From 24c892841733f6ac779be33a3a154f982f732090 Mon Sep 17 00:00:00 2001
From: Conrad Nied <conrad.logos@gmail.com>
Date: Tue, 17 Sep 2024 17:25:24 -0700
Subject: [PATCH] CLDR-10478 Add latest data from Macau census

This updates the Macau population language data with up-to-date census information.

CLDR-10478 Update GenerateLikelyTestData

 java -jar tools/cldr-code/target/cldr-code.jar GenerateLikelyTestData

CLDR-10478 Fix official languages for Macau

CLDR-10478 Remove `cmn` from Macau because of overlap with `zh`

Even though `cmn` knowledge is at 45% of Macau, since `zh` is implied to be `cmn` it ends up being double counted. Potentially we can separate `zh` from `cmn` -- but that's a whole new discussion that's best saved for later.

CLDR-10478 Add Cantonese (Macau) locale xml

Since I added a new locale that has "de_facto_official" status I need to add a new xml -- easy enough, I'll just have it inherit from root for now.

I also re-generated the test data with `java -jar tools/cldr-code/target/cldr-code.jar GenerateLikelyTestData`

CLDR-10478 Add latest data from Macau census

This updates the Macau population language data with up-to-date census information.

CLDR-10478 Fix official languages for Macau

CLDR-10478 Remove `cmn` from Macau because of overlap with `zh`

Even though `cmn` knowledge is at 45% of Macau, since `zh` is implied to be `cmn` it ends up being double counted. Potentially we can separate `zh` from `cmn` -- but that's a whole new discussion that's best saved for later.
---
 common/main/yue_Hant_MO.xml                       | 15 +++++++++++++++
 common/supplemental/likelySubtags.xml             |  2 +-
 common/supplemental/supplementalData.xml          | 14 ++++++++------
 .../testData/localeIdentifiers/likelySubtags.txt  |  3 ++-
 .../util/data/country_language_population.tsv     | 11 +++++++----
 5 files changed, 33 insertions(+), 12 deletions(-)
 create mode 100644 common/main/yue_Hant_MO.xml

