| <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 "License");<a name="line.6"></a> |
| <FONT color="green">007</FONT> * you may not use this file except in compliance with the License.<a name="line.7"></a> |
| <FONT color="green">008</FONT> * 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> * $Id: DTMStringPool.java 468653 2006-10-28 07:07:05Z minchau $<a name="line.19"></a> |
| <FONT color="green">020</FONT> */<a name="line.20"></a> |
| <FONT color="green">021</FONT> <a name="line.21"></a> |
| <FONT color="green">022</FONT> package org.apache.xml.dtm.ref;<a name="line.22"></a> |
| <FONT color="green">023</FONT> <a name="line.23"></a> |
| <FONT color="green">024</FONT> import java.util.Vector;<a name="line.24"></a> |
| <FONT color="green">025</FONT> <a name="line.25"></a> |
| <FONT color="green">026</FONT> import org.apache.xml.utils.IntVector;<a name="line.26"></a> |
| <FONT color="green">027</FONT> <a name="line.27"></a> |
| <FONT color="green">028</FONT> /** <p>DTMStringPool is an "interning" mechanism for strings. It will<a name="line.28"></a> |
| <FONT color="green">029</FONT> * create a stable 1:1 mapping between a set of string values and a set of<a name="line.29"></a> |
| <FONT color="green">030</FONT> * integer index values, so the integers can be used to reliably and<a name="line.30"></a> |
| <FONT color="green">031</FONT> * uniquely identify (and when necessary retrieve) the strings.</p><a name="line.31"></a> |
| <FONT color="green">032</FONT> *<a name="line.32"></a> |
| <FONT color="green">033</FONT> * <p>Design Priorities:<a name="line.33"></a> |
| <FONT color="green">034</FONT> * <ul><a name="line.34"></a> |
| <FONT color="green">035</FONT> * <li>String-to-index lookup speed is critical.</li><a name="line.35"></a> |
| <FONT color="green">036</FONT> * <li>Index-to-String lookup speed is slightly less so.</li><a name="line.36"></a> |
| <FONT color="green">037</FONT> * <li>Threadsafety is not guaranteed at this level.<a name="line.37"></a> |
| <FONT color="green">038</FONT> * Enforce that in the application if needed.</li><a name="line.38"></a> |
| <FONT color="green">039</FONT> * <li>Storage efficiency is an issue but not a huge one.<a name="line.39"></a> |
| <FONT color="green">040</FONT> * It is expected that string pools won't exceed about 2000 entries.</li><a name="line.40"></a> |
| <FONT color="green">041</FONT> * </ul><a name="line.41"></a> |
| <FONT color="green">042</FONT> * </p><a name="line.42"></a> |
| <FONT color="green">043</FONT> *<a name="line.43"></a> |
| <FONT color="green">044</FONT> * <p>Implementation detail: A standard Hashtable is relatively<a name="line.44"></a> |
| <FONT color="green">045</FONT> * inefficient when looking up primitive int values, especially when<a name="line.45"></a> |
| <FONT color="green">046</FONT> * we're already maintaining an int-to-string vector. So I'm<a name="line.46"></a> |
| <FONT color="green">047</FONT> * maintaining a simple hash chain within this class.</p><a name="line.47"></a> |
| <FONT color="green">048</FONT> *<a name="line.48"></a> |
| <FONT color="green">049</FONT> * <p>NOTE: There is nothing in the code that has a real dependency upon<a name="line.49"></a> |
| <FONT color="green">050</FONT> * String. It would work with any object type that implements reliable<a name="line.50"></a> |
| <FONT color="green">051</FONT> * .hashCode() and .equals() operations. The API enforces Strings because<a name="line.51"></a> |
| <FONT color="green">052</FONT> * it's safer that way, but this could trivially be turned into a general<a name="line.52"></a> |
| <FONT color="green">053</FONT> * ObjectPool if one was needed.</p><a name="line.53"></a> |
