<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.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.conf.Configurable;<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.io.WritableComparator;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.io.WritableUtils;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.io.Text;<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.lib.partition.KeyFieldHelper.KeyDescription;<a name="line.33"></a>
<FONT color="green">034</FONT>    <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>     * This comparator implementation provides a subset of the features provided<a name="line.37"></a>
<FONT color="green">038</FONT>     * by the Unix/GNU Sort. In particular, the supported features are:<a name="line.38"></a>
<FONT color="green">039</FONT>     * -n, (Sort numerically)<a name="line.39"></a>
<FONT color="green">040</FONT>     * -r, (Reverse the result of comparison)<a name="line.40"></a>
<FONT color="green">041</FONT>     * -k pos1[,pos2], where pos is of the form f[.c][opts], where f is the number<a name="line.41"></a>
<FONT color="green">042</FONT>     *  of the field to use, and c is the number of the first character from the<a name="line.42"></a>
<FONT color="green">043</FONT>     *  beginning of the field. Fields and character posns are numbered starting<a name="line.43"></a>
<FONT color="green">044</FONT>     *  with 1; a character position of zero in pos2 indicates the field's last<a name="line.44"></a>
<FONT color="green">045</FONT>     *  character. If '.c' is omitted from pos1, it defaults to 1 (the beginning<a name="line.45"></a>
<FONT color="green">046</FONT>     *  of the field); if omitted from pos2, it defaults to 0 (the end of the<a name="line.46"></a>
<FONT color="green">047</FONT>     *  field). opts are ordering options (any of 'nr' as described above). <a name="line.47"></a>
<FONT color="green">048</FONT>     * We assume that the fields in the key are separated by <a name="line.48"></a>
<FONT color="green">049</FONT>     * {@link JobContext#MAP_OUTPUT_KEY_FIELD_SEPERATOR}.<a name="line.49"></a>
<FONT color="green">050</FONT>     */<a name="line.50"></a>
<FONT color="green">051</FONT>    @InterfaceAudience.Public<a name="line.51"></a>
<FONT color="green">052</FONT>    @InterfaceStability.Stable<a name="line.52"></a>
<FONT color="green">053</FONT>    public class KeyFieldBasedComparator&lt;K, V&gt; extends WritableComparator <a name="line.53"></a>
<FONT color="green">054</FONT>        implements Configurable {<a name="line.54"></a>
<FONT color="green">055</FONT>      private KeyFieldHelper keyFieldHelper = new KeyFieldHelper();<a name="line.55"></a>
<FONT color="green">056</FONT>      public static String COMPARATOR_OPTIONS = "mapreduce.partition.keycomparator.options";<a name="line.56"></a>
<FONT color="green">057</FONT>      private static final byte NEGATIVE = (byte)'-';<a name="line.57"></a>
<FONT color="green">058</FONT>      private static final byte ZERO = (byte)'0';<a name="line.58"></a>
<FONT color="green">059</FONT>      private static final byte DECIMAL = (byte)'.';<a name="line.59"></a>
<FONT color="green">060</FONT>      private Configuration conf;<a name="line.60"></a>
<FONT color="green">061</FONT>    <a name="line.61"></a>
<FONT color="green">062</FONT>      public void setConf(Configuration conf) {<a name="line.62"></a>
<FONT color="green">063</FONT>        this.conf = conf;<a name="line.63"></a>
<FONT color="green">064</FONT>        String option = conf.get(COMPARATOR_OPTIONS);<a name="line.64"></a>
<FONT color="green">065</FONT>        String keyFieldSeparator = conf.get(MRJobConfig.MAP_OUTPUT_KEY_FIELD_SEPERATOR,"\t");<a name="line.65"></a>
<FONT color="green">066</FONT>        keyFieldHelper.setKeyFieldSeparator(keyFieldSeparator);<a name="line.66"></a>
