<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.input;<a name="line.18"></a>
<FONT color="green">019</FONT>    <a name="line.19"></a>
<FONT color="green">020</FONT>    import java.util.Collections;<a name="line.20"></a>
<FONT color="green">021</FONT>    import java.util.HashMap;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.Map;<a name="line.22"></a>
<FONT color="green">023</FONT>    <a name="line.23"></a>
<FONT color="green">024</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.fs.Path;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.mapreduce.InputFormat;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapreduce.Mapper;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.util.ReflectionUtils;<a name="line.32"></a>
<FONT color="green">033</FONT>    <a name="line.33"></a>
<FONT color="green">034</FONT>    /**<a name="line.34"></a>
<FONT color="green">035</FONT>     * This class supports MapReduce jobs that have multiple input paths with<a name="line.35"></a>
<FONT color="green">036</FONT>     * a different {@link InputFormat} and {@link Mapper} for each path <a name="line.36"></a>
<FONT color="green">037</FONT>     */<a name="line.37"></a>
<FONT color="green">038</FONT>    @InterfaceAudience.Public<a name="line.38"></a>
<FONT color="green">039</FONT>    @InterfaceStability.Stable<a name="line.39"></a>
<FONT color="green">040</FONT>    public class MultipleInputs {<a name="line.40"></a>
<FONT color="green">041</FONT>      public static final String DIR_FORMATS = <a name="line.41"></a>
<FONT color="green">042</FONT>        "mapreduce.input.multipleinputs.dir.formats";<a name="line.42"></a>
<FONT color="green">043</FONT>      public static final String DIR_MAPPERS = <a name="line.43"></a>
<FONT color="green">044</FONT>        "mapreduce.input.multipleinputs.dir.mappers";<a name="line.44"></a>
<FONT color="green">045</FONT>      <a name="line.45"></a>
<FONT color="green">046</FONT>      /**<a name="line.46"></a>
<FONT color="green">047</FONT>       * Add a {@link Path} with a custom {@link InputFormat} to the list of<a name="line.47"></a>
<FONT color="green">048</FONT>       * inputs for the map-reduce job.<a name="line.48"></a>
<FONT color="green">049</FONT>       * <a name="line.49"></a>
<FONT color="green">050</FONT>       * @param job The {@link Job}<a name="line.50"></a>
<FONT color="green">051</FONT>       * @param path {@link Path} to be added to the list of inputs for the job<a name="line.51"></a>
<FONT color="green">052</FONT>       * @param inputFormatClass {@link InputFormat} class to use for this path<a name="line.52"></a>
<FONT color="green">053</FONT>       */<a name="line.53"></a>
<FONT color="green">054</FONT>      @SuppressWarnings("unchecked")<a name="line.54"></a>
<FONT color="green">055</FONT>      public static void addInputPath(Job job, Path path,<a name="line.55"></a>
<FONT color="green">056</FONT>          Class&lt;? extends InputFormat&gt; inputFormatClass) {<a name="line.56"></a>
<FONT color="green">057</FONT>        String inputFormatMapping = path.toString() + ";"<a name="line.57"></a>
<FONT color="green">058</FONT>           + inputFormatClass.getName();<a name="line.58"></a>
<FONT color="green">059</FONT>        Configuration conf = job.getConfiguration();<a name="line.59"></a>
<FONT color="green">060</FONT>        String inputFormats = conf.get(DIR_FORMATS);<a name="line.60"></a>
<FONT color="green">061</FONT>        conf.set(DIR_FORMATS,<a name="line.61"></a>
<FONT color="green">062</FONT>           inputFormats == null ? inputFormatMapping : inputFormats + ","<a name="line.62"></a>
<FONT color="green">063</FONT>               + inputFormatMapping);<a name="line.63"></a>
<FONT color="green">064</FONT>    <a name="line.64"></a>
