blob: 0f12c343bc0aabe27258aee5650f82636cd67906 [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: CharInfo.java 468654 2006-10-28 07:09:23Z minchau $<a name="line.19"></a>
<FONT color="green">020</FONT> */<a name="line.20"></a>
<FONT color="green">021</FONT> package org.apache.xml.serializer;<a name="line.21"></a>
<FONT color="green">022</FONT> <a name="line.22"></a>
<FONT color="green">023</FONT> import java.io.BufferedReader;<a name="line.23"></a>
<FONT color="green">024</FONT> import java.io.InputStream;<a name="line.24"></a>
<FONT color="green">025</FONT> import java.io.InputStreamReader;<a name="line.25"></a>
<FONT color="green">026</FONT> import java.io.UnsupportedEncodingException;<a name="line.26"></a>
<FONT color="green">027</FONT> import java.net.URL;<a name="line.27"></a>
<FONT color="green">028</FONT> import java.util.Enumeration;<a name="line.28"></a>
<FONT color="green">029</FONT> import java.util.HashMap;<a name="line.29"></a>
<FONT color="green">030</FONT> import java.util.Hashtable;<a name="line.30"></a>
<FONT color="green">031</FONT> import java.util.PropertyResourceBundle;<a name="line.31"></a>
<FONT color="green">032</FONT> import java.util.ResourceBundle;<a name="line.32"></a>
<FONT color="green">033</FONT> import java.security.AccessController;<a name="line.33"></a>
<FONT color="green">034</FONT> import java.security.PrivilegedAction;<a name="line.34"></a>
<FONT color="green">035</FONT> <a name="line.35"></a>
<FONT color="green">036</FONT> import javax.xml.transform.TransformerException;<a name="line.36"></a>
<FONT color="green">037</FONT> <a name="line.37"></a>
<FONT color="green">038</FONT> import org.apache.xml.serializer.utils.MsgKey;<a name="line.38"></a>
<FONT color="green">039</FONT> import org.apache.xml.serializer.utils.SystemIDResolver;<a name="line.39"></a>
<FONT color="green">040</FONT> import org.apache.xml.serializer.utils.Utils;<a name="line.40"></a>
<FONT color="green">041</FONT> import org.apache.xml.serializer.utils.WrappedRuntimeException;<a name="line.41"></a>
<FONT color="green">042</FONT> <a name="line.42"></a>
<FONT color="green">043</FONT> /**<a name="line.43"></a>
<FONT color="green">044</FONT> * This class provides services that tell if a character should have<a name="line.44"></a>
<FONT color="green">045</FONT> * special treatement, such as entity reference substitution or normalization<a name="line.45"></a>
<FONT color="green">046</FONT> * of a newline character. It also provides character to entity reference<a name="line.46"></a>
<FONT color="green">047</FONT> * lookup.<a name="line.47"></a>
<FONT color="green">048</FONT> *<a name="line.48"></a>
<FONT color="green">049</FONT> * DEVELOPERS: See Known Issue in the constructor.<a name="line.49"></a>
<FONT color="green">050</FONT> * <a name="line.50"></a>
<FONT color="green">051</FONT> * @xsl.usage internal<a name="line.51"></a>
<FONT color="green">052</FONT> */<a name="line.52"></a>
<FONT color="green">053</FONT> final class CharInfo<a name="line.53"></a>
<FONT color="green">054</FONT> {<a name="line.54"></a>
<FONT color="green">055</FONT> /** Given a character, lookup a String to output (e.g. a decorated entity reference). */<a name="line.55"></a>
<FONT color="green">056</FONT> private HashMap m_charToString;<a name="line.56"></a>
<FONT color="green">057</FONT> <a name="line.57"></a>
<FONT color="green">058</FONT> /**<a name="line.58"></a>
<FONT color="green">059</FONT> * The name of the HTML entities file.<a name="line.59"></a>
<FONT color="green">060</FONT> * If specified, the file will be resource loaded with the default class loader.<a name="line.60"></a>
<FONT color="green">061</FONT> */<a name="line.61"></a>
<FONT color="green">062</FONT> public static final String HTML_ENTITIES_RESOURCE = <a name="line.62"></a>
<FONT color="green">063</FONT> SerializerBase.PKG_NAME+".HTMLEntities";<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> * The name of the XML entities file.<a name="line.66"></a>
<FONT color="green">067</FONT> * If specified, the file will be resource loaded with the default class loader.<a name="line.67"></a>
<FONT color="green">068</FONT> */<a name="line.68"></a>
<FONT color="green">069</FONT> public static final String XML_ENTITIES_RESOURCE = <a name="line.69"></a>
<FONT color="green">070</FONT> SerializerBase.PKG_NAME+".XMLEntities";<a name="line.70"></a>
<FONT color="green">071</FONT> <a name="line.71"></a>
<FONT color="green">072</FONT> /** The horizontal tab character, which the parser should always normalize. */<a name="line.72"></a>
<FONT color="green">073</FONT> static final char S_HORIZONAL_TAB = 0x09;<a name="line.73"></a>
<FONT color="green">074</FONT> <a name="line.74"></a>
