CLDR-16499 merge from main

unicode-org · May 6, 2024 · f490498 · f490498
2 parents 8e0c21b + 5881198
commit f490498
Show file tree

Hide file tree

Showing 150 changed files with 7,374 additions and 6,016 deletions.
diff --git a/.github/workflows/gh-pages.yml b/.github/workflows/gh-pages.yml
@@ -1,5 +1,11 @@
+
 name: Publish to gh-pages
 
+permissions:
+  pages: write
+  deployments: write
+  id-token: write
+
 on:
   push:
     branches:
@@ -53,22 +59,16 @@ jobs:
       - name: Build Jekyll part of the site
         run: |
           gem install bundler github-pages kramdown-parser-gfm  # should pull in jekyll, etc.
-          jekyll build -s docs -d _site
+          cd docs &&  github-pages build && mkdir -vp ../_site/ldml
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Rearrange stuff
         run: 'cp -vr tools/scripts/tr-archive/dist/* ./_site/ldml/ && cp tools/scripts/tr-archive/reports-v2.css ./_site/'
       - name: Deploy to GitHub Pages (main)
         if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: Cecilapp/GitHub-Pages-deploy@v3
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          # email: [email protected]
-          build_dir: _site               # optional
-          branch: gh-pages                # optional
-          # cname: domain.tld              # optional
-          # jekyll: no                     # optional
-          commit_message: CLDR-00000 Automated Build of Pages # optional
+        uses: actions/upload-pages-artifact@v2
       - name: Deploy to Smoketest
+        if: github.repository == 'unicode-org/cldr'
         shell: bash
         env:
           RSA_KEY_CCC: ${{ secrets.RSA_KEY_CCC }}
@@ -86,6 +86,16 @@ jobs:
           rsync -cav --delete-after -e "ssh -o UserKnownHostsFile=${HOME}/.knownhosts -i ${HOME}/.key -p ${CCC_PORT}" ./_site/ ${CCC_USER}@${CCC_HOST}:spec/$(basename ${GITHUB_REF_NAME})/
           echo "::endgroup::"
           echo "Now go to https://cldr-smoke.unicode.org/spec/"$(basename ${GITHUB_REF_NAME})
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{steps.deployment.outputs.page_url}}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v2
 
 # only run one of these at a time
 concurrency:

diff --git a/.github/workflows/maven.yml b/.github/workflows/maven.yml
@@ -187,7 +187,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: run CLDR console check
-        run: java -DCLDR_GITHUB_ANNOTATIONS=true -DCLDR_DIR=$(pwd) -Xmx6g -jar tools/cldr-code/target/cldr-code.jar check -S common,seed -e -z FINAL_TESTING
+        run: java -DCLDR_GITHUB_ANNOTATIONS=true -DCLDR_DIR=$(pwd) -Xmx6g -jar tools/cldr-code/target/cldr-code.jar check -S common,seed -e -z BUILD
   deploy:
     # don't run deploy on manual builds!
     if: github.repository == 'unicode-org/cldr' && github.event_name == 'push' && github.ref == 'refs/heads/main' && github.event.inputs.git-ref == ''

diff --git a/.node-version b/.node-version
@@ -1 +1 @@
-v18.15.0
+v20.12.2
diff --git a/README.md b/README.md
@@ -10,14 +10,14 @@ For current CLDR release information, see [cldr.unicode.org](https://cldr.unicod
 
 ## Status
 
-Update: 2024-04-03
+Update: 2024-04-22
 
 <!-- [inapplicable lines are commented out.]-->
-<!-- **Note:**  CLDR 45 is in development and not recommended for use at this stage. -->
-<!--**Note:**  This is the milestone 1 version of CLDR 45, intended for those wishing to do pre-release testing. It is not recommended for production use.-->
-<!--**Note:** This is a preliminary version of CLDR 45, 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 45, intended for testing. It is not recommended for production use.
-<!--This is the final release version of CLDR 45.-->
+**Note:**  CLDR 46 is in development and not recommended for use at this stage.
+<!--**Note:**  This is the milestone 1 version of CLDR 46, intended for those wishing to do pre-release testing. It is not recommended for production use.-->
+<!--**Note:** This is a preliminary version of CLDR 46, 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 46, intended for testing. It is not recommended for production use. -->
+<!--This is the final release version of CLDR 46.-->
 
