[jvm-packages] Add Scala version suffix to xgboost-jvm package (#9776)

* Update JVM script (#9714)

* Bump version to 2.0.2; revamp pom.xml

* Update instructions in prepare_jvm_release.py

* Fix formatting

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.18 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 2.0.1)
+project(xgboost LANGUAGES CXX C VERSION 2.0.2)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

R-package/DESCRIPTION

@@ -1,7 +1,7 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 2.0.1.1
+Version: 2.0.2.1
 Date: 2023-10-12
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for xgboost 2.0.1.
+# Generated by GNU Autoconf 2.71 for xgboost 2.0.2.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -607,8 +607,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='2.0.1'
+PACKAGE_VERSION='2.0.2'
-PACKAGE_STRING='xgboost 2.0.1'
+PACKAGE_STRING='xgboost 2.0.2'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1225,7 +1225,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures xgboost 2.0.1 to adapt to many kinds of systems.
+\`configure' configures xgboost 2.0.2 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1287,7 +1287,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 2.0.1:";;
+     short | recursive ) echo "Configuration of xgboost 2.0.2:";;
    esac
   cat <<\_ACEOF
 
@@ -1367,7 +1367,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 2.0.1
+xgboost configure 2.0.2
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1533,7 +1533,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by xgboost $as_me 2.0.1, which was
+It was created by xgboost $as_me 2.0.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3412,7 +3412,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by xgboost $as_me 2.0.1, which was
+This file was extended by xgboost $as_me 2.0.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3467,7 +3467,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-xgboost config.status 2.0.1
+xgboost config.status 2.0.2
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[2.0.1],[],[xgboost],[])
+AC_INIT([xgboost],[2.0.2],[],[xgboost],[])
 
 : ${R_HOME=`R RHOME`}
 if test -z "${R_HOME}"; then

dev/prepare_jvm_release.py

@@ -21,12 +21,14 @@ def normpath(path):
     else:
         return normalized
 
+
 def cp(source, target):
     source = normpath(source)
     target = normpath(target)
     print("cp {0} {1}".format(source, target))
     shutil.copy(source, target)
 
+
 def maybe_makedirs(path):
     path = normpath(path)
     print("mkdir -p " + path)
@@ -36,6 +38,7 @@ def maybe_makedirs(path):
         if e.errno != errno.EEXIST:
             raise
 
+
 @contextmanager
 def cd(path):
     path = normpath(path)
@@ -47,18 +50,22 @@ def cd(path):
     finally:
         os.chdir(cwd)
 
+
 def run(command, **kwargs):
     print(command)
     subprocess.check_call(command, shell=True, **kwargs)
 
+
 def get_current_git_tag():
     out = subprocess.check_output(["git", "tag", "--points-at", "HEAD"])
     return out.decode().split("\n")[0]
 
+
 def get_current_commit_hash():
     out = subprocess.check_output(["git", "rev-parse", "HEAD"])
     return out.decode().split("\n")[0]
 
+
 def get_current_git_branch():
     out = subprocess.check_output(["git", "log", "-n", "1", "--pretty=%d", "HEAD"])
     m = re.search(r"release_[0-9\.]+", out.decode())
@@ -66,38 +73,53 @@ def get_current_git_branch():
         raise ValueError("Expected branch name of form release_xxx")
     return m.group(0)
 
+
 def retrieve(url, filename=None):
     print(f"{url} -> {filename}")
     return urlretrieve(url, filename)
 
+
 def main():
     parser = argparse.ArgumentParser()
-    parser.add_argument("--release-version", type=str, required=True,
+    parser.add_argument(
-                        help="Version of the release being prepared")
+        "--release-version",
+        type=str,
+        required=True,
+        help="Version of the release being prepared",
+    )
     args = parser.parse_args()
 
