YuweiXiao commented on code in PR #4480:
URL: https://github.com/apache/hudi/pull/4480#discussion_r866536775
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/index/bucket/BucketIdentifier.java:
##########
@@ -22,41 +22,50 @@
import org.apache.hudi.common.model.HoodieKey;
import org.apache.hudi.common.model.HoodieRecord;
+import java.io.Serializable;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
-public class BucketIdentifier {
- // compatible with the spark bucket name
+public class BucketIdentifier implements Serializable {
+ // Compatible with the spark bucket name
private static final Pattern BUCKET_NAME =
Pattern.compile(".*_(\\d+)(?:\\..*)?$");
public static int getBucketId(HoodieRecord record, String indexKeyFields,
int numBuckets) {
return getBucketId(record.getKey(), indexKeyFields, numBuckets);
}
public static int getBucketId(HoodieKey hoodieKey, String indexKeyFields,
int numBuckets) {
- return getBucketId(hoodieKey.getRecordKey(), indexKeyFields, numBuckets);
+ return (getHashKeys(hoodieKey, indexKeyFields).hashCode() &
Integer.MAX_VALUE) % numBuckets;
}
public static int getBucketId(String recordKey, String indexKeyFields, int
numBuckets) {
- List<String> hashKeyFields;
+ return (getHashKeys(recordKey, indexKeyFields).hashCode() &
Integer.MAX_VALUE) % numBuckets;
+ }
+
+ public static List<String> getHashKeys(HoodieKey hoodieKey, String
indexKeyFields) {
+ return getHashKeys(hoodieKey.getRecordKey(), indexKeyFields);
+ }
+
+ protected static List<String> getHashKeys(String recordKey, String
indexKeyFields) {
+ List<String> hashKeys;
if (!recordKey.contains(":")) {
- hashKeyFields = Collections.singletonList(recordKey);
+ hashKeys = Collections.singletonList(recordKey);
} else {
Map<String, String> recordKeyPairs = Arrays.stream(recordKey.split(","))
.map(p -> p.split(":"))
.collect(Collectors.toMap(p -> p[0], p -> p[1]));
- hashKeyFields = Arrays.stream(indexKeyFields.split(","))
+ hashKeys = Arrays.stream(indexKeyFields.split(","))
.map(f -> recordKeyPairs.get(f))
.collect(Collectors.toList());
}
- return (hashKeyFields.hashCode() & Integer.MAX_VALUE) % numBuckets;
+ return hashKeys;
}
- // only for test
+ // Only for test
Review Comment:
The code is from the original simple bucket index implementation. I just
re-organized the code to remove this test-only function.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
