<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.mapred.lib;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.*;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.lang.reflect.*;<a name="line.22"></a>
<FONT color="green">023</FONT>    <a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.hadoop.fs.FileSystem;<a name="line.24"></a>
<FONT color="green">025</FONT>    <a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.mapred.*;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.29"></a>
<FONT color="green">030</FONT>    <a name="line.30"></a>
<FONT color="green">031</FONT>    /**<a name="line.31"></a>
<FONT color="green">032</FONT>     * A generic RecordReader that can hand out different recordReaders<a name="line.32"></a>
<FONT color="green">033</FONT>     * for each chunk in a {@link CombineFileSplit}.<a name="line.33"></a>
<FONT color="green">034</FONT>     * A CombineFileSplit can combine data chunks from multiple files. <a name="line.34"></a>
<FONT color="green">035</FONT>     * This class allows using different RecordReaders for processing<a name="line.35"></a>
<FONT color="green">036</FONT>     * these data chunks from different files.<a name="line.36"></a>
<FONT color="green">037</FONT>     * @see CombineFileSplit<a name="line.37"></a>
<FONT color="green">038</FONT>     */<a name="line.38"></a>
<FONT color="green">039</FONT>    @InterfaceAudience.Public<a name="line.39"></a>
<FONT color="green">040</FONT>    @InterfaceStability.Stable<a name="line.40"></a>
<FONT color="green">041</FONT>    public class CombineFileRecordReader&lt;K, V&gt; implements RecordReader&lt;K, V&gt; {<a name="line.41"></a>
<FONT color="green">042</FONT>    <a name="line.42"></a>
<FONT color="green">043</FONT>      static final Class [] constructorSignature = new Class [] <a name="line.43"></a>
<FONT color="green">044</FONT>                                             {CombineFileSplit.class, <a name="line.44"></a>
<FONT color="green">045</FONT>                                              Configuration.class, <a name="line.45"></a>
<FONT color="green">046</FONT>                                              Reporter.class,<a name="line.46"></a>
<FONT color="green">047</FONT>                                              Integer.class};<a name="line.47"></a>
<FONT color="green">048</FONT>    <a name="line.48"></a>
<FONT color="green">049</FONT>      protected CombineFileSplit split;<a name="line.49"></a>
<FONT color="green">050</FONT>      protected JobConf jc;<a name="line.50"></a>
<FONT color="green">051</FONT>      protected Reporter reporter;<a name="line.51"></a>
<FONT color="green">052</FONT>      protected Class&lt;RecordReader&lt;K, V&gt;&gt; rrClass;<a name="line.52"></a>
<FONT color="green">053</FONT>      protected Constructor&lt;RecordReader&lt;K, V&gt;&gt; rrConstructor;<a name="line.53"></a>
<FONT color="green">054</FONT>      protected FileSystem fs;<a name="line.54"></a>
<FONT color="green">055</FONT>      <a name="line.55"></a>
<FONT color="green">056</FONT>      protected int idx;<a name="line.56"></a>
<FONT color="green">057</FONT>      protected long progress;<a name="line.57"></a>
<FONT color="green">058</FONT>      protected RecordReader&lt;K, V&gt; curReader;<a name="line.58"></a>
<FONT color="green">059</FONT>      <a name="line.59"></a>
<FONT color="green">060</FONT>      public boolean next(K key, V value) throws IOException {<a name="line.60"></a>
<FONT color="green">061</FONT>    <a name="line.61"></a>
<FONT color="green">062</FONT>        while ((curReader == null) || !curReader.next(key, value)) {<a name="line.62"></a>
<FONT color="green">063</FONT>          if (!initNextRecordReader()) {<a name="line.63"></a>
<FONT color="green">064</FONT>            return false;<a name="line.64"></a>
<FONT color="green">065</FONT>          }<a name="line.65"></a>
