Merge remote-tracking branch 'la-vache/main' into pipeline-gap-174-C20

unicode-org · Oct 16, 2024 · a19b6aa · a19b6aa
2 parents 4b5e8a9 + 69a376c
commit a19b6aa
Show file tree

Hide file tree

Showing 356 changed files with 3,636,633 additions and 17,947 deletions.
diff --git a/.github/workflows/build-jsp.yml b/.github/workflows/build-jsp.yml
@@ -1,8 +1,8 @@
 name: Build JSP
 
 env:
-  CURRENT_UVERSION: 16.0.0
-  PREVIOUS_UVERSION: 15.1.0  # not used at present
+  CURRENT_UVERSION: 17.0.0 # FIX_FOR_NEW_VERSION
+  PREVIOUS_UVERSION: 16.0.0  # not used at present
 
 on:
   push:
@@ -69,7 +69,7 @@ jobs:
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     - name: Upload UnicodeJsps.war
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: UnicodeJsps
         path: UnicodeJsps/target/UnicodeJsps.war

diff --git a/.github/workflows/cli-build-instructions.yml b/.github/workflows/cli-build-instructions.yml
@@ -9,8 +9,8 @@ on:
     - '*'
 
 env:
-  CURRENT_UVERSION: 16.0.0
-  PREVIOUS_UVERSION: 15.1.0
+  CURRENT_UVERSION: 17.0.0  # FIX_FOR_NEW_VERSION
+  PREVIOUS_UVERSION: 16.0.0
 
 jobs:
 

diff --git a/.github/workflows/pipeline.yml b/.github/workflows/pipeline.yml
@@ -53,7 +53,7 @@ jobs:
       uses: actions/checkout@v3
       with:
         sparse-checkout: py/pipeline-workflow
-    - name: Check L2 document
+    - name: Check L2 document and WG references
       run: |
         python3 py/pipeline-workflow/check-l2-document.py
   utc-decision:

diff --git a/.github/workflows/push-jsp-on-tag.yml b/.github/workflows/push-jsp-on-tag.yml
@@ -49,7 +49,7 @@ jobs:
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     - name: Upload UnicodeJsps.war
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: UnicodeJsps
         path: UnicodeJsps/target/UnicodeJsps.war

diff --git a/.github/workflows/pythonpackage.yml b/.github/workflows/pythonpackage.yml
@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.8]
+        python-version: [3.12]
 
     steps:
     - uses: actions/checkout@v3

diff --git a/README.md b/README.md
@@ -25,6 +25,6 @@ The tools maintainers use GH issues for issues with the code in this repo.
 
 Copyright © 2001-2024 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries.
 
-The project is released under [LICENSE](./LICENSE).
-
 A CLA is required to contribute to this project - please refer to the [CONTRIBUTING.md](https://github.com/unicode-org/.github/blob/main/.github/CONTRIBUTING.md) file (or start a Pull Request) for more information.
+
+The contents of this repository are governed by the Unicode [Terms of Use](https://www.unicode.org/copyright.html) and are released under [LICENSE](./LICENSE).
diff --git a/UnicodeJsps/src/test/java/org/unicode/jsptest/TestJsp.java b/UnicodeJsps/src/test/java/org/unicode/jsptest/TestJsp.java
@@ -929,7 +929,7 @@ public void TestIdna() {
         checkValues(error, Uts46.SINGLETON);
         checkValidIdna(Uts46.SINGLETON, "À｡÷");
         checkValidIdna(Uts46.SINGLETON, "≠"); // valid since Unicode 15.1
-        checkInvalidIdna(Uts46.SINGLETON, "\u0001");
+        checkInvalidIdna(Uts46.SINGLETON, "\u0080");
         checkToUnicode(Uts46.SINGLETON, "ß｡ab", "ß.ab");
         // checkToPunyCode(Uts46.SINGLETON, "\u0002", "xn---");
         checkToPunyCode(Uts46.SINGLETON, "ß｡ab", "ss.ab");
@@ -973,7 +973,8 @@ public void TestIdna() {
     private void checkValues(boolean[] error, Idna idna) {
         checkToUnicodeAndPunyCode(idna, "α.xn--mxa", "α.α", "xn--mxa.xn--mxa");
         checkValidIdna(idna, "a");
-        checkInvalidIdna(idna, "=");
+        // 33C2          ; disallowed                 # 1.1  SQUARE AM
+        checkInvalidIdna(idna, "㏂");
     }
 
     private void checkToUnicodeAndPunyCode(

diff --git a/docs/emoji/aac.md b/docs/emoji/aac.md
@@ -5,15 +5,6 @@
 Once the emoji are finalized for new version of TR51, or there is a new version
 of CLDR, run AacOrder.java to generate 3 new files which will be checked in.
 
