CLDR-16943 Merge origin/main

README.md

@@ -10,15 +10,14 @@ For current CLDR release information, see [cldr.unicode.org](https://cldr.unicod
 
 ## Status
 
-Update: 2023-08-31
+Update: 2023-09-28
 
 <!-- [inapplicable lines are commented out.]-->
 <!--**Note:**  CLDR 44 is in development and not recommended for use at this stage.-->
 <!--**Note:**  This is the milestone 1 version of CLDR 44, intended for those wishing to do pre-release testing. It is not recommended for production use.-->
-> **Note:** This is a preliminary version of CLDR 44, intended for those wishing to do pre-release testing. It is not recommended for production use.</p>
-<!--**Note:**  This is a pre-release candidate version of CLDR 44, intended for testing.
-It is not recommended for production use.</p>-->
-<!--<p>This is the final release version of CLDR 44.</p>-->
+<!--**Note:** This is a preliminary version of CLDR 44, intended for those wishing to do pre-release testing. It is not recommended for production use.-->
+**Note:**  This is a pre-release candidate version of CLDR 44, intended for testing. It is not recommended for production use.
+<!--This is the final release version of CLDR 44.-->
 
 ### What is CLDR?
 The Unicode CLDR provides key building blocks for software to support the world's languages, with the largest and most extensive standard repository of locale data available. This data is used by a wide spectrum of companies for their software internationalization and localization, adapting software to the conventions of different languages for such common software tasks.

common/main/en.xml

@@ -3904,15 +3904,6 @@ annotations.
 			<zone type="Etc/Unknown">
 				<exemplarCity>Unknown City</exemplarCity>
 			</zone>
-			<zone type="Antarctica/DumontDUrville">
-				<exemplarCity>Dumont d’Urville</exemplarCity>
-			</zone>
-			<zone type="America/St_Barthelemy">
-				<exemplarCity>St. Barthélemy</exemplarCity>
-			</zone>
-			<zone type="America/Curacao">
-				<exemplarCity>Curaçao</exemplarCity>
-			</zone>
 			<zone type="Europe/London">
 				<long>
 					<daylight>British Summer Time</daylight>
@@ -3926,21 +3917,9 @@ annotations.
 			<zone type="Asia/Qostanay">
 				<exemplarCity>Kostanay</exemplarCity>
 			</zone>
-			<zone type="America/Asuncion">
-				<exemplarCity>Asunción</exemplarCity>
-			</zone>
-			<zone type="Indian/Reunion">
-				<exemplarCity>Réunion</exemplarCity>
-			</zone>
-			<zone type="Africa/Sao_Tome">
-				<exemplarCity>São Tomé</exemplarCity>
-			</zone>
 			<zone type="Europe/Uzhgorod">
 				<exemplarCity>Uzhhorod</exemplarCity>
 			</zone>
-			<zone type="Europe/Kiev">
-				<exemplarCity>Kyiv</exemplarCity>
-			</zone>
 			<zone type="Pacific/Honolulu">
 				<short>
 					<generic>HST</generic>

common/main/fr.xml

@@ -3026,7 +3026,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 							<dayPeriod type="morning1">matin</dayPeriod>
 							<dayPeriod type="afternoon1">après-midi</dayPeriod>
 							<dayPeriod type="evening1">soir</dayPeriod>
-							<dayPeriod type="night1">nuit</dayPeriod>
+							<dayPeriod type="night1">matin</dayPeriod>
 						</dayPeriodWidth>
 						<dayPeriodWidth type="narrow">
 							<dayPeriod type="midnight">↑↑↑</dayPeriod>

common/main/root.xml

@@ -2899,7 +2899,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 				<exemplarCity>Dumont d’Urville</exemplarCity>
 			</zone>
 			<zone type="America/St_Barthelemy">
-				<exemplarCity>St. Barthelemy</exemplarCity>
+				<exemplarCity>St. Barthélemy</exemplarCity>
 			</zone>
 			<zone type="America/Coral_Harbour">
 				<exemplarCity>Atikokan</exemplarCity>
@@ -3006,6 +3006,18 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 			<zone type="Asia/Saigon">
 				<exemplarCity>Ho Chi Minh</exemplarCity>
 			</zone>
+			<zone type="America/Curacao">
+				<exemplarCity>Curaçao</exemplarCity>
+			</zone>
+			<zone type="America/Asuncion">
+				<exemplarCity>Asunción</exemplarCity>
+			</zone>
+			<zone type="Indian/Reunion">
+				<exemplarCity>Réunion</exemplarCity>
+			</zone>
+			<zone type="Africa/Sao_Tome">
+				<exemplarCity>São Tomé</exemplarCity>
+			</zone>
 		</timeZoneNames>
 	</dates>
 	<numbers>

