From c5fbc9640b001d12297a5d5f1788ed85db903ba5 Mon Sep 17 00:00:00 2001 From: Conrad Nied Date: Mon, 9 Dec 2024 22:54:10 -0800 Subject: [PATCH] CLDR-18108 Give all languages a primary script: trivial cases (#4210) This change adds "primary" scripts to many languages in language_script.tsv. This won't change likely subtags, rather this just future-proofs our data by recognizing a singular primary script, avoiding issues where ambiguities served customers the wrong script. I also added scripts for languages in country_language_population.tsv that were missing. There are many more tasks, especially more complicated ones, in the parent ticket https://unicode-org.atlassian.net/browse/CLDR-18102 --- common/supplemental/supplementalData.xml | 132 ++++++++++-------- .../language-script-description.md | 20 +-- .../cldr/tool/ConvertLanguageData.java | 30 +--- .../cldr/util/data/language_script.tsv | 117 +++++++++------- .../cldr/unittest/TestInheritance.java | 4 +- 5 files changed, 153 insertions(+), 150 deletions(-) diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml index 58893bc9318..1989ef6be8f 100644 --- a/common/supplemental/supplementalData.xml +++ b/common/supplemental/supplementalData.xml @@ -1291,7 +1291,7 @@ XXX Code for transations where no currency is involved - + @@ -1302,7 +1302,7 @@ XXX Code for transations where no currency is involved - + @@ -1311,11 +1311,13 @@ XXX Code for transations where no currency is involved - + + + @@ -1327,7 +1329,7 @@ XXX Code for transations where no currency is involved - + @@ -1340,7 +1342,7 @@ XXX Code for transations where no currency is involved - + @@ -1397,6 +1399,7 @@ XXX Code for transations where no currency is involved + @@ -1422,6 +1425,7 @@ XXX Code for transations where no currency is involved + @@ -1445,6 +1449,7 @@ XXX Code for transations where no currency is involved + @@ -1455,7 +1460,7 @@ XXX Code for transations where no currency is involved - + @@ -1488,10 +1493,11 @@ XXX Code for transations where no currency is involved - + + - + @@ -1523,7 +1529,7 @@ XXX Code for transations where no currency is involved - + @@ -1531,19 +1537,19 @@ XXX Code for transations where no currency is involved - + - + - + @@ -1577,8 +1583,8 @@ XXX Code for transations where no currency is involved - - + + @@ -1611,7 +1617,7 @@ XXX Code for transations where no currency is involved - + @@ -1620,18 +1626,18 @@ XXX Code for transations where no currency is involved - - + + - + - + - + @@ -1662,7 +1668,7 @@ XXX Code for transations where no currency is involved - + @@ -1694,13 +1700,13 @@ XXX Code for transations where no currency is involved - + - + @@ -1712,6 +1718,7 @@ XXX Code for transations where no currency is involved + @@ -1721,12 +1728,13 @@ XXX Code for transations where no currency is involved + - + @@ -1738,7 +1746,8 @@ XXX Code for transations where no currency is involved - + + @@ -1749,6 +1758,7 @@ XXX Code for transations where no currency is involved + @@ -1786,6 +1796,7 @@ XXX Code for transations where no currency is involved + @@ -1831,8 +1842,9 @@ XXX Code for transations where no currency is involved - - + + + @@ -1845,6 +1857,7 @@ XXX Code for transations where no currency is involved + @@ -1856,7 +1869,7 @@ XXX Code for transations where no currency is involved - + @@ -1881,19 +1894,19 @@ XXX Code for transations where no currency is involved - + - + - + @@ -1925,6 +1938,7 @@ XXX Code for transations where no currency is involved + @@ -1944,7 +1958,7 @@ XXX Code for transations where no currency