<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.text.NumberFormat;<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.conf.Configuration;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.fs.FileSystem;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.fs.Path;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.io.compress.CompressionCodec;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.fs.FileAlreadyExistsException;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapred.InvalidJobConfException;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.OutputCommitter;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.mapreduce.OutputFormat;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.mapreduce.RecordWriter;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.37"></a>
<FONT color="green">038</FONT>    import org.apache.hadoop.mapreduce.TaskID;<a name="line.38"></a>
<FONT color="green">039</FONT>    import org.apache.hadoop.mapreduce.TaskInputOutputContext;<a name="line.39"></a>
<FONT color="green">040</FONT>    import org.apache.hadoop.mapreduce.security.TokenCache;<a name="line.40"></a>
<FONT color="green">041</FONT>    <a name="line.41"></a>
<FONT color="green">042</FONT>    /** A base class for {@link OutputFormat}s that read from {@link FileSystem}s.*/<a name="line.42"></a>
<FONT color="green">043</FONT>    @InterfaceAudience.Public<a name="line.43"></a>
<FONT color="green">044</FONT>    @InterfaceStability.Stable<a name="line.44"></a>
<FONT color="green">045</FONT>    public abstract class FileOutputFormat&lt;K, V&gt; extends OutputFormat&lt;K, V&gt; {<a name="line.45"></a>
<FONT color="green">046</FONT>    <a name="line.46"></a>
<FONT color="green">047</FONT>      /** Construct output file names so that, when an output directory listing is<a name="line.47"></a>
<FONT color="green">048</FONT>       * sorted lexicographically, positions correspond to output partitions.*/<a name="line.48"></a>
<FONT color="green">049</FONT>      private static final NumberFormat NUMBER_FORMAT = NumberFormat.getInstance();<a name="line.49"></a>
<FONT color="green">050</FONT>      protected static final String BASE_OUTPUT_NAME = "mapreduce.output.basename";<a name="line.50"></a>
<FONT color="green">051</FONT>      protected static final String PART = "part";<a name="line.51"></a>
<FONT color="green">052</FONT>      static {<a name="line.52"></a>
<FONT color="green">053</FONT>        NUMBER_FORMAT.setMinimumIntegerDigits(5);<a name="line.53"></a>
<FONT color="green">054</FONT>        NUMBER_FORMAT.setGroupingUsed(false);<a name="line.54"></a>
<FONT color="green">055</FONT>      }<a name="line.55"></a>
<FONT color="green">056</FONT>      private FileOutputCommitter committer = null;<a name="line.56"></a>
<FONT color="green">057</FONT>    public static final String COMPRESS ="mapreduce.output.fileoutputformat.compress";<a name="line.57"></a>
<FONT color="green">058</FONT>    public static final String COMPRESS_CODEC = <a name="line.58"></a>
<FONT color="green">059</FONT>    "mapreduce.output.fileoutputformat.compress.codec";<a name="line.59"></a>
<FONT color="green">060</FONT>    public static final String COMPRESS_TYPE = "mapreduce.output.fileoutputformat.compress.type";<a name="line.60"></a>
<FONT color="green">061</FONT>    public static final String OUTDIR = "mapreduce.output.fileoutputformat.outputdir";<a name="line.61"></a>
<FONT color="green">062</FONT>    <a name="line.62"></a>
<FONT color="green">063</FONT>      /**<a name="line.63"></a>
<FONT color="green">064</FONT>       * Set whether the output of the job is compressed.<a name="line.64"></a>
<FONT color="green">065</FONT>       * @param job the job to modify<a name="line.65"></a>
<FONT color="green">066</FONT>       * @param compress should the output of the job be compressed?<a name="line.66"></a>
<FONT color="green">067</FONT>       */<a name="line.67"></a>
<FONT color="green">068</FONT>      public static void setCompressOutput(Job job, boolean compress) {<a name="line.68"></a>
<FONT color="green">069</FONT>        job.getConfiguration().setBoolean(FileOutputFormat.COMPRESS, compress);<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>       * Is the job output compressed?<a name="line.73"></a>
<FONT color="green">074</FONT>       * @param job the Job to look in<a name="line.74"></a>
<FONT color="green">075</FONT>       * @return &lt;code&gt;true&lt;/code&gt; if the job output should be compressed,<a name="line.75"></a>
