HuangZhenQiu commented on a change in pull request #6483: [FLINK-7243][flink-formats] Add parquet input format URL: https://github.com/apache/flink/pull/6483#discussion_r223934091
########## File path: flink-formats/flink-parquet/src/main/java/org/apache/flink/formats/parquet/ParquetInputFormat.java ########## @@ -0,0 +1,191 @@ +/* + * 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.parquet; + +import org.apache.flink.api.common.io.CheckpointableInputFormat; +import org.apache.flink.api.common.io.FileInputFormat; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.core.fs.FileInputSplit; +import org.apache.flink.core.fs.Path; +import org.apache.flink.formats.parquet.utils.ParquetRecordReader; +import org.apache.flink.formats.parquet.utils.ParquetSchemaConverter; +import org.apache.flink.formats.parquet.utils.RowReadSupport; +import org.apache.flink.metrics.Counter; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; + +import org.apache.parquet.ParquetReadOptions; +import org.apache.parquet.filter2.compat.FilterCompat; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.util.HadoopInputFile; +import org.apache.parquet.io.InputFile; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; + +/** + * The base InputFormat class to read from Parquet files. + * For specific return types the {@link #convert(Row)} method need to be implemented. + * + * <P>Using {@link ParquetRecordReader} to Read files instead of {@link org.apache.flink.core.fs.FSDataInputStream}, + * we override {@link #open(FileInputSplit)} and {@link #close()} to change the behaviors. + * + * @param <E> The type of record to read. + */ +public abstract class ParquetInputFormat<E> extends FileInputFormat<E> implements + CheckpointableInputFormat<FileInputSplit, Tuple2<Long, Long>> { + + private static final long serialVersionUID = 1L; + + private static final Logger LOG = LoggerFactory.getLogger(ParquetInputFormat.class); + + private transient Counter recordConsumed; + + protected RowTypeInfo readType; + + protected boolean isStandard; Review comment: Yes, It was original added to distinguish the backward compatible schema. It is not needed here. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on 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 With regards, Apache Git Services