<FONT color="green">067</FONT>        keyFieldHelper.parseOption(option);<a name="line.67"></a>
<FONT color="green">068</FONT>      }<a name="line.68"></a>
<FONT color="green">069</FONT>    <a name="line.69"></a>
<FONT color="green">070</FONT>      public Configuration getConf() {<a name="line.70"></a>
<FONT color="green">071</FONT>        return conf;<a name="line.71"></a>
<FONT color="green">072</FONT>      }<a name="line.72"></a>
<FONT color="green">073</FONT>      <a name="line.73"></a>
<FONT color="green">074</FONT>      public KeyFieldBasedComparator() {<a name="line.74"></a>
<FONT color="green">075</FONT>        super(Text.class);<a name="line.75"></a>
<FONT color="green">076</FONT>      }<a name="line.76"></a>
<FONT color="green">077</FONT>        <a name="line.77"></a>
<FONT color="green">078</FONT>      public int compare(byte[] b1, int s1, int l1,<a name="line.78"></a>
<FONT color="green">079</FONT>          byte[] b2, int s2, int l2) {<a name="line.79"></a>
<FONT color="green">080</FONT>        int n1 = WritableUtils.decodeVIntSize(b1[s1]);<a name="line.80"></a>
<FONT color="green">081</FONT>        int n2 = WritableUtils.decodeVIntSize(b2[s2]);<a name="line.81"></a>
<FONT color="green">082</FONT>        List &lt;KeyDescription&gt; allKeySpecs = keyFieldHelper.keySpecs();<a name="line.82"></a>
<FONT color="green">083</FONT>    <a name="line.83"></a>
<FONT color="green">084</FONT>        if (allKeySpecs.size() == 0) {<a name="line.84"></a>
<FONT color="green">085</FONT>          return compareBytes(b1, s1 + n1, l1 - n1, b2, s2 + n2, l2 - n2);<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>        int []lengthIndicesFirst = <a name="line.88"></a>
<FONT color="green">089</FONT>          keyFieldHelper.getWordLengths(b1, s1 + n1, s1 + l1);<a name="line.89"></a>
<FONT color="green">090</FONT>        int []lengthIndicesSecond = <a name="line.90"></a>
<FONT color="green">091</FONT>          keyFieldHelper.getWordLengths(b2, s2 + n2, s2 + l2);<a name="line.91"></a>
<FONT color="green">092</FONT>        <a name="line.92"></a>
<FONT color="green">093</FONT>        for (KeyDescription keySpec : allKeySpecs) {<a name="line.93"></a>
<FONT color="green">094</FONT>          int startCharFirst = keyFieldHelper.getStartOffset(b1, s1 + n1, s1 + l1,<a name="line.94"></a>
<FONT color="green">095</FONT>            lengthIndicesFirst, keySpec);<a name="line.95"></a>
<FONT color="green">096</FONT>          int endCharFirst = keyFieldHelper.getEndOffset(b1, s1 + n1, s1 + l1, <a name="line.96"></a>
<FONT color="green">097</FONT>            lengthIndicesFirst, keySpec);<a name="line.97"></a>
<FONT color="green">098</FONT>          int startCharSecond = keyFieldHelper.getStartOffset(b2, s2 + n2, s2 + l2,<a name="line.98"></a>
<FONT color="green">099</FONT>            lengthIndicesSecond, keySpec);<a name="line.99"></a>
<FONT color="green">100</FONT>          int endCharSecond = keyFieldHelper.getEndOffset(b2, s2 + n2, s2 + l2, <a name="line.100"></a>
<FONT color="green">101</FONT>            lengthIndicesSecond, keySpec);<a name="line.101"></a>
<FONT color="green">102</FONT>          int result;<a name="line.102"></a>
<FONT color="green">103</FONT>          if ((result = compareByteSequence(b1, startCharFirst, endCharFirst, b2, <a name="line.103"></a>
<FONT color="green">104</FONT>              startCharSecond, endCharSecond, keySpec)) != 0) {<a name="line.104"></a>
<FONT color="green">105</FONT>            return result;<a name="line.105"></a>
<FONT color="green">106</FONT>          }<a name="line.106"></a>
<FONT color="green">107</FONT>        }<a name="line.107"></a>
<FONT color="green">108</FONT>        return 0;<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>      private int compareByteSequence(byte[] first, int start1, int end1, <a name="line.111"></a>