 ### What is CLDR?
 The Unicode Common Locale Data Repository (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](https://cldr.unicode.org/index#h.ezpykkomyltl) for their software internationalization and localization, adapting software to the conventions of different languages for such common software tasks.

diff --git a/common/annotations/en.xml b/common/annotations/en.xml
@@ -3907,5 +3907,21 @@ annotations.
 		<annotation cp="³" type="tts">superscript three</annotation>
 		<annotation cp="µ">measure | micro sign</annotation>
 		<annotation cp="µ" type="tts">micro sign</annotation>
+		<!--  start hand-generated lines from E16 -->
+		<annotation cp='🪉' type='tts'>harp</annotation>
+		<annotation cp='🪉'>music | instrument | love | cupid | orchestra</annotation>
+		<annotation cp='🪏' type='tts'>shovel</annotation>
+		<annotation cp='🪏'>dig | spade | hole | scoop</annotation>
+		<annotation cp='🪾' type='tts'>leafless tree</annotation>
+		<annotation cp='🪾'>winter | barren | drought</annotation>
+		<annotation cp='🫆' type='tts'>fingerprint</annotation>
+		<annotation cp='🫆'>forensics | identity | safety</annotation>
+		<annotation cp='🫜' type='tts'>root vegetable</annotation>
+		<annotation cp='🫜'>root | vegetable | garden | beet | turnip</annotation>
+		<annotation cp='🫟' type='tts'>splatter</annotation>
+		<annotation cp='🫟'>paint | holi | spill | stain</annotation>
+		<annotation cp='🫩' type='tts'>face with bags under eyes</annotation>
+		<annotation cp='🫩'>tired | sleepy | exhausted</annotation>
+		<!--  end hand-generated lines from E16 -->
 	</annotations>
 </ldml>
diff --git a/common/annotations/root.xml b/common/annotations/root.xml
@@ -3908,5 +3908,21 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="³" type="tts">E13-137</annotation>
 		<annotation cp="µ">E13-150</annotation>
 		<annotation cp="µ" type="tts">E13-150</annotation>
+		<!--  start hand-generated lines from E16 -->
+		<annotation cp='🪉'>E16-001</annotation>
+		<annotation cp='🪉' type='tts'>E16-001</annotation>
+		<annotation cp='🪏'>E16-002</annotation>
+		<annotation cp='🪏' type='tts'>E16-002</annotation>
+		<annotation cp='🪾'>E16-003</annotation>
+		<annotation cp='🪾' type='tts'>E16-003</annotation>
+		<annotation cp='🫆'>E16-004</annotation>
+		<annotation cp='🫆' type='tts'>E16-004</annotation>
+		<annotation cp='🫜'>E16-005</annotation>
+		<annotation cp='🫜' type='tts'>E16-005</annotation>
+		<annotation cp='🫟'>E16-006</annotation>
+		<annotation cp='🫟' type='tts'>E16-006</annotation>
+		<annotation cp='🫩'>E16-007</annotation>
+		<annotation cp='🫩' type='tts'>E16-007</annotation>
+		<!--  end hand-generated lines from E16 -->
 	</annotations>
 </ldml>
diff --git a/common/bcp47/number.xml b/common/bcp47/number.xml
@@ -28,12 +28,14 @@ For terms of use, see http://www.unicode.org/copyright.html
             <type name="ethi" description="Ethiopic numerals — algorithmic"/>
             <type name="finance" description="Financial numerals — may be algorithmic" since="21"/>
             <type name="fullwide" description="Full width digits"/>
+            <type name="gara" description="Garay digits" since="46"/>
             <type name="geor" description="Georgian numerals — algorithmic"/>
             <type name="gong" description="Gunjala Gondi digits" since="33.1"/>
             <type name="gonm" description="Masaram Gondi digits" since="32"/>
