<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.join;<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.List;<a name="line.23"></a>
<FONT color="green">024</FONT>    import java.util.Map;<a name="line.24"></a>
<FONT color="green">025</FONT>    import java.util.regex.Matcher;<a name="line.25"></a>
<FONT color="green">026</FONT>    import java.util.regex.Pattern;<a name="line.26"></a>
<FONT color="green">027</FONT>    <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.conf.Configuration;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.fs.Path;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.io.WritableComparable;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.mapreduce.InputFormat;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.mapreduce.InputSplit;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.mapreduce.RecordReader;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.37"></a>
<FONT color="green">038</FONT>    <a name="line.38"></a>
<FONT color="green">039</FONT>    /**<a name="line.39"></a>
<FONT color="green">040</FONT>     * An InputFormat capable of performing joins over a set of data sources sorted<a name="line.40"></a>
<FONT color="green">041</FONT>     * and partitioned the same way.<a name="line.41"></a>
<FONT color="green">042</FONT>     * @see #setFormat<a name="line.42"></a>
<FONT color="green">043</FONT>     *<a name="line.43"></a>
<FONT color="green">044</FONT>     * A user may define new join types by setting the property<a name="line.44"></a>
<FONT color="green">045</FONT>     * &lt;tt&gt;mapreduce.join.define.&amp;lt;ident&amp;gt;&lt;/tt&gt; to a classname. <a name="line.45"></a>
<FONT color="green">046</FONT>     * In the expression &lt;tt&gt;mapreduce.join.expr&lt;/tt&gt;, the identifier will be<a name="line.46"></a>
<FONT color="green">047</FONT>     * assumed to be a ComposableRecordReader.<a name="line.47"></a>
<FONT color="green">048</FONT>     * &lt;tt&gt;mapreduce.join.keycomparator&lt;/tt&gt; can be a classname used to compare <a name="line.48"></a>
<FONT color="green">049</FONT>     * keys in the join.<a name="line.49"></a>
<FONT color="green">050</FONT>     * @see JoinRecordReader<a name="line.50"></a>
<FONT color="green">051</FONT>     * @see MultiFilterRecordReader<a name="line.51"></a>
<FONT color="green">052</FONT>     */<a name="line.52"></a>
<FONT color="green">053</FONT>    @SuppressWarnings("unchecked")<a name="line.53"></a>
<FONT color="green">054</FONT>    @InterfaceAudience.Public<a name="line.54"></a>
<FONT color="green">055</FONT>    @InterfaceStability.Stable<a name="line.55"></a>
<FONT color="green">056</FONT>    public class CompositeInputFormat&lt;K extends WritableComparable&gt;<a name="line.56"></a>
<FONT color="green">057</FONT>        extends InputFormat&lt;K, TupleWritable&gt; {<a name="line.57"></a>
<FONT color="green">058</FONT>    <a name="line.58"></a>
<FONT color="green">059</FONT>      public static final String JOIN_EXPR = "mapreduce.join.expr";<a name="line.59"></a>
<FONT color="green">060</FONT>      public static final String JOIN_COMPARATOR = "mapreduce.join.keycomparator";<a name="line.60"></a>
<FONT color="green">061</FONT>      <a name="line.61"></a>
<FONT color="green">062</FONT>      // expression parse tree to which IF requests are proxied<a name="line.62"></a>
<FONT color="green">063</FONT>      private Parser.Node root;<a name="line.63"></a>
<FONT color="green">064</FONT>    <a name="line.64"></a>
<FONT color="green">065</FONT>      public CompositeInputFormat() { }<a name="line.65"></a>
<FONT color="green">066</FONT>    <a name="line.66"></a>
<FONT color="green">067</FONT>    <a name="line.67"></a>
<FONT color="green">068</FONT>      /**<a name="line.68"></a>
