From bca324f7967163fcb9ca5e7ec9a2ca3f8bc791c3 Mon Sep 17 00:00:00 2001
From: Conrad Nied <conrad@unicode.org>
Date: Tue, 1 Oct 2024 11:04:11 -0700
Subject: [PATCH] CLDR-10015 Update errors in Likely Subtags (#4068)

`zlm` and `apd` are not languages of Togo -- there's a copy-paste error in the Likely Subtags overrides.

This fixes `apd` (Sudanese Arabic) by adding population counts -- I'll note that the ethnologue estimate is 48,000,000 million people, but the last Sudan census we have in the data shows only ~41 million people in the country -- so I want to be cautious. Since I had problems finding a reliable census I just duplicated the Standard Arabic value since likely most people in Sudan that use Arabic speak the Sudanese dialect but write Standard Arabic/ar.

For `zlm` -- Malay (individual language) that's even harder to get a thorough population value so I just fixed the override entry in GenerateLikelySubtags.
---
 common/supplemental/likelySubtags.xml                        | 5 ++---
 common/supplemental/supplementalData.xml                     | 2 ++
 .../java/org/unicode/cldr/tool/GenerateLikelySubtags.java    | 3 +--
 .../unicode/cldr/util/data/country_language_population.tsv   | 1 +
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/common/supplemental/likelySubtags.xml b/common/supplemental/likelySubtags.xml
index e81f6d9b341..98a02fc243c 100644
--- a/common/supplemental/likelySubtags.xml
+++ b/common/supplemental/likelySubtags.xml
@@ -36,7 +36,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="ann" to="ann_Latn_NG"/>		<!--Obolo‧?‧?	➡ Obolo‧Latin‧Nigeria-->
 		<likelySubtag from="aoz" to="aoz_Latn_ID"/>		<!--Uab Meto‧?‧?	➡ Uab Meto‧Latin‧Indonesia-->
 		<likelySubtag from="apc" to="apc_Arab_SY"/>		<!--Levantine Arabic‧?‧?	➡ Levantine Arabic‧Arabic‧Syria-->
-		<likelySubtag from="apd" to="apd_Arab_TG"/>		<!--Sudanese Arabic‧?‧?	➡ Sudanese Arabic‧Arabic‧Togo-->
+		<likelySubtag from="apd" to="apd_Arab_SD"/>		<!--Sudanese Arabic‧?‧?	➡ Sudanese Arabic‧Arabic‧Sudan-->
 		<likelySubtag from="ar" to="ar_Arab_EG"/>		<!--Arabic‧?‧?	➡ Arabic‧Arabic‧Egypt-->
 		<likelySubtag from="arc" to="arc_Armi_IR"/>		<!--Aramaic‧?‧?	➡ Aramaic‧Imperial Aramaic‧Iran-->
 		<likelySubtag from="arc_Hatr" to="arc_Hatr_IQ"/>		<!--Aramaic‧Hatran‧?	➡ Aramaic‧Hatran‧Iraq-->
@@ -844,7 +844,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="zh_Hant" to="zh_Hant_TW"/>		<!--Chinese‧Traditional‧?	➡ Chinese‧Traditional‧Taiwan-->
 		<likelySubtag from="zhx" to="zhx_Nshu_CN"/>		<!--Chinese (family)‧?‧?	➡ Chinese (family)‧Nüshu‧China-->
 		<likelySubtag from="zkt" to="zkt_Kits_CN"/>		<!--Kitan‧?‧?	➡ Kitan‧Khitan small script‧China-->
-		<likelySubtag from="zlm" to="zlm_Latn_TG"/>		<!--Malay (individual language)‧?‧?	➡ Malay (individual language)‧Latin‧Togo-->
+		<likelySubtag from="zlm" to="zlm_Latn_MY"/>		<!--Malay (individual language)‧?‧?	➡ Malay (individual language)‧Latin‧Malaysia-->
 		<likelySubtag from="zmi" to="zmi_Latn_MY"/>		<!--Negeri Sembilan Malay‧?‧?	➡ Negeri Sembilan Malay‧Latin‧Malaysia-->
 		<likelySubtag from="zu" to="zu_Latn_ZA"/>		<!--Zulu‧?‧?	➡ Zulu‧Latin‧South Africa-->
 		<likelySubtag from="zza" to="zza_Latn_TR"/>		<!--Zaza‧?‧?	➡ Zaza‧Latin‧Türkiye-->
@@ -1063,7 +1063,6 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_Arab_MU" to="ur_Arab_MU"/>		<!--?‧Arabic‧Mauritius	➡ Urdu‧Arabic‧Mauritius-->
 		<likelySubtag from="und_Arab_NG" to="ha_Arab_NG"/>		<!--?‧Arabic‧Nigeria	➡ Hausa‧Arabic‧Nigeria-->
 		<likelySubtag from="und_Arab_PK" to="ur_Arab_PK"/>		<!--?‧Arabic‧Pakistan	➡ Urdu‧Arabic‧Pakistan-->
