diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml index 42eb17c054b..1ce551c9e89 100644 --- a/common/supplemental/likelySubtags.xml +++ b/common/supplemental/likelySubtags.xml @@ -369,6 +369,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -406,6 +407,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -431,6 +433,8 @@ not be patched by hand, as any changes made in that fashion may be lost. + + @@ -533,6 +537,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -725,6 +730,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -967,7 +973,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -1006,7 +1011,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -1042,7 +1046,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -3982,7 +3985,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -4244,7 +4246,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -4433,14 +4434,12 @@ not be patched by hand, as any changes made in that fashion may be lost. - - @@ -5333,7 +5332,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - @@ -6663,7 +6661,6 @@ not be patched by hand, as any changes made in that fashion may be lost. - diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml index 7e87532db12..028286c1395 100644 --- a/common/supplemental/supplementalData.xml +++ b/common/supplemental/supplementalData.xml @@ -1387,7 +1387,7 @@ XXX Code for transations where no currency is involved - + @@ -2195,6 +2195,7 @@ XXX Code for transations where no currency is involved + @@ -2293,6 +2294,7 @@ XXX Code for transations where no currency is involved + @@ -3658,11 +3660,11 @@ XXX Code for transations where no currency is involved - + - + - + @@ -4208,8 +4210,9 @@ XXX Code for transations where no currency is involved - - + + + @@ -4433,10 +4436,17 @@ XXX Code for transations where no currency is involved - + + - - + + + + + + + + @@ -5591,7 +5601,7 @@ XXX Code for transations where no currency is involved [missing] Deva is the official script for sd in India; set to 55%. Arab, Guru, Khoj also used. The lingua franca of 80% of the population - [missing] + 2016 Census and https://en.wikipedia.org/wiki/Mru_language - More than 95% of Pakistanis can speak or understand Urdu as their second or third language [missing] @@ -5672,7 +5682,7 @@ XXX Code for transations where no currency is involved Used in schools up to University. Also called Sakha. No indigenous inhabitants. http://en.wikipedia.org/wiki/French_Southern_Territories - [missing] + 2022 Census language spoken at home Shows 50% literacy Most also use Swahili with 50% literacy. Only 5% monolingual. Most also use Swahili @@ -5772,7 +5782,7 @@ XXX Code for transations where no currency is involved near zero literacy; pop ~80000 (2009) see David Lawrence, Tanzania and its People, page 121, Google books (baseline) No population figure yet on use of Latin in Vatican. Estimate 100% of Vatican residents can use Latin. - [missing] + 2010 Census: Widely Spoken Language of Communication No figures available for this language. Estimating at 5%. [missing] [missing] diff --git a/common/testData/localeIdentifiers/likelySubtags.txt b/common/testData/localeIdentifiers/likelySubtags.txt index aca47b1a577..a7f083a8125 100644 --- 