| <FONT color="green">054</FONT> *<a name="line.54"></a> |
| <FONT color="green">055</FONT> * <p>Status: Passed basic test in main().</p><a name="line.55"></a> |
| <FONT color="green">056</FONT> * */<a name="line.56"></a> |
| <FONT color="green">057</FONT> public class DTMStringPool<a name="line.57"></a> |
| <FONT color="green">058</FONT> {<a name="line.58"></a> |
| <FONT color="green">059</FONT> Vector m_intToString;<a name="line.59"></a> |
| <FONT color="green">060</FONT> static final int HASHPRIME=101;<a name="line.60"></a> |
| <FONT color="green">061</FONT> int[] m_hashStart=new int[HASHPRIME];<a name="line.61"></a> |
| <FONT color="green">062</FONT> IntVector m_hashChain;<a name="line.62"></a> |
| <FONT color="green">063</FONT> public static final int NULL=-1;<a name="line.63"></a> |
| <FONT color="green">064</FONT> <a name="line.64"></a> |
| <FONT color="green">065</FONT> /**<a name="line.65"></a> |
| <FONT color="green">066</FONT> * Create a DTMStringPool using the given chain size<a name="line.66"></a> |
| <FONT color="green">067</FONT> * <a name="line.67"></a> |
| <FONT color="green">068</FONT> * @param chainSize The size of the hash chain vector<a name="line.68"></a> |
| <FONT color="green">069</FONT> */<a name="line.69"></a> |
| <FONT color="green">070</FONT> public DTMStringPool(int chainSize)<a name="line.70"></a> |
| <FONT color="green">071</FONT> {<a name="line.71"></a> |
| <FONT color="green">072</FONT> m_intToString=new Vector();<a name="line.72"></a> |
| <FONT color="green">073</FONT> m_hashChain=new IntVector(chainSize);<a name="line.73"></a> |
| <FONT color="green">074</FONT> removeAllElements();<a name="line.74"></a> |
| <FONT color="green">075</FONT> <a name="line.75"></a> |
| <FONT color="green">076</FONT> // -sb Add this to force empty strings to be index 0.<a name="line.76"></a> |
| <FONT color="green">077</FONT> stringToIndex("");<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 DTMStringPool()<a name="line.80"></a> |
| <FONT color="green">081</FONT> {<a name="line.81"></a> |
| <FONT color="green">082</FONT> this(512); <a name="line.82"></a> |
| <FONT color="green">083</FONT> }<a name="line.83"></a> |
| <FONT color="green">084</FONT> <a name="line.84"></a> |
| <FONT color="green">085</FONT> public void removeAllElements()<a name="line.85"></a> |
| <FONT color="green">086</FONT> {<a name="line.86"></a> |
| <FONT color="green">087</FONT> m_intToString.removeAllElements();<a name="line.87"></a> |
| <FONT color="green">088</FONT> for(int i=0;i<HASHPRIME;++i)<a name="line.88"></a> |
| <FONT color="green">089</FONT> m_hashStart[i]=NULL;<a name="line.89"></a> |
| <FONT color="green">090</FONT> m_hashChain.removeAllElements();<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> /** @return string whose value is uniquely identified by this integer index.<a name="line.93"></a> |
| <FONT color="green">094</FONT> * @throws java.lang.ArrayIndexOutOfBoundsException<a name="line.94"></a> |
| <FONT color="green">095</FONT> * if index doesn't map to a string.<a name="line.95"></a> |
| <FONT color="green">096</FONT> * */ <a name="line.96"></a> |
| <FONT color="green">097</FONT> public String indexToString(int i)<a name="line.97"></a> |
| <FONT color="green">098</FONT> throws java.lang.ArrayIndexOutOfBoundsException<a name="line.98"></a> |
| <FONT color="green">099</FONT> {<a name="line.99"></a> |
| <FONT color="green">100</FONT> if(i==NULL) return null;<a name="line.100"></a> |
| <FONT color="green">101</FONT> return (String) m_intToString.elementAt(i);<a name="line.101"></a> |
| <FONT color="green">102</FONT> }<a name="line.102"></a> |
| <FONT color="green">103</FONT> <a name="line.103"></a> |