-		<likelySubtag from="und_Arab_TG" to="apd_Arab_TG"/>		<!--?‧Arabic‧Togo	➡ Sudanese Arabic‧Arabic‧Togo-->
 		<likelySubtag from="und_Arab_TH" to="mfa_Arab_TH"/>		<!--?‧Arabic‧Thailand	➡ Pattani Malay‧Arabic‧Thailand-->
 		<likelySubtag from="und_Arab_TJ" to="fa_Arab_TJ"/>		<!--?‧Arabic‧Tajikistan	➡ Persian‧Arabic‧Tajikistan-->
 		<likelySubtag from="und_Arab_TR" to="apc_Arab_TR"/>		<!--?‧Arabic‧Türkiye	➡ Levantine Arabic‧Arabic‧Türkiye-->
diff --git a/common/supplemental/supplementalData.xml b/common/supplemental/supplementalData.xml
index b344266964f..6498637dd9e 100644
--- a/common/supplemental/supplementalData.xml
+++ b/common/supplemental/supplementalData.xml
@@ -1316,6 +1316,7 @@ XXX Code for transations where no currency is involved
 		<language type="anp" scripts="Deva"/>
 		<language type="aoz" scripts="Latn"/>
 		<language type="apc" territories="IL JO LB PS SY TR" alt="secondary"/>
+		<language type="apd" territories="SD" alt="secondary"/>
 		<language type="ar" scripts="Arab" territories="AE BH DJ DZ EG EH ER IL IQ JO KM KW LB LY MA MR OM PS QA SA SD SO SY TD TN YE"/>
 		<language type="ar" scripts="Syrc" territories="IR SS" alt="secondary"/>
 		<language type="arc" scripts="Armi Nbat Palm" alt="secondary"/>
@@ -4035,6 +4036,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="en" populationPercent="38" officialStatus="official"/>	<!--English-->
 		</territory>
 		<territory type="SD" gdp="136000000000" literacyPercent="71.9" population="50467300">	<!--Sudan-->
+			<languagePopulation type="apd" populationPercent="61"/>	<!--Sudanese Arabic-->
 			<languagePopulation type="ar" populationPercent="61" officialStatus="official" references="R1234"/>	<!--Arabic-->
 			<languagePopulation type="en" populationPercent="61" officialStatus="official" references="R1235"/>	<!--English-->
 			<languagePopulation type="bej" populationPercent="5.4" references="R1314"/>	<!--Beja-->
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 b14bfbb81d3..eb92736b471 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
@@ -313,8 +313,7 @@ public static void main(String[] args) throws IOException {
                             "fuf_Latn_GN",
                             "kby_Arab_NE",
                             "kdh_Latn_TG",
-                            "apd_Arab_TG",
-                            "zlm_Latn_TG",
+                            "zlm_Latn_MY",
                             "cr_Cans_CA",
                             "hif_Latn_FJ",
                             "gon_Telu_IN",
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 e2b1238c10d..41f2018a786 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
@@ -1255,6 +1255,7 @@ St. Pierre & Miquelon	PM	"5,471"	99%	"261,300,000"		English	en	188
 St. Pierre & Miquelon	PM	"5,471"	99%	"261,300,000"	official	French	fr	"5,110"
 St. Vincent & Grenadines	VC	"101,844"	96%	"1,265,000,000"	official	English	en	96%
 Sudan	SD	"43,120,843"	72%	"177,400,000,000"	official	Arabic	ar	61%			https://www.cia.gov/library/publications/the-world-factbook/geos/su.html - source for GDP
+Sudan	SD	"43,120,843"	72%	"177,400,000,000"		Sudanese Arabic	apd	61%
 Sudan	SD	"43,120,843"	72%	"177,400,000,000"		Beja	bej	5.4%			http://www.axl.cefan.ulaval.ca/afrique/soudan.htm
 Sudan	SD	"43,120,843"	72%	"177,400,000,000"	official	English	en	61%			"https://www.cia.gov/library/publications/the-world-factbook/geos/su.html - source for GDP Level of English usage unclear, but official for govt and education"
 Sudan	SD	"43,120,843"	72%	"177,400,000,000"		Fur	fvr	"1,170,000"			http://www.axl.cefan.ulaval.ca/afrique/soudan.htm