1
0

HUDI-243 Rename HoodieInputFormat and HoodieRealtimeInputFormat to HoodieParquetInputFormat and HoodieParquetRealtimeInputFormat

This commit is contained in:
Balaji Varadarajan
2019-09-11 11:31:07 -07:00
committed by vinoth chandar
parent d0b9b56b7d
commit 93bc5e2153
10 changed files with 31 additions and 27 deletions

View File

@@ -18,9 +18,11 @@
package com.uber.hoodie.hadoop;
import org.apache.hudi.hadoop.HoodieParquetInputFormat;
/**
* Temporary class to allow seamless migration of com.uber.hoodie to org.apache.hudi
*/
public class HoodieInputFormat extends org.apache.hudi.hadoop.HoodieInputFormat {
public class HoodieInputFormat extends HoodieParquetInputFormat {
}

View File

@@ -18,9 +18,11 @@
package com.uber.hoodie.hadoop.realtime;
import org.apache.hudi.hadoop.realtime.HoodieParquetRealtimeInputFormat;
/**
* Temporary class to allow seamless migration of com.uber.hoodie to org.apache.hudi
*/
public class HoodieRealtimeInputFormat extends org.apache.hudi.hadoop.realtime.HoodieRealtimeInputFormat {
public class HoodieRealtimeInputFormat extends HoodieParquetRealtimeInputFormat {
}

View File

@@ -57,9 +57,9 @@ import org.apache.log4j.Logger;
* Hoodie/Non-Hoodie datasets
*/
@UseFileSplitsFromInputFormat
public class HoodieInputFormat extends MapredParquetInputFormat implements Configurable {
public class HoodieParquetInputFormat extends MapredParquetInputFormat implements Configurable {
private static final transient Logger LOG = LogManager.getLogger(HoodieInputFormat.class);
private static final transient Logger LOG = LogManager.getLogger(HoodieParquetInputFormat.class);
protected Configuration conf;

View File

@@ -70,8 +70,8 @@ import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.lib.CombineFileInputFormat;
import org.apache.hadoop.mapred.lib.CombineFileSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hudi.hadoop.HoodieInputFormat;
import org.apache.hudi.hadoop.realtime.HoodieRealtimeInputFormat;
import org.apache.hudi.hadoop.HoodieParquetInputFormat;
import org.apache.hudi.hadoop.realtime.HoodieParquetRealtimeInputFormat;
import org.apache.log4j.LogManager;
import org.apache.log4j.Logger;
@@ -403,9 +403,9 @@ public class HoodieCombineHiveInputFormat<K extends WritableComparable, V extend
InputFormat inputFormat = getInputFormatFromCache(inputFormatClass, job);
LOG.info("Input Format => " + inputFormatClass.getName());
// **MOD** Set the hoodie filter in the combine
if (inputFormatClass.getName().equals(HoodieInputFormat.class.getName())) {
if (inputFormatClass.getName().equals(HoodieParquetInputFormat.class.getName())) {
combine.setHoodieFilter(true);
} else if (inputFormatClass.getName().equals(HoodieRealtimeInputFormat.class.getName())) {
} else if (inputFormatClass.getName().equals(HoodieParquetRealtimeInputFormat.class.getName())) {
LOG.info("Setting hoodie filter and realtime input format");
combine.setHoodieFilter(true);
combine.setRealTime(true);
@@ -857,13 +857,13 @@ public class HoodieCombineHiveInputFormat<K extends WritableComparable, V extend
LOG.info("Listing status in HoodieCombineHiveInputFormat.HoodieCombineFileInputFormatShim");
List<FileStatus> result;
if (hoodieFilter) {
HoodieInputFormat input;
HoodieParquetInputFormat input;
if (isRealTime) {
LOG.info("Using HoodieRealtimeInputFormat");
input = new HoodieRealtimeInputFormat();
input = new HoodieParquetRealtimeInputFormat();
} else {
LOG.info("Using HoodieInputFormat");
input = new HoodieInputFormat();
input = new HoodieParquetInputFormat();
}
input.setConf(job.getConfiguration());
result = new ArrayList<FileStatus>(

View File

@@ -52,7 +52,7 @@ import org.apache.hudi.common.util.FSUtils;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.exception.HoodieException;
import org.apache.hudi.exception.HoodieIOException;
import org.apache.hudi.hadoop.HoodieInputFormat;
import org.apache.hudi.hadoop.HoodieParquetInputFormat;
import org.apache.hudi.hadoop.UseFileSplitsFromInputFormat;
import org.apache.log4j.LogManager;
import org.apache.log4j.Logger;
@@ -61,9 +61,9 @@ import org.apache.log4j.Logger;
* Input Format, that provides a real-time view of data in a Hoodie dataset
*/
@UseFileSplitsFromInputFormat
public class HoodieRealtimeInputFormat extends HoodieInputFormat implements Configurable {
public class HoodieParquetRealtimeInputFormat extends HoodieParquetInputFormat implements Configurable {
private static final transient Logger LOG = LogManager.getLogger(HoodieRealtimeInputFormat.class);
private static final transient Logger LOG = LogManager.getLogger(HoodieParquetRealtimeInputFormat.class);
// These positions have to be deterministic across all tables
public static final int HOODIE_COMMIT_TIME_COL_POS = 0;

View File

@@ -80,7 +80,7 @@ class RealtimeCompactedRecordReader extends AbstractRealtimeRecordReader impleme
// TODO(VC): Right now, we assume all records in log, have a matching base record. (which
// would be true until we have a way to index logs too)
// return from delta records map if we have some match.
String key = arrayWritable.get()[HoodieRealtimeInputFormat.HOODIE_RECORD_KEY_COL_POS]
String key = arrayWritable.get()[HoodieParquetRealtimeInputFormat.HOODIE_RECORD_KEY_COL_POS]
.toString();
if (deltaRecordMap.containsKey(key)) {
// TODO(NA): Invoke preCombine here by converting arrayWritable to Avro. This is required since the