From 5fb2a6ad06f5fbf621eb04b04687b9cf0f4986c0 Mon Sep 17 00:00:00 2001 From: Mihai Nita Date: Fri, 1 Sep 2023 01:47:32 -0700 Subject: [PATCH] ICU-22324 Mavenization, updating the cldr-to-icu scripts and instructions --- CONTRIBUTING.md | 2 +- docs/processes/cldr-icu.md | 72 ++++++++-------- docs/processes/release/tasks/integration.md | 2 +- docs/processes/release/tasks/miscellaneous.md | 2 +- .../release/tasks/updating-measure-unit.md | 4 +- docs/processes/release/tasks/versions.md | 4 +- docs/userguide/dev/rules_update.md | 16 ++-- docs/userguide/format_parse/messages/mf2.md | 4 +- icu4c/source/data/icu4j-readme.txt | 10 +-- icu4c/source/data/makedata.mak | 2 +- icu4c/source/test/cintltst/ccaltst.c | 2 +- icu4c/source/test/cintltst/ulocbuildertst.c | 2 +- .../test/intltest/localebuildertest.cpp | 2 +- .../test/intltest/numbertest_permutation.cpp | 2 +- icu4c/source/test/testdata/Makefile.in | 2 +- .../test/testdata/break_rules/README.md | 2 +- icu4c/source/test/testdata/rbbitst.txt | 2 +- icu4j/extract-data-files.sh | 84 +++++++++++++++++++ .../java/com/ibm/icu/text/CollationKey.java | 2 +- .../java/com/ibm/icu/lang/UCharacter.java | 2 +- .../ibm/icu/message2/MessageFormatter.java | 2 +- .../icu/dev/test/rbbi/break_rules/readme.txt | 2 +- .../com/ibm/icu/dev/test/rbbi/rbbitst.txt | 2 +- tools/cldr/build.xml | 2 +- tools/cldr/cldr-to-icu/build-icu-data.xml | 2 +- .../tool/cldrtoicu/ant/GenerateCodeTask.java | 2 +- 26 files changed, 156 insertions(+), 76 deletions(-) create mode 100755 icu4j/extract-data-files.sh diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index a0d6c489fe9..90af30f8a84 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -105,7 +105,7 @@ The project is released under [LICENSE](./LICENSE). [bugs]: https://icu.unicode.org/bugs [cintltst]: ./icu4c/source/test/cintltst/ [coding-guidelines]: docs/userguide/dev/codingguidelines.md -[com.ibm.icu.dev.test]: ./icu4j/main/tests/framework/src/com/ibm/icu/dev/test/ +[com.ibm.icu.dev.test]: ./icu4j/main/framework/src/test/java/com/ibm/icu/dev/test/ [contacts]: https://icu.unicode.org/contacts [copyright]: http://www.unicode.org/copyright.html [design]: docs/userguide/icu/design.md diff --git a/docs/processes/cldr-icu.md b/docs/processes/cldr-icu.md index 6bd5fefd557..8202280d633 100644 --- a/docs/processes/cldr-icu.md +++ b/docs/processes/cldr-icu.md @@ -87,7 +87,7 @@ considerations: There are several environment variables that need to be defined. -1. Java- and ant-related variables +1. Java-, ant-, and maven-related variables * `JAVA_HOME`: Path to JDK (a directory, containing e.g. `bin/java`, `bin/javac`, etc.); on many systems this can be set using the output of `/usr/libexec/java_home`. @@ -95,6 +95,9 @@ There are several environment variables that need to be defined. * `ANT_OPTS`: You may want to set `-Xmx8192m` to give Java more memory; otherwise it may run out of heap. + * `MAVEN_ARGS`: You may want to set `--no-transfer-progress` to reduce the noise + from the download progress. + 2. CLDR-related variables * `CLDR_DIR`: This is the path to the to root of standard CLDR sources, below @@ -123,10 +126,11 @@ There are several environment variables that need to be defined. ## 1 Environment variables -1a. Java and ant variables, adjust for your system +1a. Java, ant, and maven variables, adjust for your system ``` -export JAVA_HOME=`/usr/libexec/java_home` +export JAVA_HOME=/usr/libexec/java_home export ANT_OPTS="-Xmx8192m" +export MAVEN_ARGS="--no-transfer-progress" ``` 1b. CLDR variables, adjust for your setup; with cygwin it might be e.g. @@ -154,6 +158,11 @@ export NOTES=...