danny0405 commented on code in PR #13017:
URL: https://github.com/apache/hudi/pull/13017#discussion_r2015267065
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/table/ITTestHoodieDataSource.java:
##########
@@ -1258,6 +1266,75 @@ void testBulkInsert(String indexType, boolean
hiveStylePartitioning) {
+ "+I[id8, Han, 56, 1970-01-01T00:00:08, par4]]");
}
+ @ParameterizedTest
+ @MethodSource("testBulkInsertWithPartitionBucketIndex")
+ void testBulkInsertWithPartitionBucketIndex(String operationType, String
tableType) throws IOException {
+ TableEnvironment tableEnv = batchTableEnv;
+ // csv source
+ String csvSourceDDL = TestConfigurations.getCsvSourceDDL("csv_source",
"test_source_5.data");
+ tableEnv.executeSql(csvSourceDDL);
+ String catalogName = "hudi_" + operationType;
+ String hudiCatalogDDL = catalog(catalogName)
+ .catalogPath(tempFile.getAbsolutePath())
+ .end();
+
+ tableEnv.executeSql(hudiCatalogDDL);
+ String dbName = "hudi";
+ tableEnv.executeSql("create database " + catalogName + "." + dbName);
+ String basePath = tempFile.getAbsolutePath() + "/hudi/hoodie_sink";
+
+ String hoodieTableDDL = sql(catalogName + ".hudi.hoodie_sink")
+ .option(FlinkOptions.PATH, basePath)
+ .option(FlinkOptions.TABLE_TYPE, tableType)
+ .option(FlinkOptions.OPERATION, operationType)
+ .option(FlinkOptions.WRITE_BULK_INSERT_SHUFFLE_INPUT, true)
+ .option(FlinkOptions.INDEX_TYPE, "BUCKET")
+ .option(FlinkOptions.HIVE_STYLE_PARTITIONING, "true")
+ .option(FlinkOptions.BUCKET_INDEX_NUM_BUCKETS, "1")
+ .option(FlinkOptions.BUCKET_INDEX_PARTITION_RULE, "regex")
+ .option(FlinkOptions.BUCKET_INDEX_PARTITION_EXPRESSIONS,
"partition=(par1|par2),2")
+ .end();
+ tableEnv.executeSql(hoodieTableDDL);
+
+ String insertInto = "insert into " + catalogName + ".hudi.hoodie_sink
select * from csv_source";
+ execInsertSql(tableEnv, insertInto);
+
+ List<Row> result1 = CollectionUtil.iterableToList(
+ () -> tableEnv.sqlQuery("select * from " + catalogName +
".hudi.hoodie_sink").execute().collect());
+ assertRowsEquals(result1, TestData.DATA_SET_SOURCE_INSERT);
+ // apply filters
+ List<Row> result2 = CollectionUtil.iterableToList(
+ () -> tableEnv.sqlQuery("select * from " + catalogName +
".hudi.hoodie_sink where uuid > 'id5'").execute().collect());
+ assertRowsEquals(result2, "["
+ + "+I[id6, Emma, 20, 1970-01-01T00:00:06, par3], "
+ + "+I[id7, Bob, 44, 1970-01-01T00:00:07, par4], "
+ + "+I[id8, Han, 56, 1970-01-01T00:00:08, par4]]");
+ HoodieTableMetaClient metaClient = StreamerUtil.createMetaClient(basePath,
new org.apache.hadoop.conf.Configuration());
+ List<String> actual =
PartitionBucketIndexUtils.getAllFileIDWithPartition(metaClient);
+
+ // based on expression partition=(par1|par2),2 and default bucket number 1
+ // par1 and par2 have two buckets.
+ // par3 and par4 have one bucket.
+ ArrayList<String> expected = new ArrayList<>();
+ expected.add("partition=par1" + "00000000");
+ expected.add("partition=par1" + "00000001");
+ expected.add("partition=par2" + "00000000");
+ expected.add("partition=par2" + "00000001");
+ expected.add("partition=par3" + "00000000");
+ expected.add("partition=par4" + "00000000");
+
+ assertEquals(expected.stream().sorted().collect(Collectors.toList()),
actual.stream().sorted().collect(Collectors.toList()));
+ }
+
+ public static List<Arguments> testBulkInsertWithPartitionBucketIndex() {
Review Comment:
-> testBulkInsertWithPartitionBucketIndexParams, and can we move it to the
bottom?
--
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]
