From d6f6b7f0f7e7cc29af0b1aaf569621064cd8fe86 Mon Sep 17 00:00:00 2001 From: Conrad Nied Date: Tue, 20 Aug 2024 10:21:36 -0700 Subject: [PATCH] CLDR-11888 Update French speakers https://unicode-org.atlassian.net/browse/CLDR-11888 was created to update the French speakers for Djibouti but while I was researching that I found many other Francophone countries that significantly underestimated French populations. Most of those gaps probably come from the number being L1 users but the point of this file is L1+L2 users -- basically how many people in each country could use an interface in this language. See the original data in: https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf mvn package -DskipTests=true java -jar tools/cldr-code/target/cldr-code.jar ConvertLanguageData java -jar tools/cldr-code/target/cldr-code.jar GenerateLikelySubtags --- common/supplemental/likelySubtags.xml | 22 ++++++----- common/supplemental/supplementalData.xml | 39 ++++++++++--------- .../util/data/country_language_population.tsv | 14 +++---- 3 files changed, 40 insertions(+), 35 deletions(-) diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml index 3dc3523d626..341bb7f7a50 100644 --- a/common/supplemental/likelySubtags.xml +++ b/common/supplemental/likelySubtags.xml @@ -433,7 +433,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -497,7 +497,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -566,7 +566,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -703,10 +703,10 @@ not be patched by hand, as any changes made in that fashion may be lost. - + - + @@ -725,7 +725,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -882,7 +882,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -911,7 +911,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -1036,6 +1036,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -1085,7 +1086,7 @@ not be patched by hand, as any changes made in that fashion may be lost. - + @@ -1131,6 +1132,7 @@ not be patched by hand, as any changes made in that fashion may be lost. + @@ -1191,7 +1193,7 @@ 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 7ddde428e6c..1ef75057d40 100644 --- a/common/supplemental/supplementalData.xml +++ b/common/supplemental/supplementalData.xml @@ -1573,7 +1573,7 @@ XXX Code for transations where no currency is involved - + @@ -1647,7 +1647,7 @@ XXX Code for transations where no currency is involved - + @@ -1890,7 +1890,7 @@ XXX Code for transations where no currency is involved - + @@ -1979,7 +1979,7 @@ XXX Code for transations where no currency is involved - + @@ -2077,7 +2077,7 @@ XXX Code for transations where no currency is involved - + @@ -2277,10 +2277,10 @@ XXX Code for transations where no currency is involved - + - + @@ -2309,7 +2309,7 @@ XXX Code for transations where no currency is involved - + @@ -2735,9 +2735,9 @@ XXX Code for transations where no currency is involved + - @@ -2895,10 +2895,10 @@ XXX Code for transations where no currency is involved + - @@ -3182,7 +3182,7 @@ XXX Code for transations where no currency is involved - + @@ -3489,9 +3489,9 @@ XXX Code for transations where no currency is involved + - @@ -3548,8 +3548,8 @@ XXX Code for transations where no currency is involved + - @@ -3653,10 +3653,10 @@ XXX Code for transations where no currency is involved + - @@ -4214,7 +4214,7 @@ XXX Code for transations where no currency is involved - + @@ -4226,7 +4226,6 @@ XXX Code for transations where no currency is involved - @@ -4235,6 +4234,7 @@ XXX Code for transations where no currency is involved + @@ -4257,6 +4257,8 @@ XXX Code for transations where no currency is involved + + @@ -5503,7 +5505,6 @@ XXX Code for transations where no currency is involved Many minor langs; Portuguese official In this and other