(some directory)... mkdir -p $NOTES ``` +1e. The name of the icu data directory for Java (for example `icudt74b`) +``` +export ICU_DATA_VER=icudt(version)b +``` + ## 2 Initial builds of ICU4C and ICU4J 2a. Configure ICU4C, build and test without new data first, to verify that @@ -173,16 +182,8 @@ there are no pre-existing errors (or at least to have the pre-existing errors as a base for comparison): ``` cd $ICU4J_ROOT -ant clean -ant check 2>&1 | tee $NOTES/icu4j-oldData-antCheck.txt -``` - -2c. Additionally for ICU4J, repeat the same as 2b, but for building with -Maven instead of with Ant. -``` -cd $ICU4J_ROOT/maven-build mvn clean -mvn verify 2>&1 | tee $NOTES/icu4j-oldData-mvnVerify.txt +mvn verify 2>&1 | tee $NOTES/icu4j-oldData-mvnCheck.txt ``` ## 3 Make pre-adjustments @@ -272,9 +273,9 @@ ant copy-cldr-testdata 5d. Copy localeCanonicalization.txt from CLDR testData and add a source reference line: ``` cp -p $CLDR_DIR/common/testData/localeIdentifiers/localeCanonicalization.txt $ICU4C_DIR/source/test/testdata/ -cp -p $CLDR_DIR/common/testData/localeIdentifiers/localeCanonicalization.txt $ICU4J_ROOT/main/tests/core/src/com/ibm/icu/dev/data/unicode/ +cp -p $CLDR_DIR/common/testData/localeIdentifiers/localeCanonicalization.txt $ICU4J_ROOT/main/core/src/test/resources/com/ibm/icu/dev/data/unicode/ open $ICU4C_DIR/source/test/testdata/localeCanonicalization.txt -open $ICU4J_ROOT/main/tests/core/src/com/ibm/icu/dev/data/unicode/localeCanonicalization.txt +open $ICU4J_ROOT/main/core/src/test/resources/com/ibm/icu/dev/data/unicode/localeCanonicalization.txt ``` At the beginning of each file add the following line:\ ``` @@ -283,7 +284,7 @@ At the beginning of each file add the following line:\ 5e. For now, manually re-add the `lstm` entries in `data/brkitr/root.txt` ``` -open $ICU4C_DIR/source/data/brkitr/root.txt +open $ICU4C_DIR/source/data/brkitr/root.txt ``` Paste the following block after the dictionaries block and before the final closing '}': ``` @@ -340,7 +341,7 @@ cd test/intltest DYLD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$DYLD_LIBRARY_PATH ./intltest -e -G format/NumberTest/NumberPermutationTest cd ../.. -cd build/test/cintltst +cd test/cintltst DYLD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$DYLD_LIBRARY_PATH ./cintltst /tsformat/ccaltst cd ../../.. ``` @@ -411,22 +412,28 @@ make icu4j-data-install 12d. Update the extracted {main, test} data files in the Maven build ``` -cd $ICU4J_ROOT/maven-build -sh ./extract-data-files.sh +cd $ICU4J_ROOT +./extract-data-files.sh ``` ## 13 Rebuild ICU4J with new data, run tests -13a. Run the tests using the ant build +13a. Run the tests using the maven build ``` cd $ICU4J_ROOT -ant clean -ant check 2>&1 | tee $NOTES/icu4j-newData-antCheck.txt +mvn clean +mvn verify 2>&1 | tee $NOTES/icu4j-newData-mvnCheck.txt ``` -To re-run a specific test if necessary when fixing bugs; for example: +It is possible to re-run a specific test class or method if necessary when fixing bugs. + +For example (using artifactId, full class name, test all methods): ``` -ant checkTest -Dtestclass='com.ibm.icu.dev.test.format.MeasureUnitTest' +mvn test -pl :core -Dtest=com.ibm.icu.dev.test.util.LocaleBuilderTest +``` +or (example of using module path, class name, one method): +``` +mvn test -pl main/common_tests -Dtest=MeasureUnitTest#TestGreek ``` 13b. Optionally run the tests in exhautive mode @@ -435,22 +442,15 @@ Optionally run before committing changes, or run to diagnose failures from running exhastive CI tests in the PR using `/azp run CI-Exhaustive`: ``` cd $ICU4J_ROOT -ant exhaustiveCheck 2>&1 | tee $NOTES/icu4j-newData-antCheckEx.txt +mvn verify -DICU.exhaustive=10 2>&1 | tee $NOTES/icu4j-newData-mvnCheckEx.txt ``` -(Not sure there is a way to re-run a specific test in exhaustive mode) -13c. Run the tests using the Maven build +Running a specific test is the same as above: ``` -cd $ICU4J_ROOT/maven-build -mvn verify 2>&1 | tee $NOTES/icu4j-newData-mavenVerify.txt +mvn test --pl :core -DICU.exhaustive=10 -Dtest=ExhaustiveNumberTest ``` -Currently (due to maven sync issues?) there may be errors in these -local maven tests even if there are no errors in the ant check tests. -Such maven errors should not be blockers for a commit and push; they -may not show up in the CI maven tests (but if they do and do not go -away after re-running the CI test, then