[wip] breaking text into bidi runs. Extract script info from unicode …

…character database.
orca-app · Nov 5, 2024 · 0d5788c · 0d5788c
1 parent b981751
commit 0d5788c
Show file tree

Hide file tree

Showing 8 changed files with 4,493 additions and 9 deletions.
diff --git a/scripts/dev.py b/scripts/dev.py
@@ -567,6 +567,9 @@ def build_fribidi(release=False):
             ], check=True)
 
             # build native
+            ############################################################
+            #TODO: sort out what we should do on Windows
+            ############################################################
             subprocess.run([
                 "./autogen.sh"
             ], check=True)

diff --git a/scripts/gen_unicode_scripts_tables.py b/scripts/gen_unicode_scripts_tables.py
@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+
+import os
+import re
+import csv
+from argparse import ArgumentParser
+
+parser = ArgumentParser(prog='gen_unicode_scripts_tables.py')
+parser.add_argument('--scripts', required=True)
+parser.add_argument('--iso', required=True)
+parser.add_argument('--out', required=True)
+
+args = parser.parse_args()
+
+with open(args.iso, "r") as f:
+    reader = csv.reader(f, delimiter=';')
+    iso = list(reader)
+
+iso = [line for line in iso if len(line) > 0 and not line[0].startswith('#') ]
+
+with open(args.scripts, "r") as f:
+    data = f.read()
+
+entries = re.findall(r'^([0-9A-Fa-f]{3,5})(\.\.([0-9A-Fa-f]{3,5}))?[ ]*; ([^ ]*) \#.*', data, re.MULTILINE)
+
+table = []
+
+for entry in entries:
+    s = entry[0]
+    e = entry[0] if entry[2] == '' else entry[2]
+    name = entry[3]
+    spaceName = name.replace('_', ' ')
+    hyphenName = name.replace('_', '-')
+
+    tag = ''
+    for line in iso:
+        if name == line[4] or name == line[2] or spaceName == line[4] or spaceName == line[2] or hyphenName == line[4] or hyphenName == line[2]:
+            tag = line[0]
+
+    if tag == '':
+        print(f"Couldn't find iso15924 for unicode script {name}")
+        exit(-1)
+
+    table.append((int(s, 16), int(e, 16), name, tag))
+
+# sort the table by range start and collate ranges
+table.sort()
+
+newTable = []
+currentStart = table[0][0]
+currentName = table[0][2]
+currentScript = table[0][3]
+
+for line in table:
+    if line[3] != currentScript:
+        newTable.append((currentStart, line[0]-1, currentName, currentScript))
+        currentStart = line[0]
+        currentName = line[2]
+        currentScript = line[3]
+
+newTable.append((currentStart, table[len(table)-1][1], currentName, currentScript))
+
+table = newTable
+
+with open(args.out, "w") as f:
+    inputName = os.path.basename(args.out)
+