-Fix the versions at the top of the file, such as:
-```
-private static final VersionInfo VERSION = Emoji.VERSION12;
-
-private static final VersionInfo UCD_VERSION = Emoji.VERSION12;
-```
-
-The emoji version will be ≥ the UCD version.
-
 **Results:**
 
 :construction: **TODO**: Work with Mark on working replacements for "draft" URLs.

diff --git a/docs/help/changes.md b/docs/help/changes.md
@@ -3,42 +3,38 @@
 The Unicode Utilities have been modified to support both properties from the
 released version of Unicode (via ICU) and from the new Unicode beta.
 
-To get the beta version of the property, insert β *after* the property name.
+To get the beta version of the property, insert `Uβ:` *before* the property name.
+The explicit version number for the β can be used;
+the resulting property is then only valid when that specific β is current.
 Examples:
 
-| `\p{Word_Break=ALetter}` | Released version of Unicode |
-| `\p{Word_Breakβ=ALetter}` | Beta version of Unicode     |
+| Query | Result |
+|---|---|
+| `\p{Word_Break=ALetter}` | Released version of Unicode. |
+| `\p{Uβ:Word_Break=ALetter}` | Beta version of Unicode; error outside of beta review. |
+| `\p{U16β:Word_Break=ALetter}` | Beta version of Unicode 16.0; error during the beta review of any other version. |
 
 
 For example, to see additions to that property value in the beta version, use:
 
 <center>
 
-[`\p{Word_Breakβ=ALetter}-\\p{Word_Break=ALetter}`](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7BWord_Break%CE%B2%3DALetter%7D-%5Cp%7BWord_Break%3DALetter%7D&g=&i=)
+[`\p{Uβ:Word_Break=ALetter}-\p{Word_Break=ALetter}`](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7BU%CE%B2%3AWord_Break%3DALetter%7D-%5Cp%7BWord_Break%3DALetter%7D&g=&i=)
 
 </center>
 
 
 ## Caveats
 
-The support is not complete done, and there are some known problems.
-
-1.  Some properties are not supported in beta versions. See
-    <https://util.unicode.org/UnicodeJsps/properties.jsp>
-    for the list.
-2.  When characters are listed, the new blocks and subheads don't show up.
-3.  If you use a property that has a β version but no ICU version, you get no
-    error: just an empty listing.
-4.  The beta properties don't yet have the "shorthands" for cases like \\p{Lu}.
-    So make sure the property is listed, eg \\p{gcβ=Lu}
-    1.  Example:
-        [`\p{gcβ=Lu}-\\p{gc=Lu}`](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7Bgc%CE%B2%3DLu%7D-%5Cp%7Bgc%3DLu%7D&g=&i=)
-5.  Tools for segmentation, etc. use the release properties; there isn't a way
+The support is not completely done, and there are some known problems.
+
+1.  The General_Category groupings such as \\p{Uβ:L} are not correctly implemented.
+    Only actual values, such as \\p{Uβ:Lu} etc., work.
+2.  Tools for segmentation, etc. use the release properties; there isn't a way
     to have them use the beta properties.
-6.  There are probably others...
+3.  There are probably others...
 
 If you find a problem, please file a ticket at
-<https://cldr.unicode.org/index/bug-reports>: make sure to start the summary with
-"Unicode Utilities: "
+https://github.com/unicode-org/unicodetools/issues.
 
