danny0405 commented on code in PR #12132:
URL: https://github.com/apache/hudi/pull/12132#discussion_r1814088198
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/source/TestIncrementalInputSplits.java:
##########
@@ -348,6 +358,51 @@ void testInputSplitsWithPartitionPruner(
assertEquals(expectedPartitions, partitions);
}
+ @Test
+ void testInputSplitsWithPartitionStatsPruner() throws Exception {
+ Configuration conf = TestConfigurations.getDefaultConf(basePath);
+ conf.set(FlinkOptions.READ_AS_STREAMING, true);
+ conf.set(FlinkOptions.READ_DATA_SKIPPING_ENABLED, true);
+
conf.setBoolean(HoodieMetadataConfig.ENABLE_METADATA_INDEX_PARTITION_STATS.key(),
true);
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+
+ // uuid > 'id5' and age < 30, only column stats of 'par3' matches the
filter.
+ ColumnStatsProbe columnStatsProbe =
+ ColumnStatsProbe.newInstance(Arrays.asList(
+ new CallExpression(
+ FunctionIdentifier.of("greaterThan"),
+ BuiltInFunctionDefinitions.GREATER_THAN,
+ Arrays.asList(
+ new FieldReferenceExpression("uuid", DataTypes.STRING(),
0, 0),
+ new ValueLiteralExpression("id5",
DataTypes.STRING().notNull())
+ ),
+ DataTypes.BOOLEAN()),
+ new CallExpression(
+ FunctionIdentifier.of("lessThan"),
+ BuiltInFunctionDefinitions.LESS_THAN,
+ Arrays.asList(
+ new FieldReferenceExpression("age", DataTypes.INT(), 2, 2),
+ new ValueLiteralExpression(30, DataTypes.INT().notNull())
+ ),
+ DataTypes.BOOLEAN())));
+
+ PartitionPruners.PartitionPruner partitionPruner =
+
PartitionPruners.builder().rowType(TestConfigurations.ROW_TYPE).basePath(basePath).conf(conf).columnStatsProbe(columnStatsProbe).build();
+ IncrementalInputSplits iis = IncrementalInputSplits.builder()
+ .conf(conf)
+ .path(new Path(basePath))
+ .rowType(TestConfigurations.ROW_TYPE)
+ .partitionPruner(partitionPruner)
+ .build();
+ metaClient = HoodieTableMetaClient.builder()
Review Comment:
can we use `HoodieTestUtils.init(basePath, HoodieTableType.COPY_ON_WRITE)`
here?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
