Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/164#discussion_r10785965 --- Diff: mllib/src/main/java/org/apache/spark/mllib/input/BatchFilesRecordReader.java --- @@ -0,0 +1,109 @@ +/* + * 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.mllib.input; + +import java.io.IOException; + +import com.google.common.io.Closeables; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.fs.FSDataInputStream; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.io.IOUtils; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.InputSplit; +import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit; +import org.apache.hadoop.mapreduce.RecordReader; +import org.apache.hadoop.mapreduce.TaskAttemptContext; + +/** + * Reads an entire file out in bytes format in <filename, content> format. + */ + +public class BatchFilesRecordReader extends RecordReader<String, Text> { + private long startOffset; + private int length; + private Path path; + + private String key = null; + private Text value = null; + + private boolean processed = false; + + private FileSystem fs; + + public BatchFilesRecordReader( + CombineFileSplit split, + TaskAttemptContext context, + Integer index) + throws IOException { + path = split.getPath(index); + startOffset = split.getOffset(index); + length = (int) split.getLength(index); + fs = path.getFileSystem(context.getConfiguration()); + } + + @Override + public void initialize(InputSplit arg0, TaskAttemptContext arg1) + throws IOException, InterruptedException { + } + + @Override + public void close() throws IOException { + } + + @Override + public float getProgress() throws IOException { + return processed ? 1.0f : 0.0f; + } + + @Override + public String getCurrentKey() throws IOException, InterruptedException { + return key; + } + + @Override + public Text getCurrentValue() throws IOException, InterruptedException{ + return value; + } + + @Override + public boolean nextKeyValue() throws IOException { + if (!processed) { --- End diff -- So it only reads the first file and throws away the rest?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---