 [Back to Unicode Utilities Help Home](index)
diff --git a/docs/pipeline.md b/docs/pipeline.md
@@ -61,6 +61,7 @@ PR preparation:
 - [ ] If from SAH — Link SAH issue
 - [ ] If from ESC or CJK — Mention ESC or CJK in the PR description
 - [ ] When for a UTC decision — Cite in the format UTC-\d\d\d-[MC]\d+ or with a link.
+- [ ] Link RMG issue
 - [ ] Whenever there is a Proposal document — Cite L2 number in the format L2/yy-nnn
 - [ ] data-for-new — Set label
 - [ ] pipeline-* — Set label to **pipeline-recommended-to-UTC** if the characters are not yet in the pipeline, and **pipeline-provisionally-assigned**, or **pipeline-`<version>`** depending on their status in [the Pipeline](https://unicode.org/alloc/Pipeline.html#future).
@@ -113,7 +114,7 @@ git checkout la-vache/main unicodetools/data/ucd/dev/extracted/*;
 git checkout la-vache/main unicodetools/data/ucd/dev/auxiliary/*;
 rm .\Generated\* -recurse -force;
 mvn compile exec:java '-Dexec.mainClass="org.unicode.text.UCD.Main"'  '-Dexec.args="build MakeUnicodeFiles"' -am -pl unicodetools  "-DCLDR_DIR=..\cldr\"  "-DUNICODETOOLS_GEN_DIR=Generated"  "-DUNICODETOOLS_REPO_DIR=.";
-cp .\Generated\UCD\16.0.0\* .\unicodetools\data\ucd\dev -recurse -force;
+cp .\Generated\UCD\17.0.0\* .\unicodetools\data\ucd\dev -recurse -force;
 rm unicodetools\data\ucd\dev\zzz-unchanged-*;
 rm unicodetools\data\ucd\dev\*\zzz-unchanged-*;
 rm .\unicodetools\data\ucd\dev\extra\*;
@@ -123,19 +124,20 @@ git merge --continue
 ```
 
 markusicu (Linux, out-of-source; main tracks unicode-org/main)
+<!--FIX_FOR_NEW_VERSION-->
 ```sh
 git merge main
 # complains about merge conflicts as expected
 git checkout main unicodetools/data/ucd/dev/Derived*
 git checkout main unicodetools/data/ucd/dev/extracted/*
 git checkout main unicodetools/data/ucd/dev/auxiliary/*
-rm -r ../Generated/BIN/16.0.0.0/
-rm -r ../Generated/BIN/UCD_Data16.0.0.bin
-mvn -s ~/.m2/settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCD.Main"  -Dexec.args="version 16.0.0 build MakeUnicodeFiles" -am -pl unicodetools  -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd)  -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd)  -DUNICODETOOLS_REPO_DIR=$(pwd)  -DUVERSION=16.0.0
+rm -r ../Generated/BIN/17.0.0.0/
+rm -r ../Generated/BIN/UCD_Data17.0.0.bin
+mvn -s ~/.m2/settings.xml compile exec:java -Dexec.mainClass="org.unicode.text.UCD.Main"  -Dexec.args="version 17.0.0 build MakeUnicodeFiles" -am -pl unicodetools  -DCLDR_DIR=$(cd ../../../cldr/mine/src ; pwd)  -DUNICODETOOLS_GEN_DIR=$(cd ../Generated ; pwd)  -DUNICODETOOLS_REPO_DIR=$(pwd)  -DUVERSION=17.0.0
 # fix merge conflicts in unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java
 #   and in UCD_Names.java
 # rerun mvn
-cp -r ../Generated/UCD/16.0.0/* unicodetools/data/ucd/dev
+cp -r ../Generated/UCD/17.0.0/* unicodetools/data/ucd/dev
 rm unicodetools/data/ucd/dev/ZZZ-UNCHANGED-*
 rm unicodetools/data/ucd/dev/*/ZZZ-UNCHANGED-*
 rm unicodetools/data/ucd/dev/extra/*
@@ -156,10 +158,11 @@ Cf. https://github.com/unicode-org/unicodetools/pull/636
 ### Regenerate UCD
 
