You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by GitBox <gi...@apache.org> on 2021/10/19 12:19:01 UTC
[GitHub] [flink] slinkydeveloper commented on a change in pull request #17520: [FLINK-24565][avro] Port avro file format factory to BulkReaderFormatFactory
slinkydeveloper commented on a change in pull request #17520:
URL: https://github.com/apache/flink/pull/17520#discussion_r731794287
##########
File path: flink-formats/flink-avro/src/main/java/org/apache/flink/formats/avro/AvroFileFormatFactory.java
##########
@@ -20,39 +20,135 @@
import org.apache.flink.annotation.Internal;
import org.apache.flink.api.common.serialization.BulkWriter;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.configuration.ConfigOption;
import org.apache.flink.configuration.ReadableConfig;
+import org.apache.flink.connector.file.src.FileSourceSplit;
+import org.apache.flink.connector.file.src.reader.BulkFormat;
import org.apache.flink.core.fs.FSDataOutputStream;
import org.apache.flink.formats.avro.typeutils.AvroSchemaConverter;
import org.apache.flink.table.connector.ChangelogMode;
+import org.apache.flink.table.connector.format.BulkDecodingFormat;
import org.apache.flink.table.connector.format.EncodingFormat;
import org.apache.flink.table.connector.sink.DynamicTableSink;
+import org.apache.flink.table.connector.source.DynamicTableSource;
+import org.apache.flink.table.data.GenericRowData;
import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.factories.BulkReaderFormatFactory;
import org.apache.flink.table.factories.BulkWriterFormatFactory;
import org.apache.flink.table.factories.DynamicTableFactory;
+import org.apache.flink.table.filesystem.FileSystemConnectorOptions;
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.utils.PartitionPathUtils;
import org.apache.avro.Schema;
import org.apache.avro.file.CodecFactory;
import org.apache.avro.file.DataFileWriter;
+import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericDatumWriter;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.io.DatumWriter;
import java.io.IOException;
import java.io.OutputStream;
import java.util.HashSet;
+import java.util.List;
import java.util.Set;
+import java.util.stream.Collectors;
import static org.apache.flink.formats.avro.AvroFormatOptions.AVRO_OUTPUT_CODEC;
/** Avro format factory for file system. */
@Internal
-public class AvroFileFormatFactory implements BulkWriterFormatFactory {
+public class AvroFileFormatFactory implements BulkReaderFormatFactory, BulkWriterFormatFactory {
public static final String IDENTIFIER = "avro";
+ @Override
+ public BulkDecodingFormat<RowData> createDecodingFormat(
+ DynamicTableFactory.Context context, ReadableConfig formatOptions) {
+ return new BulkDecodingFormat<RowData>() {
+ @Override
+ public BulkFormat<RowData, FileSourceSplit> createRuntimeDecoder(
+ DynamicTableSource.Context sourceContext, DataType producedDataType) {
+ RowType physicalRowype =
+ (RowType)
+ context.getCatalogTable()
+ .getResolvedSchema()
+ .toPhysicalRowDataType()
+ .getLogicalType();
Review comment:
You should be able to just use `producedDataType` here.
##########
File path: flink-formats/flink-avro/pom.xml
##########
@@ -47,13 +47,11 @@ under the License.
<!-- Table ecosystem -->
- <!-- Projects depending on this project won't depend on flink-table-*. -->
<dependency>
<groupId>org.apache.flink</groupId>
- <artifactId>flink-table-common</artifactId>
+ <artifactId>flink-table-runtime_${scala.binary.version}</artifactId>
Review comment:
Why this depedency change?