is involved - + @@ -1980,7 +1994,7 @@ XXX Code for transations where no currency is involved - + @@ -2022,8 +2036,8 @@ XXX Code for transations where no currency is involved - - + + @@ -2058,7 +2072,7 @@ XXX Code for transations where no currency is involved - + @@ -2074,10 +2088,11 @@ XXX Code for transations where no currency is involved - + - - + + + @@ -2088,10 +2103,11 @@ XXX Code for transations where no currency is involved + - - + + @@ -2179,7 +2195,7 @@ XXX Code for transations where no currency is involved - + @@ -2204,10 +2220,11 @@ XXX Code for transations where no currency is involved - + + @@ -2249,7 +2266,7 @@ XXX Code for transations where no currency is involved - + @@ -2296,11 +2313,12 @@ XXX Code for transations where no currency is involved + - + @@ -2335,7 +2353,7 @@ XXX Code for transations where no currency is involved - + @@ -2364,8 +2382,8 @@ XXX Code for transations where no currency is involved - - + + @@ -2391,21 +2409,21 @@ XXX Code for transations where no currency is involved - + - - + + - - - + + + - - + + @@ -2425,7 +2443,7 @@ XXX Code for transations where no currency is involved - + diff --git a/docs/site/development/updating-codes/update-language-script-info/language-script-description.md b/docs/site/development/updating-codes/update-language-script-info/language-script-description.md index 4662c1a22a4..56873b8642d 100644 --- a/docs/site/development/updating-codes/update-language-script-info/language-script-description.md +++ b/docs/site/development/updating-codes/update-language-script-info/language-script-description.md @@ -4,19 +4,13 @@ title: Language Script Description # Language Script Description -The language\_script spreadsheet should list all of the language / script combinations that are in common modern use. The countries are not important, since their function has been overtaken by the country\_language\_population spreadsheet. +The [`language\_script.tsv`](https://github.com/unicode-org/cldr/blob/main/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/language_script.tsv) data file should list all of the language / script combinations that are in common use. Usage by country is indicated in the [`country\_language\_population.tsv`](https://github.com/unicode-org/cldr/blob/main/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/country_language_population.tsv) spreadsheet. -1. If the language and script are both modern, and the script is a major way to write the language in some country, then we should see that line marked as **primary**. -2. Otherwise it should be marked **secondary**. +1. Every language should have 1 script considered the **primary** script. + 1. This data is currently used to determine [the likely script for a language](/development/updating-codes/likelysubtags-and-default-content) so there needs to be at least 1 primary value. Because it is the default, it determines the script of locales without language codes in the ``. + 2. __Changed in v47__ Include a primary script for historical languages (eg. Ancient Greek, Coptic). The primary script should reflect where the majority of the written corpus originates from. +2. Other scripts used for a language should be marked **secondary**. -Every language that is in official use in any country according to country\_language\_population  should have at least one primary script in the language\_script spreadsheet. - -If a language has multiple primary scripts, then it should not appear without the script tag in the country\_language\_population.tsv. For