blob: 268b62dfb974c91c0ca2d73ec8da70b8a0c6faa2 [file] [log] [blame]
<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: StringComparable.java 468655 2006-10-28 07:12:06Z 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.utils;<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> import java.text.Collator;<a name="line.25"></a>
<FONT color="green">026</FONT> import java.text.RuleBasedCollator;<a name="line.26"></a>
<FONT color="green">027</FONT> import java.text.CollationElementIterator;<a name="line.27"></a>
<FONT color="green">028</FONT> import java.util.Locale;<a name="line.28"></a>
<FONT color="green">029</FONT> import java.text.CollationKey;<a name="line.29"></a>
<FONT color="green">030</FONT> <a name="line.30"></a>
<FONT color="green">031</FONT> <a name="line.31"></a>
<FONT color="green">032</FONT> /**<a name="line.32"></a>
<FONT color="green">033</FONT> * International friendly string comparison with case-order<a name="line.33"></a>
<FONT color="green">034</FONT> * @author Igor Hersht, igorh@ca.ibm.com<a name="line.34"></a>
<FONT color="green">035</FONT> */<a name="line.35"></a>
<FONT color="green">036</FONT> public class StringComparable implements Comparable {<a name="line.36"></a>
<FONT color="green">037</FONT> <a name="line.37"></a>
<FONT color="green">038</FONT> public final static int UNKNOWN_CASE = -1;<a name="line.38"></a>
<FONT color="green">039</FONT> public final static int UPPER_CASE = 1;<a name="line.39"></a>
<FONT color="green">040</FONT> public final static int LOWER_CASE = 2;<a name="line.40"></a>
<FONT color="green">041</FONT> <a name="line.41"></a>
<FONT color="green">042</FONT> private String m_text;<a name="line.42"></a>
<FONT color="green">043</FONT> private Locale m_locale;<a name="line.43"></a>
<FONT color="green">044</FONT> private RuleBasedCollator m_collator;<a name="line.44"></a>
<FONT color="green">045</FONT> private String m_caseOrder;<a name="line.45"></a>
<FONT color="green">046</FONT> private int m_mask = 0xFFFFFFFF; <a name="line.46"></a>
<FONT color="green">047</FONT> <a name="line.47"></a>
<FONT color="green">048</FONT> public StringComparable(final String text, final Locale locale, final Collator collator, final String caseOrder){<a name="line.48"></a>
<FONT color="green">049</FONT> m_text = text;<a name="line.49"></a>
<FONT color="green">050</FONT> m_locale = locale;<a name="line.50"></a>
<FONT color="green">051</FONT> m_collator = (RuleBasedCollator)collator;<a name="line.51"></a>
<FONT color="green">052</FONT> m_caseOrder = caseOrder;<a name="line.52"></a>
<FONT color="green">053</FONT> m_mask = getMask(m_collator.getStrength());<a name="line.53"></a>
<FONT color="green">054</FONT> }<a name="line.54"></a>
<FONT color="green">055</FONT> <a name="line.55"></a>
<FONT color="green">056</FONT> public final static Comparable getComparator( final String text, final Locale locale, final Collator collator, final String caseOrder){<a name="line.56"></a>
<FONT color="green">057</FONT> if((caseOrder == null) ||(caseOrder.length() == 0)){// no case-order specified<a name="line.57"></a>
<FONT color="green">058</FONT> return ((RuleBasedCollator)collator).getCollationKey(text);<a name="line.58"></a>
<FONT color="green">059</FONT> }else{<a name="line.59"></a>
<FONT color="green">060</FONT> return new StringComparable(text, locale, collator, caseOrder);<a name="line.60"></a>
<FONT color="green">061</FONT> } <a name="line.61"></a>
<FONT color="green">062</FONT> }<a name="line.62"></a>
<FONT color="green">063</FONT> <a name="line.63"></a>
<FONT color="green">064</FONT> public final String toString(){return m_text;}<a name="line.64"></a>
<FONT color="green">065</FONT> <a name="line.65"></a>
<FONT color="green">066</FONT> public int compareTo(Object o) {<a name="line.66"></a>
