CLDR-9791 Add language for South Georgia and Bouvet Islands (#4166)

conradarcturus · web-flow · commit 959045eb0da4 · 2024-10-30T07:26:04.000-07:00
diff --git a/common/main/en_GS.xml b/common/main/en_GS.xml
@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
+<!-- Copyright © 1991-2024 Unicode, Inc.
+For terms of use, see https://www.unicode.org/copyright.html
+SPDX-License-Identifier: Unicode-3.0
+CLDR data files are interpreted according to the LDML specification (https://unicode.org/reports/tr35/)
+-->
+<ldml>
+	<identity>
+		<version number="$Revision$"/>
+		<language type="en"/>
+		<territory type="GS"/>
+	</identity>
+</ldml>
diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml
@@ -877,6 +877,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_BQ" to="pap_Latn_BQ"/>		<!--?‧?‧Caribbean Netherlands	➡ Papiamento‧Latin‧Caribbean Netherlands-->
 		<likelySubtag from="und_BR" to="pt_Latn_BR"/>		<!--?‧?‧Brazil	➡ Portuguese‧Latin‧Brazil-->
 		<likelySubtag from="und_BT" to="dz_Tibt_BT"/>		<!--?‧?‧Bhutan	➡ Dzongkha‧Tibetan‧Bhutan-->
+		<likelySubtag from="und_BV" to="no_Latn_BV"/>		<!--?‧?‧Bouvet Island	➡ Norwegian‧Latin‧Bouvet Island-->
 		<likelySubtag from="und_BY" to="be_Cyrl_BY"/>		<!--?‧?‧Belarus	➡ Belarusian‧Cyrillic‧Belarus-->
 		<likelySubtag from="und_CC" to="ms_Arab_CC"/>		<!--?‧?‧Cocos (Keeling) Islands	➡ Malay‧Arabic‧Cocos (Keeling) Islands-->
 		<likelySubtag from="und_CD" to="sw_Latn_CD"/>		<!--?‧?‧Congo - Kinshasa	➡ Swahili‧Latin‧Congo - Kinshasa-->
diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml
@@ -1540,7 +1540,7 @@ XXX Code for transations where no currency is involved
 		<language type="eka" scripts="Latn"/>
 		<language type="eky" scripts="Kali"/>
 		<language type="el" scripts="Grek" territories="CY GR"/>
-		<language type="en" scripts="Latn" territories="AG AI AS AU BB BI BM BS BW BZ CA CC CK CM CQ CX DG DM ER FJ FK FM GB GD GG GH GI GM GU GY HK IE IM IN IO JE JM KE KI KN KY LC LR LS MG MH MP MS MT MU MW NA NF NG NR NU NZ PG PH PK PN PR PW RW SB SC SD SG SH SL SS SX SZ TC TK TO TT TV TZ UG UM US VC VG VI VU WS ZA ZM ZW"/>
+		<language type="en" scripts="Latn" territories="AG AI AS AU BB BI BM BS BW BZ CA CC CK CM CQ CX DG DM ER FJ FK FM GB GD GG GH GI GM GS GU GY HK IE IM IN IO JE JM KE KI KN KY LC LR LS MG MH MP MS MT MU MW NA NF NG NR NU NZ PG PH PK PN PR PW RW SB SC SD SG SH SL SS SX SZ TC TK TO TT TV TZ UG UM US VC VG VI VU WS ZA ZM ZW"/>
 		<language type="en" scripts="Dsrt Shaw" territories="AC AE AR AT BA BD BE BG BR CH CL CY CZ DE DK DZ EE EG ES ET FI FR GR HR HU IL IQ IT JO KZ LB LK LT LU LV MA MV MX MY NL PL PT RO SE SI SK TA TH TR YE" alt="secondary"/>
 		<language type="enm" scripts="Latn" alt="secondary"/>
 		<language type="eo" scripts="Latn"/>
@@ -2013,6 +2013,7 @@ XXX Code for transations where no currency is involved
 		<language type="nn" scripts="Latn" territories="NO"/>
 		<language type="nnh" scripts="Latn"/>
 		<language type="no" scripts="Latn" territories="NO"/>
+		<language type="no" territories="BV" alt="secondary"/>
 		<language type="nod" scripts="Lana"/>
 		<language type="nod" territories="TH" alt="secondary"/>
 		<language type="noe" scripts="Deva"/>