they need investigation). -## 14 Investigate and fix ant check test failures +## 14 Investigate and fix maven check test failures Fix test cases and repeat from step 13, or fix CLDR data and repeat from step 4, as appropriate, until there are no more failures in ICU4C or ICU4J. @@ -477,7 +477,7 @@ com.ibm.icu.dev.test.format.PluralRulesTest (TestLocales) To address these requires updating the LOCALE_SNAPSHOT data in ``` -$ICU4J_ROOT/main/tests/core/src/com/ibm/icu/dev/test/format/PluralRulesTest.java +$ICU4J_ROOT/main/common_tests/src/test/java/com/ibm/icu/dev/test/format/PluralRulesTest.java ``` by modifying the TestLocales() test there to run `generateLOCALE_SNAPSHOT()` and then copying in the updated data. @@ -488,7 +488,7 @@ then copying in the updated data. cd $ICU4C_DIR/source make clean cd $ICU4J_ROOT -ant clean +mvn clean cd .. git status ``` diff --git a/docs/processes/release/tasks/integration.md b/docs/processes/release/tasks/integration.md index 275ecb718cb..892deb894cf 100644 --- a/docs/processes/release/tasks/integration.md +++ b/docs/processes/release/tasks/integration.md @@ -472,7 +472,7 @@ usually done just before publishing release candidate. 3. Run - `ant serialTestData` 4. Copy a folder with ICU version (e.g. ICU_61.1) generated under /out/serialTestData to /main/tests/core/src/com/ibm/icu/dev/test/serializable/data. + root>/main/core/src/test/resources/com/ibm/icu/dev/test/serializable/data. 5. Delete the oldest serialization test data after ICU 3.6 (do not delete ICU_3.6) from the directory. the oldest one - ICU_3.6). 6. Run `ant check` again before committing the changes. diff --git a/docs/processes/release/tasks/miscellaneous.md b/docs/processes/release/tasks/miscellaneous.md index 0b0073171ed..e524964af27 100644 --- a/docs/processes/release/tasks/miscellaneous.md +++ b/docs/processes/release/tasks/miscellaneous.md @@ -39,7 +39,7 @@ and use it for future testing. 2. The target generates test data and runs some serialization test cases. 3. Once you confirm the test runs clean, copy `out/serialTestData/ICU_` to - `main/tests/core/src/com/ibm/icu/dev/test/serializable/data/ICU_`. + `main/core/src/test/resources/com/ibm/icu/dev/test/serializable/data/ICU_`. --- diff --git a/docs/processes/release/tasks/updating-measure-unit.md b/docs/processes/release/tasks/updating-measure-unit.md index a3a52d53a9c..f5d9219cf95 100644 --- a/docs/processes/release/tasks/updating-measure-unit.md +++ b/docs/processes/release/tasks/updating-measure-unit.md @@ -44,7 +44,7 @@ After syncing CLDR data with ICU do the following. This documentation assumes that you are updating the MeasureUnit clases for ICU 68. * Check out - $GIT_ROOT/icu4j/main/tests/core/src/com/ibm/icu/dev/test/format/MeasureUnitTest.java + $GIT_ROOT/icu4j/main/common_tests/src/test/java/com/ibm/icu/dev/test/format/MeasureUnitTest.java * Open MeasureUnitTest.java. * Find the `testZZZ` test, its code should all be commented out. This test will execute last and will run the desired code. @@ -57,7 +57,7 @@ that you are updating the MeasureUnit clases for ICU 68. * Change `testZZZ` to run `generateConstants(“68”); // ICU 68.` * Run MeasureUnitTest.java, copy the generated code (see instructions above). * Open MeasureUnit.java: - $GIT_ROOT/icu4j/main/classes/core/src/com/ibm/icu/util/MeasureUnit.java + $GIT_ROOT/icu4j/main/core/src/main/java/com/ibm/icu/util/MeasureUnit.java * Look for line containing: `// Start generated MeasureUnit constants` diff --git a/docs/processes/release/tasks/versions.md b/docs/processes/release/tasks/versions.md index 48913c70261..920cbd4f83e 100644 --- a/docs/processes/release/tasks/versions.md +++ b/docs/processes/release/tasks/versions.md @@ -146,7 +146,7 @@ For updating ICU version numbers, follow the steps below. number such as "60.1" for official releases, "61.1-SNAPSHOT" until 61.1 release, after 