| <FONT color="green">104</FONT> /** @return integer index uniquely identifying the value of this string. */ <a name="line.104"></a> |
| <FONT color="green">105</FONT> public int stringToIndex(String s)<a name="line.105"></a> |
| <FONT color="green">106</FONT> {<a name="line.106"></a> |
| <FONT color="green">107</FONT> if(s==null) return NULL;<a name="line.107"></a> |
| <FONT color="green">108</FONT> <a name="line.108"></a> |
| <FONT color="green">109</FONT> int hashslot=s.hashCode()%HASHPRIME;<a name="line.109"></a> |
| <FONT color="green">110</FONT> if(hashslot<0) hashslot=-hashslot;<a name="line.110"></a> |
| <FONT color="green">111</FONT> <a name="line.111"></a> |
| <FONT color="green">112</FONT> // Is it one we already know?<a name="line.112"></a> |
| <FONT color="green">113</FONT> int hashlast=m_hashStart[hashslot];<a name="line.113"></a> |
| <FONT color="green">114</FONT> int hashcandidate=hashlast;<a name="line.114"></a> |
| <FONT color="green">115</FONT> while(hashcandidate!=NULL)<a name="line.115"></a> |
| <FONT color="green">116</FONT> {<a name="line.116"></a> |
| <FONT color="green">117</FONT> if(m_intToString.elementAt(hashcandidate).equals(s))<a name="line.117"></a> |
| <FONT color="green">118</FONT> return hashcandidate;<a name="line.118"></a> |
| <FONT color="green">119</FONT> <a name="line.119"></a> |
| <FONT color="green">120</FONT> hashlast=hashcandidate;<a name="line.120"></a> |
| <FONT color="green">121</FONT> hashcandidate=m_hashChain.elementAt(hashcandidate);<a name="line.121"></a> |
| <FONT color="green">122</FONT> }<a name="line.122"></a> |
| <FONT color="green">123</FONT> <a name="line.123"></a> |
| <FONT color="green">124</FONT> // New value. Add to tables.<a name="line.124"></a> |
| <FONT color="green">125</FONT> int newIndex=m_intToString.size();<a name="line.125"></a> |
| <FONT color="green">126</FONT> m_intToString.addElement(s);<a name="line.126"></a> |
| <FONT color="green">127</FONT> <a name="line.127"></a> |
| <FONT color="green">128</FONT> m_hashChain.addElement(NULL); // Initialize to no-following-same-hash<a name="line.128"></a> |
| <FONT color="green">129</FONT> if(hashlast==NULL) // First for this hash<a name="line.129"></a> |
| <FONT color="green">130</FONT> m_hashStart[hashslot]=newIndex;<a name="line.130"></a> |
| <FONT color="green">131</FONT> else // Link from previous with same hash<a name="line.131"></a> |
| <FONT color="green">132</FONT> m_hashChain.setElementAt(newIndex,hashlast);<a name="line.132"></a> |
| <FONT color="green">133</FONT> <a name="line.133"></a> |
| <FONT color="green">134</FONT> return newIndex;<a name="line.134"></a> |
| <FONT color="green">135</FONT> }<a name="line.135"></a> |
| <FONT color="green">136</FONT> <a name="line.136"></a> |
| <FONT color="green">137</FONT> /** Command-line unit test driver. This test relies on the fact that<a name="line.137"></a> |
| <FONT color="green">138</FONT> * this version of the pool assigns indices consecutively, starting<a name="line.138"></a> |
| <FONT color="green">139</FONT> * from zero, as new unique strings are encountered.<a name="line.139"></a> |
| <FONT color="green">140</FONT> */<a name="line.140"></a> |
| <FONT color="green">141</FONT> public static void main(String[] args)<a name="line.141"></a> |
| <FONT color="green">142</FONT> {<a name="line.142"></a> |
| <FONT color="green">143</FONT> String[] word={<a name="line.143"></a> |
| <FONT color="green">144</FONT> "Zero","One","Two","Three","Four","Five",<a name="line.144"></a> |
| <FONT color="green">145</FONT> "Six","Seven","Eight","Nine","Ten",<a name="line.145"></a> |
| <FONT color="green">146</FONT> "Eleven","Twelve","Thirteen","Fourteen","Fifteen",<a name="line.146"></a> |
