<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT>    /**<a name="line.1"></a>
<FONT color="green">002</FONT>     * Licensed to the Apache Software Foundation (ASF) under one<a name="line.2"></a>
<FONT color="green">003</FONT>     * or more contributor license agreements.  See the NOTICE file<a name="line.3"></a>
<FONT color="green">004</FONT>     * distributed with this work for additional information<a name="line.4"></a>
<FONT color="green">005</FONT>     * regarding copyright ownership.  The ASF licenses this file<a name="line.5"></a>
<FONT color="green">006</FONT>     * to you under the Apache License, Version 2.0 (the<a name="line.6"></a>
<FONT color="green">007</FONT>     * "License"); you may not use this file except in compliance<a name="line.7"></a>
<FONT color="green">008</FONT>     * with the License.  You may obtain a copy of the License at<a name="line.8"></a>
<FONT color="green">009</FONT>     *<a name="line.9"></a>
<FONT color="green">010</FONT>     *     http://www.apache.org/licenses/LICENSE-2.0<a name="line.10"></a>
<FONT color="green">011</FONT>     *<a name="line.11"></a>
<FONT color="green">012</FONT>     * Unless required by applicable law or agreed to in writing, software<a name="line.12"></a>
<FONT color="green">013</FONT>     * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.13"></a>
<FONT color="green">014</FONT>     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.14"></a>
<FONT color="green">015</FONT>     * See the License for the specific language governing permissions and<a name="line.15"></a>
<FONT color="green">016</FONT>     * limitations under the License.<a name="line.16"></a>
<FONT color="green">017</FONT>     */<a name="line.17"></a>
<FONT color="green">018</FONT>    <a name="line.18"></a>
<FONT color="green">019</FONT>    package org.apache.hadoop.mapred.lib;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.IOException;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.ArrayList;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.util.Iterator;<a name="line.23"></a>
<FONT color="green">024</FONT>    import java.util.List;<a name="line.24"></a>
<FONT color="green">025</FONT>    <a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.commons.logging.Log;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.commons.logging.LogFactory;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.io.Text;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapred.JobConf;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.mapred.Mapper;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.mapred.OutputCollector;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapred.Reducer;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.mapred.Reporter;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.mapred.TextInputFormat;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.mapreduce.lib.fieldsel.*;<a name="line.37"></a>
<FONT color="green">038</FONT>    <a name="line.38"></a>
<FONT color="green">039</FONT>    /**<a name="line.39"></a>
<FONT color="green">040</FONT>     * This class implements a mapper/reducer class that can be used to perform<a name="line.40"></a>
<FONT color="green">041</FONT>     * field selections in a manner similar to unix cut. The input data is treated<a name="line.41"></a>
<FONT color="green">042</FONT>     * as fields separated by a user specified separator (the default value is<a name="line.42"></a>
<FONT color="green">043</FONT>     * "\t"). The user can specify a list of fields that form the map output keys,<a name="line.43"></a>
<FONT color="green">044</FONT>     * and a list of fields that form the map output values. If the inputformat is<a name="line.44"></a>
<FONT color="green">045</FONT>     * TextInputFormat, the mapper will ignore the key to the map function. and the<a name="line.45"></a>
<FONT color="green">046</FONT>     * fields are from the value only. Otherwise, the fields are the union of those<a name="line.46"></a>
<FONT color="green">047</FONT>     * from the key and those from the value.<a name="line.47"></a>
<FONT color="green">048</FONT>     * <a name="line.48"></a>
<FONT color="green">049</FONT>     * The field separator is under attribute "mapreduce.fieldsel.data.field.separator"<a name="line.49"></a>
<FONT color="green">050</FONT>     * <a name="line.50"></a>
<FONT color="green">051</FONT>     * The map output field list spec is under attribute <a name="line.51"></a>