@@ -2334,7 +2335,7 @@ XXX Code for transations where no currency is involved
 		<language type="uli" scripts="Latn"/>
 		<language type="umb" scripts="Latn"/>
 		<language type="umb" territories="AO" alt="secondary"/>
-		<language type="und" territories="AQ BV CP GS HM" alt="secondary"/>
+		<language type="und" territories="AQ CP HM" alt="secondary"/>
 		<language type="unr" scripts="Beng Deva"/>
 		<language type="unr" territories="IN" alt="secondary"/>
 		<language type="unx" scripts="Beng Deva"/>
@@ -2638,7 +2639,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="lep" populationPercent="3.9"/>	<!--Lepcha-->
 		</territory>
 		<territory type="BV" gdp="54050" literacyPercent="99" population="1">	<!--Bouvet Island-->
-			<languagePopulation type="und" populationPercent="100"/>	<!--Unknown language-->
+			<languagePopulation type="no" populationPercent="100" references="R1062"/>	<!--Norwegian-->
 		</territory>
 		<territory type="BW" gdp="46740000000" literacyPercent="85.1" population="2450670">	<!--Botswana-->
 			<languagePopulation type="en" populationPercent="81" officialStatus="official" references="R1009"/>	<!--English-->
@@ -2830,7 +2831,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="yrl" populationPercent="0.006" references="R1327"/>	<!--Nheengatu-->
 		</territory>
 		<territory type="CP" gdp="55050" literacyPercent="99" population="1">	<!--Clipperton Island-->
-			<languagePopulation type="und" populationPercent="100" references="R1062"/>	<!--Unknown language-->
+			<languagePopulation type="und" populationPercent="100" references="R1178"/>	<!--Unknown language-->
 		</territory>
 		<territory type="CQ" gdp="21940000" literacyPercent="99" population="492">	<!--Sark-->
 			<languagePopulation type="en" populationPercent="98" officialStatus="official" references="R1166"/>	<!--English-->
@@ -3148,7 +3149,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="tsd" populationPercent="0.0019"/>	<!--Tsakonian-->
 		</territory>
 		<territory type="GS" gdp="1081000" literacyPercent="99" population="20">	<!--South Georgia & South Sandwich Islands-->
-			<languagePopulation type="und" literacyPercent="100" populationPercent="100" references="R1178"/>	<!--Unknown language-->
+			<languagePopulation type="en" populationPercent="100" officialStatus="official" references="R1338"/>	<!--English-->
 		</territory>
 		<territory type="GT" gdp="223200000000" literacyPercent="75.9" population="18255200">	<!--Guatemala-->
 			<languagePopulation type="es" populationPercent="93" officialStatus="official" references="R1227"/>	<!--Spanish-->
@@ -5462,7 +5463,7 @@ XXX Code for transations where no currency is involved
 
 	<parentLocales>
 		<parentLocale parent="root" localeRules="nonlikelyScript" locales="az_Arab az_Cyrl bal_Latn blt_Latn bm_Nkoo bs_Cyrl byn_Latn cu_Glag dje_Arab dyo_Arab en_Dsrt en_Shaw ff_Adlm ff_Arab ha_Arab iu_Latn kaa_Latn kk_Arab kok_Latn ks_Deva ku_Arab kxv_Deva kxv_Orya kxv_Telu ky_Arab ky_Latn ml_Arab mn_Mong mni_Mtei ms_Arab pa_Arab sat_Deva sd_Deva sd_Khoj sd_Sind shi_Latn so_Arab sr_Latn sw_Arab tg_Arab ug_Cyrl uz_Arab uz_Cyrl vai_Latn wo_Arab yo_Arab yue_Hans zh_Hant"/>
