<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.mapreduce.lib.output;<a name="line.18"></a>
<FONT color="green">019</FONT>    <a name="line.19"></a>
<FONT color="green">020</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.20"></a>
<FONT color="green">021</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.21"></a>
<FONT color="green">022</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.22"></a>
<FONT color="green">023</FONT>    import org.apache.hadoop.mapreduce.*;<a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl;<a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.util.ReflectionUtils;<a name="line.25"></a>
<FONT color="green">026</FONT>    <a name="line.26"></a>
<FONT color="green">027</FONT>    import java.io.IOException;<a name="line.27"></a>
<FONT color="green">028</FONT>    import java.util.*;<a name="line.28"></a>
<FONT color="green">029</FONT>    <a name="line.29"></a>
<FONT color="green">030</FONT>    /**<a name="line.30"></a>
<FONT color="green">031</FONT>     * The MultipleOutputs class simplifies writing output data <a name="line.31"></a>
<FONT color="green">032</FONT>     * to multiple outputs<a name="line.32"></a>
<FONT color="green">033</FONT>     * <a name="line.33"></a>
<FONT color="green">034</FONT>     * &lt;p&gt; <a name="line.34"></a>
<FONT color="green">035</FONT>     * Case one: writing to additional outputs other than the job default output.<a name="line.35"></a>
<FONT color="green">036</FONT>     *<a name="line.36"></a>
<FONT color="green">037</FONT>     * Each additional output, or named output, may be configured with its own<a name="line.37"></a>
<FONT color="green">038</FONT>     * &lt;code&gt;OutputFormat&lt;/code&gt;, with its own key class and with its own value<a name="line.38"></a>
<FONT color="green">039</FONT>     * class.<a name="line.39"></a>
<FONT color="green">040</FONT>     * <a name="line.40"></a>
<FONT color="green">041</FONT>     * &lt;p&gt;<a name="line.41"></a>
<FONT color="green">042</FONT>     * Case two: to write data to different files provided by user<a name="line.42"></a>
<FONT color="green">043</FONT>     * &lt;/p&gt;<a name="line.43"></a>
<FONT color="green">044</FONT>     * <a name="line.44"></a>
<FONT color="green">045</FONT>     * &lt;p&gt;<a name="line.45"></a>
<FONT color="green">046</FONT>     * MultipleOutputs supports counters, by default they are disabled. The <a name="line.46"></a>
<FONT color="green">047</FONT>     * counters group is the {@link MultipleOutputs} class name. The names of the <a name="line.47"></a>
<FONT color="green">048</FONT>     * counters are the same as the output name. These count the number records <a name="line.48"></a>
<FONT color="green">049</FONT>     * written to each output name.<a name="line.49"></a>
<FONT color="green">050</FONT>     * &lt;/p&gt;<a name="line.50"></a>
<FONT color="green">051</FONT>     * <a name="line.51"></a>
<FONT color="green">052</FONT>     * Usage pattern for job submission:<a name="line.52"></a>
<FONT color="green">053</FONT>     * &lt;pre&gt;<a name="line.53"></a>
<FONT color="green">054</FONT>     *<a name="line.54"></a>
<FONT color="green">055</FONT>     * Job job = new Job();<a name="line.55"></a>
<FONT color="green">056</FONT>     *<a name="line.56"></a>
<FONT color="green">057</FONT>     * FileInputFormat.setInputPath(job, inDir);<a name="line.57"></a>
<FONT color="green">058</FONT>     * FileOutputFormat.setOutputPath(job, outDir);<a name="line.58"></a>
<FONT color="green">059</FONT>     *<a name="line.59"></a>
<FONT color="green">060</FONT>     * job.setMapperClass(MOMap.class);<a name="line.60"></a>
<FONT color="green">061</FONT>     * job.setReducerClass(MOReduce.class);<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>     * // Defines additional single text based output 'text' for the job<a name="line.64"></a>
<FONT color="green">065</FONT>     * MultipleOutputs.addNamedOutput(job, "text", TextOutputFormat.class,<a name="line.65"></a>
<FONT color="green">066</FONT>     * LongWritable.class, Text.class);<a name="line.66"></a>
<FONT color="green">067</FONT>     *<a name="line.67"></a>
<FONT color="green">068</FONT>     * // Defines additional sequence-file based output 'sequence' for the job<a name="line.68"></a>
<FONT color="green">069</FONT>     * MultipleOutputs.addNamedOutput(job, "seq",<a name="line.69"></a>
<FONT color="green">070</FONT>     *   SequenceFileOutputFormat.class,<a name="line.70"></a>
<FONT color="green">071</FONT>     *   LongWritable.class, Text.class);<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>     * job.waitForCompletion(true);<a name="line.74"></a>
<FONT color="green">075</FONT>     * ...<a name="line.75"></a>
<FONT color="green">076</FONT>     * &lt;/pre&gt;<a name="line.76"></a>
<FONT color="green">077</FONT>     * &lt;p&gt;<a name="line.77"></a>
<FONT color="green">078</FONT>     * Usage in Reducer:<a name="line.78"></a>
<FONT color="green">079</FONT>     * &lt;pre&gt;<a name="line.79"></a>
<FONT color="green">080</FONT>     * &lt;K, V&gt; String generateFileName(K k, V v) {<a name="line.80"></a>
<FONT color="green">081</FONT>     *   return k.toString() + "_" + v.toString();<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>     * public class MOReduce extends<a name="line.84"></a>
<FONT color="green">085</FONT>     *   Reducer&amp;lt;WritableComparable, Writable,WritableComparable, Writable&amp;gt; {<a name="line.85"></a>