<FONT color="green">052</FONT>     * "mapreduce.fieldsel.map.output.key.value.fields.spec".<a name="line.52"></a>
<FONT color="green">053</FONT>     * The value is expected to be like "keyFieldsSpec:valueFieldsSpec"<a name="line.53"></a>
<FONT color="green">054</FONT>     * key/valueFieldsSpec are comma (,) separated field spec: fieldSpec,fieldSpec,fieldSpec ...<a name="line.54"></a>
<FONT color="green">055</FONT>     * Each field spec can be a simple number (e.g. 5) specifying a specific field, or a range<a name="line.55"></a>
<FONT color="green">056</FONT>     * (like 2-5) to specify a range of fields, or an open range (like 3-) specifying all <a name="line.56"></a>
<FONT color="green">057</FONT>     * the fields starting from field 3. The open range field spec applies value fields only.<a name="line.57"></a>
<FONT color="green">058</FONT>     * They have no effect on the key fields.<a name="line.58"></a>
<FONT color="green">059</FONT>     * <a name="line.59"></a>
<FONT color="green">060</FONT>     * Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields 4,3,0 and 1 for keys,<a name="line.60"></a>
<FONT color="green">061</FONT>     * and use fields 6,5,1,2,3,7 and above for values.<a name="line.61"></a>
<FONT color="green">062</FONT>     * <a name="line.62"></a>
<FONT color="green">063</FONT>     * The reduce output field list spec is under attribute <a name="line.63"></a>
<FONT color="green">064</FONT>     * "mapreduce.fieldsel.reduce.output.key.value.fields.spec".<a name="line.64"></a>
<FONT color="green">065</FONT>     * <a name="line.65"></a>
<FONT color="green">066</FONT>     * The reducer extracts output key/value pairs in a similar manner, except that<a name="line.66"></a>
<FONT color="green">067</FONT>     * the key is never ignored.<a name="line.67"></a>
<FONT color="green">068</FONT>     */<a name="line.68"></a>
<FONT color="green">069</FONT>    @InterfaceAudience.Public<a name="line.69"></a>
<FONT color="green">070</FONT>    @InterfaceStability.Stable<a name="line.70"></a>
<FONT color="green">071</FONT>    public class FieldSelectionMapReduce&lt;K, V&gt;<a name="line.71"></a>
<FONT color="green">072</FONT>        implements Mapper&lt;K, V, Text, Text&gt;, Reducer&lt;Text, Text, Text, Text&gt; {<a name="line.72"></a>
<FONT color="green">073</FONT>    <a name="line.73"></a>
<FONT color="green">074</FONT>      private String mapOutputKeyValueSpec;<a name="line.74"></a>
<FONT color="green">075</FONT>    <a name="line.75"></a>
<FONT color="green">076</FONT>      private boolean ignoreInputKey;<a name="line.76"></a>
<FONT color="green">077</FONT>    <a name="line.77"></a>
<FONT color="green">078</FONT>      private String fieldSeparator = "\t";<a name="line.78"></a>
<FONT color="green">079</FONT>    <a name="line.79"></a>
<FONT color="green">080</FONT>      private List&lt;Integer&gt; mapOutputKeyFieldList = new ArrayList&lt;Integer&gt;();<a name="line.80"></a>
<FONT color="green">081</FONT>    <a name="line.81"></a>
<FONT color="green">082</FONT>      private List&lt;Integer&gt; mapOutputValueFieldList = new ArrayList&lt;Integer&gt;();<a name="line.82"></a>
<FONT color="green">083</FONT>    <a name="line.83"></a>
<FONT color="green">084</FONT>      private int allMapValueFieldsFrom = -1;<a name="line.84"></a>
<FONT color="green">085</FONT>    <a name="line.85"></a>
<FONT color="green">086</FONT>      private String reduceOutputKeyValueSpec;<a name="line.86"></a>
<FONT color="green">087</FONT>    <a name="line.87"></a>
<FONT color="green">088</FONT>      private List&lt;Integer&gt; reduceOutputKeyFieldList = new ArrayList&lt;Integer&gt;();<a name="line.88"></a>
<FONT color="green">089</FONT>    <a name="line.89"></a>
<FONT color="green">090</FONT>      private List&lt;Integer&gt; reduceOutputValueFieldList = new ArrayList&lt;Integer&gt;();<a name="line.90"></a>
<FONT color="green">091</FONT>    <a name="line.91"></a>
<FONT color="green">092</FONT>      private int allReduceValueFieldsFrom = -1;<a name="line.92"></a>
<FONT color="green">093</FONT>    <a name="line.93"></a>
<FONT color="green">094</FONT>    <a name="line.94"></a>
<FONT color="green">095</FONT>      public static final Log LOG = LogFactory.getLog("FieldSelectionMapReduce");<a name="line.95"></a>
<FONT color="green">096</FONT>    <a name="line.96"></a>
<FONT color="green">097</FONT>      private String specToString() {<a name="line.97"></a>
<FONT color="green">098</FONT>        StringBuffer sb = new StringBuffer();<a name="line.98"></a>
