Unicode 16.0→ 17.0 (#931)

* Copy emoji/dev to emoji/16.0. * Copy idna/dev to idna/16.0.0. * Copy security/dev to security/16.0.0. * Copy uca/dev to uca/16.0.0. * Copy ucd/dev to ucd/16.0.0. * Copy ucdxml/dev to ucdxml/16.0.0. * Bump version and revision numbers in pub/meow.sh. * Manually fix a dozen files * Regenerate UCD * spotless * Fix LoadIdnaTest for the new ""
unicode-org · Sep 12, 2024 · 8e56687 · 8e56687
1 parent d050b8a
commit 8e56687
Show file tree

Hide file tree

Showing 253 changed files with 3,547,488 additions and 39 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:

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/docs/pipeline.md b/docs/pipeline.md
@@ -114,7 +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\*;
@@ -124,19 +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/*
@@ -157,10 +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\*
@@ -172,10 +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`
 

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/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