From 30fe595df4fc8ced0c45efde4d186a5a6c29d428 Mon Sep 17 00:00:00 2001 From: yangjie01 Date: Mon, 4 Aug 2025 10:48:44 +0800 Subject: [PATCH 1/4] init --- .github/workflows/build_java21.yml | 3 ++- .github/workflows/build_non_ansi.yml | 1 + .../org/apache/spark/util/sketch/SparkBloomFilterSuite.java | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/.github/workflows/build_java21.yml b/.github/workflows/build_java21.yml index c9a6ed270546c..68049422d59cb 100644 --- a/.github/workflows/build_java21.yml +++ b/.github/workflows/build_java21.yml @@ -41,7 +41,8 @@ jobs: "PYTHON_TO_TEST": "python3.11", "SKIP_MIMA": "true", "SKIP_UNIDOC": "true", - "DEDICATED_JVM_SBT_TESTS": "org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV1Suite,org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV2Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV1Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV2Suite" + "DEDICATED_JVM_SBT_TESTS": "org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV1Suite,org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV2Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV1Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV2Suite", + "SPARK_TEST_SPARK_BF_SUITE_ENABLED": "true" } jobs: >- { diff --git a/.github/workflows/build_non_ansi.yml b/.github/workflows/build_non_ansi.yml index 547a227e61d7e..36cfd84f21ed3 100644 --- a/.github/workflows/build_non_ansi.yml +++ b/.github/workflows/build_non_ansi.yml @@ -40,6 +40,7 @@ jobs: "PYSPARK_IMAGE_TO_TEST": "python-311", "PYTHON_TO_TEST": "python3.11", "SPARK_ANSI_SQL_MODE": "false", + "SPARK_TEST_SPARK_BF_SUITE_ENABLED": "true" } jobs: >- { diff --git a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java index 529ba54193387..c5f9e863d0a43 100644 --- a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java +++ b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java @@ -18,6 +18,7 @@ package org.apache.spark.util.sketch; import org.junit.jupiter.api.*; +import org.junit.jupiter.api.condition.EnabledIfEnvironmentVariable; import org.junit.jupiter.params.ParameterizedTest; import org.junit.jupiter.params.provider.Arguments; import org.junit.jupiter.params.provider.MethodSource; @@ -33,7 +34,7 @@ import java.util.stream.LongStream; import java.util.stream.Stream; -@Disabled("TODO(SPARK-53077): Re-enable with a resonable test time.") +@EnabledIfEnvironmentVariable(named = "SPARK_TEST_SPARK_BF_SUITE_ENABLED", matches = "true") public class SparkBloomFilterSuite { // the implemented fpp limit is only approximating the hard boundary, From 40c123ec258029195245bc0ea190e77990b612d2 Mon Sep 17 00:00:00 2001 From: yangjie01 Date: Mon, 4 Aug 2025 13:20:06 +0800 Subject: [PATCH 2/4] address commments --- .github/workflows/build_java21.yml | 3 +-- .github/workflows/build_non_ansi.yml | 2 +- .../org/apache/spark/util/sketch/SparkBloomFilterSuite.java | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/.github/workflows/build_java21.yml b/.github/workflows/build_java21.yml index 68049422d59cb..c9a6ed270546c 100644 --- a/.github/workflows/build_java21.yml +++ b/.github/workflows/build_java21.yml @@ -41,8 +41,7 @@ jobs: "PYTHON_TO_TEST": "python3.11", "SKIP_MIMA": "true", "SKIP_UNIDOC": "true", - "DEDICATED_JVM_SBT_TESTS": "org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV1Suite,org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV2Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV1Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV2Suite", - "SPARK_TEST_SPARK_BF_SUITE_ENABLED": "true" + "DEDICATED_JVM_SBT_TESTS": "org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV1Suite,org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormatV2Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV1Suite,org.apache.spark.sql.execution.datasources.orc.OrcSourceV2Suite" } jobs: >- { diff --git a/.github/workflows/build_non_ansi.yml b/.github/workflows/build_non_ansi.yml index 36cfd84f21ed3..debdaf4f8709d 100644 --- a/.github/workflows/build_non_ansi.yml +++ b/.github/workflows/build_non_ansi.yml @@ -40,7 +40,7 @@ jobs: "PYSPARK_IMAGE_TO_TEST": "python-311", "PYTHON_TO_TEST": "python3.11", "SPARK_ANSI_SQL_MODE": "false", - "SPARK_TEST_SPARK_BF_SUITE_ENABLED": "true" + "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED": "true" } jobs: >- { diff --git a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java index c5f9e863d0a43..04657137bfd78 100644 --- a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java +++ b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java @@ -34,7 +34,7 @@ import java.util.stream.LongStream; import java.util.stream.Stream; -@EnabledIfEnvironmentVariable(named = "SPARK_TEST_SPARK_BF_SUITE_ENABLED", matches = "true") +@EnabledIfEnvironmentVariable(named = "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED", matches = "true") public class SparkBloomFilterSuite { // the implemented fpp limit is only approximating the hard boundary, From 6307c8f6f7ff92281a456df48989a2fc5eaf73bd Mon Sep 17 00:00:00 2001 From: yangjie01 Date: Mon, 4 Aug 2025 14:47:56 +0800 Subject: [PATCH 3/4] fix format --- .../org/apache/spark/util/sketch/SparkBloomFilterSuite.java | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java index 04657137bfd78..751eb6763b785 100644 --- a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java +++ b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java @@ -34,7 +34,8 @@ import java.util.stream.LongStream; import java.util.stream.Stream; -@EnabledIfEnvironmentVariable(named = "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED", matches = "true") +@EnabledIfEnvironmentVariable( + named = "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED", matches = "true") public class SparkBloomFilterSuite { // the implemented fpp limit is only approximating the hard boundary, From c54984a921e8299b297d0c9e8e13966ab11281b6 Mon Sep 17 00:00:00 2001 From: yangjie01 Date: Mon, 4 Aug 2025 14:54:30 +0800 Subject: [PATCH 4/4] format --- .../org/apache/spark/util/sketch/SparkBloomFilterSuite.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java index 751eb6763b785..a7186853edfc6 100644 --- a/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java +++ b/common/sketch/src/test/java/org/apache/spark/util/sketch/SparkBloomFilterSuite.java @@ -35,7 +35,7 @@ import java.util.stream.Stream; @EnabledIfEnvironmentVariable( - named = "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED", matches = "true") + named = "SPARK_TEST_SPARK_BLOOM_FILTER_SUITE_ENABLED", matches = "true") public class SparkBloomFilterSuite { // the implemented fpp limit is only approximating the hard boundary,