-		<parentLocale parent="en_001" locales="en_150 en_AG en_AI en_AU en_BB en_BM en_BS en_BW en_BZ en_CC en_CK en_CM en_CX en_CY en_DG en_DM en_ER en_FJ en_FK en_FM en_GB en_GD en_GG en_GH en_GI en_GM en_GY en_HK en_ID en_IE en_IL en_IM en_IN en_IO en_JE en_JM en_KE en_KI en_KN en_KY en_LC en_LR en_LS en_MG en_MO en_MS en_MT en_MU en_MV en_MW en_MY en_NA en_NF en_NG en_NR en_NU en_NZ en_PG en_PK en_PN en_PW en_RW en_SB en_SC en_SD en_SG en_SH en_SL en_SS en_SX en_SZ en_TC en_TK en_TO en_TT en_TV en_TZ en_UG en_VC en_VG en_VU en_WS en_ZA en_ZM en_ZW"/>
+		<parentLocale parent="en_001" locales="en_150 en_AG en_AI en_AU en_BB en_BM en_BS en_BW en_BZ en_CC en_CK en_CM en_CX en_CY en_DG en_DM en_ER en_FJ en_FK en_FM en_GB en_GD en_GG en_GH en_GI en_GM en_GS en_GY en_HK en_ID en_IE en_IL en_IM en_IN en_IO en_JE en_JM en_KE en_KI en_KN en_KY en_LC en_LR en_LS en_MG en_MO en_MS en_MT en_MU en_MV en_MW en_MY en_NA en_NF en_NG en_NR en_NU en_NZ en_PG en_PK en_PN en_PW en_RW en_SB en_SC en_SD en_SG en_SH en_SL en_SS en_SX en_SZ en_TC en_TK en_TO en_TT en_TV en_TZ en_UG en_VC en_VG en_VU en_WS en_ZA en_ZM en_ZW"/>
 		<parentLocale parent="en_150" locales="en_AT en_BE en_CH en_DE en_DK en_FI en_NL en_SE en_SI"/>
 		<parentLocale parent="en_IN" locales="hi_Latn"/>
 		<parentLocale parent="es_419" locales="es_AR es_BO es_BR es_BZ es_CL es_CO es_CR es_CU es_DO es_EC es_GT es_HN es_JP es_MX es_NI es_PA es_PE es_PR es_PY es_SV es_US es_UY es_VE"/>
@@ -5549,7 +5550,7 @@ XXX Code for transations where no currency is involved
 		<reference type="R1059" uri="https://www.cia.gov/cia/publications/factbook/fields/2098.html">English official on some islands, total 9.4%</reference>
 		<reference type="R1060" uri="https://www.nsf.gov/od/opp/support/southp.jsp">https://astro.uchicago.edu/cara/vtour/mcmurdo/ https://www.usap.gov/videoclipsandmaps/mcmwebcam.cfm Winter population is listed.</reference>
 		<reference type="R1061" uri="https://www.ethnologue.com/show_language.asp?code=tem">1.2mil 1st lang + 240k 2nd lang users, low literacy</reference>
-		<reference type="R1062" uri="https://en.wikipedia.org/wiki/Clipperton_Island">[missing]</reference>
+		<reference type="R1062" uri="https://en.wikipedia.org/wiki/Bouvet_Island">Has rotating Norwegian population at Norvegia Station</reference>
 		<reference type="R1063" uri="https://www.flw.com/languages/creoleseychelles.htm">https://www.mavicanet.com/directory/eng/2436.html</reference>
 		<reference type="R1064" uri="https://www.cia.gov/cia/publications/factbook/geos/hm.html">Uninhabited, barren, sub-Antarctic islands</reference>
 		<reference type="R1065" uri="https://en.wikipedia.org/wiki/Diego_Garcia">[missing]</reference>
@@ -5665,7 +5666,7 @@ XXX Code for transations where no currency is involved
 		<reference type="R1175" uri="https://en.wikipedia.org/wiki/Saho_language">[missing]</reference>
 		<reference type="R1176" uri="https://en.wikipedia.org/wiki/Spanish_language#Spain">98.8% speak Spanish. Also, https://www.cia.gov/library/publications/the-world-factbook/geos/sp.html</reference>
 		<reference type="R1177" uri="https://www.cia.gov/library/publications/the-world-factbook/geos/sp.html">[missing]</reference>