+    print("/*********************************************************************", file=f)
+    print("*", file=f)
+    print("*  Orca", file=f)
+    print("*  Copyright 2023 Martin Fouilleul and the Orca project contributors", file=f)
+    print("*  See LICENSE.txt for licensing information", file=f)
+    print("*", file=f)
+    print(f"*  Unicode script tables generated by gen_unicode_scripts_tables.py from {inputName}", file=f)
+    print("*", file=f)
+    print("**********************************************************************/", file=f)
+    print("#ifndef __UNICODE_SCRIPTS_TABLE_H_", file=f)
+    print("#define __UNICODE_SCRIPTS_TABLE_H_", file=f)
+    print("", file=f)
+
+    print("#include \"util/typedefs.h\"", file=f)
+    print("#include \"util/macros.h\"", file=f)
+    print("", file=f)
+
+    print("#define OC_UNICODE_SCRIPTS(_) \\", file=f)
+    for line in table:
+        print(f"    _({line[2].upper()}, {hex(line[0])}, {hex(line[1])}, {line[3]}) \\", file=f)
+    print("", file=f)
+
+    print("typedef enum {", file=f)
+    print("#define X(name, ...) OC_CAT2(OC_UNICODE_SCRIPT_, name),", file=f)
+    print("    OC_UNICODE_SCRIPTS(X)", file=f)
+    print("#undef X", file=f)
+    print("} oc_unicode_script;", file=f)
+    print("", file=f);
+
+    print("typedef struct oc_unicode_script_range {", file=f)
+    print("    u64 start;", file=f)
+    print("    u64 end;", file=f)
+    print("    oc_unicode_script script;", file=f)
+    print("    oc_str8 tag;", file=f)
+    print("} oc_unicode_script_range;", file=f)
+    print("", file=f)
+
+    print("static const oc_unicode_script_range OC_UNICODE_SCRIPT_RANGES[] = {", file=f)
+
+    for line in table:
+        print(f"    {{ {hex(line[0])}, {hex(line[1])}, OC_UNICODE_SCRIPT_{line[2].upper()}, OC_STR8_LIT(\"{line[3]}\") }},", file=f)
+
+    print("};", file=f)
+
+    print("", file=f)
+    print("enum {", file=f)
+    print(f"    OC_UNICODE_SCRIPT_RANGE_COUNT = {len(table)},", file=f)
+    print("};", file=f)
+    print("", file=f)
+
+    print("#endif // __UNICODE_SCRIPTS_TABLE_H_", file=f)
diff --git a/scripts/iso15924.txt b/scripts/iso15924.txt
@@ -0,0 +1,230 @@
+#
+# ISO 15924 - Codes for the representation of names of scripts
+#             Codes pour la représentation des noms d’écritures
+# Format:
+#             Code;N°;English Name;Nom français;PVA;Unicode Version;Date
+#
+
+Adlm;166;Adlam;adlam;Adlam;9.0;2016-12-05
+Afak;439;Afaka;afaka;;;2010-12-21
+Aghb;239;Caucasian Albanian;aghbanien;Caucasian_Albanian;7.0;2014-11-15
+Ahom;338;Ahom, Tai Ahom;âhom;Ahom;8.0;2015-07-07
+Arab;160;Arabic;arabe;Arabic;1.1;2004-05-01
+Aran;161;Arabic (Nastaliq variant);arabe (variante nastalique);;1.1;2014-11-15