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 ; @@ -1441,7 +1446,7 @@ und-Latn-MQ ; fr-Latn-MQ ; fr-MQ ; und-Latn-MR ; fr-Latn-MR ; fr-MR ; und-Latn-MS ; en-Latn-MS ; en-MS ; und-Latn-MT ; mt-Latn-MT ; mt ; -und-Latn-MU ; mfe-Latn-MU ; mfe ; +und-Latn-MU ; en-Latn-MU ; en-MU ; und-Latn-MV ; en-Latn-MV ; en-MV ; und-Latn-MW ; en-Latn-MW ; en-MW ; und-Latn-MX ; es-Latn-MX ; es-MX ; @@ -1484,7 +1489,7 @@ und-Latn-SH ; en-Latn-SH ; en-SH ; und-Latn-SI ; sl-Latn-SI ; sl ; und-Latn-SJ ; nb-Latn-SJ ; nb-SJ ; und-Latn-SK ; sk-Latn-SK ; sk ; -und-Latn-SL ; kri-Latn-SL ; kri ; +und-Latn-SL ; en-Latn-SL ; en-SL ; und-Latn-SM ; it-Latn-SM ; it-SM ; und-Latn-SN ; fr-Latn-SN ; fr-SN ; und-Latn-SO ; so-Latn-SO ; so ; @@ -1524,7 +1529,7 @@ und-Latn-WS ; sm-Latn-WS ; sm ; und-Latn-XK ; sq-Latn-XK ; sq-XK ; und-Latn-YT ; fr-Latn-YT ; fr-YT ; und-Latn-ZA ; en-Latn-ZA ; en-ZA ; -und-Latn-ZM ; bem-Latn-ZM ; bem ; +und-Latn-ZM ; en-Latn-ZM ; en-ZM ; und-Latn-ZW ; sn-Latn-ZW ; sn ; und-MA ; ar-Arab-MA ; ar-MA ; und-MC ; fr-Latn-MC ; fr-MC ; @@ -1543,7 +1548,7 @@ und-MQ ; fr-Latn-MQ ; fr-MQ ; und-MR ; ar-Arab-MR ; ar-MR ; und-MS ; en-Latn-MS ; en-MS ; und-MT ; mt-Latn-MT ; mt ; -und-MU ; mfe-Latn-MU ; mfe ; +und-MU ; en-Latn-MU ; en-MU ; und-MV ; dv-Thaa-MV ; dv ; und-MW ; en-Latn-MW ; en-MW ; und-MX ; es-Latn-MX ; es-MX ; @@ -1607,7 +1612,7 @@ und-SH ; en-Latn-SH ; en-SH ; und-SI ; sl-Latn-SI ; sl ; und-SJ ; nb-Latn-SJ ; nb-SJ ; und-SK ; sk-Latn-SK ; sk ; -und-SL ; kri-Latn-SL ; kri ; +und-SL ; en-Latn-SL ; en-SL ; und-SM ; it-Latn-SM ; it-SM ; und-SN ; fr-Latn-SN ; fr-SN ; und-SO ; so-Latn-SO ; so ; @@ -1674,7 +1679,7 @@ und-Yiii ; ii-Yiii-CN ; ii ; und-Yiii-AQ ; ii-Yiii-AQ ; ii-AQ ; und-Yiii-CN ; ii-Yiii-CN ; ii ; und-ZA ; en-Latn-ZA ; en-ZA ; -und-ZM ; bem-Latn-ZM ; bem ; +und-ZM ; en-Latn-ZM ; en-ZM ; und-ZW ; sn-Latn-ZW ; sn ; ur ; ur-Arab-PK ; ur ; ur-AQ ; ur-Arab-AQ ; ur-AQ ; diff --git a/common/testData/localeIdentifiers/localeDisplayName.txt b/common/testData/localeIdentifiers/localeDisplayName.txt index 9abbc13423c..39e14107e8f 100644 --- 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/java/org/unicode/cldr/tool/GenerateLikelySubtags.java b/tools/cldr-code/src/main/java/org/unicode/cldr/tool/GenerateLikelySubtags.java index a67fb3c088f..0bf2237ab29 100644 --- 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 @@ -433,15 +433,11 @@ public static void main(String[] args) throws IOException { {"und_Latn_PH", "fil_Latn_PH"}, {"und_ML", "bm_Latn_ML"}, {"und_Latn_ML", "bm_Latn_ML"}, - {"und_MU", "mfe_Latn_MU"}, - {"und_Latn_MU", "mfe_Latn_MU"}, {"und_NE", "ha_Latn_NE"}, {"und_PH", "fil_Latn_PH"}, {"und_PK", "ur_Arab_PK"}, {"und_SO", "so_Latn_SO"}, {"und_SS", "en_Latn_SS"}, - {"und_TK", "tkl_Latn_TK"}, - {"und_Latn_TK", "tkl_Latn_TK"}, {"vo", "vo_Latn_001"}, {"vo_Latn", "vo_Latn_001"}, // {"yi", "yi_Hebr_001"}, @@ -498,11 +494,7 @@ public static void main(String[] args) throws IOException { // new additions for compatibility with old {"und_419", "es_Latn_419"}, - {"und_ZM", "bem_Latn_ZM"}, - {"und_Latn_ZM", "bem_Latn_ZM"}, {"und_CC", "ms_Arab_CC"}, - {"und_SL", "kri_Latn_SL"}, - {"und_Latn_SL", "kri_Latn_SL"}, {"und_SS", "ar_Arab_SS"}, // additions for missing values from LikelySubtagsText 