<FONT color="green">112</FONT>          byte[] second, int start2, int end2, KeyDescription key) {<a name="line.112"></a>
<FONT color="green">113</FONT>        if (start1 == -1) {<a name="line.113"></a>
<FONT color="green">114</FONT>          if (key.reverse) {<a name="line.114"></a>
<FONT color="green">115</FONT>            return 1;<a name="line.115"></a>
<FONT color="green">116</FONT>          }<a name="line.116"></a>
<FONT color="green">117</FONT>          return -1;<a name="line.117"></a>
<FONT color="green">118</FONT>        }<a name="line.118"></a>
<FONT color="green">119</FONT>        if (start2 == -1) {<a name="line.119"></a>
<FONT color="green">120</FONT>          if (key.reverse) {<a name="line.120"></a>
<FONT color="green">121</FONT>            return -1; <a name="line.121"></a>
<FONT color="green">122</FONT>          }<a name="line.122"></a>
<FONT color="green">123</FONT>          return 1;<a name="line.123"></a>
<FONT color="green">124</FONT>        }<a name="line.124"></a>
<FONT color="green">125</FONT>        int compareResult = 0;<a name="line.125"></a>
<FONT color="green">126</FONT>        if (!key.numeric) {<a name="line.126"></a>
<FONT color="green">127</FONT>          compareResult = compareBytes(first, start1, end1-start1 + 1, second,<a name="line.127"></a>
<FONT color="green">128</FONT>            start2, end2 - start2 + 1);<a name="line.128"></a>
<FONT color="green">129</FONT>        }<a name="line.129"></a>
<FONT color="green">130</FONT>        if (key.numeric) {<a name="line.130"></a>
<FONT color="green">131</FONT>          compareResult = numericalCompare (first, start1, end1, second, start2,<a name="line.131"></a>
<FONT color="green">132</FONT>            end2);<a name="line.132"></a>
<FONT color="green">133</FONT>        }<a name="line.133"></a>
<FONT color="green">134</FONT>        if (key.reverse) {<a name="line.134"></a>
<FONT color="green">135</FONT>          return -compareResult;<a name="line.135"></a>
<FONT color="green">136</FONT>        }<a name="line.136"></a>
<FONT color="green">137</FONT>        return compareResult;<a name="line.137"></a>
<FONT color="green">138</FONT>      }<a name="line.138"></a>
<FONT color="green">139</FONT>      <a name="line.139"></a>
<FONT color="green">140</FONT>      private int numericalCompare (byte[] a, int start1, int end1, <a name="line.140"></a>
<FONT color="green">141</FONT>          byte[] b, int start2, int end2) {<a name="line.141"></a>
<FONT color="green">142</FONT>        int i = start1;<a name="line.142"></a>
<FONT color="green">143</FONT>        int j = start2;<a name="line.143"></a>
<FONT color="green">144</FONT>        int mul = 1;<a name="line.144"></a>
<FONT color="green">145</FONT>        byte first_a = a[i];<a name="line.145"></a>
<FONT color="green">146</FONT>        byte first_b = b[j];<a name="line.146"></a>
<FONT color="green">147</FONT>        if (first_a == NEGATIVE) {<a name="line.147"></a>
<FONT color="green">148</FONT>          if (first_b != NEGATIVE) {<a name="line.148"></a>
<FONT color="green">149</FONT>            //check for cases like -0.0 and 0.0 (they should be declared equal)<a name="line.149"></a>
<FONT color="green">150</FONT>            return oneNegativeCompare(a, start1 + 1, end1, b, start2, end2);<a name="line.150"></a>
<FONT color="green">151</FONT>          }<a name="line.151"></a>
<FONT color="green">152</FONT>          i++;<a name="line.152"></a>
<FONT color="green">153</FONT>        }<a name="line.153"></a>
<FONT color="green">154</FONT>        if (first_b == NEGATIVE) {<a name="line.154"></a>
<FONT color="green">155</FONT>          if (first_a != NEGATIVE) {<a name="line.155"></a>
<FONT color="green">156</FONT>            //check for cases like 0.0 and -0.0 (they should be declared equal)<a name="line.156"></a>
