D7AF # Hangul Syllables U+20A9 # ₩ } ko = $hangul # Korean #--------------------------------------------------------------------# # # Languages using Ethiopic scripts (possibly) # $ethiopic = { $common U+1200..U+137F # Ethiopic Unicode block U+1380..U+139F # Ethiopic Supplement U+2D80..U+2DDF # Ethiopic Extended U+AB00..U+AB2F # Ethiopic Extended-A U+1E7E0..U+1E7FF # Ethiopic Extended-B } # Ethiosemitic: am = $ethiopic # Amharic (Ge'ez) agj = $ethiopic # Argobba gez = $ethiopic # Ge'ez (Ge'ez) har = $ethiopic # Harari (Ge'ez) ior = $ethiopic # Inor mvz = $ethiopic # Mesqan # Muher (missing code) sgw = $ethiopic # Sebat Bet Gurage (Ge'ez) stv = $ethiopic # Silt'e wle = $ethiopic # Wolane gru = $ethiopic # Soddo (Kistane) ti = $ethiopic # Tigrinya (Ge'ez) tig = $ethiopic # Tigre (Ge'ez) zwa = $ethiopic # Zay (Ge'ez) # Cusitic: aa = $ethiopic # Afar (Ge'ez, Latin) gwd = $ethiopic # Ale (Ethiopic) arv = $ethiopic # Arbore awn = $ethiopic # Awngi bsw = $ethiopic # Baiso byn = $ethiopic # Bilen (Ge'ez) dox = $ethiopic # Bussa bji = $ethiopic # Burji (Ethiopic) # Daasanach (Latin) gdl = $ethiopic # Dirasha drs = $ethiopic # Gedeo hdy = $ethiopic # Hadiyya (Latin, Ge'ez) ktb = $ethiopic # Kambaata (Ethiopic, Latin) alw = $ethiopic # Kambaata, Alaba-K'abeena (Ethiopic, Latin) kxc = $ethiopic # Konso (Ethiopic) liq = $ethiopic # Libido # Oromo (Latin) ahg = $ethiopic # Qimant ssy = $ethiopic # Saho sid = $ethiopic # Sidama # Somali (Latin, Arabic) tsb = $ethiopic # Tsamai xan = $ethiopic # Xamtanga # Omotic: aiw = $ethiopic # Aari myo = $ethiopic # Anfillo myf = $ethiopic # Bambassi bst = $ethiopic # Basketo bcq = $ethiopic # Bench bwo = $ethiopic # Shinasha cra = $ethiopic # Chara dim = $ethiopic # Dime mdx = $ethiopic # Dizin doz = $ethiopic # Dorze gmv = $ethiopic # Gamo (Ethiopic, Latin) gof = $ethiopic # Gofa (Ethiopic, Latin) dwr = $ethiopic # Dawro (Ethiopic, Latin) gza = $ethiopic # Ganza gyl = $ethiopic # Gayil amf = $ethiopic # Hamer hoz = $ethiopic # Hozo kcx = $ethiopic # Kachama-Ganjule kbr = $ethiopic # Kafa kxh = $ethiopic # Karo kqy = $ethiopic # Koore (Ethiopic, Latin) mdy = $ethiopic # Maale (Ethiopic) mfx = $ethiopic # Melo noz = $ethiopic # Nayi oyd = $ethiopic # Oyda sze = $ethiopic # Seze moy = $ethiopic # Shakacho (Ethiopic, Latin) she = $ethiopic # Sheko # Wolaitta (Latin) jnj = $ethiopic # Yem (Ethiopic, Latin) zay = $ethiopic # Zayse-Zergulla (Ethiopic) # Nil-Saharan: anu = $ethiopic # Anuak wti = $ethiopic # Berta dtn = $ethiopic # Daats'iin guk = $ethiopic # Gumuz (Ethiopic, Latin) koe = $ethiopic # Baale xom = $ethiopic # Komo kmq = $ethiopic # Kwama xwg = $ethiopic # Kwegu mpe = $ethiopic # Majang mym = $ethiopic # Me'en (was Ge'ez, Latin) # Murle (Latin) muz = $ethiopic # Mursi (Ethiopic) # Nuer (Latin) nnj = $ethiopic # Nyangatom lgn = $ethiopic # Opuo sbf = $ethiopic # Shabo # Suri (Latin) # Uduk (Latin) #--------------------------------------------------------------------# # # Languages using Cherokee script # $cherokee = { $common U+13A0..U+13FF # Cherokee Unicode block U+AB70..U+ABBF # Cherokee Supplement } chr = $cherokee # Cherokee #--------------------------------------------------------------------# # # Languages using Canadian Aboriginal scripts # $canadian_aboriginal = { $common U+1400..U+167F # Unified Canadian Aboriginal Syllabics U+18B0..U+18FF # Unified Canadian Aboriginal Syllabics Extended } alg = $canadian_aboriginal # Algonquian: cr = $canadian_aboriginal # Cree crk = cr # Plains Cree cwd = cr # Woods Cree csw = cr # Swampy Cree crm = cr # Moose Cree crl = cr # Northern East Cree crj = cr # Southern East Cree nsk = cr # Naskapi moe = cr # Montagnais atj = cr # Atikamekw oj = $canadian_aboriginal # Ojibwe/Chippewa ojs = oj # Severn Ojibwa ojg = oj # Eastern Ojibwa ojc = oj # Central Ojibwa ojb = oj # Northwestern Ojibwa ojw = oj # Western Ojibwa otw = oj # Ottawa alq = oj # Algonquin ciw = oj # Chippewa bla = $canadian_aboriginal # Blackfoot (Siksika) esx = $canadian_aboriginal # Eskimo-Aleut: iu = $canadian_aboriginal # Inuktitut (also Latin) ike = iu # Eastern Canadian Inuktitut ikt = iu # Inuinnaqtun ath = $canadian_aboriginal # Athabaskan: bea = $canadian_aboriginal # Dane-zaa den = $canadian_aboriginal # Slavey scs = den # North Slavey xsl = den # South Slavey chp = $canadian_aboriginal # Chipewyan crx = $canadian_aboriginal # Carrier caf = crx # Southern Carrier sek = $canadian_aboriginal # Sekani #--------------------------------------------------------------------# # # Languages using Hanunoo script # $hanunoo = $common U+1720..U+173F hnn = $hanunoo # Hanunoo #--------------------------------------------------------------------# # # Languages using Buhid script # $buhid = $common U+1740..U+175F bku = $buhid # Buhid #--------------------------------------------------------------------# # # Languages using Tagbanwa script # $tagbanwa = $common U+1760..U+177F tbw = $tagbanwa # Aborlan Tagbanwa tbk = $tagbanwa # Calamian Tagbanwa tgt = $tagbanwa # Central Tagbanwa #--------------------------------------------------------------------# # # Languages using Khmer script # $khmer = { $common U+1780..U+17FF # Khmer U+19E0..U+19FF # Khmer Symbols } km = $khmer # Central Khmer kxm = $khmer # Northern Khmer jra = $khmer # Jarai #--------------------------------------------------------------------# # # Languages using Limbu script # $limbu = $common U+1900..U+194F lif = $limbu # Limbu #--------------------------------------------------------------------# # # Languages using Tai Le script # $tai_le = $common U+1950..U+197F tdd = $tai_le # Tai Nüa thi = $tai_le # Tai Long pll = $myanmar $tai_le # Palaung, Shwe pce = $myanmar $tai_le # Palaung, Ruching rbb = $myanmar $tai_le # Palaung, Rumai blr = $tai_tham $tai_le # Blang stu = $tai_tham $tai_le # Samtao #--------------------------------------------------------------------# # # Languages using New Tai Lue script # $new_tai_lue = $common U+1980..U+19DF khb = $thai $tai_tham $new_tai_lue # Tai Lue #--------------------------------------------------------------------# # # Languages using Buginese (Lontara) script # $buginese = $common U+1A00..U+1A1F bug = $buginese # Buginese mak = $buginese # Makassarese bhp = $buginese # Bima end = $buginese # Ende mdr = $buginese # Mandar smw = $buginese # Sumbawa #--------------------------------------------------------------------# # # Languages using Tai Tham script # $tai_tham = $common U+1A20..U+1AAF nod = $tai_tham $thai $lao # Northern Thai kkh = $tai_tham $thai # Khün tts = $tai_tham $thai # Isan #--------------------------------------------------------------------# # # Languages using Balinese script # $balinese = $common U+1B00..U+1B7F ban = $balinese # Balinese (mostly Latin) sas = $balinese # Sasak #--------------------------------------------------------------------# # # Languages using Sundanese script # $sundanese = { $common U+1B80..U+1BBF # Sundanese U+1CC0..U+1CCF # Sundanese Supplement } su = $sundanese # Sundanese bac = su # Baduy Sundanese #--------------------------------------------------------------------# # # Languages using Batak script # $batak = $common U+1BC0..U+1BFF btk = $batak # Batak languages btd = btk # Pakpak (Dairi) btx = btk # Karo btz = btk # Alas bts = btk # Simalungun bbc = btk # Toba Batak akb = btk # Angkola btm = btk # Mandailing #--------------------------------------------------------------------# # # Languages using Lepcha script # $lepcha = $common U+1C00..U+1C4F lep = $lepcha # Lepcha #--------------------------------------------------------------------# # # Languages using Ol Chiki script # $ol_chiki = $common U+1C50..U+1C7F sat = $ol_chiki # Santali mjx = $ol_chiki # Mahali #--------------------------------------------------------------------# # # Languages using Coptic script # $coptic = { $common U+0300..U+036F # Combining Diacritical Marks U+0370..U+03FF # Greek and Coptic U+2C80..U+2CFF # Coptic } cop = $coptic # Coptic #--------------------------------------------------------------------# # # Languages using Tifinagh script # $tifinagh = $common U+2D30..U+2D7F $berber_latin = { $common $common_marks U+00C2 #  U+00C4 # Ä U+00CA # Ê U+00CE # Î U+00D0..U+00D1 # ÐÑ U+00D4 # Ô U+00DB # Û U+00E2 # â U+00E4 # ä U+00EA # ê U+00EE # î U+00F0..U+00F1 # ðñ U+00F4 # ô U+00FB # û U+0100..U+0101 # Āā U+0102..U+0103 # Ăă U+010C..U+010D # Čč U+0120..U+0121 # Ġġ U+012A..U+012B # Īī U+014A..U+014B # Ŋŋ U+0158..U+0159 # Řř U+0160..U+0161 # Šš U+0162..U+0163 # Ţţ U+016A..U+016B # Ūū U+017D..U+017E # Žž U+018E..U+018F # ƎƏ U+0190 # Ɛ U+0194 # Ɣ U+01DD # ǝ U+01E6..U+01E7 # Ǧǧ U+01F0 # ǰ U+0259 # ə U+025B # ɛ U+0263 # ɣ U+0294..U+0295 # ʔʕ U+0393 # Γ U+0398 # Θ U+03B3 # γ U+03B8 # θ U+1E04..U+1E05 # Ḅḅ U+1E0C..U+1E0D # Ḍḍ U+1E24..U+1E25 # Ḥḥ U+1E32..U+1E33 # Ḳḳ U+1E36..U+1E37 # Ḷḷ U+1E42..U+1E43 # Ṃṃ U+1E46..U+1E47 # Ṇṇ U+1E5A..U+1E5B # Ṛṛ U+1E62..U+1E63 # Ṣṣ U+1E6C..U+1E6D # Ṭṭ U+1E88..U+1E89 # Ẉẉ U+1E92..U+1E93 # Ẓẓ U+0320 # combining minus sign below U+0331..U+0332 # macron below, low line } ber = $tifinagh $berber_latin # Berber languages mzb = ber # Mozabite rif = ber # Riffian shy = ber # Shawiya tzm = ber # Central Atlas Tamazight shi = ber # Shilha kab = ber # Kabyle tmh = ber # Tuareg thv = ber # Tamahaq taq = ber # Tamasheq zen = ber # Zenaga zgh = ber # Standard Moroccan Tamazight #--------------------------------------------------------------------# # # Languages using Yi script # $yi = { $common U+A000..U+A48F # Yi Syllables U+A490..U+A4CF # Yi Radicals } ii = $yi # Northern Yi (Nuosu) # Western Yi (Lalo) - no writing system listed # Central Yi (Lolopo): ycl = $yi # Lolopo ysp = $yi # Southern Lolopo # Southern Yi (Nisu): nsd = $yi # Nisu, Southern yiv = $yi # Nisu, Northern nos = $yi # Nisu, Eastern nsv = $yi # Nisu, Southwestern nsf = $yi # Nisu, Northwestern # Southeastern Yi (Sani) - no writing system listed # Eastern Yi (Nasu): ywq = $yi # Nasu (Wulu) ygp = $yi # Gepo (Köpu) yig = $yi # Wusa Nasu ywu = $yi # Wumeng Nasu nty = $yi # Mantsi #--------------------------------------------------------------------# # # Languages using Lisu script # $lisu = $common U+A4D0..U+A4FF lis = $lisu # Lisu #--------------------------------------------------------------------# # # Languages using Vai script # $vai = $common U+A500..U+A63F vai = $vai # Vai #--------------------------------------------------------------------# # # Languages using Bamum script # $bamum = $common U+A6A0..U+A6FF bax = $bamum # Bamum #--------------------------------------------------------------------# # # Languages using Syloti Nagri script # $syloti_nagri = $common U+A800..U+A82F syl = $syloti_nagri # Sylheti #--------------------------------------------------------------------# # # Languages using Kayah Li script # $kayah_li = $common U+A900..U+A92F eky = $kayah_li # Eastern Kayah kyu = $kayah_li # Western Kayah kvy = $kayah_li # Yintale (unwritten?) #--------------------------------------------------------------------# # # Languages using Javanese script # $javanese = $common U+A980..U+A9DF jv = $javanese # Javanese jvn = jv # Caribbean Javanese jas = jv # New Caledonian Javanese osi = jv # Osing tes = jv # Tenggerese kaw = jv # Kawi mad = { # Madurese $common $common_marks U+00C2 #  U+00C8 # È U+00D1 # Ñ U+00E2 # â U+00E8 # è U+00F1 # ñ U+1E0C..U+1E0D # Ḍḍ U+1E46..U+1E47 # Ṇṇ U+1E6C..U+1E6D # Ṭṭ $javanese } #--------------------------------------------------------------------# # # Languages using Cham script # $cham = $common U+AA00..U+AA5F cja = $cham # Western Cham cjm = $cham # Eastern Cham #--------------------------------------------------------------------# # # Languages using Tai Viet script # $tai_viet = $common U+AA80..U+AADF blt = $tai_viet # Tai Dam tyr = $tai_viet # Tai Daeng twh = $tai_viet # Tai Dón soa = $thai $tai_viet # Thai Song tyt = $tai_viet # Tày Tac #--------------------------------------------------------------------# # # Languages using Meetei Mayek script # $meetei_mayek = $common U+ABC0..U+ABFF mni = $meetei_mayek # Meitei #--------------------------------------------------------------------#