<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.fieldsel;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.util.List;<a name="line.21"></a>
<FONT color="green">022</FONT>    <a name="line.22"></a>
<FONT color="green">023</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.io.Text;<a name="line.25"></a>
<FONT color="green">026</FONT>    <a name="line.26"></a>
<FONT color="green">027</FONT>    /**<a name="line.27"></a>
<FONT color="green">028</FONT>     * This class implements a mapper/reducer class that can be used to perform<a name="line.28"></a>
<FONT color="green">029</FONT>     * field selections in a manner similar to unix cut. The input data is treated<a name="line.29"></a>
<FONT color="green">030</FONT>     * as fields separated by a user specified separator (the default value is<a name="line.30"></a>
<FONT color="green">031</FONT>     * "\t"). The user can specify a list of fields that form the map output keys,<a name="line.31"></a>
<FONT color="green">032</FONT>     * and a list of fields that form the map output values. If the inputformat is<a name="line.32"></a>
<FONT color="green">033</FONT>     * TextInputFormat, the mapper will ignore the key to the map function. and the<a name="line.33"></a>
<FONT color="green">034</FONT>     * fields are from the value only. Otherwise, the fields are the union of those<a name="line.34"></a>
<FONT color="green">035</FONT>     * from the key and those from the value.<a name="line.35"></a>
<FONT color="green">036</FONT>     * <a name="line.36"></a>
<FONT color="green">037</FONT>     * The field separator is under attribute "mapreduce.fieldsel.data.field.separator"<a name="line.37"></a>
<FONT color="green">038</FONT>     * <a name="line.38"></a>
<FONT color="green">039</FONT>     * The map output field list spec is under attribute <a name="line.39"></a>
<FONT color="green">040</FONT>     * "mapreduce.fieldsel.map.output.key.value.fields.spec".<a name="line.40"></a>
<FONT color="green">041</FONT>     * The value is expected to be like "keyFieldsSpec:valueFieldsSpec"<a name="line.41"></a>
<FONT color="green">042</FONT>     * key/valueFieldsSpec are comma (,) separated field spec: fieldSpec,fieldSpec,fieldSpec ...<a name="line.42"></a>
<FONT color="green">043</FONT>     * Each field spec can be a simple number (e.g. 5) specifying a specific field, or a range<a name="line.43"></a>
<FONT color="green">044</FONT>     * (like 2-5) to specify a range of fields, or an open range (like 3-) specifying all <a name="line.44"></a>
<FONT color="green">045</FONT>     * the fields starting from field 3. The open range field spec applies value fields only.<a name="line.45"></a>
<FONT color="green">046</FONT>     * They have no effect on the key fields.<a name="line.46"></a>
<FONT color="green">047</FONT>     * <a name="line.47"></a>
<FONT color="green">048</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.48"></a>
<FONT color="green">049</FONT>     * and use fields 6,5,1,2,3,7 and above for values.<a name="line.49"></a>
<FONT color="green">050</FONT>     * <a name="line.50"></a>
<FONT color="green">051</FONT>     * The reduce output field list spec is under attribute <a name="line.51"></a>
<FONT color="green">052</FONT>     * "mapreduce.fieldsel.reduce.output.key.value.fields.spec".<a name="line.52"></a>
<FONT color="green">053</FONT>     * <a name="line.53"></a>
<FONT color="green">054</FONT>     * The reducer extracts output key/value pairs in a similar manner, except that<a name="line.54"></a>
<FONT color="green">055</FONT>     * the key is never ignored.<a name="line.55"></a>
<FONT color="green">056</FONT>     * <a name="line.56"></a>
<FONT color="green">057</FONT>     */<a name="line.57"></a>
<FONT color="green">058</FONT>    @InterfaceAudience.Public<a name="line.58"></a>
<FONT color="green">059</FONT>    @InterfaceStability.Stable<a name="line.59"></a>
<FONT color="green">060</FONT>    public class FieldSelectionHelper {<a name="line.60"></a>
<FONT color="green">061</FONT>    <a name="line.61"></a>
<FONT color="green">062</FONT>      public static Text emptyText = new Text("");<a name="line.62"></a>
<FONT color="green">063</FONT>      public static final String DATA_FIELD_SEPERATOR = <a name="line.63"></a>
<FONT color="green">064</FONT>        "mapreduce.fieldsel.data.field.separator";<a name="line.64"></a>
<FONT color="green">065</FONT>      public static final String MAP_OUTPUT_KEY_VALUE_SPEC = <a name="line.65"></a>
<FONT color="green">066</FONT>        "mapreduce.fieldsel.map.output.key.value.fields.spec";<a name="line.66"></a>
