<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT>    /**<a name="line.1"></a>
<FONT color="green">002</FONT>     * Licensed to the Apache Software Foundation (ASF) under one<a name="line.2"></a>
<FONT color="green">003</FONT>     * or more contributor license agreements.  See the NOTICE file<a name="line.3"></a>
<FONT color="green">004</FONT>     * distributed with this work for additional information<a name="line.4"></a>
<FONT color="green">005</FONT>     * regarding copyright ownership.  The ASF licenses this file<a name="line.5"></a>
<FONT color="green">006</FONT>     * to you under the Apache License, Version 2.0 (the<a name="line.6"></a>
<FONT color="green">007</FONT>     * "License"); you may not use this file except in compliance<a name="line.7"></a>
<FONT color="green">008</FONT>     * with the License.  You may obtain a copy of the License at<a name="line.8"></a>
<FONT color="green">009</FONT>     *<a name="line.9"></a>
<FONT color="green">010</FONT>     *     http://www.apache.org/licenses/LICENSE-2.0<a name="line.10"></a>
<FONT color="green">011</FONT>     *<a name="line.11"></a>
<FONT color="green">012</FONT>     * Unless required by applicable law or agreed to in writing, software<a name="line.12"></a>
<FONT color="green">013</FONT>     * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.13"></a>
<FONT color="green">014</FONT>     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.14"></a>
<FONT color="green">015</FONT>     * See the License for the specific language governing permissions and<a name="line.15"></a>
<FONT color="green">016</FONT>     * limitations under the License.<a name="line.16"></a>
<FONT color="green">017</FONT>     */<a name="line.17"></a>
<FONT color="green">018</FONT>    <a name="line.18"></a>
<FONT color="green">019</FONT>    package org.apache.hadoop.mapreduce.lib.input;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.IOException;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.ArrayList;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.util.List;<a name="line.23"></a>
<FONT color="green">024</FONT>    <a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.fs.FSDataInputStream;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.fs.FileStatus;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.fs.FileSystem;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.fs.Path;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.io.LongWritable;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.io.Text;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.InputSplit;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.mapreduce.RecordReader;<a name="line.37"></a>
<FONT color="green">038</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.38"></a>
<FONT color="green">039</FONT>    import org.apache.hadoop.util.LineReader;<a name="line.39"></a>
<FONT color="green">040</FONT>    <a name="line.40"></a>
<FONT color="green">041</FONT>    /**<a name="line.41"></a>
<FONT color="green">042</FONT>     * NLineInputFormat which splits N lines of input as one split.<a name="line.42"></a>
<FONT color="green">043</FONT>     *<a name="line.43"></a>
<FONT color="green">044</FONT>     * In many "pleasantly" parallel applications, each process/mapper <a name="line.44"></a>
<FONT color="green">045</FONT>     * processes the same input file (s), but with computations are <a name="line.45"></a>
<FONT color="green">046</FONT>     * controlled by different parameters.(Referred to as "parameter sweeps").<a name="line.46"></a>
<FONT color="green">047</FONT>     * One way to achieve this, is to specify a set of parameters <a name="line.47"></a>
<FONT color="green">048</FONT>     * (one set per line) as input in a control file <a name="line.48"></a>
<FONT color="green">049</FONT>     * (which is the input path to the map-reduce application,<a name="line.49"></a>
<FONT color="green">050</FONT>     * where as the input dataset is specified <a name="line.50"></a>
<FONT color="green">051</FONT>     * via a config variable in JobConf.).<a name="line.51"></a>
<FONT color="green">052</FONT>     * <a name="line.52"></a>
<FONT color="green">053</FONT>     * The NLineInputFormat can be used in such applications, that splits <a name="line.53"></a>
<FONT color="green">054</FONT>     * the input file such that by default, one line is fed as<a name="line.54"></a>
<FONT color="green">055</FONT>     * a value to one map task, and key is the offset.<a name="line.55"></a>
