<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.input;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.DataInput;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.io.DataOutput;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.io.IOException;<a name="line.23"></a>
<FONT color="green">024</FONT>    <a name="line.24"></a>
<FONT color="green">025</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.25"></a>
<FONT color="green">026</FONT>    import org.apache.hadoop.classification.InterfaceStability;<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.io.Text;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.io.Writable;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.mapreduce.InputSplit;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.mapreduce.RecordReader;<a name="line.31"></a>
<FONT color="green">032</FONT>    <a name="line.32"></a>
<FONT color="green">033</FONT>    /**<a name="line.33"></a>
<FONT color="green">034</FONT>     * A sub-collection of input files. <a name="line.34"></a>
<FONT color="green">035</FONT>     * <a name="line.35"></a>
<FONT color="green">036</FONT>     * Unlike {@link FileSplit}, CombineFileSplit class does not represent <a name="line.36"></a>
<FONT color="green">037</FONT>     * a split of a file, but a split of input files into smaller sets. <a name="line.37"></a>
<FONT color="green">038</FONT>     * A split may contain blocks from different file but all <a name="line.38"></a>
<FONT color="green">039</FONT>     * the blocks in the same split are probably local to some rack &lt;br&gt; <a name="line.39"></a>
<FONT color="green">040</FONT>     * CombineFileSplit can be used to implement {@link RecordReader}'s, <a name="line.40"></a>
<FONT color="green">041</FONT>     * with reading one record per file.<a name="line.41"></a>
<FONT color="green">042</FONT>     * <a name="line.42"></a>
<FONT color="green">043</FONT>     * @see FileSplit<a name="line.43"></a>
<FONT color="green">044</FONT>     * @see CombineFileInputFormat <a name="line.44"></a>
<FONT color="green">045</FONT>     */<a name="line.45"></a>
<FONT color="green">046</FONT>    @InterfaceAudience.Public<a name="line.46"></a>
<FONT color="green">047</FONT>    @InterfaceStability.Stable<a name="line.47"></a>
<FONT color="green">048</FONT>    public class CombineFileSplit extends InputSplit implements Writable {<a name="line.48"></a>
<FONT color="green">049</FONT>    <a name="line.49"></a>
<FONT color="green">050</FONT>      private Path[] paths;<a name="line.50"></a>
<FONT color="green">051</FONT>      private long[] startoffset;<a name="line.51"></a>
<FONT color="green">052</FONT>      private long[] lengths;<a name="line.52"></a>
<FONT color="green">053</FONT>      private String[] locations;<a name="line.53"></a>
<FONT color="green">054</FONT>      private long totLength;<a name="line.54"></a>
<FONT color="green">055</FONT>    <a name="line.55"></a>
<FONT color="green">056</FONT>      /**<a name="line.56"></a>
<FONT color="green">057</FONT>       * default constructor<a name="line.57"></a>
<FONT color="green">058</FONT>       */<a name="line.58"></a>
<FONT color="green">059</FONT>      public CombineFileSplit() {}<a name="line.59"></a>
<FONT color="green">060</FONT>      public CombineFileSplit(Path[] files, long[] start, <a name="line.60"></a>
<FONT color="green">061</FONT>                              long[] lengths, String[] locations) {<a name="line.61"></a>
<FONT color="green">062</FONT>        initSplit(files, start, lengths, locations);<a name="line.62"></a>
<FONT color="green">063</FONT>      }<a name="line.63"></a>
<FONT color="green">064</FONT>    <a name="line.64"></a>
<FONT color="green">065</FONT>      public CombineFileSplit(Path[] files, long[] lengths) {<a name="line.65"></a>
<FONT color="green">066</FONT>        long[] startoffset = new long[files.length];<a name="line.66"></a>
<FONT color="green">067</FONT>        for (int i = 0; i &lt; startoffset.length; i++) {<a name="line.67"></a>
<FONT color="green">068</FONT>          startoffset[i] = 0;<a name="line.68"></a>
<FONT color="green">069</FONT>        }<a name="line.69"></a>
<FONT color="green">070</FONT>        String[] locations = new String[files.length];<a name="line.70"></a>
<FONT color="green">071</FONT>        for (int i = 0; i &lt; locations.length; i++) {<a name="line.71"></a>
<FONT color="green">072</FONT>          locations[i] = "";<a name="line.72"></a>
<FONT color="green">073</FONT>        }<a name="line.73"></a>
<FONT color="green">074</FONT>        initSplit(files, startoffset, lengths, locations);<a name="line.74"></a>
<FONT color="green">075</FONT>      }<a name="line.75"></a>
<FONT color="green">076</FONT>      <a name="line.76"></a>