             <type name="grek" description="Greek upper case numerals — algorithmic"/>
             <type name="greklow" description="Greek lower case numerals — algorithmic"/>
             <type name="gujr" description="Gujarati digits"/>
+            <type name="gukh" description="Gurung Khema digits" since="46"/>
             <type name="guru" description="Gurmukhi digits"/>
             <type name="hanidays" description="Han-character day-of-month numbering for lunar/other traditional calendars" since="25"/>
             <type name="hanidec" description="Positional decimal system using Chinese number ideographs as digits" since="1.9"/>
@@ -52,6 +54,7 @@ For terms of use, see http://www.unicode.org/copyright.html
             <type name="kawi" description="Kawi digits" since="42"/>
             <type name="khmr" description="Khmer digits"/>
             <type name="knda" description="Kannada digits"/>
+            <type name="krai" description="Kirat Rai digits" since="46"/>
             <type name="lana" description="Tai Tham Hora (secular) digits" since="21"/>
             <type name="lanatham" description="Tai Tham Tham (ecclesiastical) digits" since="21"/>
             <type name="laoo" description="Lao digits"/>
@@ -69,15 +72,19 @@ For terms of use, see http://www.unicode.org/copyright.html
             <type name="mroo" description="Mro digits" since="28"/>
             <type name="mtei" description="Meetei Mayek digits" since="21"/>
             <type name="mymr" description="Myanmar digits"/>
+            <type name="mymrepka" description="Myanmar Eastern Pwo Karen digits" since="46"/>
+            <type name="mymrpao" description="Myanmar Pao digits" since="46"/>
             <type name="mymrshan" description="Myanmar Shan digits" since="21"/>
             <type name="mymrtlng" description="Myanmar Tai Laing digits" since="28"/>
             <type name="nagm" description="Nag Mundari digits" since="42"/>
             <type name="native" description="Native digits" since="21"/>
             <type name="newa" description="Newa digits" since="30"/>
             <type name="nkoo" description="N'Ko digits" since="21"/>
             <type name="olck" description="Ol Chiki digits" since="21"/>
+            <type name="onao" description="Ol Onal digits" since="46"/>
             <type name="orya" description="Oriya digits"/>
             <type name="osma" description="Osmanya digits" since="21"/>
+            <type name="outlined" description="Legacy computing outlined digits" since="46"/>
             <type name="rohg" description="Hanifi Rohingya digits" since="33.1"/>
             <type name="roman" description="Roman upper case numerals — algorithmic"/>
             <type name="romanlow" description="Roman lowercase numerals — algorithmic"/>
@@ -88,6 +95,7 @@ For terms of use, see http://www.unicode.org/copyright.html
             <type name="sinh" description="Sinhala Lith digits" since="28"/>
             <type name="sora" description="Sora_Sompeng digits" since="21"/>
             <type name="sund" description="Sundanese digits" since="21"/>
+            <type name="sunu" description="Sunuwar digits" since="46"/>
             <type name="takr" description="Takri digits" since="21"/>
             <type name="talu" description="New Tai Lue digits" since="21"/>
             <type name="taml" description="Tamil numerals — algorithmic"/>

