<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.output;<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.Arrays;<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>    import org.apache.hadoop.fs.Path;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.fs.FileUtil;<a name="line.26"></a>
<FONT color="green">027</FONT>    <a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.io.MapFile;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.io.WritableComparable;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.io.Writable;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.io.SequenceFile.CompressionType;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.io.compress.CompressionCodec;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.io.compress.DefaultCodec;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.Partitioner;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.mapreduce.RecordWriter;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.util.ReflectionUtils;<a name="line.37"></a>
<FONT color="green">038</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.38"></a>
<FONT color="green">039</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.39"></a>
<FONT color="green">040</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.40"></a>
<FONT color="green">041</FONT>    <a name="line.41"></a>
<FONT color="green">042</FONT>    /** <a name="line.42"></a>
<FONT color="green">043</FONT>     * An {@link org.apache.hadoop.mapreduce.OutputFormat} that writes <a name="line.43"></a>
<FONT color="green">044</FONT>     * {@link MapFile}s.<a name="line.44"></a>
<FONT color="green">045</FONT>     */<a name="line.45"></a>
<FONT color="green">046</FONT>    @InterfaceAudience.Public<a name="line.46"></a>
<FONT color="green">047</FONT>    @InterfaceStability.Stable<a name="line.47"></a>
<FONT color="green">048</FONT>    public class MapFileOutputFormat <a name="line.48"></a>
<FONT color="green">049</FONT>        extends FileOutputFormat&lt;WritableComparable&lt;?&gt;, Writable&gt; {<a name="line.49"></a>
<FONT color="green">050</FONT>    <a name="line.50"></a>
<FONT color="green">051</FONT>      public RecordWriter&lt;WritableComparable&lt;?&gt;, Writable&gt; getRecordWriter(<a name="line.51"></a>
<FONT color="green">052</FONT>          TaskAttemptContext context) throws IOException {<a name="line.52"></a>
<FONT color="green">053</FONT>        Configuration conf = context.getConfiguration();<a name="line.53"></a>
<FONT color="green">054</FONT>        CompressionCodec codec = null;<a name="line.54"></a>
<FONT color="green">055</FONT>        CompressionType compressionType = CompressionType.NONE;<a name="line.55"></a>
<FONT color="green">056</FONT>        if (getCompressOutput(context)) {<a name="line.56"></a>
<FONT color="green">057</FONT>          // find the kind of compression to do<a name="line.57"></a>
<FONT color="green">058</FONT>          compressionType = SequenceFileOutputFormat.getOutputCompressionType(context);<a name="line.58"></a>
<FONT color="green">059</FONT>    <a name="line.59"></a>
<FONT color="green">060</FONT>          // find the right codec<a name="line.60"></a>
<FONT color="green">061</FONT>          Class&lt;?&gt; codecClass = getOutputCompressorClass(context,<a name="line.61"></a>
<FONT color="green">062</FONT>                                      DefaultCodec.class);<a name="line.62"></a>
<FONT color="green">063</FONT>          codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf);<a name="line.63"></a>
<FONT color="green">064</FONT>        }<a name="line.64"></a>
<FONT color="green">065</FONT>    <a name="line.65"></a>
<FONT color="green">066</FONT>        Path file = getDefaultWorkFile(context, "");<a name="line.66"></a>
<FONT color="green">067</FONT>        FileSystem fs = file.getFileSystem(conf);<a name="line.67"></a>
<FONT color="green">068</FONT>        // ignore the progress parameter, since MapFile is local<a name="line.68"></a>
<FONT color="green">069</FONT>        final MapFile.Writer out =<a name="line.69"></a>
<FONT color="green">070</FONT>          new MapFile.Writer(conf, fs, file.toString(),<a name="line.70"></a>
<FONT color="green">071</FONT>            context.getOutputKeyClass().asSubclass(WritableComparable.class),<a name="line.71"></a>
<FONT color="green">072</FONT>            context.getOutputValueClass().asSubclass(Writable.class),<a name="line.72"></a>
<FONT color="green">073</FONT>            compressionType, codec, context);<a name="line.73"></a>
<FONT color="green">074</FONT>    <a name="line.74"></a>
<FONT color="green">075</FONT>        return new RecordWriter&lt;WritableComparable&lt;?&gt;, Writable&gt;() {<a name="line.75"></a>
<FONT color="green">076</FONT>            public void write(WritableComparable&lt;?&gt; key, Writable value)<a name="line.76"></a>
<FONT color="green">077</FONT>                throws IOException {<a name="line.77"></a>
<FONT color="green">078</FONT>              out.append(key, value);<a name="line.78"></a>
<FONT color="green">079</FONT>            }<a name="line.79"></a>
<FONT color="green">080</FONT>    <a name="line.80"></a>
<FONT color="green">081</FONT>            public void close(TaskAttemptContext context) throws IOException { <a name="line.81"></a>
<FONT color="green">082</FONT>              out.close();<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>      }<a name="line.85"></a>
<FONT color="green">086</FONT>    <a name="line.86"></a>
<FONT color="green">087</FONT>      /** Open the output generated by this format. */<a name="line.87"></a>
<FONT color="green">088</FONT>      public static MapFile.Reader[] getReaders(Path dir,<a name="line.88"></a>
<FONT color="green">089</FONT>          Configuration conf) throws IOException {<a name="line.89"></a>
<FONT color="green">090</FONT>        FileSystem fs = dir.getFileSystem(conf);<a name="line.90"></a>
<FONT color="green">091</FONT>        Path[] names = FileUtil.stat2Paths(fs.listStatus(dir));<a name="line.91"></a>
<FONT color="green">092</FONT>    <a name="line.92"></a>
<FONT color="green">093</FONT>        // sort names, so that hash partitioning works<a name="line.93"></a>
<FONT color="green">094</FONT>        Arrays.sort(names);<a name="line.94"></a>
<FONT color="green">095</FONT>        <a name="line.95"></a>
<FONT color="green">096</FONT>        MapFile.Reader[] parts = new MapFile.Reader[names.length];<a name="line.96"></a>
<FONT color="green">097</FONT>        for (int i = 0; i &lt; names.length; i++) {<a name="line.97"></a>
<FONT color="green">098</FONT>          parts[i] = new MapFile.Reader(fs, names[i].toString(), conf);<a name="line.98"></a>
<FONT color="green">099</FONT>        }<a name="line.99"></a>
<FONT color="green">100</FONT>        return parts;<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>      /** Get an entry from output generated by this class. */<a name="line.103"></a>
<FONT color="green">104</FONT>      public static &lt;K extends WritableComparable&lt;?&gt;, V extends Writable&gt;<a name="line.104"></a>
<FONT color="green">105</FONT>          Writable getEntry(MapFile.Reader[] readers, <a name="line.105"></a>
<FONT color="green">106</FONT>          Partitioner&lt;K, V&gt; partitioner, K key, V value) throws IOException {<a name="line.106"></a>
<FONT color="green">107</FONT>        int part = partitioner.getPartition(key, value, readers.length);<a name="line.107"></a>
<FONT color="green">108</FONT>        return readers[part].get(key, value);<a name="line.108"></a>
<FONT color="green">109</FONT>      }<a name="line.109"></a>
<FONT color="green">110</FONT>    }<a name="line.110"></a>
<FONT color="green">111</FONT>    <a name="line.111"></a>




























































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