<FONT color="green">086</FONT>     * private MultipleOutputs mos;<a name="line.86"></a>
<FONT color="green">087</FONT>     * public void setup(Context context) {<a name="line.87"></a>
<FONT color="green">088</FONT>     * ...<a name="line.88"></a>
<FONT color="green">089</FONT>     * mos = new MultipleOutputs(context);<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>     * public void reduce(WritableComparable key, Iterator&amp;lt;Writable&amp;gt; values,<a name="line.92"></a>
<FONT color="green">093</FONT>     * Context context)<a name="line.93"></a>
<FONT color="green">094</FONT>     * throws IOException {<a name="line.94"></a>
<FONT color="green">095</FONT>     * ...<a name="line.95"></a>
<FONT color="green">096</FONT>     * mos.write("text", , key, new Text("Hello"));<a name="line.96"></a>
<FONT color="green">097</FONT>     * mos.write("seq", LongWritable(1), new Text("Bye"), "seq_a");<a name="line.97"></a>
<FONT color="green">098</FONT>     * mos.write("seq", LongWritable(2), key, new Text("Chau"), "seq_b");<a name="line.98"></a>
<FONT color="green">099</FONT>     * mos.write(key, new Text("value"), generateFileName(key, new Text("value")));<a name="line.99"></a>
<FONT color="green">100</FONT>     * ...<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>     * public void cleanup(Context) throws IOException {<a name="line.103"></a>
<FONT color="green">104</FONT>     * mos.close();<a name="line.104"></a>
<FONT color="green">105</FONT>     * ...<a name="line.105"></a>
<FONT color="green">106</FONT>     * }<a name="line.106"></a>
<FONT color="green">107</FONT>     *<a name="line.107"></a>
<FONT color="green">108</FONT>     * }<a name="line.108"></a>
<FONT color="green">109</FONT>     * &lt;/pre&gt;<a name="line.109"></a>
<FONT color="green">110</FONT>     */<a name="line.110"></a>
<FONT color="green">111</FONT>    @InterfaceAudience.Public<a name="line.111"></a>
<FONT color="green">112</FONT>    @InterfaceStability.Stable<a name="line.112"></a>
<FONT color="green">113</FONT>    public class MultipleOutputs&lt;KEYOUT, VALUEOUT&gt; {<a name="line.113"></a>
<FONT color="green">114</FONT>    <a name="line.114"></a>
<FONT color="green">115</FONT>      private static final String MULTIPLE_OUTPUTS = "mapreduce.multipleoutputs";<a name="line.115"></a>
<FONT color="green">116</FONT>    <a name="line.116"></a>
<FONT color="green">117</FONT>      private static final String MO_PREFIX = <a name="line.117"></a>
<FONT color="green">118</FONT>        "mapreduce.multipleoutputs.namedOutput.";<a name="line.118"></a>
<FONT color="green">119</FONT>    <a name="line.119"></a>
<FONT color="green">120</FONT>      private static final String FORMAT = ".format";<a name="line.120"></a>
<FONT color="green">121</FONT>      private static final String KEY = ".key";<a name="line.121"></a>
<FONT color="green">122</FONT>      private static final String VALUE = ".value";<a name="line.122"></a>
<FONT color="green">123</FONT>      private static final String COUNTERS_ENABLED = <a name="line.123"></a>
<FONT color="green">124</FONT>        "mapreduce.multipleoutputs.counters";<a name="line.124"></a>
<FONT color="green">125</FONT>    <a name="line.125"></a>
<FONT color="green">126</FONT>      /**<a name="line.126"></a>
<FONT color="green">127</FONT>       * Counters group used by the counters of MultipleOutputs.<a name="line.127"></a>
<FONT color="green">128</FONT>       */<a name="line.128"></a>
<FONT color="green">129</FONT>      private static final String COUNTERS_GROUP = MultipleOutputs.class.getName();<a name="line.129"></a>
<FONT color="green">130</FONT>    <a name="line.130"></a>
<FONT color="green">131</FONT>      /**<a name="line.131"></a>
<FONT color="green">132</FONT>       * Cache for the taskContexts<a name="line.132"></a>
<FONT color="green">133</FONT>       */<a name="line.133"></a>
<FONT color="green">134</FONT>      private Map&lt;String, TaskAttemptContext&gt; taskContexts = new HashMap&lt;String, TaskAttemptContext&gt;();<a name="line.134"></a>
<FONT color="green">135</FONT>      /**<a name="line.135"></a>
<FONT color="green">136</FONT>       * Cached TaskAttemptContext which uses the job's configured settings<a name="line.136"></a>
<FONT color="green">137</FONT>       */<a name="line.137"></a>
<FONT color="green">138</FONT>      private TaskAttemptContext jobOutputFormatContext;<a name="line.138"></a>
<FONT color="green">139</FONT>    <a name="line.139"></a>
<FONT color="green">140</FONT>      /**<a name="line.140"></a>
<FONT color="green">141</FONT>       * Checks if a named output name is valid token.<a name="line.141"></a>
<FONT color="green">142</FONT>       *<a name="line.142"></a>
<FONT color="green">143</FONT>       * @param namedOutput named output Name<a name="line.143"></a>
<FONT color="green">144</FONT>       * @throws IllegalArgumentException if the output name is not valid.<a name="line.144"></a>
<FONT color="green">145</FONT>       */<a name="line.145"></a>
<FONT color="green">146</FONT>      private static void checkTokenName(String namedOutput) {<a name="line.146"></a>
<FONT color="green">147</FONT>        if (namedOutput == null || namedOutput.length() == 0) {<a name="line.147"></a>
<FONT color="green">148</FONT>          throw new IllegalArgumentException(<a name="line.148"></a>
<FONT color="green">149</FONT>            "Name cannot be NULL or emtpy");<a name="line.149"></a>
<FONT color="green">150</FONT>        }<a name="line.150"></a>