<FONT color="green">077</FONT>      private void initSplit(Path[] files, long[] start, <a name="line.77"></a>
<FONT color="green">078</FONT>                             long[] lengths, String[] locations) {<a name="line.78"></a>
<FONT color="green">079</FONT>        this.startoffset = start;<a name="line.79"></a>
<FONT color="green">080</FONT>        this.lengths = lengths;<a name="line.80"></a>
<FONT color="green">081</FONT>        this.paths = files;<a name="line.81"></a>
<FONT color="green">082</FONT>        this.totLength = 0;<a name="line.82"></a>
<FONT color="green">083</FONT>        this.locations = locations;<a name="line.83"></a>
<FONT color="green">084</FONT>        for(long length : lengths) {<a name="line.84"></a>
<FONT color="green">085</FONT>          totLength += length;<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>      /**<a name="line.89"></a>
<FONT color="green">090</FONT>       * Copy constructor<a name="line.90"></a>
<FONT color="green">091</FONT>       */<a name="line.91"></a>
<FONT color="green">092</FONT>      public CombineFileSplit(CombineFileSplit old) throws IOException {<a name="line.92"></a>
<FONT color="green">093</FONT>        this(old.getPaths(), old.getStartOffsets(),<a name="line.93"></a>
<FONT color="green">094</FONT>             old.getLengths(), old.getLocations());<a name="line.94"></a>
<FONT color="green">095</FONT>      }<a name="line.95"></a>
<FONT color="green">096</FONT>    <a name="line.96"></a>
<FONT color="green">097</FONT>      public long getLength() {<a name="line.97"></a>
<FONT color="green">098</FONT>        return totLength;<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>      /** Returns an array containing the start offsets of the files in the split*/ <a name="line.101"></a>
<FONT color="green">102</FONT>      public long[] getStartOffsets() {<a name="line.102"></a>
<FONT color="green">103</FONT>        return startoffset;<a name="line.103"></a>
<FONT color="green">104</FONT>      }<a name="line.104"></a>
<FONT color="green">105</FONT>      <a name="line.105"></a>
<FONT color="green">106</FONT>      /** Returns an array containing the lengths of the files in the split*/ <a name="line.106"></a>
<FONT color="green">107</FONT>      public long[] getLengths() {<a name="line.107"></a>
<FONT color="green">108</FONT>        return lengths;<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>      /** Returns the start offset of the i&lt;sup&gt;th&lt;/sup&gt; Path */<a name="line.111"></a>
<FONT color="green">112</FONT>      public long getOffset(int i) {<a name="line.112"></a>
<FONT color="green">113</FONT>        return startoffset[i];<a name="line.113"></a>
<FONT color="green">114</FONT>      }<a name="line.114"></a>
<FONT color="green">115</FONT>      <a name="line.115"></a>
<FONT color="green">116</FONT>      /** Returns the length of the i&lt;sup&gt;th&lt;/sup&gt; Path */<a name="line.116"></a>
<FONT color="green">117</FONT>      public long getLength(int i) {<a name="line.117"></a>
<FONT color="green">118</FONT>        return lengths[i];<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>      /** Returns the number of Paths in the split */<a name="line.121"></a>
<FONT color="green">122</FONT>      public int getNumPaths() {<a name="line.122"></a>
<FONT color="green">123</FONT>        return paths.length;<a name="line.123"></a>
<FONT color="green">124</FONT>      }<a name="line.124"></a>
<FONT color="green">125</FONT>    <a name="line.125"></a>
<FONT color="green">126</FONT>      /** Returns the i&lt;sup&gt;th&lt;/sup&gt; Path */<a name="line.126"></a>
<FONT color="green">127</FONT>      public Path getPath(int i) {<a name="line.127"></a>
<FONT color="green">128</FONT>        return paths[i];<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>      /** Returns all the Paths in the split */<a name="line.131"></a>
<FONT color="green">132</FONT>      public Path[] getPaths() {<a name="line.132"></a>
<FONT color="green">133</FONT>        return paths;<a name="line.133"></a>
<FONT color="green">134</FONT>      }<a name="line.134"></a>
<FONT color="green">135</FONT>    <a name="line.135"></a>
<FONT color="green">136</FONT>      /** Returns all the Paths where this input-split resides */<a name="line.136"></a>
<FONT color="green">137</FONT>      public String[] getLocations() throws IOException {<a name="line.137"></a>
<FONT color="green">138</FONT>        return locations;<a name="line.138"></a>
<FONT color="green">139</FONT>      }<a name="line.139"></a>
<FONT color="green">140</FONT>    <a name="line.140"></a>
<FONT color="green">141</FONT>      public void readFields(DataInput in) throws IOException {<a name="line.141"></a>
<FONT color="green">142</FONT>        totLength = in.readLong();<a name="line.142"></a>
