Merge branch 'master' into SPARK-49789

.github/workflows/build_and_test.yml

@@ -600,19 +600,16 @@ jobs:
         done
     - name: Install Conda for pip packaging test
       if: contains(matrix.modules, 'pyspark-errors')
-      run: |
-        curl -s -L "https://github.com/conda-forge/miniforge/releases/download/24.11.2-1/Miniforge3-Linux-x86_64.sh" > miniforge3.sh
-        bash miniforge3.sh -b -p $HOME/miniforge3
-        rm miniforge3.sh
+      uses: conda-incubator/setup-miniconda@v3
+      with:
+        miniforge-version: latest
     # Run the tests.
     - name: Run tests
       env: ${{ fromJSON(inputs.envs) }}
       shell: 'script -q -e -c "bash {0}"'
       run: |
         if [[ "$MODULES_TO_TEST" == *"pyspark-errors"* ]]; then
-          export PATH=$PATH:$HOME/miniforge3/bin
-          env
-          which conda
+          export PATH=$CONDA/bin:$PATH
           export SKIP_PACKAGING=false
           echo "Python Packaging Tests Enabled!"
         fi
@@ -625,9 +622,10 @@ jobs:
     - name: Upload coverage to Codecov
       if: fromJSON(inputs.envs).PYSPARK_CODECOV == 'true'
       uses: codecov/codecov-action@v5
+      env:
+        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
       with:
         files: ./python/coverage.xml
-        token: ${{ secrets.CODECOV_TOKEN }}
         flags: unittests
         name: PySpark
         verbose: true

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

@@ -467,9 +467,6 @@ private enum CaseSensitivity {
        */
       private static final int CASE_SENSITIVITY_MASK = 0b1;
 
-      private static final String UTF8_BINARY_COLLATION_NAME = "UTF8_BINARY";
-      private static final String UTF8_LCASE_COLLATION_NAME = "UTF8_LCASE";
-
       private static final int UTF8_BINARY_COLLATION_ID =
         new CollationSpecUTF8(CaseSensitivity.UNSPECIFIED, SpaceTrimming.NONE).collationId;
       private static final int UTF8_LCASE_COLLATION_ID =
@@ -655,9 +652,9 @@ protected CollationMeta buildCollationMeta() {
       protected String normalizedCollationName() {
         StringBuilder builder = new StringBuilder();
         if(caseSensitivity == CaseSensitivity.UNSPECIFIED){
-          builder.append(UTF8_BINARY_COLLATION_NAME);
+          builder.append(CollationNames.UTF8_BINARY);
         } else{
-          builder.append(UTF8_LCASE_COLLATION_NAME);
+          builder.append(CollationNames.UTF8_LCASE);
         }
         if (spaceTrimming != SpaceTrimming.NONE) {
           builder.append('_');
@@ -669,12 +666,12 @@ protected String normalizedCollationName() {
       static List<CollationIdentifier> listCollations() {
         CollationIdentifier UTF8_BINARY_COLLATION_IDENT = new CollationIdentifier(
             PROVIDER_SPARK,
-            UTF8_BINARY_COLLATION_NAME,
+            CollationNames.UTF8_BINARY,
             CollationSpecICU.ICU_VERSION
         );
         CollationIdentifier UTF8_LCASE_COLLATION_IDENT = new CollationIdentifier(
             PROVIDER_SPARK,
-            UTF8_LCASE_COLLATION_NAME,
+            CollationNames.UTF8_LCASE,
             CollationSpecICU.ICU_VERSION
         );
         return Arrays.asList(UTF8_BINARY_COLLATION_IDENT, UTF8_LCASE_COLLATION_IDENT);
@@ -758,7 +755,7 @@ private enum AccentSensitivity {
         VersionInfo.ICU_VERSION.getMinor());
 
       static {
-        ICULocaleMap.put("UNICODE", ULocale.ROOT);
+        ICULocaleMap.put(CollationNames.UNICODE, ULocale.ROOT);
         // ICU-implemented `ULocale`s which have corresponding `Collator` installed.
         ULocale[] locales = Collator.getAvailableULocales();
         // Build locale names in format: language["_" optional script]["_" optional country code].
@@ -806,13 +803,13 @@ private enum AccentSensitivity {
       }
 
       private static final int UNICODE_COLLATION_ID = new CollationSpecICU(
-        "UNICODE",
+        CollationNames.UNICODE,
         CaseSensitivity.CS,
         AccentSensitivity.AS,
         SpaceTrimming.NONE).collationId;
 
       private static final int UNICODE_CI_COLLATION_ID = new CollationSpecICU(
-        "UNICODE",
+        CollationNames.UNICODE,
         CaseSensitivity.CI,
         AccentSensitivity.AS,
         SpaceTrimming.NONE).collationId;

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

@@ -0,0 +1,25 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark.sql.catalyst.util;
+
+public class CollationNames {
+  public static final String UTF8_BINARY = "UTF8_BINARY";
+  public static final String UTF8_LCASE = "UTF8_LCASE";
+  public static final String UNICODE = "UNICODE";
+  public static final String UNICODE_CI = "UNICODE_CI";
+}