<FONT color="green">069</FONT>       * Interpret a given string as a composite expression.<a name="line.69"></a>
<FONT color="green">070</FONT>       * {@code<a name="line.70"></a>
<FONT color="green">071</FONT>       *   func  ::= &lt;ident&gt;([&lt;func&gt;,]*&lt;func&gt;)<a name="line.71"></a>
<FONT color="green">072</FONT>       *   func  ::= tbl(&lt;class&gt;,"&lt;path&gt;")<a name="line.72"></a>
<FONT color="green">073</FONT>       *   class ::= @see java.lang.Class#forName(java.lang.String)<a name="line.73"></a>
<FONT color="green">074</FONT>       *   path  ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String)<a name="line.74"></a>
<FONT color="green">075</FONT>       * }<a name="line.75"></a>
<FONT color="green">076</FONT>       * Reads expression from the &lt;tt&gt;mapreduce.join.expr&lt;/tt&gt; property and<a name="line.76"></a>
<FONT color="green">077</FONT>       * user-supplied join types from &lt;tt&gt;mapreduce.join.define.&amp;lt;ident&amp;gt;&lt;/tt&gt;<a name="line.77"></a>
<FONT color="green">078</FONT>       *  types. Paths supplied to &lt;tt&gt;tbl&lt;/tt&gt; are given as input paths to the<a name="line.78"></a>
<FONT color="green">079</FONT>       * InputFormat class listed.<a name="line.79"></a>
<FONT color="green">080</FONT>       * @see #compose(java.lang.String, java.lang.Class, java.lang.String...)<a name="line.80"></a>
<FONT color="green">081</FONT>       */<a name="line.81"></a>
<FONT color="green">082</FONT>      public void setFormat(Configuration conf) throws IOException {<a name="line.82"></a>
<FONT color="green">083</FONT>        addDefaults();<a name="line.83"></a>
<FONT color="green">084</FONT>        addUserIdentifiers(conf);<a name="line.84"></a>
<FONT color="green">085</FONT>        root = Parser.parse(conf.get(JOIN_EXPR, null), conf);<a name="line.85"></a>
<FONT color="green">086</FONT>      }<a name="line.86"></a>
<FONT color="green">087</FONT>    <a name="line.87"></a>
<FONT color="green">088</FONT>      /**<a name="line.88"></a>
<FONT color="green">089</FONT>       * Adds the default set of identifiers to the parser.<a name="line.89"></a>
<FONT color="green">090</FONT>       */<a name="line.90"></a>
<FONT color="green">091</FONT>      protected void addDefaults() {<a name="line.91"></a>
<FONT color="green">092</FONT>        try {<a name="line.92"></a>
<FONT color="green">093</FONT>          Parser.CNode.addIdentifier("inner", InnerJoinRecordReader.class);<a name="line.93"></a>
<FONT color="green">094</FONT>          Parser.CNode.addIdentifier("outer", OuterJoinRecordReader.class);<a name="line.94"></a>
<FONT color="green">095</FONT>          Parser.CNode.addIdentifier("override", OverrideRecordReader.class);<a name="line.95"></a>
<FONT color="green">096</FONT>          Parser.WNode.addIdentifier("tbl", WrappedRecordReader.class);<a name="line.96"></a>
<FONT color="green">097</FONT>        } catch (NoSuchMethodException e) {<a name="line.97"></a>
<FONT color="green">098</FONT>          throw new RuntimeException("FATAL: Failed to init defaults", e);<a name="line.98"></a>
<FONT color="green">099</FONT>        }<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>       * Inform the parser of user-defined types.<a name="line.103"></a>
<FONT color="green">104</FONT>       */<a name="line.104"></a>
<FONT color="green">105</FONT>      private void addUserIdentifiers(Configuration conf) throws IOException {<a name="line.105"></a>
<FONT color="green">106</FONT>        Pattern x = Pattern.compile("^mapreduce\\.join\\.define\\.(\\w+)$");<a name="line.106"></a>
<FONT color="green">107</FONT>        for (Map.Entry&lt;String,String&gt; kv : conf) {<a name="line.107"></a>
<FONT color="green">108</FONT>          Matcher m = x.matcher(kv.getKey());<a name="line.108"></a>