 eggrobin (Windows, in-source).
+<!--FIX_FOR_NEW_VERSION-->
 ```powershell
 rm .\Generated\* -recurse -force
 mvn compile exec:java '-Dexec.mainClass="org.unicode.text.UCD.Main"'  '-Dexec.args="build MakeUnicodeFiles"' -am -pl unicodetools  "-DCLDR_DIR=..\cldr\"  "-DUNICODETOOLS_GEN_DIR=Generated"  "-DUNICODETOOLS_REPO_DIR=."
-cp .\Generated\UCD\16.0.0\* .\unicodetools\data\ucd\dev -recurse -force
+cp .\Generated\UCD\17.0.0\* .\unicodetools\data\ucd\dev -recurse -force
 rm unicodetools\data\ucd\dev\zzz-unchanged-*
 rm unicodetools\data\ucd\dev\*\zzz-unchanged-*
 rm .\unicodetools\data\ucd\dev\extra\*
@@ -171,10 +174,11 @@ git commit -m "Regenerate UCD"
 ### Regenerate LineBreak
 
 eggrobin (Windows, in-source).
+<!--FIX_FOR_NEW_VERSION-->
 ```powershell
 rm .\Generated\* -recurse -force
 mvn compile exec:java '-Dexec.mainClass="org.unicode.text.UCD.Main"'  '-Dexec.args="build MakeUnicodeFiles"' -am -pl unicodetools  "-DCLDR_DIR=..\cldr\"  "-DUNICODETOOLS_GEN_DIR=Generated"  "-DUNICODETOOLS_REPO_DIR=."
-cp .\Generated\UCD\16.0.0\LineBreak.txt .\unicodetools\data\ucd\dev
+cp .\Generated\UCD\17.0.0\LineBreak.txt .\unicodetools\data\ucd\dev
 ```
 
 ### GenerateEnums

diff --git a/pub/copy-alpha-to-draft.sh b/pub/copy-alpha-to-draft.sh
@@ -12,8 +12,8 @@ UNITOOLS_DATA=$UNICODETOOLS/unicodetools/data
 
 # Adjust the following for each year and version as needed.
 COPY_YEAR=2024
-UNI_VER=16.0.0
-EMOJI_VER=16.0
+UNI_VER=17.0.0
+EMOJI_VER=17.0
 
 TODAY=`date --iso-8601`
 

diff --git a/pub/copy-beta-to-draft.sh b/pub/copy-beta-to-draft.sh
@@ -12,11 +12,11 @@ UNITOOLS_DATA=$UNICODETOOLS/unicodetools/data
 
 # Adjust the following for each year and version as needed.
 COPY_YEAR=2024
-UNI_VER=16.0.0
-EMOJI_VER=16.0
+UNI_VER=17.0.0
+EMOJI_VER=17.0
 # UTS #10 release revision number to be used in CollationTest.html:
 # One more than the last release revision number.
-TR10_REV=tr10-50
+TR10_REV=tr10-52
 
 TODAY=`date --iso-8601`
 
@@ -42,7 +42,7 @@ mv $DRAFT/UCD/ucd/zipped-ReadMe.txt $DRAFT/zipped/ReadMe.txt
 
 mkdir -p $DRAFT/UCA
 cp -r $UNITOOLS_DATA/uca/dev/* $DRAFT/UCA
-sed -i -f $DEST/sed-readmes.txt $DRAFT/UCA/CollationTest.html
+sed -i -f $DRAFT/sed-readmes.txt $DRAFT/UCA/CollationTest.html
 
 mkdir -p $DRAFT/emoji
 cp $UNITOOLS_DATA/emoji/dev/* $DRAFT/emoji

diff --git a/pub/copy-final.sh b/pub/copy-final.sh
@@ -12,11 +12,11 @@ UNITOOLS_DATA=$UNICODETOOLS/unicodetools/data
 
 # Adjust the following for each year and version as needed.
 COPY_YEAR=2024
-UNI_VER=16.0.0
-EMOJI_VER=16.0
+UNI_VER=17.0.0
+EMOJI_VER=17.0
 # UTS #10 release revision number to be used in CollationTest.html:
 # *Two* more than the last release revision number.
-TR10_REV=tr10-51
+TR10_REV=tr10-53
 
 TODAY=`date --iso-8601`
 

diff --git a/py/pipeline-workflow/check-l2-document.py b/py/pipeline-workflow/check-l2-document.py
@@ -18,4 +18,9 @@
           "PRs for character additions must include a link to the SAH issue, or "
           "the mention ESC or CJK.")
     errors += 1
+if not re.search(r"(unicode-org/utc-release-management(#|/issues/)\d)", pr_body):
+    print("::error title=Need RMG reference::"
+          "PRs for character additions must include a link to the corresponding "
+          "RMG issue.")
+    errors += 1
 exit(errors)
diff --git a/unicodetools/data/emoji/16.0/ReadMe.txt b/unicodetools/data/emoji/16.0/ReadMe.txt
@@ -0,0 +1,21 @@
+# Unicode Emoji
+# © COPY_YEAR Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
+
+This directory contains PUB_STATUS data files for Unicode Emoji, Version EMOJI_VER
+
+PUBLIC_EMOJI/
+
+  emoji-sequences.txt
+  emoji-zwj-sequences.txt
+  emoji-test.txt
+
+The following related files are found in the UCD for Version EMOJI_VER
+
+PUBLIC_UCD/ucd/emoji/
+
+  emoji-data.txt
+  emoji-variation-sequences.txt
+
+For documentation, see UTS #51 Unicode Emoji, Version EMOJI_VER