Github user jackylk commented on a diff in the pull request:

    https://github.com/apache/incubator-carbondata/pull/233#discussion_r83360081
  
    --- Diff: 
hadoop/src/main/java/org/apache/carbondata/hadoop/mapreduce/CSVInputFormat.java 
---
    @@ -0,0 +1,180 @@
    +/*
    + * 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.carbondata.hadoop.mapreduce;
    +
    +import java.io.IOException;
    +import java.io.InputStream;
    +import java.io.InputStreamReader;
    +import java.io.Reader;
    +
    +import org.apache.carbondata.hadoop.io.BoundedInputStream;
    +import org.apache.carbondata.hadoop.io.StringArrayWritable;
    +import org.apache.carbondata.hadoop.util.CSVInputFormatUtil;
    +
    +import com.univocity.parsers.csv.CsvParser;
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.fs.FSDataInputStream;
    +import org.apache.hadoop.fs.FileSystem;
    +import org.apache.hadoop.fs.Path;
    +import org.apache.hadoop.fs.Seekable;
    +import org.apache.hadoop.io.NullWritable;
    +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.CompressionCodecFactory;
    +import org.apache.hadoop.io.compress.CompressionInputStream;
    +import org.apache.hadoop.io.compress.Decompressor;
    +import org.apache.hadoop.io.compress.SplitCompressionInputStream;
    +import org.apache.hadoop.io.compress.SplittableCompressionCodec;
    +import org.apache.hadoop.mapreduce.InputSplit;
    +import org.apache.hadoop.mapreduce.RecordReader;
    +import org.apache.hadoop.mapreduce.TaskAttemptContext;
    +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
    +import org.apache.hadoop.mapreduce.lib.input.FileSplit;
    +import org.apache.hadoop.util.LineReader;
    +
    +/**
    + * An {@link org.apache.hadoop.mapreduce.InputFormat} for csv files.  
Files are broken into lines.
    + * Values are the line of csv files.
    + */
    +public class CSVInputFormat extends FileInputFormat<NullWritable, 
StringArrayWritable> {
    +
    +  @Override
    +  public RecordReader<NullWritable, StringArrayWritable> 
createRecordReader(InputSplit inputSplit,
    +      TaskAttemptContext context) throws IOException, InterruptedException 
{
    +    return new NewCSVRecordReader();
    +  }
    +
    +  /**
    +   * Treats value as line in file. Key is null.
    +   */
    +  public static class NewCSVRecordReader extends 
RecordReader<NullWritable, StringArrayWritable> {
    +
    +    private long start;
    +    private long end;
    +    private BoundedInputStream boundedInputStream;
    +    private Reader reader;
    +    private CsvParser csvParser;
    +    private StringArrayWritable value;
    +    private String[] columns;
    +    private Seekable filePosition;
    +    private boolean isCompressedInput;
    +    private Decompressor decompressor;
    +
    +    @Override
    +    public void initialize(InputSplit inputSplit, TaskAttemptContext 
context)
    +        throws IOException, InterruptedException {
    +      FileSplit split = (FileSplit) inputSplit;
    +      this.start = split.getStart();
    --- End diff --
    
    No need to use `this.start`, you can use `start` directly. 
    The same for all occurrence in this file


---
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.
---

Reply via email to