-    if sys.platform != "darwin" or platform.machine() != "x86_64":
+    if sys.platform != "darwin" or platform.machine() != "arm64":
-        raise NotImplementedError("Please run this script using an Intel Mac")
+        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()
     if current_git_tag != expected_git_tag:
         if not current_git_tag:
-            raise ValueError(f"Expected git tag {expected_git_tag} but current HEAD has no tag. "
+            raise ValueError(
-                             f"Run: git checkout {expected_git_tag}")
+                f"Expected git tag {expected_git_tag} but current HEAD has no tag. "
-        raise ValueError(f"Expected git tag {expected_git_tag} but current HEAD is at tag "
+                f"Run: git checkout {expected_git_tag}"
-                         f"{current_git_tag}. Run: git checkout {expected_git_tag}")
+            )
+        raise ValueError(
+            f"Expected git tag {expected_git_tag} but current HEAD is at tag "
+            f"{current_git_tag}. Run: git checkout {expected_git_tag}"
+        )
 
     commit_hash = get_current_commit_hash()
     git_branch = get_current_git_branch()
-    print(f"Using commit {commit_hash} of branch {git_branch}, git tag {current_git_tag}")
+    print(
+        f"Using commit {commit_hash} of branch {git_branch}, git tag {current_git_tag}"
+    )
 
     with cd("jvm-packages/"):
         print("====copying pure-Python tracker====")
         for use_cuda in [True, False]:
             xgboost4j = "xgboost4j-gpu" if use_cuda else "xgboost4j"
-            cp("../python-package/xgboost/tracker.py", f"{xgboost4j}/src/main/resources")
+            cp(
+                "../python-package/xgboost/tracker.py",
+                f"{xgboost4j}/src/main/resources",
+            )
 
         print("====copying resources for testing====")
         with cd("../demo/CLI/regression"):
@@ -115,7 +137,11 @@ def main():
                 cp(file, f"{xgboost4j_spark}/src/test/resources")
 
         print("====Creating directories to hold native binaries====")
-        for os_ident, arch in [("linux", "x86_64"), ("windows", "x86_64"), ("macos", "x86_64")]:
+        for os_ident, arch in [
+            ("linux", "x86_64"),
+            ("windows", "x86_64"),
+            ("macos", "x86_64"),
+        ]:
             output_dir = f"xgboost4j/src/main/resources/lib/{os_ident}/{arch}"
             maybe_makedirs(output_dir)
         for os_ident, arch in [("linux", "x86_64")]:
@@ -123,52 +149,86 @@ def main():
             maybe_makedirs(output_dir)
 
         print("====Downloading native binaries from CI====")
-        nightly_bucket_prefix = "https://s3-us-west-2.amazonaws.com/xgboost-nightly-builds"
+        nightly_bucket_prefix = (
-        maven_repo_prefix = "https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/release/ml/dmlc"
+            "https://s3-us-west-2.amazonaws.com/xgboost-nightly-builds"
+        )
+        maven_repo_prefix = (
+            "https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/release/ml/dmlc"
+        )
 
-        retrieve(url=f"{nightly_bucket_prefix}/{git_branch}/xgboost4j_{commit_hash}.dll",
+        retrieve(
-                 filename="xgboost4j/src/main/resources/lib/windows/x86_64/xgboost4j.dll")
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/xgboost4j_{commit_hash}.dll",
+            filename="xgboost4j/src/main/resources/lib/windows/x86_64/xgboost4j.dll",
+        )
+        retrieve(
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_{commit_hash}.dylib",
+            filename="xgboost4j/src/main/resources/lib/macos/x86_64/libxgboost4j.dylib",
+        )
 
         with tempfile.TemporaryDirectory() as tempdir:
             # libxgboost4j.so for Linux x86_64, CPU only
             zip_path = os.path.join(tempdir, "xgboost4j_2.12.jar")
             extract_dir = os.path.join(tempdir, "xgboost4j")
-            retrieve(url=f"{maven_repo_prefix}/xgboost4j_2.12/{version}/"
+            retrieve(
+                url=f"{maven_repo_prefix}/xgboost4j_2.12/{version}/"
                 f"xgboost4j_2.12-{version}.jar",
-                     filename=zip_path)
+                filename=zip_path,
+            )
             os.mkdir(extract_dir)
             with zipfile.ZipFile(zip_path, "r") as t:
                 t.extractall(extract_dir)
-            cp(os.path.join(extract_dir, "lib", "linux", "x86_64", "libxgboost4j.so"),
+            cp(
-               "xgboost4j/src/main/resources/lib/linux/x86_64/libxgboost4j.so")
+                os.path.join(extract_dir, "lib", "linux", "x86_64", "libxgboost4j.so"),
+                "xgboost4j/src/main/resources/lib/linux/x86_64/libxgboost4j.so",
+            )
 