<FONT color="green">157</FONT>            return -oneNegativeCompare(b, start2+1, end2, a, start1, end1);<a name="line.157"></a>
<FONT color="green">158</FONT>          }<a name="line.158"></a>
<FONT color="green">159</FONT>          j++;<a name="line.159"></a>
<FONT color="green">160</FONT>        }<a name="line.160"></a>
<FONT color="green">161</FONT>        if (first_b == NEGATIVE &amp;&amp; first_a == NEGATIVE) {<a name="line.161"></a>
<FONT color="green">162</FONT>          mul = -1;<a name="line.162"></a>
<FONT color="green">163</FONT>        }<a name="line.163"></a>
<FONT color="green">164</FONT>    <a name="line.164"></a>
<FONT color="green">165</FONT>        //skip over ZEROs<a name="line.165"></a>
<FONT color="green">166</FONT>        while (i &lt;= end1) {<a name="line.166"></a>
<FONT color="green">167</FONT>          if (a[i] != ZERO) {<a name="line.167"></a>
<FONT color="green">168</FONT>            break;<a name="line.168"></a>
<FONT color="green">169</FONT>          }<a name="line.169"></a>
<FONT color="green">170</FONT>          i++;<a name="line.170"></a>
<FONT color="green">171</FONT>        }<a name="line.171"></a>
<FONT color="green">172</FONT>        while (j &lt;= end2) {<a name="line.172"></a>
<FONT color="green">173</FONT>          if (b[j] != ZERO) {<a name="line.173"></a>
<FONT color="green">174</FONT>            break;<a name="line.174"></a>
<FONT color="green">175</FONT>          }<a name="line.175"></a>
<FONT color="green">176</FONT>          j++;<a name="line.176"></a>
<FONT color="green">177</FONT>        }<a name="line.177"></a>
<FONT color="green">178</FONT>        <a name="line.178"></a>
<FONT color="green">179</FONT>        //skip over equal characters and stopping at the first nondigit char<a name="line.179"></a>
<FONT color="green">180</FONT>        //The nondigit character could be '.'<a name="line.180"></a>
<FONT color="green">181</FONT>        while (i &lt;= end1 &amp;&amp; j &lt;= end2) {<a name="line.181"></a>
<FONT color="green">182</FONT>          if (!isdigit(a[i]) || a[i] != b[j]) {<a name="line.182"></a>
<FONT color="green">183</FONT>            break;<a name="line.183"></a>
<FONT color="green">184</FONT>          }<a name="line.184"></a>
<FONT color="green">185</FONT>          i++; j++;<a name="line.185"></a>
<FONT color="green">186</FONT>        }<a name="line.186"></a>
<FONT color="green">187</FONT>        if (i &lt;= end1) {<a name="line.187"></a>
<FONT color="green">188</FONT>          first_a = a[i];<a name="line.188"></a>
<FONT color="green">189</FONT>        }<a name="line.189"></a>
<FONT color="green">190</FONT>        if (j &lt;= end2) {<a name="line.190"></a>
<FONT color="green">191</FONT>          first_b = b[j];<a name="line.191"></a>
<FONT color="green">192</FONT>        }<a name="line.192"></a>
<FONT color="green">193</FONT>        //store the result of the difference. This could be final result if the<a name="line.193"></a>
<FONT color="green">194</FONT>        //number of digits in the mantissa is the same in both the numbers <a name="line.194"></a>
<FONT color="green">195</FONT>        int firstResult = first_a - first_b;<a name="line.195"></a>
<FONT color="green">196</FONT>        <a name="line.196"></a>
<FONT color="green">197</FONT>        //check whether we hit a decimal in the earlier scan<a name="line.197"></a>
<FONT color="green">198</FONT>        if ((first_a == DECIMAL &amp;&amp; (!isdigit(first_b) || j &gt; end2)) ||<a name="line.198"></a>
<FONT color="green">199</FONT>                (first_b == DECIMAL &amp;&amp; (!isdigit(first_a) || i &gt; end1))) {<a name="line.199"></a>
<FONT color="green">200</FONT>          return ((mul &lt; 0) ? -decimalCompare(a, i, end1, b, j, end2) : <a name="line.200"></a>
