lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

New Features in DeltaStreamer :

Browse Source 
(1) Apply transformation when using delta-streamer to ingest data.
 (2) Add Hudi Incremental Source for Delta Streamer
 (3) Allow delta-streamer config-property to be passed as command-line
 (4) Add Hive Integration to Delta-Streamer and address Review comments
 (5) Ensure MultiPartKeysValueExtractor  handle hive style partition description
 (6) Reuse same spark session on both source and transformer
 (7) Support extracting partition fields from _hoodie_partition_path for HoodieIncrSource
 (8) Reuse Binary Avro coders
 (9) Add push down filter for Incremental source
 (10) Add Hoodie DeltaStreamer metrics to track total time taken
This commit is contained in:
Balaji Varadarajan
2018-10-10 10:31:34 -07:00
committed by vinoth chandar
parent c70dbc13e9
commit 3a0044216c
65 changed files with 2752 additions and 911 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
hoodie-spark/src/main/java/com/uber/hoodie/DataSourceUtils.java
View File

@@ -29,8 +29,13 @@ import com.uber.hoodie.config.HoodieWriteConfig;
import com.uber.hoodie.exception.DatasetNotFoundException;
import com.uber.hoodie.exception.HoodieException;
import com.uber.hoodie.exception.HoodieNotSupportedException;
import com.uber.hoodie.hive.HiveSyncConfig;
import com.uber.hoodie.hive.PartitionValueExtractor;
import com.uber.hoodie.hive.SlashEncodedDayPartitionValueExtractor;
import com.uber.hoodie.index.HoodieIndex;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
@@ -86,6 +91,17 @@ public class DataSourceUtils {
}
}
/**
* Create a partition value extractor class via reflection, passing in any configs needed
*/
public static PartitionValueExtractor createPartitionExtractor(String partitionExtractorClass) {
try {
return (PartitionValueExtractor) ReflectionUtils.loadClass(partitionExtractorClass);
} catch (Throwable e) {
throw new HoodieException("Could not load partition extractor class " + partitionExtractorClass, e);
}
}
/**
* Create a payload class via reflection, passing in an ordering/precombine value.
*/
@@ -169,4 +185,28 @@ public class DataSourceUtils {
.withProps(parameters).build();
return dropDuplicates(jssc, incomingHoodieRecords, writeConfig);
}
public static HiveSyncConfig buildHiveSyncConfig(TypedProperties props, String basePath) {
checkRequiredProperties(props, Arrays.asList(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY()));
HiveSyncConfig hiveSyncConfig = new HiveSyncConfig();
hiveSyncConfig.basePath = basePath;
hiveSyncConfig.assumeDatePartitioning =
props.getBoolean(DataSourceWriteOptions.HIVE_ASSUME_DATE_PARTITION_OPT_KEY(),
Boolean.valueOf(DataSourceWriteOptions.DEFAULT_HIVE_ASSUME_DATE_PARTITION_OPT_VAL()));
hiveSyncConfig.databaseName = props.getString(DataSourceWriteOptions.HIVE_DATABASE_OPT_KEY(),
DataSourceWriteOptions.DEFAULT_HIVE_DATABASE_OPT_VAL());
hiveSyncConfig.tableName = props.getString(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY());
hiveSyncConfig.hiveUser = props.getString(DataSourceWriteOptions.HIVE_USER_OPT_KEY(),
DataSourceWriteOptions.DEFAULT_HIVE_USER_OPT_VAL());
hiveSyncConfig.hivePass = props.getString(DataSourceWriteOptions.HIVE_PASS_OPT_KEY(),
DataSourceWriteOptions.DEFAULT_HIVE_PASS_OPT_VAL());
hiveSyncConfig.jdbcUrl = props.getString(DataSourceWriteOptions.HIVE_URL_OPT_KEY(),
DataSourceWriteOptions.DEFAULT_HIVE_URL_OPT_VAL());
hiveSyncConfig.partitionFields =
props.getStringList(DataSourceWriteOptions.HIVE_PARTITION_FIELDS_OPT_KEY(), ",", new ArrayList<>());
hiveSyncConfig.partitionValueExtractorClass =
props.getString(DataSourceWriteOptions.HIVE_PARTITION_EXTRACTOR_CLASS_OPT_KEY(),
SlashEncodedDayPartitionValueExtractor.class.getName());
return hiveSyncConfig;
}
}