<FONT color="green">151</FONT>        for (char ch : namedOutput.toCharArray()) {<a name="line.151"></a>
<FONT color="green">152</FONT>          if ((ch &gt;= 'A') &amp;&amp; (ch &lt;= 'Z')) {<a name="line.152"></a>
<FONT color="green">153</FONT>            continue;<a name="line.153"></a>
<FONT color="green">154</FONT>          }<a name="line.154"></a>
<FONT color="green">155</FONT>          if ((ch &gt;= 'a') &amp;&amp; (ch &lt;= 'z')) {<a name="line.155"></a>
<FONT color="green">156</FONT>            continue;<a name="line.156"></a>
<FONT color="green">157</FONT>          }<a name="line.157"></a>
<FONT color="green">158</FONT>          if ((ch &gt;= '0') &amp;&amp; (ch &lt;= '9')) {<a name="line.158"></a>
<FONT color="green">159</FONT>            continue;<a name="line.159"></a>
<FONT color="green">160</FONT>          }<a name="line.160"></a>
<FONT color="green">161</FONT>          throw new IllegalArgumentException(<a name="line.161"></a>
<FONT color="green">162</FONT>            "Name cannot be have a '" + ch + "' char");<a name="line.162"></a>
<FONT color="green">163</FONT>        }<a name="line.163"></a>
<FONT color="green">164</FONT>      }<a name="line.164"></a>
<FONT color="green">165</FONT>    <a name="line.165"></a>
<FONT color="green">166</FONT>      /**<a name="line.166"></a>
<FONT color="green">167</FONT>       * Checks if output name is valid.<a name="line.167"></a>
<FONT color="green">168</FONT>       *<a name="line.168"></a>
<FONT color="green">169</FONT>       * name cannot be the name used for the default output<a name="line.169"></a>
<FONT color="green">170</FONT>       * @param outputPath base output Name<a name="line.170"></a>
<FONT color="green">171</FONT>       * @throws IllegalArgumentException if the output name is not valid.<a name="line.171"></a>
<FONT color="green">172</FONT>       */<a name="line.172"></a>
<FONT color="green">173</FONT>      private static void checkBaseOutputPath(String outputPath) {<a name="line.173"></a>
<FONT color="green">174</FONT>        if (outputPath.equals(FileOutputFormat.PART)) {<a name="line.174"></a>
<FONT color="green">175</FONT>          throw new IllegalArgumentException("output name cannot be 'part'");<a name="line.175"></a>
<FONT color="green">176</FONT>        }<a name="line.176"></a>
<FONT color="green">177</FONT>      }<a name="line.177"></a>
<FONT color="green">178</FONT>      <a name="line.178"></a>
<FONT color="green">179</FONT>      /**<a name="line.179"></a>
<FONT color="green">180</FONT>       * Checks if a named output name is valid.<a name="line.180"></a>
<FONT color="green">181</FONT>       *<a name="line.181"></a>
<FONT color="green">182</FONT>       * @param namedOutput named output Name<a name="line.182"></a>
<FONT color="green">183</FONT>       * @throws IllegalArgumentException if the output name is not valid.<a name="line.183"></a>
<FONT color="green">184</FONT>       */<a name="line.184"></a>
<FONT color="green">185</FONT>      private static void checkNamedOutputName(JobContext job,<a name="line.185"></a>
<FONT color="green">186</FONT>          String namedOutput, boolean alreadyDefined) {<a name="line.186"></a>
<FONT color="green">187</FONT>        checkTokenName(namedOutput);<a name="line.187"></a>
<FONT color="green">188</FONT>        checkBaseOutputPath(namedOutput);<a name="line.188"></a>
<FONT color="green">189</FONT>        List&lt;String&gt; definedChannels = getNamedOutputsList(job);<a name="line.189"></a>
<FONT color="green">190</FONT>        if (alreadyDefined &amp;&amp; definedChannels.contains(namedOutput)) {<a name="line.190"></a>
<FONT color="green">191</FONT>          throw new IllegalArgumentException("Named output '" + namedOutput +<a name="line.191"></a>
<FONT color="green">192</FONT>            "' already alreadyDefined");<a name="line.192"></a>
<FONT color="green">193</FONT>        } else if (!alreadyDefined &amp;&amp; !definedChannels.contains(namedOutput)) {<a name="line.193"></a>
<FONT color="green">194</FONT>          throw new IllegalArgumentException("Named output '" + namedOutput +<a name="line.194"></a>
<FONT color="green">195</FONT>            "' not defined");<a name="line.195"></a>
<FONT color="green">196</FONT>        }<a name="line.196"></a>
<FONT color="green">197</FONT>      }<a name="line.197"></a>
<FONT color="green">198</FONT>    <a name="line.198"></a>
<FONT color="green">199</FONT>      // Returns list of channel names.<a name="line.199"></a>
<FONT color="green">200</FONT>      private static List&lt;String&gt; getNamedOutputsList(JobContext job) {<a name="line.200"></a>
<FONT color="green">201</FONT>        List&lt;String&gt; names = new ArrayList&lt;String&gt;();<a name="line.201"></a>
<FONT color="green">202</FONT>        StringTokenizer st = new StringTokenizer(<a name="line.202"></a>
<FONT color="green">203</FONT>          job.getConfiguration().get(MULTIPLE_OUTPUTS, ""), " ");<a name="line.203"></a>
<FONT color="green">204</FONT>        while (st.hasMoreTokens()) {<a name="line.204"></a>
<FONT color="green">205</FONT>          names.add(st.nextToken());<a name="line.205"></a>
<FONT color="green">206</FONT>        }<a name="line.206"></a>
<FONT color="green">207</FONT>        return names;<a name="line.207"></a>
<FONT color="green">208</FONT>      }<a name="line.208"></a>
<FONT color="green">209</FONT>    <a name="line.209"></a>
<FONT color="green">210</FONT>      // Returns the named output OutputFormat.<a name="line.210"></a>