60.1. -3. [icu4j/main/classes/core/src/com/ibm/icu/util/VersionInfo.java](https://github.com/unicode-org/icu/blob/main/icu4j/main/classes/core/src/com/ibm/icu/util/VersionInfo.java) +3. [icu4j/main/core/src/main/java/com/ibm/icu/util/VersionInfo.java](https://github.com/unicode-org/icu/blob/main/icu4j/main/core/src/main/java/com/ibm/icu/util/VersionInfo.java) There is a static block starting at line 501 (as of 54.1) in the source file - @@ -270,7 +270,7 @@ For updating ICU version numbers, follow the steps below. example, see [tags/release-4-4-2-eclipse37-20110208/eclipse-build/build.properties](http://source.icu-project.org/repos/icu/tags/icu4j/release-4-4-2-eclipse37-20110208/eclipse-build/build.properties). -7. [DebugUtilitiesData.java](https://github.com/unicode-org/icu/blob/main/icu4j/main/tests/core/src/com/ibm/icu/dev/test/util/DebugUtilities.java) +7. [DebugUtilitiesData.java](https://github.com/unicode-org/icu/blob/main/icu4j/main/core/src/test/java/com/ibm/icu/dev/test/util/DebugUtilities.java) This file is automatically generated when data is generated for ICU4J. The ICU4C version number string should be check to ensure that the correct diff --git a/docs/userguide/dev/rules_update.md b/docs/userguide/dev/rules_update.md index 3a27420a719..57d3fd96d45 100644 --- a/docs/userguide/dev/rules_update.md +++ b/docs/userguide/dev/rules_update.md @@ -50,9 +50,9 @@ Often ICU will implement draft versions of proposed specification updates, to ch ||| | icu/icu4j/... | .../main/shared/data/icudata.jar | Data jar, includes break rules. Derived from ICU4C. -| .../main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt | Test data, copied from ICU4C. -| .../main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/* | Monkey test rules, copied from ICU4C. -| .../main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java | Monkey test w rules as code. Port from ICU4C. +| .../main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt | Test data, copied from ICU4C. +| .../main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/* | Monkey test rules, copied from ICU4C. +| .../main/core/src/test/java/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java | Monkey test w rules as code. Port from ICU4C. ## ICU4C @@ -90,7 +90,7 @@ The rule updates are done first for ICU4C, and then ported (code changes) or mov probably means that some earlier change to ICU4C was not fully ported to ICU4J, and this needs to be resolved before proceeding. - diff icu4c/source/test/testdata/rbbitst.txt icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt + diff icu4c/source/test/testdata/rbbitst.txt icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt Should show no difference. @@ -250,7 +250,7 @@ The rule updates are done first for ICU4C, and then ported (code changes) or mov Copy the file `rbbitst.txt` from ICU4C to ICU4J, and run the Java test. It should fail until the rules are updated. cd - cp icu4c/source/test/testdata/rbbitst.txt icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt + cp icu4c/source/test/testdata/rbbitst.txt icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt Run the test from Eclipse. @@ -272,7 +272,7 @@ The rule updates are done first for ICU4C, and then ported (code changes) or mov ICU4C file to port from: `source/test/intltest/rbbitst.cpp` - ICU4J file to port to: `main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java` + ICU4J file to port to: `main/core/src/test/java/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java` To conveniently run the individual tests, look for the test functions `TestCharMonkey()`, `TestWordMonkey()`, etc. in `RBBITestMonkey.java`. @@ -288,9 +288,9 @@ The rule updates are done first for ICU4C, and then ported (code changes) or mov ICU4C directory, to copy from: `source/test/testdata/break_rules/` - ICU4J directory, to copy to: `main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/` + ICU4J directory, to copy to: `main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/` - Then rerun the rule based monkey test, in the file `main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBIMonkeyTest.java`. Find