<FONT color="green">201</FONT>            decimalCompare(a, i, end1, b, j, end2));<a name="line.201"></a>
<FONT color="green">202</FONT>        }<a name="line.202"></a>
<FONT color="green">203</FONT>        //check the number of digits in the mantissa of the numbers<a name="line.203"></a>
<FONT color="green">204</FONT>        int numRemainDigits_a = 0;<a name="line.204"></a>
<FONT color="green">205</FONT>        int numRemainDigits_b = 0;<a name="line.205"></a>
<FONT color="green">206</FONT>        while (i &lt;= end1) {<a name="line.206"></a>
<FONT color="green">207</FONT>          //if we encounter a non-digit treat the corresponding number as being <a name="line.207"></a>
<FONT color="green">208</FONT>          //smaller      <a name="line.208"></a>
<FONT color="green">209</FONT>          if (isdigit(a[i++])) {<a name="line.209"></a>
<FONT color="green">210</FONT>            numRemainDigits_a++;<a name="line.210"></a>
<FONT color="green">211</FONT>          } else break;<a name="line.211"></a>
<FONT color="green">212</FONT>        }<a name="line.212"></a>
<FONT color="green">213</FONT>        while (j &lt;= end2) {<a name="line.213"></a>
<FONT color="green">214</FONT>          //if we encounter a non-digit treat the corresponding number as being <a name="line.214"></a>
<FONT color="green">215</FONT>          //smaller<a name="line.215"></a>
<FONT color="green">216</FONT>          if (isdigit(b[j++])) {<a name="line.216"></a>
<FONT color="green">217</FONT>            numRemainDigits_b++;<a name="line.217"></a>
<FONT color="green">218</FONT>          } else break;<a name="line.218"></a>
<FONT color="green">219</FONT>        }<a name="line.219"></a>
<FONT color="green">220</FONT>        int ret = numRemainDigits_a - numRemainDigits_b;<a name="line.220"></a>
<FONT color="green">221</FONT>        if (ret == 0) { <a name="line.221"></a>
<FONT color="green">222</FONT>          return ((mul &lt; 0) ? -firstResult : firstResult);<a name="line.222"></a>
<FONT color="green">223</FONT>        } else {<a name="line.223"></a>
<FONT color="green">224</FONT>          return ((mul &lt; 0) ? -ret : ret);<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>      private boolean isdigit(byte b) {<a name="line.227"></a>
<FONT color="green">228</FONT>        if ('0' &lt;= b &amp;&amp; b &lt;= '9') {<a name="line.228"></a>
<FONT color="green">229</FONT>          return true;<a name="line.229"></a>
<FONT color="green">230</FONT>        }<a name="line.230"></a>
<FONT color="green">231</FONT>        return false;<a name="line.231"></a>
<FONT color="green">232</FONT>      }<a name="line.232"></a>
<FONT color="green">233</FONT>      private int decimalCompare(byte[] a, int i, int end1, <a name="line.233"></a>
<FONT color="green">234</FONT>                                 byte[] b, int j, int end2) {<a name="line.234"></a>
<FONT color="green">235</FONT>        if (i &gt; end1) {<a name="line.235"></a>
<FONT color="green">236</FONT>          //if a[] has nothing remaining<a name="line.236"></a>
<FONT color="green">237</FONT>          return -decimalCompare1(b, ++j, end2);<a name="line.237"></a>
<FONT color="green">238</FONT>        }<a name="line.238"></a>
<FONT color="green">239</FONT>        if (j &gt; end2) {<a name="line.239"></a>
<FONT color="green">240</FONT>          //if b[] has nothing remaining<a name="line.240"></a>
<FONT color="green">241</FONT>          return decimalCompare1(a, ++i, end1);<a name="line.241"></a>
<FONT color="green">242</FONT>        }<a name="line.242"></a>
<FONT color="green">243</FONT>        if (a[i] == DECIMAL &amp;&amp; b[j] == DECIMAL) {<a name="line.243"></a>
<FONT color="green">244</FONT>          while (i &lt;= end1 &amp;&amp; j &lt;= end2) {<a name="line.244"></a>
<FONT color="green">245</FONT>            if (a[i] != b[j]) {<a name="line.245"></a>
