Merge branch 'master' into np_upgrade

.asf.yaml

@@ -31,6 +31,8 @@ github:
     merge: false
     squash: true
     rebase: true
+  ghp_branch: master
+  ghp_path: /docs
 
 notifications:
   pullrequests: reviews@spark.apache.org

.github/workflows/build_python_connect.yml

@@ -71,7 +71,7 @@ jobs:
           python packaging/connect/setup.py sdist
           cd dist
           pip install pyspark*connect-*.tar.gz
-          pip install 'six==1.16.0' 'pandas<=2.2.2' scipy 'plotly>=4.8' 'mlflow>=2.8.1' coverage matplotlib openpyxl 'memory-profiler>=0.61.0' 'scikit-learn>=1.3.2' 'graphviz==0.20.3' torch torchvision torcheval deepspeed unittest-xml-reporting
+          pip install 'six==1.16.0' 'pandas<=2.2.2' scipy 'plotly>=4.8' 'mlflow>=2.8.1' coverage matplotlib openpyxl 'memory-profiler>=0.61.0' 'scikit-learn>=1.3.2' 'graphviz==0.20.3' torch torchvision torcheval deepspeed unittest-xml-reporting 'plotly>=4.8'
       - name: Run tests
         env:
           SPARK_TESTING: 1

.github/workflows/maven_test.yml

@@ -40,7 +40,7 @@ on:
         description: OS to run this build.
         required: false
         type: string
-        default: ubuntu-22.04
+        default: ubuntu-latest
       envs:
         description: Additional environment variables to set when running the tests. Should be in JSON format.
         required: false

.github/workflows/pages.yml

@@ -0,0 +1,97 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+name: GitHub Pages deployment
+
+on:
+  push:
+    branches:
+      - master
+
+concurrency:
+  group: 'docs preview'
+  cancel-in-progress: false
+
+jobs:
+  docs:
+    name: Build and deploy documentation
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      pages: write
+    environment:
+      name: github-pages # https://github.com/actions/deploy-pages/issues/271
+    env:
+      SPARK_TESTING: 1 # Reduce some noise in the logs
+      RELEASE_VERSION: 'In-Progress'
+    steps:
+      - name: Checkout Spark repository
+        uses: actions/checkout@v4
+        with:
+          repository: apache/spark
+          ref: 'master'
+      - name: Install Java 17
+        uses: actions/setup-java@v4
+        with:
+          distribution: zulu
+          java-version: 17
+      - name: Install Python 3.9
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+          architecture: x64
+          cache: 'pip'
+      - name: Install Python dependencies
+        run: |
+         pip install 'sphinx==4.5.0' mkdocs 'pydata_sphinx_theme>=0.13' sphinx-copybutton nbsphinx numpydoc jinja2 markupsafe 'pyzmq<24.0.0' \
+            ipython ipython_genutils sphinx_plotly_directive 'numpy>=1.20.0' pyarrow 'pandas==2.2.2' 'plotly>=4.8' 'docutils<0.18.0' \
+            'flake8==3.9.0' 'mypy==1.8.0' 'pytest==7.1.3' 'pytest-mypy-plugins==1.9.3' 'black==23.9.1' \
+            'pandas-stubs==1.2.0.53' 'grpcio==1.62.0' 'grpcio-status==1.62.0' 'grpc-stubs==1.24.11' 'googleapis-common-protos-stubs==2.2.0' \
+            'sphinxcontrib-applehelp==1.0.4' 'sphinxcontrib-devhelp==1.0.2' 'sphinxcontrib-htmlhelp==2.0.1' 'sphinxcontrib-qthelp==1.0.3' 'sphinxcontrib-serializinghtml==1.1.5'
+      - name: Install Ruby for documentation generation
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: '3.3'
+          bundler-cache: true
+      - name: Install Pandoc
+        run: |
+          sudo apt-get update -y
+          sudo apt-get install pandoc
+      - name: Install dependencies for documentation generation
+        run: |
+          cd docs
+          gem install bundler -v 2.4.22 -n /usr/local/bin
+          bundle install --retry=100
+      - name: Run documentation build
+        run: |
+          sed -i".tmp1" 's/SPARK_VERSION:.*$/SPARK_VERSION: '"$RELEASE_VERSION"'/g' docs/_config.yml
+          sed -i".tmp2" 's/SPARK_VERSION_SHORT:.*$/SPARK_VERSION_SHORT: '"$RELEASE_VERSION"'/g' docs/_config.yml
+          sed -i".tmp3" "s/'facetFilters':.*$/'facetFilters': [\"version:$RELEASE_VERSION\"]/g" docs/_config.yml
+          sed -i".tmp4" 's/__version__: str = .*$/__version__: str = "'"$RELEASE_VERSION"'"/' python/pyspark/version.py
+          cd docs
+          SKIP_RDOC=1 bundle exec jekyll build
+      - name: Setup Pages
+        uses: actions/configure-pages@v5
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: 'docs/_site'
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java