the test function `TestMonkey()`; it include comments describing how to run it with parameters from Eclipse. + Then rerun the rule based monkey test, in the file `main/core/src/test/java/com/ibm/icu/dev/test/rbbi/RBBIMonkeyTest.java`. Find the test function `TestMonkey()`; it include comments describing how to run it with parameters from Eclipse. Run the test(s) for the changed rules for an extended amount of time (with Dloop=-1). diff --git a/docs/userguide/format_parse/messages/mf2.md b/docs/userguide/format_parse/messages/mf2.md index eb8bf584b65..31895219dcd 100644 --- a/docs/userguide/format_parse/messages/mf2.md +++ b/docs/userguide/format_parse/messages/mf2.md @@ -131,7 +131,7 @@ plural selectors (`plural` and `selectordinal`), and general selector (`select`), very similar to what MessageFormat offers. -The [ICU test code](https://github.com/unicode-org/icu/tree/main/icu4j/main/tests/core/src/com/ibm/icu/dev/test/message2) +The [ICU test code](https://github.com/unicode-org/icu/tree/main/icu4j/main/core/src/test/java/com/ibm/icu/dev/test/message2) covers most features, and has examples of how to make custom placeholder formatters; you can look for classes that implement `com.ibm.icu.message2.FormatterFactory` (they are named `Custom*Test.java`). @@ -272,7 +272,7 @@ You can experiment with more messages using as inspiration: - the [syntax document](https://github.com/unicode-org/message-format-wg/blob/main/spec/syntax.md) - the official [ICU4J javadoc](https://unicode-org.github.io/icu-docs/apidoc/released/icu4j//index.html?com/ibm/icu/message2/) -- the [ICU4J unit tests](https://github.com/unicode-org/icu/tree/main/icu4j/main/tests/core/src/com/ibm/icu/dev/test/message2) +- the [ICU4J unit tests](https://github.com/unicode-org/icu/tree/main/icu4j/main/core/src/test/java/com/ibm/icu/dev/test/message2) You should be able to use your preferred IDE (Eclipse, IntelliJ, Visual Studio Code, more), use a different build system, etc. diff --git a/icu4c/source/data/icu4j-readme.txt b/icu4c/source/data/icu4j-readme.txt index 8d087c16c7c..2bc699e13c6 100644 --- a/icu4c/source/data/icu4j-readme.txt +++ b/icu4c/source/data/icu4j-readme.txt @@ -71,12 +71,8 @@ icutzdata.jar in $icu4j_root/main/shared/data. *Java* -3. After the ICU4C-side steps above, build the main target of the - ICU4J ant build to unpack the jar files with the following commands: +3. After the ICU4C-side steps above, build the ICU4J artifacts and run + the tests locally to make sure they pass: cd $icu4j_root - ant main - - Run the tests locally and make sure they pass: - - ant check + mvn verify diff --git a/icu4c/source/data/makedata.mak b/icu4c/source/data/makedata.mak index 579e23fcea2..08fb53954a5 100644 --- a/icu4c/source/data/makedata.mak +++ b/icu4c/source/data/makedata.mak @@ -362,7 +362,7 @@ generate-data: GODATA "$(ICUOUT)\$(ICUPKG).dat" uni-core-data ## Compare to: source\data\Makefile.in and source\test\testdata\Makefile.in -DEBUGUTILITIESDATA_DIR=main\tests\core\src\com\ibm\icu\dev\test\util +DEBUGUTILITIESDATA_DIR=main\core\src\test\java\com\ibm\icu\dev\test\util DEBUGUTILITIESDATA_SRC=DebugUtilitiesData.java # Build DebugUtilitiesData.java diff --git a/icu4c/source/test/cintltst/ccaltst.c b/icu4c/source/test/cintltst/ccaltst.c index 0cf10822f91..0744ba14abf 100644 --- a/icu4c/source/test/cintltst/ccaltst.c +++ b/icu4c/source/test/cintltst/ccaltst.c @@ -1728,7 +1728,7 @@ static void TestGetKeywordValuesForLocale() { /* * Weekend tests, ported from - * icu4j/trunk/main/tests/core/src/com/ibm/icu/dev/test/calendar/IBMCalendarTest.java + * icu4j/main/core/src/test/java/com/ibm/icu/dev/test/calendar/IBMCalendarTest.java * and extended a bit. Notes below from IBMCalendarTest.java ... * This test tests for specific locale data. This is probably okay * as far as US data is concerned, but if the Arabic/Yemen data diff --git a/icu4c/source/test/cintltst/ulocbuildertst.c b/icu4c/source/test/cintltst/ulocbuildertst.c index 