Fill Java CI gaps for Maven Central publication

.github/workflows/build.yaml

@@ -541,3 +541,23 @@ jobs:
           name: cudf_java_maven_repo
           path: ${{ runner.temp }}/maven-repo
           if-no-files-found: error
+
+  # Publish tagged release candidates to Maven Central via the Sonatype
+  # Central Publisher Portal.
+  java-publish:
+    needs: [java-gather]
+    if: ${{ github.ref_type == 'tag' && (inputs.build_type || 'branch') == 'branch' }}
+    permissions:
+      actions: read
+      contents: read
+    uses: rapidsai/shared-workflows/.github/workflows/maven-publish.yaml@release/26.08
+    secrets:
+      GPG_PRIVATE_KEY: ${{ secrets.GPG_PRIVATE_KEY }}
+      GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
+      MAVEN_DEPLOY_TOKEN: ${{ secrets.MAVEN_DEPLOY_TOKEN }}
+    with:
+      publication-type: 'rc'
+      artifact-name: cudf_java_maven_repo
+      source-git-sha: ${{ inputs.sha || github.sha }}
+      # false = validate + drop (safe). true = stage PENDING for manual publish.
+      stage-for-maven-central-publish: true

java/ci/README.md

@@ -34,12 +34,15 @@ so plain `rm -rf` works.
 ### Step 2 - Package the cuDF Java JAR for one classifier
 
 ```bash
-./java/ci/build_cudf_java_jar.sh \
+GITHUB_REF=refs/heads/my-branch ./java/ci/build_cudf_java_jar.sh \
   --libcudf-dir /tmp/libcudf-cuda12 \
   --output-dir /tmp/jars \
   --cuda-version 12.9
 ```
 
+`GITHUB_REF` is required and selects release-tag vs SNAPSHOT versioning. See
+the versioning section below.
+
 This compiles the JNI layer against the static libcudf from Step 1 and emits
 the classifier JAR (e.g. `cudf-26.08.0-SNAPSHOT-cuda12.jar`), a
 classifier-independent sources jar and javadoc jar, and the POM into a
@@ -72,12 +75,14 @@ inside the container.
 
 This walks every subdirectory of `--jars-dir` (each subdir name IS the
 classifier), gathers the per-classifier JAR, one shared sources jar, one
-shared javadoc jar, and the shared POM, derives the artifact version from
-the JAR filenames (requiring a single unique version across subdirs), and
+shared javadoc jar, the shared POM, and seeds an unclassified primary JAR
+as a copy of the `cuda12` classifier. Derives the artifact version from
+the JAR filenames (requiring a single unique version across subdirs) and
 lays them out as:
 
 ```
 /tmp/maven-repo/ai/rapids/cudf/26.08.0-SNAPSHOT/
+    cudf-26.08.0-SNAPSHOT.jar
     cudf-26.08.0-SNAPSHOT-cuda12.jar
     cudf-26.08.0-SNAPSHOT-cuda13.jar
     cudf-26.08.0-SNAPSHOT-sources.jar
@@ -88,7 +93,27 @@ lays them out as:
 The set of classifiers is whatever subdirectories are present under
 `--jars-dir`. For a local `x86_64`-only run, populate `/tmp/jars/cuda12/`
 and `/tmp/jars/cuda13/`. For the full four-way release build, add
-`/tmp/jars/cuda12-arm64/` and `/tmp/jars/cuda13-arm64/`.
+`/tmp/jars/cuda12-arm64/` and `/tmp/jars/cuda13-arm64/`. The `cuda12`
+subdirectory is required because the unclassified primary JAR is copied from
+it, so an `aarch64`-only set of subdirectories is not a valid gather input.
+
+### Release Tag vs SNAPSHOT versioning
+
+Release tag CI runs (`GITHUB_REF=refs/tags/vYY.MM.PP`) produce release-versioned
+JARs (`cudf-26.08.0-*.jar`). All other runs produce `-SNAPSHOT`. Gated by
+[`rapids-is-release-build`](https://github.com/rapidsai/gha-tools/blob/main/tools/rapids-is-release-build).
+`GITHUB_REF` is required. `test_java_build_local.sh` defaults it to the current
+branch.
+
+To rehearse the release path locally:
+
+```bash
+GITHUB_REF=refs/tags/vYY.MM.PP ./java/ci/test_java_build_local.sh
+```
+
+Rewrites `java/pom.xml` in place. Restore with `git checkout java/pom.xml`.