##########
File path: flink-formats/flink-avro/src/main/java/org/apache/flink/formats/avro/AvroFileFormatFactory.java
##########
@@ -20,39 +20,135 @@
import org.apache.flink.annotation.Internal;
import org.apache.flink.api.common.serialization.BulkWriter;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.configuration.ConfigOption;
import org.apache.flink.configuration.ReadableConfig;
+import org.apache.flink.connector.file.src.FileSourceSplit;
+import org.apache.flink.connector.file.src.reader.BulkFormat;
import org.apache.flink.core.fs.FSDataOutputStream;
import org.apache.flink.formats.avro.typeutils.AvroSchemaConverter;
import org.apache.flink.table.connector.ChangelogMode;
+import org.apache.flink.table.connector.format.BulkDecodingFormat;
import org.apache.flink.table.connector.format.EncodingFormat;
import org.apache.flink.table.connector.sink.DynamicTableSink;
+import org.apache.flink.table.connector.source.DynamicTableSource;
+import org.apache.flink.table.data.GenericRowData;
import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.factories.BulkReaderFormatFactory;
import org.apache.flink.table.factories.BulkWriterFormatFactory;
import org.apache.flink.table.factories.DynamicTableFactory;
+import org.apache.flink.table.filesystem.FileSystemConnectorOptions;
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.utils.PartitionPathUtils;
import org.apache.avro.Schema;
import org.apache.avro.file.CodecFactory;
import org.apache.avro.file.DataFileWriter;
+import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericDatumWriter;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.io.DatumWriter;
import java.io.IOException;
import java.io.OutputStream;
import java.util.HashSet;
+import java.util.List;
import java.util.Set;
+import java.util.stream.Collectors;
import static org.apache.flink.formats.avro.AvroFormatOptions.AVRO_OUTPUT_CODEC;
/** Avro format factory for file system. */
@Internal
-public class AvroFileFormatFactory implements BulkWriterFormatFactory {
+public class AvroFileFormatFactory implements BulkReaderFormatFactory, BulkWriterFormatFactory {
public static final String IDENTIFIER = "avro";
+ @Override
+ public BulkDecodingFormat<RowData> createDecodingFormat(
+ DynamicTableFactory.Context context, ReadableConfig formatOptions) {
+ return new BulkDecodingFormat<RowData>() {
+ @Override
+ public BulkFormat<RowData, FileSourceSplit> createRuntimeDecoder(
+ DynamicTableSource.Context sourceContext, DataType producedDataType) {
+ RowType physicalRowype =
+ (RowType)
+ context.getCatalogTable()
+ .getResolvedSchema()
+ .toPhysicalRowDataType()
+ .getLogicalType();
+ List<String> physicalFieldNames = physicalRowype.getFieldNames();
Review comment:
You should use `DataType.getFieldNames()` static method
##########
File path: flink-formats/flink-avro/src/main/java/org/apache/flink/formats/avro/AvroFormatFactory.java
##########
@@ -1,108 +0,0 @@
-/*
- * 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.flink.formats.avro;
-
-import org.apache.flink.annotation.Internal;
-import org.apache.flink.api.common.serialization.DeserializationSchema;
-import org.apache.flink.api.common.serialization.SerializationSchema;
-import org.apache.flink.api.common.typeinfo.TypeInformation;
-import org.apache.flink.configuration.ConfigOption;
-import org.apache.flink.configuration.ReadableConfig;
-import org.apache.flink.table.connector.ChangelogMode;
-import org.apache.flink.table.connector.format.DecodingFormat;
-import org.apache.flink.table.connector.format.EncodingFormat;
-import org.apache.flink.table.connector.sink.DynamicTableSink;
-import org.apache.flink.table.connector.source.DynamicTableSource;
-import org.apache.flink.table.data.RowData;
-import org.apache.flink.table.factories.DeserializationFormatFactory;
-import org.apache.flink.table.factories.DynamicTableFactory;
-import org.apache.flink.table.factories.FactoryUtil;
-import org.apache.flink.table.factories.SerializationFormatFactory;
-import org.apache.flink.table.types.DataType;
-import org.apache.flink.table.types.logical.RowType;
-
-import java.util.Collections;
-import java.util.Set;
-
-/**
- * Table format factory for providing configured instances of Avro to RowData {@link
- * SerializationSchema} and {@link DeserializationSchema}.
- */
-@Internal
-public class AvroFormatFactory implements DeserializationFormatFactory, SerializationFormatFactory {
Review comment:
Why removing this? We still need it for Kafka and other connectors that require avro deserialization record by record
--
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: issues-unsubscribe@flink.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org