<FONT color="green">211</FONT>      @SuppressWarnings("unchecked")<a name="line.211"></a>
<FONT color="green">212</FONT>      private static Class&lt;? extends OutputFormat&lt;?, ?&gt;&gt; getNamedOutputFormatClass(<a name="line.212"></a>
<FONT color="green">213</FONT>        JobContext job, String namedOutput) {<a name="line.213"></a>
<FONT color="green">214</FONT>        return (Class&lt;? extends OutputFormat&lt;?, ?&gt;&gt;)<a name="line.214"></a>
<FONT color="green">215</FONT>          job.getConfiguration().getClass(MO_PREFIX + namedOutput + FORMAT, null,<a name="line.215"></a>
<FONT color="green">216</FONT>          OutputFormat.class);<a name="line.216"></a>
<FONT color="green">217</FONT>      }<a name="line.217"></a>
<FONT color="green">218</FONT>    <a name="line.218"></a>
<FONT color="green">219</FONT>      // Returns the key class for a named output.<a name="line.219"></a>
<FONT color="green">220</FONT>      private static Class&lt;?&gt; getNamedOutputKeyClass(JobContext job,<a name="line.220"></a>
<FONT color="green">221</FONT>                                                    String namedOutput) {<a name="line.221"></a>
<FONT color="green">222</FONT>        return job.getConfiguration().getClass(MO_PREFIX + namedOutput + KEY, null,<a name="line.222"></a>
<FONT color="green">223</FONT>          Object.class);<a name="line.223"></a>
<FONT color="green">224</FONT>      }<a name="line.224"></a>
<FONT color="green">225</FONT>    <a name="line.225"></a>
<FONT color="green">226</FONT>      // Returns the value class for a named output.<a name="line.226"></a>
<FONT color="green">227</FONT>      private static Class&lt;?&gt; getNamedOutputValueClass(<a name="line.227"></a>
<FONT color="green">228</FONT>          JobContext job, String namedOutput) {<a name="line.228"></a>
<FONT color="green">229</FONT>        return job.getConfiguration().getClass(MO_PREFIX + namedOutput + VALUE,<a name="line.229"></a>
<FONT color="green">230</FONT>          null, Object.class);<a name="line.230"></a>
<FONT color="green">231</FONT>      }<a name="line.231"></a>
<FONT color="green">232</FONT>    <a name="line.232"></a>
<FONT color="green">233</FONT>      /**<a name="line.233"></a>
<FONT color="green">234</FONT>       * Adds a named output for the job.<a name="line.234"></a>
<FONT color="green">235</FONT>       * &lt;p/&gt;<a name="line.235"></a>
<FONT color="green">236</FONT>       *<a name="line.236"></a>
<FONT color="green">237</FONT>       * @param job               job to add the named output<a name="line.237"></a>
<FONT color="green">238</FONT>       * @param namedOutput       named output name, it has to be a word, letters<a name="line.238"></a>
<FONT color="green">239</FONT>       *                          and numbers only, cannot be the word 'part' as<a name="line.239"></a>
<FONT color="green">240</FONT>       *                          that is reserved for the default output.<a name="line.240"></a>
<FONT color="green">241</FONT>       * @param outputFormatClass OutputFormat class.<a name="line.241"></a>
<FONT color="green">242</FONT>       * @param keyClass          key class<a name="line.242"></a>
<FONT color="green">243</FONT>       * @param valueClass        value class<a name="line.243"></a>
<FONT color="green">244</FONT>       */<a name="line.244"></a>
<FONT color="green">245</FONT>      @SuppressWarnings("unchecked")<a name="line.245"></a>
<FONT color="green">246</FONT>      public static void addNamedOutput(Job job, String namedOutput,<a name="line.246"></a>
<FONT color="green">247</FONT>          Class&lt;? extends OutputFormat&gt; outputFormatClass,<a name="line.247"></a>
<FONT color="green">248</FONT>          Class&lt;?&gt; keyClass, Class&lt;?&gt; valueClass) {<a name="line.248"></a>
<FONT color="green">249</FONT>        checkNamedOutputName(job, namedOutput, true);<a name="line.249"></a>
<FONT color="green">250</FONT>        Configuration conf = job.getConfiguration();<a name="line.250"></a>
<FONT color="green">251</FONT>        conf.set(MULTIPLE_OUTPUTS,<a name="line.251"></a>
<FONT color="green">252</FONT>          conf.get(MULTIPLE_OUTPUTS, "") + " " + namedOutput);<a name="line.252"></a>
<FONT color="green">253</FONT>        conf.setClass(MO_PREFIX + namedOutput + FORMAT, outputFormatClass,<a name="line.253"></a>
<FONT color="green">254</FONT>          OutputFormat.class);<a name="line.254"></a>
<FONT color="green">255</FONT>        conf.setClass(MO_PREFIX + namedOutput + KEY, keyClass, Object.class);<a name="line.255"></a>
<FONT color="green">256</FONT>        conf.setClass(MO_PREFIX + namedOutput + VALUE, valueClass, Object.class);<a name="line.256"></a>
<FONT color="green">257</FONT>      }<a name="line.257"></a>
<FONT color="green">258</FONT>    <a name="line.258"></a>
<FONT color="green">259</FONT>      /**<a name="line.259"></a>
<FONT color="green">260</FONT>       * Enables or disables counters for the named outputs.<a name="line.260"></a>
<FONT color="green">261</FONT>       * <a name="line.261"></a>
<FONT color="green">262</FONT>       * The counters group is the {@link MultipleOutputs} class name.<a name="line.262"></a>
<FONT color="green">263</FONT>       * The names of the counters are the same as the named outputs. These<a name="line.263"></a>
<FONT color="green">264</FONT>       * counters count the number records written to each output name.<a name="line.264"></a>
<FONT color="green">265</FONT>       * By default these counters are disabled.<a name="line.265"></a>
