apache · yihua · Jun 27, 2026 · Jun 27, 2026 · Jun 27, 2026 · Jun 27, 2026
diff --git a/.github/workflows/bot.yml b/.github/workflows/bot.yml
@@ -311,14 +311,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.3"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
-
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.4"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
-
+          # Full suite runs only on the latest 3.x (Spark 3.5 / Scala 2.12 / Java 11).
+          # Older 3.x versions run the curated core set in test-spark-core-tests.
           - scalaProfile: "scala-2.12"
             sparkProfile: "spark3.5"
             sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
@@ -368,14 +362,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.3"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
-
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.4"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
-
           - scalaProfile: "scala-2.12"
             sparkProfile: "spark3.5"
             sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
@@ -440,14 +426,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.3"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
-
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.4"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
-
           - scalaProfile: "scala-2.12"
             sparkProfile: "spark3.5"
             sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
@@ -505,14 +483,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.3"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
-
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.4"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
-
           - scalaProfile: "scala-2.12"
             sparkProfile: "spark3.5"
             sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
@@ -570,14 +540,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.3"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
-
-          - scalaProfile: "scala-2.12"
-            sparkProfile: "spark3.4"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
-
           - scalaProfile: "scala-2.12"
             sparkProfile: "spark3.5"
             sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
@@ -685,15 +647,9 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark3.5"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.0"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.1"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
+          # Full suite runs only on the latest 4.x (Spark 4.2 / Scala 2.13 / Java 17).
+          # Spark 3.5/4.0/4.1 on Java 17 run the curated core set in
+          # test-spark-core-tests.
           - scalaProfile: "scala-2.13"
             sparkProfile: "spark4.2"
             sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
@@ -743,15 +699,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark3.5"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.0"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.1"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
           - scalaProfile: "scala-2.13"
             sparkProfile: "spark4.2"
             sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
@@ -816,15 +763,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark3.5"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.0"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.1"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
           - scalaProfile: "scala-2.13"
             sparkProfile: "spark4.2"
             sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
@@ -882,15 +820,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark3.5"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.0"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.1"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
           - scalaProfile: "scala-2.13"
             sparkProfile: "spark4.2"
             sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
@@ -948,15 +877,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark3.5"
-            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.0"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
-          - scalaProfile: "scala-2.13"
-            sparkProfile: "spark4.1"
-            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
           - scalaProfile: "scala-2.13"
             sparkProfile: "spark4.2"
             sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
@@ -1008,6 +928,105 @@ jobs:
           flags: spark-scala-tests
           token: ${{ secrets.CODECOV_TOKEN }}
 