diff --git a/common/dtd/ldml.dtd b/common/dtd/ldml.dtd
@@ -42,7 +42,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ATTLIST version number CDATA #REQUIRED >
     <!--@MATCH:regex/\$Revision.*\$-->
     <!--@METADATA-->
-<!ATTLIST version cldrVersion CDATA #FIXED "45" >
+<!ATTLIST version cldrVersion CDATA #FIXED "46" >
     <!--@MATCH:any-->
     <!--@VALUE-->
 <!ATTLIST version draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >

diff --git a/common/dtd/ldml.xsd b/common/dtd/ldml.xsd
@@ -128,10 +128,10 @@ Note: DTD @-annotations are not currently converted to .xsd. For full CLDR file
   <xs:element name="version">
     <xs:complexType>
       <xs:attribute name="number" use="required"/>
-      <xs:attribute default="45" name="cldrVersion">
+      <xs:attribute default="46" name="cldrVersion">
         <xs:simpleType>
           <xs:restriction base="xs:string">
-            <xs:enumeration value="45"/>
+            <xs:enumeration value="46"/>
           </xs:restriction>
         </xs:simpleType>
       </xs:attribute>

diff --git a/common/dtd/ldmlBCP47.dtd b/common/dtd/ldmlBCP47.dtd
@@ -12,7 +12,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ATTLIST version number CDATA #REQUIRED >
     <!--@MATCH:regex/\$Revision.*\$-->
     <!--@METADATA-->
-<!ATTLIST version cldrVersion CDATA #FIXED "45" >
+<!ATTLIST version cldrVersion CDATA #FIXED "46" >
     <!--@MATCH:version-->
     <!--@VALUE-->
 

diff --git a/common/dtd/ldmlBCP47.xsd b/common/dtd/ldmlBCP47.xsd
@@ -24,10 +24,10 @@ Note: DTD @-annotations are not currently converted to .xsd. For full CLDR file
   <xs:element name="version">
     <xs:complexType>
       <xs:attribute name="number" use="required"/>
-      <xs:attribute default="45" name="cldrVersion">
+      <xs:attribute default="46" name="cldrVersion">
         <xs:simpleType>
           <xs:restriction base="xs:string">
-            <xs:enumeration value="45"/>
+            <xs:enumeration value="46"/>
           </xs:restriction>
         </xs:simpleType>
       </xs:attribute>

diff --git a/common/dtd/ldmlSupplemental.dtd b/common/dtd/ldmlSupplemental.dtd
@@ -12,10 +12,10 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ATTLIST version number CDATA #REQUIRED >
     <!--@MATCH:any-->
     <!--@METADATA-->
-<!ATTLIST version cldrVersion CDATA #FIXED "45" >
+<!ATTLIST version cldrVersion CDATA #FIXED "46" >
     <!--@MATCH:version-->
     <!--@VALUE-->
-<!ATTLIST version unicodeVersion CDATA #FIXED "15.1.0" >
+<!ATTLIST version unicodeVersion CDATA #FIXED "16.0.0" >
     <!--@MATCH:version-->
     <!--@VALUE-->
 
@@ -1078,7 +1078,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ATTLIST numberingSystem radix NMTOKEN #IMPLIED >
     <!--@VALUE-->
 <!ATTLIST numberingSystem digits CDATA #IMPLIED >
-    <!--@MATCH:unicodeset/[\p{Nd}[\u3007\u4E00\u4E03\u4E09\u4E5D\u4E8C\u4E94\u516B\u516D\u56DB][\U00011F50-\U00011F59\U0001E4F0-\U0001E4F9]]-->
+    <!--@MATCH:unicodeset/[\p{Nd}[\u3007\u4E00\u4E03\u4E09\u4E5D\u4E8C\u4E94\u516B\u516D\u56DB][\U00010D40-\U00010D49\U000116D0-\U000116E3\U00011BF0-\U00011BF9\U00016130-\U00016139\U00016D70-\U00016D79\U0001CCF0-\U0001CCF9\U0001E5F1-\U0001E5FA]]-->
     <!--@VALUE-->
 <!ATTLIST numberingSystem rules CDATA #IMPLIED >
     <!--@MATCH:any-->
@@ -1155,17 +1155,17 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT matchVariable EMPTY >
 <!ATTLIST matchVariable id CDATA #REQUIRED >
-    <!--@MATCH:regex/\$[a-zA-Z0-9_]+-->
+    <!--@MATCH:regex/(?!undefined)\$[a-zA-Z0-9_]+-->
 <!ATTLIST matchVariable value CDATA #REQUIRED >
-    <!--@MATCH:any-->
+    <!--@MATCH:regex/([A-Z]{2}|[0-9]{3})(\+([A-Z]{2}|[0-9]{3}))*-->
     <!--@VALUE-->
 
