Merge remote-tracking branch 'la-vache/main' into ˈˌ

Author: eggrobin

.github/workflows/build-jsp.yml

@@ -1,8 +1,8 @@
 name: Build JSP
 
 env:
-  CURRENT_UVERSION: 17.0.0 # FIX_FOR_NEW_VERSION
-  PREVIOUS_UVERSION: 16.0.0  # not used at present
+  CURRENT_UVERSION: 18.0.0 # FIX_FOR_NEW_VERSION
+  PREVIOUS_UVERSION: 17.0.0  # not used at present
   REGISTRY: ghcr.io
   IMAGE_NAME: ${{ github.repository }}
 

.github/workflows/cli-build-instructions.yml

@@ -9,8 +9,8 @@ on:
     - '*'
 
 env:
-  CURRENT_UVERSION: 17.0.0  # FIX_FOR_NEW_VERSION
-  PREVIOUS_UVERSION: 16.0.0
+  CURRENT_UVERSION: 18.0.0  # FIX_FOR_NEW_VERSION
+  PREVIOUS_UVERSION: 17.0.0
 
 jobs:
 

.github/workflows/codeql.yml

@@ -27,16 +27,16 @@ jobs:
         uses: actions/checkout@v3
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@v3
         with:
           languages: ${{ matrix.language }}
           queries: +security-and-quality
 
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v2
+        uses: github/codeql-action/autobuild@v3
         if: ${{ matrix.language == 'javascript' || matrix.language == 'python' }}
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v2
+        uses: github/codeql-action/analyze@v3
         with:
           category: "/language:${{ matrix.language }}"

.gitignore

@@ -43,6 +43,7 @@ perf-*.xml
 test-*.xml
 
 # Directories
+.idea/
 .settings/
 .vs/
 .vscode/

README.md

@@ -13,6 +13,10 @@ Some of the documentation still refers to the previous Subversion repository.
 This GitHub repo reflects the svn repo up to r1566,
 plus a few snapshots up to r1830. (Don’t ask.)
 
+### Online Web Tools
+
+This repository includes the source for the tooling at <https://util.unicode.org> - see [`/UnicodeJsps`](./UnicodeJsps/README.md)
+
 ### Bug reports
 
 For feedback on the Unicode Standard and bug reports against the Unicode Character Database,
@@ -23,7 +27,7 @@ The tools maintainers use GH issues for issues with the code in this repo.
 
 ### Copyright & Licenses
 
-Copyright © 2001-2024 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries.
+Copyright © 2001-2025 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries.
 
 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.
 

UnicodeJsps/Dockerfile

@@ -3,7 +3,8 @@ FROM alpine as cbuild
 WORKDIR /build
 RUN apk add --update wget make gcc musl-dev
 ARG CPATH=https://www.unicode.org/Public/PROGRAMS/BidiReferenceC/
-ARG CVERSION=15.1.0
+# FIX_FOR_NEW_VERSION
+ARG CVERSION=16.0.0
 RUN wget -np -nv --reject-regex='.*\.(lib|exe)$' --cut-dirs=4 -nH -r ${CPATH}${CVERSION}/
 RUN cd source && gcc -I ../include/ -static -Os -o3 -o bidiref1 bidiref1.c brutils.c brtest.c brtable.c brrule.c
 RUN ls -lh /build/source/bidiref1 && (/build/source/bidiref1 || true)

UnicodeJsps/README.md

@@ -0,0 +1,15 @@
+# UnicodeJsps
+
+This subdirectory includes the source for the tooling at <https://util.unicode.org>
+
+## Building
+
+See [/docs/unicodejsps](../docs/unicodejsps/index.md)
+
+### Copyright & Licenses
+
+Copyright © 2001-2025 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries.
+
+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).