<FONT color="green">075</FONT> /** The linefeed character, which the parser should always normalize. */<a name="line.75"></a>
<FONT color="green">076</FONT> static final char S_LINEFEED = 0x0A;<a name="line.76"></a>
<FONT color="green">077</FONT> <a name="line.77"></a>
<FONT color="green">078</FONT> /** The carriage return character, which the parser should always normalize. */<a name="line.78"></a>
<FONT color="green">079</FONT> static final char S_CARRIAGERETURN = 0x0D;<a name="line.79"></a>
<FONT color="green">080</FONT> static final char S_SPACE = 0x20;<a name="line.80"></a>
<FONT color="green">081</FONT> static final char S_QUOTE = 0x22;<a name="line.81"></a>
<FONT color="green">082</FONT> static final char S_LT = 0x3C;<a name="line.82"></a>
<FONT color="green">083</FONT> static final char S_GT = 0x3E;<a name="line.83"></a>
<FONT color="green">084</FONT> static final char S_NEL = 0x85; <a name="line.84"></a>
<FONT color="green">085</FONT> static final char S_LINE_SEPARATOR = 0x2028;<a name="line.85"></a>
<FONT color="green">086</FONT> <a name="line.86"></a>
<FONT color="green">087</FONT> /** This flag is an optimization for HTML entities. It false if entities <a name="line.87"></a>
<FONT color="green">088</FONT> * other than quot (34), amp (38), lt (60) and gt (62) are defined<a name="line.88"></a>
<FONT color="green">089</FONT> * in the range 0 to 127.<a name="line.89"></a>
<FONT color="green">090</FONT> * @xsl.usage internal<a name="line.90"></a>
<FONT color="green">091</FONT> */ <a name="line.91"></a>
<FONT color="green">092</FONT> boolean onlyQuotAmpLtGt;<a name="line.92"></a>
<FONT color="green">093</FONT> <a name="line.93"></a>
<FONT color="green">094</FONT> /** Copy the first 0,1 ... ASCII_MAX values into an array */<a name="line.94"></a>
<FONT color="green">095</FONT> static final int ASCII_MAX = 128;<a name="line.95"></a>
<FONT color="green">096</FONT> <a name="line.96"></a>
<FONT color="green">097</FONT> /** Array of values is faster access than a set of bits <a name="line.97"></a>
<FONT color="green">098</FONT> * to quickly check ASCII characters in attribute values,<a name="line.98"></a>
<FONT color="green">099</FONT> * the value is true if the character in an attribute value<a name="line.99"></a>
<FONT color="green">100</FONT> * should be mapped to a String. <a name="line.100"></a>
<FONT color="green">101</FONT> */<a name="line.101"></a>
<FONT color="green">102</FONT> private final boolean[] shouldMapAttrChar_ASCII;<a name="line.102"></a>
<FONT color="green">103</FONT> <a name="line.103"></a>
<FONT color="green">104</FONT> /** Array of values is faster access than a set of bits <a name="line.104"></a>
<FONT color="green">105</FONT> * to quickly check ASCII characters in text nodes, <a name="line.105"></a>
<FONT color="green">106</FONT> * the value is true if the character in a text node<a name="line.106"></a>
<FONT color="green">107</FONT> * should be mapped to a String. <a name="line.107"></a>
<FONT color="green">108</FONT> */<a name="line.108"></a>
<FONT color="green">109</FONT> private final boolean[] shouldMapTextChar_ASCII;<a name="line.109"></a>
<FONT color="green">110</FONT> <a name="line.110"></a>
<FONT color="green">111</FONT> /** An array of bits to record if the character is in the set.<a name="line.111"></a>
<FONT color="green">112</FONT> * Although information in this array is complete, the<a name="line.112"></a>
<FONT color="green">113</FONT> * isSpecialAttrASCII array is used first because access to its values<a name="line.113"></a>
<FONT color="green">114</FONT> * is common and faster.<a name="line.114"></a>
<FONT color="green">115</FONT> */ <a name="line.115"></a>
<FONT color="green">116</FONT> private final int array_of_bits[];<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> // 5 for 32 bit words, 6 for 64 bit words ...<a name="line.119"></a>
<FONT color="green">120</FONT> /*<a name="line.120"></a>
<FONT color="green">121</FONT> * This constant is used to shift an integer to quickly<a name="line.121"></a>
<FONT color="green">122</FONT> * calculate which element its bit is stored in.<a name="line.122"></a>
<FONT color="green">123</FONT> * 5 for 32 bit words (int) , 6 for 64 bit words (long)<a name="line.123"></a>
<FONT color="green">124</FONT> */<a name="line.124"></a>
<FONT color="green">125</FONT> private static final int SHIFT_PER_WORD = 5;<a name="line.125"></a>
<FONT color="green">126</FONT> <a name="line.126"></a>
<FONT color="green">127</FONT> /*<a name="line.127"></a>
<FONT color="green">128</FONT> * A mask to get the low order bits which are used to<a name="line.128"></a>
