[ 
https://issues.apache.org/jira/browse/CARBONDATA-296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15574281#comment-15574281
 ] 

ASF GitHub Bot commented on CARBONDATA-296:
-------------------------------------------

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

    https://github.com/apache/incubator-carbondata/pull/233#discussion_r83359593
  
    --- 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> {
    --- End diff --
    
    Why is it a static class? And you can rename it to `CSVRecordReader`


> 1.Add CSVInputFormat to read csv files.
> ---------------------------------------
>
>                 Key: CARBONDATA-296
>                 URL: https://issues.apache.org/jira/browse/CARBONDATA-296
>             Project: CarbonData
>          Issue Type: Sub-task
>            Reporter: Ravindra Pesala
>            Assignee: QiangCai
>             Fix For: 0.2.0-incubating
>
>
> Add CSVInputFormat to read csv files, it should use Univocity parser to read 
> csv files to get optimal performance. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to