ICU-22707 Unicode 16 script metadata

unicode-org · Apr 9, 2024 · 1a85d48 · 1a85d48
1 parent c3014df
commit 1a85d48
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 11 deletions.
diff --git a/icu4c/source/common/uscript_props.cpp b/icu4c/source/common/uscript_props.cpp
@@ -244,6 +244,14 @@ const int32_t SCRIPT_PROPS[] = {
     0x10582 | EXCLUSION | CASED,  // Vith
     0x11F1B | EXCLUSION | LB_LETTERS,  // Kawi
     0x1E4E6 | EXCLUSION,  // Nagm
+    0,
+    0x10D5D | EXCLUSION | RTL | CASED,  // Gara
+    0x1611C | EXCLUSION,  // Gukh
+    0x16D45 | EXCLUSION,  // Krai
+    0x1E5D0 | EXCLUSION,  // Onao
+    0x11BC4 | EXCLUSION,  // Sunu
+    0x105C2 | EXCLUSION,  // Todr
+    0x11392 | EXCLUSION,  // Tutg
     // End copy-paste from parsescriptmetadata.py
 };
 

diff --git a/icu4c/source/data/unidata/changes.txt b/icu4c/source/data/unidata/changes.txt
@@ -50,7 +50,6 @@ and see the change logs below.
 Unicode 16.0 update for ICU 76
 
 TODO
-- In the Unicode Tools repo: Delete the org.unicode.text.tools.RecommendedSetGenerator.
 - In corepropsbuilder.cpp, remove the isA9CF hack.
 
 https://www.unicode.org/versions/Unicode16.0.0/
@@ -62,6 +61,8 @@ https://www.unicode.org/reports/tr44/tr44-33.html
 https://unicode-org.atlassian.net/browse/ICU-22707 Unicode 16
 https://unicode-org.atlassian.net/browse/CLDR-17226 BRS Unicode 16
 
+https://github.com/unicode-org/unicodetools/pull/774 delete the RecommendedSetGenerator
+
 https://github.com/unicode-org/unicodetools/issues/492 adjust cldr/*BreakTest generation for Unicode 15.1
 
 * Command-line environment setup
@@ -198,8 +199,6 @@ export UNICODE_TOOLS=~/oss/unicodetools/mine/src
   + Indic_Syllabic_Category: uchar.h & UCharacter.IndicSyllabicCategory
   + after adding new API constants, run preparseucd.py again
 
-TODO: need to update CLDR script metadata first
-
 * update Script metadata: SCRIPT_PROPS[] in uscript_props.cpp & UScript.ScriptMetadata
     (not strictly necessary for NOT_ENCODED scripts)
   $ICU_SRC/tools/unicode$ py/parsescriptmetadata.py $ICU_SRC/icu4c/source/common/unicode/uscript.h $CLDR_SRC/common/properties/scriptMetadata.txt
@@ -219,8 +218,6 @@ to find out the latest `bazel` version, and
 copying that version number into the $ICU_SRC/.bazeliskrc config file.
 (Revert if you find incompatibilities, or, better, update our build & config files.)
 
-TODO
-
 * generate data files
 
 - remember to define the environment variables
@@ -233,6 +230,8 @@ TODO
 - build/bootstrap/generate new files:
     icu4c/source/data/unidata/generate.sh
 
+TODO
+
 * run & fix ICU4C tests
 - Note: Some of the collation data and test data will be updated below,
   so at this time we might get some collation test failures.
@@ -328,14 +327,14 @@ TODO
   output:
     ...
     make[1]: Entering directory '/usr/local/google/home/mscherer/icu/uni/dbg/icu4c/data'
-    mkdir -p ./out/icu4j/com/ibm/icu/impl/data/icudt74b
-    mkdir -p ./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt74b
-    LD_LIBRARY_PATH=../lib:../stubdata:../tools/ctestfw:$LD_LIBRARY_PATH  ../bin/icupkg ./out/tmp/icudt74l.dat ./out/icu4j/icudt74b.dat -s ./out/build/icudt74l -x '*' -tb -d ./out/icu4j/com/ibm/icu/impl/data/icudt74b
-    mv ./out/icu4j/"com/ibm/icu/impl/data/icudt74b/zoneinfo64.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt74b/metaZones.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt74b/timezoneTypes.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt74b/windowsZones.res" "./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt74b"
-    jar cf ./out/icu4j/icudata.jar -C ./out/icu4j com/ibm/icu/impl/data/icudt74b/
+    mkdir -p ./out/icu4j/com/ibm/icu/impl/data/icudt75b
+    mkdir -p ./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt75b
+    LD_LIBRARY_PATH=../lib:../stubdata:../tools/ctestfw:$LD_LIBRARY_PATH  ../bin/icupkg ./out/tmp/icudt75l.dat ./out/icu4j/icudt75b.dat -s ./out/build/icudt75l -x '*' -tb -d ./out/icu4j/com/ibm/icu/impl/data/icudt75b
+    mv ./out/icu4j/"com/ibm/icu/impl/data/icudt75b/zoneinfo64.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt75b/metaZones.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt75b/timezoneTypes.res" ./out/icu4j/"com/ibm/icu/impl/data/icudt75b/windowsZones.res" "./out/icu4j/tzdata/com/ibm/icu/impl/data/icudt75b"
+    jar cf ./out/icu4j/icudata.jar -C ./out/icu4j com/ibm/icu/impl/data/icudt75b/
     mkdir -p /tmp/icu4j/main/shared/data
     cp ./out/icu4j/icudata.jar /tmp/icu4j/main/shared/data
-    jar cf ./out/icu4j/icutzdata.jar -C ./out/icu4j/tzdata com/ibm/icu/impl/data/icudt74b/
+    jar cf ./out/icu4j/icutzdata.jar -C ./out/icu4j/tzdata com/ibm/icu/impl/data/icudt75b/
     mkdir -p /tmp/icu4j/main/shared/data
     cp ./out/icu4j/icutzdata.jar /tmp/icu4j/main/shared/data
     make[1]: Leaving directory '/usr/local/google/home/mscherer/icu/uni/dbg/icu4c/data'

diff --git a/icu4j/main/core/src/main/java/com/ibm/icu/lang/UScript.java b/icu4j/main/core/src/main/java/com/ibm/icu/lang/UScript.java
@@ -1585,6 +1585,14 @@ private static final class ScriptMetadata {
             0x10582 | EXCLUSION | CASED,  // Vith
             0x11F1B | EXCLUSION | LB_LETTERS,  // Kawi
             0x1E4E6 | EXCLUSION,  // Nagm
+            0,
+            0x10D5D | EXCLUSION | RTL | CASED,  // Gara
+            0x1611C | EXCLUSION,  // Gukh
+            0x16D45 | EXCLUSION,  // Krai
+            0x1E5D0 | EXCLUSION,  // Onao
+            0x11BC4 | EXCLUSION,  // Sunu
+            0x105C2 | EXCLUSION,  // Todr
+            0x11392 | EXCLUSION,  // Tutg
             // End copy-paste from parsescriptmetadata.py
         };