+Armi;124;Imperial Aramaic;araméen impérial;Imperial_Aramaic;5.2;2009-06-01
+Armn;230;Armenian;arménien;Armenian;1.1;2004-05-01
+Avst;134;Avestan;avestique;Avestan;5.2;2009-06-01
+Bali;360;Balinese;balinais;Balinese;5.0;2006-10-10
+Bamu;435;Bamum;bamoum;Bamum;5.2;2009-06-01
+Bass;259;Bassa Vah;bassa;Bassa_Vah;7.0;2014-11-15
+Batk;365;Batak;batak;Batak;6.0;2010-07-23
+Beng;325;Bengali (Bangla);bengalî (bangla);Bengali;1.1;2016-12-05
+Bhks;334;Bhaiksuki;bhaïksukî;Bhaiksuki;9.0;2016-12-05
+Blis;550;Blissymbols;symboles Bliss;;;2004-05-01
+Bopo;285;Bopomofo;bopomofo;Bopomofo;1.1;2004-05-01
+Brah;300;Brahmi;brahma;Brahmi;6.0;2010-07-23
+Brai;570;Braille;braille;Braille;3.0;2004-05-01
+Bugi;367;Buginese;bouguis;Buginese;4.1;2006-06-21
+Buhd;372;Buhid;bouhide;Buhid;3.2;2004-05-01
+Cakm;349;Chakma;chakma;Chakma;6.1;2012-02-06
+Cans;440;Unified Canadian Aboriginal Syllabics;syllabaire autochtone canadien unifié;Canadian_Aboriginal;3.0;2004-05-29
+Cari;201;Carian;carien;Carian;5.1;2007-07-02
+Cham;358;Cham;cham (čam, tcham);Cham;5.1;2009-11-11
+Cher;445;Cherokee;tchérokî;Cherokee;3.0;2004-05-01
+Chis;298;Chisoi;chisoi;;;2023-09-12
+Chrs;109;Chorasmian;chorasmien;Chorasmian;13.0;2019-08-19
+Cirt;291;Cirth;cirth;;;2004-05-01
+Copt;204;Coptic;copte;Coptic;4.1;2006-06-21
+Cpmn;402;Cypro-Minoan;syllabaire chypro-minoen;Cypro_Minoan;14.0;2017-07-26
+Cprt;403;Cypriot syllabary;syllabaire chypriote;Cypriot;4.0;2017-07-26
+Cyrl;220;Cyrillic;cyrillique;Cyrillic;1.1;2004-05-01
+Cyrs;221;Cyrillic (Old Church Slavonic variant);cyrillique (variante slavonne);;1.1;2004-05-01
+Deva;315;Devanagari (Nagari);dévanâgarî;Devanagari;1.1;2004-05-01
+Diak;342;Dives Akuru;dives akuru;Dives_Akuru;13.0;2019-08-19
+Dogr;328;Dogra;dogra;Dogra;11.0;2016-12-05
+Dsrt;250;Deseret (Mormon);déseret (mormon);Deseret;3.1;2004-05-01
+Dupl;755;Duployan shorthand, Duployan stenography;sténographie Duployé;Duployan;7.0;2014-11-15
+Egyd;070;Egyptian demotic;démotique égyptien;;;2004-05-01
+Egyh;060;Egyptian hieratic;hiératique égyptien;;5.2;2004-05-01
+Egyp;050;Egyptian hieroglyphs;hiéroglyphes égyptiens;Egyptian_Hieroglyphs;5.2;2009-06-01
+Elba;226;Elbasan;elbasan;Elbasan;7.0;2014-11-15
+Elym;128;Elymaic;élymaïque;Elymaic;12.0;2018-08-26
+Ethi;430;Ethiopic (Geʻez);éthiopien (geʻez, guèze);Ethiopic;3.0;2004-10-25
+Gara;164;Garay;garay;;;2023-09-12
+Geok;241;Khutsuri (Asomtavruli and Nuskhuri);khoutsouri (assomtavrouli et nouskhouri);Georgian;1.1;2012-10-16
+Geor;240;Georgian (Mkhedruli and Mtavruli);géorgien (mkhédrouli et mtavrouli);Georgian;1.1;2016-12-05
+Glag;225;Glagolitic;glagolitique;Glagolitic;4.1;2006-06-21
+Gong;312;Gunjala Gondi;gunjala gondî;Gunjala_Gondi;11.0;2016-12-05
+Gonm;313;Masaram Gondi;masaram gondî;Masaram_Gondi;10.0;2017-07-26