<FONT color="green">266</FONT>       *<a name="line.266"></a>
<FONT color="green">267</FONT>       * @param job    job  to enable counters<a name="line.267"></a>
<FONT color="green">268</FONT>       * @param enabled indicates if the counters will be enabled or not.<a name="line.268"></a>
<FONT color="green">269</FONT>       */<a name="line.269"></a>
<FONT color="green">270</FONT>      public static void setCountersEnabled(Job job, boolean enabled) {<a name="line.270"></a>
<FONT color="green">271</FONT>        job.getConfiguration().setBoolean(COUNTERS_ENABLED, enabled);<a name="line.271"></a>
<FONT color="green">272</FONT>      }<a name="line.272"></a>
<FONT color="green">273</FONT>    <a name="line.273"></a>
<FONT color="green">274</FONT>      /**<a name="line.274"></a>
<FONT color="green">275</FONT>       * Returns if the counters for the named outputs are enabled or not.<a name="line.275"></a>
<FONT color="green">276</FONT>       * By default these counters are disabled.<a name="line.276"></a>
<FONT color="green">277</FONT>       *<a name="line.277"></a>
<FONT color="green">278</FONT>       * @param job    the job <a name="line.278"></a>
<FONT color="green">279</FONT>       * @return TRUE if the counters are enabled, FALSE if they are disabled.<a name="line.279"></a>
<FONT color="green">280</FONT>       */<a name="line.280"></a>
<FONT color="green">281</FONT>      public static boolean getCountersEnabled(JobContext job) {<a name="line.281"></a>
<FONT color="green">282</FONT>        return job.getConfiguration().getBoolean(COUNTERS_ENABLED, false);<a name="line.282"></a>
<FONT color="green">283</FONT>      }<a name="line.283"></a>
<FONT color="green">284</FONT>    <a name="line.284"></a>
<FONT color="green">285</FONT>      /**<a name="line.285"></a>
<FONT color="green">286</FONT>       * Wraps RecordWriter to increment counters. <a name="line.286"></a>
<FONT color="green">287</FONT>       */<a name="line.287"></a>
<FONT color="green">288</FONT>      @SuppressWarnings("unchecked")<a name="line.288"></a>
<FONT color="green">289</FONT>      private static class RecordWriterWithCounter extends RecordWriter {<a name="line.289"></a>
<FONT color="green">290</FONT>        private RecordWriter writer;<a name="line.290"></a>
<FONT color="green">291</FONT>        private String counterName;<a name="line.291"></a>
<FONT color="green">292</FONT>        private TaskInputOutputContext context;<a name="line.292"></a>
<FONT color="green">293</FONT>    <a name="line.293"></a>
<FONT color="green">294</FONT>        public RecordWriterWithCounter(RecordWriter writer, String counterName,<a name="line.294"></a>
<FONT color="green">295</FONT>                                       TaskInputOutputContext context) {<a name="line.295"></a>
<FONT color="green">296</FONT>          this.writer = writer;<a name="line.296"></a>
<FONT color="green">297</FONT>          this.counterName = counterName;<a name="line.297"></a>
<FONT color="green">298</FONT>          this.context = context;<a name="line.298"></a>
<FONT color="green">299</FONT>        }<a name="line.299"></a>
<FONT color="green">300</FONT>    <a name="line.300"></a>
<FONT color="green">301</FONT>        @SuppressWarnings({"unchecked"})<a name="line.301"></a>
<FONT color="green">302</FONT>        public void write(Object key, Object value) <a name="line.302"></a>
<FONT color="green">303</FONT>            throws IOException, InterruptedException {<a name="line.303"></a>
<FONT color="green">304</FONT>          context.getCounter(COUNTERS_GROUP, counterName).increment(1);<a name="line.304"></a>
<FONT color="green">305</FONT>          writer.write(key, value);<a name="line.305"></a>
<FONT color="green">306</FONT>        }<a name="line.306"></a>
<FONT color="green">307</FONT>    <a name="line.307"></a>
<FONT color="green">308</FONT>        public void close(TaskAttemptContext context) <a name="line.308"></a>
<FONT color="green">309</FONT>            throws IOException, InterruptedException {<a name="line.309"></a>
<FONT color="green">310</FONT>          writer.close(context);<a name="line.310"></a>
<FONT color="green">311</FONT>        }<a name="line.311"></a>
<FONT color="green">312</FONT>      }<a name="line.312"></a>
<FONT color="green">313</FONT>    <a name="line.313"></a>
<FONT color="green">314</FONT>      // instance code, to be used from Mapper/Reducer code<a name="line.314"></a>
<FONT color="green">315</FONT>    <a name="line.315"></a>
<FONT color="green">316</FONT>      private TaskInputOutputContext&lt;?, ?, KEYOUT, VALUEOUT&gt; context;<a name="line.316"></a>
<FONT color="green">317</FONT>      private Set&lt;String&gt; namedOutputs;<a name="line.317"></a>
<FONT color="green">318</FONT>      private Map&lt;String, RecordWriter&lt;?, ?&gt;&gt; recordWriters;<a name="line.318"></a>
<FONT color="green">319</FONT>      private boolean countersEnabled;<a name="line.319"></a>
<FONT color="green">320</FONT>      <a name="line.320"></a>
<FONT color="green">321</FONT>      /**<a name="line.321"></a>
<FONT color="green">322</FONT>       * Creates and initializes multiple outputs support,<a name="line.322"></a>
<FONT color="green">323</FONT>       * it should be instantiated in the Mapper/Reducer setup method.<a name="line.323"></a>
<FONT color="green">324</FONT>       *<a name="line.324"></a>
<FONT color="green">325</FONT>       * @param context the TaskInputOutputContext object<a name="line.325"></a>
<FONT color="green">326</FONT>       */<a name="line.326"></a>