diff --git a/common/main/yue_Hant_MO.xml b/common/main/yue_Hant_MO.xml
new file mode 100644
index 00000000000..1a44ad133f2
--- /dev/null
+++ b/common/main/yue_Hant_MO.xml
@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
+<!-- Copyright © 1991-2024 Unicode, Inc.
+For terms of use, see http://www.unicode.org/copyright.html
+SPDX-License-Identifier: Unicode-3.0
+CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
+-->
+<ldml>
+	<identity>
+		<version number="$Revision$"/>
+		<language type="yue"/>
+		<script type="Hant"/>
+		<territory type="MO"/>
+	</identity>
+</ldml>
diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml
index 98a02fc243c..c1ce8491f95 100644
--- a/common/supplemental/likelySubtags.xml
+++ b/common/supplemental/likelySubtags.xml
@@ -1202,7 +1202,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_Latn_MA" to="fr_Latn_MA"/>		<!--?‧Latin‧Morocco	➡ French‧Latin‧Morocco-->
 		<likelySubtag from="und_Latn_MK" to="sq_Latn_MK"/>		<!--?‧Latin‧North Macedonia	➡ Albanian‧Latin‧North Macedonia-->
 		<likelySubtag from="und_Latn_MM" to="kac_Latn_MM"/>		<!--?‧Latin‧Myanmar (Burma)	➡ Kachin‧Latin‧Myanmar (Burma)-->
-		<likelySubtag from="und_Latn_MO" to="pt_Latn_MO"/>		<!--?‧Latin‧Macao SAR China	➡ Portuguese‧Latin‧Macao SAR China-->
+		<likelySubtag from="und_Latn_MO" to="en_Latn_MO"/>		<!--?‧Latin‧Macao SAR China	➡ English‧Latin‧Macao SAR China-->
 		<likelySubtag from="und_Latn_MR" to="fr_Latn_MR"/>		<!--?‧Latin‧Mauritania	➡ French‧Latin‧Mauritania-->
 		<likelySubtag from="und_Latn_MU" to="en_Latn_MU"/>		<!--?‧Latin‧Mauritius	➡ English‧Latin‧Mauritius-->
 		<likelySubtag from="und_Latn_MV" to="en_Latn_MV"/>		<!--?‧Latin‧Maldives	➡ English‧Latin‧Maldives-->
diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml
index 6498637dd9e..4d2838a8d38 100644
--- a/common/supplemental/supplementalData.xml
+++ b/common/supplemental/supplementalData.xml
@@ -1541,7 +1541,7 @@ XXX Code for transations where no currency is involved
 		<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="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="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 MO 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"/>
 		<language type="es" scripts="Latn" territories="AR BO CL CO CR CU DO EA EC ES GQ GT HN IC MX NI PA PE PR PY SV UY VE"/>
@@ -2410,7 +2410,7 @@ XXX Code for transations where no currency is involved
 		<language type="yrk" scripts="Cyrl"/>
 		<language type="yrl" scripts="Latn"/>
 		<language type="yua" scripts="Latn"/>
-		<language type="yue" scripts="Hans Hant"/>
+		<language type="yue" scripts="Hans Hant" territories="MO"/>
 		<language type="yue" territories="CN HK" alt="secondary"/>
 		<language type="za" scripts="Latn"/>
 		<language type="za" scripts="Hans" territories="CN" alt="secondary"/>
@@ -3629,9 +3629,12 @@ XXX Code for transations where no currency is involved
 		</territory>
 		<territory type="MO" gdp="71840000000" literacyPercent="95.6" population="644426">	<!--Macao SAR China-->
 			<languagePopulation type="zh_Hant" populationPercent="98" officialStatus="official"/>	<!--Chinese (Traditional)-->
-			<languagePopulation type="pt" populationPercent="5" officialStatus="official" references="R1085"/>	<!--Portuguese-->
+			<languagePopulation type="yue" populationPercent="86" officialStatus="de_facto_official" references="R1337"/>	<!--Cantonese-->
+			<languagePopulation type="en" populationPercent="23" references="R1337"/>	<!--English-->
 			<languagePopulation type="zh" populationPercent="5" references="R1143"/>	<!--Chinese-->
-			<languagePopulation type="en" populationPercent="2.3" references="R1273"/>	<!--English-->
+			<languagePopulation type="nan" populationPercent="3.7" references="R1338"/>	<!--Min Nan Chinese-->
+			<languagePopulation type="fil" populationPercent="3.1" references="R1337"/>	<!--Filipino-->
+			<languagePopulation type="pt" populationPercent="2.3" officialStatus="official" references="R1337"/>	<!--Portuguese-->
 		</territory>
 		<territory type="MP" gdp="1242000000" literacyPercent="97" population="51118">	<!--Northern Mariana Islands-->
 			<languagePopulation type="en" populationPercent="97" officialStatus="de_facto_official"/>	<!--English-->
@@ -5571,7 +5574,6 @@ XXX Code for transations where no currency is involved
 		<reference type="R1082" uri="http://www.ethnologue.com/show_language.asp?code=eng">Ethnologue lists 1 million 2nd lang users of English; no other good figures found.</reference>
 		<reference type="R1083" uri="http://www.bhas.ba/index.php?option=com_content&amp;view=article&amp;id=52&amp;itemid=80&amp;lang=en&amp;Itemid="> also: http://en.wikipedia.org/wiki/Bosnian_language</reference>
 		<reference type="R1084" uri="http://www.nationsonline.org/oneworld/equatorial_guinea.htm">French is a minority official language. Crude estimate of usage based on import partner data.</reference>
-		<reference type="R1085" uri="http://en.wikipedia.org/wiki/Geographic_distribution_of_Portuguese">Macao reported 5% native Portuguese speakers.</reference>
 		<reference type="R1086">5% writing pop estimated in absence of other data</reference>
 		<reference type="R1087" uri="http://www.ethnologue.com/show_language.asp?code=rkt">[missing]</reference>
 		<reference type="R1088" uri="http://www.nationsonline.org/oneworld/syria.htm">Crude estimate based on import partner data.</reference>