example, we should not see "az", but rather "az\_Cyrl", "az\_Latn", and so on. For each country where the language is used, we should see figures on the script\-specific values. The values may overlap, that is, we may see az\_Cyrl at 60% and az\_Latn at 55%. However, the combination with the predominantly used script **must** have a larger figure than the others. - -This is also reflected in CLDR main: languages with multiple scripts will have that reflected in their structure (eg sr\-Cyrl\-RS), with aliases for the language\-region combinations. - -Files in https://github.com/unicode-org/cldr/tree/main/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data - -1. country\_language\_population.tsv -2. language\_script.tsv +Languages with multiple ambiguous scripts should have that reflected in their CLDR structure (eg. `sr_Cyrl_RS`), with aliases for the language\-region combinations. +In order to re-generate the XML data use ConvertLanguageData as written about in [the article about updating the language scripts](/development/updating-codes/update-language-script-info). diff --git a/tools/cldr-code/src/main/java/org/unicode/cldr/tool/ConvertLanguageData.java b/tools/cldr-code/src/main/java/org/unicode/cldr/tool/ConvertLanguageData.java index 53a1245509e..23eb045e45c 100644 --- a/tools/cldr-code/src/main/java/org/unicode/cldr/tool/ConvertLanguageData.java +++ b/tools/cldr-code/src/main/java/org/unicode/cldr/tool/ConvertLanguageData.java @@ -34,7 +34,6 @@ import java.util.regex.Matcher; import org.unicode.cldr.draft.FileUtilities; import org.unicode.cldr.draft.ScriptMetadata; -import org.unicode.cldr.draft.ScriptMetadata.IdUsage; import org.unicode.cldr.draft.ScriptMetadata.Info; import org.unicode.cldr.util.Builder; import org.unicode.cldr.util.CLDRFile; @@ -2036,7 +2035,8 @@ static void getLanguage2Scripts(Set sortedInput) throws IOException { if (!checkCode(LstrType.language, language, row)) continue; for (String script : scripts.split("\\s+")) { if (!checkCode(LstrType.script, script, row)) continue; - // if the script is not modern, demote + + // Make sure the script has information Info scriptInfo = ScriptMetadata.getInfo(script); if (scriptInfo == null) { BadItem.ERROR.toString( @@ -2045,24 +2045,8 @@ static void getLanguage2Scripts(Set sortedInput) throws IOException { row); continue; } - IdUsage idUsage = scriptInfo.idUsage; - if (status == BasicLanguageData.Type.primary - && idUsage != IdUsage.RECOMMENDED) { - if (idUsage == IdUsage.ASPIRATIONAL || idUsage == IdUsage.LIMITED_USE) { - BadItem.WARNING.toString( - "Script has unexpected usage; make secondary if a Recommended script is used widely for the langauge", - idUsage + ", " + script + "=" + getULocaleScriptName(script), - row); - } else { - BadItem.ERROR.toString( - "Script is not modern; make secondary", - idUsage + ", " + script + "=" + getULocaleScriptName(script), - row); - status = BasicLanguageData.Type.secondary; - } - } - // if the language is not modern, demote + // Make sure the language code is valid if (LOCALE_ALIAS_INFO.get("language").containsKey(language)) { BadItem.ERROR.toString( "Remove/Change deprecated language", @@ -2074,14 +2058,6 @@ static void getLanguage2Scripts(Set sortedInput) throws IOException { row); continue; } - if (status == BasicLanguageData.Type.primary - && !sc.isModernLanguage(language)) { - BadItem.ERROR.toString( - "Should be secondary, language is not modern", - language + " " + getLanguageName(language), - row); - status = BasicLanguageData.Type.secondary; - } addLanguage2Script(language, status, script); if (row.size() > 5) { diff --git a/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/language_script.tsv b/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/language_script.tsv index 6b43e3e3ef9..2811e48eb2d 100644 --- a/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/language_script.tsv +++ b/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/language_script.tsv @@ -10,7 +10,7 @@ ace Achinese primary Latn Latin ach Acoli primary Latn Latin ada Adangme primary Latn Latin ady Adyghe primary Cyrl Cyrillic -ae Avestan secondary Avst Avestan +ae Avestan primary Avst Avestan aeb Tunisian Arabic primary Arab Arabic af Afrikaans primary Latn Latin agq Aghem primary Latn Latin @@ -19,7 +19,7 @@ aii Assyrian Neo-Aramaic secondary Syrc Syriac ain Ainu secondary Kana Katakana ain Ainu secondary Latn Latin ak Akan primary Latn Latin -akk Akkadian secondary Xsux Sumero-Akkadian Cuneiform +akk Akkadian primary Xsux Sumero-Akkadian Cuneiform akz Alabama primary Latn Latin ale Aleut primary Latn Latin aln Gheg Albanian primary Latn Latin @@ -27,10 +27,12 @@ alt Southern Altai primary Cyrl Cyrillic am Amharic primary Ethi Ethiopic amo Amo primary Latn Latin an Aragonese primary Latn Latin -ang Old English secondary Latn Latin +ang Old English primary Latn Latin ann Obolo primary Latn Latin anp Angika primary Deva Devanagari aoz Uab Meto primary Latn Latin +apc Levantine Arabic primary Arab Arabic +apd Sudanese Arabic primary Arab Arabic ar Arabic primary Arab Arabic ar Arabic secondary Syrc Syriac arc Aramaic secondary Armi Imperial Aramaic @@ -41,7 +43,7 @@ aro Araona primary Latn Latin arp Arapaho primary Latn Latin arq Algerian Arabic primary Arab Arabic ars Najdi Arabic primary Arab Arabic -arw Arawak secondary Latn Latin +arw Arawak primary Latn Latin ary Moroccan Arabic primary Arab Arabic arz Egyptian Arabic primary Arab Arabic as Assamese primary Beng Bangla @@ -49,7 +51,7 @@ asa Asu primary Latn Latin ast Asturian primary Latn Latin atj Atikamekw primary Latn Latin av Avaric primary Cyrl Cyrillic -avk Kotava secondary Latn Latin +avk Kotava primary Latn Latin awa Awadhi primary Deva Devanagari ay Aymara primary Latn Latin az Azerbaijani primary Arab Arabic @@ -84,12 +86,14 @@ bgn Western Balochi primary Arab Arabic bgx Balkan Gagauz Turkish primary Grek Greek bhb Bhili primary Deva Devanagari bhi Bhilali primary Deva Devanagari +bhk Albay Bicolano primary Latn Latin bho Bhojpuri primary Deva Devanagari bi Bislama primary Latn Latin bik Bikol primary Latn Latin bin Bini primary Latn Latin bjj Kanauji primary Deva Devanagari bjn Banjar primary Latn Latin +bjt Balanta-Ganja primary Latn Latin bkm Kom primary Latn Latin bku Buhid primary Latn Latin bku Buhid secondary Buhd Buhid @@ -111,6 +115,7 @@ brh Brahui secondary Latn Latin brx Bodo primary Deva Devanagari bs Bosnian primary Cyrl Cyrillic bs Bosnian primary Latn Latin +bsc Bassari primary Latn Latin bss Akoose primary Latn Latin bto Rinconada Bikol primary Latn Latin btv Bateri primary Deva Devanagari @@ -131,13 +136,14 @@ cay Cayuga primary Latn Latin cch Atsam primary Latn Latin ccp Chakma primary Beng Bangla ccp Chakma primary Cakm Chakma +ccr Cacaopera primary Latn Latin ce Chechen primary Cyrl Cyrillic ceb Cebuano primary Latn Latin cgg Chiga primary Latn Latin ch Chamorro primary Latn Latin chk Chuukese primary Latn Latin chm Mari primary Cyrl Cyrillic -chn Chinook Jargon secondary Latn Latin +chn Chinook Jargon