<FONT color="green">246</FONT>              if (isdigit(a[i]) &amp;&amp; isdigit(b[j])) {<a name="line.246"></a>
<FONT color="green">247</FONT>                return a[i] - b[j];<a name="line.247"></a>
<FONT color="green">248</FONT>              }<a name="line.248"></a>
<FONT color="green">249</FONT>              if (isdigit(a[i])) {<a name="line.249"></a>
<FONT color="green">250</FONT>                return 1;<a name="line.250"></a>
<FONT color="green">251</FONT>              }<a name="line.251"></a>
<FONT color="green">252</FONT>              if (isdigit(b[j])) {<a name="line.252"></a>
<FONT color="green">253</FONT>                return -1;<a name="line.253"></a>
<FONT color="green">254</FONT>              }<a name="line.254"></a>
<FONT color="green">255</FONT>              return 0;<a name="line.255"></a>
<FONT color="green">256</FONT>            }<a name="line.256"></a>
<FONT color="green">257</FONT>            i++; j++;<a name="line.257"></a>
<FONT color="green">258</FONT>          }<a name="line.258"></a>
<FONT color="green">259</FONT>          if (i &gt; end1 &amp;&amp; j &gt; end2) {<a name="line.259"></a>
<FONT color="green">260</FONT>            return 0;<a name="line.260"></a>
<FONT color="green">261</FONT>          }<a name="line.261"></a>
<FONT color="green">262</FONT>            <a name="line.262"></a>
<FONT color="green">263</FONT>          if (i &gt; end1) {<a name="line.263"></a>
<FONT color="green">264</FONT>            //check whether there is a non-ZERO digit after potentially<a name="line.264"></a>
<FONT color="green">265</FONT>            //a number of ZEROs (e.g., a=.4444, b=.444400004)<a name="line.265"></a>
<FONT color="green">266</FONT>            return -decimalCompare1(b, j, end2);<a name="line.266"></a>
<FONT color="green">267</FONT>          }<a name="line.267"></a>
<FONT color="green">268</FONT>          if (j &gt; end2) {<a name="line.268"></a>
<FONT color="green">269</FONT>            //check whether there is a non-ZERO digit after potentially<a name="line.269"></a>
<FONT color="green">270</FONT>            //a number of ZEROs (e.g., b=.4444, a=.444400004)<a name="line.270"></a>
<FONT color="green">271</FONT>            return decimalCompare1(a, i, end1);<a name="line.271"></a>
<FONT color="green">272</FONT>          }<a name="line.272"></a>
<FONT color="green">273</FONT>        }<a name="line.273"></a>
<FONT color="green">274</FONT>        else if (a[i] == DECIMAL) {<a name="line.274"></a>
<FONT color="green">275</FONT>          return decimalCompare1(a, ++i, end1);<a name="line.275"></a>
<FONT color="green">276</FONT>        }<a name="line.276"></a>
<FONT color="green">277</FONT>        else if (b[j] == DECIMAL) {<a name="line.277"></a>
<FONT color="green">278</FONT>          return -decimalCompare1(b, ++j, end2);<a name="line.278"></a>
<FONT color="green">279</FONT>        }<a name="line.279"></a>
<FONT color="green">280</FONT>        return 0;<a name="line.280"></a>
<FONT color="green">281</FONT>      }<a name="line.281"></a>
<FONT color="green">282</FONT>      <a name="line.282"></a>
<FONT color="green">283</FONT>      private int decimalCompare1(byte[] a, int i, int end) {<a name="line.283"></a>
<FONT color="green">284</FONT>        while (i &lt;= end) {<a name="line.284"></a>
<FONT color="green">285</FONT>          if (a[i] == ZERO) {<a name="line.285"></a>
<FONT color="green">286</FONT>            i++;<a name="line.286"></a>
<FONT color="green">287</FONT>            continue;<a name="line.287"></a>
<FONT color="green">288</FONT>          }<a name="line.288"></a>
<FONT color="green">289</FONT>          if (isdigit(a[i])) {<a name="line.289"></a>
<FONT color="green">290</FONT>            return 1;<a name="line.290"></a>
<FONT color="green">291</FONT>          } else {<a name="line.291"></a>