<FONT color="green">327</FONT>      public MultipleOutputs(<a name="line.327"></a>
<FONT color="green">328</FONT>          TaskInputOutputContext&lt;?, ?, KEYOUT, VALUEOUT&gt; context) {<a name="line.328"></a>
<FONT color="green">329</FONT>        this.context = context;<a name="line.329"></a>
<FONT color="green">330</FONT>        namedOutputs = Collections.unmodifiableSet(<a name="line.330"></a>
<FONT color="green">331</FONT>          new HashSet&lt;String&gt;(MultipleOutputs.getNamedOutputsList(context)));<a name="line.331"></a>
<FONT color="green">332</FONT>        recordWriters = new HashMap&lt;String, RecordWriter&lt;?, ?&gt;&gt;();<a name="line.332"></a>
<FONT color="green">333</FONT>        countersEnabled = getCountersEnabled(context);<a name="line.333"></a>
<FONT color="green">334</FONT>      }<a name="line.334"></a>
<FONT color="green">335</FONT>    <a name="line.335"></a>
<FONT color="green">336</FONT>      /**<a name="line.336"></a>
<FONT color="green">337</FONT>       * Write key and value to the namedOutput.<a name="line.337"></a>
<FONT color="green">338</FONT>       *<a name="line.338"></a>
<FONT color="green">339</FONT>       * Output path is a unique file generated for the namedOutput.<a name="line.339"></a>
<FONT color="green">340</FONT>       * For example, {namedOutput}-(m|r)-{part-number}<a name="line.340"></a>
<FONT color="green">341</FONT>       * <a name="line.341"></a>
<FONT color="green">342</FONT>       * @param namedOutput the named output name<a name="line.342"></a>
<FONT color="green">343</FONT>       * @param key         the key<a name="line.343"></a>
<FONT color="green">344</FONT>       * @param value       the value<a name="line.344"></a>
<FONT color="green">345</FONT>       */<a name="line.345"></a>
<FONT color="green">346</FONT>      @SuppressWarnings("unchecked")<a name="line.346"></a>
<FONT color="green">347</FONT>      public &lt;K, V&gt; void write(String namedOutput, K key, V value)<a name="line.347"></a>
<FONT color="green">348</FONT>          throws IOException, InterruptedException {<a name="line.348"></a>
<FONT color="green">349</FONT>        write(namedOutput, key, value, namedOutput);<a name="line.349"></a>
<FONT color="green">350</FONT>      }<a name="line.350"></a>
<FONT color="green">351</FONT>    <a name="line.351"></a>
<FONT color="green">352</FONT>      /**<a name="line.352"></a>
<FONT color="green">353</FONT>       * Write key and value to baseOutputPath using the namedOutput.<a name="line.353"></a>
<FONT color="green">354</FONT>       * <a name="line.354"></a>
<FONT color="green">355</FONT>       * @param namedOutput    the named output name<a name="line.355"></a>
<FONT color="green">356</FONT>       * @param key            the key<a name="line.356"></a>
<FONT color="green">357</FONT>       * @param value          the value<a name="line.357"></a>
<FONT color="green">358</FONT>       * @param baseOutputPath base-output path to write the record to.<a name="line.358"></a>
<FONT color="green">359</FONT>       * Note: Framework will generate unique filename for the baseOutputPath<a name="line.359"></a>
<FONT color="green">360</FONT>       */<a name="line.360"></a>
<FONT color="green">361</FONT>      @SuppressWarnings("unchecked")<a name="line.361"></a>
<FONT color="green">362</FONT>      public &lt;K, V&gt; void write(String namedOutput, K key, V value,<a name="line.362"></a>
<FONT color="green">363</FONT>          String baseOutputPath) throws IOException, InterruptedException {<a name="line.363"></a>
<FONT color="green">364</FONT>        checkNamedOutputName(context, namedOutput, false);<a name="line.364"></a>
<FONT color="green">365</FONT>        checkBaseOutputPath(baseOutputPath);<a name="line.365"></a>
<FONT color="green">366</FONT>        if (!namedOutputs.contains(namedOutput)) {<a name="line.366"></a>
<FONT color="green">367</FONT>          throw new IllegalArgumentException("Undefined named output '" +<a name="line.367"></a>
<FONT color="green">368</FONT>            namedOutput + "'");<a name="line.368"></a>
<FONT color="green">369</FONT>        }<a name="line.369"></a>
<FONT color="green">370</FONT>        TaskAttemptContext taskContext = getContext(namedOutput);<a name="line.370"></a>
<FONT color="green">371</FONT>        getRecordWriter(taskContext, baseOutputPath).write(key, value);<a name="line.371"></a>
<FONT color="green">372</FONT>      }<a name="line.372"></a>
<FONT color="green">373</FONT>    <a name="line.373"></a>
<FONT color="green">374</FONT>      /**<a name="line.374"></a>
<FONT color="green">375</FONT>       * Write key value to an output file name.<a name="line.375"></a>
<FONT color="green">376</FONT>       * <a name="line.376"></a>
<FONT color="green">377</FONT>       * Gets the record writer from job's output format.  <a name="line.377"></a>
<FONT color="green">378</FONT>       * Job's output format should be a FileOutputFormat.<a name="line.378"></a>
<FONT color="green">379</FONT>       * <a name="line.379"></a>
<FONT color="green">380</FONT>       * @param key       the key<a name="line.380"></a>
<FONT color="green">381</FONT>       * @param value     the value<a name="line.381"></a>
<FONT color="green">382</FONT>       * @param baseOutputPath base-output path to write the record to.<a name="line.382"></a>
<FONT color="green">383</FONT>       * Note: Framework will generate unique filename for the baseOutputPath<a name="line.383"></a>