<FONT color="green">066</FONT>        }<a name="line.66"></a>
<FONT color="green">067</FONT>        return true;<a name="line.67"></a>
<FONT color="green">068</FONT>      }<a name="line.68"></a>
<FONT color="green">069</FONT>    <a name="line.69"></a>
<FONT color="green">070</FONT>      public K createKey() {<a name="line.70"></a>
<FONT color="green">071</FONT>        return curReader.createKey();<a name="line.71"></a>
<FONT color="green">072</FONT>      }<a name="line.72"></a>
<FONT color="green">073</FONT>      <a name="line.73"></a>
<FONT color="green">074</FONT>      public V createValue() {<a name="line.74"></a>
<FONT color="green">075</FONT>        return curReader.createValue();<a name="line.75"></a>
<FONT color="green">076</FONT>      }<a name="line.76"></a>
<FONT color="green">077</FONT>      <a name="line.77"></a>
<FONT color="green">078</FONT>      /**<a name="line.78"></a>
<FONT color="green">079</FONT>       * return the amount of data processed<a name="line.79"></a>
<FONT color="green">080</FONT>       */<a name="line.80"></a>
<FONT color="green">081</FONT>      public long getPos() throws IOException {<a name="line.81"></a>
<FONT color="green">082</FONT>        return progress;<a name="line.82"></a>
<FONT color="green">083</FONT>      }<a name="line.83"></a>
<FONT color="green">084</FONT>      <a name="line.84"></a>
<FONT color="green">085</FONT>      public void close() throws IOException {<a name="line.85"></a>
<FONT color="green">086</FONT>        if (curReader != null) {<a name="line.86"></a>
<FONT color="green">087</FONT>          curReader.close();<a name="line.87"></a>
<FONT color="green">088</FONT>          curReader = null;<a name="line.88"></a>
<FONT color="green">089</FONT>        }<a name="line.89"></a>
<FONT color="green">090</FONT>      }<a name="line.90"></a>
<FONT color="green">091</FONT>      <a name="line.91"></a>
<FONT color="green">092</FONT>      /**<a name="line.92"></a>
<FONT color="green">093</FONT>       * return progress based on the amount of data processed so far.<a name="line.93"></a>
<FONT color="green">094</FONT>       */<a name="line.94"></a>
<FONT color="green">095</FONT>      public float getProgress() throws IOException {<a name="line.95"></a>
<FONT color="green">096</FONT>        return Math.min(1.0f,  progress/(float)(split.getLength()));<a name="line.96"></a>
<FONT color="green">097</FONT>      }<a name="line.97"></a>
<FONT color="green">098</FONT>      <a name="line.98"></a>
<FONT color="green">099</FONT>      /**<a name="line.99"></a>
<FONT color="green">100</FONT>       * A generic RecordReader that can hand out different recordReaders<a name="line.100"></a>
<FONT color="green">101</FONT>       * for each chunk in the CombineFileSplit.<a name="line.101"></a>
<FONT color="green">102</FONT>       */<a name="line.102"></a>
<FONT color="green">103</FONT>      public CombineFileRecordReader(JobConf job, CombineFileSplit split, <a name="line.103"></a>
<FONT color="green">104</FONT>                                     Reporter reporter,<a name="line.104"></a>
<FONT color="green">105</FONT>                                     Class&lt;RecordReader&lt;K, V&gt;&gt; rrClass)<a name="line.105"></a>
<FONT color="green">106</FONT>        throws IOException {<a name="line.106"></a>
<FONT color="green">107</FONT>        this.split = split;<a name="line.107"></a>
<FONT color="green">108</FONT>        this.jc = job;<a name="line.108"></a>
<FONT color="green">109</FONT>        this.rrClass = rrClass;<a name="line.109"></a>
<FONT color="green">110</FONT>        this.reporter = reporter;<a name="line.110"></a>
<FONT color="green">111</FONT>        this.idx = 0;<a name="line.111"></a>
<FONT color="green">112</FONT>        this.curReader = null;<a name="line.112"></a>
<FONT color="green">113</FONT>        this.progress = 0;<a name="line.113"></a>
<FONT color="green">114</FONT>    <a name="line.114"></a>