<FONT color="green">067</FONT> final String pattern = ((StringComparable)o).toString();<a name="line.67"></a>
<FONT color="green">068</FONT> if(m_text.equals(pattern)){//Code-point equals <a name="line.68"></a>
<FONT color="green">069</FONT> return 0;<a name="line.69"></a>
<FONT color="green">070</FONT> }<a name="line.70"></a>
<FONT color="green">071</FONT> final int savedStrength = m_collator.getStrength(); <a name="line.71"></a>
<FONT color="green">072</FONT> int comp = 0;<a name="line.72"></a>
<FONT color="green">073</FONT> // Is there difference more significant than case-order? <a name="line.73"></a>
<FONT color="green">074</FONT> if(((savedStrength == Collator.PRIMARY) || (savedStrength == Collator.SECONDARY))){ <a name="line.74"></a>
<FONT color="green">075</FONT> comp = m_collator.compare(m_text, pattern ); <a name="line.75"></a>
<FONT color="green">076</FONT> }else{// more than SECONDARY<a name="line.76"></a>
<FONT color="green">077</FONT> m_collator.setStrength(Collator.SECONDARY);<a name="line.77"></a>
<FONT color="green">078</FONT> comp = m_collator.compare(m_text, pattern );<a name="line.78"></a>
<FONT color="green">079</FONT> m_collator.setStrength(savedStrength);<a name="line.79"></a>
<FONT color="green">080</FONT> }<a name="line.80"></a>
<FONT color="green">081</FONT> if(comp != 0){//Difference more significant than case-order <a name="line.81"></a>
<FONT color="green">082</FONT> return comp ; <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> // No difference more significant than case-order. <a name="line.85"></a>
<FONT color="green">086</FONT> // Find case difference<a name="line.86"></a>
<FONT color="green">087</FONT> comp = getCaseDiff(m_text, pattern);<a name="line.87"></a>
<FONT color="green">088</FONT> if(comp != 0){ <a name="line.88"></a>
<FONT color="green">089</FONT> return comp;<a name="line.89"></a>
<FONT color="green">090</FONT> }else{// No case differences. Less significant difference could exist <a name="line.90"></a>
<FONT color="green">091</FONT> return m_collator.compare(m_text, pattern );<a name="line.91"></a>
<FONT color="green">092</FONT> } <a name="line.92"></a>
<FONT color="green">093</FONT> }<a name="line.93"></a>
<FONT color="green">094</FONT> <a name="line.94"></a>
<FONT color="green">095</FONT> <a name="line.95"></a>
<FONT color="green">096</FONT> private final int getCaseDiff (final String text, final String pattern){<a name="line.96"></a>
<FONT color="green">097</FONT> final int savedStrength = m_collator.getStrength();<a name="line.97"></a>
<FONT color="green">098</FONT> final int savedDecomposition = m_collator.getDecomposition();<a name="line.98"></a>
<FONT color="green">099</FONT> m_collator.setStrength(Collator.TERTIARY);// not to ignore case <a name="line.99"></a>
<FONT color="green">100</FONT> m_collator.setDecomposition(Collator.CANONICAL_DECOMPOSITION );// corresponds NDF<a name="line.100"></a>
<FONT color="green">101</FONT> <a name="line.101"></a>
<FONT color="green">102</FONT> final int diff[] =getFirstCaseDiff (text, pattern, m_locale);<a name="line.102"></a>
<FONT color="green">103</FONT> m_collator.setStrength(savedStrength);// restore<a name="line.103"></a>
<FONT color="green">104</FONT> m_collator.setDecomposition(savedDecomposition); //restore<a name="line.104"></a>
<FONT color="green">105</FONT> if(diff != null){ <a name="line.105"></a>
<FONT color="green">106</FONT> if((m_caseOrder).equals("upper-first")){<a name="line.106"></a>
<FONT color="green">107</FONT> if(diff[0] == UPPER_CASE){<a name="line.107"></a>
<FONT color="green">108</FONT> return -1;<a name="line.108"></a>
<FONT color="green">109</FONT> }else{<a name="line.109"></a>
<FONT color="green">110</FONT> return 1;<a name="line.110"></a>
<FONT color="green">111</FONT> }<a name="line.111"></a>
<FONT color="green">112</FONT> }else{// lower-first<a name="line.112"></a>