<FONT color="green">109</FONT>          if (m.matches()) {<a name="line.109"></a>
<FONT color="green">110</FONT>            try {<a name="line.110"></a>
<FONT color="green">111</FONT>              Parser.CNode.addIdentifier(m.group(1),<a name="line.111"></a>
<FONT color="green">112</FONT>                  conf.getClass(m.group(0), null, ComposableRecordReader.class));<a name="line.112"></a>
<FONT color="green">113</FONT>            } catch (NoSuchMethodException e) {<a name="line.113"></a>
<FONT color="green">114</FONT>              throw new IOException("Invalid define for " + m.group(1), e);<a name="line.114"></a>
<FONT color="green">115</FONT>            }<a name="line.115"></a>
<FONT color="green">116</FONT>          }<a name="line.116"></a>
<FONT color="green">117</FONT>        }<a name="line.117"></a>
<FONT color="green">118</FONT>      }<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>       * Build a CompositeInputSplit from the child InputFormats by assigning the<a name="line.121"></a>
<FONT color="green">122</FONT>       * ith split from each child to the ith composite split.<a name="line.122"></a>
<FONT color="green">123</FONT>       */<a name="line.123"></a>
<FONT color="green">124</FONT>      @SuppressWarnings("unchecked")<a name="line.124"></a>
<FONT color="green">125</FONT>      public List&lt;InputSplit&gt; getSplits(JobContext job) <a name="line.125"></a>
<FONT color="green">126</FONT>          throws IOException, InterruptedException {<a name="line.126"></a>
<FONT color="green">127</FONT>        setFormat(job.getConfiguration());<a name="line.127"></a>
<FONT color="green">128</FONT>        job.getConfiguration().setLong("mapreduce.input.fileinputformat.split.minsize", Long.MAX_VALUE);<a name="line.128"></a>
<FONT color="green">129</FONT>        return root.getSplits(job);<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>       * Construct a CompositeRecordReader for the children of this InputFormat<a name="line.133"></a>
<FONT color="green">134</FONT>       * as defined in the init expression.<a name="line.134"></a>
<FONT color="green">135</FONT>       * The outermost join need only be composable, not necessarily a composite.<a name="line.135"></a>
<FONT color="green">136</FONT>       * Mandating TupleWritable isn't strictly correct.<a name="line.136"></a>
<FONT color="green">137</FONT>       */<a name="line.137"></a>
<FONT color="green">138</FONT>      @SuppressWarnings("unchecked") // child types unknown<a name="line.138"></a>
<FONT color="green">139</FONT>      public RecordReader&lt;K,TupleWritable&gt; createRecordReader(InputSplit split, <a name="line.139"></a>
<FONT color="green">140</FONT>          TaskAttemptContext taskContext) <a name="line.140"></a>
<FONT color="green">141</FONT>          throws IOException, InterruptedException {<a name="line.141"></a>
<FONT color="green">142</FONT>        setFormat(taskContext.getConfiguration());<a name="line.142"></a>
<FONT color="green">143</FONT>        return root.createRecordReader(split, taskContext);<a name="line.143"></a>
<FONT color="green">144</FONT>      }<a name="line.144"></a>
<FONT color="green">145</FONT>    <a name="line.145"></a>
<FONT color="green">146</FONT>      /**<a name="line.146"></a>
<FONT color="green">147</FONT>       * Convenience method for constructing composite formats.<a name="line.147"></a>
<FONT color="green">148</FONT>       * Given InputFormat class (inf), path (p) return:<a name="line.148"></a>
<FONT color="green">149</FONT>       * {@code tbl(&lt;inf&gt;, &lt;p&gt;) }<a name="line.149"></a>
<FONT color="green">150</FONT>       */<a name="line.150"></a>
<FONT color="green">151</FONT>      public static String compose(Class&lt;? extends InputFormat&gt; inf, <a name="line.151"></a>