             # libxgboost4j.so for Linux x86_64, GPU support
             zip_path = os.path.join(tempdir, "xgboost4j-gpu_2.12.jar")
             extract_dir = os.path.join(tempdir, "xgboost4j-gpu")
-            retrieve(url=f"{maven_repo_prefix}/xgboost4j-gpu_2.12/{version}/"
+            retrieve(
+                url=f"{maven_repo_prefix}/xgboost4j-gpu_2.12/{version}/"
                 f"xgboost4j-gpu_2.12-{version}.jar",
-                     filename=zip_path)
+                filename=zip_path,
+            )
             os.mkdir(extract_dir)
             with zipfile.ZipFile(zip_path, "r") as t:
                 t.extractall(extract_dir)
-            cp(os.path.join(extract_dir, "lib", "linux", "x86_64", "libxgboost4j.so"),
+            cp(
-               "xgboost4j-gpu/src/main/resources/lib/linux/x86_64/libxgboost4j.so")
+                os.path.join(extract_dir, "lib", "linux", "x86_64", "libxgboost4j.so"),
-
+                "xgboost4j-gpu/src/main/resources/lib/linux/x86_64/libxgboost4j.so",
+            )
 
     print("====Next Steps====")
     print("1. Gain upload right to Maven Central repo.")
     print("1-1. Sign up for a JIRA account at Sonatype: ")
-    print("1-2. File a JIRA ticket: "
+    print(
+        "1-2. File a JIRA ticket: "
         "https://issues.sonatype.org/secure/CreateIssue.jspa?issuetype=21&pid=10134. Example: "
-          "https://issues.sonatype.org/browse/OSSRH-67724")
+        "https://issues.sonatype.org/browse/OSSRH-67724"
-    print("2. Store the Sonatype credentials in .m2/settings.xml. See insturctions in "
+    )
-          "https://central.sonatype.org/publish/publish-maven/")
+    print(
-    print("3. Now on a Mac machine, run:")
+        "2. Store the Sonatype credentials in .m2/settings.xml. See insturctions in "
+        "https://central.sonatype.org/publish/publish-maven/"
+    )
+    print(
+        "3. Now on a M1 Mac machine, run the following to build Scala 2.12 artifacts:"
+    )
     print("   GPG_TTY=$(tty) mvn deploy -Prelease -DskipTests")
-    print("4. Log into https://oss.sonatype.org/. On the left menu panel, click Staging "
+    print(
-          "Repositories. Visit the URL https://oss.sonatype.org/content/repositories/mldmlc-1085 "
+        "4. Log into https://oss.sonatype.org/. On the left menu panel, click Staging "
+        "Repositories. Visit the URL https://oss.sonatype.org/content/repositories/mldmlc-xxxx "
         "to inspect the staged JAR files. Finally, press Release button to publish the "
-          "artifacts to the Maven Central repository.")
+        "artifacts to the Maven Central repository. The top-level metapackage should be "
+        "named xgboost-jvm_2.12."
+    )
+    print("5. Remove the Scala 2.12 artifacts and build Scala 2.13 artifacts:")
+    print("   rm -rf targets/")
+    print("   GPG_TTY=$(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."
+        "The top-level metapackage should be named xgboost-jvm_2.13."
+    )
+
 
 if __name__ == "__main__":
     main()

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 2  /* NOLINT */
 #define XGBOOST_VER_MINOR 0  /* NOLINT */
-#define XGBOOST_VER_PATCH 1  /* NOLINT */
+#define XGBOOST_VER_PATCH 2  /* NOLINT */
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -5,8 +5,8 @@
     <modelVersion>4.0.0</modelVersion>
 
