satishkotha commented on a change in pull request #2379:
URL: https://github.com/apache/hudi/pull/2379#discussion_r549824242
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/timeline/HoodieDefaultTimeline.java
##########
@@ -95,6 +95,13 @@ public HoodieTimeline filterPendingExcludingCompaction() {
&&
(!instant.getAction().equals(HoodieTimeline.COMPACTION_ACTION))), details);
}
+ @Override
+ public HoodieTimeline filterPendingExcludingCompactionAndClustering() {
+ return new HoodieDefaultTimeline(instants.stream().filter(instant ->
(!instant.isCompleted())
+ && (!instant.getAction().equals(HoodieTimeline.COMPACTION_ACTION))
+ &&
(!instant.getAction().equals(HoodieTimeline.REPLACE_COMMIT_ACTION))), details);
Review comment:
hmm, this is actually tricky. what if the replace_commit belongs to
insert_overwrite? We have to rollback insert_overwrite related replacecommits,
but not clustering related ones.
We could move this method out of timeline into a utils method and parse
content to filter only clustering instants.
##########
File path:
hudi-utilities/src/main/java/org/apache/hudi/utilities/deltastreamer/DeltaSync.java
##########
@@ -296,7 +296,9 @@ public void refreshTimeline() throws IOException {
// Retrieve the previous round checkpoints, if any
Option<String> resumeCheckpointStr = Option.empty();
if (commitTimelineOpt.isPresent()) {
- Option<HoodieInstant> lastCommit = commitTimelineOpt.get().lastInstant();
+ // TODO: now not support replace action
Review comment:
I think you created a ticket for this TODO? could you link the ticket
here?
##########
File path:
hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
##########
@@ -0,0 +1,152 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.utilities;
+
+import com.beust.jcommander.JCommander;
+import com.beust.jcommander.Parameter;
+import org.apache.avro.Schema;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hudi.client.SparkRDDWriteClient;
+import org.apache.hudi.client.WriteStatus;
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.List;
+
+public class HoodieClusteringJob {
+
+ private static final Logger LOG =
LogManager.getLogger(HoodieClusteringJob.class);
+ private final Config cfg;
+ private transient FileSystem fs;
+ private TypedProperties props;
+ private final JavaSparkContext jsc;
+
+ public HoodieClusteringJob(JavaSparkContext jsc, Config cfg) {
+ this.cfg = cfg;
+ this.jsc = jsc;
+ this.props = cfg.propsFilePath == null
+ ? UtilHelpers.buildProperties(cfg.configs)
+ : readConfigFromFileSystem(jsc, cfg);
+ }
+
+ private TypedProperties readConfigFromFileSystem(JavaSparkContext jsc,
Config cfg) {
+ final FileSystem fs = FSUtils.getFs(cfg.basePath,
jsc.hadoopConfiguration());
+
+ return UtilHelpers
+ .readConfig(fs, new Path(cfg.propsFilePath), cfg.configs)
+ .getConfig();
+ }
+
+ public static class Config implements Serializable {
+ @Parameter(names = {"--base-path", "-sp"}, description = "Base path for
the table", required = true)
+ public String basePath = null;
+ @Parameter(names = {"--table-name", "-tn"}, description = "Table name",
required = true)
+ public String tableName = null;
+ @Parameter(names = {"--instant-time", "-it"}, description = "Clustering
Instant time", required = true)
+ public String clusteringInstantTime = null;
+ @Parameter(names = {"--parallelism", "-pl"}, description = "Parallelism
for hoodie insert", required = false)
+ public int parallelism = 1;
+ @Parameter(names = {"--schema-file", "-sf"}, description = "path for Avro
schema file", required = true)
Review comment:
can we get schema from latest commit instead of requiring additional
config to simplify?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