<FONT color="green">076</FONT>       *         &lt;code&gt;false&lt;/code&gt; otherwise<a name="line.76"></a>
<FONT color="green">077</FONT>       */<a name="line.77"></a>
<FONT color="green">078</FONT>      public static boolean getCompressOutput(JobContext job) {<a name="line.78"></a>
<FONT color="green">079</FONT>        return job.getConfiguration().getBoolean(<a name="line.79"></a>
<FONT color="green">080</FONT>          FileOutputFormat.COMPRESS, false);<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>      /**<a name="line.83"></a>
<FONT color="green">084</FONT>       * Set the {@link CompressionCodec} to be used to compress job outputs.<a name="line.84"></a>
<FONT color="green">085</FONT>       * @param job the job to modify<a name="line.85"></a>
<FONT color="green">086</FONT>       * @param codecClass the {@link CompressionCodec} to be used to<a name="line.86"></a>
<FONT color="green">087</FONT>       *                   compress the job outputs<a name="line.87"></a>
<FONT color="green">088</FONT>       */<a name="line.88"></a>
<FONT color="green">089</FONT>      public static void <a name="line.89"></a>
<FONT color="green">090</FONT>      setOutputCompressorClass(Job job, <a name="line.90"></a>
<FONT color="green">091</FONT>                               Class&lt;? extends CompressionCodec&gt; codecClass) {<a name="line.91"></a>
<FONT color="green">092</FONT>        setCompressOutput(job, true);<a name="line.92"></a>
<FONT color="green">093</FONT>        job.getConfiguration().setClass(FileOutputFormat.COMPRESS_CODEC, <a name="line.93"></a>
<FONT color="green">094</FONT>                                        codecClass, <a name="line.94"></a>
<FONT color="green">095</FONT>                                        CompressionCodec.class);<a name="line.95"></a>
<FONT color="green">096</FONT>      }<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>       * Get the {@link CompressionCodec} for compressing the job outputs.<a name="line.99"></a>
<FONT color="green">100</FONT>       * @param job the {@link Job} to look in<a name="line.100"></a>
<FONT color="green">101</FONT>       * @param defaultValue the {@link CompressionCodec} to return if not set<a name="line.101"></a>
<FONT color="green">102</FONT>       * @return the {@link CompressionCodec} to be used to compress the <a name="line.102"></a>
<FONT color="green">103</FONT>       *         job outputs<a name="line.103"></a>
<FONT color="green">104</FONT>       * @throws IllegalArgumentException if the class was specified, but not found<a name="line.104"></a>
<FONT color="green">105</FONT>       */<a name="line.105"></a>
<FONT color="green">106</FONT>      public static Class&lt;? extends CompressionCodec&gt; <a name="line.106"></a>
<FONT color="green">107</FONT>      getOutputCompressorClass(JobContext job, <a name="line.107"></a>
<FONT color="green">108</FONT>                                           Class&lt;? extends CompressionCodec&gt; defaultValue) {<a name="line.108"></a>
<FONT color="green">109</FONT>        Class&lt;? extends CompressionCodec&gt; codecClass = defaultValue;<a name="line.109"></a>
<FONT color="green">110</FONT>        Configuration conf = job.getConfiguration();<a name="line.110"></a>
<FONT color="green">111</FONT>        String name = conf.get(FileOutputFormat.COMPRESS_CODEC);<a name="line.111"></a>
<FONT color="green">112</FONT>        if (name != null) {<a name="line.112"></a>
<FONT color="green">113</FONT>          try {<a name="line.113"></a>
<FONT color="green">114</FONT>            codecClass = <a name="line.114"></a>
<FONT color="green">115</FONT>                    conf.getClassByName(name).asSubclass(CompressionCodec.class);<a name="line.115"></a>
<FONT color="green">116</FONT>          } catch (ClassNotFoundException e) {<a name="line.116"></a>
<FONT color="green">117</FONT>            throw new IllegalArgumentException("Compression codec " + name + <a name="line.117"></a>
<FONT color="green">118</FONT>                                               " was not found.", e);<a name="line.118"></a>
<FONT color="green">119</FONT>          }<a name="line.119"></a>
<FONT color="green">120</FONT>        }<a name="line.120"></a>
<FONT color="green">121</FONT>        return codecClass;<a name="line.121"></a>
<FONT color="green">122</FONT>      }<a name="line.122"></a>
<FONT color="green">123</FONT>      <a name="line.123"></a>