common/segments/en_US_POSIX.xml

@@ -16,7 +16,6 @@ For terms of use, see http://www.unicode.org/copyright.html
 		<segmentation type="WordBreak">
 			<variables>
 				<variable id="$MidNumLet">[[$MidNumLet]-[.]]</variable>
-				<variable id="$MidLetter">[[$MidLetter]-[\:]]</variable>
 				<variable id="$MidNum">[[$MidNum] [.]]</variable>
 			</variables>
 		</segmentation>

common/segments/root.xml

@@ -375,7 +375,7 @@ For terms of use, see http://www.unicode.org/copyright.html
 				<variable id="$Format">[\p{Word_Break=Format}]</variable>
 				<variable id="$Katakana">\p{Word_Break=Katakana}</variable>
 				<variable id="$ALetter">\p{Word_Break=ALetter}</variable>
-				<variable id="$MidLetter">\p{Word_Break=MidLetter}</variable>
+				<variable id="$MidLetter">[\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]]</variable>
 				<variable id="$MidNum">\p{Word_Break=MidNum}</variable>
 				<variable id="$MidNumLet">\p{Word_Break=MidNumLet}</variable>
 				<variable id="$Numeric">\p{Word_Break=Numeric}</variable>

common/supplemental/likelySubtags.xml

@@ -1653,7 +1653,9 @@ not be patched by hand, as any changes made in that fashion may be lost.
 
 		<!-- Retain und and und+macroregions that are in CLDR locales, except those mapping to en anyway  -->
 		<likelySubtag from="und" to="en_Latn_US"/>
+		<likelySubtag from="und_Latn" to="en_Latn_US"/>
 		<likelySubtag from="und_419" to="es_Latn_419"/>
+		<likelySubtag from="und_Latn_419" to="es_Latn_419"/>
 
 		<!--{ ?; ?; ? } => { English; Latin; United States }-->
 
@@ -1733,6 +1735,7 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<likelySubtag from="und_Cyrl_MK" to="mk_Cyrl_MK"/>
 		<likelySubtag from="und_Cyrl_MN" to="mn_Cyrl_MN"/>
 		<likelySubtag from="und_Cyrl_RS" to="sr_Cyrl_RS"/>
+		<likelySubtag from="und_Latn_RS" to="sr_Latn_RS"/>
 		<likelySubtag from="und_Cyrl_TJ" to="tg_Cyrl_TJ"/>
 		<likelySubtag from="und_Cyrl_UA" to="uk_Cyrl_UA"/>
 		<likelySubtag from="und_Deva_NP" to="ne_Deva_NP"/>