-		<reference type="R1178" uri="https://www.cia.gov/cia/publications/factbook/geos/sx.html">No indigenous inhabitants. https://en.wikipedia.org/wiki/Heard_Island_and_McDonald_Islands</reference>
+		<reference type="R1178" uri="https://en.wikipedia.org/wiki/Clipperton_Island">Colony of France but uninhabited</reference>
 		<reference type="R1179" uri="https://www.cia.gov/cia/publications/factbook/geos/io.html">No indigenous inhabitants. https://en.wikipedia.org/wiki/British_Indian_Ocean_Territory</reference>
 		<reference type="R1180" uri="https://www.ethnologue.com/show_language.asp?code=saq">Many also use Swahili</reference>
 		<reference type="R1181" uri="https://www.ethnologue.com/show_language.asp?code=shi">Latin is not shown as being used, rather Arabic</reference>
@@ -5825,5 +5826,6 @@ XXX Code for transations where no currency is involved
 		<reference type="R1335" uri="https://en.wikipedia.org/wiki/Greeks_in_Russia_and_Ukraine#cite_ref-15">Greek population in Russia -- most ancestrally used Pontic Greek -- modern usage almost certainly has dropped off but we don't have clear statistics on current usage.</reference>
 		<reference type="R1336" uri="https://joshuaproject.net/people_groups/14444/TU">[missing]</reference>
 		<reference type="R1337" uri="https://www.wsj.com/articles/BL-263B-3637">Lower estimate of Coptic population, actual language literacy unknown </reference>
+		<reference type="R1338" uri="https://commonwealthchamber.com/associated-territories/south-georgia-and-the-south-sandwich-islands/">[missing]</reference>
 	</references>
 </supplementalData>
diff --git a/common/testData/localeIdentifiers/likelySubtags.txt b/common/testData/localeIdentifiers/likelySubtags.txt
@@ -512,6 +512,11 @@ hsb-AQ ;	hsb-Latn-AQ ;	hsb-AQ ;
 hsb-DE ;	hsb-Latn-DE ;	hsb ;	
 hsb-Egyp ;	hsb-Egyp-DE ;	hsb-Egyp ;	
 hsb-Latn ;	hsb-Latn-DE ;	hsb ;	
+ht ;	ht-Latn-HT ;	ht ;	
+ht-AQ ;	ht-Latn-AQ ;	ht-AQ ;	
+ht-Egyp ;	ht-Egyp-HT ;	ht-Egyp ;	
+ht-HT ;	ht-Latn-HT ;	ht ;	
+ht-Latn ;	ht-Latn-HT ;	ht ;	
 hu ;	hu-Latn-HU ;	hu ;	
 hu-AQ ;	hu-Latn-AQ ;	hu-AQ ;	
 hu-Egyp ;	hu-Egyp-HU ;	hu-Egyp ;	
diff --git a/common/testData/localeIdentifiers/localeDisplayName.txt b/common/testData/localeIdentifiers/localeDisplayName.txt
@@ -1310,6 +1310,32 @@ nl-Latn-BE; flamšćina (łaćonsce)
 zh-Hans-fonipa; chinšćina [zjednorjena] (FONIPA)
 
 
+@locale=ht
+@languageDisplay=standard
+
+en-MM; anglais (Myanmar [Birmanie])
+es; espagnol
+es-419; espagnol (Amérique latine)
+es-Cyrl-MX; espagnol (cyrillique, Mexique)
+hi-Latn; hindi (latin)
+nl-BE; néerlandais (Belgique)
+nl-Latn-BE; néerlandais (latin, Belgique)
+zh-Hans-fonipa; chinois (simplifié, alphabet phonétique international)
+
+
+@locale=ht
+@languageDisplay=dialect
+
+en-MM; anglais (Myanmar [Birmanie])
+es; espagnol
+es-419; espagnol d’Amérique latine
+es-Cyrl-MX; espagnol du Mexique (cyrillique)
+hi-Latn; hindi (latin)
+nl-BE; flamand
+nl-Latn-BE; flamand (latin)
+zh-Hans-fonipa; chinois simplifié (alphabet phonétique international)
+
+
 @locale=hu
 @languageDisplay=standard
 