<FONT color="green">292</FONT>            return 0;<a name="line.292"></a>
<FONT color="green">293</FONT>          }<a name="line.293"></a>
<FONT color="green">294</FONT>        }<a name="line.294"></a>
<FONT color="green">295</FONT>        return 0;<a name="line.295"></a>
<FONT color="green">296</FONT>      }<a name="line.296"></a>
<FONT color="green">297</FONT>      <a name="line.297"></a>
<FONT color="green">298</FONT>      private int oneNegativeCompare(byte[] a, int start1, int end1, <a name="line.298"></a>
<FONT color="green">299</FONT>          byte[] b, int start2, int end2) {<a name="line.299"></a>
<FONT color="green">300</FONT>        //here a[] is negative and b[] is positive<a name="line.300"></a>
<FONT color="green">301</FONT>        //We have to ascertain whether the number contains any digits.<a name="line.301"></a>
<FONT color="green">302</FONT>        //If it does, then it is a smaller number for sure. If not,<a name="line.302"></a>
<FONT color="green">303</FONT>        //then we need to scan b[] to find out whether b[] has a digit<a name="line.303"></a>
<FONT color="green">304</FONT>        //If b[] does contain a digit, then b[] is certainly<a name="line.304"></a>
<FONT color="green">305</FONT>        //greater. If not, that is, both a[] and b[] don't contain<a name="line.305"></a>
<FONT color="green">306</FONT>        //digits then they should be considered equal.<a name="line.306"></a>
<FONT color="green">307</FONT>        if (!isZero(a, start1, end1)) {<a name="line.307"></a>
<FONT color="green">308</FONT>          return -1;<a name="line.308"></a>
<FONT color="green">309</FONT>        }<a name="line.309"></a>
<FONT color="green">310</FONT>        //reached here - this means that a[] is a ZERO<a name="line.310"></a>
<FONT color="green">311</FONT>        if (!isZero(b, start2, end2)) {<a name="line.311"></a>
<FONT color="green">312</FONT>          return -1;<a name="line.312"></a>
<FONT color="green">313</FONT>        }<a name="line.313"></a>
<FONT color="green">314</FONT>        //reached here - both numbers are basically ZEROs and hence<a name="line.314"></a>
<FONT color="green">315</FONT>        //they should compare equal<a name="line.315"></a>
<FONT color="green">316</FONT>        return 0;<a name="line.316"></a>
<FONT color="green">317</FONT>      }<a name="line.317"></a>
<FONT color="green">318</FONT>      <a name="line.318"></a>
<FONT color="green">319</FONT>      private boolean isZero(byte a[], int start, int end) {<a name="line.319"></a>
<FONT color="green">320</FONT>        //check for zeros in the significand part as well as the decimal part<a name="line.320"></a>
<FONT color="green">321</FONT>        //note that we treat the non-digit characters as ZERO<a name="line.321"></a>
<FONT color="green">322</FONT>        int i = start;<a name="line.322"></a>
<FONT color="green">323</FONT>        //we check the significand for being a ZERO<a name="line.323"></a>
<FONT color="green">324</FONT>        while (i &lt;= end) {<a name="line.324"></a>
<FONT color="green">325</FONT>          if (a[i] != ZERO) {<a name="line.325"></a>
<FONT color="green">326</FONT>            if (a[i] != DECIMAL &amp;&amp; isdigit(a[i])) {<a name="line.326"></a>
<FONT color="green">327</FONT>              return false;<a name="line.327"></a>
<FONT color="green">328</FONT>            }<a name="line.328"></a>
<FONT color="green">329</FONT>            break;<a name="line.329"></a>
<FONT color="green">330</FONT>          }<a name="line.330"></a>
<FONT color="green">331</FONT>          i++;<a name="line.331"></a>
<FONT color="green">332</FONT>        }<a name="line.332"></a>
<FONT color="green">333</FONT>    <a name="line.333"></a>
<FONT color="green">334</FONT>        if (i != (end+1) &amp;&amp; a[i++] == DECIMAL) {<a name="line.334"></a>
