[GitHub] [iceberg] openinx commented on a change in pull request #1623: Add a rewrite datafile action for flink

[GitBox <gi...@apache.org>]

openinx commented on a change in pull request #1623:
URL: https://github.com/apache/iceberg/pull/1623#discussion_r507536858



##########
File path: flink/src/main/java/org/apache/iceberg/flink/source/RowDataRewriter.java
##########
@@ -0,0 +1,193 @@
+/*
+ * 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.iceberg.flink.source;
+
+import java.io.Serializable;
+import java.util.Collection;
+import java.util.List;
+import java.util.Locale;
+import java.util.Map;
+import java.util.stream.Collectors;
+import org.apache.flink.api.common.functions.RichMapFunction;
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.types.logical.RowType;
+import org.apache.iceberg.CombinedScanTask;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.PartitionSpec;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.TableProperties;
+import org.apache.iceberg.encryption.EncryptionManager;
+import org.apache.iceberg.flink.FlinkSchemaUtil;
+import org.apache.iceberg.flink.sink.RowDataTaskWriterFactory;
+import org.apache.iceberg.flink.sink.TaskWriterFactory;
+import org.apache.iceberg.io.FileIO;
+import org.apache.iceberg.io.LocationProvider;
+import org.apache.iceberg.io.TaskWriter;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import static org.apache.iceberg.TableProperties.DEFAULT_NAME_MAPPING;
+
+public class RowDataRewriter implements Serializable {
+
+  private static final Logger LOG = LoggerFactory.getLogger(RowDataRewriter.class);
+
+  private final Schema schema;
+  private final PartitionSpec spec;
+  private final Map<String, String> properties;
+  private final FileFormat format;
+  private final LocationProvider locations;
+  private final String nameMapping;
+  private final FileIO io;
+  private final boolean caseSensitive;
+  private final EncryptionManager encryptionManager;
+  private final Table table;
+
+  private final TaskWriterFactory<RowData> taskWriterFactory;
+
+  public RowDataRewriter(Table table, PartitionSpec spec, boolean caseSensitive,
+                         FileIO io, EncryptionManager encryptionManager) {
+    this.table = table;
+    this.schema = table.schema();
+    this.spec = spec;
+    this.locations = table.locationProvider();
+    this.properties = table.properties();
+    this.io = io;
+    this.encryptionManager = encryptionManager;
+
+    this.caseSensitive = caseSensitive;
+    this.nameMapping = table.properties().get(DEFAULT_NAME_MAPPING);
+
+    String formatString = table.properties().getOrDefault(
+        TableProperties.DEFAULT_FILE_FORMAT, TableProperties.DEFAULT_FILE_FORMAT_DEFAULT);
+    this.format = FileFormat.valueOf(formatString.toUpperCase(Locale.ENGLISH));
+
+    RowType flinkSchema = FlinkSchemaUtil.convert(table.schema());
+    taskWriterFactory = new RowDataTaskWriterFactory(table.schema(),
+        flinkSchema,
+        table.spec(),
+        table.locationProvider(),
+        table.io(),
+        table.encryption(),
+        Long.MAX_VALUE,
+        format,
+        table.properties());
+  }
+
+
+  public List<DataFile> rewriteDataForTasks(DataSet<CombinedScanTask> dataSet) throws Exception {
+
+    RewriteMap map = new RewriteMap(schema, nameMapping, io, caseSensitive,
+        encryptionManager,
+        taskWriterFactory);
+
+    DataSet<List<DataFile>> ds = dataSet.map(map);
+    return ds.collect().stream()
+        .flatMap(Collection::stream)
+        .collect(Collectors.toList());
+  }
+
+  public static class RewriteMap extends RichMapFunction<CombinedScanTask, List<DataFile>> {
+
+    private transient TaskWriter<RowData> writer;
+    private transient int subTaskId;
+    private transient int attemptId;
+
+    private final Schema schema;
+    private final String nameMapping;
+    private final FileIO io;
+    private final boolean caseSensitive;
+    private final EncryptionManager encryptionManager;
+    private final TaskWriterFactory<RowData> taskWriterFactory;
+
+    public RewriteMap(Schema schema, String nameMapping, FileIO io, boolean caseSensitive,
+                      EncryptionManager encryptionManager,
+                      TaskWriterFactory<RowData> taskWriterFactory) {
+      this.schema = schema;
+      this.nameMapping = nameMapping;
+      this.io = io;
+      this.caseSensitive = caseSensitive;
+      this.encryptionManager = encryptionManager;
+      this.taskWriterFactory = taskWriterFactory;
+    }
+
+    @Override
+    public void open(Configuration parameters) {
+      this.subTaskId = getRuntimeContext().getIndexOfThisSubtask();
+      this.attemptId = getRuntimeContext().getAttemptNumber();
+
+      // Initialize the task writer factory.
+      this.taskWriterFactory.initialize(subTaskId, attemptId);
+
+    }
+
+
+    @Override
+    public List<DataFile> map(CombinedScanTask task) throws Exception {
+      // Initialize the task writer.
+      this.writer = taskWriterFactory.create();
+      RowDataIterator iterator =
+          new RowDataIterator(task, io, encryptionManager, schema, schema,
+              nameMapping, caseSensitive);
+      try {
+        while (iterator.hasNext()) {
+          RowData rowData = iterator.next();
+          writer.write(rowData);
+        }
+        iterator.close();
+        writer.close();
+        return Lists.newArrayList(writer.complete()).stream()

Review comment:
       Could we just return  the `Lists.newArrayList(writer.complete())` ? 




----------------------------------------------------------------
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



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org