<FONT color="green">067</FONT>      public static final String REDUCE_OUTPUT_KEY_VALUE_SPEC = <a name="line.67"></a>
<FONT color="green">068</FONT>        "mapreduce.fieldsel.reduce.output.key.value.fields.spec";<a name="line.68"></a>
<FONT color="green">069</FONT>    <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>       * Extract the actual field numbers from the given field specs.<a name="line.72"></a>
<FONT color="green">073</FONT>       * If a field spec is in the form of "n-" (like 3-), then n will be the <a name="line.73"></a>
<FONT color="green">074</FONT>       * return value. Otherwise, -1 will be returned.  <a name="line.74"></a>
<FONT color="green">075</FONT>       * @param fieldListSpec an array of field specs<a name="line.75"></a>
<FONT color="green">076</FONT>       * @param fieldList an array of field numbers extracted from the specs.<a name="line.76"></a>
<FONT color="green">077</FONT>       * @return number n if some field spec is in the form of "n-", -1 otherwise.<a name="line.77"></a>
<FONT color="green">078</FONT>       */<a name="line.78"></a>
<FONT color="green">079</FONT>      private static int extractFields(String[] fieldListSpec,<a name="line.79"></a>
<FONT color="green">080</FONT>          List&lt;Integer&gt; fieldList) {<a name="line.80"></a>
<FONT color="green">081</FONT>        int allFieldsFrom = -1;<a name="line.81"></a>
<FONT color="green">082</FONT>        int i = 0;<a name="line.82"></a>
<FONT color="green">083</FONT>        int j = 0;<a name="line.83"></a>
<FONT color="green">084</FONT>        int pos = -1;<a name="line.84"></a>
<FONT color="green">085</FONT>        String fieldSpec = null;<a name="line.85"></a>
<FONT color="green">086</FONT>        for (i = 0; i &lt; fieldListSpec.length; i++) {<a name="line.86"></a>
<FONT color="green">087</FONT>          fieldSpec = fieldListSpec[i];<a name="line.87"></a>
<FONT color="green">088</FONT>          if (fieldSpec.length() == 0) {<a name="line.88"></a>
<FONT color="green">089</FONT>            continue;<a name="line.89"></a>
<FONT color="green">090</FONT>          }<a name="line.90"></a>
<FONT color="green">091</FONT>          pos = fieldSpec.indexOf('-');<a name="line.91"></a>
<FONT color="green">092</FONT>          if (pos &lt; 0) {<a name="line.92"></a>
<FONT color="green">093</FONT>            Integer fn = new Integer(fieldSpec);<a name="line.93"></a>
<FONT color="green">094</FONT>            fieldList.add(fn);<a name="line.94"></a>
<FONT color="green">095</FONT>          } else {<a name="line.95"></a>
<FONT color="green">096</FONT>            String start = fieldSpec.substring(0, pos);<a name="line.96"></a>
<FONT color="green">097</FONT>            String end = fieldSpec.substring(pos + 1);<a name="line.97"></a>
<FONT color="green">098</FONT>            if (start.length() == 0) {<a name="line.98"></a>
<FONT color="green">099</FONT>              start = "0";<a name="line.99"></a>
<FONT color="green">100</FONT>            }<a name="line.100"></a>
<FONT color="green">101</FONT>            if (end.length() == 0) {<a name="line.101"></a>
<FONT color="green">102</FONT>              allFieldsFrom = Integer.parseInt(start);<a name="line.102"></a>
<FONT color="green">103</FONT>              continue;<a name="line.103"></a>
<FONT color="green">104</FONT>            }<a name="line.104"></a>
<FONT color="green">105</FONT>            int startPos = Integer.parseInt(start);<a name="line.105"></a>
<FONT color="green">106</FONT>            int endPos = Integer.parseInt(end);<a name="line.106"></a>
<FONT color="green">107</FONT>            for (j = startPos; j &lt;= endPos; j++) {<a name="line.107"></a>
<FONT color="green">108</FONT>              fieldList.add(j);<a name="line.108"></a>
<FONT color="green">109</FONT>            }<a name="line.109"></a>
<FONT color="green">110</FONT>          }<a name="line.110"></a>
<FONT color="green">111</FONT>        }<a name="line.111"></a>
<FONT color="green">112</FONT>        return allFieldsFrom;<a name="line.112"></a>
<FONT color="green">113</FONT>      }<a name="line.113"></a>
<FONT color="green">114</FONT>    <a name="line.114"></a>
<FONT color="green">115</FONT>      private static String selectFields(String[] fields, List&lt;Integer&gt; fieldList,<a name="line.115"></a>
<FONT color="green">116</FONT>          int allFieldsFrom, String separator) {<a name="line.116"></a>
<FONT color="green">117</FONT>        String retv = null;<a name="line.117"></a>