+Goth;206;Gothic;gotique;Gothic;3.1;2004-05-01
+Gran;343;Grantha;grantha;Grantha;7.0;2014-11-15
+Grek;200;Greek;grec;Greek;1.1;2004-05-01
+Gujr;320;Gujarati;goudjarâtî (gujrâtî);Gujarati;1.1;2004-05-01
+Gukh;397;Gurung Khema;gurung khema;;;2023-09-12
+Guru;310;Gurmukhi;gourmoukhî;Gurmukhi;1.1;2004-05-01
+Hanb;503;Han with Bopomofo (alias for Han + Bopomofo);han avec bopomofo (alias pour han + bopomofo);;1.1;2016-01-19
+Hang;286;Hangul (Hangŭl, Hangeul);hangûl (hangŭl, hangeul);Hangul;1.1;2004-05-29
+Hani;500;Han (Hanzi, Kanji, Hanja);idéogrammes han (sinogrammes);Han;1.1;2009-02-23
+Hano;371;Hanunoo (Hanunóo);hanounóo;Hanunoo;3.2;2004-05-29
+Hans;501;Han (Simplified variant);idéogrammes han (variante simplifiée);;1.1;2004-05-29
+Hant;502;Han (Traditional variant);idéogrammes han (variante traditionnelle);;1.1;2004-05-29
+Hatr;127;Hatran;hatrénien;Hatran;8.0;2015-07-07
+Hebr;125;Hebrew;hébreu;Hebrew;1.1;2004-05-01
+Hira;410;Hiragana;hiragana;Hiragana;1.1;2004-05-01
+Hluw;080;Anatolian Hieroglyphs (Luwian Hieroglyphs, Hittite Hieroglyphs);hiéroglyphes anatoliens (hiéroglyphes louvites, hiéroglyphes hittites);Anatolian_Hieroglyphs;8.0;2015-07-07
+Hmng;450;Pahawh Hmong;pahawh hmong;Pahawh_Hmong;7.0;2014-11-15
+Hmnp;451;Nyiakeng Puachue Hmong;nyiakeng puachue hmong;Nyiakeng_Puachue_Hmong;12.0;2017-07-26
+Hrkt;412;Japanese syllabaries (alias for Hiragana + Katakana);syllabaires japonais (alias pour hiragana + katakana);Katakana_Or_Hiragana;1.1;2011-06-21
+Hung;176;Old Hungarian (Hungarian Runic);runes hongroises (ancien hongrois);Old_Hungarian;8.0;2015-07-07
+Inds;610;Indus (Harappan);indus;;;2004-05-01
+Ital;210;Old Italic (Etruscan, Oscan, etc.);ancien italique (étrusque, osque, etc.);Old_Italic;3.1;2004-05-29
+Jamo;284;Jamo (alias for Jamo subset of Hangul);jamo (alias pour le sous-ensemble jamo du hangûl);;1.1;2016-01-19
+Java;361;Javanese;javanais;Javanese;5.2;2009-06-01
+Jpan;413;Japanese (alias for Han + Hiragana + Katakana);japonais (alias pour han + hiragana + katakana);;1.1;2006-06-21
+Jurc;510;Jurchen;jurchen;;;2010-12-21
+Kali;357;Kayah Li;kayah li;Kayah_Li;5.1;2007-07-02
+Kana;411;Katakana;katakana;Katakana;1.1;2004-05-01
+Kawi;368;Kawi;kawi;Kawi;15.0;2021-12-03
+Khar;305;Kharoshthi;kharochthî;Kharoshthi;4.1;2006-06-21
+Khmr;355;Khmer;khmer;Khmer;3.0;2004-05-29
+Khoj;322;Khojki;khojkî;Khojki;7.0;2014-11-15
+Kitl;505;Khitan large script;grande écriture khitan;;;2015-07-15
+Kits;288;Khitan small script;petite écriture khitan;Khitan_Small_Script;13.0;2015-07-15
+Knda;345;Kannada;kannara (canara);Kannada;1.1;2004-05-29
+Kore;287;Korean (alias for Hangul + Han);coréen (alias pour hangûl + han);;1.1;2007-06-13
+Kpel;436;Kpelle;kpèllé;;;2010-03-26