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 index 7ed8c346c61..737f338d9e1 100644 --- 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 @@ -842,10 +842,10 @@ Mauritania MR "3,840,429" 59% "17,280,000,000" French fr 17% http://www.natio Mauritania MR "3,840,429" 59% "17,280,000,000" Fulah ff 5.7% Mauritania MR "3,840,429" 59% "17,280,000,000" Fulah (Adlam) ff_Adlm 1 No estimate available. Mauritania MR "3,840,429" 59% "17,280,000,000" Wolof wo "10,000" -Mauritius MU "1,364,283" 89% "28,270,000,000" Bhojpuri bho 27% +Mauritius MU "1,364,283" 89% "28,270,000,000" Bhojpuri bho 8.6% Mauritius MU "1,364,283" 89% "28,270,000,000" official English en 72% http://www.chass.utoronto.ca/~cpercy/courses/6362-chiba.htm -Mauritius MU "1,364,283" 89% "28,270,000,000" official French fr 3% -Mauritius MU "1,364,283" 89% "28,270,000,000" Morisyen mfe 90% +Mauritius MU "1,364,283" 89% "28,270,000,000" official French fr 4.4% https://statsmauritius.govmu.org/Documents/Statistics/ESI/2022/EI1687/2022%20Population%20Census_Main%20Results_18112022.pdf 2022 Census language spoken at home +Mauritius MU "1,364,283" 89% "28,270,000,000" Morisyen mfe 90% https://statsmauritius.govmu.org/Documents/Statistics/ESI/2022/EI1687/2022%20Population%20Census_Main%20Results_18112022.pdf 2022 Census language spoken at home Mauritius MU "1,364,283" 89% "28,270,000,000" Tamil ta "34,200" Mauritius MU "1,364,283" 89% "28,270,000,000" Urdu ur 5.2% Mayotte YT "194,000" 92% "953,600,000" Bushi buc 23% @@ -1183,9 +1183,9 @@ Seychelles SC "94,633" 92% "2,750,000,000" Seselwa Creole French crs 98% http Sierra Leone SL "6,312,212" 43% "11,550,000,000" official English en 35% Sierra Leone SL "6,312,212" 43% "11,550,000,000" Fulah ff 1 No estimate available. Sierra Leone SL "6,312,212" 43% "11,550,000,000" Fulah (Adlam) ff_Adlm 1 No estimate available. -Sierra Leone SL "6,312,212" 43% "11,550,000,000" Krio kri 95% https://www.cia.gov/cia/publications/factbook/fields/2098.html 'A lingua franca and a first language for 10% of the population but understood by 95%' http://en.wikipedia.org/wiki/Krio_language -Sierra Leone SL "6,312,212" 43% "11,550,000,000" Mende men 27% -Sierra Leone SL "6,312,212" 43% "11,550,000,000" Timne tem 26% 6% "http://www.ethnologue.com/show_language.asp?code=tem 1.2mil 1st lang + 240k 2nd lang users, low literacy" +Sierra Leone SL "6,312,212" 43% "11,550,000,000" recognized Krio kri 95% https://www.cia.gov/cia/publications/factbook/fields/2098.html 'A lingua franca and a first language for 10% of the population but understood by 95%' http://en.wikipedia.org/wiki/Krio_language +Sierra Leone SL "6,312,212" 43% "11,550,000,000" recognized Mende men 27% +Sierra Leone SL "6,312,212" 43% "11,550,000,000" recognized Timne tem 26% 6% "http://www.ethnologue.com/show_language.asp?code=tem 1.2mil 1st lang + 240k 2nd lang users, low literacy" Singapore SG "5,995,991" 96% "528,100,000,000" official Chinese zh 77% Singapore SG "5,995,991" 96% "528,100,000,000" official English en 93% http://en.wikipedia.org/wiki/Singapore English is the first language learned by half the children by the time they reach preschool age; using 92.6% of pop for the English figure Singapore SG "5,995,991" 96% "528,100,000,000" official Malay ms 14% @@ -1340,8 +1340,9 @@ Togo TG "8,176,449" 60% "12,970,000,000" Ewe ee 17% Togo TG "8,176,449" 60% "12,970,000,000" official French fr 61% Togo TG "8,176,449" 60% "12,970,000,000" Ifè ife "107,000" 15% http://www.ethnologue.com/18/language/ife/ Togo TG "8,176,449" 60% "12,970,000,000" Anii blo "12,300" https://en.wikipedia.org/wiki/Anii_language/ -Tokelau TK "1,285" 94% "1,500,000" official English en 100% -Tokelau TK "1,285" 94% "1,500,000" official Tokelau tkl 100% 5% https://www.cia.gov/library/publications/the-world-factbook/geos/tl.html +Tokelau TK "1,285" 94% "1,500,000" official English en 48.6% 90.4% http://www.tokelau.org.nz/Stats.html 2016 Census +Tokelau TK "1,285" 94% "1,500,000" official Tokelau tkl 88.1% 70.9% http://www.tokelau.org.nz/Stats.html 2016 Census +Tokelau TK "1,285" 94% "1,500,000" Samoan sm 26% http://www.tokelau.org.nz/Stats.html 2016 Census Tonga TO "106,398" 99% "591,000,000" official English en 28% "http://www.pressreference.com/Sw-Ur/Tonga.html The Tonga Chronicle is a government-owned newspaper... It publishes two editions, one in Tongan with a circulation of 5,000, and one in English with a circulation of 1,500; Writing pop figure shown for English is set to 30% of that for Tonga. " Tonga TO "106,398" 99% "591,000,000" official Tongan to 95% Trinidad & Tobago TT "1,215,527" 99% "42,850,000,000" official English en 88% @@ -1501,10 +1502,17 @@ Wallis & Futuna WF "15,763" 50% "60,000,000" Wallisian wls "9,440" Western Sahara EH "619,551" 50% "906,500,000" official Arabic ar 100% Yemen YE "28,667,230" 65% "73,630,000,000" official Arabic ar 74% Yemen YE "28,667,230" 65% "73,630,000,000" English en 9% -Zambia ZM "16,445,079" 61% "68,930,000,000" Bemba bem 31% http://www.ethnologue.com/show_language.asp?code=bem +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Bemba bem 33.5% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Nyanja ny 19.3% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication Zambia ZM "16,445,079" 61% "68,930,000,000" official English en 16% -Zambia ZM "16,445,079" 61% "68,930,000,000" Lozi loz 6% https://en.wikipedia.org/wiki/Lozi_language -Zambia ZM "16,445,079" 61% "68,930,000,000" Nyanja ny 15% +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Tonga (Zambia) toi 11.4% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Lozi loz 5.5% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" Nsenga nse 3.0% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" Lala-Bisa leb 2.8% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" Tumbuka tum 2.6% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Lunda lun 1.9% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Kaonde kqn 1.9% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication +Zambia ZM "16,445,079" 61% "68,930,000,000" recognized Luvale lue 1.5% http://www.zamstats.gov.zm/phocadownload/2010_Census/2010%20Census%20of%20Population%20National%20Analytical%20Report.pdf 2010 Census: Widely Spoken Language of Communication Zimbabwe ZW "14,030,368" 84% "34,270,000,000" official English en 42% "Common lingua franca, widely used. High literacy." Zimbabwe ZW "14,030,368" 84% "34,270,000,000" Kalanga kck 5.3% Zimbabwe ZW "14,030,368" 84% "34,270,000,000" Manyika mxc 6.5%