[jvm-packages] Fix POM for xgboost-jvm metapackage (#9893)

* [jvm-packages] Fix POM for xgboost-jvm metapackage

* Add script for updating the Scala version

dev/change_scala_version.py

@@ -0,0 +1,45 @@
+import argparse
+import pathlib
+import re
+import shutil
+
+try:
+    import sh
+except ImportError as e:
+    raise ImportError(
+        "Please install sh in your Python environment.\n"
+        " - Pip: pip install sh\n"
+        " - Conda: conda install -c conda-forge sh"
+    ) from e
+
+
+def main(args):
+    # Clean artifacts
+    for target in pathlib.Path("jvm-packages/").glob("**/target"):
+        if target.is_dir():
+            print(f"Removing {target}...")
+            shutil.rmtree(target)
+
+    # Update pom.xml
+    for pom in pathlib.Path("jvm-packages/").glob("**/pom.xml"):
+        print(f"Updating {pom}...")
+        sh.sed(
+            [
+                "-i",
+                f"s/<artifactId>xgboost-jvm_[0-9\\.]*/<artifactId>xgboost-jvm_{args.scala_version}/g",
+                str(pom),
+            ]
+        )
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--scala-version",
+        type=str,
+        required=True,
+        help="Version of Scala to use in the JVM packages",
+        choices=["2.12", "2.13"],
+    )
+    parsed_args = parser.parse_args()
+    main(parsed_args)

dev/prepare_jvm_release.py

@@ -2,7 +2,6 @@ import argparse
 import errno
 import glob
 import os
-import platform
 import re
 import shutil
 import subprocess
@@ -88,10 +87,6 @@ def main():
         help="Version of the release being prepared",
     )
     args = parser.parse_args()
-
-    if sys.platform != "darwin" or platform.machine() != "arm64":
-        raise NotImplementedError("Please run this script using an M1 Mac")
-
     version = args.release_version
     expected_git_tag = "v" + version
     current_git_tag = get_current_git_tag()
@@ -141,6 +136,7 @@ def main():
             ("linux", "x86_64"),
             ("windows", "x86_64"),
             ("macos", "x86_64"),
+            ("macos", "aarch64"),
         ]:
             output_dir = f"xgboost4j/src/main/resources/lib/{os_ident}/{arch}"
             maybe_makedirs(output_dir)
@@ -164,6 +160,10 @@ def main():
             url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_{commit_hash}.dylib",
             filename="xgboost4j/src/main/resources/lib/macos/x86_64/libxgboost4j.dylib",
         )
+        retrieve(
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_m1_{commit_hash}.dylib",
+            filename="xgboost4j/src/main/resources/lib/macos/aarch64/libxgboost4j.dylib",
+        )
 
         with tempfile.TemporaryDirectory() as tempdir:
             # libxgboost4j.so for Linux x86_64, CPU only
@@ -211,9 +211,14 @@ def main():
         "https://central.sonatype.org/publish/publish-maven/"
     )
     print(
-        "3. Now on a M1 Mac machine, run the following to build Scala 2.12 artifacts:"
+        "3. Now on a Linux machine, run the following to build Scala 2.12 artifacts. "
+        "Make sure to use an Internet connection with fast upload speed:"
+    )
+    print(
+        "   # Skip native build, since we have all needed native binaries from CI\n"
+        "   export MAVEN_SKIP_NATIVE_BUILD=1\n"
+        "   GPG_TTY=$(tty) mvn deploy -Prelease -DskipTests"
     )
-    print("   GPG_TTY=$(tty) mvn deploy -Prelease -DskipTests")
     print(
         "4. Log into https://oss.sonatype.org/. On the left menu panel, click Staging "
         "Repositories. Visit the URL https://oss.sonatype.org/content/repositories/mldmlc-xxxx "
@@ -221,11 +226,14 @@ def main():
         "artifacts to the Maven Central repository. The top-level metapackage should be "
         "named xgboost-jvm_2.12."
     )
-    print("5. Remove the Scala 2.12 artifacts and build Scala 2.13 artifacts:")
-    print("   rm -rf targets/")
-    print("   GPG_TTY=$(tty) mvn deploy -Prelease-cpu-only,scala-2.13 -DskipTests")
     print(
-        "6. Go to https://oss.sonatype.org/ to release the Scala 2.13 artifacts."
+        "5. Remove the Scala 2.12 artifacts and build Scala 2.13 artifacts:\n"
+        "   export MAVEN_SKIP_NATIVE_BUILD=1\n"
+        "   python dev/change_scala_version.py --scala-version 2.13\n"
+        "   GPG_TTY=$(tty) mvn deploy -Prelease-cpu-only,scala-2.13 -DskipTests"
+    )
+    print(
+        "6. Go to https://oss.sonatype.org/ to release the Scala 2.13 artifacts. "
         "The top-level metapackage should be named xgboost-jvm_2.13."
     )
 

jvm-packages/create_jni.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
-import errno
 import argparse
+import errno
 import glob
 import os
 import platform
@@ -19,11 +19,10 @@ CONFIG = {
     "USE_HDFS": "OFF",
     "USE_AZURE": "OFF",
     "USE_S3": "OFF",
-
     "USE_CUDA": "OFF",
     "USE_NCCL": "OFF",
     "JVM_BINDINGS": "ON",
-    "LOG_CAPI_INVOCATION": "OFF"
+    "LOG_CAPI_INVOCATION": "OFF",
 }
 
