CLDR-17897 Stabilize LikelySubtags but adding missing primary scripts…

… and likely subtag overrides The generated files for ConvertLanguageData and GenerateLikelySubtags change if input files are modified. This change seeks to stablize the scripts outputs. CLDR-17897 Add overrides to Likely Subtags
conradarcturus · Aug 29, 2024 · e5fa96d · e5fa96d
1 parent 5f091da
commit e5fa96d
Show file tree

Hide file tree

Showing 4 changed files with 35 additions and 16 deletions.
diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml
@@ -261,6 +261,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="ha_CM" to="ha_Arab_CM"/>		<!--Hausa‧?‧Cameroon	➡ Hausa‧Arabic‧Cameroon-->
 		<likelySubtag from="ha_SD" to="ha_Arab_SD"/>		<!--Hausa‧?‧Sudan	➡ Hausa‧Arabic‧Sudan-->
 		<likelySubtag from="hak" to="hak_Hans_CN"/>		<!--Hakka Chinese‧?‧?	➡ Hakka Chinese‧Simplified‧China-->
+		<likelySubtag from="hak_Hant" to="hak_Hant_TW"/>		<!--Hakka Chinese‧Traditional‧?	➡ Hakka Chinese‧Traditional‧Taiwan-->
 		<likelySubtag from="haw" to="haw_Latn_US"/>		<!--Hawaiian‧?‧?	➡ Hawaiian‧Latin‧United States-->
 		<likelySubtag from="haz" to="haz_Arab_AF"/>		<!--Hazaragi‧?‧?	➡ Hazaragi‧Arabic‧Afghanistan-->
 		<likelySubtag from="he" to="he_Hebr_IL"/>		<!--Hebrew‧?‧?	➡ Hebrew‧Hebrew‧Israel-->
@@ -434,6 +435,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="lwl" to="lwl_Thai_TH"/>		<!--Eastern Lawa‧?‧?	➡ Eastern Lawa‧Thai‧Thailand-->
 		<likelySubtag from="lzh" to="lzh_Hans_CN"/>		<!--Literary Chinese‧?‧?	➡ Literary Chinese‧Simplified‧China-->
 		<likelySubtag from="lzz" to="lzz_Latn_TR"/>		<!--Laz‧?‧?	➡ Laz‧Latin‧Türkiye-->
+		<likelySubtag from="lzz_Geor" to="lzz_Geor_GE"/>		<!--Laz‧Georgian‧?	➡ Laz‧Georgian‧Georgia-->
 		<likelySubtag from="mad" to="mad_Latn_ID"/>		<!--Madurese‧?‧?	➡ Madurese‧Latin‧Indonesia-->
 		<likelySubtag from="maf" to="maf_Latn_CM"/>		<!--Mafa‧?‧?	➡ Mafa‧Latin‧Cameroon-->
 		<likelySubtag from="mag" to="mag_Deva_IN"/>		<!--Magahi‧?‧?	➡ Magahi‧Devanagari‧India-->
@@ -498,6 +500,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="mzn" to="mzn_Arab_IR"/>		<!--Mazanderani‧?‧?	➡ Mazanderani‧Arabic‧Iran-->
 		<likelySubtag from="na" to="na_Latn_NR"/>		<!--Nauru‧?‧?	➡ Nauru‧Latin‧Nauru-->
 		<likelySubtag from="nan" to="nan_Hans_CN"/>		<!--Min Nan Chinese‧?‧?	➡ Min Nan Chinese‧Simplified‧China-->
+		<likelySubtag from="nan_Hant" to="nan_Hant_TW"/>		<!--Min Nan Chinese‧Traditional‧?	➡ Min Nan Chinese‧Traditional‧Taiwan-->
 		<likelySubtag from="nap" to="nap_Latn_IT"/>		<!--Neapolitan‧?‧?	➡ Neapolitan‧Latin‧Italy-->
 		<likelySubtag from="naq" to="naq_Latn_NA"/>		<!--Nama‧?‧?	➡ Nama‧Latin‧Namibia-->
 		<likelySubtag from="nb" to="nb_Latn_NO"/>		<!--Norwegian Bokmål‧?‧?	➡ Norwegian Bokmål‧Latin‧Norway-->
@@ -703,10 +706,10 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="tiv" to="tiv_Latn_NG"/>		<!--Tiv‧?‧?	➡ Tiv‧Latin‧Nigeria-->
 		<likelySubtag from="tk" to="tk_Latn_TM"/>		<!--Turkmen‧?‧?	➡ Turkmen‧Latin‧Turkmenistan-->