<FONT color="green">118</FONT>        int i = 0;<a name="line.118"></a>
<FONT color="green">119</FONT>        StringBuffer sb = null;<a name="line.119"></a>
<FONT color="green">120</FONT>        if (fieldList != null &amp;&amp; fieldList.size() &gt; 0) {<a name="line.120"></a>
<FONT color="green">121</FONT>          if (sb == null) {<a name="line.121"></a>
<FONT color="green">122</FONT>            sb = new StringBuffer();<a name="line.122"></a>
<FONT color="green">123</FONT>          }<a name="line.123"></a>
<FONT color="green">124</FONT>          for (Integer index : fieldList) {<a name="line.124"></a>
<FONT color="green">125</FONT>            if (index &lt; fields.length) {<a name="line.125"></a>
<FONT color="green">126</FONT>              sb.append(fields[index]);<a name="line.126"></a>
<FONT color="green">127</FONT>            }<a name="line.127"></a>
<FONT color="green">128</FONT>            sb.append(separator);<a name="line.128"></a>
<FONT color="green">129</FONT>          }<a name="line.129"></a>
<FONT color="green">130</FONT>        }<a name="line.130"></a>
<FONT color="green">131</FONT>        if (allFieldsFrom &gt;= 0) {<a name="line.131"></a>
<FONT color="green">132</FONT>          if (sb == null) {<a name="line.132"></a>
<FONT color="green">133</FONT>            sb = new StringBuffer();<a name="line.133"></a>
<FONT color="green">134</FONT>          }<a name="line.134"></a>
<FONT color="green">135</FONT>          for (i = allFieldsFrom; i &lt; fields.length; i++) {<a name="line.135"></a>
<FONT color="green">136</FONT>            sb.append(fields[i]).append(separator);<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>        if (sb != null) {<a name="line.139"></a>
<FONT color="green">140</FONT>          retv = sb.toString();<a name="line.140"></a>
<FONT color="green">141</FONT>          if (retv.length() &gt; 0) {<a name="line.141"></a>
<FONT color="green">142</FONT>            retv = retv.substring(0, retv.length() - 1);<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>        return retv;<a name="line.145"></a>
<FONT color="green">146</FONT>      }<a name="line.146"></a>
<FONT color="green">147</FONT>      <a name="line.147"></a>
<FONT color="green">148</FONT>      public static int parseOutputKeyValueSpec(String keyValueSpec,<a name="line.148"></a>
<FONT color="green">149</FONT>          List&lt;Integer&gt; keyFieldList, List&lt;Integer&gt; valueFieldList) {<a name="line.149"></a>
<FONT color="green">150</FONT>        String[] keyValSpecs = keyValueSpec.split(":", -1);<a name="line.150"></a>
<FONT color="green">151</FONT>        <a name="line.151"></a>
<FONT color="green">152</FONT>        String[] keySpec = keyValSpecs[0].split(",");<a name="line.152"></a>
<FONT color="green">153</FONT>        <a name="line.153"></a>
<FONT color="green">154</FONT>        String[] valSpec = new String[0];<a name="line.154"></a>
<FONT color="green">155</FONT>        if (keyValSpecs.length &gt; 1) {<a name="line.155"></a>
<FONT color="green">156</FONT>          valSpec = keyValSpecs[1].split(",");<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>        FieldSelectionHelper.extractFields(keySpec, keyFieldList);<a name="line.159"></a>
<FONT color="green">160</FONT>        return FieldSelectionHelper.extractFields(valSpec, valueFieldList);<a name="line.160"></a>
<FONT color="green">161</FONT>      }<a name="line.161"></a>
<FONT color="green">162</FONT>    <a name="line.162"></a>
<FONT color="green">163</FONT>      public static String specToString(String fieldSeparator, String keyValueSpec,<a name="line.163"></a>
<FONT color="green">164</FONT>          int allValueFieldsFrom, List&lt;Integer&gt; keyFieldList,<a name="line.164"></a>
<FONT color="green">165</FONT>          List&lt;Integer&gt; valueFieldList) {<a name="line.165"></a>
<FONT color="green">166</FONT>        StringBuffer sb = new StringBuffer();<a name="line.166"></a>
<FONT color="green">167</FONT>        sb.append("fieldSeparator: ").append(fieldSeparator).append("\n");<a name="line.167"></a>
<FONT color="green">168</FONT>    <a name="line.168"></a>
<FONT color="green">169</FONT>        sb.append("keyValueSpec: ").append(keyValueSpec).append("\n");<a name="line.169"></a>
<FONT color="green">170</FONT>        sb.append("allValueFieldsFrom: ").append(allValueFieldsFrom);<a name="line.170"></a>
<FONT color="green">171</FONT>        sb.append("\n");<a name="line.171"></a>
<FONT color="green">172</FONT>        sb.append("keyFieldList.length: ").append(keyFieldList.size());<a name="line.172"></a>
