Merge pull request #2420 from unicode-org/maint/maint-42

Co-authored-by: Annemarie Apple <AEApple@users.noreply.github.com>, Mark Davis <mark@macchiato.com>, Steven R. Loomis <srl295@gmail.com>, Yoshito Umaoka <yumaoka@users.noreply.github.com> * CLDR-16002 json: update 'modern' logic (#2347) - update logic for 'modern' vs 'full' - new StandardCodes.getHighestLocaleCoverageLevel() which checks parent locales (but not root) * CLDR-15977 fix spaces in th and lao in person names (#2349) * CLDR-16005 BRS v42: Update ICU4J libs before beta1 (#2351) * CLDR-16006 CLDRModify fixes spacing in seed/main/en_Shaw_GB.xml (#2352) * CLDR-15958 json: fix currency generation (#2348) - due to CLDR-14336 - also, update the converter to drop draft status in later stages of process - expose a pattern in CLDRFile with draft status * CLDR-15414 json: personNames structure, other improvements (#2353) - drop xml:space from json, everywhere - reorg how the copyright date is done in json (to avoid a yearly bump) - improve how packageDesc is handled, so more packages have descriptions - add comments in JSON_config.txt * CLDR-15464 build: post maint branches and releases to smoketest (#2355) * CLDR-15933 Remove unnecessary & incorrect legacy alias added for key "mu" (#2361) * CLDR-16026 Add stub LDM section for Person Names, link to it from other sections (#2362) * CLDR-15876 Update parentLocales guidelines and invariants (#2364) * CLDR-15246 Remove dangerous and unneeded unpaired RLEs from annotations/ar.xml (#2368) * CLDR-15286 Document new dateTimeFormat "atTime" variant and when to use it (#2367) * CLDR-15626 Document currencyPattern alts alphaNextToNumber,noCurrency and currencyPatternAppendISO (#2366) * CLDR-16028 doc: update Latest Proposed Update link (#2370) * CLDR-16018 fix table in Multimap configuration (#2372) * CLDR-15956 Specify relations between the unit preferences data and the locale identifier (#2373) * CLDR-16036 BRS v42: Update ICU4J libs to release-72-rc before CLDR 42 beta2 (#2374) * CLDR-15609 Allow numeric signs in plural rule sample values (#2379) * CLDR-15900 v42: SLL extended transition period (#2375) * CLDR-14875 Document the usage of animate and inanimate with gender (#2380) * CLDR-15002 Update locale coverage chart for v42 (#2377) * CLDR-15955 Add constraints for unit IDs (#2378) * CLDR-15614 spec: link to OT feature registry (#2388) * CLDR-15559 the date format item count= not documented (#2384) * CLDR-15956 Incorporate text from #2365 (#2383) -fixing the spelling, and adding pointer to Unit Conversion and Unit Preferences. * CLDR-15655 spec v42 update .html links to .md (#2387) - kept .html when referring to network URLs * CLDR-15522 spec: correct link to ULI (#2392) * CLDR-15974 json: fix to PACKAGES.md (#2393) * CLDR-15608 Specify ranges of numbers with qualifiers (#2381) * CLDR-15524 doc: fix http to https (#2396) - also fix one bad link broken in CLDR-15655 - also unicode.org -> www.unicode.org * CLDR-15613 More info on matching pattern field lengths to requested skeleton field lengths (#2397) * CLDR-13370 Fix hybrid locales tags (#2390) - and add more explanation for what script is used for hybrid locales * CLDR-13722 Roll in Person Names body converted from GoogleDoc (pass 1) (#2398) * CLDR-16045 Remove Australia/India/Vietnam as keywords for non-globe emoji in some langs (#2399) * CLDR-16046 CLDRModify updates annotations ordering (#2400) * CLDR-15618 spec: improve docs about value+children (#2395) * CLDR-13722 refine person names spec algorithms (#2403) * CLDR-16051 tzdata 2022d updates (#2406)
unicode-org · Oct 3, 2022 · 7b370d0 · 7b370d0
2 parents d70f5d0 + 79919ae
commit 7b370d0
Show file tree

Hide file tree

Showing 185 changed files with 5,266 additions and 3,817 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -4,7 +4,7 @@ CLDR-_____
 
 <!--
 Thank you for your pull request.
-Please see http://cldr.unicode.org/index/process for general
+Please see https://cldr.unicode.org/index/process for general
 information on contributing to CLDR.
 
