Skip to content

Commit

Permalink
CLDR-11888 Update French speakers
Browse files Browse the repository at this point in the history 
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
  • Loading branch information
@conradarcturus
conradarcturus committed Aug 27, 2024
1 parent 5f091da commit 838e118
Show file tree
Hide file tree
Showing 2 changed files with 28 additions and 25 deletions.
39 changes: 21 additions & 18 deletions common/supplemental/supplementalData.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1573,7 +1573,7 @@ XXX Code for transations where no currency is involved
<language type="fon" scripts="Latn"/>
<language type="fon" territories="BJ" alt="secondary"/>
<language type="fr" scripts="Latn" territories="BE BF BI BJ BL CA CD CF CG CH CI CM DJ DZ FR GA GF GN GP GQ HT KM LU MA MC MF MG ML MQ MU NC NE PF PM RE RW SC SN SY TD TG TN VU WF YT"/>
<language type="fr" scripts="Dupl" territories="DE GB IT NL PT RO TF US" alt="secondary"/>
<language type="fr" scripts="Dupl" territories="DE GB IT LB NL PT RO TF US" alt="secondary"/>
<language type="frc" scripts="Latn"/>
<language type="frm" scripts="Latn" alt="secondary"/>
<language type="fro" scripts="Latn" alt="secondary"/>
Expand Down Expand Up @@ -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" territories="TW"/>
<language type="hak" territories="CN" alt="secondary"/>
<language type="haw" scripts="Latn"/>
<language type="haw" territories="US" alt="secondary"/>
Expand Down Expand Up @@ -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"/>
Expand Down Expand Up @@ -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" territories="TW"/>
<language type="nan" territories="CN" alt="secondary"/>
<language type="nap" scripts="Latn"/>
<language type="naq" scripts="Latn"/>
Expand Down Expand Up @@ -2077,7 +2077,7 @@ XXX Code for transations where no currency is involved
<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="Cyrl Grek Latn"/>
<language type="pon" scripts="Latn"/>
<language type="pon" territories="FM" alt="secondary"/>
<language type="pqm" scripts="Latn"/>
Expand Down Expand Up @@ -2277,10 +2277,10 @@ 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"/>
Expand Down Expand Up @@ -2309,7 +2309,7 @@ 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"/>
Expand Down Expand Up @@ -2735,9 +2735,9 @@ XXX Code for transations where no currency is involved
</territory>
<territory type="CH" gdp="733800000000" literacyPercent="99" population="8860570"> <!--Switzerland-->
<languagePopulation type="de" populationPercent="73" officialStatus="official"/> <!--German-->
<languagePopulation type="fr" populationPercent="67" officialStatus="official" references="R1335"/> <!--French-->
<languagePopulation type="gsw" writingPercent="5" populationPercent="65" officialStatus="de_facto_official" references="R1006"/> <!--Swiss German-->
<languagePopulation type="en" populationPercent="61" references="R1137"/> <!--English-->
<languagePopulation type="fr" populationPercent="21" officialStatus="official" references="R1137"/> <!--French-->
<languagePopulation type="it" populationPercent="4.3" officialStatus="official"/> <!--Italian-->
<languagePopulation type="lmo" writingPercent="5" populationPercent="4.1" references="R1086"/> <!--Lombard-->
<languagePopulation type="pt" populationPercent="3.4" references="R1316"/> <!--Portuguese-->
Expand Down Expand Up @@ -2895,10 +2895,10 @@ XXX Code for transations where no currency is involved
<languagePopulation type="en" populationPercent="99" officialStatus="de_facto_official" references="R1065"/> <!--English-->
</territory>
<territory type="DJ" gdp="7380000000" literacyPercent="67.9" population="994974"> <!--Djibouti-->
<languagePopulation type="fr" populationPercent="50" officialStatus="official" references="R1335"/> <!--French-->
<languagePopulation type="aa" populationPercent="42"/> <!--Afar-->
<languagePopulation type="so" populationPercent="41"/> <!--Somali-->