+Krai;396;Kirat Rai;kirat rai;;;2023-09-12
+Kthi;317;Kaithi;kaithî;Kaithi;5.2;2009-06-01
+Lana;351;Tai Tham (Lanna);taï tham (lanna);Tai_Tham;5.2;2009-06-01
+Laoo;356;Lao;laotien;Lao;1.1;2004-05-01
+Latf;217;Latin (Fraktur variant);latin (variante brisée);;1.1;2004-05-01
+Latg;216;Latin (Gaelic variant);latin (variante gaélique);;1.1;2004-05-01
+Latn;215;Latin;latin;Latin;1.1;2004-05-01
+Leke;364;Leke;léké;;;2015-07-07
+Lepc;335;Lepcha (Róng);lepcha (róng);Lepcha;5.1;2007-07-02
+Limb;336;Limbu;limbou;Limbu;4.0;2004-05-29
+Lina;400;Linear A;linéaire A;Linear_A;7.0;2014-11-15
+Linb;401;Linear B;linéaire B;Linear_B;4.0;2004-05-29
+Lisu;399;Lisu (Fraser);lisu (Fraser);Lisu;5.2;2009-06-01
+Loma;437;Loma;loma;;;2010-03-26
+Lyci;202;Lycian;lycien;Lycian;5.1;2007-07-02
+Lydi;116;Lydian;lydien;Lydian;5.1;2007-07-02
+Mahj;314;Mahajani;mahâjanî;Mahajani;7.0;2014-11-15
+Maka;366;Makasar;makassar;Makasar;11.0;2016-12-05
+Mand;140;Mandaic, Mandaean;mandéen;Mandaic;6.0;2010-07-23
+Mani;139;Manichaean;manichéen;Manichaean;7.0;2014-11-15
+Marc;332;Marchen;marchen;Marchen;9.0;2016-12-05
+Maya;090;Mayan hieroglyphs;hiéroglyphes mayas;;;2004-05-01
+Medf;265;Medefaidrin (Oberi Okaime, Oberi Ɔkaimɛ);médéfaïdrine;Medefaidrin;11.0;2016-12-05
+Mend;438;Mende Kikakui;mendé kikakui;Mende_Kikakui;7.0;2014-11-15
+Merc;101;Meroitic Cursive;cursif méroïtique;Meroitic_Cursive;6.1;2012-02-06
+Mero;100;Meroitic Hieroglyphs;hiéroglyphes méroïtiques;Meroitic_Hieroglyphs;6.1;2012-02-06
+Mlym;347;Malayalam;malayâlam;Malayalam;1.1;2004-05-01
+Modi;324;Modi, Moḍī;modî;Modi;7.0;2014-11-15
+Mong;145;Mongolian;mongol;Mongolian;3.0;2004-05-01
+Moon;218;Moon (Moon code, Moon script, Moon type);écriture Moon;;;2006-12-11
+Mroo;264;Mro, Mru;mro;Mro;7.0;2016-12-05
+Mtei;337;Meitei Mayek (Meithei, Meetei);meitei mayek;Meetei_Mayek;5.2;2009-06-01
+Mult;323;Multani;multanî;Multani;8.0;2015-07-07
+Mymr;350;Myanmar (Burmese);birman;Myanmar;3.0;2004-05-01
+Nagm;295;Nag Mundari;nag mundari;Nag_Mundari;15.0;2021-12-03
+Nand;311;Nandinagari;nandinâgarî;Nandinagari;12.0;2018-08-26
+Narb;106;Old North Arabian (Ancient North Arabian);nord-arabique;Old_North_Arabian;7.0;2014-11-15
+Nbat;159;Nabataean;nabatéen;Nabataean;7.0;2014-11-15
+Newa;333;Newa, Newar, Newari, Nepāla lipi;néwa, néwar, néwari, nepāla lipi;Newa;9.0;2016-12-05
+Nkdb;085;Naxi Dongba (na²¹ɕi³³ to³³ba²¹, Nakhi Tomba);naxi dongba;;;2017-07-26
+Nkgb;420;Naxi Geba (na²¹ɕi³³ gʌ²¹ba²¹, 'Na-'Khi ²Ggŏ-¹baw, Nakhi Geba);naxi geba, nakhi geba;;;2017-07-26
+Nkoo;165;N’Ko;n’ko;Nko;5.0;2006-10-10
+Nshu;499;Nüshu;nüshu;Nushu;10.0;2017-07-26
+Ogam;212;Ogham;ogam;Ogham;3.0;2004-05-01
+Olck;261;Ol Chiki (Ol Cemet’, Ol, Santali);ol tchiki;Ol_Chiki;5.1;2007-07-02