<FONT color="green">124</FONT>      public abstract RecordWriter&lt;K, V&gt; <a name="line.124"></a>
<FONT color="green">125</FONT>         getRecordWriter(TaskAttemptContext job<a name="line.125"></a>
<FONT color="green">126</FONT>                         ) throws IOException, InterruptedException;<a name="line.126"></a>
<FONT color="green">127</FONT>    <a name="line.127"></a>
<FONT color="green">128</FONT>      public void checkOutputSpecs(JobContext job<a name="line.128"></a>
<FONT color="green">129</FONT>                                   ) throws FileAlreadyExistsException, IOException{<a name="line.129"></a>
<FONT color="green">130</FONT>        // Ensure that the output directory is set and not already there<a name="line.130"></a>
<FONT color="green">131</FONT>        Path outDir = getOutputPath(job);<a name="line.131"></a>
<FONT color="green">132</FONT>        if (outDir == null) {<a name="line.132"></a>
<FONT color="green">133</FONT>          throw new InvalidJobConfException("Output directory not set.");<a name="line.133"></a>
<FONT color="green">134</FONT>        }<a name="line.134"></a>
<FONT color="green">135</FONT>    <a name="line.135"></a>
<FONT color="green">136</FONT>        // get delegation token for outDir's file system<a name="line.136"></a>
<FONT color="green">137</FONT>        TokenCache.obtainTokensForNamenodes(job.getCredentials(),<a name="line.137"></a>
<FONT color="green">138</FONT>            new Path[] { outDir }, job.getConfiguration());<a name="line.138"></a>
<FONT color="green">139</FONT>    <a name="line.139"></a>
<FONT color="green">140</FONT>        if (outDir.getFileSystem(job.getConfiguration()).exists(outDir)) {<a name="line.140"></a>
<FONT color="green">141</FONT>          throw new FileAlreadyExistsException("Output directory " + outDir + <a name="line.141"></a>
<FONT color="green">142</FONT>                                               " already exists");<a name="line.142"></a>
<FONT color="green">143</FONT>        }<a name="line.143"></a>
<FONT color="green">144</FONT>      }<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>       * Set the {@link Path} of the output directory for the map-reduce job.<a name="line.147"></a>
<FONT color="green">148</FONT>       *<a name="line.148"></a>
<FONT color="green">149</FONT>       * @param job The job to modify<a name="line.149"></a>
<FONT color="green">150</FONT>       * @param outputDir the {@link Path} of the output directory for <a name="line.150"></a>
<FONT color="green">151</FONT>       * the map-reduce job.<a name="line.151"></a>
<FONT color="green">152</FONT>       */<a name="line.152"></a>
<FONT color="green">153</FONT>      public static void setOutputPath(Job job, Path outputDir) throws IOException {<a name="line.153"></a>
<FONT color="green">154</FONT>        outputDir = outputDir.getFileSystem(job.getConfiguration()).makeQualified(<a name="line.154"></a>
<FONT color="green">155</FONT>            outputDir);<a name="line.155"></a>
<FONT color="green">156</FONT>        job.getConfiguration().set(FileOutputFormat.OUTDIR, outputDir.toString());<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>
<FONT color="green">159</FONT>      /**<a name="line.159"></a>
<FONT color="green">160</FONT>       * Get the {@link Path} to the output directory for the map-reduce job.<a name="line.160"></a>
<FONT color="green">161</FONT>       * <a name="line.161"></a>
<FONT color="green">162</FONT>       * @return the {@link Path} to the output directory for the map-reduce job.<a name="line.162"></a>
<FONT color="green">163</FONT>       * @see FileOutputFormat#getWorkOutputPath(TaskInputOutputContext)<a name="line.163"></a>
<FONT color="green">164</FONT>       */<a name="line.164"></a>
<FONT color="green">165</FONT>      public static Path getOutputPath(JobContext job) {<a name="line.165"></a>
<FONT color="green">166</FONT>        String name = job.getConfiguration().get(FileOutputFormat.OUTDIR);<a name="line.166"></a>
<FONT color="green">167</FONT>        return name == null ? null: new Path(name);<a name="line.167"></a>
<FONT color="green">168</FONT>      }<a name="line.168"></a>
<FONT color="green">169</FONT>      <a name="line.169"></a>
<FONT color="green">170</FONT>      /**<a name="line.170"></a>
<FONT color="green">171</FONT>       *  Get the {@link Path} to the task's temporary output directory <a name="line.171"></a>