 		<likelySubtag from="tkl" to="tkl_Latn_TK"/>		<!--Tokelau‧?‧?	➡ Tokelau‧Latin‧Tokelau-->
-		<likelySubtag from="tkr" to="tkr_Latn_AZ"/>		<!--Tsakhur‧?‧?	➡ Tsakhur‧Latin‧Azerbaijan-->
+		<likelySubtag from="tkr" to="tkr_Cyrl_AZ"/>		<!--Tsakhur‧?‧?	➡ Tsakhur‧Cyrillic‧Azerbaijan-->
 		<likelySubtag from="tkt" to="tkt_Deva_NP"/>		<!--Kathoriya Tharu‧?‧?	➡ Kathoriya Tharu‧Devanagari‧Nepal-->
 		<likelySubtag from="tl" to="tl_Latn_PH"/>		<!--Tagalog‧?‧?	➡ Tagalog‧Latin‧Philippines-->
-		<likelySubtag from="tly" to="tly_Latn_AZ"/>		<!--Talysh‧?‧?	➡ Talysh‧Latin‧Azerbaijan-->
+		<likelySubtag from="tly" to="tly_Arab_AZ"/>		<!--Talysh‧?‧?	➡ Talysh‧Arabic‧Azerbaijan-->
 		<likelySubtag from="tmh" to="tmh_Latn_NE"/>		<!--Tamashek‧?‧?	➡ Tamashek‧Latin‧Niger-->
 		<likelySubtag from="tn" to="tn_Latn_ZA"/>		<!--Tswana‧?‧?	➡ Tswana‧Latin‧South Africa-->
 		<likelySubtag from="tnr" to="tnr_Latn_SN"/>		<!--Ménik‧?‧?	➡ Ménik‧Latin‧Senegal-->
@@ -725,7 +728,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="tt" to="tt_Cyrl_RU"/>		<!--Tatar‧?‧?	➡ Tatar‧Cyrillic‧Russia-->
 		<likelySubtag from="ttj" to="ttj_Latn_UG"/>		<!--Tooro‧?‧?	➡ Tooro‧Latin‧Uganda-->
 		<likelySubtag from="tts" to="tts_Thai_TH"/>		<!--Northeastern Thai‧?‧?	➡ Northeastern Thai‧Thai‧Thailand-->
-		<likelySubtag from="ttt" to="ttt_Latn_AZ"/>		<!--Muslim Tat‧?‧?	➡ Muslim Tat‧Latin‧Azerbaijan-->
+		<likelySubtag from="ttt" to="ttt_Cyrl_AZ"/>		<!--Muslim Tat‧?‧?	➡ Muslim Tat‧Cyrillic‧Azerbaijan-->
 		<likelySubtag from="tum" to="tum_Latn_MW"/>		<!--Tumbuka‧?‧?	➡ Tumbuka‧Latin‧Malawi-->
 		<likelySubtag from="tvl" to="tvl_Latn_TV"/>		<!--Tuvalu‧?‧?	➡ Tuvalu‧Latin‧Tuvalu-->
 		<likelySubtag from="twq" to="twq_Latn_NE"/>		<!--Tasawaq‧?‧?	➡ Tasawaq‧Latin‧Niger-->
@@ -1036,6 +1039,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_Ahom" to="aho_Ahom_IN"/>		<!--?‧Ahom‧?	➡ Ahom‧Ahom‧India-->
 		<likelySubtag from="und_Arab" to="ar_Arab_EG"/>		<!--?‧Arabic‧?	➡ Arabic‧Arabic‧Egypt-->
 		<likelySubtag from="und_Arab_AF" to="fa_Arab_AF"/>		<!--?‧Arabic‧Afghanistan	➡ Persian‧Arabic‧Afghanistan-->
+		<likelySubtag from="und_Arab_AZ" to="tly_Arab_AZ"/>		<!--?‧Arabic‧Azerbaijan	➡ Talysh‧Arabic‧Azerbaijan-->
 		<likelySubtag from="und_Arab_BN" to="ms_Arab_BN"/>		<!--?‧Arabic‧Brunei	➡ Malay‧Arabic‧Brunei-->
 		<likelySubtag from="und_Arab_CC" to="ms_Arab_CC"/>		<!--?‧Arabic‧Cocos (Keeling) Islands	➡ Malay‧Arabic‧Cocos (Keeling) Islands-->
 		<likelySubtag from="und_Arab_CN" to="ug_Arab_CN"/>		<!--?‧Arabic‧China	➡ Uyghur‧Arabic‧China-->
@@ -1131,6 +1135,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_Hani" to="zh_Hani_CN"/>		<!--?‧Han‧?	➡ Chinese‧Han‧China-->
 		<likelySubtag from="und_Hano" to="hnn_Hano_PH"/>		<!--?‧Hanunoo‧?	➡ Hanunoo‧Hanunoo‧Philippines-->
 		<likelySubtag from="und_Hans" to="zh_Hans_CN"/>		<!--?‧Simplified‧?	➡ Chinese‧Simplified‧China-->