<FONT color="green">129</FONT> * calculate the value of the bit within a given word,<a name="line.129"></a>
<FONT color="green">130</FONT> * that will represent the presence of the integer in the <a name="line.130"></a>
<FONT color="green">131</FONT> * set.<a name="line.131"></a>
<FONT color="green">132</FONT> * <a name="line.132"></a>
<FONT color="green">133</FONT> * 0x1F for 32 bit words (int),<a name="line.133"></a>
<FONT color="green">134</FONT> * or 0x3F for 64 bit words (long) <a name="line.134"></a>
<FONT color="green">135</FONT> */<a name="line.135"></a>
<FONT color="green">136</FONT> private static final int LOW_ORDER_BITMASK = 0x1f;<a name="line.136"></a>
<FONT color="green">137</FONT> <a name="line.137"></a>
<FONT color="green">138</FONT> /*<a name="line.138"></a>
<FONT color="green">139</FONT> * This is used for optimizing the lookup of bits representing<a name="line.139"></a>
<FONT color="green">140</FONT> * the integers in the set. It is the index of the first element<a name="line.140"></a>
<FONT color="green">141</FONT> * in the array array_of_bits[] that is not used.<a name="line.141"></a>
<FONT color="green">142</FONT> */<a name="line.142"></a>
<FONT color="green">143</FONT> private int firstWordNotUsed;<a name="line.143"></a>
<FONT color="green">144</FONT> <a name="line.144"></a>
<FONT color="green">145</FONT> <a name="line.145"></a>
<FONT color="green">146</FONT> /**<a name="line.146"></a>
<FONT color="green">147</FONT> * A base constructor just to explicitly create the fields,<a name="line.147"></a>
<FONT color="green">148</FONT> * with the exception of m_charToString which is handled<a name="line.148"></a>
<FONT color="green">149</FONT> * by the constructor that delegates base construction to this one.<a name="line.149"></a>
<FONT color="green">150</FONT> * &lt;p&gt;<a name="line.150"></a>
<FONT color="green">151</FONT> * m_charToString is not created here only for performance reasons,<a name="line.151"></a>
<FONT color="green">152</FONT> * to avoid creating a Hashtable that will be replaced when<a name="line.152"></a>
<FONT color="green">153</FONT> * making a mutable copy, {@link #mutableCopyOf(CharInfo)}. <a name="line.153"></a>
<FONT color="green">154</FONT> *<a name="line.154"></a>
<FONT color="green">155</FONT> */<a name="line.155"></a>
<FONT color="green">156</FONT> private CharInfo() <a name="line.156"></a>
<FONT color="green">157</FONT> {<a name="line.157"></a>
<FONT color="green">158</FONT> this.array_of_bits = createEmptySetOfIntegers(65535);<a name="line.158"></a>
<FONT color="green">159</FONT> this.firstWordNotUsed = 0;<a name="line.159"></a>
<FONT color="green">160</FONT> this.shouldMapAttrChar_ASCII = new boolean[ASCII_MAX];<a name="line.160"></a>
<FONT color="green">161</FONT> this.shouldMapTextChar_ASCII = new boolean[ASCII_MAX];<a name="line.161"></a>
<FONT color="green">162</FONT> this.m_charKey = new CharKey();<a name="line.162"></a>
<FONT color="green">163</FONT> <a name="line.163"></a>
<FONT color="green">164</FONT> // Not set here, but in a constructor that uses this one<a name="line.164"></a>
<FONT color="green">165</FONT> // this.m_charToString = new Hashtable(); <a name="line.165"></a>
<FONT color="green">166</FONT> <a name="line.166"></a>
<FONT color="green">167</FONT> this.onlyQuotAmpLtGt = true;<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> return;<a name="line.170"></a>
<FONT color="green">171</FONT> }<a name="line.171"></a>
<FONT color="green">172</FONT> <a name="line.172"></a>
<FONT color="green">173</FONT> private CharInfo(String entitiesResource, String method, boolean internal)<a name="line.173"></a>
<FONT color="green">174</FONT> {<a name="line.174"></a>
<FONT color="green">175</FONT> // call the default constructor to create the fields<a name="line.175"></a>
<FONT color="green">176</FONT> this();<a name="line.176"></a>
<FONT color="green">177</FONT> m_charToString = new HashMap();<a name="line.177"></a>
<FONT color="green">178</FONT> <a name="line.178"></a>
<FONT color="green">179</FONT> ResourceBundle entities = null;<a name="line.179"></a>
<FONT color="green">180</FONT> boolean noExtraEntities = true;<a name="line.180"></a>
<FONT color="green">181</FONT> <a name="line.181"></a>
<FONT color="green">182</FONT> // Make various attempts to interpret the parameter as a properties<a name="line.182"></a>
<FONT color="green">183</FONT> // file or resource file, as follows:<a name="line.183"></a>
<FONT color="green">184</FONT> //<a name="line.184"></a>
<FONT color="green">185</FONT> // 1) attempt to load .properties file using ResourceBundle<a name="line.185"></a>
<FONT color="green">186</FONT> // 2) try using the class loader to find the specified file a resource<a name="line.186"></a>