<FONT color="green">335</FONT>          //we check the decimal part for being a ZERO<a name="line.335"></a>
<FONT color="green">336</FONT>          while (i &lt;= end) {<a name="line.336"></a>
<FONT color="green">337</FONT>            if (a[i] != ZERO) {<a name="line.337"></a>
<FONT color="green">338</FONT>              if (isdigit(a[i])) {<a name="line.338"></a>
<FONT color="green">339</FONT>                return false;<a name="line.339"></a>
<FONT color="green">340</FONT>              }<a name="line.340"></a>
<FONT color="green">341</FONT>              break;<a name="line.341"></a>
<FONT color="green">342</FONT>            }<a name="line.342"></a>
<FONT color="green">343</FONT>            i++;<a name="line.343"></a>
<FONT color="green">344</FONT>          }<a name="line.344"></a>
<FONT color="green">345</FONT>        }<a name="line.345"></a>
<FONT color="green">346</FONT>        return true;<a name="line.346"></a>
<FONT color="green">347</FONT>      }<a name="line.347"></a>
<FONT color="green">348</FONT>      /**<a name="line.348"></a>
<FONT color="green">349</FONT>       * Set the {@link KeyFieldBasedComparator} options used to compare keys.<a name="line.349"></a>
<FONT color="green">350</FONT>       * <a name="line.350"></a>
<FONT color="green">351</FONT>       * @param keySpec the key specification of the form -k pos1[,pos2], where,<a name="line.351"></a>
<FONT color="green">352</FONT>       *  pos is of the form f[.c][opts], where f is the number<a name="line.352"></a>
<FONT color="green">353</FONT>       *  of the key field to use, and c is the number of the first character from<a name="line.353"></a>
<FONT color="green">354</FONT>       *  the beginning of the field. Fields and character posns are numbered <a name="line.354"></a>
<FONT color="green">355</FONT>       *  starting with 1; a character position of zero in pos2 indicates the<a name="line.355"></a>
<FONT color="green">356</FONT>       *  field's last character. If '.c' is omitted from pos1, it defaults to 1<a name="line.356"></a>
<FONT color="green">357</FONT>       *  (the beginning of the field); if omitted from pos2, it defaults to 0 <a name="line.357"></a>
<FONT color="green">358</FONT>       *  (the end of the field). opts are ordering options. The supported options<a name="line.358"></a>
<FONT color="green">359</FONT>       *  are:<a name="line.359"></a>
<FONT color="green">360</FONT>       *    -n, (Sort numerically)<a name="line.360"></a>
<FONT color="green">361</FONT>       *    -r, (Reverse the result of comparison)                 <a name="line.361"></a>
<FONT color="green">362</FONT>       */<a name="line.362"></a>
<FONT color="green">363</FONT>      public static void setKeyFieldComparatorOptions(Job job, String keySpec) {<a name="line.363"></a>
<FONT color="green">364</FONT>        job.getConfiguration().set(COMPARATOR_OPTIONS, keySpec);<a name="line.364"></a>
<FONT color="green">365</FONT>      }<a name="line.365"></a>
<FONT color="green">366</FONT>      <a name="line.366"></a>
<FONT color="green">367</FONT>      /**<a name="line.367"></a>
<FONT color="green">368</FONT>       * Get the {@link KeyFieldBasedComparator} options<a name="line.368"></a>
<FONT color="green">369</FONT>       */<a name="line.369"></a>
<FONT color="green">370</FONT>      public static String getKeyFieldComparatorOption(JobContext job) {<a name="line.370"></a>
<FONT color="green">371</FONT>        return job.getConfiguration().get(COMPARATOR_OPTIONS);<a name="line.371"></a>
<FONT color="green">372</FONT>      }<a name="line.372"></a>
<FONT color="green">373</FONT>    <a name="line.373"></a>
<FONT color="green">374</FONT>    <a name="line.374"></a>
<FONT color="green">375</FONT>    }<a name="line.375"></a>




























































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