jackierwzhang commented on code in PR #51182: URL: https://github.com/apache/spark/pull/51182#discussion_r2150952529
########## sql/core/src/main/java/org/apache/spark/sql/execution/datasources/HadoopLineRecordReader.java: ########## @@ -0,0 +1,294 @@ +/* + * 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.spark.sql.execution.datasources; + +import java.io.IOException; +import java.io.InputStream; + +import scala.Option; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FSDataInputStream; +import org.apache.hadoop.fs.FutureDataInputStreamBuilder; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.fs.Seekable; +import org.apache.hadoop.io.LongWritable; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.io.compress.CodecPool; +import org.apache.hadoop.io.compress.CompressionCodec; +import org.apache.hadoop.io.compress.SplitCompressionInputStream; +import org.apache.hadoop.io.compress.SplittableCompressionCodec; +import org.apache.hadoop.io.compress.Decompressor; +import org.apache.hadoop.mapreduce.InputSplit; +import org.apache.hadoop.mapreduce.MRJobConfig; +import org.apache.hadoop.mapreduce.RecordReader; +import org.apache.hadoop.mapreduce.TaskAttemptContext; +import org.apache.hadoop.mapreduce.lib.input.FileSplit; +import org.apache.hadoop.mapreduce.lib.input.SplitLineReader; +import org.apache.hadoop.mapreduce.lib.input.CompressedSplitLineReader; +import org.apache.hadoop.mapreduce.lib.input.UncompressedSplitLineReader; +import org.apache.hadoop.util.functional.FutureIO; +import org.apache.spark.internal.SparkLogger; +import org.apache.spark.internal.SparkLoggerFactory; +import org.apache.spark.io.HadoopCodecStreams; + +import static org.apache.hadoop.fs.Options.OpenFileOptions.FS_OPTION_OPENFILE_SPLIT_END; +import static org.apache.hadoop.fs.Options.OpenFileOptions.FS_OPTION_OPENFILE_SPLIT_START; + +/** + * Inlined from Hadoop's LineRecordReader to add support for passing compression option + * and also add support for other codecs like ZSTD. + */ + +/** + * Treats keys as offset in file and value as line. + */ +public class HadoopLineRecordReader extends RecordReader<LongWritable, Text> { Review Comment: Could you describe the changes with more details for this inlined library? Maybe add inline comments to the exact lines that are altered -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