1fb9017f22d..25e56b3af64 100644 --- a/icu4c/source/test/cintltst/ulocbuildertst.c +++ b/icu4c/source/test/cintltst/ulocbuildertst.c @@ -38,7 +38,7 @@ static void Verify(ULocaleBuilder* bld, const char* expected, const char* msg) { static void TestLocaleBuilder() { // The following test data are copy from - // icu4j/main/tests/core/src/com/ibm/icu/dev/test/util/LocaleBuilderTest.java + // icu4j/main/core/src/test/java/com/ibm/icu/dev/test/util/LocaleBuilderTest.java // "L": +1 = language // "S": +1 = script // "R": +1 = region diff --git a/icu4c/source/test/intltest/localebuildertest.cpp b/icu4c/source/test/intltest/localebuildertest.cpp index 5623dd1e37c..fa706db728f 100644 --- a/icu4c/source/test/intltest/localebuildertest.cpp +++ b/icu4c/source/test/intltest/localebuildertest.cpp @@ -83,7 +83,7 @@ void LocaleBuilderTest::Verify(LocaleBuilder& bld, const char* expected, const c void LocaleBuilderTest::TestLocaleBuilder() { // The following test data are copy from - // icu4j/main/tests/core/src/com/ibm/icu/dev/test/util/LocaleBuilderTest.java + // icu4j/main/core/src/test/java/com/ibm/icu/dev/test/util/LocaleBuilderTest.java // "L": +1 = language // "S": +1 = script // "R": +1 = region diff --git a/icu4c/source/test/intltest/numbertest_permutation.cpp b/icu4c/source/test/intltest/numbertest_permutation.cpp index 77135e5e497..587e79c4242 100644 --- a/icu4c/source/test/intltest/numbertest_permutation.cpp +++ b/icu4c/source/test/intltest/numbertest_permutation.cpp @@ -75,7 +75,7 @@ static const double kNumbersToTest[]{0, 91827.3645, -0.22222}; * On Linux, from icu4c/source: * make -j -l2.5 tests && (cd test/intltest && LD_LIBRARY_PATH=../../lib:../../tools/ctestfw ./intltest -e -G format/NumberTest/NumberPermutationTest) * After re-generating the file, copy it into icu4j: - * cp test/testdata/numberpermutationtest.txt ../../icu4j/main/tests/core/src/com/ibm/icu/dev/data/numberpermutationtest.txt + * cp test/testdata/numberpermutationtest.txt ../../icu4j/main/core/src/test/resources/com/ibm/icu/dev/data/numberpermutationtest.txt */ void NumberPermutationTest::testPermutations() { IcuTestErrorCode status(*this, "testPermutations"); diff --git a/icu4c/source/test/testdata/Makefile.in b/icu4c/source/test/testdata/Makefile.in index 21dcfcbd2df..f94b7e42283 100644 --- a/icu4c/source/test/testdata/Makefile.in +++ b/icu4c/source/test/testdata/Makefile.in @@ -167,7 +167,7 @@ $(OUTDIR)/icu4j/testdata.jar: build-dir testdata $(TESTOUTDIR)/testdata.dat $(JAR) cf $(OUTDIR)/icu4j/testdata.jar -C $(OUTDIR)/icu4j com/ibm/icu/dev/data/testdata -DEBUGUTILITIESDATA_DIR=main/tests/core/src/com/ibm/icu/dev/test/util +DEBUGUTILITIESDATA_DIR=main/core/src/test/java/com/ibm/icu/dev/test/util DEBUGUTILITIESDATA_SRC=DebugUtilitiesData.java ICU4J_DATA=$(OUTDIR)/icu4j/src/$(DEBUGUTILITIESDATA_SRC) $(OUTDIR)/icu4j/testdata.jar diff --git a/icu4c/source/test/testdata/break_rules/README.md b/icu4c/source/test/testdata/break_rules/README.md index 1deb4dfc32f..7468a1cb147 100644 --- a/icu4c/source/test/testdata/break_rules/README.md +++ b/icu4c/source/test/testdata/break_rules/README.md @@ -12,7 +12,7 @@ The rules in this directory track the boundary rules from Unicode UAX 14 and 29. to provide an expected set of boundary positions to compare with the results from ICU break iteration. ICU4J also includes copies of the test reference rules, located in the directory -main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/ +main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/ The copies should be kept synchronized; there should be no differences. Each set of reference break rules lives in a separate file. diff --git a/icu4c/source/test/testdata/rbbitst.txt b/icu4c/source/test/testdata/rbbitst.txt index 772acf24363..274b4051d24 100644 --- a/icu4c/source/test/testdata/rbbitst.txt +++ b/icu4c/source/test/testdata/rbbitst.txt @@ -30,7 +30,7 @@ # # There are two copies of this file in the source repository, # [ICU4C] source/test/testdata/rbbitst.txt -# [ICU4J] main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt +# [ICU4J] main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt # # ICU4C's copy is the primary one. If any changes are made to ICU4J's copy, make sure they # are merged back into ICU4C's copy of the file, lest they get overwritten later. diff --git a/icu4j/extract-data-files.sh b/icu4j/extract-data-files.sh new file mode 100755 index 00000000000..01e491249dc --- /dev/null +++ b/icu4j/extract-data-files.sh @@ -0,0 +1,84 @@ +#!