lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-4140] Fixing hive style partitioning and default partition with bulk insert row writer with SimpleKeyGen and virtual keys (#5664)

Browse Source 
Bulk insert row writer code path had a gap wrt hive style partitioning and default partition when virtual keys are enabled with SimpleKeyGen.  This patch fixes the issue.
This commit is contained in:
Sivabalan Narayanan
2022-06-06 13:21:00 -04:00
committed by GitHub
parent 4f7ea8c79a
commit 4f6fc726d0
4 changed files with 63 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/internal/BulkInsertDataInternalWriterHelper.java
View File

@@ -23,6 +23,7 @@ import org.apache.hudi.client.HoodieInternalWriteStatus;
import org.apache.hudi.common.config.TypedProperties;
import org.apache.hudi.common.model.HoodieRecord;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.PartitionPathEncodeUtils;
import org.apache.hudi.config.HoodieWriteConfig;
import org.apache.hudi.exception.HoodieIOException;
import org.apache.hudi.io.storage.row.HoodieRowCreateHandle;
@@ -128,7 +129,11 @@ public class BulkInsertDataInternalWriterHelper {
if (!keyGeneratorOpt.isPresent()) { // NoPartitionerKeyGen
partitionPath = "";
} else if (simpleKeyGen) { // SimpleKeyGen
partitionPath = (record.get(simplePartitionFieldIndex, simplePartitionFieldDataType)).toString();
Object parititionPathValue = record.get(simplePartitionFieldIndex, simplePartitionFieldDataType);
partitionPath = parititionPathValue != null ? parititionPathValue.toString() : PartitionPathEncodeUtils.DEFAULT_PARTITION_PATH;
if (writeConfig.isHiveStylePartitioningEnabled()) {
partitionPath = (keyGeneratorOpt.get()).getPartitionPathFields().get(0) + "=" + partitionPath;
}
} else {
// only BuiltIn key generators are supported if meta fields are disabled.
partitionPath = keyGeneratorOpt.get().getPartitionPath(record, structType);

5
hudi-spark-datasource/hudi-spark-common/src/test/java/org/apache/hudi/internal/HoodieBulkInsertInternalWriterTestBase.java
View File

@@ -70,6 +70,10 @@ public class HoodieBulkInsertInternalWriterTestBase extends HoodieClientTestHarn
}
protected HoodieWriteConfig getWriteConfig(boolean populateMetaFields) {
return getWriteConfig(populateMetaFields, DataSourceWriteOptions.HIVE_STYLE_PARTITIONING().defaultValue());
}
protected HoodieWriteConfig getWriteConfig(boolean populateMetaFields, String hiveStylePartitioningValue) {
Properties properties = new Properties();
if (!populateMetaFields) {
properties.setProperty(DataSourceWriteOptions.KEYGENERATOR_CLASS_NAME().key(), SimpleKeyGenerator.class.getName());
@@ -77,6 +81,7 @@ public class HoodieBulkInsertInternalWriterTestBase extends HoodieClientTestHarn
properties.setProperty(DataSourceWriteOptions.PARTITIONPATH_FIELD().key(), SparkDatasetTestUtils.PARTITION_PATH_FIELD_NAME);
properties.setProperty(HoodieTableConfig.POPULATE_META_FIELDS.key(), "false");
}
properties.setProperty(DataSourceWriteOptions.HIVE_STYLE_PARTITIONING().key(), hiveStylePartitioningValue);
return getConfigBuilder(basePath, timelineServicePort).withProperties(properties).build();
}