+
+### GitHub Actions
 
 In GitHub Actions (`.github/workflows/build.yaml`), the `java-build` matrix job
 runs Steps 1-2 per (CUDA x arch) entry and uploads each classifier subdir as a

java/ci/assemble_maven_repo.sh

@@ -166,12 +166,26 @@ if [[ -z "${FIRST_VERSION}" ]]; then
   exit 1
 fi
 
+DEST_DIR="${OUTPUT_DIR}/${GROUP_PATH}/${ARTIFACT_ID}/${FIRST_VERSION}"
+
+# Seed the unclassified primary from cuda12. Maven Central serves this to
+# consumers depending on ai.rapids:cudf without a <classifier>.
+PRIMARY_SOURCE="${DEST_DIR}/cudf-${FIRST_VERSION}-cuda12.jar"
+if [[ ! -f "${PRIMARY_SOURCE}" ]]; then
+  echo "Error: ${PRIMARY_SOURCE} missing." >&2
+  exit 1
+fi
+UNCLASSIFIED="${DEST_DIR}/cudf-${FIRST_VERSION}.jar"
+if [[ ! -f "${UNCLASSIFIED}" ]]; then
+  cp -f "${PRIMARY_SOURCE}" "${UNCLASSIFIED}"
+  echo "  + cudf-${FIRST_VERSION}.jar (unclassified primary, copy of cuda12)"
+fi
+
 # Sources and javadoc jars are classifier-independent (pure Java, no arch or
 # cuda variation). Every classifier subdir produces byte-equivalent copies;
 # pick the lexicographically first subdir's copy as canonical. Fail fast if
 # any subdir is missing either file - that indicates -Prelease or
 # -Pjavadoc-jdk17 did not activate for that classifier's build.
-DEST_DIR="${OUTPUT_DIR}/${GROUP_PATH}/${ARTIFACT_ID}/${FIRST_VERSION}"
 FIRST_CLASSIFIER_SUBDIR=""
 for subdir in "${JARS_DIR}"/*/; do
   if [[ -z ${FIRST_CLASSIFIER_SUBDIR} ]]; then

java/ci/build_cudf_java_jar.sh

@@ -121,6 +121,8 @@ require_arg --libcudf-dir  "${LIBCUDF_DIR}"
 require_arg --output-dir   "${OUTPUT_DIR}"
 require_arg --cuda-version "${CUDA_VERSION}"
 
+: "${GITHUB_REF:?GITHUB_REF must be set.}"
+
 if [[ ! -d ${LIBCUDF_DIR} ]]; then
   echo "Error: --libcudf-dir '${LIBCUDF_DIR}' does not exist."
   exit 1
@@ -194,6 +196,7 @@ DOCKER_ARGS=(
   --env PARALLEL_LEVEL="${PARALLEL_LEVEL}"
   --env HOST_UID="$(id -u)"
   --env HOST_GID="$(id -g)"
+  --env GITHUB_REF="${GITHUB_REF}"
 )
 
 if [[ -n ${CMAKE_CUDA_ARCHITECTURES} ]]; then

java/ci/build_cudf_java_jar_in_container.sh

@@ -38,7 +38,16 @@ if [[ -z ${HOST_UID} || -z ${HOST_GID} ]]; then
   exit 1
 fi
 
+# TEMPORARY: same patch as spark-rapids-jni
+# (NVIDIA/cudf-spark-jni patches/0001-use-static-nvcomp-from-libcudf.patch).
+# Static CUDF_JNI_LIBCUDF_STATIC=ON JARs embed nvcomp in libcudf and do not
+# package libnvcomp.so. NativeDepsLoader still requires it unless this patch
+# drops "nvcomp" from loadOrder for packaging only.
+NVCOMP_LOADER_PATCH="${REPO_ROOT}/java/ci/patches/0001-use-static-nvcomp-from-libcudf.patch"
+
 _chown_outputs_on_exit() {
+  # Best-effort: leave /repo clean even if packaging failed mid-build.
+  git -C "${REPO_ROOT}" apply --reverse "${NVCOMP_LOADER_PATCH}" >/dev/null 2>&1 || true
   chown -R "${HOST_UID}:${HOST_GID}" "${OUTPUT_DIR}" "${REPO_ROOT}/java/target" 2>/dev/null || true
 }
 trap _chown_outputs_on_exit EXIT
@@ -107,8 +116,29 @@ fi
 cd "${REPO_ROOT}/java"
 
 CUDF_VERSION="$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout "${BUILD_ARG[@]}")"
+
+# Release tag builds strip -SNAPSHOT and rewrite the POM so packaged artifacts
+# carry the release version. Non-release builds keep -SNAPSHOT.
