<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>    package org.apache.hadoop.mapred;<a name="line.18"></a>
<FONT color="green">019</FONT>    <a name="line.19"></a>
<FONT color="green">020</FONT>    import java.io.IOException;<a name="line.20"></a>
<FONT color="green">021</FONT>    <a name="line.21"></a>
<FONT color="green">022</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.22"></a>
<FONT color="green">023</FONT>    import org.apache.hadoop.classification.InterfaceStability;<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.io.BytesWritable;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.io.SequenceFile;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.io.SequenceFile.CompressionType;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.io.Writable;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.io.WritableComparable;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.io.compress.CompressionCodec;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.io.compress.DefaultCodec;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.util.Progressable;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.util.ReflectionUtils;<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 {@link OutputFormat} that writes keys, values to <a name="line.37"></a>
<FONT color="green">038</FONT>     * {@link SequenceFile}s in binary(raw) format<a name="line.38"></a>
<FONT color="green">039</FONT>     */<a name="line.39"></a>
<FONT color="green">040</FONT>    @InterfaceAudience.Public<a name="line.40"></a>
<FONT color="green">041</FONT>    @InterfaceStability.Stable<a name="line.41"></a>
<FONT color="green">042</FONT>    public class SequenceFileAsBinaryOutputFormat <a name="line.42"></a>
<FONT color="green">043</FONT>     extends SequenceFileOutputFormat &lt;BytesWritable,BytesWritable&gt; {<a name="line.43"></a>
<FONT color="green">044</FONT>    <a name="line.44"></a>
<FONT color="green">045</FONT>      /** <a name="line.45"></a>
<FONT color="green">046</FONT>       * Inner class used for appendRaw<a name="line.46"></a>
<FONT color="green">047</FONT>       */<a name="line.47"></a>
<FONT color="green">048</FONT>      static protected class WritableValueBytes extends org.apache.hadoop.mapreduce<a name="line.48"></a>
<FONT color="green">049</FONT>          .lib.output.SequenceFileAsBinaryOutputFormat.WritableValueBytes {<a name="line.49"></a>
<FONT color="green">050</FONT>      }<a name="line.50"></a>
<FONT color="green">051</FONT>    <a name="line.51"></a>
<FONT color="green">052</FONT>      /**<a name="line.52"></a>
<FONT color="green">053</FONT>       * Set the key class for the {@link SequenceFile}<a name="line.53"></a>
<FONT color="green">054</FONT>       * &lt;p&gt;This allows the user to specify the key class to be different <a name="line.54"></a>
<FONT color="green">055</FONT>       * from the actual class ({@link BytesWritable}) used for writing &lt;/p&gt;<a name="line.55"></a>
<FONT color="green">056</FONT>       * <a name="line.56"></a>
<FONT color="green">057</FONT>       * @param conf the {@link JobConf} to modify<a name="line.57"></a>
<FONT color="green">058</FONT>       * @param theClass the SequenceFile output key class.<a name="line.58"></a>
<FONT color="green">059</FONT>       */<a name="line.59"></a>
<FONT color="green">060</FONT>      static public void setSequenceFileOutputKeyClass(JobConf conf, <a name="line.60"></a>
<FONT color="green">061</FONT>                                                       Class&lt;?&gt; theClass) {<a name="line.61"></a>
<FONT color="green">062</FONT>        conf.setClass(org.apache.hadoop.mapreduce.lib.output.<a name="line.62"></a>
<FONT color="green">063</FONT>          SequenceFileAsBinaryOutputFormat.KEY_CLASS, theClass, Object.class);<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>      /**<a name="line.66"></a>
<FONT color="green">067</FONT>       * Set the value class for the {@link SequenceFile}<a name="line.67"></a>
<FONT color="green">068</FONT>       * &lt;p&gt;This allows the user to specify the value class to be different <a name="line.68"></a>