<FONT color="green">187</FONT> // file<a name="line.187"></a>
<FONT color="green">188</FONT> // 3) try treating the resource a URI<a name="line.188"></a>
<FONT color="green">189</FONT> <a name="line.189"></a>
<FONT color="green">190</FONT> if (internal) { <a name="line.190"></a>
<FONT color="green">191</FONT> try {<a name="line.191"></a>
<FONT color="green">192</FONT> // Load entity property files by using PropertyResourceBundle,<a name="line.192"></a>
<FONT color="green">193</FONT> // cause of security issure for applets<a name="line.193"></a>
<FONT color="green">194</FONT> entities = PropertyResourceBundle.getBundle(entitiesResource);<a name="line.194"></a>
<FONT color="green">195</FONT> } catch (Exception e) {}<a name="line.195"></a>
<FONT color="green">196</FONT> }<a name="line.196"></a>
<FONT color="green">197</FONT> <a name="line.197"></a>
<FONT color="green">198</FONT> if (entities != null) {<a name="line.198"></a>
<FONT color="green">199</FONT> Enumeration keys = entities.getKeys();<a name="line.199"></a>
<FONT color="green">200</FONT> while (keys.hasMoreElements()){<a name="line.200"></a>
<FONT color="green">201</FONT> String name = (String) keys.nextElement();<a name="line.201"></a>
<FONT color="green">202</FONT> String value = entities.getString(name);<a name="line.202"></a>
<FONT color="green">203</FONT> int code = Integer.parseInt(value);<a name="line.203"></a>
<FONT color="green">204</FONT> boolean extra = defineEntity(name, (char) code);<a name="line.204"></a>
<FONT color="green">205</FONT> if (extra)<a name="line.205"></a>
<FONT color="green">206</FONT> noExtraEntities = false;<a name="line.206"></a>
<FONT color="green">207</FONT> }<a name="line.207"></a>
<FONT color="green">208</FONT> } else {<a name="line.208"></a>
<FONT color="green">209</FONT> InputStream is = null;<a name="line.209"></a>
<FONT color="green">210</FONT> <a name="line.210"></a>
<FONT color="green">211</FONT> // Load user specified resource file by using URL loading, it<a name="line.211"></a>
<FONT color="green">212</FONT> // requires a valid URI as parameter<a name="line.212"></a>
<FONT color="green">213</FONT> try {<a name="line.213"></a>
<FONT color="green">214</FONT> if (internal) {<a name="line.214"></a>
<FONT color="green">215</FONT> is = CharInfo.class.getResourceAsStream(entitiesResource);<a name="line.215"></a>
<FONT color="green">216</FONT> } else {<a name="line.216"></a>
<FONT color="green">217</FONT> ClassLoader cl = ObjectFactory.findClassLoader();<a name="line.217"></a>
<FONT color="green">218</FONT> if (cl == null) {<a name="line.218"></a>
<FONT color="green">219</FONT> is = ClassLoader.getSystemResourceAsStream(entitiesResource);<a name="line.219"></a>
<FONT color="green">220</FONT> } else {<a name="line.220"></a>
<FONT color="green">221</FONT> is = cl.getResourceAsStream(entitiesResource);<a name="line.221"></a>
<FONT color="green">222</FONT> }<a name="line.222"></a>
<FONT color="green">223</FONT> <a name="line.223"></a>
<FONT color="green">224</FONT> if (is == null) {<a name="line.224"></a>
<FONT color="green">225</FONT> try {<a name="line.225"></a>
<FONT color="green">226</FONT> URL url = new URL(entitiesResource);<a name="line.226"></a>
<FONT color="green">227</FONT> is = url.openStream();<a name="line.227"></a>
<FONT color="green">228</FONT> } catch (Exception e) {}<a name="line.228"></a>
<FONT color="green">229</FONT> }<a name="line.229"></a>
<FONT color="green">230</FONT> }<a name="line.230"></a>
<FONT color="green">231</FONT> <a name="line.231"></a>
<FONT color="green">232</FONT> if (is == null) {<a name="line.232"></a>
<FONT color="green">233</FONT> throw new RuntimeException(<a name="line.233"></a>
<FONT color="green">234</FONT> Utils.messages.createMessage(<a name="line.234"></a>
<FONT color="green">235</FONT> MsgKey.ER_RESOURCE_COULD_NOT_FIND,<a name="line.235"></a>
<FONT color="green">236</FONT> new Object[] {entitiesResource, entitiesResource}));<a name="line.236"></a>
<FONT color="green">237</FONT> }<a name="line.237"></a>
<FONT color="green">238</FONT> <a name="line.238"></a>
<FONT color="green">239</FONT> // Fix Bugzilla#4000: force reading in UTF-8<a name="line.239"></a>
<FONT color="green">240</FONT> // This creates the de facto standard that Xalan's resource <a name="line.240"></a>
<FONT color="green">241</FONT> // files must be encoded in UTF-8. This should work in all<a name="line.241"></a>
<FONT color="green">242</FONT> // JVMs.<a name="line.242"></a>
<FONT color="green">243</FONT> //<a name="line.243"></a>
<FONT color="green">244</FONT> // %REVIEW% KNOWN ISSUE: IT FAILS IN MICROSOFT VJ++, which<a name="line.244"></a>