+if rapids-is-release-build; then
+  CUDF_VERSION="${CUDF_VERSION%-SNAPSHOT}"
+  mvn versions:set -DnewVersion="${CUDF_VERSION}" -DgenerateBackupPoms=false "${BUILD_ARG[@]}"
+fi
+
 rapids-logger "Packaging cuDF Java JAR version ${CUDF_VERSION} (libcudf: ${CUDF_INSTALL_DIR})"
 
+# PIC libspdlog.a / libfmt.a are installed into the static libcudf prefix
+# (same tree as rmm) and linked via $<INSTALL_PREFIX> from the packaging
+# cmake patch. Fail early if this mount is missing them.
+for _logging_lib in libfmt.a libspdlog.a; do
+  if [[ ! -f ${CUDF_INSTALL_DIR}/lib/${_logging_lib} ]]; then
+    echo "Error: ${CUDF_INSTALL_DIR}/lib/${_logging_lib} missing; rebuild static libcudf with install_static_logging_libs" >&2
+    exit 1
+  fi
+done
+
+rapids-logger "Applying temporary nvcomp NativeDepsLoader patch (same as spark-rapids-jni)"
+git -C "${REPO_ROOT}" apply "${NVCOMP_LOADER_PATCH}"
+
 # The `clean` goal is intentionally omitted: /repo/java/target is a
 # bind-mount point, so when `mvn clean` attempts to remove the directory,
 # it fails with EBUSY. The host wrapper (build_cudf_java_jar.sh) recreates
@@ -162,4 +192,6 @@ done
 cp -f "${MAIN_JAR}" "${OUTPUT_DIR}/"
 cp -f pom.xml "${OUTPUT_DIR}/cudf-${CUDF_VERSION}.pom"
 
+bash "${REPO_ROOT}/java/ci/check_jar_libcudf_needed.sh" "${OUTPUT_DIR}/$(basename "${MAIN_JAR}")"
+
 rapids-logger "Emitted $(basename "${MAIN_JAR}"), cudf-${CUDF_VERSION}-sources.jar, cudf-${CUDF_VERSION}-javadoc.jar, and cudf-${CUDF_VERSION}.pom to ${OUTPUT_DIR}"

java/ci/build_static_libcudf_in_container.sh

@@ -34,6 +34,14 @@ if [[ -z ${HOST_UID} || -z ${HOST_GID} ]]; then
   exit 1
 fi
 
+SPDLOG_FMT_PATCH="${REPO_ROOT}/java/ci/patches/0002-static-spdlog-fmt-for-java-libcudf.patch"
+
+_cleanup_on_exit() {
+  git -C "${REPO_ROOT}" apply --reverse "${SPDLOG_FMT_PATCH}" >/dev/null 2>&1 || true
+  chown -R "${HOST_UID}:${HOST_GID}" "${INSTALL_PREFIX}" 2>/dev/null || true
+}
+trap _cleanup_on_exit EXIT
+
 if [[ -z ${PARALLEL_LEVEL} ]]; then
   PARALLEL_LEVEL=$(nproc)
 fi
@@ -62,6 +70,13 @@ if [[ -z ${LIBCUDF_KERNEL_CACHE_PATH} ]]; then
   export LIBCUDF_KERNEL_CACHE_PATH=/tmp/rapids-kernel-cache
 fi
 
+# PIC libfmt.a / libspdlog.a into the same install prefix as rmm / rapids_logger.
+# shellcheck disable=SC1091
+. "${REPO_ROOT}/java/ci/install_static_logging_libs.sh"
+install_static_logging_libs "${INSTALL_PREFIX}"
+
+git -C "${REPO_ROOT}" apply "${SPDLOG_FMT_PATCH}"
+
 CMAKE_ARGS=(
   -S "${REPO_ROOT}/cpp"
   -B "${BUILD_DIR}"
@@ -91,5 +106,4 @@ cmake --build "${BUILD_DIR}" --parallel "${PARALLEL_LEVEL}"
 rapids-logger "Installing static libcudf to ${INSTALL_PREFIX}"
 cmake --install "${BUILD_DIR}"
 
-rapids-logger "Chowning ${INSTALL_PREFIX} to ${HOST_UID}:${HOST_GID}"
-chown -R "${HOST_UID}:${HOST_GID}" "${INSTALL_PREFIX}"
+rapids-logger "Emitted static libcudf install tree to ${INSTALL_PREFIX}"

java/ci/check_jar_libcudf_needed.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+# SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Fail if a cudf classifier JAR's libcudf.so DT_NEEDs libspdlog or libfmt.