+		<likelySubtag from="und_Hans_TW" to="nan_Hans_TW"/>		<!--?‧Simplified‧Taiwan	➡ Min Nan Chinese‧Simplified‧Taiwan-->
 		<likelySubtag from="und_Hant" to="zh_Hant_TW"/>		<!--?‧Traditional‧?	➡ Chinese‧Traditional‧Taiwan-->
 		<likelySubtag from="und_Hant_CA" to="yue_Hant_CA"/>		<!--?‧Traditional‧Canada	➡ Cantonese‧Traditional‧Canada-->
 		<likelySubtag from="und_Hant_CN" to="yue_Hant_CN"/>		<!--?‧Traditional‧China	➡ Cantonese‧Traditional‧China-->

diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml
@@ -1647,7 +1647,7 @@ XXX Code for transations where no currency is involved
 		<language type="ha" scripts="Arab Latn"/>
 		<language type="ha" territories="NE NG" alt="secondary"/>
 		<language type="hai" scripts="Latn"/>
-		<language type="hak" scripts="Hans"/>
+		<language type="hak" scripts="Hans Hant" territories="TW"/>
 		<language type="hak" territories="CN" alt="secondary"/>
 		<language type="haw" scripts="Latn"/>
 		<language type="haw" territories="US" alt="secondary"/>
@@ -1890,7 +1890,7 @@ XXX Code for transations where no currency is involved
 		<language type="lv" scripts="Latn" territories="LV"/>
 		<language type="lwl" scripts="Thai"/>
 		<language type="lzh" scripts="Hans" alt="secondary"/>
-		<language type="lzz" scripts="Latn Geor"/>
+		<language type="lzz" scripts="Geor Latn"/>
 		<language type="mad" scripts="Latn"/>
 		<language type="mad" territories="ID" alt="secondary"/>
 		<language type="maf" scripts="Latn"/>
@@ -1979,7 +1979,7 @@ XXX Code for transations where no currency is involved
 		<language type="mzn" scripts="Arab"/>
 		<language type="mzn" territories="IR" alt="secondary"/>
 		<language type="na" scripts="Latn" territories="NR"/>
-		<language type="nan" scripts="Hans"/>
+		<language type="nan" scripts="Hans Hant" territories="TW"/>
 		<language type="nan" territories="CN" alt="secondary"/>
 		<language type="nap" scripts="Latn"/>
 		<language type="naq" scripts="Latn"/>
@@ -2070,14 +2070,15 @@ XXX Code for transations where no currency is involved
 		<language type="peo" scripts="Xpeo" alt="secondary"/>
 		<language type="pfl" scripts="Latn"/>
 		<language type="phn" scripts="Phnx" alt="secondary"/>
-		<language type="pi" scripts="Deva Sinh Thai" alt="secondary"/>
+		<language type="pi" scripts="Deva Mymr Sinh Thai" alt="secondary"/>
 		<language type="pis" scripts="Latn"/>
 		<language type="pis" territories="SB" alt="secondary"/>
 		<language type="pko" scripts="Latn"/>
 		<language type="pl" scripts="Latn" territories="PL"/>
 		<language type="pl" territories="GB" alt="secondary"/>
 		<language type="pms" scripts="Latn"/>
-		<language type="pnt" scripts="Grek Cyrl Latn"/>
+		<language type="pnt" scripts="Grek"/>
+		<language type="pnt" scripts="Cyrl Latn" alt="secondary"/>
 		<language type="pon" scripts="Latn"/>
 		<language type="pon" territories="FM" alt="secondary"/>
 		<language type="pqm" scripts="Latn"/>
@@ -2277,10 +2278,10 @@ XXX Code for transations where no currency is involved