<languagePopulation type="ar" populationPercent="7.3" officialStatus="official"/> <!--Arabic-->
<languagePopulation type="fr" populationPercent="2.1" officialStatus="official"/> <!--French-->
</territory>
<territory type="DK" gdp="428400000000" literacyPercent="99" population="5973140"> <!--Denmark-->
<languagePopulation type="da" populationPercent="93" officialStatus="official"/> <!--Danish-->
Expand Down Expand Up @@ -3182,7 +3182,7 @@ XXX Code for transations where no currency is involved
</territory>
<territory type="HT" gdp="34410000000" literacyPercent="48.7" population="11753900"> <!--Haiti-->
<languagePopulation type="ht" populationPercent="81" officialStatus="official" references="R1029"/> <!--Haitian Creole-->
<languagePopulation type="fr" literacyPercent="100" populationPercent="4.7" officialStatus="official" references="R1030"/> <!--French-->
<languagePopulation type="fr" literacyPercent="100" populationPercent="42" officialStatus="official" references="R1335"/> <!--French-->
</territory>
<territory type="HU" gdp="388900000000" literacyPercent="99" population="9855750"> <!--Hungary-->
<languagePopulation type="hu" populationPercent="100" officialStatus="official"/> <!--Hungarian-->
Expand Down Expand Up @@ -3489,9 +3489,9 @@ XXX Code for transations where no currency is involved
<languagePopulation type="apc" populationPercent="100" references="R1173"/> <!--Levantine Arabic-->
<languagePopulation type="ar" populationPercent="86" officialStatus="official"/> <!--Arabic-->
<languagePopulation type="en" populationPercent="40"/> <!--English-->
<languagePopulation type="fr" populationPercent="38" references="R1335"/> <!--French-->
<languagePopulation type="hy" populationPercent="5.2"/> <!--Armenian-->
<languagePopulation type="ku_Arab" populationPercent="1.7"/> <!--Kurdish (Arabic)-->
<languagePopulation type="fr" populationPercent="0.37"/> <!--French-->
</territory>
<territory type="LC" gdp="4083000000" literacyPercent="90.1" population="168038"> <!--St. Lucia-->
<languagePopulation type="en" populationPercent="90" officialStatus="official"/> <!--English-->
Expand Down Expand Up @@ -3548,8 +3548,8 @@ XXX Code for transations where no currency is involved
<territory type="MA" gdp="337500000000" literacyPercent="67.1" population="37387600"> <!--Morocco-->
<languagePopulation type="ary" populationPercent="87"/> <!--Moroccan Arabic-->
<languagePopulation type="ar" populationPercent="62" officialStatus="official"/> <!--Arabic-->
<languagePopulation type="fr" populationPercent="35" officialStatus="de_facto_official" references="R1335"/> <!--French-->
<languagePopulation type="zgh" populationPercent="22" references="R1254"/> <!--Standard Moroccan Tamazight-->
<languagePopulation type="fr" populationPercent="20" officialStatus="de_facto_official" references="R1050"/> <!--French-->
<languagePopulation type="en" populationPercent="14" references="R1050"/> <!--English-->
<languagePopulation type="tzm" literacyPercent="25" populationPercent="9.8" officialStatus="official"/> <!--Central Atlas Tamazight-->
<languagePopulation type="shi" populationPercent="8.7"/> <!--Tachelhit-->
Expand Down Expand Up @@ -3653,10 +3653,10 @@ XXX Code for transations where no currency is involved
</territory>
<territory type="MU" gdp="33530000000" literacyPercent="88.8" population="1310500"> <!--Mauritius-->
<languagePopulation type="mfe" populationPercent="90"/> <!--Morisyen-->
<languagePopulation type="fr" populationPercent="73" officialStatus="official" references="R1335"/> <!--French-->
<languagePopulation type="en" populationPercent="72" officialStatus="official" references="R1152"/> <!--English-->
<languagePopulation type="bho" populationPercent="27"/> <!--Bhojpuri-->
<languagePopulation type="ur" populationPercent="5.2"/> <!--Urdu-->
<languagePopulation type="fr" populationPercent="3" officialStatus="official"/> <!--French-->
<languagePopulation type="ta" populationPercent="2.5"/> <!--Tamil-->
</territory>
<territory type="MV" gdp="11650000000" literacyPercent="98.4" population="388858"> <!--Maldives-->