     <groupId>ml.dmlc</groupId>
-    <artifactId>xgboost-jvm</artifactId>
+    <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-    <version>2.0.1</version>
+    <version>2.0.2</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>
@@ -189,6 +189,93 @@
                 </plugins>
             </build>
         </profile>
+        <profile>
+            <id>release-cpu-only</id>
+            <modules>
+                <module>xgboost4j</module>
+                <module>xgboost4j-example</module>
+                <module>xgboost4j-spark</module>
+                <module>xgboost4j-flink</module>
+            </modules>
+            <build>
+                <plugins>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-jar-plugin</artifactId>
+                        <version>3.3.0</version>
+                        <executions>
+                            <execution>
+                                <id>empty-javadoc-jar</id>
+                                <phase>package</phase>
+                                <goals>
+                                    <goal>jar</goal>
+                                </goals>
+                                <configuration>
+                                    <classifier>javadoc</classifier>
+                                    <classesDirectory>${basedir}/javadoc</classesDirectory>
+                                </configuration>
+                            </execution>
+                        </executions>
+                    </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-release-plugin</artifactId>
+                        <version>3.0.1</version>
+                        <configuration>
+                            <autoVersionSubmodules>true</autoVersionSubmodules>
+                            <useReleaseProfile>false</useReleaseProfile>
+                            <releaseProfiles>release</releaseProfiles>
+                            <goals>deploy</goals>
+                        </configuration>
+                    </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-gpg-plugin</artifactId>
+                        <version>3.1.0</version>
+                        <executions>
+                            <execution>
+                                <id>sign-artifacts</id>
+                                <phase>verify</phase>
+                                <goals>
+                                    <goal>sign</goal>
+                                </goals>
+                            </execution>
+                        </executions>
+                    </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-source-plugin</artifactId>
+                        <version>3.3.0</version>
+                        <executions>
+                            <execution>
+                                <id>attach-sources</id>
+                                <goals>
+                                    <goal>jar-no-fork</goal>
+                                </goals>
+                            </execution>
+                        </executions>
+                    </plugin>
+                    <plugin>
+                        <groupId>org.sonatype.plugins</groupId>
+                        <artifactId>nexus-staging-maven-plugin</artifactId>
+                        <version>1.6.13</version>
+                        <extensions>true</extensions>
+                        <configuration>
+                            <serverId>ossrh</serverId>
+                            <nexusUrl>https://oss.sonatype.org/</nexusUrl>
+                            <autoReleaseAfterClose>false</autoReleaseAfterClose>
+                        </configuration>
+                    </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-surefire-plugin</artifactId>
+                        <configuration>
+                            <skipTests>true</skipTests>
+                        </configuration>
+                    </plugin>
+                </plugins>
+            </build>
+        </profile>
         <profile>
             <id>assembly</id>
             <build>

jvm-packages/xgboost4j-example/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
     <name>xgboost4j-example</name>
     <artifactId>xgboost4j-example_${scala.binary.version}</artifactId>
-    <version>2.0.1</version>
+    <version>2.0.2</version>
     <packaging>jar</packaging>
     <build>
         <plugins>

jvm-packages/xgboost4j-flink/pom.xml

@@ -5,13 +5,13 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
 
     <name>xgboost4j-flink</name>
     <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-    <version>2.0.1</version>
+    <version>2.0.2</version>
     <properties>
       <flink-ml.version>2.2.0</flink-ml.version>
     </properties>

jvm-packages/xgboost4j-gpu/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
     <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>
     <name>xgboost4j-gpu</name>
-    <version>2.0.1</version>
+    <version>2.0.2</version>
     <packaging>jar</packaging>
 
     <dependencies>

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

@@ -5,8 +5,8 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
     <name>xgboost4j-spark-gpu</name>
     <artifactId>xgboost4j-spark-gpu_${scala.binary.version}</artifactId>

jvm-packages/xgboost4j-spark/pom.xml

@@ -5,8 +5,8 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
     <name>xgboost4j-spark</name>
     <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>

jvm-packages/xgboost4j/pom.xml

@@ -5,12 +5,12 @@
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>ml.dmlc</groupId>
-        <artifactId>xgboost-jvm</artifactId>
+        <artifactId>xgboost-jvm_${scala.binary.version}</artifactId>
-        <version>2.0.1</version>
+        <version>2.0.2</version>
     </parent>
     <name>xgboost4j</name>
     <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-    <version>2.0.1</version>
+    <version>2.0.2</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "packager.pep517"
 
 [project]
 name = "xgboost"
-version = "2.0.1"
+version = "2.0.2"
 authors = [
     { name = "Hyunsu Cho", email = "chohyu01@cs.washington.edu" },
     { name = "Jiaming Yuan", email = "jm.yuan@outlook.com" }

python-package/xgboost/VERSION

@@ -1 +1 @@
-2.0.1
+2.0.2