<FONT color="green">113</FONT> if(diff[0] == LOWER_CASE){<a name="line.113"></a>
<FONT color="green">114</FONT> return -1;<a name="line.114"></a>
<FONT color="green">115</FONT> }else{<a name="line.115"></a>
<FONT color="green">116</FONT> return 1;<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> }else{// No case differences<a name="line.119"></a>
<FONT color="green">120</FONT> return 0;<a name="line.120"></a>
<FONT color="green">121</FONT> }<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> <a name="line.124"></a>
<FONT color="green">125</FONT> <a name="line.125"></a>
<FONT color="green">126</FONT> <a name="line.126"></a>
<FONT color="green">127</FONT> private final int[] getFirstCaseDiff(final String text, final String pattern, final Locale locale){<a name="line.127"></a>
<FONT color="green">128</FONT> <a name="line.128"></a>
<FONT color="green">129</FONT> final CollationElementIterator targIter = m_collator.getCollationElementIterator(text);<a name="line.129"></a>
<FONT color="green">130</FONT> final CollationElementIterator patIter = m_collator.getCollationElementIterator(pattern); <a name="line.130"></a>
<FONT color="green">131</FONT> int startTarg = -1;<a name="line.131"></a>
<FONT color="green">132</FONT> int endTarg = -1;<a name="line.132"></a>
<FONT color="green">133</FONT> int startPatt = -1;<a name="line.133"></a>
<FONT color="green">134</FONT> int endPatt = -1;<a name="line.134"></a>
<FONT color="green">135</FONT> final int done = getElement(CollationElementIterator.NULLORDER);<a name="line.135"></a>
<FONT color="green">136</FONT> int patternElement = 0, targetElement = 0;<a name="line.136"></a>
<FONT color="green">137</FONT> boolean getPattern = true, getTarget = true;<a name="line.137"></a>
<FONT color="green">138</FONT> <a name="line.138"></a>
<FONT color="green">139</FONT> while (true) { <a name="line.139"></a>
<FONT color="green">140</FONT> if (getPattern){<a name="line.140"></a>
<FONT color="green">141</FONT> startPatt = patIter.getOffset();<a name="line.141"></a>
<FONT color="green">142</FONT> patternElement = getElement(patIter.next());<a name="line.142"></a>
<FONT color="green">143</FONT> endPatt = patIter.getOffset();<a name="line.143"></a>
<FONT color="green">144</FONT> }<a name="line.144"></a>
<FONT color="green">145</FONT> if ((getTarget)){ <a name="line.145"></a>
<FONT color="green">146</FONT> startTarg = targIter.getOffset(); <a name="line.146"></a>
<FONT color="green">147</FONT> targetElement = getElement(targIter.next()); <a name="line.147"></a>
<FONT color="green">148</FONT> endTarg = targIter.getOffset();<a name="line.148"></a>
<FONT color="green">149</FONT> }<a name="line.149"></a>
<FONT color="green">150</FONT> getTarget = getPattern = true; <a name="line.150"></a>
<FONT color="green">151</FONT> if ((patternElement == done) ||( targetElement == done)) {<a name="line.151"></a>
<FONT color="green">152</FONT> return null; <a name="line.152"></a>
<FONT color="green">153</FONT> } else if (targetElement == 0) {<a name="line.153"></a>
<FONT color="green">154</FONT> getPattern = false; <a name="line.154"></a>
<FONT color="green">155</FONT> } else if (patternElement == 0) {<a name="line.155"></a>
<FONT color="green">156</FONT> getTarget = false; <a name="line.156"></a>
<FONT color="green">157</FONT> } else if (targetElement != patternElement) {// mismatch<a name="line.157"></a>
<FONT color="green">158</FONT> if((startPatt &lt; endPatt) &amp;&amp; (startTarg &lt; endTarg)){<a name="line.158"></a>
<FONT color="green">159</FONT> final String subText = text.substring(startTarg, endTarg);<a name="line.159"></a>
<FONT color="green">160</FONT> final String subPatt = pattern.substring(startPatt, endPatt);<a name="line.160"></a>
<FONT color="green">161</FONT> final String subTextUp = subText.toUpperCase(locale);<a name="line.161"></a>