<FONT color="green">069</FONT>       * from the actual class ({@link BytesWritable}) used for writing &lt;/p&gt;<a name="line.69"></a>
<FONT color="green">070</FONT>       * <a name="line.70"></a>
<FONT color="green">071</FONT>       * @param conf the {@link JobConf} to modify<a name="line.71"></a>
<FONT color="green">072</FONT>       * @param theClass the SequenceFile output key class.<a name="line.72"></a>
<FONT color="green">073</FONT>       */<a name="line.73"></a>
<FONT color="green">074</FONT>      static public void setSequenceFileOutputValueClass(JobConf conf, <a name="line.74"></a>
<FONT color="green">075</FONT>                                                         Class&lt;?&gt; theClass) {<a name="line.75"></a>
<FONT color="green">076</FONT>        conf.setClass(org.apache.hadoop.mapreduce.lib.output.<a name="line.76"></a>
<FONT color="green">077</FONT>          SequenceFileAsBinaryOutputFormat.VALUE_CLASS, theClass, Object.class);<a name="line.77"></a>
<FONT color="green">078</FONT>      }<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>       * Get the key class for the {@link SequenceFile}<a name="line.81"></a>
<FONT color="green">082</FONT>       * <a name="line.82"></a>
<FONT color="green">083</FONT>       * @return the key class of the {@link SequenceFile}<a name="line.83"></a>
<FONT color="green">084</FONT>       */<a name="line.84"></a>
<FONT color="green">085</FONT>      static public Class&lt;? extends WritableComparable&gt; getSequenceFileOutputKeyClass(JobConf conf) { <a name="line.85"></a>
<FONT color="green">086</FONT>        return conf.getClass(org.apache.hadoop.mapreduce.lib.output.<a name="line.86"></a>
<FONT color="green">087</FONT>          SequenceFileAsBinaryOutputFormat.KEY_CLASS, <a name="line.87"></a>
<FONT color="green">088</FONT>          conf.getOutputKeyClass().asSubclass(WritableComparable.class),<a name="line.88"></a>
<FONT color="green">089</FONT>          WritableComparable.class);<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>       * Get the value class for the {@link SequenceFile}<a name="line.93"></a>
<FONT color="green">094</FONT>       * <a name="line.94"></a>
<FONT color="green">095</FONT>       * @return the value class of the {@link SequenceFile}<a name="line.95"></a>
<FONT color="green">096</FONT>       */<a name="line.96"></a>
<FONT color="green">097</FONT>      static public Class&lt;? extends Writable&gt; getSequenceFileOutputValueClass(JobConf conf) { <a name="line.97"></a>
<FONT color="green">098</FONT>        return conf.getClass(org.apache.hadoop.mapreduce.lib.output.<a name="line.98"></a>
<FONT color="green">099</FONT>          SequenceFileAsBinaryOutputFormat.VALUE_CLASS, <a name="line.99"></a>
<FONT color="green">100</FONT>          conf.getOutputValueClass().asSubclass(Writable.class), Writable.class);<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>      @Override <a name="line.103"></a>
<FONT color="green">104</FONT>      public RecordWriter &lt;BytesWritable, BytesWritable&gt; <a name="line.104"></a>
<FONT color="green">105</FONT>                 getRecordWriter(FileSystem ignored, JobConf job,<a name="line.105"></a>
<FONT color="green">106</FONT>                                 String name, Progressable progress)<a name="line.106"></a>
<FONT color="green">107</FONT>        throws IOException {<a name="line.107"></a>
<FONT color="green">108</FONT>        // get the path of the temporary output file <a name="line.108"></a>
<FONT color="green">109</FONT>        Path file = FileOutputFormat.getTaskOutputPath(job, name);<a name="line.109"></a>
<FONT color="green">110</FONT>        <a name="line.110"></a>
<FONT color="green">111</FONT>        FileSystem fs = file.getFileSystem(job);<a name="line.111"></a>
<FONT color="green">112</FONT>        CompressionCodec codec = null;<a name="line.112"></a>
<FONT color="green">113</FONT>        CompressionType compressionType = CompressionType.NONE;<a name="line.113"></a>
<FONT color="green">114</FONT>        if (getCompressOutput(job)) {<a name="line.114"></a>