primary Latn Latin cho Choctaw primary Latn Latin chp Chipewyan primary Latn Latin chp Chipewyan secondary Cans Unified Canadian Aboriginal Syllabics @@ -169,12 +175,12 @@ crl Northern East Cree secondary Latn Latin crm Moose Cree primary Cans Unified Canadian Aboriginal Syllabics crs Seselwa Creole French primary Latn Latin cs Czech primary Latn Latin -csb Kashubian secondary Latn Latin +csb Kashubian primary Latn Latin csw Swampy Cree primary Cans Unified Canadian Aboriginal Syllabics ctd Tedim Chin primary Latn Latin cwd Woods Cree primary Cans Unified Canadian Aboriginal Syllabics cwd Woods Cree secondary Latn Latin -cu Church Slavic secondary Cyrl Cyrillic +cu Church Slavic primary Cyrl Cyrillic cv Chuvash primary Cyrl Cyrillic cy Welsh primary Latn Latin da Danish primary Latn Latin @@ -200,7 +206,7 @@ dtm Tomo Kan Dogon primary Latn Latin dtp Central Dusun primary Latn Latin dty Dotyali primary Deva Devanagari dua Duala primary Latn Latin -dum Middle Dutch secondary Latn Latin +dum Middle Dutch primary Latn Latin dv Divehi primary Thaa Thaana dyo Jola-Fonyi primary Latn Latin dyo Jola-Fonyi secondary Arab Arabic @@ -211,14 +217,14 @@ ecy Eteocypriot primary Cprt Cypriot Syllabary ee Ewe primary Latn Latin efi Efik primary Latn Latin egl Emilian primary Latn Latin -egy Ancient Egyptian secondary Egyp Egyptian hieroglyphs +egy Ancient Egyptian primary Egyp Egyptian hieroglyphs eka Ekajuk primary Latn Latin eky Eastern Kayah primary Kali Kayah Li el Greek primary Grek Greek en English primary Latn Latin en English secondary Dsrt Deseret en English secondary Shaw Shavian -enm Middle English secondary Latn Latin +enm Middle English primary Latn Latin eo Esperanto primary Latn Latin es Spanish primary Latn Latin esu Central Yupik primary Latn Latin @@ -245,8 +251,8 @@ fon Fon primary Latn Latin fr French primary Latn Latin fr French secondary Dupl Duployan shorthand frc Cajun French primary Latn Latin -frm Middle French secondary Latn Latin -fro Old French secondary Latn Latin +frm Middle French primary Latn Latin +fro Old French primary Latn Latin frp Arpitan primary Latn Latin frr Northern Frisian primary Latn Latin frs Eastern Frisian primary Latn Latin @@ -267,22 +273,22 @@ gbm Garhwali primary Deva Devanagari gbz Zoroastrian Dari primary Arab Arabic gcr Guianese Creole French primary Latn Latin gd Scottish Gaelic primary Latn Latin -gez Geez secondary Ethi Ethiopic +gez Geez primary Ethi Ethiopic gil Gilbertese primary Latn Latin gjk Kachi Koli primary Arab Arabic gju Gujari primary Arab Arabic gl Galician primary Latn Latin gld Nanai primary Cyrl Cyrillic glk Gilaki primary Arab Arabic -gmh Middle High German secondary Latn Latin +gmh Middle High German primary Latn Latin gmy Mycenaean Greek primary Linb Linear B gn Guarani primary Latn Latin -goh Old High German secondary Latn Latin +goh Old High German primary Latn Latin gon Gondi primary Deva Devanagari gon Gondi primary Telu Telugu gor Gorontalo primary Latn Latin gos Gronings primary Latn Latin -got Gothic secondary Goth Gothic +got Gothic primary Goth Gothic grb Grebo primary Latn Latin grc Ancient Greek primary Grek Greek grt Garo primary Beng Bangla @@ -309,7 +315,7 @@ hi Hindi secondary Mahj Mahajani hif Fiji Hindi primary Deva Devanagari hif Fiji Hindi primary Latn Latin hil Hiligaynon primary Latn Latin -hit Hittite secondary Xsux Sumero-Akkadian Cuneiform +hit Hittite primary Xsux Sumero-Akkadian Cuneiform hmd Large Flowery Miao primary Plrd Pollard Phonetic hmn Hmong primary Latn