manojpec commented on a change in pull request #4352:
URL: https://github.com/apache/hudi/pull/4352#discussion_r793425309
##########
File path:
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/metadata/SparkHoodieBackedTableMetadataWriter.java
##########
@@ -171,17 +172,34 @@ protected void commit(HoodieData<HoodieRecord>
hoodieDataRecords, String partiti
/**
* Tag each record with the location in the given partition.
- *
+ * <p>
* The record is tagged with respective file slice's location based on its
record key.
*/
- private JavaRDD<HoodieRecord> prepRecords(JavaRDD<HoodieRecord> recordsRDD,
String partitionName, int numFileGroups) {
- List<FileSlice> fileSlices =
HoodieTableMetadataUtil.getPartitionLatestFileSlices(metadataMetaClient,
partitionName);
- ValidationUtils.checkArgument(fileSlices.size() == numFileGroups,
String.format("Invalid number of file groups: found=%d, required=%d",
fileSlices.size(), numFileGroups));
-
- return recordsRDD.map(r -> {
- FileSlice slice =
fileSlices.get(HoodieTableMetadataUtil.mapRecordKeyToFileGroupIndex(r.getRecordKey(),
numFileGroups));
- r.setCurrentLocation(new
HoodieRecordLocation(slice.getBaseInstantTime(), slice.getFileId()));
- return r;
- });
+ private JavaRDD<HoodieRecord> prepRecords(Map<MetadataPartitionType,
HoodieData<HoodieRecord>> partitionRecordsMap) {
+ // The result set
+ JavaRDD<HoodieRecord> rddAllPartitionRecords = ((HoodieSparkEngineContext)
engineContext).getJavaSparkContext().emptyRDD();
+
+ for (Map.Entry<MetadataPartitionType, HoodieData<HoodieRecord>> entry :
partitionRecordsMap.entrySet()) {
+ final String partitionName = entry.getKey().getPartitionPath();
+ final int fileGroupCount = entry.getKey().getFileGroupCount();
Review comment:
Fixed this.
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/config/HoodieMetadataConfig.java
##########
@@ -157,6 +197,26 @@ public boolean enabled() {
return getBoolean(ENABLE);
}
+ public boolean isMetadataIndexBloomFilterEnabled() {
+ return getBooleanOrDefault(ENABLE_METADATA_INDEX_BLOOM_FILTER);
+ }
+
+ public boolean isMetadataIndexColumnStatsEnabled() {
+ return getBooleanOrDefault(ENABLE_METADATA_INDEX_COLUMN_STATS);
+ }
+
+ public boolean isMetadataIndexColumnStatsForAllColumns() {
Review comment:
fixed.
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/config/HoodieMetadataConfig.java
##########
@@ -157,6 +197,26 @@ public boolean enabled() {
return getBoolean(ENABLE);
}
+ public boolean isMetadataIndexBloomFilterEnabled() {
Review comment:
fixed.
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/config/HoodieMetadataConfig.java
##########
@@ -199,6 +259,16 @@ public Builder enable(boolean enable) {
return this;
}
+ public Builder withMetadataIndexBloomFilter(boolean enable) {
Review comment:
fixed
--
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: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