 
@@ -70,26 +69,22 @@ def normpath(path):
         return normalized
 
 
-if __name__ == "__main__":
+def native_build(args):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--log-capi-invocation', type=str, choices=['ON', 'OFF'], default='OFF')
-    parser.add_argument('--use-cuda', type=str, choices=['ON', 'OFF'], default='OFF')
-    cli_args = parser.parse_args()
-
     if sys.platform == "darwin":
         # Enable of your compiler supports OpenMP.
         CONFIG["USE_OPENMP"] = "OFF"
-        os.environ["JAVA_HOME"] = subprocess.check_output(
+        os.environ["JAVA_HOME"] = (
-            "/usr/libexec/java_home").strip().decode()
+            subprocess.check_output("/usr/libexec/java_home").strip().decode()
+        )
 
     print("building Java wrapper")
     with cd(".."):
-        build_dir = 'build-gpu' if cli_args.use_cuda == 'ON' else 'build'
+        build_dir = "build-gpu" if cli_args.use_cuda == "ON" else "build"
         maybe_makedirs(build_dir)
         with cd(build_dir):
             if sys.platform == "win32":
                 # Force x64 build on Windows.
-                maybe_generator = ' -A x64'
+                maybe_generator = " -A x64"
             else:
                 maybe_generator = ""
             if sys.platform == "linux":
@@ -97,12 +92,12 @@ if __name__ == "__main__":
             else:
                 maybe_parallel_build = ""
 
-            if cli_args.log_capi_invocation == 'ON':
+            if cli_args.log_capi_invocation == "ON":
-                CONFIG['LOG_CAPI_INVOCATION'] = 'ON'
+                CONFIG["LOG_CAPI_INVOCATION"] = "ON"
 
-            if cli_args.use_cuda == 'ON':
+            if cli_args.use_cuda == "ON":
-                CONFIG['USE_CUDA'] = 'ON'
+                CONFIG["USE_CUDA"] = "ON"
-                CONFIG['USE_NCCL'] = 'ON'
+                CONFIG["USE_NCCL"] = "ON"
 
             args = ["-D{0}:BOOL={1}".format(k, v) for k, v in CONFIG.items()]
 
@@ -115,7 +110,7 @@ if __name__ == "__main__":
             if gpu_arch_flag is not None:
                 args.append("%s" % gpu_arch_flag)
 
-            lib_dir = os.path.join(os.pardir, 'lib')
+            lib_dir = os.path.join(os.pardir, "lib")
             if os.path.exists(lib_dir):
                 shutil.rmtree(lib_dir)
             run("cmake .. " + " ".join(args) + maybe_generator)
@@ -125,8 +120,10 @@ if __name__ == "__main__":
             run(f'"{sys.executable}" mapfeat.py')
             run(f'"{sys.executable}" mknfold.py machine.txt 1')
 
-    xgboost4j = 'xgboost4j-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j'
+    xgboost4j = "xgboost4j-gpu" if cli_args.use_cuda == "ON" else "xgboost4j"
-    xgboost4j_spark = 'xgboost4j-spark-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j-spark'
+    xgboost4j_spark = (
+        "xgboost4j-spark-gpu" if cli_args.use_cuda == "ON" else "xgboost4j-spark"
+    )
 
     print("copying native library")
     library_name, os_folder = {
@@ -141,14 +138,19 @@ if __name__ == "__main__":
         "i86pc": "x86_64",  # on Solaris x86_64
         "sun4v": "sparc",  # on Solaris sparc
         "arm64": "aarch64",  # on macOS & Windows ARM 64-bit
-        "aarch64": "aarch64"
+        "aarch64": "aarch64",
     }[platform.machine().lower()]
-    output_folder = "{}/src/main/resources/lib/{}/{}".format(xgboost4j, os_folder, arch_folder)
+    output_folder = "{}/src/main/resources/lib/{}/{}".format(
+        xgboost4j, os_folder, arch_folder
+    )
     maybe_makedirs(output_folder)
     cp("../lib/" + library_name, output_folder)
 
     print("copying pure-Python tracker")
-    cp("../python-package/xgboost/tracker.py", "{}/src/main/resources".format(xgboost4j))
+    cp(
+        "../python-package/xgboost/tracker.py",
+        "{}/src/main/resources".format(xgboost4j),
+    )
 
     print("copying train/test files")
     maybe_makedirs("{}/src/test/resources".format(xgboost4j_spark))
@@ -164,3 +166,18 @@ if __name__ == "__main__":
     maybe_makedirs("{}/src/test/resources".format(xgboost4j))
     for file in glob.glob("../demo/data/agaricus.*"):
         cp(file, "{}/src/test/resources".format(xgboost4j))
+
+
+if __name__ == "__main__":
+    if "MAVEN_SKIP_NATIVE_BUILD" in os.environ:
+        print("MAVEN_SKIP_NATIVE_BUILD is set. Skipping native build...")
+    else:
+        parser = argparse.ArgumentParser()
+        parser.add_argument(
+            "--log-capi-invocation", type=str, choices=["ON", "OFF"], default="OFF"
+        )
+        parser.add_argument(
+            "--use-cuda", type=str, choices=["ON", "OFF"], default="OFF"
+        )
+        cli_args = parser.parse_args()
+        native_build(cli_args)

jvm-packages/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
 
     <groupId>ml.dmlc</groupId>
-    <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+    <artifactId>xgboost-jvm_2.12</artifactId>
     <version>2.0.2</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>

jvm-packages/xgboost4j-example/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
     <name>xgboost4j-example</name>

jvm-packages/xgboost4j-flink/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
 

jvm-packages/xgboost4j-gpu/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
     <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>

jvm-packages/xgboost4j-spark-gpu/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
     <name>xgboost4j-spark-gpu</name>

jvm-packages/xgboost4j-spark/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
     <name>xgboost4j-spark</name>

jvm-packages/xgboost4j/pom.xml

@@ -5,7 +5,7 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
+        <artifactId>xgboost-jvm_2.12</artifactId>
         <version>2.0.2</version>
     </parent>
     <name>xgboost4j</name>