<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.partition;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.UnsupportedEncodingException;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.List;<a name="line.22"></a>
<FONT color="green">023</FONT>    <a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.commons.logging.Log;<a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.commons.logging.LogFactory;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.conf.Configurable;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.mapreduce.MRJobConfig;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.mapreduce.Partitioner;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.lib.partition.KeyFieldHelper.KeyDescription;<a name="line.34"></a>
<FONT color="green">035</FONT>    <a name="line.35"></a>
<FONT color="green">036</FONT>     /**   <a name="line.36"></a>
<FONT color="green">037</FONT>      *  Defines a way to partition keys based on certain key fields (also see<a name="line.37"></a>
<FONT color="green">038</FONT>      *  {@link KeyFieldBasedComparator}.<a name="line.38"></a>
<FONT color="green">039</FONT>      *  The key specification supported is of the form -k pos1[,pos2], where,<a name="line.39"></a>
<FONT color="green">040</FONT>      *  pos is of the form f[.c][opts], where f is the number<a name="line.40"></a>
<FONT color="green">041</FONT>      *  of the key field to use, and c is the number of the first character from<a name="line.41"></a>
<FONT color="green">042</FONT>      *  the beginning of the field. Fields and character posns are numbered <a name="line.42"></a>
<FONT color="green">043</FONT>      *  starting with 1; a character position of zero in pos2 indicates the<a name="line.43"></a>
<FONT color="green">044</FONT>      *  field's last character. If '.c' is omitted from pos1, it defaults to 1<a name="line.44"></a>
<FONT color="green">045</FONT>      *  (the beginning of the field); if omitted from pos2, it defaults to 0 <a name="line.45"></a>
<FONT color="green">046</FONT>      *  (the end of the field).<a name="line.46"></a>
<FONT color="green">047</FONT>      * <a name="line.47"></a>
<FONT color="green">048</FONT>      */<a name="line.48"></a>
<FONT color="green">049</FONT>    @InterfaceAudience.Public<a name="line.49"></a>
<FONT color="green">050</FONT>    @InterfaceStability.Stable<a name="line.50"></a>
<FONT color="green">051</FONT>    public class KeyFieldBasedPartitioner&lt;K2, V2&gt; extends Partitioner&lt;K2, V2&gt; <a name="line.51"></a>
<FONT color="green">052</FONT>        implements Configurable {<a name="line.52"></a>
<FONT color="green">053</FONT>    <a name="line.53"></a>
<FONT color="green">054</FONT>      private static final Log LOG = LogFactory.getLog(<a name="line.54"></a>
<FONT color="green">055</FONT>                                       KeyFieldBasedPartitioner.class.getName());<a name="line.55"></a>
<FONT color="green">056</FONT>      public static String PARTITIONER_OPTIONS = <a name="line.56"></a>
<FONT color="green">057</FONT>        "mapreduce.partition.keypartitioner.options";<a name="line.57"></a>
<FONT color="green">058</FONT>      private int numOfPartitionFields;<a name="line.58"></a>
<FONT color="green">059</FONT>      <a name="line.59"></a>
<FONT color="green">060</FONT>      private KeyFieldHelper keyFieldHelper = new KeyFieldHelper();<a name="line.60"></a>
<FONT color="green">061</FONT>      <a name="line.61"></a>
<FONT color="green">062</FONT>      private Configuration conf;<a name="line.62"></a>
<FONT color="green">063</FONT>    <a name="line.63"></a>
<FONT color="green">064</FONT>      public void setConf(Configuration conf) {<a name="line.64"></a>
<FONT color="green">065</FONT>        this.conf = conf;<a name="line.65"></a>
<FONT color="green">066</FONT>        String keyFieldSeparator = <a name="line.66"></a>
