openinx commented on a change in pull request #1185:
URL: https://github.com/apache/iceberg/pull/1185#discussion_r478790684
##########
File path: core/src/main/java/org/apache/iceberg/io/FileAppenderFactory.java
##########
@@ -19,14 +19,15 @@
package org.apache.iceberg.io;
+import java.io.Serializable;
import org.apache.iceberg.FileFormat;
/**
* Factory to create a new {@link FileAppender} to write records.
*
* @param <T> data type of the rows to append.
*/
-public interface FileAppenderFactory<T> {
+public interface FileAppenderFactory<T> extends Serializable {
Review comment:
That sounds reasonable.
##########
File path: flink/src/main/java/org/apache/iceberg/flink/sink/FlinkSink.java
##########
@@ -0,0 +1,192 @@
+/*
+ * 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.sink;
+
+import java.util.Locale;
+import java.util.Map;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.common.typeinfo.Types;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import org.apache.flink.streaming.api.functions.sink.DiscardingSink;
+import org.apache.flink.table.api.TableSchema;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.data.util.DataFormatConverters;
+import org.apache.flink.table.runtime.typeutils.RowDataTypeInfo;
+import org.apache.flink.table.types.DataType;
+import org.apache.flink.table.types.logical.LogicalType;
+import org.apache.flink.table.types.logical.RowType;
+import org.apache.flink.table.types.utils.TypeConversions;
+import org.apache.flink.types.Row;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.flink.FlinkSchemaUtil;
+import org.apache.iceberg.flink.TableLoader;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.types.TypeUtil;
+import org.apache.iceberg.util.PropertyUtil;
+
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
+import static org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES;
+import static
org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT;
+
+public class FlinkSink {
+
+ private static final String ICEBERG_STREAM_WRITER_NAME =
IcebergStreamWriter.class.getSimpleName();
+ private static final String ICEBERG_FILES_COMMITTER_NAME =
IcebergFilesCommitter.class.getSimpleName();
+
+ private FlinkSink() {
+ }
+
+ public static Builder forRow(DataStream<Row> input) {
+ return new Builder().forRow(input);
Review comment:
It will be quite easy to support other object models, we only need a
`MapFunction` to convert the generic object to `RowData` and define what's the
`TypeInformation` for `RowData`. For example, we could create a separate
builder interfaces for the generic object models on top of this builder:
```java
public static <T> Builder builderFor(DataStream<T> input,
Function<T, RowData> converter,
TypeInformation<RowData> outputType) {
DataStream<RowData> dataStream = input.map(converter::apply, outputType);
return forRowData(dataStream);
}
```
##########
File path: flink/src/main/java/org/apache/iceberg/flink/sink/FlinkSink.java
##########
@@ -0,0 +1,192 @@
+/*
+ * 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.sink;
+
+import java.util.Locale;
+import java.util.Map;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.common.typeinfo.Types;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import org.apache.flink.streaming.api.functions.sink.DiscardingSink;
+import org.apache.flink.table.api.TableSchema;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.data.util.DataFormatConverters;
+import org.apache.flink.table.runtime.typeutils.RowDataTypeInfo;
+import org.apache.flink.table.types.DataType;
+import org.apache.flink.table.types.logical.LogicalType;
+import org.apache.flink.table.types.logical.RowType;
+import org.apache.flink.table.types.utils.TypeConversions;
+import org.apache.flink.types.Row;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.flink.FlinkSchemaUtil;
+import org.apache.iceberg.flink.TableLoader;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.types.TypeUtil;
+import org.apache.iceberg.util.PropertyUtil;
+
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
+import static org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES;
+import static
org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT;
+
+public class FlinkSink {
+
+ private static final String ICEBERG_STREAM_WRITER_NAME =
IcebergStreamWriter.class.getSimpleName();
+ private static final String ICEBERG_FILES_COMMITTER_NAME =
IcebergFilesCommitter.class.getSimpleName();
+
+ private FlinkSink() {
+ }
+
+ public static Builder forRow(DataStream<Row> input) {
+ return new Builder().forRow(input);
+ }
+
+ public static Builder forRowData(DataStream<RowData> input) {
+ return new Builder().forRowData(input);
+ }
+
+ public static class Builder {
+ private DataStream<Row> rowInput = null;
+ private DataStream<RowData> rowDataInput = null;
+ private TableLoader tableLoader;
+ private Configuration hadoopConf;
+ private Table table;
+ private TableSchema tableSchema;
+
+ private Builder forRow(DataStream<Row> newRowInput) {
+ this.rowInput = newRowInput;
+ return this;
+ }
+
+ private Builder forRowData(DataStream<RowData> newRowDataInput) {
+ this.rowDataInput = newRowDataInput;
+ return this;
+ }
+
+ public Builder table(Table newTable) {
+ this.table = newTable;
+ return this;
+ }
+
+ public Builder tableLoader(TableLoader newTableLoader) {
+ this.tableLoader = newTableLoader;
+ return this;
+ }
+
+ public Builder hadoopConf(Configuration newHadoopConf) {
+ this.hadoopConf = newHadoopConf;
+ return this;
+ }
+
+ public Builder tableSchema(TableSchema newTableSchema) {
+ this.tableSchema = newTableSchema;
+ return this;
+ }
+
+ private DataStream<RowData> convert() {
+ Preconditions.checkArgument(rowInput != null, "The DataStream<Row> to
convert shouldn't be null");
+
+ RowType rowType;
+ DataType[] fieldDataTypes;
+ if (tableSchema != null) {
+ rowType = (RowType) tableSchema.toRowDataType().getLogicalType();
+ fieldDataTypes = tableSchema.getFieldDataTypes();
+ } else {
+ rowType = FlinkSchemaUtil.convert(table.schema());
+ fieldDataTypes =
TypeConversions.fromLogicalToDataType(rowType.getChildren().toArray(new
LogicalType[0]));
+ }
+
+ DataFormatConverters.RowConverter rowConverter = new
DataFormatConverters.RowConverter(fieldDataTypes);
+
+ return rowInput.map(rowConverter::toInternal,
RowDataTypeInfo.of(rowType));
+ }
+
+ @SuppressWarnings("unchecked")
+ public DataStreamSink<RowData> build() {
+ Preconditions.checkArgument(rowInput != null || rowDataInput != null,
+ "Should initialize input DataStream first with DataStream<Row> or
DataStream<RowData>");
Review comment:
OK, let me make those more clear.