 		<language type="tk" scripts="Arab Cyrl Latn" territories="TM"/>
 		<language type="tk" territories="AF IR" alt="secondary"/>
 		<language type="tkl" scripts="Latn" territories="TK"/>
-		<language type="tkr" scripts="Latn Cyrl"/>
+		<language type="tkr" scripts="Cyrl Latn"/>
 		<language type="tkt" scripts="Deva"/>
 		<language type="tli" scripts="Latn"/>
-		<language type="tly" scripts="Latn Arab Cyrl"/>
+		<language type="tly" scripts="Arab Cyrl Latn"/>
 		<language type="tly" territories="AZ" alt="secondary"/>
 		<language type="tmh" scripts="Latn"/>
 		<language type="tmh" territories="NE" alt="secondary"/>
@@ -2309,7 +2310,7 @@ XXX Code for transations where no currency is involved
 		<language type="ttj" scripts="Latn"/>
 		<language type="tts" scripts="Thai"/>
 		<language type="tts" territories="TH" alt="secondary"/>
-		<language type="ttt" scripts="Latn Cyrl"/>
+		<language type="ttt" scripts="Cyrl Latn"/>
 		<language type="ttt" scripts="Arab" alt="secondary"/>
 		<language type="tum" scripts="Latn"/>
 		<language type="tum" territories="MW" alt="secondary"/>
@@ -4226,7 +4227,6 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="ku" populationPercent="5.5"/>	<!--Kurdish-->
 			<languagePopulation type="apc" populationPercent="5.2" references="R1173"/>	<!--Levantine Arabic-->
 			<languagePopulation type="zza" populationPercent="1.4"/>	<!--Zaza-->
-			<languagePopulation type="kaa" populationPercent="0.1" references="R1199"/>	<!--Kara-Kalpak-->
 			<languagePopulation type="kbd" populationPercent="0.77"/>	<!--Kabardian-->
 			<languagePopulation type="az" populationPercent="0.74"/>	<!--Azerbaijani-->
 			<languagePopulation type="az_Arab" populationPercent="0.65"/>	<!--Azerbaijani (Arabic)-->
@@ -4235,6 +4235,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="bg" populationPercent="0.42"/>	<!--Bulgarian-->
 			<languagePopulation type="ady" populationPercent="0.39"/>	<!--Adyghe-->
 			<languagePopulation type="kiu" populationPercent="0.19"/>	<!--Kirmanjki-->
+			<languagePopulation type="kaa" populationPercent="0.1" references="R1199"/>	<!--Kara-Kalpak-->
 			<languagePopulation type="hy" populationPercent="0.056"/>	<!--Armenian-->
 			<languagePopulation type="ka" populationPercent="0.056"/>	<!--Georgian-->
 			<languagePopulation type="sr_Latn" writingPercent="5" populationPercent="0.028" references="R1017"/>	<!--Serbian (Latin)-->
@@ -4257,6 +4258,8 @@ XXX Code for transations where no currency is involved
 		</territory>
 		<territory type="TW" gdp="1143000000000" literacyPercent="96.1" population="23595300">	<!--Taiwan-->
 			<languagePopulation type="zh_Hant" populationPercent="95" officialStatus="official"/>	<!--Chinese (Traditional)-->
+			<languagePopulation type="nan" populationPercent="57" officialStatus="official" references="R1219"/>	<!--Min Nan Chinese-->
+			<languagePopulation type="hak" populationPercent="11" officialStatus="official" references="R1333"/>	<!--Hakka Chinese-->