common/testData/localeIdentifiers/likelySubtags.txt

@@ -1259,7 +1259,7 @@ und-Latn-001 ;	en-Latn-001 ;	en-001 ;
 und-Latn-150 ;	en-Latn-150 ;	en-150 ;	
 und-Latn-419 ;	es-Latn-419 ;	es-419 ;	
 und-Latn-AD ;	ca-Latn-AD ;	ca-AD ;	
-und-Latn-AE ;	ar-Latn-AE ;	 ;	
+und-Latn-AE ;	en-Latn-AE ;	en-AE ;	
 und-Latn-AG ;	en-Latn-AG ;	en-AG ;	
 und-Latn-AI ;	en-Latn-AI ;	en-AI ;	
 und-Latn-AL ;	sq-Latn-AL ;	sq ;	
@@ -1288,7 +1288,7 @@ und-Latn-BS ;	en-Latn-BS ;	en-BS ;
 und-Latn-BW ;	en-Latn-BW ;	en-BW ;	
 und-Latn-BZ ;	en-Latn-BZ ;	en-BZ ;	
 und-Latn-CA ;	en-Latn-CA ;	en-CA ;	
-und-Latn-CC ;	ms-Latn-CC ;	 ;	
+und-Latn-CC ;	en-Latn-CC ;	en-CC ;	
 und-Latn-CD ;	sw-Latn-CD ;	sw-CD ;	
 und-Latn-CF ;	fr-Latn-CF ;	fr-CF ;	
 und-Latn-CG ;	fr-Latn-CG ;	fr-CG ;	
@@ -1316,7 +1316,7 @@ und-Latn-DZ ;	fr-Latn-DZ ;	fr-DZ ;
 und-Latn-EA ;	es-Latn-EA ;	es-EA ;	
 und-Latn-EC ;	es-Latn-EC ;	es-EC ;	
 und-Latn-EE ;	et-Latn-EE ;	et ;	
-und-Latn-ER ;	ti-Latn-ER ;	 ;	
+und-Latn-ER ;	en-Latn-ER ;	en-ER ;	
 und-Latn-ES ;	es-Latn-ES ;	es ;	
 und-Latn-ET ;	en-Latn-ET ;	en-ET ;	
 und-Latn-FI ;	fi-Latn-FI ;	fi ;	
@@ -1341,17 +1341,17 @@ und-Latn-GT ;	es-Latn-GT ;	es-GT ;
 und-Latn-GU ;	en-Latn-GU ;	en-GU ;	
 und-Latn-GW ;	pt-Latn-GW ;	pt-GW ;	
 und-Latn-GY ;	en-Latn-GY ;	en-GY ;	
-und-Latn-HK ;	zh-Latn-HK ;	 ;	
+und-Latn-HK ;	en-Latn-HK ;	en-HK ;	
 und-Latn-HN ;	es-Latn-HN ;	es-HN ;	
 und-Latn-HR ;	hr-Latn-HR ;	hr ;	
 und-Latn-HT ;	ht-Latn-HT ;	ht ;	
 und-Latn-HU ;	hu-Latn-HU ;	hu ;	
 und-Latn-IC ;	es-Latn-IC ;	es-IC ;	
 und-Latn-ID ;	id-Latn-ID ;	id ;	
 und-Latn-IE ;	en-Latn-IE ;	en-IE ;	
-und-Latn-IL ;	he-Latn-IL ;	he-Latn ;	
+und-Latn-IL ;	en-Latn-IL ;	en-IL ;	
 und-Latn-IM ;	en-Latn-IM ;	en-IM ;	
-und-Latn-IN ;	hi-Latn-IN ;	hi-Latn ;	
+und-Latn-IN ;	en-Latn-IN ;	en-IN ;	
 und-Latn-IO ;	en-Latn-IO ;	en-IO ;	
 und-Latn-IS ;	is-Latn-IS ;	is ;	
 und-Latn-IT ;	it-Latn-IT ;	it ;	
@@ -1385,7 +1385,7 @@ 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-MV ;	dv-Latn-MV ;	dv-Latn ;	
+und-Latn-MV ;	en-Latn-MV ;	en-MV ;	
 und-Latn-MW ;	en-Latn-MW ;	en-MW ;	
 und-Latn-MX ;	es-Latn-MX ;	es-MX ;	
 und-Latn-MY ;	ms-Latn-MY ;	ms ;	
@@ -1406,7 +1406,7 @@ und-Latn-PE ;	es-Latn-PE ;	es-PE ;
 und-Latn-PF ;	fr-Latn-PF ;	fr-PF ;	
 und-Latn-PG ;	tpi-Latn-PG ;	tpi ;	
 und-Latn-PH ;	fil-Latn-PH ;	fil ;	
-und-Latn-PK ;	ur-Latn-PK ;	ur-Latn ;	
+und-Latn-PK ;	en-Latn-PK ;	en-PK ;	
 und-Latn-PL ;	pl-Latn-PL ;	pl ;	
 und-Latn-PM ;	fr-Latn-PM ;	fr-PM ;	
 und-Latn-PN ;	en-Latn-PN ;	en-PN ;	
@@ -1420,7 +1420,7 @@ und-Latn-RS ;	sr-Latn-RS ;	sr-Latn ;
 und-Latn-RW ;	rw-Latn-RW ;	rw ;	
 und-Latn-SB ;	en-Latn-SB ;	en-SB ;	
 und-Latn-SC ;	fr-Latn-SC ;	fr-SC ;	
-und-Latn-SD ;	ar-Latn-SD ;	 ;	
+und-Latn-SD ;	en-Latn-SD ;	en-SD ;	
 und-Latn-SE ;	sv-Latn-SE ;	sv ;	
 und-Latn-SG ;	en-Latn-SG ;	en-SG ;	
 und-Latn-SH ;	en-Latn-SH ;	en-SH ;	
@@ -1432,7 +1432,7 @@ und-Latn-SM ;	it-Latn-SM ;	it-SM ;
 und-Latn-SN ;	fr-Latn-SN ;	fr-SN ;	
 und-Latn-SO ;	so-Latn-SO ;	so ;	
 und-Latn-SR ;	nl-Latn-SR ;	nl-SR ;	
-und-Latn-SS ;	ar-Latn-SS ;	 ;	
+und-Latn-SS ;	en-Latn-SS ;	en-SS ;	
 und-Latn-ST ;	pt-Latn-ST ;	pt-ST ;	
 und-Latn-SV ;	es-Latn-SV ;	es-SV ;	
 und-Latn-SX ;	en-Latn-SX ;	en-SX ;	