<FONT color="green">143</FONT>        int arrLength = in.readInt();<a name="line.143"></a>
<FONT color="green">144</FONT>        lengths = new long[arrLength];<a name="line.144"></a>
<FONT color="green">145</FONT>        for(int i=0; i&lt;arrLength;i++) {<a name="line.145"></a>
<FONT color="green">146</FONT>          lengths[i] = in.readLong();<a name="line.146"></a>
<FONT color="green">147</FONT>        }<a name="line.147"></a>
<FONT color="green">148</FONT>        int filesLength = in.readInt();<a name="line.148"></a>
<FONT color="green">149</FONT>        paths = new Path[filesLength];<a name="line.149"></a>
<FONT color="green">150</FONT>        for(int i=0; i&lt;filesLength;i++) {<a name="line.150"></a>
<FONT color="green">151</FONT>          paths[i] = new Path(Text.readString(in));<a name="line.151"></a>
<FONT color="green">152</FONT>        }<a name="line.152"></a>
<FONT color="green">153</FONT>        arrLength = in.readInt();<a name="line.153"></a>
<FONT color="green">154</FONT>        startoffset = new long[arrLength];<a name="line.154"></a>
<FONT color="green">155</FONT>        for(int i=0; i&lt;arrLength;i++) {<a name="line.155"></a>
<FONT color="green">156</FONT>          startoffset[i] = in.readLong();<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>    <a name="line.159"></a>
<FONT color="green">160</FONT>      public void write(DataOutput out) throws IOException {<a name="line.160"></a>
<FONT color="green">161</FONT>        out.writeLong(totLength);<a name="line.161"></a>
<FONT color="green">162</FONT>        out.writeInt(lengths.length);<a name="line.162"></a>
<FONT color="green">163</FONT>        for(long length : lengths) {<a name="line.163"></a>
<FONT color="green">164</FONT>          out.writeLong(length);<a name="line.164"></a>
<FONT color="green">165</FONT>        }<a name="line.165"></a>
<FONT color="green">166</FONT>        out.writeInt(paths.length);<a name="line.166"></a>
<FONT color="green">167</FONT>        for(Path p : paths) {<a name="line.167"></a>
<FONT color="green">168</FONT>          Text.writeString(out, p.toString());<a name="line.168"></a>
<FONT color="green">169</FONT>        }<a name="line.169"></a>
<FONT color="green">170</FONT>        out.writeInt(startoffset.length);<a name="line.170"></a>
<FONT color="green">171</FONT>        for(long length : startoffset) {<a name="line.171"></a>
<FONT color="green">172</FONT>          out.writeLong(length);<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>      <a name="line.175"></a>
<FONT color="green">176</FONT>      @Override<a name="line.176"></a>
<FONT color="green">177</FONT>     public String toString() {<a name="line.177"></a>
<FONT color="green">178</FONT>        StringBuffer sb = new StringBuffer();<a name="line.178"></a>
<FONT color="green">179</FONT>        for (int i = 0; i &lt; paths.length; i++) {<a name="line.179"></a>
<FONT color="green">180</FONT>          if (i == 0 ) {<a name="line.180"></a>
<FONT color="green">181</FONT>            sb.append("Paths:");<a name="line.181"></a>
<FONT color="green">182</FONT>          }<a name="line.182"></a>
<FONT color="green">183</FONT>          sb.append(paths[i].toUri().getPath() + ":" + startoffset[i] +<a name="line.183"></a>
<FONT color="green">184</FONT>                    "+" + lengths[i]);<a name="line.184"></a>
<FONT color="green">185</FONT>          if (i &lt; paths.length -1) {<a name="line.185"></a>
<FONT color="green">186</FONT>            sb.append(",");<a name="line.186"></a>
<FONT color="green">187</FONT>          }<a name="line.187"></a>
<FONT color="green">188</FONT>        }<a name="line.188"></a>
<FONT color="green">189</FONT>        if (locations != null) {<a name="line.189"></a>
<FONT color="green">190</FONT>          String locs = "";<a name="line.190"></a>
<FONT color="green">191</FONT>          StringBuffer locsb = new StringBuffer();<a name="line.191"></a>
<FONT color="green">192</FONT>          for (int i = 0; i &lt; locations.length; i++) {<a name="line.192"></a>
<FONT color="green">193</FONT>            locsb.append(locations[i] + ":");<a name="line.193"></a>
<FONT color="green">194</FONT>          }<a name="line.194"></a>
<FONT color="green">195</FONT>          locs = locsb.toString();<a name="line.195"></a>
<FONT color="green">196</FONT>          sb.append(" Locations:" + locs + "; ");<a name="line.196"></a>
<FONT color="green">197</FONT>        }<a name="line.197"></a>
<FONT color="green">198</FONT>        return sb.toString();<a name="line.198"></a>
<FONT color="green">199</FONT>      }<a name="line.199"></a>
<FONT color="green">200</FONT>    }<a name="line.200"></a>




























































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