<FONT color="green">056</FONT>     * i.e. (k,v) is (LongWritable, Text).<a name="line.56"></a>
<FONT color="green">057</FONT>     * The location hints will span the whole mapred cluster.<a name="line.57"></a>
<FONT color="green">058</FONT>     */<a name="line.58"></a>
<FONT color="green">059</FONT>    @InterfaceAudience.Public<a name="line.59"></a>
<FONT color="green">060</FONT>    @InterfaceStability.Stable<a name="line.60"></a>
<FONT color="green">061</FONT>    public class NLineInputFormat extends FileInputFormat&lt;LongWritable, Text&gt; { <a name="line.61"></a>
<FONT color="green">062</FONT>      public static final String LINES_PER_MAP = <a name="line.62"></a>
<FONT color="green">063</FONT>        "mapreduce.input.lineinputformat.linespermap";<a name="line.63"></a>
<FONT color="green">064</FONT>    <a name="line.64"></a>
<FONT color="green">065</FONT>      public RecordReader&lt;LongWritable, Text&gt; createRecordReader(<a name="line.65"></a>
<FONT color="green">066</FONT>          InputSplit genericSplit, TaskAttemptContext context) <a name="line.66"></a>
<FONT color="green">067</FONT>          throws IOException {<a name="line.67"></a>
<FONT color="green">068</FONT>        context.setStatus(genericSplit.toString());<a name="line.68"></a>
<FONT color="green">069</FONT>        return new LineRecordReader();<a name="line.69"></a>
<FONT color="green">070</FONT>      }<a name="line.70"></a>
<FONT color="green">071</FONT>    <a name="line.71"></a>
<FONT color="green">072</FONT>      /** <a name="line.72"></a>
<FONT color="green">073</FONT>       * Logically splits the set of input files for the job, splits N lines<a name="line.73"></a>
<FONT color="green">074</FONT>       * of the input as one split.<a name="line.74"></a>
<FONT color="green">075</FONT>       * <a name="line.75"></a>
<FONT color="green">076</FONT>       * @see FileInputFormat#getSplits(JobContext)<a name="line.76"></a>
<FONT color="green">077</FONT>       */<a name="line.77"></a>
<FONT color="green">078</FONT>      public List&lt;InputSplit&gt; getSplits(JobContext job)<a name="line.78"></a>
<FONT color="green">079</FONT>      throws IOException {<a name="line.79"></a>
<FONT color="green">080</FONT>        List&lt;InputSplit&gt; splits = new ArrayList&lt;InputSplit&gt;();<a name="line.80"></a>
<FONT color="green">081</FONT>        int numLinesPerSplit = getNumLinesPerSplit(job);<a name="line.81"></a>
<FONT color="green">082</FONT>        for (FileStatus status : listStatus(job)) {<a name="line.82"></a>
<FONT color="green">083</FONT>          splits.addAll(getSplitsForFile(status,<a name="line.83"></a>
<FONT color="green">084</FONT>            job.getConfiguration(), numLinesPerSplit));<a name="line.84"></a>
<FONT color="green">085</FONT>        }<a name="line.85"></a>
<FONT color="green">086</FONT>        return splits;<a name="line.86"></a>
<FONT color="green">087</FONT>      }<a name="line.87"></a>
<FONT color="green">088</FONT>      <a name="line.88"></a>
<FONT color="green">089</FONT>      public static List&lt;FileSplit&gt; getSplitsForFile(FileStatus status,<a name="line.89"></a>
<FONT color="green">090</FONT>          Configuration conf, int numLinesPerSplit) throws IOException {<a name="line.90"></a>
<FONT color="green">091</FONT>        List&lt;FileSplit&gt; splits = new ArrayList&lt;FileSplit&gt; ();<a name="line.91"></a>
<FONT color="green">092</FONT>        Path fileName = status.getPath();<a name="line.92"></a>
<FONT color="green">093</FONT>        if (status.isDirectory()) {<a name="line.93"></a>
<FONT color="green">094</FONT>          throw new IOException("Not a file: " + fileName);<a name="line.94"></a>
<FONT color="green">095</FONT>        }<a name="line.95"></a>
<FONT color="green">096</FONT>        FileSystem  fs = fileName.getFileSystem(conf);<a name="line.96"></a>
<FONT color="green">097</FONT>        LineReader lr = null;<a name="line.97"></a>
<FONT color="green">098</FONT>        try {<a name="line.98"></a>
<FONT color="green">099</FONT>          FSDataInputStream in  = fs.open(fileName);<a name="line.99"></a>
<FONT color="green">100</FONT>          lr = new LineReader(in, conf);<a name="line.100"></a>
<FONT color="green">101</FONT>          Text line = new Text();<a name="line.101"></a>
<FONT color="green">102</FONT>          int numLines = 0;<a name="line.102"></a>
<FONT color="green">103</FONT>          long begin = 0;<a name="line.103"></a>
<FONT color="green">104</FONT>          long length = 0;<a name="line.104"></a>