<FONT color="green">384</FONT>       */<a name="line.384"></a>
<FONT color="green">385</FONT>      @SuppressWarnings("unchecked")<a name="line.385"></a>
<FONT color="green">386</FONT>      public void write(KEYOUT key, VALUEOUT value, String baseOutputPath) <a name="line.386"></a>
<FONT color="green">387</FONT>          throws IOException, InterruptedException {<a name="line.387"></a>
<FONT color="green">388</FONT>        checkBaseOutputPath(baseOutputPath);<a name="line.388"></a>
<FONT color="green">389</FONT>        if (jobOutputFormatContext == null) {<a name="line.389"></a>
<FONT color="green">390</FONT>          jobOutputFormatContext = <a name="line.390"></a>
<FONT color="green">391</FONT>            new TaskAttemptContextImpl(context.getConfiguration(), <a name="line.391"></a>
<FONT color="green">392</FONT>                                       context.getTaskAttemptID(),<a name="line.392"></a>
<FONT color="green">393</FONT>                                       new WrappedStatusReporter(context));<a name="line.393"></a>
<FONT color="green">394</FONT>        }<a name="line.394"></a>
<FONT color="green">395</FONT>        getRecordWriter(jobOutputFormatContext, baseOutputPath).write(key, value);<a name="line.395"></a>
<FONT color="green">396</FONT>      }<a name="line.396"></a>
<FONT color="green">397</FONT>    <a name="line.397"></a>
<FONT color="green">398</FONT>      // by being synchronized MultipleOutputTask can be use with a<a name="line.398"></a>
<FONT color="green">399</FONT>      // MultithreadedMapper.<a name="line.399"></a>
<FONT color="green">400</FONT>      @SuppressWarnings("unchecked")<a name="line.400"></a>
<FONT color="green">401</FONT>      private synchronized RecordWriter getRecordWriter(<a name="line.401"></a>
<FONT color="green">402</FONT>          TaskAttemptContext taskContext, String baseFileName) <a name="line.402"></a>
<FONT color="green">403</FONT>          throws IOException, InterruptedException {<a name="line.403"></a>
<FONT color="green">404</FONT>        <a name="line.404"></a>
<FONT color="green">405</FONT>        // look for record-writer in the cache<a name="line.405"></a>
<FONT color="green">406</FONT>        RecordWriter writer = recordWriters.get(baseFileName);<a name="line.406"></a>
<FONT color="green">407</FONT>        <a name="line.407"></a>
<FONT color="green">408</FONT>        // If not in cache, create a new one<a name="line.408"></a>
<FONT color="green">409</FONT>        if (writer == null) {<a name="line.409"></a>
<FONT color="green">410</FONT>          // get the record writer from context output format<a name="line.410"></a>
<FONT color="green">411</FONT>          FileOutputFormat.setOutputName(taskContext, baseFileName);<a name="line.411"></a>
<FONT color="green">412</FONT>          try {<a name="line.412"></a>
<FONT color="green">413</FONT>            writer = ((OutputFormat) ReflectionUtils.newInstance(<a name="line.413"></a>
<FONT color="green">414</FONT>              taskContext.getOutputFormatClass(), taskContext.getConfiguration()))<a name="line.414"></a>
<FONT color="green">415</FONT>              .getRecordWriter(taskContext);<a name="line.415"></a>
<FONT color="green">416</FONT>          } catch (ClassNotFoundException e) {<a name="line.416"></a>
<FONT color="green">417</FONT>            throw new IOException(e);<a name="line.417"></a>
<FONT color="green">418</FONT>          }<a name="line.418"></a>
<FONT color="green">419</FONT>     <a name="line.419"></a>
<FONT color="green">420</FONT>          // if counters are enabled, wrap the writer with context <a name="line.420"></a>
<FONT color="green">421</FONT>          // to increment counters <a name="line.421"></a>
<FONT color="green">422</FONT>          if (countersEnabled) {<a name="line.422"></a>
<FONT color="green">423</FONT>            writer = new RecordWriterWithCounter(writer, baseFileName, context);<a name="line.423"></a>
<FONT color="green">424</FONT>          }<a name="line.424"></a>
<FONT color="green">425</FONT>          <a name="line.425"></a>
<FONT color="green">426</FONT>          // add the record-writer to the cache<a name="line.426"></a>
<FONT color="green">427</FONT>          recordWriters.put(baseFileName, writer);<a name="line.427"></a>
<FONT color="green">428</FONT>        }<a name="line.428"></a>
<FONT color="green">429</FONT>        return writer;<a name="line.429"></a>
<FONT color="green">430</FONT>      }<a name="line.430"></a>
<FONT color="green">431</FONT>    <a name="line.431"></a>
<FONT color="green">432</FONT>       // Create a taskAttemptContext for the named output with <a name="line.432"></a>
<FONT color="green">433</FONT>       // output format and output key/value types put in the context<a name="line.433"></a>
<FONT color="green">434</FONT>      private TaskAttemptContext getContext(String nameOutput) throws IOException {<a name="line.434"></a>
<FONT color="green">435</FONT>          <a name="line.435"></a>
<FONT color="green">436</FONT>        TaskAttemptContext taskContext = taskContexts.get(nameOutput);<a name="line.436"></a>
<FONT color="green">437</FONT>        <a name="line.437"></a>
<FONT color="green">438</FONT>        if (taskContext != null) {<a name="line.438"></a>
<FONT color="green">439</FONT>            return taskContext;<a name="line.439"></a>
<FONT color="green">440</FONT>        }<a name="line.440"></a>
<FONT color="green">441</FONT>        <a name="line.441"></a>