<FONT color="green">099</FONT>        sb.append("fieldSeparator: ").append(fieldSeparator).append("\n");<a name="line.99"></a>
<FONT color="green">100</FONT>    <a name="line.100"></a>
<FONT color="green">101</FONT>        sb.append("mapOutputKeyValueSpec: ").append(mapOutputKeyValueSpec).append(<a name="line.101"></a>
<FONT color="green">102</FONT>            "\n");<a name="line.102"></a>
<FONT color="green">103</FONT>        sb.append("reduceOutputKeyValueSpec: ").append(reduceOutputKeyValueSpec)<a name="line.103"></a>
<FONT color="green">104</FONT>            .append("\n");<a name="line.104"></a>
<FONT color="green">105</FONT>    <a name="line.105"></a>
<FONT color="green">106</FONT>        sb.append("allMapValueFieldsFrom: ").append(allMapValueFieldsFrom).append(<a name="line.106"></a>
<FONT color="green">107</FONT>            "\n");<a name="line.107"></a>
<FONT color="green">108</FONT>    <a name="line.108"></a>
<FONT color="green">109</FONT>        sb.append("allReduceValueFieldsFrom: ").append(allReduceValueFieldsFrom)<a name="line.109"></a>
<FONT color="green">110</FONT>            .append("\n");<a name="line.110"></a>
<FONT color="green">111</FONT>    <a name="line.111"></a>
<FONT color="green">112</FONT>        int i = 0;<a name="line.112"></a>
<FONT color="green">113</FONT>    <a name="line.113"></a>
<FONT color="green">114</FONT>        sb.append("mapOutputKeyFieldList.length: ").append(<a name="line.114"></a>
<FONT color="green">115</FONT>            mapOutputKeyFieldList.size()).append("\n");<a name="line.115"></a>
<FONT color="green">116</FONT>        for (i = 0; i &lt; mapOutputKeyFieldList.size(); i++) {<a name="line.116"></a>
<FONT color="green">117</FONT>          sb.append("\t").append(mapOutputKeyFieldList.get(i)).append("\n");<a name="line.117"></a>
<FONT color="green">118</FONT>        }<a name="line.118"></a>
<FONT color="green">119</FONT>        sb.append("mapOutputValueFieldList.length: ").append(<a name="line.119"></a>
<FONT color="green">120</FONT>            mapOutputValueFieldList.size()).append("\n");<a name="line.120"></a>
<FONT color="green">121</FONT>        for (i = 0; i &lt; mapOutputValueFieldList.size(); i++) {<a name="line.121"></a>
<FONT color="green">122</FONT>          sb.append("\t").append(mapOutputValueFieldList.get(i)).append("\n");<a name="line.122"></a>
<FONT color="green">123</FONT>        }<a name="line.123"></a>
<FONT color="green">124</FONT>    <a name="line.124"></a>
<FONT color="green">125</FONT>        sb.append("reduceOutputKeyFieldList.length: ").append(<a name="line.125"></a>
<FONT color="green">126</FONT>            reduceOutputKeyFieldList.size()).append("\n");<a name="line.126"></a>
<FONT color="green">127</FONT>        for (i = 0; i &lt; reduceOutputKeyFieldList.size(); i++) {<a name="line.127"></a>
<FONT color="green">128</FONT>          sb.append("\t").append(reduceOutputKeyFieldList.get(i)).append("\n");<a name="line.128"></a>
<FONT color="green">129</FONT>        }<a name="line.129"></a>
<FONT color="green">130</FONT>        sb.append("reduceOutputValueFieldList.length: ").append(<a name="line.130"></a>
<FONT color="green">131</FONT>            reduceOutputValueFieldList.size()).append("\n");<a name="line.131"></a>
<FONT color="green">132</FONT>        for (i = 0; i &lt; reduceOutputValueFieldList.size(); i++) {<a name="line.132"></a>
<FONT color="green">133</FONT>          sb.append("\t").append(reduceOutputValueFieldList.get(i)).append("\n");<a name="line.133"></a>
<FONT color="green">134</FONT>        }<a name="line.134"></a>
<FONT color="green">135</FONT>        return sb.toString();<a name="line.135"></a>
<FONT color="green">136</FONT>      }<a name="line.136"></a>
<FONT color="green">137</FONT>    <a name="line.137"></a>
<FONT color="green">138</FONT>      /**<a name="line.138"></a>
<FONT color="green">139</FONT>       * The identify function. Input key/value pair is written directly to output.<a name="line.139"></a>
<FONT color="green">140</FONT>       */<a name="line.140"></a>
<FONT color="green">141</FONT>      public void map(K key, V val,<a name="line.141"></a>
<FONT color="green">142</FONT>          OutputCollector&lt;Text, Text&gt; output, Reporter reporter) <a name="line.142"></a>
<FONT color="green">143</FONT>          throws IOException {<a name="line.143"></a>
<FONT color="green">144</FONT>        FieldSelectionHelper helper = new FieldSelectionHelper(<a name="line.144"></a>