<FONT color="green">105</FONT>          int num = -1;<a name="line.105"></a>
<FONT color="green">106</FONT>          while ((num = lr.readLine(line)) &gt; 0) {<a name="line.106"></a>
<FONT color="green">107</FONT>            numLines++;<a name="line.107"></a>
<FONT color="green">108</FONT>            length += num;<a name="line.108"></a>
<FONT color="green">109</FONT>            if (numLines == numLinesPerSplit) {<a name="line.109"></a>
<FONT color="green">110</FONT>              // NLineInputFormat uses LineRecordReader, which always reads<a name="line.110"></a>
<FONT color="green">111</FONT>              // (and consumes) at least one character out of its upper split<a name="line.111"></a>
<FONT color="green">112</FONT>              // boundary. So to make sure that each mapper gets N lines, we<a name="line.112"></a>
<FONT color="green">113</FONT>              // move back the upper split limits of each split <a name="line.113"></a>
<FONT color="green">114</FONT>              // by one character here.<a name="line.114"></a>
<FONT color="green">115</FONT>              if (begin == 0) {<a name="line.115"></a>
<FONT color="green">116</FONT>                splits.add(new FileSplit(fileName, begin, length - 1,<a name="line.116"></a>
<FONT color="green">117</FONT>                  new String[] {}));<a name="line.117"></a>
<FONT color="green">118</FONT>              } else {<a name="line.118"></a>
<FONT color="green">119</FONT>                splits.add(new FileSplit(fileName, begin - 1, length,<a name="line.119"></a>
<FONT color="green">120</FONT>                  new String[] {}));<a name="line.120"></a>
<FONT color="green">121</FONT>              }<a name="line.121"></a>
<FONT color="green">122</FONT>              begin += length;<a name="line.122"></a>
<FONT color="green">123</FONT>              length = 0;<a name="line.123"></a>
<FONT color="green">124</FONT>              numLines = 0;<a name="line.124"></a>
<FONT color="green">125</FONT>            }<a name="line.125"></a>
<FONT color="green">126</FONT>          }<a name="line.126"></a>
<FONT color="green">127</FONT>          if (numLines != 0) {<a name="line.127"></a>
<FONT color="green">128</FONT>            splits.add(new FileSplit(fileName, begin, length, new String[]{}));<a name="line.128"></a>
<FONT color="green">129</FONT>          }<a name="line.129"></a>
<FONT color="green">130</FONT>        } finally {<a name="line.130"></a>
<FONT color="green">131</FONT>          if (lr != null) {<a name="line.131"></a>
<FONT color="green">132</FONT>            lr.close();<a name="line.132"></a>
<FONT color="green">133</FONT>          }<a name="line.133"></a>
<FONT color="green">134</FONT>        }<a name="line.134"></a>
<FONT color="green">135</FONT>        return splits; <a name="line.135"></a>
<FONT color="green">136</FONT>      }<a name="line.136"></a>
<FONT color="green">137</FONT>      <a name="line.137"></a>
<FONT color="green">138</FONT>      /**<a name="line.138"></a>
<FONT color="green">139</FONT>       * Set the number of lines per split<a name="line.139"></a>
<FONT color="green">140</FONT>       * @param job the job to modify<a name="line.140"></a>
<FONT color="green">141</FONT>       * @param numLines the number of lines per split<a name="line.141"></a>
<FONT color="green">142</FONT>       */<a name="line.142"></a>
<FONT color="green">143</FONT>      public static void setNumLinesPerSplit(Job job, int numLines) {<a name="line.143"></a>
<FONT color="green">144</FONT>        job.getConfiguration().setInt(LINES_PER_MAP, numLines);<a name="line.144"></a>
<FONT color="green">145</FONT>      }<a name="line.145"></a>
<FONT color="green">146</FONT>    <a name="line.146"></a>
<FONT color="green">147</FONT>      /**<a name="line.147"></a>
<FONT color="green">148</FONT>       * Get the number of lines per split<a name="line.148"></a>
<FONT color="green">149</FONT>       * @param job the job<a name="line.149"></a>
<FONT color="green">150</FONT>       * @return the number of lines per split<a name="line.150"></a>
<FONT color="green">151</FONT>       */<a name="line.151"></a>
<FONT color="green">152</FONT>      public static int getNumLinesPerSplit(JobContext job) {<a name="line.152"></a>
<FONT color="green">153</FONT>        return job.getConfiguration().getInt(LINES_PER_MAP, 1);<a name="line.153"></a>
<FONT color="green">154</FONT>      }<a name="line.154"></a>
<FONT color="green">155</FONT>    }<a name="line.155"></a>




























































</PRE>
</BODY>
</HTML>