<FONT color="green">442</FONT>        // The following trick leverages the instantiation of a record writer via<a name="line.442"></a>
<FONT color="green">443</FONT>        // the job thus supporting arbitrary output formats.<a name="line.443"></a>
<FONT color="green">444</FONT>        Job job = new Job(context.getConfiguration());<a name="line.444"></a>
<FONT color="green">445</FONT>        job.setOutputFormatClass(getNamedOutputFormatClass(context, nameOutput));<a name="line.445"></a>
<FONT color="green">446</FONT>        job.setOutputKeyClass(getNamedOutputKeyClass(context, nameOutput));<a name="line.446"></a>
<FONT color="green">447</FONT>        job.setOutputValueClass(getNamedOutputValueClass(context, nameOutput));<a name="line.447"></a>
<FONT color="green">448</FONT>        taskContext = new TaskAttemptContextImpl(job.getConfiguration(), context<a name="line.448"></a>
<FONT color="green">449</FONT>            .getTaskAttemptID(), new WrappedStatusReporter(context));<a name="line.449"></a>
<FONT color="green">450</FONT>    <a name="line.450"></a>
<FONT color="green">451</FONT>        taskContexts.put(nameOutput, taskContext);<a name="line.451"></a>
<FONT color="green">452</FONT>    <a name="line.452"></a>
<FONT color="green">453</FONT>        return taskContext;<a name="line.453"></a>
<FONT color="green">454</FONT>      }<a name="line.454"></a>
<FONT color="green">455</FONT>    <a name="line.455"></a>
<FONT color="green">456</FONT>      private static class WrappedStatusReporter extends StatusReporter {<a name="line.456"></a>
<FONT color="green">457</FONT>    <a name="line.457"></a>
<FONT color="green">458</FONT>        TaskAttemptContext context;<a name="line.458"></a>
<FONT color="green">459</FONT>    <a name="line.459"></a>
<FONT color="green">460</FONT>        public WrappedStatusReporter(TaskAttemptContext context) {<a name="line.460"></a>
<FONT color="green">461</FONT>          this.context = context;<a name="line.461"></a>
<FONT color="green">462</FONT>        }<a name="line.462"></a>
<FONT color="green">463</FONT>    <a name="line.463"></a>
<FONT color="green">464</FONT>        @Override<a name="line.464"></a>
<FONT color="green">465</FONT>        public Counter getCounter(Enum&lt;?&gt; name) {<a name="line.465"></a>
<FONT color="green">466</FONT>          return context.getCounter(name);<a name="line.466"></a>
<FONT color="green">467</FONT>        }<a name="line.467"></a>
<FONT color="green">468</FONT>    <a name="line.468"></a>
<FONT color="green">469</FONT>        @Override<a name="line.469"></a>
<FONT color="green">470</FONT>        public Counter getCounter(String group, String name) {<a name="line.470"></a>
<FONT color="green">471</FONT>          return context.getCounter(group, name);<a name="line.471"></a>
<FONT color="green">472</FONT>        }<a name="line.472"></a>
<FONT color="green">473</FONT>    <a name="line.473"></a>
<FONT color="green">474</FONT>        @Override<a name="line.474"></a>
<FONT color="green">475</FONT>        public void progress() {<a name="line.475"></a>
<FONT color="green">476</FONT>          context.progress();<a name="line.476"></a>
<FONT color="green">477</FONT>        }<a name="line.477"></a>
<FONT color="green">478</FONT>    <a name="line.478"></a>
<FONT color="green">479</FONT>        @Override<a name="line.479"></a>
<FONT color="green">480</FONT>        public float getProgress() {<a name="line.480"></a>
<FONT color="green">481</FONT>          return context.getProgress();<a name="line.481"></a>
<FONT color="green">482</FONT>        }<a name="line.482"></a>
<FONT color="green">483</FONT>        <a name="line.483"></a>
<FONT color="green">484</FONT>        @Override<a name="line.484"></a>
<FONT color="green">485</FONT>        public void setStatus(String status) {<a name="line.485"></a>
<FONT color="green">486</FONT>          context.setStatus(status);<a name="line.486"></a>
<FONT color="green">487</FONT>        }<a name="line.487"></a>
<FONT color="green">488</FONT>      }<a name="line.488"></a>
<FONT color="green">489</FONT>    <a name="line.489"></a>
<FONT color="green">490</FONT>      /**<a name="line.490"></a>
<FONT color="green">491</FONT>       * Closes all the opened outputs.<a name="line.491"></a>
<FONT color="green">492</FONT>       * <a name="line.492"></a>
<FONT color="green">493</FONT>       * This should be called from cleanup method of map/reduce task.<a name="line.493"></a>
<FONT color="green">494</FONT>       * If overridden subclasses must invoke &lt;code&gt;super.close()&lt;/code&gt; at the<a name="line.494"></a>
<FONT color="green">495</FONT>       * end of their &lt;code&gt;close()&lt;/code&gt;<a name="line.495"></a>
<FONT color="green">496</FONT>       * <a name="line.496"></a>
<FONT color="green">497</FONT>       */<a name="line.497"></a>
<FONT color="green">498</FONT>      @SuppressWarnings("unchecked")<a name="line.498"></a>
<FONT color="green">499</FONT>      public void close() throws IOException, InterruptedException {<a name="line.499"></a>
<FONT color="green">500</FONT>        for (RecordWriter writer : recordWriters.values()) {<a name="line.500"></a>
<FONT color="green">501</FONT>          writer.close(context);<a name="line.501"></a>
<FONT color="green">502</FONT>        }<a name="line.502"></a>
<FONT color="green">503</FONT>      }<a name="line.503"></a>
<FONT color="green">504</FONT>    }<a name="line.504"></a>




























































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