<FONT color="green">162</FONT> final String subPattUp = subPatt.toUpperCase(locale);<a name="line.162"></a>
<FONT color="green">163</FONT> if(m_collator.compare(subTextUp, subPattUp) != 0){ // not case diffference<a name="line.163"></a>
<FONT color="green">164</FONT> continue;<a name="line.164"></a>
<FONT color="green">165</FONT> }<a name="line.165"></a>
<FONT color="green">166</FONT> <a name="line.166"></a>
<FONT color="green">167</FONT> int diff[] = {UNKNOWN_CASE, UNKNOWN_CASE};<a name="line.167"></a>
<FONT color="green">168</FONT> if(m_collator.compare(subText, subTextUp) == 0){<a name="line.168"></a>
<FONT color="green">169</FONT> diff[0] = UPPER_CASE;<a name="line.169"></a>
<FONT color="green">170</FONT> }else if(m_collator.compare(subText, subText.toLowerCase(locale)) == 0){<a name="line.170"></a>
<FONT color="green">171</FONT> diff[0] = LOWER_CASE; <a name="line.171"></a>
<FONT color="green">172</FONT> }<a name="line.172"></a>
<FONT color="green">173</FONT> if(m_collator.compare(subPatt, subPattUp) == 0){<a name="line.173"></a>
<FONT color="green">174</FONT> diff[1] = UPPER_CASE;<a name="line.174"></a>
<FONT color="green">175</FONT> }else if(m_collator.compare(subPatt, subPatt.toLowerCase(locale)) == 0){<a name="line.175"></a>
<FONT color="green">176</FONT> diff[1] = LOWER_CASE; <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> if(((diff[0] == UPPER_CASE) &amp;&amp; ( diff[1] == LOWER_CASE)) ||<a name="line.179"></a>
<FONT color="green">180</FONT> ((diff[0] == LOWER_CASE) &amp;&amp; ( diff[1] == UPPER_CASE))){ <a name="line.180"></a>
<FONT color="green">181</FONT> return diff;<a name="line.181"></a>
<FONT color="green">182</FONT> }else{// not case diff<a name="line.182"></a>
<FONT color="green">183</FONT> continue; <a name="line.183"></a>
<FONT color="green">184</FONT> } <a name="line.184"></a>
<FONT color="green">185</FONT> }else{<a name="line.185"></a>
<FONT color="green">186</FONT> continue; <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> }<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>
<FONT color="green">192</FONT> }<a name="line.192"></a>
<FONT color="green">193</FONT> <a name="line.193"></a>
<FONT color="green">194</FONT> <a name="line.194"></a>
<FONT color="green">195</FONT> // Return a mask for the part of the order we're interested in<a name="line.195"></a>
<FONT color="green">196</FONT> private static final int getMask(final int strength) {<a name="line.196"></a>
<FONT color="green">197</FONT> switch (strength) {<a name="line.197"></a>
<FONT color="green">198</FONT> case Collator.PRIMARY:<a name="line.198"></a>
<FONT color="green">199</FONT> return 0xFFFF0000;<a name="line.199"></a>
<FONT color="green">200</FONT> case Collator.SECONDARY:<a name="line.200"></a>
<FONT color="green">201</FONT> return 0xFFFFFF00;<a name="line.201"></a>
<FONT color="green">202</FONT> default: <a name="line.202"></a>
<FONT color="green">203</FONT> return 0xFFFFFFFF;<a name="line.203"></a>
<FONT color="green">204</FONT> }<a name="line.204"></a>
<FONT color="green">205</FONT> }<a name="line.205"></a>
<FONT color="green">206</FONT> //get collation element with given strength<a name="line.206"></a>
<FONT color="green">207</FONT> // from the element with max strength<a name="line.207"></a>
<FONT color="green">208</FONT> private final int getElement(int maxStrengthElement){<a name="line.208"></a>
<FONT color="green">209</FONT> <a name="line.209"></a>
<FONT color="green">210</FONT> return (maxStrengthElement &amp; m_mask);<a name="line.210"></a>
<FONT color="green">211</FONT> } <a name="line.211"></a>
<FONT color="green">212</FONT> <a name="line.212"></a>
<FONT color="green">213</FONT> }//StringComparable <a name="line.213"></a>
<FONT color="green">214</FONT> <a name="line.214"></a>
<FONT color="green">215</FONT> <a name="line.215"></a>
</PRE>
</BODY>
</HTML>