common/transforms/Cyrillic-Latin.xml

@@ -17,6 +17,7 @@ For terms of use, see http://www.unicode.org/copyright.html
 # :: [\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]] ;
 ### WARNING, ̈ must be added to the generated filters, in both directions ###
 # MINIMAL FILTER
+# Cyrillic-Latin
 :: [ҺһңҢҰұҮүөӨҚқ̈Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ̆Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ;
 :: NFD (NFC) ;
 $modprime = ʹ;
@@ -75,15 +76,10 @@ $beforeLower = $ignoreForCase * $lower ;
 Ћ ↔ C $acute ; # CYRILLIC CAPITAL LETTER TSHE
 џ ↔ d $hat ; # CYRILLIC SMALL LETTER DZHE
 Џ ↔ D $hat ; # CYRILLIC CAPITAL LETTER DZHE
-
-х ↔ kh ; # CYRILLIC SMALL LETTER HA
-Х } $beforeLower ↔ Kh ;
-Х ↔ KH; # CYRILLIC CAPITAL LETTER HA
-
-# Insert separator between K and characters that result in h
-# And delete going the other way
-[Kk] { } [Һһ] → ‧ ;
-← ‧ ;
+# https://www.eki.ee/wgrs/v2_2/rom2_az.htm
+# but modified to not collide with Cyrillic HA
+һ ↔ h $breveBelow ; # CYRILLIC SMALL LETTER SHHA
+Һ ↔ H $breveBelow; # CYRILLIC CAPITAL LETTER SHHA
 
 # Normal order
 а ↔ a ; # CYRILLIC SMALL LETTER A
@@ -179,9 +175,8 @@ $beforeLower = $ignoreForCase * $lower ;
 # Ѹ ↔ XXX ; # CYRILLIC CAPITAL LETTER UK
 ф ↔ f ; # CYRILLIC SMALL LETTER EF
 Ф ↔ F ; # CYRILLIC CAPITAL LETTER EF
-#https://www.eki.ee/wgrs/v2_2/rom2_az.htm
-һ ↔ h ; # CYRILLIC SMALL LETTER SHHA
-Һ ↔ H ; # CYRILLIC CAPITAL LETTER SHHA
+х ↔ h ; # CYRILLIC SMALL LETTER HA
+Х ↔ H; # CYRILLIC CAPITAL LETTER HA
 # ҳ ↔ XXX ; # CYRILLIC SMALL LETTER HA WITH DESCENDER
 # Ҳ ↔ XXX ; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER
 # ѡ ↔ XXX ; # CYRILLIC SMALL LETTER OMEGA
@@ -295,7 +290,7 @@ $ignore = [[:Mark:]''] * ;
 # note: a global filter is more efficient, but MUST include all source chars!!
 # :: ([\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:] ‧]);
 # MINIMAL FILTER: Latin-Cyrillic
-:: ( [hH‧ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;
+:: ( [ḫḪhH‧ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;
 			]]></tRule>
 		</transform>
 	</transforms>