lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

Implement Merge on Read Storage (#76)

Browse Source 
1. Create HoodieTable abstraction for commits and fileSystemView
2. HoodieMergeOnReadTable created
3. View is now always obtained from the table and the correct view based on the table type is returned
This commit is contained in:
prazanna
2017-02-21 15:24:00 -08:00
committed by Prasanna Rajaperumal
parent 11d2fd3428
commit eb46e7c72b
47 changed files with 1113 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
hoodie-hadoop-mr/src/main/java/com/uber/hoodie/hadoop/HoodieInputFormat.java
View File

@@ -22,8 +22,7 @@ import com.uber.hoodie.common.table.HoodieTableMetaClient;
import com.uber.hoodie.common.table.HoodieTimeline;
import com.uber.hoodie.common.table.TableFileSystemView;
import com.uber.hoodie.common.table.timeline.HoodieInstant;
import com.uber.hoodie.common.table.view.ReadOptimizedTableView;
import com.uber.hoodie.common.util.FSUtils;
import com.uber.hoodie.common.table.view.HoodieTableFileSystemView;
import com.uber.hoodie.exception.InvalidDatasetException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
@@ -95,8 +94,9 @@ public class HoodieInputFormat extends MapredParquetInputFormat
LOG.info("Hoodie Metadata initialized with completed commit Ts as :" + metadata);
String tableName = metadata.getTableConfig().getTableName();
String mode = HoodieHiveUtil.readMode(Job.getInstance(job), tableName);
TableFileSystemView fsView = new ReadOptimizedTableView(FSUtils.getFs(), metadata);
HoodieTimeline timeline = metadata.getActiveTimeline().getCommitTimeline().filterCompletedInstants();
TableFileSystemView fsView = new HoodieTableFileSystemView(metadata, timeline);
if (HoodieHiveUtil.INCREMENTAL_SCAN_MODE.equals(mode)) {
// this is of the form commitTs_partition_sequenceNumber
String lastIncrementalTs = HoodieHiveUtil.readStartCommitTime(Job.getInstance(job), tableName);