Latin hmn Hmong secondary Hmng Pahawh Hmong @@ -333,12 +339,12 @@ hup Hupa primary Latn Latin hur Halkomelem primary Latn Latin hy Armenian primary Armn Armenian hz Herero primary Latn Latin -ia Interlingua secondary Latn Latin +ia Interlingua primary Latn Latin iba Iban primary Latn Latin ibb Ibibio primary Latn Latin id Indonesian primary Latn Latin id Indonesian secondary Arab Arabic -ie Interlingue secondary Latn Latin +ie Interlingue primary Latn Latin ife Ifè primary Latn Latin ig Igbo primary Latn Latin ii Sichuan Yi primary Yiii Yi @@ -349,6 +355,7 @@ ilo Iloko primary Latn Latin inh Ingush primary Cyrl Cyrillic inh Ingush secondary Arab Arabic inh Ingush secondary Latn Latin +io Ido primary Latn Latin is Icelandic primary Latn Latin it Italian primary Latn Latin iu Inuktitut primary Cans Unified Canadian Aboriginal Syllabics @@ -356,12 +363,13 @@ iu Inuktitut primary Latn Latin izh Ingrian primary Latn Latin ja Japanese primary Jpan Japanese jam Jamaican Creole English primary Latn Latin +jbo Lojban primary Latn Latin jgo Ngomba primary Latn Latin jmc Machame primary Latn Latin jml Jumli primary Deva Devanagari jpr Judeo-Persian primary Hebr Hebrew jrb Judeo-Arabic primary Hebr Hebrew -jut Jutish secondary Latn Latin +jut Jutish primary Latn Latin jv Javanese primary Latn Latin jv Javanese secondary Java Javanese ka Georgian primary Geor Georgian @@ -382,6 +390,7 @@ kck Kalanga primary Latn Latin kde Makonde primary Latn Latin kdt Kuy primary Thai Thai kea Kabuverdianu primary Latn Latin +ken Kenyang primary Latn Latin kfo Koro primary Latn Latin kfr Kachhi primary Deva Devanagari kfy Kumaoni primary Deva Devanagari @@ -409,6 +418,7 @@ kln Kalenjin primary Latn Latin km Khmer primary Khmr Khmer kmb Kimbundu primary Latn Latin kn Kannada primary Knda Kannada +knf Mankanya primary Latn Latin knn Konkani primary Deva Devanagari ko Korean primary Kore Korean koi Komi-Permyak primary Cyrl Cyrillic @@ -449,8 +459,8 @@ ky Kyrgyz primary Arab Arabic ky Kyrgyz primary Cyrl Cyrillic ky Kyrgyz primary Latn Latin kyu Western Kayah primary Kali Kayah Li -la Latin secondary Latn Latin -lab Linear A secondary Lina Linear A +la Latin primary Latn Latin +lab Linear A primary Lina Linear A lad Ladino primary Hebr Hebrew lag Langi primary Latn Latin lah Lahnda primary Arab Arabic @@ -460,6 +470,7 @@ lb Luxembourgish primary Latn Latin lbe Lak primary Cyrl Cyrillic lbw Tolaki primary Latn Latin lcp Western Lawa primary Thai Thai +len Lenca primary Latn Latin lep Lepcha primary Lepc Lepcha lez Lezghian primary Cyrl Cyrillic lez Lezghian secondary Aghb Caucasian Albanian @@ -472,7 +483,7 @@ lif Limbu primary Limb Limbu lij Ligurian primary Latn Latin lil Lillooet primary Latn Latin lis Lisu primary Lisu Fraser -liv Livonian secondary Latn Latin +liv Livonian primary Latn Latin ljp Lampung Api primary Latn Latin lki Laki primary Arab Arabic lkt Lakota primary Latn Latin @@ -488,16 +499,16 @@ lt Lithuanian primary Latn Latin ltg Latgalian primary Latn Latin lu Luba-Katanga primary Latn Latin lua Luba-Lulua primary Latn Latin -lui Luiseno secondary Latn Latin +lui Luiseno primary Latn Latin lun Lunda primary Latn Latin luo Luo primary Latn Latin lus Mizo primary Beng Bangla -lut Lushootseed secondary Latn Latin +lut Lushootseed primary Latn Latin luy Luyia primary Latn Latin luz Southern Luri primary Arab Arabic lv Latvian primary Latn Latin lwl Eastern Lawa primary Thai Thai -lzh Literary Chinese secondary Hans Simplified +lzh Literary Chinese primary Hans Simplified lzz