UnicodeJsps/src/main/java/org/unicode/jsp/BidiCharMap.java

@@ -48,7 +48,7 @@ class BidiCharMap {
 
         for (UnicodeSetIterator it =
                         new UnicodeSetIterator(
-                                new UnicodeSet("[[:ascii:]-[[:cc:]-[:whitespace:]]]"));
+                                new UnicodeSet("[[:Block=ASCII:]-[[:cc:]-[:whitespace:]]]"));
                 it.next(); ) {
             asciiHackMap.put(
                     it.codepoint,

UnicodeJsps/src/main/java/org/unicode/jsp/Common.java

@@ -7,9 +7,7 @@
 import com.ibm.icu.text.Normalizer2;
 import com.ibm.icu.text.StringTransform;
 import com.ibm.icu.text.Transform;
-import com.ibm.icu.text.UTF16;
 import com.ibm.icu.text.UnicodeSet;
-import com.ibm.icu.util.ULocale;
 import java.util.Arrays;
 import java.util.List;
 import org.unicode.jsp.XPropertyFactory.HanType.HanTypeValues;
@@ -47,18 +45,7 @@ public String transform(String source) {
             };
 
     static List<String> XPROPERTY_NAMES =
-            Arrays.asList(
-                    new String[] {
-                        "toNFC",
-                        "toNFD",
-                        "toNFKC",
-                        "toNFKD",
-                        "toCasefold",
-                        "toLowercase",
-                        "toUppercase",
-                        "toTitlecase",
-                        "subhead"
-                    });
+            Arrays.asList(new String[] {"toNFC", "toNFD", "toNFKC", "toNFKD"});
     static final int XSTRING_START = UProperty.STRING_LIMIT;
 
     public static String getXStringPropertyValue(int propertyEnum, int codepoint, int nameChoice) {
@@ -72,16 +59,6 @@ public static String getXStringPropertyValue(int propertyEnum, int codepoint, in
                 return Common.MyNormalize(codepoint, Normalizer.NFKC);
             case Common.TO_NFKD:
                 return Common.MyNormalize(codepoint, Normalizer.NFKD);
-            case Common.TO_CASEFOLD:
-                return UCharacter.foldCase(UTF16.valueOf(codepoint), true);
-            case Common.TO_LOWERCASE:
-                return UCharacter.toLowerCase(ULocale.ROOT, UTF16.valueOf(codepoint));
-            case Common.TO_UPPERCASE:
-                return UCharacter.toUpperCase(ULocale.ROOT, UTF16.valueOf(codepoint));
-            case Common.TO_TITLECASE:
-                return UCharacter.toTitleCase(ULocale.ROOT, UTF16.valueOf(codepoint), null);
-            case Common.SUBHEAD:
-                return UnicodeUtilities.getSubheader().getSubheader(codepoint);
         }
         return UCharacter.getStringPropertyValue(propertyEnum, codepoint, nameChoice);
     }
@@ -120,12 +97,7 @@ static String MyNormalize(String string, Mode mode) {
     static final int TO_NFD = UProperty.STRING_LIMIT + 1;
     static final int TO_NFKC = UProperty.STRING_LIMIT + 2;
     static final int TO_NFKD = UProperty.STRING_LIMIT + 3;
-    static final int TO_CASEFOLD = UProperty.STRING_LIMIT + 4;
-    static final int TO_LOWERCASE = UProperty.STRING_LIMIT + 5;
-    static final int TO_UPPERCASE = UProperty.STRING_LIMIT + 6;
-    static final int TO_TITLECASE = UProperty.STRING_LIMIT + 7;
-    public static final int SUBHEAD = TO_TITLECASE + 1;
-    static final int XSTRING_LIMIT = SUBHEAD + 1;
+    static final int XSTRING_LIMIT = TO_NFKD + 1;
     //    static UnicodeSet       isCaseFolded  = new UnicodeSet();
     //    static UnicodeSet       isLowercase   = new UnicodeSet();
     //    static UnicodeSet       isUppercase   = new UnicodeSet();