<FONT color="green">172</FONT>       *  for the map-reduce job<a name="line.172"></a>
<FONT color="green">173</FONT>       *  <a name="line.173"></a>
<FONT color="green">174</FONT>       * &lt;h4 id="SideEffectFiles"&gt;Tasks' Side-Effect Files&lt;/h4&gt;<a name="line.174"></a>
<FONT color="green">175</FONT>       * <a name="line.175"></a>
<FONT color="green">176</FONT>       * &lt;p&gt;Some applications need to create/write-to side-files, which differ from<a name="line.176"></a>
<FONT color="green">177</FONT>       * the actual job-outputs.<a name="line.177"></a>
<FONT color="green">178</FONT>       * <a name="line.178"></a>
<FONT color="green">179</FONT>       * &lt;p&gt;In such cases there could be issues with 2 instances of the same TIP <a name="line.179"></a>
<FONT color="green">180</FONT>       * (running simultaneously e.g. speculative tasks) trying to open/write-to the<a name="line.180"></a>
<FONT color="green">181</FONT>       * same file (path) on HDFS. Hence the application-writer will have to pick <a name="line.181"></a>
<FONT color="green">182</FONT>       * unique names per task-attempt (e.g. using the attemptid, say <a name="line.182"></a>
<FONT color="green">183</FONT>       * &lt;tt&gt;attempt_200709221812_0001_m_000000_0&lt;/tt&gt;), not just per TIP.&lt;/p&gt; <a name="line.183"></a>
<FONT color="green">184</FONT>       * <a name="line.184"></a>
<FONT color="green">185</FONT>       * &lt;p&gt;To get around this the Map-Reduce framework helps the application-writer <a name="line.185"></a>
<FONT color="green">186</FONT>       * out by maintaining a special <a name="line.186"></a>
<FONT color="green">187</FONT>       * &lt;tt&gt;${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}&lt;/tt&gt; <a name="line.187"></a>
<FONT color="green">188</FONT>       * sub-directory for each task-attempt on HDFS where the output of the <a name="line.188"></a>
<FONT color="green">189</FONT>       * task-attempt goes. On successful completion of the task-attempt the files <a name="line.189"></a>
<FONT color="green">190</FONT>       * in the &lt;tt&gt;${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}&lt;/tt&gt; (only) <a name="line.190"></a>
<FONT color="green">191</FONT>       * are &lt;i&gt;promoted&lt;/i&gt; to &lt;tt&gt;${mapreduce.output.fileoutputformat.outputdir}&lt;/tt&gt;. Of course, the <a name="line.191"></a>
<FONT color="green">192</FONT>       * framework discards the sub-directory of unsuccessful task-attempts. This <a name="line.192"></a>
<FONT color="green">193</FONT>       * is completely transparent to the application.&lt;/p&gt;<a name="line.193"></a>
<FONT color="green">194</FONT>       * <a name="line.194"></a>
<FONT color="green">195</FONT>       * &lt;p&gt;The application-writer can take advantage of this by creating any <a name="line.195"></a>
<FONT color="green">196</FONT>       * side-files required in a work directory during execution <a name="line.196"></a>
<FONT color="green">197</FONT>       * of his task i.e. via <a name="line.197"></a>
<FONT color="green">198</FONT>       * {@link #getWorkOutputPath(TaskInputOutputContext)}, and<a name="line.198"></a>
<FONT color="green">199</FONT>       * the framework will move them out similarly - thus she doesn't have to pick <a name="line.199"></a>
<FONT color="green">200</FONT>       * unique paths per task-attempt.&lt;/p&gt;<a name="line.200"></a>
<FONT color="green">201</FONT>       * <a name="line.201"></a>
<FONT color="green">202</FONT>       * &lt;p&gt;The entire discussion holds true for maps of jobs with <a name="line.202"></a>
<FONT color="green">203</FONT>       * reducer=NONE (i.e. 0 reduces) since output of the map, in that case, <a name="line.203"></a>
<FONT color="green">204</FONT>       * goes directly to HDFS.&lt;/p&gt; <a name="line.204"></a>
<FONT color="green">205</FONT>       * <a name="line.205"></a>
<FONT color="green">206</FONT>       * @return the {@link Path} to the task's temporary output directory <a name="line.206"></a>
<FONT color="green">207</FONT>       * for the map-reduce job.<a name="line.207"></a>
<FONT color="green">208</FONT>       */<a name="line.208"></a>
<FONT color="green">209</FONT>      public static Path getWorkOutputPath(TaskInputOutputContext&lt;?,?,?,?&gt; context<a name="line.209"></a>
<FONT color="green">210</FONT>                                           ) throws IOException, <a name="line.210"></a>
<FONT color="green">211</FONT>                                                    InterruptedException {<a name="line.211"></a>