diff --git a/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/country_language_population.tsv b/tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/country_language_population.tsv
@@ -113,7 +113,7 @@ Bosnia & Herzegovina	BA	"3,849,891"	98%	"44,830,000,000"	official	Serbian (Latin
 Botswana	BW	"2,249,104"	85%	"39,010,000,000"		Afrikaans	af	"6,000"
 Botswana	BW	"2,249,104"	85%	"39,010,000,000"	official	English	en	81%			"https://www.cia.gov/cia/publications/factbook/geos/bc.html English official, 81% literacy; the figure is derived from literacy * lang pop"
 Botswana	BW	"2,249,104"	85%	"39,010,000,000"	official	Tswana	tn	62%
-Bouvet Island	BV	1	99%	"44,930"		Unknown language	und	1
+Bouvet Island	BV	6	99%	"44,930"		Norwegian	no	100%			https://en.wikipedia.org/wiki/Bouvet_Island Has rotating Norwegian population at Norvegia Station
 Brazil	BR	"208,846,892"	90%	"3,248,000,000,000"		English	en	8%
 Brazil	BR	"208,846,892"	90%	"3,248,000,000,000"		German	de	"1,750,000"
 Brazil	BR	"208,846,892"	90%	"3,248,000,000,000"		Guajajára	gub	"17,500"
@@ -279,7 +279,7 @@ China	CN	"1,384,688,986"	95%	"23,210,000,000,000"		Xiang Chinese	hsn	"39,600,000
 China	CN	"1,384,688,986"	95%	"23,210,000,000,000"	official_regional	Zhuang	za	"4,260,000"
 China	CN	"1,384,688,986"	95%	"23,210,000,000,000"		Hmong Njua	hnj	"56,000"			https://joshuaproject.net/languages/hnj
 Christmas Island	CX	"2,205"	99%	"117,200,000"	official	English	en	"1,400"
-Clipperton Island	CP	1	99%	"42,400"		Unknown language	und	1			https://en.wikipedia.org/wiki/Clipperton_Island
+Clipperton Island	CP	1	99%	"42,400"		Unknown language	und	1			https://en.wikipedia.org/wiki/Clipperton_Island Colony of France but uninhabited
 Cocos (Keeling) Islands	CC	596	99%	"31,690,000"	de_facto_official	English	en	100
 Cocos (Keeling) Islands	CC	596	99%	"31,690,000"		Malay (Arabic)	ms_Arab	496
 Colombia	CO	"48,168,996"	94%	"711,600,000,000"	official	Spanish	es	93%			https://www.cia.gov/cia/publications/factbook/geos/co.html Spanish official
@@ -1230,7 +1230,7 @@ South Africa	ZA	"55,380,210"	93%	"767,200,000,000"	official_regional	Tswana	tn	8
 South Africa	ZA	"55,380,210"	93%	"767,200,000,000"	official_regional	Venda	ve	"1,270,000"	50%
 South Africa	ZA	"55,380,210"	93%	"767,200,000,000"	official_regional	Xhosa	xh	18%	50%
 South Africa	ZA	"55,380,210"	93%	"767,200,000,000"	official_regional	Zulu	zu	24%	50%
-South Georgia & South Sandwich Islands	GS	20	99%	"898,500"		Unknown language	und	20	100%		https://www.cia.gov/cia/publications/factbook/geos/sx.html No indigenous inhabitants. https://en.wikipedia.org/wiki/Heard_Island_and_McDonald_Islands
+South Georgia & South Sandwich Islands	GS	20	100%	"898,500"	official	English	en	100%			https://commonwealthchamber.com/associated-territories/south-georgia-and-the-south-sandwich-islands/
 South Korea	KR	"51,418,097"	98%	"2,035,000,000,000"	official	Korean	ko	100%
 South Sudan	SS	"10,204,581"	27%	"20,010,000,000"		Arabic	ar	27%			https://www.cia.gov/library/publications/the-world-factbook/geos/od.html https://en.wikipedia.org/wiki/South_Sudan
 South Sudan	SS	"10,204,581"	27%	"20,010,000,000"	official	English	en	27%			https://www.cia.gov/library/publications/the-world-factbook/geos/od.html https://en.wikipedia.org/wiki/South_Sudan