Laz primary Latn Latin lzz Laz secondary Geor Georgian mad Madurese primary Latn Latin @@ -521,6 +532,7 @@ men Mende secondary Mend Mende mer Meru primary Latn Latin mfa Pattani Malay primary Arab Arabic mfe Morisyen primary Latn Latin +mfv Mandjak primary Latn Latin mg Malagasy primary Latn Latin mgh Makhuwa-Meetto primary Latn Latin mgo Metaʼ primary Latn Latin @@ -537,7 +549,7 @@ mls Masalit primary Latn Latin mn Mongolian primary Cyrl Cyrillic mn Mongolian secondary Mong Mongolian mn Mongolian secondary Phag Phags-pa -mnc Manchu secondary Mong Mongolian +mnc Manchu primary Mong Mongolian mni Manipuri primary Beng Bangla mni Manipuri secondary Mtei Meitei Mayek mns Mansi primary Cyrl Cyrillic @@ -566,7 +578,7 @@ mxc Manyika primary Latn Latin my Burmese primary Mymr Myanmar myv Erzya primary Cyrl Cyrillic myx Masaaba primary Latn Latin -myz Classical Mandaic secondary Mand Mandaean +myz Classical Mandaic primary Mand Mandaean mzn Mazanderani primary Arab Arabic na Nauru primary Latn Latin nan Min Nan Chinese primary Hans Simplified @@ -596,8 +608,8 @@ no Norwegian primary Latn Latin nod Northern Thai primary Lana Lanna noe Nimadi primary Deva Devanagari nog Nogai primary Cyrl Cyrillic -non Old Norse secondary Runr Runic -nov Novial secondary Latn Latin +non Old Norse primary Runr Runic +nov Novial primary Latn Latin nqo N’Ko primary Nkoo N’Ko nr South Ndebele primary Latn Latin nsk Naskapi primary Cans Unified Canadian Aboriginal Syllabics @@ -625,7 +637,7 @@ osa Osage primary Osge Osage osa Osage secondary Latn Latin osc Oscan secondary Ital Old Italic osc Oscan secondary Latn Latin -otk Old Turkish secondary Orkh Orkhon +otk Old Turkish primary Orkh Orkhon pa Punjabi primary Arab Arabic pa Punjabi primary Guru Gurmukhi pag Pangasinan primary Latn Latin @@ -638,9 +650,9 @@ pcd Picard primary Latn Latin pcm Nigerian Pidgin primary Latn Latin pdc Pennsylvania German primary Latn Latin pdt Plautdietsch primary Latn Latin -peo Old Persian secondary Xpeo Old Persian +peo Old Persian primary Xpeo Old Persian pfl Palatine German primary Latn Latin -phn Phoenician secondary Phnx Phoenician +phn Phoenician primary Phnx Phoenician pi Pali primary Mymr Myanmar pi Pali secondary Deva Devanagari pi Pali secondary Sinh Sinhala @@ -653,10 +665,11 @@ pnt Pontic primary Grek Greek pnt Pontic secondary Cyrl Cyrillic pnt Pontic secondary Latn Latin pon Pohnpeian primary Latn Latin +ppl Nahaut Pipil primary Latn Latin pqm Malecite primary Latn Latin prd Parsi-Dari primary Arab Arabic -prg Prussian secondary Latn Latin -pro Old Provençal secondary Latn Latin +prg Prussian primary Latn Latin +pro Old Provençal primary Latn Latin ps Pashto primary Arab Arabic pt Portuguese primary Latn Latin puu Punu primary Latn Latin @@ -735,7 +748,7 @@ see Seneca primary Latn Latin sef Cebaara Senoufo primary Latn Latin seh Sena primary Latn Latin sei Seri primary Latn Latin -sel Selkup secondary Cyrl Cyrillic +sel Selkup primary Cyrl Cyrillic ses Koyraboro Senni primary Latn Latin sg Sango primary Latn Latin sga Old Irish secondary Latn Latin @@ -756,9 +769,10 @@ sm Samoan primary Latn Latin sma Southern Sami primary Latn Latin smj Lule Sami primary Latn Latin smn Inari Sami primary Latn Latin -smp Samaritan secondary Samr Samaritan +smp Samaritan primary Samr Samaritan sms Skolt Sami primary Latn Latin sn Shona primary Latn Latin +snf Noon primary Latn Latin snk Soninke primary Latn Latin so Somali primary Latn Latin so Somali secondary Arab Arabic @@ -792,7 +806,7 @@ sxn Sangir