| <FONT color="green">147</FONT> "Sixteen","Seventeen","Eighteen","Nineteen","Twenty",<a name="line.147"></a> |
| <FONT color="green">148</FONT> "Twenty-One","Twenty-Two","Twenty-Three","Twenty-Four",<a name="line.148"></a> |
| <FONT color="green">149</FONT> "Twenty-Five","Twenty-Six","Twenty-Seven","Twenty-Eight",<a name="line.149"></a> |
| <FONT color="green">150</FONT> "Twenty-Nine","Thirty","Thirty-One","Thirty-Two",<a name="line.150"></a> |
| <FONT color="green">151</FONT> "Thirty-Three","Thirty-Four","Thirty-Five","Thirty-Six",<a name="line.151"></a> |
| <FONT color="green">152</FONT> "Thirty-Seven","Thirty-Eight","Thirty-Nine"};<a name="line.152"></a> |
| <FONT color="green">153</FONT> <a name="line.153"></a> |
| <FONT color="green">154</FONT> DTMStringPool pool=new DTMStringPool();<a name="line.154"></a> |
| <FONT color="green">155</FONT> <a name="line.155"></a> |
| <FONT color="green">156</FONT> System.out.println("If no complaints are printed below, we passed initial test.");<a name="line.156"></a> |
| <FONT color="green">157</FONT> <a name="line.157"></a> |
| <FONT color="green">158</FONT> for(int pass=0;pass<=1;++pass)<a name="line.158"></a> |
| <FONT color="green">159</FONT> {<a name="line.159"></a> |
| <FONT color="green">160</FONT> int i;<a name="line.160"></a> |
| <FONT color="green">161</FONT> <a name="line.161"></a> |
| <FONT color="green">162</FONT> for(i=0;i<word.length;++i)<a name="line.162"></a> |
| <FONT color="green">163</FONT> {<a name="line.163"></a> |
| <FONT color="green">164</FONT> int j=pool.stringToIndex(word[i]);<a name="line.164"></a> |
| <FONT color="green">165</FONT> if(j!=i)<a name="line.165"></a> |
| <FONT color="green">166</FONT> System.out.println("\tMismatch populating pool: assigned "+<a name="line.166"></a> |
| <FONT color="green">167</FONT> j+" for create "+i);<a name="line.167"></a> |
| <FONT color="green">168</FONT> }<a name="line.168"></a> |
| <FONT color="green">169</FONT> <a name="line.169"></a> |
| <FONT color="green">170</FONT> for(i=0;i<word.length;++i)<a name="line.170"></a> |
| <FONT color="green">171</FONT> {<a name="line.171"></a> |
| <FONT color="green">172</FONT> int j=pool.stringToIndex(word[i]);<a name="line.172"></a> |
| <FONT color="green">173</FONT> if(j!=i)<a name="line.173"></a> |
| <FONT color="green">174</FONT> System.out.println("\tMismatch in stringToIndex: returned "+<a name="line.174"></a> |
| <FONT color="green">175</FONT> j+" for lookup "+i);<a name="line.175"></a> |
| <FONT color="green">176</FONT> }<a name="line.176"></a> |
| <FONT color="green">177</FONT> <a name="line.177"></a> |
| <FONT color="green">178</FONT> for(i=0;i<word.length;++i)<a name="line.178"></a> |
| <FONT color="green">179</FONT> {<a name="line.179"></a> |
| <FONT color="green">180</FONT> String w=pool.indexToString(i);<a name="line.180"></a> |
| <FONT color="green">181</FONT> if(!word[i].equals(w))<a name="line.181"></a> |
| <FONT color="green">182</FONT> System.out.println("\tMismatch in indexToString: returned"+<a name="line.182"></a> |
| <FONT color="green">183</FONT> w+" for lookup "+i);<a name="line.183"></a> |
| <FONT color="green">184</FONT> }<a name="line.184"></a> |
| <FONT color="green">185</FONT> <a name="line.185"></a> |
| <FONT color="green">186</FONT> pool.removeAllElements();<a name="line.186"></a> |
| <FONT color="green">187</FONT> <a name="line.187"></a> |
| <FONT color="green">188</FONT> System.out.println("\nPass "+pass+" complete\n");<a name="line.188"></a> |
| <FONT color="green">189</FONT> } // end pass loop<a name="line.189"></a> |
| <FONT color="green">190</FONT> }<a name="line.190"></a> |
| <FONT color="green">191</FONT> }<a name="line.191"></a> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </PRE> |
| </BODY> |
| </HTML> |