<FONT color="green">115</FONT>          // find the kind of compression to do<a name="line.115"></a>
<FONT color="green">116</FONT>          compressionType = getOutputCompressionType(job);<a name="line.116"></a>
<FONT color="green">117</FONT>    <a name="line.117"></a>
<FONT color="green">118</FONT>          // find the right codec<a name="line.118"></a>
<FONT color="green">119</FONT>          Class&lt;? extends CompressionCodec&gt; codecClass = getOutputCompressorClass(job,<a name="line.119"></a>
<FONT color="green">120</FONT>              DefaultCodec.class);<a name="line.120"></a>
<FONT color="green">121</FONT>          codec = ReflectionUtils.newInstance(codecClass, job);<a name="line.121"></a>
<FONT color="green">122</FONT>        }<a name="line.122"></a>
<FONT color="green">123</FONT>        final SequenceFile.Writer out = <a name="line.123"></a>
<FONT color="green">124</FONT>          SequenceFile.createWriter(fs, job, file,<a name="line.124"></a>
<FONT color="green">125</FONT>                        getSequenceFileOutputKeyClass(job),<a name="line.125"></a>
<FONT color="green">126</FONT>                        getSequenceFileOutputValueClass(job),<a name="line.126"></a>
<FONT color="green">127</FONT>                        compressionType,<a name="line.127"></a>
<FONT color="green">128</FONT>                        codec,<a name="line.128"></a>
<FONT color="green">129</FONT>                        progress);<a name="line.129"></a>
<FONT color="green">130</FONT>    <a name="line.130"></a>
<FONT color="green">131</FONT>        return new RecordWriter&lt;BytesWritable, BytesWritable&gt;() {<a name="line.131"></a>
<FONT color="green">132</FONT>            <a name="line.132"></a>
<FONT color="green">133</FONT>            private WritableValueBytes wvaluebytes = new WritableValueBytes();<a name="line.133"></a>
<FONT color="green">134</FONT>    <a name="line.134"></a>
<FONT color="green">135</FONT>            public void write(BytesWritable bkey, BytesWritable bvalue)<a name="line.135"></a>
<FONT color="green">136</FONT>              throws IOException {<a name="line.136"></a>
<FONT color="green">137</FONT>    <a name="line.137"></a>
<FONT color="green">138</FONT>              wvaluebytes.reset(bvalue);<a name="line.138"></a>
<FONT color="green">139</FONT>              out.appendRaw(bkey.getBytes(), 0, bkey.getLength(), wvaluebytes);<a name="line.139"></a>
<FONT color="green">140</FONT>              wvaluebytes.reset(null);<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>            public void close(Reporter reporter) throws IOException { <a name="line.143"></a>
<FONT color="green">144</FONT>              out.close();<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>    <a name="line.148"></a>
<FONT color="green">149</FONT>      }<a name="line.149"></a>
<FONT color="green">150</FONT>    <a name="line.150"></a>
<FONT color="green">151</FONT>      @Override <a name="line.151"></a>
<FONT color="green">152</FONT>      public void checkOutputSpecs(FileSystem ignored, JobConf job) <a name="line.152"></a>
<FONT color="green">153</FONT>                throws IOException {<a name="line.153"></a>
<FONT color="green">154</FONT>        super.checkOutputSpecs(ignored, job);<a name="line.154"></a>
<FONT color="green">155</FONT>        if (getCompressOutput(job) &amp;&amp; <a name="line.155"></a>
<FONT color="green">156</FONT>            getOutputCompressionType(job) == CompressionType.RECORD ){<a name="line.156"></a>
<FONT color="green">157</FONT>            throw new InvalidJobConfException("SequenceFileAsBinaryOutputFormat "<a name="line.157"></a>
<FONT color="green">158</FONT>                        + "doesn't support Record Compression" );<a name="line.158"></a>
<FONT color="green">159</FONT>        }<a name="line.159"></a>
<FONT color="green">160</FONT>    <a name="line.160"></a>
<FONT color="green">161</FONT>      }<a name="line.161"></a>
<FONT color="green">162</FONT>    <a name="line.162"></a>
<FONT color="green">163</FONT>    }<a name="line.163"></a>




























































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