<FONT color="green">245</FONT> // didn't implement the UTF-8 encoding. Theoretically, we should<a name="line.245"></a>
<FONT color="green">246</FONT> // simply let it fail in that case, since the JVM is obviously<a name="line.246"></a>
<FONT color="green">247</FONT> // broken if it doesn't support such a basic standard. But<a name="line.247"></a>
<FONT color="green">248</FONT> // since there are still some users attempting to use VJ++ for<a name="line.248"></a>
<FONT color="green">249</FONT> // development, we have dropped in a fallback which makes a<a name="line.249"></a>
<FONT color="green">250</FONT> // second attempt using the platform's default encoding. In VJ++<a name="line.250"></a>
<FONT color="green">251</FONT> // this is apparently ASCII, which is subset of UTF-8... and<a name="line.251"></a>
<FONT color="green">252</FONT> // since the strings we'll be reading here are also primarily<a name="line.252"></a>
<FONT color="green">253</FONT> // limited to the 7-bit ASCII range (at least, in English<a name="line.253"></a>
<FONT color="green">254</FONT> // versions of Xalan), this should work well enough to keep us<a name="line.254"></a>
<FONT color="green">255</FONT> // on the air until we're ready to officially decommit from<a name="line.255"></a>
<FONT color="green">256</FONT> // VJ++.<a name="line.256"></a>
<FONT color="green">257</FONT> <a name="line.257"></a>
<FONT color="green">258</FONT> BufferedReader reader;<a name="line.258"></a>
<FONT color="green">259</FONT> try {<a name="line.259"></a>
<FONT color="green">260</FONT> reader = new BufferedReader(new InputStreamReader(is, "UTF-8"));<a name="line.260"></a>
<FONT color="green">261</FONT> } catch (UnsupportedEncodingException e) {<a name="line.261"></a>
<FONT color="green">262</FONT> reader = new BufferedReader(new InputStreamReader(is));<a name="line.262"></a>
<FONT color="green">263</FONT> }<a name="line.263"></a>
<FONT color="green">264</FONT> <a name="line.264"></a>
<FONT color="green">265</FONT> String line = reader.readLine();<a name="line.265"></a>
<FONT color="green">266</FONT> <a name="line.266"></a>
<FONT color="green">267</FONT> while (line != null) {<a name="line.267"></a>
<FONT color="green">268</FONT> if (line.length() == 0 || line.charAt(0) == '#') {<a name="line.268"></a>
<FONT color="green">269</FONT> line = reader.readLine();<a name="line.269"></a>
<FONT color="green">270</FONT> <a name="line.270"></a>
<FONT color="green">271</FONT> continue;<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> int index = line.indexOf(' ');<a name="line.274"></a>
<FONT color="green">275</FONT> <a name="line.275"></a>
<FONT color="green">276</FONT> if (index &gt; 1) {<a name="line.276"></a>
<FONT color="green">277</FONT> String name = line.substring(0, index);<a name="line.277"></a>
<FONT color="green">278</FONT> <a name="line.278"></a>
<FONT color="green">279</FONT> ++index;<a name="line.279"></a>
<FONT color="green">280</FONT> <a name="line.280"></a>
<FONT color="green">281</FONT> if (index &lt; line.length()) {<a name="line.281"></a>
<FONT color="green">282</FONT> String value = line.substring(index);<a name="line.282"></a>
<FONT color="green">283</FONT> index = value.indexOf(' ');<a name="line.283"></a>
<FONT color="green">284</FONT> <a name="line.284"></a>
<FONT color="green">285</FONT> if (index &gt; 0) {<a name="line.285"></a>
<FONT color="green">286</FONT> value = value.substring(0, index);<a name="line.286"></a>
<FONT color="green">287</FONT> }<a name="line.287"></a>
<FONT color="green">288</FONT> <a name="line.288"></a>
<FONT color="green">289</FONT> int code = Integer.parseInt(value);<a name="line.289"></a>
<FONT color="green">290</FONT> <a name="line.290"></a>
<FONT color="green">291</FONT> boolean extra = defineEntity(name, (char) code);<a name="line.291"></a>
<FONT color="green">292</FONT> if (extra)<a name="line.292"></a>
<FONT color="green">293</FONT> noExtraEntities = false;<a name="line.293"></a>
<FONT color="green">294</FONT> }<a name="line.294"></a>
<FONT color="green">295</FONT> }<a name="line.295"></a>
<FONT color="green">296</FONT> <a name="line.296"></a>
<FONT color="green">297</FONT> line = reader.readLine();<a name="line.297"></a>
<FONT color="green">298</FONT> }<a name="line.298"></a>
<FONT color="green">299</FONT> <a name="line.299"></a>
<FONT color="green">300</FONT> is.close();<a name="line.300"></a>
<FONT color="green">301</FONT> } catch (Exception e) {<a name="line.301"></a>
<FONT color="green">302</FONT> throw new RuntimeException(<a name="line.302"></a>
<FONT color="green">303</FONT> Utils.messages.createMessage(<a name="line.303"></a>
<FONT color="green">304</FONT> MsgKey.ER_RESOURCE_COULD_NOT_LOAD,<a name="line.304"></a>