 1. Make sure the ticket is filed at
@@ -14,5 +14,5 @@ message to include the ticket ID (CLDR-_____)
 3. You will be automatically asked to sign the contributors’
 license before the PR is accepted.
 - sign: https://cla-assistant.io/unicode-org/cldr
-- license: http://www.unicode.org/copyright.html#License
+- license: https://www.unicode.org/copyright.html#License
 -->
diff --git a/.github/workflows/gh-pages.yml b/.github/workflows/gh-pages.yml
@@ -4,12 +4,15 @@ on:
   push:
     branches:
       - main
+      - "maint/maint-*"
+    tags:
+      - "release-*"
     # Only run if docs change.
-    paths:
-      - "tools/scripts/tr-archive/**"
-      - "docs/**"
-      - '.github/workflows/gh-pages.yml'
-
+    ## TODO CLDR-15464 reenable this!!
+    # paths:
+    #   - "tools/scripts/tr-archive/**"
+    #   - "docs/**"
+    #   - '.github/workflows/gh-pages.yml'
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -36,23 +39,18 @@ jobs:
         run: npx markdownlint-cli *.md {specs,docs}/*.md $(find .github -name '*.md') || (echo Warning, please fix these ; true)
       - name: Note any changes
         run: git status ; git diff
-      - name: Ruby cache
-        uses: actions/cache@v3
-        with:
-          path: ${{ github.workspace }}/vendor
-          key: ${{ runner.os }}-gems-${{ hashFiles('docs/**/Gemfile.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-gems-
       - uses: ruby/setup-ruby@v1
         with:
           ruby-version: 2.6
+          bundler-cache: true
       - 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
       - 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
+      - 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 }}
@@ -63,5 +61,23 @@ jobs:
           # cname: domain.tld              # optional
           # jekyll: no                     # optional
           commit_message: CLDR-00000 Automated Build of Pages # optional
+      - name: Deploy to Smoketest
+        shell: bash
+        env:
+          RSA_KEY_CCC: ${{ secrets.RSA_KEY_CCC }}
+          # the SSH port
+          CCC_USER: ${{ secrets.CCC_USER }}
+          CCC_PORT: 22
+          # the SSH host
+          CCC_HOST: cldr-smoke.unicode.org
+          # the ~/.ssh/known_hosts line mentioning SMOKETEST_HOST
+          CCC_KNOWNHOSTS: ${{ secrets.CCC_KNOWNHOSTS }}
+        run: |
+          echo "::group::Publish HTML"
+          echo "${RSA_KEY_CCC}" > ${HOME}/.key && chmod go= ${HOME}/.key
+          echo "${CCC_KNOWNHOSTS}" > ${HOME}/.knownhosts && chmod go= ${HOME}/.knownhosts
+          rsync -cav --delete-after -e "ssh -o UserKnownHostsFile=${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})
 
 # zero change
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -93,7 +93,7 @@ Copyright &copy; 1991-2022 Unicode, Inc.
 All rights reserved. [Terms of use][]
 
 [Survey Tool]: https://cldr.unicode.org/index/survey-tool
-[Terms of use]: http://www.unicode.org/copyright.html
+[Terms of use]: https://www.unicode.org/copyright.html
 [Jira]: https://github.com/unicode-org/cldr/blob/main/docs/requesting_changes.md
 [Tools source]: https://github.com/unicode-org/cldr/tree/main/tools
 [Maven setup]: https://cldr.unicode.org/development/cldr-development-site/maven-setup

diff --git a/README.md b/README.md
@@ -24,13 +24,13 @@ describing the organization of files within this repository
 ### Contributing
 
 Most data submissions are done via the [CLDR Survey Tool](https://st.unicode.org/cldr-apps/), which is open and available on predetermined cycles.
-Click [HERE](http://unicode.org/cldr/survey_tool.html) for information on how to obtain a survey tool account.
+Click [HERE](https://www.unicode.org/cldr/survey_tool.html) for information on how to obtain a survey tool account.
 
 For details about code and other contributions, see [CONTRIBUTING.md](./CONTRIBUTING.md)
 
 ### Licenses
 
-- Usage of CLDR data and software is governed by the [Unicode Terms of Use](http://www.unicode.org/copyright.html)
+- Usage of CLDR data and software is governed by the [Unicode Terms of Use](https://www.unicode.org/copyright.html)
 a copy of which is included as [unicode-license.txt](./unicode-license.txt).
 