<FONT color="green">115</FONT>        try {<a name="line.115"></a>
<FONT color="green">116</FONT>          rrConstructor = rrClass.getDeclaredConstructor(constructorSignature);<a name="line.116"></a>
<FONT color="green">117</FONT>          rrConstructor.setAccessible(true);<a name="line.117"></a>
<FONT color="green">118</FONT>        } catch (Exception e) {<a name="line.118"></a>
<FONT color="green">119</FONT>          throw new RuntimeException(rrClass.getName() + <a name="line.119"></a>
<FONT color="green">120</FONT>                                     " does not have valid constructor", e);<a name="line.120"></a>
<FONT color="green">121</FONT>        }<a name="line.121"></a>
<FONT color="green">122</FONT>        initNextRecordReader();<a name="line.122"></a>
<FONT color="green">123</FONT>      }<a name="line.123"></a>
<FONT color="green">124</FONT>      <a name="line.124"></a>
<FONT color="green">125</FONT>      /**<a name="line.125"></a>
<FONT color="green">126</FONT>       * Get the record reader for the next chunk in this CombineFileSplit.<a name="line.126"></a>
<FONT color="green">127</FONT>       */<a name="line.127"></a>
<FONT color="green">128</FONT>      protected boolean initNextRecordReader() throws IOException {<a name="line.128"></a>
<FONT color="green">129</FONT>    <a name="line.129"></a>
<FONT color="green">130</FONT>        if (curReader != null) {<a name="line.130"></a>
<FONT color="green">131</FONT>          curReader.close();<a name="line.131"></a>
<FONT color="green">132</FONT>          curReader = null;<a name="line.132"></a>
<FONT color="green">133</FONT>          if (idx &gt; 0) {<a name="line.133"></a>
<FONT color="green">134</FONT>            progress += split.getLength(idx-1);    // done processing so far<a name="line.134"></a>
<FONT color="green">135</FONT>          }<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>        // if all chunks have been processed, nothing more to do.<a name="line.138"></a>
<FONT color="green">139</FONT>        if (idx == split.getNumPaths()) {<a name="line.139"></a>
<FONT color="green">140</FONT>          return false;<a name="line.140"></a>
<FONT color="green">141</FONT>        }<a name="line.141"></a>
<FONT color="green">142</FONT>    <a name="line.142"></a>
<FONT color="green">143</FONT>        // get a record reader for the idx-th chunk<a name="line.143"></a>
<FONT color="green">144</FONT>        try {<a name="line.144"></a>
<FONT color="green">145</FONT>          curReader =  rrConstructor.newInstance(new Object [] <a name="line.145"></a>
<FONT color="green">146</FONT>                                {split, jc, reporter, Integer.valueOf(idx)});<a name="line.146"></a>
<FONT color="green">147</FONT>    <a name="line.147"></a>
<FONT color="green">148</FONT>          // setup some helper config variables.<a name="line.148"></a>
<FONT color="green">149</FONT>          jc.set(JobContext.MAP_INPUT_FILE, split.getPath(idx).toString());<a name="line.149"></a>
<FONT color="green">150</FONT>          jc.setLong(JobContext.MAP_INPUT_START, split.getOffset(idx));<a name="line.150"></a>
<FONT color="green">151</FONT>          jc.setLong(JobContext.MAP_INPUT_PATH, split.getLength(idx));<a name="line.151"></a>
<FONT color="green">152</FONT>        } catch (Exception e) {<a name="line.152"></a>
<FONT color="green">153</FONT>          throw new RuntimeException (e);<a name="line.153"></a>
<FONT color="green">154</FONT>        }<a name="line.154"></a>
<FONT color="green">155</FONT>        idx++;<a name="line.155"></a>
<FONT color="green">156</FONT>        return true;<a name="line.156"></a>
<FONT color="green">157</FONT>      }<a name="line.157"></a>
<FONT color="green">158</FONT>    }<a name="line.158"></a>




























































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