<FONT color="green">305</FONT> new Object[] { entitiesResource,<a name="line.305"></a>
<FONT color="green">306</FONT> e.toString(),<a name="line.306"></a>
<FONT color="green">307</FONT> entitiesResource,<a name="line.307"></a>
<FONT color="green">308</FONT> e.toString()}));<a name="line.308"></a>
<FONT color="green">309</FONT> } finally {<a name="line.309"></a>
<FONT color="green">310</FONT> if (is != null) {<a name="line.310"></a>
<FONT color="green">311</FONT> try {<a name="line.311"></a>
<FONT color="green">312</FONT> is.close();<a name="line.312"></a>
<FONT color="green">313</FONT> } catch (Exception except) {}<a name="line.313"></a>
<FONT color="green">314</FONT> }<a name="line.314"></a>
<FONT color="green">315</FONT> }<a name="line.315"></a>
<FONT color="green">316</FONT> }<a name="line.316"></a>
<FONT color="green">317</FONT> <a name="line.317"></a>
<FONT color="green">318</FONT> onlyQuotAmpLtGt = noExtraEntities;<a name="line.318"></a>
<FONT color="green">319</FONT> <a name="line.319"></a>
<FONT color="green">320</FONT> /* Now that we've used get(ch) just above to initialize the<a name="line.320"></a>
<FONT color="green">321</FONT> * two arrays we will change by adding a tab to the set of <a name="line.321"></a>
<FONT color="green">322</FONT> * special chars for XML (but not HTML!).<a name="line.322"></a>
<FONT color="green">323</FONT> * We do this because a tab is always a<a name="line.323"></a>
<FONT color="green">324</FONT> * special character in an XML attribute, <a name="line.324"></a>
<FONT color="green">325</FONT> * but only a special character in XML text <a name="line.325"></a>
<FONT color="green">326</FONT> * if it has an entity defined for it.<a name="line.326"></a>
<FONT color="green">327</FONT> * This is the reason for this delay.<a name="line.327"></a>
<FONT color="green">328</FONT> */<a name="line.328"></a>
<FONT color="green">329</FONT> if (Method.XML.equals(method)) <a name="line.329"></a>
<FONT color="green">330</FONT> { <a name="line.330"></a>
<FONT color="green">331</FONT> // We choose not to escape the quotation mark as &amp;quot; in text nodes<a name="line.331"></a>
<FONT color="green">332</FONT> shouldMapTextChar_ASCII[S_QUOTE] = false;<a name="line.332"></a>
<FONT color="green">333</FONT> }<a name="line.333"></a>
<FONT color="green">334</FONT> <a name="line.334"></a>
<FONT color="green">335</FONT> if (Method.HTML.equals(method)) {<a name="line.335"></a>
<FONT color="green">336</FONT> // The XSLT 1.0 recommendation says <a name="line.336"></a>
<FONT color="green">337</FONT> // "The html output method should not escape &lt; characters occurring in attribute values."<a name="line.337"></a>
<FONT color="green">338</FONT> // So we don't escape '&lt;' in an attribute for HTML<a name="line.338"></a>
<FONT color="green">339</FONT> shouldMapAttrChar_ASCII['&lt;'] = false; <a name="line.339"></a>
<FONT color="green">340</FONT> <a name="line.340"></a>
<FONT color="green">341</FONT> // We choose not to escape the quotation mark as &amp;quot; in text nodes.<a name="line.341"></a>
<FONT color="green">342</FONT> shouldMapTextChar_ASCII[S_QUOTE] = false;<a name="line.342"></a>
<FONT color="green">343</FONT> }<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> /**<a name="line.346"></a>
<FONT color="green">347</FONT> * Defines a new character reference. The reference's name and value are<a name="line.347"></a>
<FONT color="green">348</FONT> * supplied. Nothing happens if the character reference is already defined.<a name="line.348"></a>
<FONT color="green">349</FONT> * &lt;p&gt;Unlike internal entities, character references are a string to single<a name="line.349"></a>
<FONT color="green">350</FONT> * character mapping. They are used to map non-ASCII characters both on<a name="line.350"></a>
<FONT color="green">351</FONT> * parsing and printing, primarily for HTML documents. '&amp;amp;lt;' is an<a name="line.351"></a>
<FONT color="green">352</FONT> * example of a character reference.&lt;/p&gt;<a name="line.352"></a>
<FONT color="green">353</FONT> *<a name="line.353"></a>
<FONT color="green">354</FONT> * @param name The entity's name<a name="line.354"></a>
<FONT color="green">355</FONT> * @param value The entity's value<a name="line.355"></a>
<FONT color="green">356</FONT> * @return true if the mapping is not one of:<a name="line.356"></a>
<FONT color="green">357</FONT> * &lt;ul&gt;<a name="line.357"></a>
<FONT color="green">358</FONT> * &lt;li&gt; '&lt;' to "&amp;lt;"<a name="line.358"></a>
<FONT color="green">359</FONT> * &lt;li&gt; '&gt;' to "&amp;gt;"<a name="line.359"></a>
<FONT color="green">360</FONT> * &lt;li&gt; '&amp;' to "&amp;amp;"<a name="line.360"></a>