 - Some CLDR tools depend on library dependencies managed via Maven,
@@ -42,4 +42,4 @@ SPDX-License-Identifier: Unicode-DFS-2016
 
 Copyright &copy; 1991-2022 Unicode, Inc.
 All rights reserved.
-[Terms of use](http://www.unicode.org/copyright.html)
+[Terms of use](https://www.unicode.org/copyright.html)
diff --git a/common/annotations/af.xml b/common/annotations/af.xml
@@ -965,8 +965,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🙉" type="tts">hoor geen kwaad nie</annotation>
 		<annotation cp="🙊">aap | boos | gesig | praat | praat geen kwaad nie | verbode</annotation>
 		<annotation cp="🙊" type="tts">praat geen kwaad nie</annotation>
-		<annotation cp="💋">hart | lippe | merk | romanse | soen | soenmerk</annotation>
-		<annotation cp="💋" type="tts">soenmerk</annotation>
 		<annotation cp="💌">brief | hart | liefde | liefdesbrief | pos | romanse</annotation>
 		<annotation cp="💌" type="tts">liefdesbrief</annotation>
 		<annotation cp="💘">cupido | hart | hartjie met pyl | kupido | pyl | romanse</annotation>
@@ -995,6 +993,8 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="❤‍🩹" type="tts">helende hart</annotation>
 		<annotation cp="❤">hart | rooi | rooi hartjie</annotation>
 		<annotation cp="❤" type="tts">rooi hartjie</annotation>
+		<annotation cp="🩷">hart | hou van | liefde | oulik | pienk</annotation>
+		<annotation cp="🩷" type="tts">pienk hart</annotation>
 		<annotation cp="🧡">oranje | oranje hartjie</annotation>
 		<annotation cp="🧡" type="tts">oranje hartjie</annotation>
 		<annotation cp="💛">geel | geel hartjie | hart</annotation>
@@ -1003,20 +1003,20 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="💚" type="tts">groen hartjie</annotation>
 		<annotation cp="💙">blou | blou hartjie | hart</annotation>
 		<annotation cp="💙" type="tts">blou hartjie</annotation>
-		<annotation cp="💜">hart | pers | pers hartjie</annotation>
-		<annotation cp="💜" type="tts">pers hartjie</annotation>
 		<annotation cp="🩵">groenblou | hart | ligblou | siaan</annotation>
 		<annotation cp="🩵" type="tts">ligblou hart</annotation>
-		<annotation cp="🩶">grys | hart | leikleurig | silwer</annotation>
-		<annotation cp="🩶" type="tts">grys hart</annotation>
-		<annotation cp="🩷">hart | hou van | liefde | oulik | pienk</annotation>
-		<annotation cp="🩷" type="tts">pienk hart</annotation>
+		<annotation cp="💜">hart | pers | pers hartjie</annotation>
+		<annotation cp="💜" type="tts">pers hartjie</annotation>
 		<annotation cp="🤎">bruin | hartjie</annotation>
 		<annotation cp="🤎" type="tts">bruin hartjie</annotation>
 		<annotation cp="🖤">boos | hart | sleg | swart | swart hartjie</annotation>
 		<annotation cp="🖤" type="tts">swart hartjie</annotation>
+		<annotation cp="🩶">grys | hart | leikleurig | silwer</annotation>
+		<annotation cp="🩶" type="tts">grys hart</annotation>
 		<annotation cp="🤍">hartjie | wit</annotation>
 		<annotation cp="🤍" type="tts">wit hartjie</annotation>
+		<annotation cp="💋">hart | lippe | merk | romanse | soen | soenmerk</annotation>
+		<annotation cp="💋" type="tts">soenmerk</annotation>
 		<annotation cp="💯">100 | honderd | honderd punte | persent | telling | vol</annotation>
 		<annotation cp="💯" type="tts">honderd punte</annotation>
 		<annotation cp="💢">kwaad | strokie | woede | woedesimbool</annotation>
@@ -1031,8 +1031,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="💨" type="tts">blitsig</annotation>
 		<annotation cp="🕳">gat</annotation>
 		<annotation cp="🕳" type="tts">gat</annotation>
-		<annotation cp="💣">bom | strokie</annotation>
-		<annotation cp="💣" type="tts">bom</annotation>
 		<annotation cp="💬">ballon | borrel | dialoog | spraak | spraakballon | strokie</annotation>
 		<annotation cp="💬" type="tts">spraakballon</annotation>
 		<annotation cp="👁‍🗨">afloer | getuie | oog in spraakborrel | spraakborrel</annotation>