Expand Down Expand Up @@ -4214,7 +4214,7 @@ XXX Code for transations where no currency is involved
<territory type="TN" gdp="153600000000" literacyPercent="79.1" population="12048800"> <!--Tunisia-->
<languagePopulation type="aeb" populationPercent="90"/> <!--Tunisian Arabic-->
<languagePopulation type="ar" populationPercent="90" officialStatus="official"/> <!--Arabic-->
<languagePopulation type="fr" populationPercent="74" officialStatus="official" references="R1132"/> <!--French-->
<languagePopulation type="fr" populationPercent="52" officialStatus="official" references="R1335"/> <!--French-->
</territory>
<territory type="TO" gdp="700400000" literacyPercent="99" population="104889"> <!--Tonga-->
<languagePopulation type="to" populationPercent="95" officialStatus="official"/> <!--Tongan-->
Expand All @@ -4226,7 +4226,6 @@ 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)-->
Expand All @@ -4235,6 +4234,7 @@ 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)-->
Expand All @@ -4257,6 +4257,8 @@ 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="R1333"/> <!--Min Nan Chinese-->
<languagePopulation type="hak" populationPercent="11" officialStatus="official" references="R1334"/> <!--Hakka Chinese-->
<languagePopulation type="trv" populationPercent="0.02"/> <!--Taroko-->
</territory>
<territory type="TZ" gdp="234100000000" literacyPercent="67.8" population="67462100"> <!--Tanzania-->
Expand Down Expand Up @@ -5503,7 +5505,6 @@ XXX Code for transations where no currency is involved
<reference type="R1027" uri="https://www.cia.gov/cia/publications/factbook/geos/pu.html">Many minor langs; Portuguese official</reference>
<reference type="R1028" uri="http://www.seasite.niu.edu/tagalog/essays_on_philippine_languages.htm">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 </reference>
<reference type="R1029" uri="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</reference>
<reference type="R1030" uri="http://www.ethnologue.com/show_language.asp?code=fra">400k 2nd language speakers</reference>
<reference type="R1031" uri="http://www.ethnologue.com/show_country.asp?name=CV">Official language, 37-77% literacy</reference>
<reference type="R1032" uri="http://www.ethnologue.com/show_country.asp?name=ER">Official language, used in some schools.</reference>
<reference type="R1033" uri="http://www.ciil.org/Main/Announcement/MBE_Programme/paper/paper2.htm">http://www.censusindia.net/cendat/datatable26.html</reference>
Expand Down Expand Up @@ -5605,7 +5606,6 @@ XXX Code for transations where no currency is involved
<reference type="R1129" uri="http://www.ethnologue.com/show_language.asp?code=skr">[missing]</reference>
<reference type="R1130" uri="http://en.wikipedia.org/wiki/R%C3%A9union">- Education is in French; using literacy rate * pop for French-using population</reference>
<reference type="R1131" uri="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</reference>
<reference type="R1132" uri="http://en.wikipedia.org/wiki/Tunisia#Language">- using pop * literacy rate</reference>
<reference type="R1133" uri="http://en.wikipedia.org/wiki/Swahili_language">- 90 percent of approximately 39 million Tanzanians speak Swahili</reference>
<reference type="R1134" uri="http://en.wikipedia.org/wiki/Swahili_language">- 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)</reference>
<reference type="R1135" uri="https://en.wikipedia.org/wiki/Talian_dialect">[missing]</reference>
Expand Down Expand Up @@ -5805,5 +5805,8 @@ 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_Hokkien">[missing]</reference>
<reference type="R1334" uri="https://en.wikipedia.org/wiki/Taiwanese_Hakka">[missing]</reference>
<reference type="R1335" uri="https://www.francophonie.org/sites/default/files/2021-04/LFDM-20Edition-2019-La-langue-fran%C3%A7aise-dans-le-monde.pdf">[missing]</reference>
</references>
</supplementalData>
Loading

0 comments on commit 838e118

Please sign in to comment.