+#
+# Usage: check_jar_libcudf_needed.sh <cudf-*-cuda*.jar>
+
+set -euo pipefail
+
+if [[ $# -ne 1 ]]; then
+  echo "Usage: $0 <cudf-classifier.jar>" >&2
+  exit 2
+fi
+
+JAR="$(realpath "$1")"
+if [[ ! -f ${JAR} ]]; then
+  echo "Error: JAR not found: ${JAR}" >&2
+  exit 1
+fi
+
+if ! command -v readelf >/dev/null 2>&1; then
+  echo "Error: readelf not found (install binutils)" >&2
+  exit 1
+fi
+
+if ! command -v unzip >/dev/null 2>&1; then
+  echo "Error: unzip not found" >&2
+  exit 1
+fi
+
+TMP="$(mktemp -d)"
+trap 'rm -rf "${TMP}"' EXIT
+
+MEMBER="$(unzip -Z1 "${JAR}" | grep -E '(^|/)libcudf\.so$' | head -1 || true)"
+if [[ -z ${MEMBER} ]]; then
+  echo "Error: ${JAR} does not contain libcudf.so" >&2
+  exit 1
+fi
+
+# -j flattens the JAR-internal path (e.g. native/.../libcudf.so) into ${TMP}.
+unzip -j -o -q "${JAR}" "${MEMBER}" -d "${TMP}"
+
+SO="${TMP}/libcudf.so"
+if [[ ! -f ${SO} ]]; then
+  echo "Error: failed to extract libcudf.so from ${JAR}" >&2
+  exit 1
+fi
+
+if readelf -d "${SO}" | grep -E 'NEEDED.*\[(libspdlog|libfmt)\.so'; then
+  echo "Error: ${JAR} libcudf.so still depends on shared spdlog/fmt:" >&2
+  readelf -d "${SO}" | grep NEEDED >&2 || true
+  exit 1
+fi
+
+echo "OK: no libspdlog/libfmt DT_NEEDED in $(basename "${JAR}")"

java/ci/install_static_logging_libs.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+# SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Install PIC static libfmt.a / libspdlog.a into the static libcudf install
+# prefix (same tree as rmm / rapids_logger). Versions match the shared libs
+# from the ci-conda build_java env (libfmt.so.12.1.0, libspdlog.so.1.17.0).
+#
+# Usage:
+#   . install_static_logging_libs.sh
+#   install_static_logging_libs "${INSTALL_PREFIX}"
+
+install_static_libfmt() {
+  local prefix="$1"
+  local src
+  src="$(mktemp -d /tmp/cudf-java-fmt.XXXXXX)"
+
+  rapids-logger "Installing static libfmt.a (12.1.0) into ${prefix}"
+  curl -fsSL "https://github.com/fmtlib/fmt/archive/refs/tags/12.1.0.tar.gz" \
+    | tar -xz -C "${src}"
+  cmake -S "${src}/fmt-12.1.0" -B "${src}/build" -GNinja \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DCMAKE_INSTALL_PREFIX="${prefix}" \
+    -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
+    -DBUILD_SHARED_LIBS=OFF \
+    -DFMT_DOC=OFF \
+    -DFMT_TEST=OFF
+  cmake --build "${src}/build" --parallel "${PARALLEL_LEVEL}"
+  cmake --install "${src}/build"
+  rm -rf "${src}"
+  [[ -f ${prefix}/lib/libfmt.a ]] \
+    || { echo "Error: failed to install ${prefix}/lib/libfmt.a" >&2; return 1; }
+}
+
+install_static_libspdlog() {
+  local prefix="$1"
+  local src
+  src="$(mktemp -d /tmp/cudf-java-spdlog.XXXXXX)"
+
+  rapids-logger "Installing static libspdlog.a (v1.17.0) into ${prefix}"
+  curl -fsSL "https://github.com/gabime/spdlog/archive/refs/tags/v1.17.0.tar.gz" \
+    | tar -xz -C "${src}"
+  cmake -S "${src}/spdlog-1.17.0" -B "${src}/build" -GNinja \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DCMAKE_INSTALL_PREFIX="${prefix}" \