<FONT color="green">173</FONT>        sb.append("\n");<a name="line.173"></a>
<FONT color="green">174</FONT>        for (Integer field : keyFieldList) {<a name="line.174"></a>
<FONT color="green">175</FONT>          sb.append("\t").append(field).append("\n");<a name="line.175"></a>
<FONT color="green">176</FONT>        }<a name="line.176"></a>
<FONT color="green">177</FONT>        sb.append("valueFieldList.length: ").append(valueFieldList.size());<a name="line.177"></a>
<FONT color="green">178</FONT>        sb.append("\n");<a name="line.178"></a>
<FONT color="green">179</FONT>        for (Integer field : valueFieldList) {<a name="line.179"></a>
<FONT color="green">180</FONT>          sb.append("\t").append(field).append("\n");<a name="line.180"></a>
<FONT color="green">181</FONT>        }<a name="line.181"></a>
<FONT color="green">182</FONT>        return sb.toString();<a name="line.182"></a>
<FONT color="green">183</FONT>      }<a name="line.183"></a>
<FONT color="green">184</FONT>    <a name="line.184"></a>
<FONT color="green">185</FONT>      private Text key = null;<a name="line.185"></a>
<FONT color="green">186</FONT>      private Text value = null;<a name="line.186"></a>
<FONT color="green">187</FONT>      <a name="line.187"></a>
<FONT color="green">188</FONT>      public FieldSelectionHelper() {<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>      public FieldSelectionHelper(Text key, Text val) {<a name="line.191"></a>
<FONT color="green">192</FONT>        this.key = key;<a name="line.192"></a>
<FONT color="green">193</FONT>        this.value = val;<a name="line.193"></a>
<FONT color="green">194</FONT>      }<a name="line.194"></a>
<FONT color="green">195</FONT>      <a name="line.195"></a>
<FONT color="green">196</FONT>      public Text getKey() {<a name="line.196"></a>
<FONT color="green">197</FONT>        return key;<a name="line.197"></a>
<FONT color="green">198</FONT>      }<a name="line.198"></a>
<FONT color="green">199</FONT>     <a name="line.199"></a>
<FONT color="green">200</FONT>      public Text getValue() {<a name="line.200"></a>
<FONT color="green">201</FONT>        return value;<a name="line.201"></a>
<FONT color="green">202</FONT>      }<a name="line.202"></a>
<FONT color="green">203</FONT>    <a name="line.203"></a>
<FONT color="green">204</FONT>      public void extractOutputKeyValue(String key, String val,<a name="line.204"></a>
<FONT color="green">205</FONT>          String fieldSep, List&lt;Integer&gt; keyFieldList, List&lt;Integer&gt; valFieldList,<a name="line.205"></a>
<FONT color="green">206</FONT>          int allValueFieldsFrom, boolean ignoreKey, boolean isMap) {<a name="line.206"></a>
<FONT color="green">207</FONT>        if (!ignoreKey) {<a name="line.207"></a>
<FONT color="green">208</FONT>          val = key + val;<a name="line.208"></a>
<FONT color="green">209</FONT>        }<a name="line.209"></a>
<FONT color="green">210</FONT>        String[] fields = val.split(fieldSep);<a name="line.210"></a>
<FONT color="green">211</FONT>        <a name="line.211"></a>
<FONT color="green">212</FONT>        String newKey = selectFields(fields, keyFieldList, -1, fieldSep);<a name="line.212"></a>
<FONT color="green">213</FONT>        String newVal = selectFields(fields, valFieldList, allValueFieldsFrom,<a name="line.213"></a>
<FONT color="green">214</FONT>          fieldSep);<a name="line.214"></a>
<FONT color="green">215</FONT>        if (isMap &amp;&amp; newKey == null) {<a name="line.215"></a>
<FONT color="green">216</FONT>          newKey = newVal;<a name="line.216"></a>
<FONT color="green">217</FONT>          newVal = null;<a name="line.217"></a>
<FONT color="green">218</FONT>        }<a name="line.218"></a>
<FONT color="green">219</FONT>        <a name="line.219"></a>
<FONT color="green">220</FONT>        if (newKey != null) {<a name="line.220"></a>
<FONT color="green">221</FONT>          this.key = new Text(newKey);<a name="line.221"></a>
<FONT color="green">222</FONT>        }<a name="line.222"></a>
<FONT color="green">223</FONT>        if (newVal != null) {<a name="line.223"></a>
<FONT color="green">224</FONT>          this.value = new Text(newVal);<a name="line.224"></a>
<FONT color="green">225</FONT>        }<a name="line.225"></a>
<FONT color="green">226</FONT>      }<a name="line.226"></a>
<FONT color="green">227</FONT>    }<a name="line.227"></a>




























































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