<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.IOException;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.List;<a name="line.22"></a>
<FONT color="green">023</FONT>    <a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.fs.FileStatus;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.fs.PathFilter;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.mapred.InputFormat;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.mapred.InputSplit;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.mapred.JobConf;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapred.RecordReader;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.mapred.Reporter;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.34"></a>
<FONT color="green">035</FONT>    <a name="line.35"></a>
<FONT color="green">036</FONT>    /**<a name="line.36"></a>
<FONT color="green">037</FONT>     * An abstract {@link org.apache.hadoop.mapred.InputFormat} that returns {@link CombineFileSplit}'s<a name="line.37"></a>
<FONT color="green">038</FONT>     * in {@link org.apache.hadoop.mapred.InputFormat#getSplits(JobConf, int)} method. <a name="line.38"></a>
<FONT color="green">039</FONT>     * Splits are constructed from the files under the input paths. <a name="line.39"></a>
<FONT color="green">040</FONT>     * A split cannot have files from different pools.<a name="line.40"></a>
<FONT color="green">041</FONT>     * Each split returned may contain blocks from different files.<a name="line.41"></a>
<FONT color="green">042</FONT>     * If a maxSplitSize is specified, then blocks on the same node are<a name="line.42"></a>
<FONT color="green">043</FONT>     * combined to form a single split. Blocks that are left over are<a name="line.43"></a>
<FONT color="green">044</FONT>     * then combined with other blocks in the same rack. <a name="line.44"></a>
<FONT color="green">045</FONT>     * If maxSplitSize is not specified, then blocks from the same rack<a name="line.45"></a>
<FONT color="green">046</FONT>     * are combined in a single split; no attempt is made to create<a name="line.46"></a>
<FONT color="green">047</FONT>     * node-local splits.<a name="line.47"></a>
<FONT color="green">048</FONT>     * If the maxSplitSize is equal to the block size, then this class<a name="line.48"></a>
<FONT color="green">049</FONT>     * is similar to the default spliting behaviour in Hadoop: each<a name="line.49"></a>
<FONT color="green">050</FONT>     * block is a locally processed split.<a name="line.50"></a>
<FONT color="green">051</FONT>     * Subclasses implement {@link org.apache.hadoop.mapred.InputFormat#getRecordReader(InputSplit, JobConf, Reporter)}<a name="line.51"></a>
<FONT color="green">052</FONT>     * to construct &lt;code&gt;RecordReader&lt;/code&gt;'s for &lt;code&gt;CombineFileSplit&lt;/code&gt;'s.<a name="line.52"></a>
<FONT color="green">053</FONT>     * @see CombineFileSplit<a name="line.53"></a>
<FONT color="green">054</FONT>     */<a name="line.54"></a>
<FONT color="green">055</FONT>    @InterfaceAudience.Public<a name="line.55"></a>
<FONT color="green">056</FONT>    @InterfaceStability.Stable<a name="line.56"></a>
<FONT color="green">057</FONT>    public abstract class CombineFileInputFormat&lt;K, V&gt;<a name="line.57"></a>
<FONT color="green">058</FONT>      extends org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat&lt;K, V&gt; <a name="line.58"></a>
<FONT color="green">059</FONT>      implements InputFormat&lt;K, V&gt;{<a name="line.59"></a>
<FONT color="green">060</FONT>    <a name="line.60"></a>
<FONT color="green">061</FONT>      /**<a name="line.61"></a>
<FONT color="green">062</FONT>       * default constructor<a name="line.62"></a>
<FONT color="green">063</FONT>       */<a name="line.63"></a>
<FONT color="green">064</FONT>      public CombineFileInputFormat() {<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>      public InputSplit[] getSplits(JobConf job, int numSplits) <a name="line.67"></a>
<FONT color="green">068</FONT>        throws IOException {<a name="line.68"></a>
<FONT color="green">069</FONT>        List&lt;org.apache.hadoop.mapreduce.InputSplit&gt; newStyleSplits =<a name="line.69"></a>
<FONT color="green">070</FONT>          super.getSplits(new Job(job));<a name="line.70"></a>
<FONT color="green">071</FONT>        InputSplit[] ret = new InputSplit[newStyleSplits.size()];<a name="line.71"></a>
<FONT color="green">072</FONT>        for(int pos = 0; pos &lt; newStyleSplits.size(); ++pos) {<a name="line.72"></a>
<FONT color="green">073</FONT>          org.apache.hadoop.mapreduce.lib.input.CombineFileSplit newStyleSplit = <a name="line.73"></a>
<FONT color="green">074</FONT>            (org.apache.hadoop.mapreduce.lib.input.CombineFileSplit) newStyleSplits.get(pos);<a name="line.74"></a>