<FONT color="green">067</FONT>          conf.get(MRJobConfig.MAP_OUTPUT_KEY_FIELD_SEPERATOR, "\t");<a name="line.67"></a>
<FONT color="green">068</FONT>        keyFieldHelper.setKeyFieldSeparator(keyFieldSeparator);<a name="line.68"></a>
<FONT color="green">069</FONT>        if (conf.get("num.key.fields.for.partition") != null) {<a name="line.69"></a>
<FONT color="green">070</FONT>          LOG.warn("Using deprecated num.key.fields.for.partition. " +<a name="line.70"></a>
<FONT color="green">071</FONT>                    "Use mapreduce.partition.keypartitioner.options instead");<a name="line.71"></a>
<FONT color="green">072</FONT>          this.numOfPartitionFields = conf.getInt("num.key.fields.for.partition",0);<a name="line.72"></a>
<FONT color="green">073</FONT>          keyFieldHelper.setKeyFieldSpec(1,numOfPartitionFields);<a name="line.73"></a>
<FONT color="green">074</FONT>        } else {<a name="line.74"></a>
<FONT color="green">075</FONT>          String option = conf.get(PARTITIONER_OPTIONS);<a name="line.75"></a>
<FONT color="green">076</FONT>          keyFieldHelper.parseOption(option);<a name="line.76"></a>
<FONT color="green">077</FONT>        }<a name="line.77"></a>
<FONT color="green">078</FONT>      }<a name="line.78"></a>
<FONT color="green">079</FONT>    <a name="line.79"></a>
<FONT color="green">080</FONT>      public Configuration getConf() {<a name="line.80"></a>
<FONT color="green">081</FONT>        return conf;<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 int getPartition(K2 key, V2 value, int numReduceTasks) {<a name="line.84"></a>
<FONT color="green">085</FONT>        byte[] keyBytes;<a name="line.85"></a>
<FONT color="green">086</FONT>    <a name="line.86"></a>
<FONT color="green">087</FONT>        List &lt;KeyDescription&gt; allKeySpecs = keyFieldHelper.keySpecs();<a name="line.87"></a>
<FONT color="green">088</FONT>        if (allKeySpecs.size() == 0) {<a name="line.88"></a>
<FONT color="green">089</FONT>          return getPartition(key.toString().hashCode(), numReduceTasks);<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>        try {<a name="line.92"></a>
<FONT color="green">093</FONT>          keyBytes = key.toString().getBytes("UTF-8");<a name="line.93"></a>
<FONT color="green">094</FONT>        } catch (UnsupportedEncodingException e) {<a name="line.94"></a>
<FONT color="green">095</FONT>          throw new RuntimeException("The current system does not " +<a name="line.95"></a>
<FONT color="green">096</FONT>              "support UTF-8 encoding!", e);<a name="line.96"></a>
<FONT color="green">097</FONT>        }<a name="line.97"></a>
<FONT color="green">098</FONT>        // return 0 if the key is empty<a name="line.98"></a>
<FONT color="green">099</FONT>        if (keyBytes.length == 0) {<a name="line.99"></a>
<FONT color="green">100</FONT>          return 0;<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>        int []lengthIndicesFirst = keyFieldHelper.getWordLengths(keyBytes, 0, <a name="line.103"></a>
<FONT color="green">104</FONT>            keyBytes.length);<a name="line.104"></a>
<FONT color="green">105</FONT>        int currentHash = 0;<a name="line.105"></a>
<FONT color="green">106</FONT>        for (KeyDescription keySpec : allKeySpecs) {<a name="line.106"></a>
<FONT color="green">107</FONT>          int startChar = keyFieldHelper.getStartOffset(keyBytes, 0, <a name="line.107"></a>
<FONT color="green">108</FONT>            keyBytes.length, lengthIndicesFirst, keySpec);<a name="line.108"></a>
<FONT color="green">109</FONT>           // no key found! continue<a name="line.109"></a>
<FONT color="green">110</FONT>          if (startChar &lt; 0) {<a name="line.110"></a>
<FONT color="green">111</FONT>            continue;<a name="line.111"></a>
<FONT color="green">112</FONT>          }<a name="line.112"></a>
<FONT color="green">113</FONT>          int endChar = keyFieldHelper.getEndOffset(keyBytes, 0, keyBytes.length, <a name="line.113"></a>