sources, such as Ethnologue, there is no estimate for number of users. http://en.wikipedia.org/wiki/Filipino_language http://www.ethnologue.com/show_language.asp?code=fil Most of the population uses Creole; see also http://www.country-studies.com/haiti/creole,-literacy,-and-education.html http://en.wikipedia.org/wiki/French_language#Haiti - 400k 2nd language speakers Official language, 37-77% literacy Official language, used in some schools. http://www.censusindia.net/cendat/datatable26.html @@ -5605,7 +5606,6 @@ XXX Code for transations where no currency is involved [missing] - Education is in French; using literacy rate * pop for French-using population 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 - - using pop * literacy rate - 90 percent of approximately 39 million Tanzanians speak Swahili - Baganda generally don't speak Swahili, but it is in common use among the 25 million people elsewhere in the country, and is currently being implemented in schools nationwide (use 75% of Cpop for this figure) [missing] @@ -5805,5 +5805,8 @@ XXX Code for transations where no currency is involved Analyzed from 2011 UK census and other sources In total 86.2% of Canadians have working knowledge of English while 29.8% have a working knowledge of French. 2014 Maldives: 98% literacy in Divehi, 75% in English + [missing] + [missing] + [missing] 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 64c5e34ffd8..132baa43703 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 @@ -336,7 +336,7 @@ Denmark DK "5,809,502" 99% "287,800,000,000" Swedish sv 13% No estimate avail Diego Garcia DG 500 99% "22,460,000" de_facto_official English en 495 http://en.wikipedia.org/wiki/Diego_Garcia Djibouti DJ "884,017" 68% "3,640,000,000" Afar aa 42% Djibouti DJ "884,017" 68% "3,640,000,000" official Arabic ar 7.3% -Djibouti DJ "884,017" 68% "3,640,000,000" official French fr "19,000" +Djibouti DJ "884,017" 68% "3,640,000,000" official French fr 50% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Djibouti DJ "884,017" 68% "3,640,000,000" Somali so 41% Dominica DM "74,027" 94% "783,000,000" official English en 94% Dominican Republic DO "10,298,756" 90% "173,000,000,000" English en "8,000" @@ -505,7 +505,7 @@ Guinea-Bissau GW "1,833,247" 55% "3,171,000,000" Fulah (Adlam) ff_Adlm 1 No e Guinea-Bissau GW "1,833,247" 55% "3,171,000,000" Mankanya knf "47,900" http://www.ethnologue.com/18/language/knf/ Guinea-Bissau GW "1,833,247" 55% "3,171,000,000" official Portuguese pt 100% https://www.cia.gov/cia/publications/factbook/geos/pu.html Many minor langs; Portuguese official Guyana GY "740,685" 92% "6,301,000,000" official English en 100% -Haiti HT "10,788,440" 49% "19,970,000,000" official French fr 4.7% 100% http://www.ethnologue.com/show_language.asp?code=fra 400k 2nd language speakers +Haiti HT "10,788,440" 49% "19,970,000,000" official French fr 42% 100% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Haiti HT "10,788,440" 49% "19,970,000,000" official Haitian Creole ht 81% "http://www.ethnologue.com/show_language.asp?code=hat Most of the population uses Creole; see also http://www.country-studies.com/haiti/creole,-literacy,-and-education.html http://en.wikipedia.org/wiki/French_language#Haiti" Heard & McDonald Islands HM 1 99% "53,170" Unknown language und 1 100% "https://www.cia.gov/cia/publications/factbook/geos/hm.html Uninhabited, barren, sub-Antarctic islands" Honduras HN "9,182,766" 85% "46,300,000,000" English en "40,400" @@ -757,7 +757,7 @@ Latvia LV "1,923,559" 100% "54,020,000,000" Russian ru 38% Lebanon LB "6,100,075" 90% "88,250,000,000" official Arabic ar 86% Lebanon LB "6,100,075" 90% "88,250,000,000" Armenian hy 5.2% Lebanon LB "6,100,075" 90% "88,250,000,000" English en 40% -Lebanon LB "6,100,075" 90% "88,250,000,000" French fr "22,300" +Lebanon LB "6,100,075" 90% "88,250,000,000" French fr 38% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Lebanon LB "6,100,075" 90% "88,250,000,000" Kurdish (Arabic) ku_Arab "101,000" Lebanon LB "6,100,075" 90% "88,250,000,000" Levantine Arabic apc "6,759,000" https://en.wikipedia.org/wiki/Levantine_Arabic#Speakers_by_country Lesotho LS "1,962,461" 90% "6,656,000,000" official English en 27% "http://www.ethnologue.com/show_country.asp?name=LS Lesotho English-using pop estimated at 5%, no figs available. Probably too low." @@ -839,7 +839,7 @@ Mauritania MR "3,840,429" 59% "17,280,000,000" Fulah (Adlam) ff_Adlm 1 No est 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" 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" official French fr 73% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Mauritius MU "1,364,283" 89% "28,270,000,000" Morisyen mfe 90% 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% @@ -880,7 +880,7 @@ Montserrat MS "5,315" 97% "167,400,000" official English en "3,490" Morocco MA "34,314,130" 67% "298,600,000,000" official Arabic ar 62% Morocco MA "34,314,130" 67% "298,600,000,000" official Central Atlas Tamazight tzm 9.8% 25% Morocco MA "34,314,130" 67% "298,600,000,000" English en 14% "http://www.ethnologue.com/show_country.asp?name=MA Ethnologue says 80k users of French. No other figures found yet, but this seems too low." -Morocco MA "34,314,130" 67% "298,600,000,000" de_facto_official French fr 20% "http://www.ethnologue.com/show_country.asp?name=MA Ethnologue says 80k users of French. No other figures found yet, but this seems too low." +Morocco MA "34,314,130" 67% "298,600,000,000" de_facto_official French fr 35% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Morocco MA "34,314,130" 67% "298,600,000,000" Moroccan Arabic ary 87% Morocco MA "34,314,130" 67% "298,600,000,000" Riffian (Tifinagh) rif_Tfng 4.9% 5% Morocco MA "34,314,130" 67% "298,600,000,000" Riffian (Latin) rif 4.9% 5% @@ -1274,7 +1274,7 @@ Sweden SE "10,040,995" 99% "518,000,000,000" recognized Tavringer Romani rmu "9, Sweden SE "10,040,995" 99% "518,000,000,000" recognized Tornedalen Finnish fit "55,500" Sweden SE "10,040,995" 99% "518,000,000,000" recognized Yiddish yi "3,000" Switzerland CH "8,292,809" 99% "523,100,000,000" English en 61% http://en.wikipedia.org/wiki/French_language -Switzerland CH "8,292,809" 99% "523,100,000,000" official French fr 21% http://en.wikipedia.org/wiki/French_language +Switzerland CH "8,292,809" 99% "523,100,000,000" official French fr 67% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Switzerland CH "8,292,809" 99% "523,100,000,000" official German de 73% Switzerland CH "8,292,809" 99% "523,100,000,000" official Italian it 4.3% Switzerland CH "8,292,809" 99% "523,100,000,000" Lombard lmo 4.1% 5% 5% writing pop estimated in absence of other data @@ -1341,7 +1341,7 @@ Trinidad & Tobago TT "1,215,527" 99% "42,850,000,000" official English en 88% Trinidad & Tobago TT "1,215,527" 99% "42,850,000,000" Spanish es "4,100" Tristan da Cunha TA 275 99% "12,350,000" English en 272 Tunisia TN "11,516,189" 79% "137,700,000,000" official Arabic ar 90% -Tunisia TN "11,516,189" 79% "137,700,000,000" official French fr 74% http://en.wikipedia.org/wiki/Tunisia#Language - using pop * literacy rate +Tunisia TN "11,516,189" 79% "137,700,000,000" official French fr 52% https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf Tunisia TN "11,516,189" 79% "137,700,000,000" Tunisian Arabic aeb 90% Turkey TR "81,257,239" 94% "2,186,000,000,000" Abkhazian ab "4,000" http://www.ethnologue.com/show_language.asp?code=abk 96% bilingual in Turkish. Turkey TR "81,257,239" 94% "2,186,000,000,000" Adyghe ady "316,000"