@@ -5759,7 +5761,6 @@ XXX Code for transations where no currency is involved
 		<reference type="R1270">Mainly unwritten</reference>
 		<reference type="R1271">Vai script is the main script for this language.</reference>
 		<reference type="R1272">Latin listed as being used (Scriptsource) but no pop figures available.</reference>
-		<reference type="R1273" uri="https://www.cia.gov/library/publications/the-world-factbook/geos/mc.html">and https://en.wikipedia.org/wiki/Macau</reference>
 		<reference type="R1274" uri="http://www.ethnologue.com/language/mgh">but no literacy data</reference>
 		<reference type="R1275" uri="http://www.ethnologue.com/language/pcm">Including 1st and 2nd lang speakers</reference>
 		<reference type="R1276" uri="http://www.ethnologue.com/show_language.asp?code=bin">[missing]</reference>
@@ -5823,5 +5824,6 @@ XXX Code for transations where no currency is involved
 		<reference type="R1334" uri="https://en.wikipedia.org/wiki/Laz_people#cite_note-ethnologue-1">[missing]</reference>
 		<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://stat.gov.pl/spisy-powszechne/nsp-2021/nsp-2021-wyniki-ostateczne/">Languages spoken at home in the 2021 Polish Census</reference>
 	</references>
 </supplementalData>
diff --git a/common/testData/localeIdentifiers/likelySubtags.txt b/common/testData/localeIdentifiers/likelySubtags.txt
index d7f06199e44..4383349ec3c 100644
--- a/common/testData/localeIdentifiers/likelySubtags.txt
+++ b/common/testData/localeIdentifiers/likelySubtags.txt
@@ -1435,7 +1435,7 @@ und-Latn-MG ;	mg-Latn-MG ;	mg ;
 und-Latn-MH ;	en-Latn-MH ;	en-MH ;	
 und-Latn-MK ;	sq-Latn-MK ;	sq-MK ;	
 und-Latn-ML ;	bm-Latn-ML ;	bm ;	
-und-Latn-MO ;	pt-Latn-MO ;	pt-MO ;	
+und-Latn-MO ;	en-Latn-MO ;	en-MO ;	
 und-Latn-MP ;	en-Latn-MP ;	en-MP ;	
 und-Latn-MQ ;	fr-Latn-MQ ;	fr-MQ ;	
 und-Latn-MR ;	fr-Latn-MR ;	fr-MR ;	
@@ -1738,6 +1738,7 @@ yue-Egyp ;	yue-Egyp-HK ;	yue-Egyp ;
 yue-HK ;	yue-Hant-HK ;	yue ;	
 yue-Hans ;	yue-Hans-CN ;	yue-Hans ;	yue-CN
 yue-Hant ;	yue-Hant-HK ;	yue ;	
+yue-MO ;	yue-Hant-MO ;	yue-MO ;	
 za ;	za-Latn-CN ;	za ;	
 za-AQ ;	za-Latn-AQ ;	za-AQ ;	
 za-CN ;	za-Latn-CN ;	za ;	
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 41f2018a786..9f5c83248a8 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
@@ -790,10 +790,13 @@ Luxembourg	LU	"605,764"	100%	"62,110,000,000"	official	French	fr	87%
 Luxembourg	LU	"605,764"	100%	"62,110,000,000"	official	German	de	63%
 Luxembourg	LU	"605,764"	100%	"62,110,000,000"	official	Luxembourgish	lb	67%	5%		"http://www.ethnologue.com/show_language.asp?code=ltz Some 99% of users are literate in French or German. For languages not customarily written, the writing population is artificially set to 5% in the absence of better information."
 Luxembourg	LU	"605,764"	100%	"62,110,000,000"		Portuguese	pt	16%			https://en.wikipedia.org/wiki/Portuguese_Luxembourger
-Macao SAR China	MO	"606,340"	96%	"71,820,000,000"		Chinese	zh	5%			Hans literacy is unknown; set to 5% artificially pending better or official figures.
-Macao SAR China	MO	"606,340"	96%	"71,820,000,000"	official	Chinese (Traditional)	zh_Hant	98%
-Macao SAR China	MO	"606,340"	96%	"71,820,000,000"		English	en	"13,900"			https://www.cia.gov/library/publications/the-world-factbook/geos/mc.html and https://en.wikipedia.org/wiki/Macau
-Macao SAR China	MO	"606,340"	96%	"71,820,000,000"	official	Portuguese	pt	5%			http://en.wikipedia.org/wiki/Geographic_distribution_of_Portuguese Macao reported 5% native Portuguese speakers.
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"		Chinese	zh	5%			Hans literacy is unknown; set to 5% artificially pending better or official figures.
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"	official	Chinese (Traditional)	zh_Hant	98%
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"		English	en	22.7%			https://www.dsec.gov.mo/getAttachment/6cb29f2f-524a-488f-aed3-4d7207bb109e/E_CEN_PUB_2021_Y.aspx 2021 Census, counting people who are fluent in the language
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"	official	Portuguese	pt	2.3%			https://www.dsec.gov.mo/getAttachment/6cb29f2f-524a-488f-aed3-4d7207bb109e/E_CEN_PUB_2021_Y.aspx 2021 Census, counting people who are fluent in the language
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"	de_facto_official	Cantonese	yue	86.2%			https://www.dsec.gov.mo/getAttachment/6cb29f2f-524a-488f-aed3-4d7207bb109e/E_CEN_PUB_2021_Y.aspx 2021 Census, counting people who are fluent in the language
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"		Filipino	fil	"20,879"			https://www.dsec.gov.mo/getAttachment/6cb29f2f-524a-488f-aed3-4d7207bb109e/E_CEN_PUB_2021_Y.aspx 2021 Census, counting people who are fluent in the language
+Macao SAR China	MO	"682,070"	96%	"71,820,000,000"		Hokkien	nan	3.7%			https://www.dsec.gov.mo/getAttachment/7a3b17c2-22cc-4197-9bd5-ccc6eec388a2/E_CEN_PUB_2011_Y.aspx 2011 Census -- the language is not distinguished in the 2021 census
 Madagascar	MG	"25,683,610"	65%	"39,850,000,000"	official	English	en	18%			No literacy figure available for English in Madagascar; newly adopted official language; 5% is an estimate.
 Madagascar	MG	"25,683,610"	65%	"39,850,000,000"	official	French	fr	69%
 Madagascar	MG	"25,683,610"	65%	"39,850,000,000"	official	Malagasy	mg	90%			http://www.wildmadagascar.org/overview/loc/27-minorities.html