+Onao;296;Ol Onal;ol onal;;;2023-09-12
+Orkh;175;Old Turkic, Orkhon Runic;orkhon;Old_Turkic;5.2;2009-06-01
+Orya;327;Oriya (Odia);oriyâ (odia);Oriya;1.1;2016-12-05
+Osge;219;Osage;osage;Osage;9.0;2016-12-05
+Osma;260;Osmanya;osmanais;Osmanya;4.0;2004-05-01
+Ougr;143;Old Uyghur;ancien ouïgour;Old_Uyghur;14.0;2021-01-25
+Palm;126;Palmyrene;palmyrénien;Palmyrene;7.0;2014-11-15
+Pauc;263;Pau Cin Hau;paou chin haou;Pau_Cin_Hau;7.0;2014-11-15
+Pcun;015;Proto-Cuneiform;proto-cunéiforme;;;2021-01-25
+Pelm;016;Proto-Elamite;proto-élamite;;;2021-01-25
+Perm;227;Old Permic;ancien permien;Old_Permic;7.0;2014-11-15
+Phag;331;Phags-pa;’phags pa;Phags_Pa;5.0;2006-10-10
+Phli;131;Inscriptional Pahlavi;pehlevi des inscriptions;Inscriptional_Pahlavi;5.2;2009-06-01
+Phlp;132;Psalter Pahlavi;pehlevi des psautiers;Psalter_Pahlavi;7.0;2014-11-15
+Phlv;133;Book Pahlavi;pehlevi des livres;;;2007-07-15
+Phnx;115;Phoenician;phénicien;Phoenician;5.0;2006-10-10
+Plrd;282;Miao (Pollard);miao (Pollard);Miao;6.1;2012-02-06
+Piqd;293;Klingon (KLI pIqaD);klingon (pIqaD du KLI);;;2015-12-16
+Prti;130;Inscriptional Parthian;parthe des inscriptions;Inscriptional_Parthian;5.2;2009-06-01
+Psin;103;Proto-Sinaitic;proto-sinaïtique;;;2021-01-25
+Qaaa;900;Reserved for private use (start);réservé à l’usage privé (début);;;2004-05-29
+Qabx;949;Reserved for private use (end);réservé à l’usage privé (fin);;;2004-05-29
+Ranj;303;Ranjana;ranjana;;;2021-01-25
+Rjng;363;Rejang (Redjang, Kaganga);redjang (kaganga);Rejang;5.1;2009-02-23
+Rohg;167;Hanifi Rohingya;hanifi rohingya;Hanifi_Rohingya;11.0;2017-11-21
+Roro;620;Rongorongo;rongorongo;;;2004-05-01
+Runr;211;Runic;runique;Runic;3.0;2004-05-01
+Samr;123;Samaritan;samaritain;Samaritan;5.2;2009-06-01
+Sara;292;Sarati;sarati;;;2004-05-29
+Sarb;105;Old South Arabian;sud-arabique, himyarite;Old_South_Arabian;5.2;2009-06-01
+Saur;344;Saurashtra;saurachtra;Saurashtra;5.1;2007-07-02
+Sgnw;095;SignWriting;SignÉcriture, SignWriting;SignWriting;8.0;2015-07-07
+Shaw;281;Shavian (Shaw);shavien (Shaw);Shavian;4.0;2004-05-01
+Shrd;319;Sharada, Śāradā;charada, shard;Sharada;6.1;2012-02-06
+Shui;530;Shuishu;shuishu;;;2017-07-26
+Sidd;302;Siddham, Siddhaṃ, Siddhamātṛkā;siddham;Siddham;7.0;2014-11-15
+Sidt;180;Sidetic;sidétique;;;2023-09-12
+Sind;318;Khudawadi, Sindhi;khoudawadî, sindhî;Khudawadi;7.0;2014-11-15
+Sinh;348;Sinhala;singhalais;Sinhala;3.0;2004-05-01
+Sogd;141;Sogdian;sogdien;Sogdian;11.0;2017-11-21
+Sogo;142;Old Sogdian;ancien sogdien;Old_Sogdian;11.0;2017-11-21
+Sora;398;Sora Sompeng;sora sompeng;Sora_Sompeng;6.1;2012-02-06
+Soyo;329;Soyombo;soyombo;Soyombo;10.0;2017-07-26
+Sund;362;Sundanese;sundanais;Sundanese;5.1;2007-07-02
+Sunu;274;Sunuwar;sunuwar;;;2021-12-03