@@ -1063,6 +1061,10 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🫳" type="tts">hand met palm ondertoe</annotation>
 		<annotation cp="🫴">bied aan | hand met palm boontoe | kom | roep | vang | Vote hand met palm boontoe</annotation>
 		<annotation cp="🫴" type="tts">hand met palm boontoe</annotation>
+		<annotation cp="🫷">druk | hand wat linkswaarts druk | linkswaarts | stop | vatvyf | wag | weier</annotation>
+		<annotation cp="🫷" type="tts">hand wat linkswaarts druk</annotation>
+		<annotation cp="🫸">druk | regswaarts | regswaarts drukkende hand | stop | vatvyf | wag | weier</annotation>
+		<annotation cp="🫸" type="tts">regswaarts drukkende hand</annotation>
 		<annotation cp="👌">hand | liggaam | ok | ok-handteken</annotation>
 		<annotation cp="👌" type="tts">ok-handteken</annotation>
 		<annotation cp="🤌">beklemtoon | handgebaar | ondervraging | sarkasties | vingerpunte saamgedruk | vingers</annotation>
@@ -1121,10 +1123,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🤝" type="tts">handskud</annotation>
 		<annotation cp="🙏">asseblief | bid | dankie | gebaar | gevoude hande | hand | liggaam</annotation>
 		<annotation cp="🙏" type="tts">gevoude hande</annotation>
-		<annotation cp="🫷">druk | hand wat linkswaarts druk | linkswaarts | stop | vatvyf | wag | weier</annotation>
-		<annotation cp="🫷" type="tts">hand wat linkswaarts druk</annotation>
-		<annotation cp="🫸">druk | regswaarts | regswaarts drukkende hand | stop | vatvyf | wag | weier</annotation>
-		<annotation cp="🫸" type="tts">regswaarts drukkende hand</annotation>
 		<annotation cp="✍">hand | hand wat skryf | skryf | skryfhand</annotation>
 		<annotation cp="✍" type="tts">hand wat skryf</annotation>
 		<annotation cp="💅">kosmetiek | manikuur | nael | naellak | politoer | versorg</annotation>
@@ -1993,6 +1991,8 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🪹" type="tts">leë nes</annotation>
 		<annotation cp="🪺">nes met eiers | nesmaak</annotation>
 		<annotation cp="🪺" type="tts">nes met eiers</annotation>
+		<annotation cp="🍄">paddastoel | plant | sampioen</annotation>
+		<annotation cp="🍄" type="tts">sampioen</annotation>
 		<annotation cp="🍇">druif | druiwe | plant | vrug</annotation>
 		<annotation cp="🍇" type="tts">druiwe</annotation>
 		<annotation cp="🍈">plant | spanspek | vrug</annotation>
@@ -2055,8 +2055,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🧄" type="tts">knoffel</annotation>
 		<annotation cp="🧅">geurmiddel | ui</annotation>
 		<annotation cp="🧅" type="tts">ui</annotation>
-		<annotation cp="🍄">paddastoel | plant | sampioen</annotation>
-		<annotation cp="🍄" type="tts">sampioen</annotation>
 		<annotation cp="🥜">grondboontjie | grondboontjies | kos | peule</annotation>
 		<annotation cp="🥜" type="tts">grondboontjies</annotation>
 		<annotation cp="🫘">bone | boontjies | kos | nierboontjies | peulgewas</annotation>
@@ -2811,16 +2809,14 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🪀" type="tts">jojo</annotation>
 		<annotation cp="🪁">sweef | vlieër | vlieg</annotation>
 		<annotation cp="🪁" type="tts">vlieër</annotation>
+		<annotation cp="🔫">rewolwer | skiet | vuurwapen | wapen</annotation>
+		<annotation cp="🔫" type="tts">rewolwer</annotation>
 		<annotation cp="🎱">8 | agt | bal | biljart | snoeker | speel</annotation>
 		<annotation cp="🎱" type="tts">biljart</annotation>
 		<annotation cp="🔮">bal | fortuinverteller | kristal | kristalbal | okkulte</annotation>
 		<annotation cp="🔮" type="tts">kristalbal</annotation>
 		<annotation cp="🪄">heks | towenaar | towerkrag | towerstaf</annotation>
 		<annotation cp="🪄" type="tts">towerstaf</annotation>
-		<annotation cp="🧿">bose oog | gelukbringer | nazar | nazar-gelukbringer | talisman</annotation>
-		<annotation cp="🧿" type="tts">nazar-gelukbringer</annotation>
-		<annotation cp="🪬">amulet | beskerming | Fatima | hamsa | hand | Maria | Miriam</annotation>
-		<annotation cp="🪬" type="tts">hamsa</annotation>
