hudi-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [incubator-hudi] leesf commented on a change in pull request #1360: [HUDI-344][RFC-09] Hudi Dataset Snapshot Exporter
Date Sun, 08 Mar 2020 02:30:28 GMT
leesf commented on a change in pull request #1360: [HUDI-344][RFC-09] Hudi Dataset Snapshot
Exporter
URL: https://github.com/apache/incubator-hudi/pull/1360#discussion_r389328898
 
 

 ##########
 File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieSnapshotExporter.java
 ##########
 @@ -0,0 +1,233 @@
+/*
+ * 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.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.FileUtil;
+import org.apache.hadoop.fs.Path;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.common.SerializableConfiguration;
+import org.apache.hudi.common.model.HoodiePartitionMetadata;
+import org.apache.hudi.common.table.HoodieTableConfig;
+import org.apache.hudi.common.table.HoodieTableMetaClient;
+import org.apache.hudi.common.table.HoodieTimeline;
+import org.apache.hudi.common.table.TableFileSystemView;
+import org.apache.hudi.common.table.timeline.HoodieInstant;
+import org.apache.hudi.common.table.view.HoodieTableFileSystemView;
+import org.apache.hudi.common.util.FSUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Column;
+import org.apache.spark.sql.DataFrameWriter;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.execution.datasources.DataSource;
+
+import scala.Tuple2;
+import scala.collection.JavaConversions;
+
+import java.io.IOException;
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+import java.util.stream.Collectors;
+
+/**
+ * Export the latest records of Hudi dataset to a set of external files (e.g., plain parquet
files).
+ */
+
+public class HoodieSnapshotExporter {
+  private static final Logger LOG = LogManager.getLogger(HoodieSnapshotExporter.class);
+
+  public static class Config implements Serializable {
+    @Parameter(names = {"--source-base-path"}, description = "Base path for the source Hudi
dataset to be snapshotted", required = true)
+    String sourceBasePath = null;
+
+    @Parameter(names = {"--target-base-path"}, description = "Base path for the target output
files (snapshots)", required = true)
+    String targetOutputPath = null;
+
+    @Parameter(names = {"--snapshot-prefix"}, description = "Snapshot prefix or directory
under the target base path in order to segregate different snapshots")
+    String snapshotPrefix;
+
+    @Parameter(names = {"--output-format"}, description = "e.g. Hudi or Parquet", required
= true)
+    String outputFormat;
+
+    @Parameter(names = {"--output-partition-field"}, description = "A field to be used by
Spark repartitioning")
+    String outputPartitionField;
+  }
+
+  public int export(SparkSession spark, Config cfg) throws IOException {
+    JavaSparkContext jsc = new JavaSparkContext(spark.sparkContext());
+    FileSystem fs = FSUtils.getFs(cfg.sourceBasePath, jsc.hadoopConfiguration());
+
+    final SerializableConfiguration serConf = new SerializableConfiguration(jsc.hadoopConfiguration());
+    final HoodieTableMetaClient tableMetadata = new HoodieTableMetaClient(fs.getConf(), cfg.sourceBasePath);
+    final TableFileSystemView.BaseFileOnlyView fsView = new HoodieTableFileSystemView(tableMetadata,
+        tableMetadata.getActiveTimeline().getCommitsTimeline().filterCompletedInstants());
+    // Get the latest commit
+    Option<HoodieInstant> latestCommit =
+        tableMetadata.getActiveTimeline().getCommitsTimeline().filterCompletedInstants().lastInstant();
+    if (!latestCommit.isPresent()) {
+      LOG.error("No commits present. Nothing to snapshot");
+      return -1;
+    }
+    final String latestCommitTimestamp = latestCommit.get().getTimestamp();
 
 Review comment:
   one minor question, would we support config commit time ? it is optional, and get lastest
commit by default or get the specified commit time. cc @xushiyan @OpenOpened 

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message