##########
File path:
flink/src/main/java/org/apache/iceberg/flink/sink/IcebergStreamWriter.java
##########
@@ -34,15 +35,16 @@
private static final long serialVersionUID = 1L;
private final String fullTableName;
+ private final TaskWriterFactory<T> taskWriterFactory;
- private transient TaskWriterFactory<T> taskWriterFactory;
private transient TaskWriter<T> writer;
private transient int subTaskId;
private transient int attemptId;
IcebergStreamWriter(String fullTableName, TaskWriterFactory<T>
taskWriterFactory) {
this.fullTableName = fullTableName;
this.taskWriterFactory = taskWriterFactory;
+ setChainingStrategy(ChainingStrategy.ALWAYS);
Review comment:
Copied the javadoc from ChainingStrategy here, it's used for chaining
the operators to be co-located on the same thread for better performance.
```java
/**
* Defines the chaining scheme for the operator. When an operator is chained
to the
* predecessor, it means that they run in the same thread. They become one
operator
* consisting of multiple steps.
*
* <p>The default value used by the StreamOperator is {@link #HEAD}, which
means that
* the operator is not chained to its predecessor. Most operators override
this with
* {@link #ALWAYS}, meaning they will be chained to predecessors whenever
possible.
*/
@PublicEvolving
public enum ChainingStrategy {
/**
* Operators will be eagerly chained whenever possible.
*
* <p>To optimize performance, it is generally a good practice to allow
maximal
* chaining and increase operator parallelism.
*/
ALWAYS,
/**
* The operator will not be chained to the preceding or succeeding
operators.
*/
NEVER,
/**
* The operator will not be chained to the predecessor, but successors
may chain to this
* operator.
*/
HEAD
}
```
##########
File path: flink/src/main/java/org/apache/iceberg/flink/sink/FlinkSink.java
##########
@@ -0,0 +1,192 @@
+/*
+ * 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.sink;
+
+import java.util.Locale;
+import java.util.Map;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.common.typeinfo.Types;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import org.apache.flink.streaming.api.functions.sink.DiscardingSink;
+import org.apache.flink.table.api.TableSchema;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.data.util.DataFormatConverters;
+import org.apache.flink.table.runtime.typeutils.RowDataTypeInfo;
+import org.apache.flink.table.types.DataType;
+import org.apache.flink.table.types.logical.LogicalType;
+import org.apache.flink.table.types.logical.RowType;
+import org.apache.flink.table.types.utils.TypeConversions;
+import org.apache.flink.types.Row;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.flink.FlinkSchemaUtil;
+import org.apache.iceberg.flink.TableLoader;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.types.TypeUtil;
+import org.apache.iceberg.util.PropertyUtil;
+
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
+import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
+import static org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES;
+import static
org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT;
+
+public class FlinkSink {
+
+ private static final String ICEBERG_STREAM_WRITER_NAME =
IcebergStreamWriter.class.getSimpleName();
+ private static final String ICEBERG_FILES_COMMITTER_NAME =
IcebergFilesCommitter.class.getSimpleName();
+
+ private FlinkSink() {
+ }
+
+ public static Builder forRow(DataStream<Row> input) {
+ return new Builder().forRow(input);
+ }
+
+ public static Builder forRowData(DataStream<RowData> input) {
+ return new Builder().forRowData(input);
+ }
+
+ public static class Builder {
+ private DataStream<Row> rowInput = null;
+ private DataStream<RowData> rowDataInput = null;
+ private TableLoader tableLoader;
+ private Configuration hadoopConf;
+ private Table table;
+ private TableSchema tableSchema;
+
+ private Builder forRow(DataStream<Row> newRowInput) {
+ this.rowInput = newRowInput;
+ return this;
+ }
+
+ private Builder forRowData(DataStream<RowData> newRowDataInput) {
+ this.rowDataInput = newRowDataInput;
+ return this;
+ }
+
+ public Builder table(Table newTable) {
+ this.table = newTable;
+ return this;
+ }
+
+ public Builder tableLoader(TableLoader newTableLoader) {
+ this.tableLoader = newTableLoader;
+ return this;
+ }
+
+ public Builder hadoopConf(Configuration newHadoopConf) {
+ this.hadoopConf = newHadoopConf;
+ return this;
+ }
+
+ public Builder tableSchema(TableSchema newTableSchema) {
+ this.tableSchema = newTableSchema;
+ return this;
+ }
+
+ private DataStream<RowData> convert() {
+ Preconditions.checkArgument(rowInput != null, "The DataStream<Row> to
convert shouldn't be null");
Review comment:
I think it could be removed now, because we've checked the nullable in
the `Builder#build`.
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