 		<annotation cp="🎮">beheer | kontrole | speel | video | videospeletjie</annotation>
 		<annotation cp="🎮" type="tts">videospeletjie</annotation>
 		<annotation cp="🕹">speel | speelstok | stang | stok | video</annotation>
@@ -2911,8 +2907,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="👚" type="tts">vroueklere</annotation>
 		<annotation cp="🪭">dans | fladder | handwaaier wat vou | skaam | verkoel | waaier | warm</annotation>
 		<annotation cp="🪭" type="tts">handwaaier wat vou</annotation>
-		<annotation cp="🪮">Afro | haarnaald | hare | kam | naald</annotation>
-		<annotation cp="🪮" type="tts">haarnaald</annotation>
 		<annotation cp="👛">beursie | geld | klere</annotation>
 		<annotation cp="👛" type="tts">beursie</annotation>
 		<annotation cp="👜">handsak | klere | sak | tas</annotation>
@@ -2941,6 +2935,8 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🩰" type="tts">balletskoene</annotation>
 		<annotation cp="👢">klere | skoen | stewel | vrou | vrouestewel</annotation>
 		<annotation cp="👢" type="tts">vrouestewel</annotation>
+		<annotation cp="🪮">Afro | haarnaald | hare | kam | naald</annotation>
+		<annotation cp="🪮" type="tts">haarnaald</annotation>
 		<annotation cp="👑">klere | koning | koningin | kroon</annotation>
 		<annotation cp="👑" type="tts">kroon</annotation>
 		<annotation cp="👒">hoed | klere | vrou | vrouehoed</annotation>
@@ -3259,8 +3255,8 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🗡" type="tts">dolk</annotation>
 		<annotation cp="⚔">gekruiste swaarde | swaarde | wapen</annotation>
 		<annotation cp="⚔" type="tts">gekruiste swaarde</annotation>
-		<annotation cp="🔫">rewolwer | skiet | vuurwapen | wapen</annotation>
-		<annotation cp="🔫" type="tts">rewolwer</annotation>
+		<annotation cp="💣">bom | strokie</annotation>
+		<annotation cp="💣" type="tts">bom</annotation>
 		<annotation cp="🪃">Australië | boemerang | terugdraai | terugkeer</annotation>
 		<annotation cp="🪃" type="tts">boemerang</annotation>
 		<annotation cp="🏹">boog | boogskutter | diereriem | pyl | pyl en boog | sagittarius | wapen</annotation>
@@ -3381,6 +3377,10 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🪦" type="tts">grafsteen</annotation>
 		<annotation cp="⚱">as | begrafnis | begrafniskruik | dood | kruik</annotation>
 		<annotation cp="⚱" type="tts">begrafniskruik</annotation>
+		<annotation cp="🧿">bose oog | gelukbringer | nazar | nazar-gelukbringer | talisman</annotation>
+		<annotation cp="🧿" type="tts">nazar-gelukbringer</annotation>
+		<annotation cp="🪬">amulet | beskerming | Fatima | hamsa | hand | Maria | Miriam</annotation>
+		<annotation cp="🪬" type="tts">hamsa</annotation>
 		<annotation cp="🗿">gesig | moai | Paaseiland | reis | standbeeld</annotation>
 		<annotation cp="🗿" type="tts">moai</annotation>
 		<annotation cp="🪧">betoging | plakkaat | protes</annotation>
@@ -3579,12 +3579,12 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🔆" type="tts">helderknoppie</annotation>
 		<annotation cp="📶">antenna | antennastawe | sein | seinsterkte | selfoon | selfoonsein</annotation>
 		<annotation cp="📶" type="tts">antennastawe</annotation>
+		<annotation cp="🛜">draadloos | internet | netwerk | rekenaar</annotation>
+		<annotation cp="🛜" type="tts">draadloos</annotation>
 		<annotation cp="📳">foon | mobiel | sel | telefoon | vibrasiemodus | vibreer</annotation>
 		<annotation cp="📳" type="tts">vibrasiemodus</annotation>
 		<annotation cp="📴">af | foon | mobiel | sel | selfoon af | telefoon</annotation>
 		<annotation cp="📴" type="tts">selfoon af</annotation>
-		<annotation cp="🛜">draadloos | internet | netwerk | rekenaar</annotation>
-		<annotation cp="🛜" type="tts">draadloos</annotation>
 		<annotation cp="♀">vroulik | vroulik-teken</annotation>
 		<annotation cp="♀" type="tts">vroulik-teken</annotation>
 		<annotation cp="♂">manlik | manlik-teken</annotation>