<FONT color="green">361</FONT> * &lt;li&gt; '"' to "&amp;quot;"<a name="line.361"></a>
<FONT color="green">362</FONT> * &lt;/ul&gt;<a name="line.362"></a>
<FONT color="green">363</FONT> */<a name="line.363"></a>
<FONT color="green">364</FONT> private boolean defineEntity(String name, char value)<a name="line.364"></a>
<FONT color="green">365</FONT> {<a name="line.365"></a>
<FONT color="green">366</FONT> StringBuffer sb = new StringBuffer("&amp;");<a name="line.366"></a>
<FONT color="green">367</FONT> sb.append(name);<a name="line.367"></a>
<FONT color="green">368</FONT> sb.append(';');<a name="line.368"></a>
<FONT color="green">369</FONT> String entityString = sb.toString();<a name="line.369"></a>
<FONT color="green">370</FONT> <a name="line.370"></a>
<FONT color="green">371</FONT> boolean extra = defineChar2StringMapping(entityString, value);<a name="line.371"></a>
<FONT color="green">372</FONT> return extra;<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>
<FONT color="green">376</FONT> * A utility object, just used to map characters to output Strings,<a name="line.376"></a>
<FONT color="green">377</FONT> * needed because a HashMap needs to map an object as a key, not a <a name="line.377"></a>
<FONT color="green">378</FONT> * Java primitive type, like a char, so this object gets around that<a name="line.378"></a>
<FONT color="green">379</FONT> * and it is reusable.<a name="line.379"></a>
<FONT color="green">380</FONT> */<a name="line.380"></a>
<FONT color="green">381</FONT> private final CharKey m_charKey;<a name="line.381"></a>
<FONT color="green">382</FONT> <a name="line.382"></a>
<FONT color="green">383</FONT> /**<a name="line.383"></a>
<FONT color="green">384</FONT> * Map a character to a String. For example given<a name="line.384"></a>
<FONT color="green">385</FONT> * the character '&gt;' this method would return the fully decorated<a name="line.385"></a>
<FONT color="green">386</FONT> * entity name "&amp;lt;".<a name="line.386"></a>
<FONT color="green">387</FONT> * Strings for entity references are loaded from a properties file,<a name="line.387"></a>
<FONT color="green">388</FONT> * but additional mappings defined through calls to defineChar2String()<a name="line.388"></a>
<FONT color="green">389</FONT> * are possible. Such entity reference mappings could be over-ridden.<a name="line.389"></a>
<FONT color="green">390</FONT> *<a name="line.390"></a>
<FONT color="green">391</FONT> * This is reusing a stored key object, in an effort to avoid<a name="line.391"></a>
<FONT color="green">392</FONT> * heap activity. Unfortunately, that introduces a threading risk.<a name="line.392"></a>
<FONT color="green">393</FONT> * Simplest fix for now is to make it a synchronized method, or to give<a name="line.393"></a>
<FONT color="green">394</FONT> * up the reuse; I see very little performance difference between them.<a name="line.394"></a>
<FONT color="green">395</FONT> * Long-term solution would be to replace the hashtable with a sparse array<a name="line.395"></a>
<FONT color="green">396</FONT> * keyed directly from the character's integer value; see DTM's<a name="line.396"></a>
<FONT color="green">397</FONT> * string pool for a related solution.<a name="line.397"></a>
<FONT color="green">398</FONT> *<a name="line.398"></a>
<FONT color="green">399</FONT> * @param value The character that should be resolved to<a name="line.399"></a>
<FONT color="green">400</FONT> * a String, e.g. resolve '&gt;' to "&amp;lt;".<a name="line.400"></a>
<FONT color="green">401</FONT> *<a name="line.401"></a>
<FONT color="green">402</FONT> * @return The String that the character is mapped to, or null if not found.<a name="line.402"></a>
<FONT color="green">403</FONT> * @xsl.usage internal<a name="line.403"></a>
<FONT color="green">404</FONT> */<a name="line.404"></a>
<FONT color="green">405</FONT> String getOutputStringForChar(char value)<a name="line.405"></a>
<FONT color="green">406</FONT> {<a name="line.406"></a>
<FONT color="green">407</FONT> // CharKey m_charKey = new CharKey(); //Alternative to synchronized<a name="line.407"></a>
<FONT color="green">408</FONT> m_charKey.setChar(value);<a name="line.408"></a>
<FONT color="green">409</FONT> return (String) m_charToString.get(m_charKey);<a name="line.409"></a>
<FONT color="green">410</FONT> }<a name="line.410"></a>
<FONT color="green">411</FONT> <a name="line.411"></a>
<FONT color="green">412</FONT> /**<a name="line.412"></a>
<FONT color="green">413</FONT> * Tell if the character argument that is from<a name="line.413"></a>
<FONT color="green">414</FONT> * an attribute value has a mapping to a String.<a name="line.414"></a>
<FONT color="green">415</FONT> * <a name="line.415"></a>