+  # Curated core flow subset (-Pcore-tests) on every Spark version, for both the
+  # Java 11 / Scala 2.12 and Java 17 / Scala 2.13 tracks in one matrix-driven job.
+  # The full unit/functional/scala suites above run only on the latest 3.x (spark3.5)
+  # and latest 4.x (spark4.2); these entries give the other versions a fast
+  # critical-path signal. The core set is excluded from the full suites
+  # (excludedGroups=core, tagsToExclude=SparkSQLCoreFlow), so no test runs twice.
+  # The per-entry mvnProfiles carries -Pjava17 for the Java 17 rows (empty for Java 11).
+  test-spark-core-tests:
+    name: test-spark-core-tests (${{ matrix.scalaProfile }}, ${{ matrix.sparkProfile }}, java${{ matrix.javaVersion }})
+    runs-on: ubuntu-latest
+    needs: changes
+    strategy:
+      matrix:
+        include:
+          - scalaProfile: "scala-2.12"
+            sparkProfile: "spark3.3"
+            sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
+            javaVersion: "11"
+            mvnProfiles: ""
+          - scalaProfile: "scala-2.12"
+            sparkProfile: "spark3.4"
+            sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
+            javaVersion: "11"
+            mvnProfiles: ""
+          - scalaProfile: "scala-2.12"
+            sparkProfile: "spark3.5"
+            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
+            javaVersion: "11"
+            mvnProfiles: ""
+          - scalaProfile: "scala-2.13"
+            sparkProfile: "spark3.5"
+            sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
+            javaVersion: "17"
+            mvnProfiles: "-Pjava17"
+          - scalaProfile: "scala-2.13"
+            sparkProfile: "spark4.0"
+            sparkModules: "hudi-spark-datasource/hudi-spark4.0.x"
+            javaVersion: "17"
+            mvnProfiles: "-Pjava17"
+          - scalaProfile: "scala-2.13"
+            sparkProfile: "spark4.1"
+            sparkModules: "hudi-spark-datasource/hudi-spark4.1.x"
+            javaVersion: "17"
+            mvnProfiles: "-Pjava17"
+          - scalaProfile: "scala-2.13"
+            sparkProfile: "spark4.2"
+            sparkModules: "hudi-spark-datasource/hudi-spark4.2.x"
+            javaVersion: "17"
+            mvnProfiles: "-Pjava17"
+
+    steps:
+      - if: needs.changes.outputs.relevant == 'true'
+        uses: actions/checkout@v5
+      - name: Set up JDK ${{ matrix.javaVersion }}
+        if: needs.changes.outputs.relevant == 'true'
+        uses: actions/setup-java@v5
+        with:
+          java-version: "${{ matrix.javaVersion }}"
+          distribution: 'temurin'
+          architecture: x64
+          cache: maven
+      - name: Build Project
+        if: needs.changes.outputs.relevant == 'true'
+        env:
+          SCALA_PROFILE: ${{ matrix.scalaProfile }}
+          SPARK_PROFILE: ${{ matrix.sparkProfile }}
+          SPARK_MODULES: ${{ matrix.sparkModules }}
+          MVN_PROFILES: ${{ matrix.mvnProfiles }}
+        run:
+          mvn clean install -T 2 $MVN_PROFILES -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DskipTests=true $MVN_ARGS -am -pl "hudi-examples/hudi-examples-spark,hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES"
+      - name: Core Tests - Common & Spark
+        if: needs.changes.outputs.relevant == 'true'
+        env:
+          SCALA_PROFILE: ${{ matrix.scalaProfile }}
+          SPARK_PROFILE: ${{ matrix.sparkProfile }}
+          SPARK_MODULES: ${{ matrix.sparkModules }}
+          MVN_PROFILES: ${{ matrix.mvnProfiles }}
+        run:
+          mvn test -Pcore-tests $MVN_PROFILES -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -fae -pl "hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS -Djacoco.skip=false
+      - name: Quickstart Test
+        if: needs.changes.outputs.relevant == 'true'
+        env:
+          SCALA_PROFILE: ${{ matrix.scalaProfile }}
+          SPARK_PROFILE: ${{ matrix.sparkProfile }}
+          MVN_PROFILES: ${{ matrix.mvnProfiles }}
+        run:
+          mvn test -Punit-tests $MVN_PROFILES -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -pl hudi-examples/hudi-examples-spark $MVN_ARGS -Djacoco.skip=false
+      - name: Generate merged coverage report
+        if: always() && needs.changes.outputs.relevant == 'true'
+        run: ./scripts/jacoco/generate_merged_coverage_report.sh $GITHUB_WORKSPACE
+      - name: Upload coverage to Codecov
+        if: always() && needs.changes.outputs.relevant == 'true'
+        uses: codecov/codecov-action@75cd11691c0faa626561e295848008c8a7dddffe # v5
+        with:
+          files: ./jacoco-report.xml
+          disable_search: true
+          flags: spark-core-tests
+          token: ${{ secrets.CODECOV_TOKEN }}
+
   test-flink-1:
     runs-on: ubuntu-latest
     needs: changes

diff --git a/hudi-spark-datasource/hudi-spark/pom.xml b/hudi-spark-datasource/hudi-spark/pom.xml
@@ -116,7 +116,7 @@
         <groupId>org.scalatest</groupId>
         <artifactId>scalatest-maven-plugin</artifactId>
         <configuration>
-          <tagsToExclude>org.apache.hudi.functional.SparkSQLCoreFlow</tagsToExclude>
+          <tagsToExclude>${hoodie.scalatest.tagsToExclude}</tagsToExclude>
         </configuration>
       </plugin>
       <plugin>

diff --git a/...rk-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestSparkOrcReader.java b/...rk-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestSparkOrcReader.java
@@ -31,6 +31,7 @@
 import static org.junit.jupiter.api.Assertions.assertEquals;
 
 @Tag("functional")
+@Tag("core")
 public class TestSparkOrcReader extends TestBootstrapReadBase {
 
   @Test

diff --git a/...atasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestSparkParquetReader.java b/...atasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestSparkParquetReader.java
@@ -31,6 +31,7 @@
 import static org.junit.jupiter.api.Assertions.assertEquals;
 
 @Tag("functional")
+@Tag("core")
 public class TestSparkParquetReader extends TestBootstrapReadBase {
 