/usr/bin/env bash +# Copyright (C) 2023 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html + +if [ -z "$ICU_DATA_VER" ]; then + echo "ICU_DATA_VER must be set to the icu folder name (for example icudt74b)" + exit +fi + +# Check that all the .jar files are present +JAR_FILE=main/shared/data/icudata.jar +if [ ! -f "$JAR_FILE" ]; then + echo "Missing $JAR_FILE" + exit +fi +JAR_FILE=main/shared/data/icutzdata.jar +if [ ! -f "$JAR_FILE" ]; then + echo "Missing $JAR_FILE" + exit +fi +JAR_FILE=main/shared/data/testdata.jar +if [ ! -f "$JAR_FILE" ]; then + echo "Missing $JAR_FILE" + exit +fi + +# Unpack the pre-built .jar files with data only + +echo "Unpacking icudata.jar" +rm -fr main/core/src/main/resources/com/ibm/icu/impl/data/icudt* +unzip -q -d main/core/src/main/resources/ main/shared/data/icudata.jar +rm -fr main/core/src/main/resources/META-INF + +echo " Moving charset data" +rm -fr main/charset/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/charset/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/*.cnv main/charset/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/cnvalias.icu main/charset/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ + +echo " Moving currency data" +rm -fr main/currdata/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/currdata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/curr main/currdata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/curr + +echo " Moving collate data" +rm -fr main/collate/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/collate/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/coll main/collate/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/coll + +echo " Moving langdata data" +rm -fr main/langdata/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/langdata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/lang main/langdata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/lang + +echo " Moving regiondata data" +rm -fr main/regiondata/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/regiondata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/region main/regiondata/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/region + +echo " Moving translit data" +rm -fr main/translit/src/main/resources/com/ibm/icu/impl/data/icudt* +mkdir -p main/translit/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/ +mv main/core/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/translit main/translit/src/main/resources/com/ibm/icu/impl/data/${ICU_DATA_VER}/translit + +echo "Unpacking icutzdata.jar" +# This unzips together with other existing core files +# So we don't remove the folder +unzip -q -d main/core/src/main/resources/ main/shared/data/icutzdata.jar +rm -fr main/core/src/main/resources/META-INF + +echo "Unpacking testdata.jar" +rm -fr main/core/src/test/resources/com/ibm/icu/dev/data/testdata/ +unzip -q -d main/core/src/test/resources/ main/shared/data/testdata.jar +rm -fr main/core/src/test/resources/META-INF + +echo "Removing jar files" +echo " icudata.jar" +rm main/shared/data/icudata.jar +echo " icutzdata.jar" +rm main/shared/data/icutzdata.jar +echo " testdata.jar" +rm main/shared/data/testdata.jar + +echo DONE diff --git a/icu4j/main/collate/src/main/java/com/ibm/icu/text/CollationKey.java b/icu4j/main/collate/src/main/java/com/ibm/icu/text/CollationKey.java index 0e848753810..fab084f7c39 100644 --- a/icu4j/main/collate/src/main/java/com/ibm/icu/text/CollationKey.java +++ b/icu4j/main/collate/src/main/java/com/ibm/icu/text/CollationKey.java @@ -383,7 +383,7 @@ public final class CollationKey implements Comparable * also match "Smithsonian" and similar. *