 			<languagePopulation type="trv" populationPercent="0.02"/>	<!--Taroko-->
 		</territory>
 		<territory type="TZ" gdp="234100000000" literacyPercent="67.8" population="67462100">	<!--Tanzania-->
@@ -5692,6 +5695,7 @@ XXX Code for transations where no currency is involved
 		<reference type="R1216">This is base pop for &quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;fub&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot;&quot; lang code; ff shows as a macrolanguage</reference>
 		<reference type="R1217" uri="http://www.ethnologue.com/language/bkm">[missing]</reference>
 		<reference type="R1218" uri="http://en.wikipedia.org/wiki/Vietnamese_language">(could be higher if 2nd lang included; no data yet)</reference>
+		<reference type="R1219" uri="https://en.wikipedia.org/wiki/Taiwanese_Hokkien">[missing]</reference>
 		<reference type="R1220" uri="http://www.ethnologue.com/18/language/knf/">[missing]</reference>
 		<reference type="R1221" uri="https://www.cia.gov/library/publications/the-world-factbook/geos/cc.html">[missing]</reference>
 		<reference type="R1222" uri="http://www.ethnologue.com/show_language.asp?code=dsb">pop 7k. Figure is questionable writing pop artificially set to 5% see also http://en.wikipedia.org/wiki/Lower_Sorbian</reference>
@@ -5805,5 +5809,6 @@ XXX Code for transations where no currency is involved
 		<reference type="R1330" uri="https://en.wikipedia.org/wiki/Languages_of_the_United_Kingdom">Analyzed from 2011 UK census and other sources</reference>
 		<reference type="R1331" uri="https://en.wikipedia.org/wiki/Languages_of_Canada">In total 86.2% of Canadians have working knowledge of English while 29.8% have a working knowledge of French.</reference>
 		<reference type="R1332" uri="https://statisticsmaldives.gov.mv/statistical-release-iii-education">2014 Maldives: 98% literacy in Divehi, 75% in English</reference>
+		<reference type="R1333" uri="https://en.wikipedia.org/wiki/Taiwanese_Hakka">[missing]</reference>
 	</references>
 </supplementalData>
diff --git a/tools/cldr-code/src/main/java/org/unicode/cldr/tool/GenerateLikelySubtags.java b/tools/cldr-code/src/main/java/org/unicode/cldr/tool/GenerateLikelySubtags.java
@@ -374,6 +374,7 @@ public static void main(String[] args) throws IOException {
                                 {"ff_NG", "ff_Latn_NG"},
                                 {"ff_SL", "ff_Latn_SL"},
                                 {"ff_Adlm", "ff_Adlm_GN"},
+                                {"hak_Hant", "hak_Hant_TW"},
                                 {"ia", "ia_Latn_001"},
                                 {"ia_Latn", "ia_Latn_001"},
                                 {"io", "io_Latn_001"},
@@ -392,6 +393,9 @@ public static void main(String[] args) throws IOException {
                                 {"mro", "mro_Mroo_BD"},
                                 {"mro_BD", "mro_Mroo_BD"},