<FONT color="green">075</FONT>          ret[pos] = new CombineFileSplit(job, newStyleSplit.getPaths(),<a name="line.75"></a>
<FONT color="green">076</FONT>            newStyleSplit.getStartOffsets(), newStyleSplit.getLengths(),<a name="line.76"></a>
<FONT color="green">077</FONT>            newStyleSplit.getLocations());<a name="line.77"></a>
<FONT color="green">078</FONT>        }<a name="line.78"></a>
<FONT color="green">079</FONT>        return ret;<a name="line.79"></a>
<FONT color="green">080</FONT>      }<a name="line.80"></a>
<FONT color="green">081</FONT>      <a name="line.81"></a>
<FONT color="green">082</FONT>      /**<a name="line.82"></a>
<FONT color="green">083</FONT>       * Create a new pool and add the filters to it.<a name="line.83"></a>
<FONT color="green">084</FONT>       * A split cannot have files from different pools.<a name="line.84"></a>
<FONT color="green">085</FONT>       * @deprecated Use {@link #createPool(List)}.<a name="line.85"></a>
<FONT color="green">086</FONT>       */<a name="line.86"></a>
<FONT color="green">087</FONT>      @Deprecated<a name="line.87"></a>
<FONT color="green">088</FONT>      protected void createPool(JobConf conf, List&lt;PathFilter&gt; filters) {<a name="line.88"></a>
<FONT color="green">089</FONT>        createPool(filters);<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>       * Create a new pool and add the filters to it. <a name="line.93"></a>
<FONT color="green">094</FONT>       * A pathname can satisfy any one of the specified filters.<a name="line.94"></a>
<FONT color="green">095</FONT>       * A split cannot have files from different pools.<a name="line.95"></a>
<FONT color="green">096</FONT>       * @deprecated Use {@link #createPool(PathFilter...)}.<a name="line.96"></a>
<FONT color="green">097</FONT>       */<a name="line.97"></a>
<FONT color="green">098</FONT>      @Deprecated<a name="line.98"></a>
<FONT color="green">099</FONT>      protected void createPool(JobConf conf, PathFilter... filters) {<a name="line.99"></a>
<FONT color="green">100</FONT>        createPool(filters);<a name="line.100"></a>
<FONT color="green">101</FONT>      }<a name="line.101"></a>
<FONT color="green">102</FONT>    <a name="line.102"></a>
<FONT color="green">103</FONT>      /**<a name="line.103"></a>
<FONT color="green">104</FONT>       * This is not implemented yet. <a name="line.104"></a>
<FONT color="green">105</FONT>       */<a name="line.105"></a>
<FONT color="green">106</FONT>      public abstract RecordReader&lt;K, V&gt; getRecordReader(InputSplit split,<a name="line.106"></a>
<FONT color="green">107</FONT>                                          JobConf job, Reporter reporter)<a name="line.107"></a>
<FONT color="green">108</FONT>        throws IOException;<a name="line.108"></a>
<FONT color="green">109</FONT>    <a name="line.109"></a>
<FONT color="green">110</FONT>      // abstract method from super class implemented to return null<a name="line.110"></a>
<FONT color="green">111</FONT>      public org.apache.hadoop.mapreduce.RecordReader&lt;K, V&gt; createRecordReader(<a name="line.111"></a>
<FONT color="green">112</FONT>          org.apache.hadoop.mapreduce.InputSplit split,<a name="line.112"></a>
<FONT color="green">113</FONT>          TaskAttemptContext context) throws IOException {<a name="line.113"></a>
<FONT color="green">114</FONT>        return null;<a name="line.114"></a>
<FONT color="green">115</FONT>      }<a name="line.115"></a>
<FONT color="green">116</FONT>      <a name="line.116"></a>
<FONT color="green">117</FONT>      /** List input directories.<a name="line.117"></a>
<FONT color="green">118</FONT>       * Subclasses may override to, e.g., select only files matching a regular<a name="line.118"></a>
<FONT color="green">119</FONT>       * expression. <a name="line.119"></a>
<FONT color="green">120</FONT>       * <a name="line.120"></a>
<FONT color="green">121</FONT>       * @param job the job to list input paths for<a name="line.121"></a>
<FONT color="green">122</FONT>       * @return array of FileStatus objects<a name="line.122"></a>
<FONT color="green">123</FONT>       * @throws IOException if zero items.<a name="line.123"></a>
<FONT color="green">124</FONT>       */<a name="line.124"></a>
<FONT color="green">125</FONT>      protected FileStatus[] listStatus(JobConf job) throws IOException {<a name="line.125"></a>
<FONT color="green">126</FONT>        List&lt;FileStatus&gt; result = super.listStatus(new Job(job));<a name="line.126"></a>
<FONT color="green">127</FONT>        return result.toArray(new FileStatus[result.size()]);<a name="line.127"></a>
<FONT color="green">128</FONT>      }<a name="line.128"></a>
<FONT color="green">129</FONT>    <a name="line.129"></a>
<FONT color="green">130</FONT>    }<a name="line.130"></a>




























































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