+    -DCMAKE_PREFIX_PATH="${prefix}" \
+    -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
+    -DSPDLOG_BUILD_SHARED=OFF \
+    -DSPDLOG_BUILD_PIC=ON \
+    -DSPDLOG_FMT_EXTERNAL=ON \
+    -DSPDLOG_BUILD_EXAMPLE=OFF \
+    -DSPDLOG_BUILD_TESTS=OFF \
+    -DSPDLOG_BUILD_BENCH=OFF
+  cmake --build "${src}/build" --parallel "${PARALLEL_LEVEL}"
+  cmake --install "${src}/build"
+  rm -rf "${src}"
+  [[ -f ${prefix}/lib/libspdlog.a ]] \
+    || { echo "Error: failed to install ${prefix}/lib/libspdlog.a" >&2; return 1; }
+}
+
+install_static_logging_libs() {
+  local prefix="$1"
+  if [[ -z ${prefix} ]]; then
+    echo "Error: install_static_logging_libs requires an install prefix" >&2
+    return 1
+  fi
+  mkdir -p "${prefix}"
+
+  [[ -f ${prefix}/lib/libfmt.a ]] || install_static_libfmt "${prefix}"
+  [[ -f ${prefix}/lib/libspdlog.a ]] || install_static_libspdlog "${prefix}"
+}

java/ci/patches/0001-use-static-nvcomp-from-libcudf.patch

@@ -0,0 +1,14 @@
+diff --git a/java/src/main/java/ai/rapids/cudf/NativeDepsLoader.java b/java/src/main/java/ai/rapids/cudf/NativeDepsLoader.java
+index 0000000000..0000000000 100644
+--- a/java/src/main/java/ai/rapids/cudf/NativeDepsLoader.java
++++ b/java/src/main/java/ai/rapids/cudf/NativeDepsLoader.java
+@@ -69,9 +69,6 @@ public class NativeDepsLoader {
+    * subsequent stages are loaded.
+    */
+   private static final String[][] loadOrder = new String[][]{
+-      new String[]{
+-          "nvcomp"
+-      },
+       new String[]{
+           "cudf"
+       },

java/ci/patches/0002-static-spdlog-fmt-for-java-libcudf.patch

@@ -0,0 +1,29 @@
+diff --git a/cpp/CMakeLists.txt b/cpp/CMakeLists.txt
+index 0000000000..1111111111 100644
+--- a/cpp/CMakeLists.txt
++++ b/cpp/CMakeLists.txt
+@@ -1359,4 +1359,23 @@ if(TARGET spdlog::spdlog)
+   else()
+-    target_link_libraries(cudf PRIVATE ${_spdlog_link})
++    # TEMPORARY (java packaging): absorb PIC static spdlog/fmt from the
++    # libcudf install prefix (same tree as rmm). BUILD_INTERFACE uses the
++    # libs found at configure time; INSTALL_INTERFACE uses $<INSTALL_PREFIX>
++    # so consumers (JAR container at /libcudf) resolve them like other deps.
++    find_library(
++      CUDF_JAVA_SPDLOG_STATIC NAMES libspdlog.a
++      PATHS "${CMAKE_INSTALL_PREFIX}/lib" NO_DEFAULT_PATH REQUIRED
++    )
++    find_library(
++      CUDF_JAVA_FMT_STATIC NAMES libfmt.a
++      PATHS "${CMAKE_INSTALL_PREFIX}/lib" NO_DEFAULT_PATH REQUIRED
++    )
++    target_link_libraries(
++      cudf
++      PRIVATE
++        "$<BUILD_INTERFACE:$<LINK_LIBRARY:WHOLE_ARCHIVE,${CUDF_JAVA_SPDLOG_STATIC}>>"
++        "$<BUILD_INTERFACE:$<LINK_LIBRARY:WHOLE_ARCHIVE,${CUDF_JAVA_FMT_STATIC}>>"
++        "$<INSTALL_INTERFACE:$<LINK_LIBRARY:WHOLE_ARCHIVE,$<INSTALL_PREFIX>/lib/libspdlog.a>>"
++        "$<INSTALL_INTERFACE:$<LINK_LIBRARY:WHOLE_ARCHIVE,$<INSTALL_PREFIX>/lib/libfmt.a>>"
++    )
+   endif()
+ endif()