                                 {"ms_Arab", "ms_Arab_MY"},
+                                {"nan", "nan_Hans_CN"},
+                                {"nan_Hans", "nan_Hans_CN"},
+                                {"nan_Hant", "nan_Hant_TW"},
                                 {"pap", "pap_Latn_CW"},
                                 {"pap_Latn", "pap_Latn_CW"},
                                 {
@@ -469,12 +473,14 @@ public static void main(String[] args) throws IOException {
                                 //        {"cr", "cr_Cans_CA"},
                                 //        {"hif", "hif_Latn_FJ"},
                                 //        {"gon", "gon_Telu_IN"},
-                                //        {"lzz", "lzz_Latn_TR"},
+                                       {"lzz", "lzz_Latn_TR"},
+                                       {"lzz_TR", "lzz_Latn_TR"},
+                                       {"lzz_Geor", "lzz_Geor_GE"},
                                 //        {"lif", "lif_Deva_NP"},
                                 //        {"unx", "unx_Beng_IN"},
                                 //        {"unr", "unr_Beng_IN"},
                                 //        {"ttt", "ttt_Latn_AZ"},
-                                //        {"pnt", "pnt_Grek_GR"},
+                                    //    {"pnt", "pnt_Grek_GR"},
                                 //        {"tly", "tly_Latn_AZ"},
                                 //        {"tkr", "tkr_Latn_AZ"},
                                 //        {"bsq", "bsq_Bass_LR"},

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
@@ -297,6 +297,7 @@ ha	Hausa	primary	Arab	Arabic
 ha	Hausa	primary	Latn	Latin
 hai	Haida	primary	Latn	Latin
 hak	Hakka Chinese	primary	Hans	Simplified
+hak	Hakka Chinese	primary	Hant	Traditional
 haw	Hawaiian	primary	Latn	Latin
 haz	Hazaragi	primary	Arab	Arabic
 he	Hebrew	primary	Hebr	Hebrew
@@ -564,6 +565,7 @@ myz	Classical Mandaic	secondary	Mand	Mandaean
 mzn	Mazanderani	primary	Arab	Arabic
 na	Nauru	primary	Latn	Latin
 nan	Min Nan Chinese	primary	Hans	Simplified
+nan	Min Nan Chinese	primary	Hant	Traditional
 nap	Neapolitan	primary	Latn	Latin
 naq	Nama	primary	Latn	Latin
 nb	Norwegian (Bokmål)	primary	Latn	Latin
@@ -633,16 +635,17 @@ pdt	Plautdietsch	primary	Latn	Latin
 peo	Old Persian	secondary	Xpeo	Old Persian
 pfl	Palatine German	primary	Latn	Latin
 phn	Phoenician	secondary	Phnx	Phoenician
+pi	Pali	primary	Mymr	Myanmar
 pi	Pali	secondary	Deva	Devanagari
 pi	Pali	secondary	Sinh	Sinhala
 pi	Pali	secondary	Thai	Thai
 pis	Pijin	primary	Latn	Latin
 pko	Pökoot	primary	Latn	Latin
 pl	Polish	primary	Latn	Latin
 pms	Piedmontese	primary	Latn	Latin
-pnt	Pontic	primary	Cyrl	Cyrillic
 pnt	Pontic	primary	Grek	Greek
-pnt	Pontic	primary	Latn	Latin
+pnt	Pontic	secondary	Cyrl	Cyrillic
+pnt	Pontic	secondary	Latn	Latin
 pon	Pohnpeian	primary	Latn	Latin
 pqm	Malecite	primary	Latn	Latin
 prd	Parsi-Dari	primary	Arab	Arabic