 <!ELEMENT languageMatch EMPTY >
     <!--@ORDERED-->
 <!ATTLIST languageMatch desired CDATA #REQUIRED >
-    <!--@MATCH:any/TODO-->
+    <!--@MATCH:regex/(?!undefined).*-->
 <!ATTLIST languageMatch supported CDATA #REQUIRED >
-    <!--@MATCH:any/TODO-->
+    <!--@MATCH:any/regex/(?!undefined).*-->
 <!ATTLIST languageMatch percent NMTOKEN #IMPLIED >
     <!--@MATCH:range/0~100-->
     <!--@VALUE-->

diff --git a/common/dtd/ldmlSupplemental.xsd b/common/dtd/ldmlSupplemental.xsd
@@ -64,17 +64,17 @@ Note: DTD @-annotations are not currently converted to .xsd. For full CLDR file
   <xs:element name="version">
     <xs:complexType>
       <xs:attribute name="number" use="required"/>
-      <xs:attribute default="45" name="cldrVersion">
+      <xs:attribute default="46" name="cldrVersion">
         <xs:simpleType>
           <xs:restriction base="xs:string">
-            <xs:enumeration value="45"/>
+            <xs:enumeration value="46"/>
           </xs:restriction>
         </xs:simpleType>
       </xs:attribute>
-      <xs:attribute default="15.1.0" name="unicodeVersion">
+      <xs:attribute default="16.0.0" name="unicodeVersion">
         <xs:simpleType>
           <xs:restriction base="xs:string">
-            <xs:enumeration value="15.1.0"/>
+            <xs:enumeration value="16.0.0"/>
           </xs:restriction>
         </xs:simpleType>
       </xs:attribute>

diff --git a/common/main/ar.xml b/common/main/ar.xml
@@ -6000,7 +6000,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		</timeZoneNames>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>arab</defaultNumberingSystem>
+		<defaultNumberingSystem>latn</defaultNumberingSystem>
 		<defaultNumberingSystem alt="latn">latn</defaultNumberingSystem>
 		<otherNumberingSystems>
 			<native>arab</native>

diff --git a/common/main/ar_AE.xml b/common/main/ar_AE.xml
@@ -47,7 +47,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</fields>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>latn</defaultNumberingSystem>
+		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>

diff --git a/common/main/ar_BH.xml b/common/main/ar_BH.xml
@@ -12,7 +12,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		<territory type="BH"/>
 	</identity>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>

diff --git a/common/main/ar_DJ.xml b/common/main/ar_DJ.xml
@@ -12,7 +12,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		<territory type="DJ"/>
 	</identity>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<currencies>
 			<currency type="DJF">
 				<symbol>Fdj</symbol>

diff --git a/common/main/ar_DZ.xml b/common/main/ar_DZ.xml
@@ -81,7 +81,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</calendars>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>latn</defaultNumberingSystem>
+		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>

diff --git a/common/main/ar_EG.xml b/common/main/ar_EG.xml
@@ -17,7 +17,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</languages>
 	</localeDisplayNames>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>

diff --git a/common/main/ar_EH.xml b/common/main/ar_EH.xml
@@ -12,6 +12,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		<territory type="EH"/>
 	</identity>
 	<numbers>
-		<defaultNumberingSystem>latn</defaultNumberingSystem>
+		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
 	</numbers>
 </ldml>
diff --git a/common/main/ar_ER.xml b/common/main/ar_ER.xml
@@ -12,7 +12,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		<territory type="ER"/>
 	</identity>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<currencies>
 			<currency type="ERN">
 				<symbol>Nfk</symbol>

diff --git a/common/main/ar_IL.xml b/common/main/ar_IL.xml
@@ -44,6 +44,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</calendars>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 	</numbers>
 </ldml>
diff --git a/common/main/ar_IQ.xml b/common/main/ar_IQ.xml
@@ -108,7 +108,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</calendars>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>

diff --git a/common/main/ar_JO.xml b/common/main/ar_JO.xml
@@ -108,7 +108,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 		</calendars>
 	</dates>
 	<numbers>
-		<defaultNumberingSystem>↑↑↑</defaultNumberingSystem>
+		<defaultNumberingSystem>arab</defaultNumberingSystem>
 		<symbols numberSystem="arab">
 			<decimal draft="contributed">↑↑↑</decimal>
 			<group draft="contributed">↑↑↑</group>