* For more on usage, see example in test procedure - * + * * src/com/ibm/icu/dev/test/collator/CollationAPITest/TestBounds. * *

diff --git a/icu4j/main/core/src/main/java/com/ibm/icu/lang/UCharacter.java b/icu4j/main/core/src/main/java/com/ibm/icu/lang/UCharacter.java index 0d8bab0e9db..3b5bff8dea3 100644 --- a/icu4j/main/core/src/main/java/com/ibm/icu/lang/UCharacter.java +++ b/icu4j/main/core/src/main/java/com/ibm/icu/lang/UCharacter.java @@ -86,7 +86,7 @@ import com.ibm.icu.util.VersionInfo; *

* Further detail on differences can be determined using the program * + * "https://github.com/unicode-org/icu/blob/main/icu4j/main/core/src/test/java/com/ibm/icu/dev/test/lang/UCharacterCompare.java"> * com.ibm.icu.dev.test.lang.UCharacterCompare *

* In addition to Java compatibility functions, which calculate derived properties, diff --git a/icu4j/main/core/src/main/java/com/ibm/icu/message2/MessageFormatter.java b/icu4j/main/core/src/main/java/com/ibm/icu/message2/MessageFormatter.java index 4ece47b0f4b..63fff2df33c 100644 --- a/icu4j/main/core/src/main/java/com/ibm/icu/message2/MessageFormatter.java +++ b/icu4j/main/core/src/main/java/com/ibm/icu/message2/MessageFormatter.java @@ -127,7 +127,7 @@ import java.util.Map; * and general selector ({@code select}), * very similar to what MessageFormat offers.

* - *

The ICU test code + *

The ICU test code * covers most features, and has examples of how to make custom placeholder formatters; * you can look for classes that implement {@code com.ibm.icu.message2.FormatterFactory} * (they are named {@code Custom*Test.java}).

diff --git a/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt b/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt index 34b1b27c594..a785aa8a47e 100644 --- a/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt +++ b/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt @@ -1,4 +1,4 @@ -file: main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt +file: main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/break_rules/readme.txt Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html diff --git a/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt b/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt index 772acf24363..274b4051d24 100644 --- a/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt +++ b/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt @@ -30,7 +30,7 @@ # # There are two copies of this file in the source repository, # [ICU4C] source/test/testdata/rbbitst.txt -# [ICU4J] main/tests/core/src/com/ibm/icu/dev/test/rbbi/rbbitst.txt +# [ICU4J] main/core/src/test/resources/com/ibm/icu/dev/test/rbbi/rbbitst.txt # # ICU4C's copy is the primary one. If any changes are made to ICU4J's copy, make sure they # are merged back into ICU4C's copy of the file, lest they get overwritten later. diff --git a/tools/cldr/build.xml b/tools/cldr/build.xml index c1b6c3f22b3..8f58dc9f834 100644 --- a/tools/cldr/build.xml +++ b/tools/cldr/build.xml @@ -31,7 +31,7 @@ - + - + diff --git a/tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/ant/GenerateCodeTask.java b/tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/ant/GenerateCodeTask.java index 058258e733e..9ab24778af9 100644 --- a/tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/ant/GenerateCodeTask.java +++ b/tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/ant/GenerateCodeTask.java @@ -37,7 +37,7 @@ public final class GenerateCodeTask extends Task { } private GeneratedFileDef[] generatedFileDefs = { - new GeneratedFileDef("common/localefallback_data.h", "src/com/ibm/icu/impl/LocaleFallbackData.java", new ResourceFallbackCodeGenerator()), + new GeneratedFileDef("common/localefallback_data.h", "src/main/java/com/ibm/icu/impl/LocaleFallbackData.java", new ResourceFallbackCodeGenerator()), }; @SuppressWarnings("unused")