<FONT color="green">065</FONT>        job.setInputFormatClass(DelegatingInputFormat.class);<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>       * Add a {@link Path} with a custom {@link InputFormat} and<a name="line.69"></a>
<FONT color="green">070</FONT>       * {@link Mapper} to the list of inputs for the map-reduce job.<a name="line.70"></a>
<FONT color="green">071</FONT>       * <a name="line.71"></a>
<FONT color="green">072</FONT>       * @param job The {@link Job}<a name="line.72"></a>
<FONT color="green">073</FONT>       * @param path {@link Path} to be added to the list of inputs for the job<a name="line.73"></a>
<FONT color="green">074</FONT>       * @param inputFormatClass {@link InputFormat} class to use for this path<a name="line.74"></a>
<FONT color="green">075</FONT>       * @param mapperClass {@link Mapper} class to use for this path<a name="line.75"></a>
<FONT color="green">076</FONT>       */<a name="line.76"></a>
<FONT color="green">077</FONT>      @SuppressWarnings("unchecked")<a name="line.77"></a>
<FONT color="green">078</FONT>      public static void addInputPath(Job job, Path path,<a name="line.78"></a>
<FONT color="green">079</FONT>          Class&lt;? extends InputFormat&gt; inputFormatClass,<a name="line.79"></a>
<FONT color="green">080</FONT>          Class&lt;? extends Mapper&gt; mapperClass) {<a name="line.80"></a>
<FONT color="green">081</FONT>    <a name="line.81"></a>
<FONT color="green">082</FONT>        addInputPath(job, path, inputFormatClass);<a name="line.82"></a>
<FONT color="green">083</FONT>        Configuration conf = job.getConfiguration();<a name="line.83"></a>
<FONT color="green">084</FONT>        String mapperMapping = path.toString() + ";" + mapperClass.getName();<a name="line.84"></a>
<FONT color="green">085</FONT>        String mappers = conf.get(DIR_MAPPERS);<a name="line.85"></a>
<FONT color="green">086</FONT>        conf.set(DIR_MAPPERS, mappers == null ? mapperMapping<a name="line.86"></a>
<FONT color="green">087</FONT>           : mappers + "," + mapperMapping);<a name="line.87"></a>
<FONT color="green">088</FONT>    <a name="line.88"></a>
<FONT color="green">089</FONT>        job.setMapperClass(DelegatingMapper.class);<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>      /**<a name="line.92"></a>
<FONT color="green">093</FONT>       * Retrieves a map of {@link Path}s to the {@link InputFormat} class<a name="line.93"></a>
<FONT color="green">094</FONT>       * that should be used for them.<a name="line.94"></a>
<FONT color="green">095</FONT>       * <a name="line.95"></a>
<FONT color="green">096</FONT>       * @param job The {@link JobContext}<a name="line.96"></a>
<FONT color="green">097</FONT>       * @see #addInputPath(JobConf, Path, Class)<a name="line.97"></a>
<FONT color="green">098</FONT>       * @return A map of paths to inputformats for the job<a name="line.98"></a>
<FONT color="green">099</FONT>       */<a name="line.99"></a>
<FONT color="green">100</FONT>      @SuppressWarnings("unchecked")<a name="line.100"></a>
<FONT color="green">101</FONT>      static Map&lt;Path, InputFormat&gt; getInputFormatMap(JobContext job) {<a name="line.101"></a>
<FONT color="green">102</FONT>        Map&lt;Path, InputFormat&gt; m = new HashMap&lt;Path, InputFormat&gt;();<a name="line.102"></a>
<FONT color="green">103</FONT>        Configuration conf = job.getConfiguration();<a name="line.103"></a>
<FONT color="green">104</FONT>        String[] pathMappings = conf.get(DIR_FORMATS).split(",");<a name="line.104"></a>
<FONT color="green">105</FONT>        for (String pathMapping : pathMappings) {<a name="line.105"></a>
<FONT color="green">106</FONT>          String[] split = pathMapping.split(";");<a name="line.106"></a>
<FONT color="green">107</FONT>          InputFormat inputFormat;<a name="line.107"></a>