+Sylo;316;Syloti Nagri;sylotî nâgrî;Syloti_Nagri;4.1;2006-06-21
+Syrc;135;Syriac;syriaque;Syriac;3.0;2004-05-01
+Syre;138;Syriac (Estrangelo variant);syriaque (variante estranghélo);;3.0;2004-05-01
+Syrj;137;Syriac (Western variant);syriaque (variante occidentale);;3.0;2004-05-01
+Syrn;136;Syriac (Eastern variant);syriaque (variante orientale);;3.0;2004-05-01
+Tagb;373;Tagbanwa;tagbanoua;Tagbanwa;3.2;2004-05-01
+Takr;321;Takri, Ṭākrī, Ṭāṅkrī;tâkrî;Takri;6.1;2012-02-06
+Tale;353;Tai Le;taï-le;Tai_Le;4.0;2004-10-25
+Talu;354;New Tai Lue;nouveau taï-lue;New_Tai_Lue;4.1;2006-06-21
+Taml;346;Tamil;tamoul;Tamil;1.1;2004-05-01
+Tang;520;Tangut;tangoute;Tangut;9.0;2016-12-05
+Tavt;359;Tai Viet;taï viêt;Tai_Viet;5.2;2009-06-01
+Tayo;380;Tai Yo;taï yo;;;2023-09-12
+Telu;340;Telugu;télougou;Telugu;1.1;2004-05-01
+Teng;290;Tengwar;tengwar;;;2004-05-01
+Tfng;120;Tifinagh (Berber);tifinagh (berbère);Tifinagh;4.1;2006-06-21
+Tglg;370;Tagalog (Baybayin, Alibata);tagal (baybayin, alibata);Tagalog;3.2;2009-02-23
+Thaa;170;Thaana;thâna;Thaana;3.0;2004-05-01
+Thai;352;Thai;thaï;Thai;1.1;2004-05-01
+Tibt;330;Tibetan;tibétain;Tibetan;2.0;2004-05-01
+Tirh;326;Tirhuta;tirhouta;Tirhuta;7.0;2014-11-15
+Tnsa;275;Tangsa;tangsa;Tangsa;14.0;2021-02-17
+Todr;229;Todhri;todhri;;;2023-09-12
+Tols;299;Tolong Siki;tolong siki;;;2023-09-12
+Toto;294;Toto;toto;Toto;14.0;2020-04-16
+Tutg;341;Tulu-Tigalari;tulu-tigalari;;;2023-09-12
+Ugar;040;Ugaritic;ougaritique;Ugaritic;4.0;2004-05-01
+Vaii;470;Vai;vaï;Vai;5.1;2007-07-02
+Visp;280;Visible Speech;parole visible;;;2004-05-01
+Vith;228;Vithkuqi;vithkuqi;Vithkuqi;14.0;2021-02-17
+Wara;262;Warang Citi (Varang Kshiti);warang citi;Warang_Citi;7.0;2014-11-15
+Wcho;283;Wancho;wantcho;Wancho;12.0;2017-07-26
+Wole;480;Woleai;woléaï;;;2010-12-21
+Xpeo;030;Old Persian;cunéiforme persépolitain;Old_Persian;4.1;2006-06-21
+Xsux;020;Cuneiform, Sumero-Akkadian;cunéiforme suméro-akkadien;Cuneiform;5.0;2006-10-10
+Yezi;192;Yezidi;yézidi;Yezidi;13.0;2019-08-19
+Yiii;460;Yi;yi;Yi;3.0;2004-05-01
+Zanb;339;Zanabazar Square (Zanabazarin Dörböljin Useg, Xewtee Dörböljin Bicig, Horizontal Square Script);zanabazar quadratique;Zanabazar_Square;10.0;2017-07-26
+Zinh;994;Code for inherited script;codet pour écriture héritée;Inherited;;2009-02-23
+Zmth;995;Mathematical notation;notation mathématique;;3.2;2007-11-26
+Zsye;993;Symbols (Emoji variant);symboles (variante émoji);;6.0;2015-12-16
+Zsym;996;Symbols;symboles;;1.1;2007-11-26
+Zxxx;997;Code for unwritten documents;codet pour les documents non écrits;;;2011-06-21
+Zyyy;998;Code for undetermined script;codet pour écriture indéterminée;Common;;2004-05-29
+Zzzz;999;Code for uncoded script;codet pour écriture non codée;Unknown;;2006-10-10