   @Test

diff --git a/...park/src/test/java/org/apache/hudi/io/storage/row/TestHoodieInternalRowParquetWriter.java b/...park/src/test/java/org/apache/hudi/io/storage/row/TestHoodieInternalRowParquetWriter.java
@@ -42,6 +42,7 @@
 import org.apache.spark.sql.types.StructType;
 import org.junit.jupiter.api.AfterEach;
 import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Tag;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.ValueSource;
 
@@ -56,6 +57,7 @@
 /**
  * Unit tests {@link HoodieInternalRowParquetWriter}.
  */
+@Tag("core")
 public class TestHoodieInternalRowParquetWriter extends HoodieSparkClientTestHarness {
 
   @BeforeEach

diff --git a/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/CoreFlow.scala b/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/CoreFlow.scala
@@ -0,0 +1,34 @@
+/*
+ * 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.hudi.functional
+
+import org.scalatest.Tag
+
+/**
+ * ScalaTest tag for the curated "core flow" subset that runs on every Spark
+ * version in CI (via the {@code core-tests} Maven profile), as opposed to the
+ * full suite that runs only on the latest Spark major versions.
+ *
+ * The tag name matches the {@link SparkSQLCoreFlow} Java {@code @TagAnnotation}
+ * so that class-level {@code @SparkSQLCoreFlow} and per-test
+ * {@code taggedAs(CoreFlow)} are selected by the same scalatest
+ * {@code tagsToInclude}/{@code tagsToExclude} value.
+ */
+object CoreFlow extends Tag("org.apache.hudi.functional.SparkSQLCoreFlow")
diff --git a/...k-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestCOWDataSource.scala b/...k-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestCOWDataSource.scala
@@ -55,7 +55,7 @@ import org.apache.spark.sql.hudi.HoodieSparkSessionExtension
 import org.apache.spark.sql.types.{ArrayType, DataTypes, DateType, IntegerType, LongType, MapType, StringType, StructField, StructType, TimestampType}
 import org.joda.time.DateTime
 import org.joda.time.format.DateTimeFormat
-import org.junit.jupiter.api.{AfterEach, BeforeEach, Disabled, Test}
+import org.junit.jupiter.api.{AfterEach, BeforeEach, Disabled, Tag, Test}
 import org.junit.jupiter.api.Assertions.{assertDoesNotThrow, assertEquals, assertFalse, assertTrue, fail}
 import org.junit.jupiter.api.function.Executable
 import org.junit.jupiter.params.ParameterizedTest
@@ -800,6 +800,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
     assertEquals(schema, actualSchema)
   }
 
+  @Tag("core")
   @ParameterizedTest
   @EnumSource(value = classOf[HoodieRecordType], names = Array("AVRO", "SPARK"))
   def testCopyOnWriteDeletes(recordType: HoodieRecordType): Unit = {
@@ -831,6 +832,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
     assertEquals(snapshotDF2.count(), 80)
   }
 
+  @Tag("core")
   @Test
   def testCopyOnWriteUpserts(): Unit = {
     val recordType = HoodieRecordType.AVRO
@@ -1217,6 +1219,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
     assertEquals(hoodieIncViewDF2.count(), insert2NewKeyCnt)
   }
 
+  @Tag("core")
   @ParameterizedTest
   @EnumSource(value = classOf[HoodieRecordType], names = Array("AVRO", "SPARK"))
   def testComplexDataTypeWriteAndReadConsistency(recordType: HoodieRecordType): Unit = {
@@ -1549,6 +1552,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
     assertEquals(false, Metrics.isInitialized(basePath))
   }
 
+  @Tag("core")
   @ParameterizedTest
   @CsvSource(Array(
     "true,false,AVRO", "true,true,AVRO", "false,true,AVRO", "false,false,AVRO"
@@ -1967,6 +1971,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
   }
 
   /** Test case to verify MAKE_NEW_COLUMNS_NULLABLE config parameter. */
+  @Tag("core")
   @Test
   def testSchemaEvolutionWithNewColumn(): Unit = {
     val df1 = spark.sql("select '1' as event_id, '2' as ts, '3' as version, 'foo' as event_date")
@@ -2263,6 +2268,7 @@ class TestCOWDataSource extends HoodieSparkClientTestBase with ScalaAssertionSup
    * - v6: Uses requestedTime for commits, open_close incremental ranges
    * - v9: Uses completionTime for commits, close_close incremental ranges
    */
+  @Tag("core")
   @ParameterizedTest
   @CsvSource(Array("6", "9"))
   def testIncrementalAndTimeTravelWithEventTimeOrdering(tableVersion: String): Unit = {