<FONT color="green">108</FONT>          try {<a name="line.108"></a>
<FONT color="green">109</FONT>           inputFormat = (InputFormat) ReflectionUtils.newInstance(conf<a name="line.109"></a>
<FONT color="green">110</FONT>               .getClassByName(split[1]), conf);<a name="line.110"></a>
<FONT color="green">111</FONT>          } catch (ClassNotFoundException e) {<a name="line.111"></a>
<FONT color="green">112</FONT>           throw new RuntimeException(e);<a name="line.112"></a>
<FONT color="green">113</FONT>          }<a name="line.113"></a>
<FONT color="green">114</FONT>          m.put(new Path(split[0]), inputFormat);<a name="line.114"></a>
<FONT color="green">115</FONT>        }<a name="line.115"></a>
<FONT color="green">116</FONT>        return m;<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>       * Retrieves a map of {@link Path}s to the {@link Mapper} class that<a name="line.120"></a>
<FONT color="green">121</FONT>       * should be used for them.<a name="line.121"></a>
<FONT color="green">122</FONT>       * <a name="line.122"></a>
<FONT color="green">123</FONT>       * @param job The {@link JobContext}<a name="line.123"></a>
<FONT color="green">124</FONT>       * @see #addInputPath(JobConf, Path, Class, Class)<a name="line.124"></a>
<FONT color="green">125</FONT>       * @return A map of paths to mappers for the job<a name="line.125"></a>
<FONT color="green">126</FONT>       */<a name="line.126"></a>
<FONT color="green">127</FONT>      @SuppressWarnings("unchecked")<a name="line.127"></a>
<FONT color="green">128</FONT>      static Map&lt;Path, Class&lt;? extends Mapper&gt;&gt; <a name="line.128"></a>
<FONT color="green">129</FONT>          getMapperTypeMap(JobContext job) {<a name="line.129"></a>
<FONT color="green">130</FONT>        Configuration conf = job.getConfiguration();<a name="line.130"></a>
<FONT color="green">131</FONT>        if (conf.get(DIR_MAPPERS) == null) {<a name="line.131"></a>
<FONT color="green">132</FONT>          return Collections.emptyMap();<a name="line.132"></a>
<FONT color="green">133</FONT>        }<a name="line.133"></a>
<FONT color="green">134</FONT>        Map&lt;Path, Class&lt;? extends Mapper&gt;&gt; m = <a name="line.134"></a>
<FONT color="green">135</FONT>          new HashMap&lt;Path, Class&lt;? extends Mapper&gt;&gt;();<a name="line.135"></a>
<FONT color="green">136</FONT>        String[] pathMappings = conf.get(DIR_MAPPERS).split(",");<a name="line.136"></a>
<FONT color="green">137</FONT>        for (String pathMapping : pathMappings) {<a name="line.137"></a>
<FONT color="green">138</FONT>          String[] split = pathMapping.split(";");<a name="line.138"></a>
<FONT color="green">139</FONT>          Class&lt;? extends Mapper&gt; mapClass;<a name="line.139"></a>
<FONT color="green">140</FONT>          try {<a name="line.140"></a>
<FONT color="green">141</FONT>           mapClass = <a name="line.141"></a>
<FONT color="green">142</FONT>             (Class&lt;? extends Mapper&gt;) conf.getClassByName(split[1]);<a name="line.142"></a>
<FONT color="green">143</FONT>          } catch (ClassNotFoundException e) {<a name="line.143"></a>
<FONT color="green">144</FONT>           throw new RuntimeException(e);<a name="line.144"></a>
<FONT color="green">145</FONT>          }<a name="line.145"></a>
<FONT color="green">146</FONT>          m.put(new Path(split[0]), mapClass);<a name="line.146"></a>
<FONT color="green">147</FONT>        }<a name="line.147"></a>
<FONT color="green">148</FONT>        return m;<a name="line.148"></a>
<FONT color="green">149</FONT>      }<a name="line.149"></a>
<FONT color="green">150</FONT>    }<a name="line.150"></a>




























































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