<FONT color="green">212</FONT>        FileOutputCommitter committer = (FileOutputCommitter) <a name="line.212"></a>
<FONT color="green">213</FONT>          context.getOutputCommitter();<a name="line.213"></a>
<FONT color="green">214</FONT>        return committer.getWorkPath();<a name="line.214"></a>
<FONT color="green">215</FONT>      }<a name="line.215"></a>
<FONT color="green">216</FONT>    <a name="line.216"></a>
<FONT color="green">217</FONT>      /**<a name="line.217"></a>
<FONT color="green">218</FONT>       * Helper function to generate a {@link Path} for a file that is unique for<a name="line.218"></a>
<FONT color="green">219</FONT>       * the task within the job output directory.<a name="line.219"></a>
<FONT color="green">220</FONT>       *<a name="line.220"></a>
<FONT color="green">221</FONT>       * &lt;p&gt;The path can be used to create custom files from within the map and<a name="line.221"></a>
<FONT color="green">222</FONT>       * reduce tasks. The path name will be unique for each task. The path parent<a name="line.222"></a>
<FONT color="green">223</FONT>       * will be the job output directory.&lt;/p&gt;ls<a name="line.223"></a>
<FONT color="green">224</FONT>       *<a name="line.224"></a>
<FONT color="green">225</FONT>       * &lt;p&gt;This method uses the {@link #getUniqueFile} method to make the file name<a name="line.225"></a>
<FONT color="green">226</FONT>       * unique for the task.&lt;/p&gt;<a name="line.226"></a>
<FONT color="green">227</FONT>       *<a name="line.227"></a>
<FONT color="green">228</FONT>       * @param context the context for the task.<a name="line.228"></a>
<FONT color="green">229</FONT>       * @param name the name for the file.<a name="line.229"></a>
<FONT color="green">230</FONT>       * @param extension the extension for the file<a name="line.230"></a>
<FONT color="green">231</FONT>       * @return a unique path accross all tasks of the job.<a name="line.231"></a>
<FONT color="green">232</FONT>       */<a name="line.232"></a>
<FONT color="green">233</FONT>      public <a name="line.233"></a>
<FONT color="green">234</FONT>      static Path getPathForWorkFile(TaskInputOutputContext&lt;?,?,?,?&gt; context, <a name="line.234"></a>
<FONT color="green">235</FONT>                                     String name,<a name="line.235"></a>
<FONT color="green">236</FONT>                                     String extension<a name="line.236"></a>
<FONT color="green">237</FONT>                                    ) throws IOException, InterruptedException {<a name="line.237"></a>
<FONT color="green">238</FONT>        return new Path(getWorkOutputPath(context),<a name="line.238"></a>
<FONT color="green">239</FONT>                        getUniqueFile(context, name, extension));<a name="line.239"></a>
<FONT color="green">240</FONT>      }<a name="line.240"></a>
<FONT color="green">241</FONT>    <a name="line.241"></a>
<FONT color="green">242</FONT>      /**<a name="line.242"></a>
<FONT color="green">243</FONT>       * Generate a unique filename, based on the task id, name, and extension<a name="line.243"></a>
<FONT color="green">244</FONT>       * @param context the task that is calling this<a name="line.244"></a>
<FONT color="green">245</FONT>       * @param name the base filename<a name="line.245"></a>
<FONT color="green">246</FONT>       * @param extension the filename extension<a name="line.246"></a>
<FONT color="green">247</FONT>       * @return a string like $name-[mrsct]-$id$extension<a name="line.247"></a>
<FONT color="green">248</FONT>       */<a name="line.248"></a>
<FONT color="green">249</FONT>      public synchronized static String getUniqueFile(TaskAttemptContext context,<a name="line.249"></a>
<FONT color="green">250</FONT>                                                      String name,<a name="line.250"></a>
<FONT color="green">251</FONT>                                                      String extension) {<a name="line.251"></a>
<FONT color="green">252</FONT>        TaskID taskId = context.getTaskAttemptID().getTaskID();<a name="line.252"></a>
<FONT color="green">253</FONT>        int partition = taskId.getId();<a name="line.253"></a>
<FONT color="green">254</FONT>        StringBuilder result = new StringBuilder();<a name="line.254"></a>
<FONT color="green">255</FONT>        result.append(name);<a name="line.255"></a>