<FONT color="green">152</FONT>          String path) {<a name="line.152"></a>
<FONT color="green">153</FONT>        return compose(inf.getName().intern(), path, <a name="line.153"></a>
<FONT color="green">154</FONT>                 new StringBuffer()).toString();<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>
<FONT color="green">158</FONT>       * Convenience method for constructing composite formats.<a name="line.158"></a>
<FONT color="green">159</FONT>       * Given operation (op), Object class (inf), set of paths (p) return:<a name="line.159"></a>
<FONT color="green">160</FONT>       * {@code &lt;op&gt;(tbl(&lt;inf&gt;,&lt;p1&gt;),tbl(&lt;inf&gt;,&lt;p2&gt;),...,tbl(&lt;inf&gt;,&lt;pn&gt;)) }<a name="line.160"></a>
<FONT color="green">161</FONT>       */<a name="line.161"></a>
<FONT color="green">162</FONT>      public static String compose(String op, <a name="line.162"></a>
<FONT color="green">163</FONT>          Class&lt;? extends InputFormat&gt; inf, String... path) {<a name="line.163"></a>
<FONT color="green">164</FONT>        final String infname = inf.getName();<a name="line.164"></a>
<FONT color="green">165</FONT>        StringBuffer ret = new StringBuffer(op + '(');<a name="line.165"></a>
<FONT color="green">166</FONT>        for (String p : path) {<a name="line.166"></a>
<FONT color="green">167</FONT>          compose(infname, p, ret);<a name="line.167"></a>
<FONT color="green">168</FONT>          ret.append(',');<a name="line.168"></a>
<FONT color="green">169</FONT>        }<a name="line.169"></a>
<FONT color="green">170</FONT>        ret.setCharAt(ret.length() - 1, ')');<a name="line.170"></a>
<FONT color="green">171</FONT>        return ret.toString();<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>      /**<a name="line.174"></a>
<FONT color="green">175</FONT>       * Convenience method for constructing composite formats.<a name="line.175"></a>
<FONT color="green">176</FONT>       * Given operation (op), Object class (inf), set of paths (p) return:<a name="line.176"></a>
<FONT color="green">177</FONT>       * {@code &lt;op&gt;(tbl(&lt;inf&gt;,&lt;p1&gt;),tbl(&lt;inf&gt;,&lt;p2&gt;),...,tbl(&lt;inf&gt;,&lt;pn&gt;)) }<a name="line.177"></a>
<FONT color="green">178</FONT>       */<a name="line.178"></a>
<FONT color="green">179</FONT>      public static String compose(String op, <a name="line.179"></a>
<FONT color="green">180</FONT>          Class&lt;? extends InputFormat&gt; inf, Path... path) {<a name="line.180"></a>
<FONT color="green">181</FONT>        ArrayList&lt;String&gt; tmp = new ArrayList&lt;String&gt;(path.length);<a name="line.181"></a>
<FONT color="green">182</FONT>        for (Path p : path) {<a name="line.182"></a>
<FONT color="green">183</FONT>          tmp.add(p.toString());<a name="line.183"></a>
<FONT color="green">184</FONT>        }<a name="line.184"></a>
<FONT color="green">185</FONT>        return compose(op, inf, tmp.toArray(new String[0]));<a name="line.185"></a>
<FONT color="green">186</FONT>      }<a name="line.186"></a>
<FONT color="green">187</FONT>    <a name="line.187"></a>
<FONT color="green">188</FONT>      private static StringBuffer compose(String inf, String path,<a name="line.188"></a>
<FONT color="green">189</FONT>          StringBuffer sb) {<a name="line.189"></a>
<FONT color="green">190</FONT>        sb.append("tbl(" + inf + ",\"");<a name="line.190"></a>
<FONT color="green">191</FONT>        sb.append(path);<a name="line.191"></a>
<FONT color="green">192</FONT>        sb.append("\")");<a name="line.192"></a>
<FONT color="green">193</FONT>        return sb;<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>




























































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