@@ -109,7 +109,7 @@ private static int lowercaseMatchLengthFrom(
     }
     // Compare the characters in the target and pattern strings.
     int matchLength = 0, codePointBuffer = -1, targetCodePoint, patternCodePoint;
-    while (targetIterator.hasNext() && patternIterator.hasNext()) {
+    while ((targetIterator.hasNext() || codePointBuffer != -1) && patternIterator.hasNext()) {
       if (codePointBuffer != -1) {
         targetCodePoint = codePointBuffer;
         codePointBuffer = -1;
@@ -211,7 +211,7 @@ private static int lowercaseMatchLengthUntil(
     }
     // Compare the characters in the target and pattern strings.
     int matchLength = 0, codePointBuffer = -1, targetCodePoint, patternCodePoint;
-    while (targetIterator.hasNext() && patternIterator.hasNext()) {
+    while ((targetIterator.hasNext() || codePointBuffer != -1) && patternIterator.hasNext()) {
       if (codePointBuffer != -1) {
         targetCodePoint = codePointBuffer;
         codePointBuffer = -1;

common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java

@@ -629,6 +629,8 @@ public void testStartsWith() throws SparkException {
     assertStartsWith("İonic", "Io", "UTF8_LCASE", false);
     assertStartsWith("İonic", "i\u0307o", "UTF8_LCASE", true);
     assertStartsWith("İonic", "İo", "UTF8_LCASE", true);
+    assertStartsWith("oİ", "oİ", "UTF8_LCASE", true);
+    assertStartsWith("oİ", "oi̇", "UTF8_LCASE", true);
     // Conditional case mapping (e.g. Greek sigmas).
     assertStartsWith("σ", "σ", "UTF8_BINARY", true);
     assertStartsWith("σ", "ς", "UTF8_BINARY", false);
@@ -880,6 +882,8 @@ public void testEndsWith() throws SparkException {
     assertEndsWith("the İo", "Io", "UTF8_LCASE", false);
     assertEndsWith("the İo", "i\u0307o", "UTF8_LCASE", true);
     assertEndsWith("the İo", "İo", "UTF8_LCASE", true);
+    assertEndsWith("İo", "İo", "UTF8_LCASE", true);
+    assertEndsWith("İo", "i̇o", "UTF8_LCASE", true);
     // Conditional case mapping (e.g. Greek sigmas).
     assertEndsWith("σ", "σ", "UTF8_BINARY", true);
     assertEndsWith("σ", "ς", "UTF8_BINARY", false);

connector/connect/client/jvm/pom.xml

@@ -88,6 +88,13 @@
       <artifactId>scalacheck_${scala.binary.version}</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.apache.spark</groupId>
+      <artifactId>spark-sql-api_${scala.binary.version}</artifactId>
+      <version>${project.version}</version>
+      <classifier>tests</classifier>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-common-utils_${scala.binary.version}</artifactId>

connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala

@@ -1035,12 +1035,7 @@ class Dataset[T] private[sql] (
     new MergeIntoWriterImpl[T](table, this, condition)
   }
 
-  /**
-   * Interface for saving the content of the streaming Dataset out into external storage.
-   *
-   * @group basic
-   * @since 3.5.0
-   */
+  /** @inheritdoc */
   def writeStream: DataStreamWriter[T] = {
     new DataStreamWriter[T](this)
   }