<FONT color="green">256</FONT>        result.append('-');<a name="line.256"></a>
<FONT color="green">257</FONT>        result.append(<a name="line.257"></a>
<FONT color="green">258</FONT>            TaskID.getRepresentingCharacter(taskId.getTaskType()));<a name="line.258"></a>
<FONT color="green">259</FONT>        result.append('-');<a name="line.259"></a>
<FONT color="green">260</FONT>        result.append(NUMBER_FORMAT.format(partition));<a name="line.260"></a>
<FONT color="green">261</FONT>        result.append(extension);<a name="line.261"></a>
<FONT color="green">262</FONT>        return result.toString();<a name="line.262"></a>
<FONT color="green">263</FONT>      }<a name="line.263"></a>
<FONT color="green">264</FONT>    <a name="line.264"></a>
<FONT color="green">265</FONT>      /**<a name="line.265"></a>
<FONT color="green">266</FONT>       * Get the default path and filename for the output format.<a name="line.266"></a>
<FONT color="green">267</FONT>       * @param context the task context<a name="line.267"></a>
<FONT color="green">268</FONT>       * @param extension an extension to add to the filename<a name="line.268"></a>
<FONT color="green">269</FONT>       * @return a full path $output/_temporary/$taskid/part-[mr]-$id<a name="line.269"></a>
<FONT color="green">270</FONT>       * @throws IOException<a name="line.270"></a>
<FONT color="green">271</FONT>       */<a name="line.271"></a>
<FONT color="green">272</FONT>      public Path getDefaultWorkFile(TaskAttemptContext context,<a name="line.272"></a>
<FONT color="green">273</FONT>                                     String extension) throws IOException{<a name="line.273"></a>
<FONT color="green">274</FONT>        FileOutputCommitter committer = <a name="line.274"></a>
<FONT color="green">275</FONT>          (FileOutputCommitter) getOutputCommitter(context);<a name="line.275"></a>
<FONT color="green">276</FONT>        return new Path(committer.getWorkPath(), getUniqueFile(context, <a name="line.276"></a>
<FONT color="green">277</FONT>          getOutputName(context), extension));<a name="line.277"></a>
<FONT color="green">278</FONT>      }<a name="line.278"></a>
<FONT color="green">279</FONT>    <a name="line.279"></a>
<FONT color="green">280</FONT>      /**<a name="line.280"></a>
<FONT color="green">281</FONT>       * Get the base output name for the output file.<a name="line.281"></a>
<FONT color="green">282</FONT>       */<a name="line.282"></a>
<FONT color="green">283</FONT>      protected static String getOutputName(JobContext job) {<a name="line.283"></a>
<FONT color="green">284</FONT>        return job.getConfiguration().get(BASE_OUTPUT_NAME, PART);<a name="line.284"></a>
<FONT color="green">285</FONT>      }<a name="line.285"></a>
<FONT color="green">286</FONT>    <a name="line.286"></a>
<FONT color="green">287</FONT>      /**<a name="line.287"></a>
<FONT color="green">288</FONT>       * Set the base output name for output file to be created.<a name="line.288"></a>
<FONT color="green">289</FONT>       */<a name="line.289"></a>
<FONT color="green">290</FONT>      protected static void setOutputName(JobContext job, String name) {<a name="line.290"></a>
<FONT color="green">291</FONT>        job.getConfiguration().set(BASE_OUTPUT_NAME, name);<a name="line.291"></a>
<FONT color="green">292</FONT>      }<a name="line.292"></a>
<FONT color="green">293</FONT>    <a name="line.293"></a>
<FONT color="green">294</FONT>      public synchronized <a name="line.294"></a>
<FONT color="green">295</FONT>         OutputCommitter getOutputCommitter(TaskAttemptContext context<a name="line.295"></a>
<FONT color="green">296</FONT>                                            ) throws IOException {<a name="line.296"></a>
<FONT color="green">297</FONT>        if (committer == null) {<a name="line.297"></a>
<FONT color="green">298</FONT>          Path output = getOutputPath(context);<a name="line.298"></a>
<FONT color="green">299</FONT>          committer = new FileOutputCommitter(output, context);<a name="line.299"></a>
<FONT color="green">300</FONT>        }<a name="line.300"></a>
<FONT color="green">301</FONT>        return committer;<a name="line.301"></a>
<FONT color="green">302</FONT>      }<a name="line.302"></a>
<FONT color="green">303</FONT>    }<a name="line.303"></a>
<FONT color="green">304</FONT>    <a name="line.304"></a>




























































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