primary Latn Latin syi Seki primary Latn Latin syl Sylheti primary Beng Bangla syl Sylheti secondary Sylo Syloti Nagri -syr Syriac secondary Syrc Syriac +syr Syriac primary Syrc Syriac szl Silesian primary Latn Latin ta Tamil primary Taml Tamil tab Tabassaran primary Cyrl Cyrillic @@ -833,6 +847,7 @@ tly Talysh secondary Arab Arabic tly Talysh secondary Cyrl Cyrillic tmh Tamashek primary Latn Latin tn Tswana primary Latn Latin +tnr Ménik primary Latn Latin to Tongan primary Latn Latin tog Nyasa Tonga primary Latn Latin tok Toki Pona primary Latn Latin @@ -867,7 +882,7 @@ udm Udmurt secondary Latn Latin ug Uyghur primary Arab Arabic ug Uyghur primary Cyrl Cyrillic ug Uyghur secondary Latn Latin -uga Ugaritic secondary Ugar Ugaritic +uga Ugaritic primary Ugar Ugaritic uk Ukrainian primary Cyrl Cyrillic uli Ulithian primary Latn Latin umb Umbundu primary Latn Latin @@ -890,8 +905,8 @@ vic Virgin Islands Creole English primary Latn Latin vls West Flemish primary Latn Latin vmf Main-Franconian primary Latn Latin vmw Makhuwa primary Latn Latin -vo Volapük secondary Latn Latin -vot Votic secondary Latn Latin +vo Volapük primary Latn Latin +vot Votic primary Latn Latin vro Võro primary Latn Latin vun Vunjo primary Latn Latin wa Walloon primary Latn Latin @@ -910,18 +925,18 @@ wtm Mewati primary Deva Devanagari wuu Wu Chinese primary Hans Simplified xal Kalmyk primary Cyrl Cyrillic xav Xavánte primary Latn Latin -xcr Carian secondary Cari Carian +xcr Carian primary Cari Carian xh Xhosa primary Latn Latin -xlc Lycian secondary Lyci Lycian -xld Lydian secondary Lydi Lydian +xlc Lycian primary Lyci Lycian +xld Lydian primary Lydi Lydian xmf Mingrelian primary Geor Georgian -xmn Manichaean Middle Persian secondary Mani Manichaean -xmr Meroitic secondary Merc Meroitic Cursive -xna Ancient North Arabian secondary Narb Old North Arabian +xmn Manichaean Middle Persian primary Mani Manichaean +xmr Meroitic primary Merc Meroitic Cursive +xna Ancient North Arabian primary Narb Old North Arabian xnr Kangri primary Deva Devanagari xog Soga primary Latn Latin -xpr Parthian secondary Prti Inscriptional Parthian -xsa Sabaean secondary Sarb Old South Arabian +xpr Parthian primary Prti Inscriptional Parthian +xsa Sabaean primary Sarb Old South Arabian xsr Sherpa primary Deva Devanagari xum Umbrian secondary Ital Old Italic xum Umbrian secondary Latn Latin @@ -942,7 +957,7 @@ zag Zaghawa primary Latn Latin zap Zapotec primary Latn Latin zdj Ngazidja Comorian primary Arab Arabic zea Zeelandic primary Latn Latin -zen Zenaga secondary Tfng Tifinagh +zen Zenaga primary Tfng Tifinagh zgh Standard Moroccan Tamazight primary Tfng Tifinagh zh Chinese primary Hans Simplified zh Chinese primary Hant Traditional diff --git a/tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestInheritance.java b/tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestInheritance.java index 612aa3948d9..2b636972a3d 100644 --- a/tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestInheritance.java +++ b/tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestInheritance.java @@ -829,7 +829,7 @@ public void TestBasicLanguageDataAgainstScriptMetadata() { + "," + " but " + language - + " is missing in language_script.txt"); + + " is missing in language_script.tsv"); continue; } for (BasicLanguageData entry : data.values()) { @@ -848,7 +848,7 @@ public void TestBasicLanguageDataAgainstScriptMetadata() { + language + " doesn't have " + script - + " in language_script.txt"); + + " in language_script.tsv"); } }