<FONT color="green">114</FONT>              lengthIndicesFirst, keySpec);<a name="line.114"></a>
<FONT color="green">115</FONT>          currentHash = hashCode(keyBytes, startChar, endChar, <a name="line.115"></a>
<FONT color="green">116</FONT>              currentHash);<a name="line.116"></a>
<FONT color="green">117</FONT>        }<a name="line.117"></a>
<FONT color="green">118</FONT>        return getPartition(currentHash, numReduceTasks);<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>      protected int hashCode(byte[] b, int start, int end, int currentHash) {<a name="line.121"></a>
<FONT color="green">122</FONT>        for (int i = start; i &lt;= end; i++) {<a name="line.122"></a>
<FONT color="green">123</FONT>          currentHash = 31*currentHash + b[i];<a name="line.123"></a>
<FONT color="green">124</FONT>        }<a name="line.124"></a>
<FONT color="green">125</FONT>        return currentHash;<a name="line.125"></a>
<FONT color="green">126</FONT>      }<a name="line.126"></a>
<FONT color="green">127</FONT>    <a name="line.127"></a>
<FONT color="green">128</FONT>      protected int getPartition(int hash, int numReduceTasks) {<a name="line.128"></a>
<FONT color="green">129</FONT>        return (hash &amp; Integer.MAX_VALUE) % numReduceTasks;<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>      /**<a name="line.132"></a>
<FONT color="green">133</FONT>       * Set the {@link KeyFieldBasedPartitioner} options used for <a name="line.133"></a>
<FONT color="green">134</FONT>       * {@link Partitioner}<a name="line.134"></a>
<FONT color="green">135</FONT>       * <a name="line.135"></a>
<FONT color="green">136</FONT>       * @param keySpec the key specification of the form -k pos1[,pos2], where,<a name="line.136"></a>
<FONT color="green">137</FONT>       *  pos is of the form f[.c][opts], where f is the number<a name="line.137"></a>
<FONT color="green">138</FONT>       *  of the key field to use, and c is the number of the first character from<a name="line.138"></a>
<FONT color="green">139</FONT>       *  the beginning of the field. Fields and character posns are numbered <a name="line.139"></a>
<FONT color="green">140</FONT>       *  starting with 1; a character position of zero in pos2 indicates the<a name="line.140"></a>
<FONT color="green">141</FONT>       *  field's last character. If '.c' is omitted from pos1, it defaults to 1<a name="line.141"></a>
<FONT color="green">142</FONT>       *  (the beginning of the field); if omitted from pos2, it defaults to 0 <a name="line.142"></a>
<FONT color="green">143</FONT>       *  (the end of the field).<a name="line.143"></a>
<FONT color="green">144</FONT>       */<a name="line.144"></a>
<FONT color="green">145</FONT>      public void setKeyFieldPartitionerOptions(Job job, String keySpec) {<a name="line.145"></a>
<FONT color="green">146</FONT>        job.getConfiguration().set(PARTITIONER_OPTIONS, keySpec);<a name="line.146"></a>
<FONT color="green">147</FONT>      }<a name="line.147"></a>
<FONT color="green">148</FONT>      <a name="line.148"></a>
<FONT color="green">149</FONT>      /**<a name="line.149"></a>
<FONT color="green">150</FONT>       * Get the {@link KeyFieldBasedPartitioner} options<a name="line.150"></a>
<FONT color="green">151</FONT>       */<a name="line.151"></a>
<FONT color="green">152</FONT>      public String getKeyFieldPartitionerOption(JobContext job) {<a name="line.152"></a>
<FONT color="green">153</FONT>        return job.getConfiguration().get(PARTITIONER_OPTIONS);<a name="line.153"></a>
<FONT color="green">154</FONT>      }<a name="line.154"></a>
<FONT color="green">155</FONT>    <a name="line.155"></a>
<FONT color="green">156</FONT>    <a name="line.156"></a>
<FONT color="green">157</FONT>    }<a name="line.157"></a>




























































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