<FONT color="green">145</FONT>          FieldSelectionHelper.emptyText, FieldSelectionHelper.emptyText);<a name="line.145"></a>
<FONT color="green">146</FONT>        helper.extractOutputKeyValue(key.toString(), val.toString(),<a name="line.146"></a>
<FONT color="green">147</FONT>          fieldSeparator, mapOutputKeyFieldList, mapOutputValueFieldList,<a name="line.147"></a>
<FONT color="green">148</FONT>          allMapValueFieldsFrom, ignoreInputKey, true);<a name="line.148"></a>
<FONT color="green">149</FONT>        output.collect(helper.getKey(), helper.getValue());<a name="line.149"></a>
<FONT color="green">150</FONT>      }<a name="line.150"></a>
<FONT color="green">151</FONT>    <a name="line.151"></a>
<FONT color="green">152</FONT>      private void parseOutputKeyValueSpec() {<a name="line.152"></a>
<FONT color="green">153</FONT>        allMapValueFieldsFrom = FieldSelectionHelper.parseOutputKeyValueSpec(<a name="line.153"></a>
<FONT color="green">154</FONT>          mapOutputKeyValueSpec, mapOutputKeyFieldList, mapOutputValueFieldList);<a name="line.154"></a>
<FONT color="green">155</FONT>        <a name="line.155"></a>
<FONT color="green">156</FONT>        allReduceValueFieldsFrom = FieldSelectionHelper.parseOutputKeyValueSpec(<a name="line.156"></a>
<FONT color="green">157</FONT>          reduceOutputKeyValueSpec, reduceOutputKeyFieldList,<a name="line.157"></a>
<FONT color="green">158</FONT>          reduceOutputValueFieldList);<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>      public void configure(JobConf job) {<a name="line.161"></a>
<FONT color="green">162</FONT>        this.fieldSeparator = job.get(FieldSelectionHelper.DATA_FIELD_SEPERATOR,<a name="line.162"></a>
<FONT color="green">163</FONT>            "\t");<a name="line.163"></a>
<FONT color="green">164</FONT>        this.mapOutputKeyValueSpec = job.get(<a name="line.164"></a>
<FONT color="green">165</FONT>            FieldSelectionHelper.MAP_OUTPUT_KEY_VALUE_SPEC, "0-:");<a name="line.165"></a>
<FONT color="green">166</FONT>        this.ignoreInputKey = TextInputFormat.class.getCanonicalName().equals(<a name="line.166"></a>
<FONT color="green">167</FONT>            job.getInputFormat().getClass().getCanonicalName());<a name="line.167"></a>
<FONT color="green">168</FONT>        this.reduceOutputKeyValueSpec = job.get(<a name="line.168"></a>
<FONT color="green">169</FONT>            FieldSelectionHelper.REDUCE_OUTPUT_KEY_VALUE_SPEC, "0-:");<a name="line.169"></a>
<FONT color="green">170</FONT>        parseOutputKeyValueSpec();<a name="line.170"></a>
<FONT color="green">171</FONT>        LOG.info(specToString());<a name="line.171"></a>
<FONT color="green">172</FONT>      }<a name="line.172"></a>
<FONT color="green">173</FONT>    <a name="line.173"></a>
<FONT color="green">174</FONT>      public void close() throws IOException {<a name="line.174"></a>
<FONT color="green">175</FONT>        // TODO Auto-generated method stub<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>      public void reduce(Text key, Iterator&lt;Text&gt; values,<a name="line.179"></a>
<FONT color="green">180</FONT>                         OutputCollector&lt;Text, Text&gt; output, Reporter reporter)<a name="line.180"></a>
<FONT color="green">181</FONT>        throws IOException {<a name="line.181"></a>
<FONT color="green">182</FONT>        String keyStr = key.toString() + this.fieldSeparator;<a name="line.182"></a>
<FONT color="green">183</FONT>        while (values.hasNext()) {<a name="line.183"></a>
<FONT color="green">184</FONT>            FieldSelectionHelper helper = new FieldSelectionHelper();<a name="line.184"></a>
<FONT color="green">185</FONT>            helper.extractOutputKeyValue(keyStr, values.next().toString(),<a name="line.185"></a>
<FONT color="green">186</FONT>              fieldSeparator, reduceOutputKeyFieldList,<a name="line.186"></a>
<FONT color="green">187</FONT>              reduceOutputValueFieldList, allReduceValueFieldsFrom, false, false);<a name="line.187"></a>
<FONT color="green">188</FONT>          output.collect(helper.getKey(), helper.getValue());<a name="line.188"></a>
<FONT color="green">189</FONT>        }<a name="line.189"></a>
<FONT color="green">190</FONT>      }<a name="line.190"></a>
<FONT color="green">191</FONT>    }<a name="line.191"></a>




























































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