<FONT color="green">416</FONT> * @param value the value of a character that is in an attribute value<a name="line.416"></a>
<FONT color="green">417</FONT> * @return true if the character should have any special treatment, <a name="line.417"></a>
<FONT color="green">418</FONT> * such as when writing out entity references.<a name="line.418"></a>
<FONT color="green">419</FONT> * @xsl.usage internal<a name="line.419"></a>
<FONT color="green">420</FONT> */<a name="line.420"></a>
<FONT color="green">421</FONT> final boolean shouldMapAttrChar(int value)<a name="line.421"></a>
<FONT color="green">422</FONT> {<a name="line.422"></a>
<FONT color="green">423</FONT> // for performance try the values in the boolean array first,<a name="line.423"></a>
<FONT color="green">424</FONT> // this is faster access than the BitSet for common ASCII values<a name="line.424"></a>
<FONT color="green">425</FONT> <a name="line.425"></a>
<FONT color="green">426</FONT> if (value &lt; ASCII_MAX)<a name="line.426"></a>
<FONT color="green">427</FONT> return shouldMapAttrChar_ASCII[value];<a name="line.427"></a>
<FONT color="green">428</FONT> <a name="line.428"></a>
<FONT color="green">429</FONT> // rather than java.util.BitSet, our private<a name="line.429"></a>
<FONT color="green">430</FONT> // implementation is faster (and less general).<a name="line.430"></a>
<FONT color="green">431</FONT> return get(value);<a name="line.431"></a>
<FONT color="green">432</FONT> } <a name="line.432"></a>
<FONT color="green">433</FONT> <a name="line.433"></a>
<FONT color="green">434</FONT> /**<a name="line.434"></a>
<FONT color="green">435</FONT> * Tell if the character argument that is from a <a name="line.435"></a>
<FONT color="green">436</FONT> * text node has a mapping to a String, for example<a name="line.436"></a>
<FONT color="green">437</FONT> * to map '&lt;' to "&amp;lt;".<a name="line.437"></a>
<FONT color="green">438</FONT> * <a name="line.438"></a>
<FONT color="green">439</FONT> * @param value the value of a character that is in a text node<a name="line.439"></a>
<FONT color="green">440</FONT> * @return true if the character has a mapping to a String, <a name="line.440"></a>
<FONT color="green">441</FONT> * such as when writing out entity references.<a name="line.441"></a>
<FONT color="green">442</FONT> * @xsl.usage internal<a name="line.442"></a>
<FONT color="green">443</FONT> */<a name="line.443"></a>
<FONT color="green">444</FONT> final boolean shouldMapTextChar(int value)<a name="line.444"></a>
<FONT color="green">445</FONT> {<a name="line.445"></a>
<FONT color="green">446</FONT> // for performance try the values in the boolean array first,<a name="line.446"></a>
<FONT color="green">447</FONT> // this is faster access than the BitSet for common ASCII values<a name="line.447"></a>
<FONT color="green">448</FONT> <a name="line.448"></a>
<FONT color="green">449</FONT> if (value &lt; ASCII_MAX)<a name="line.449"></a>
<FONT color="green">450</FONT> return shouldMapTextChar_ASCII[value];<a name="line.450"></a>
<FONT color="green">451</FONT> <a name="line.451"></a>
<FONT color="green">452</FONT> // rather than java.util.BitSet, our private<a name="line.452"></a>
<FONT color="green">453</FONT> // implementation is faster (and less general).<a name="line.453"></a>
<FONT color="green">454</FONT> return get(value);<a name="line.454"></a>
<FONT color="green">455</FONT> }<a name="line.455"></a>
<FONT color="green">456</FONT> <a name="line.456"></a>
<FONT color="green">457</FONT> <a name="line.457"></a>
<FONT color="green">458</FONT> <a name="line.458"></a>
<FONT color="green">459</FONT> private static CharInfo getCharInfoBasedOnPrivilege(<a name="line.459"></a>
<FONT color="green">460</FONT> final String entitiesFileName, final String method, <a name="line.460"></a>
<FONT color="green">461</FONT> final boolean internal){<a name="line.461"></a>
<FONT color="green">462</FONT> return (CharInfo) AccessController.doPrivileged(<a name="line.462"></a>
<FONT color="green">463</FONT> new PrivilegedAction() {<a name="line.463"></a>
<FONT color="green">464</FONT> public Object run() {<a name="line.464"></a>
<FONT color="green">465</FONT> return new CharInfo(entitiesFileName, <a name="line.465"></a>
<FONT color="green">466</FONT> method, internal);}<a name="line.466"></a>
<FONT color="green">467</FONT> }); <a name="line.467"></a>
<FONT color="green">468</FONT> }<a name="line.468"></a>
<FONT color="green">469</FONT> <a name="line.469"></a>
<FONT color="green">470</FONT> /**<a name="line.470"></a>
<FONT color="green">471</FONT> * Factory that reads in a resource file that describes the mapping of<a name="line.471"></a>
<FONT color="green">472</FONT> * characters to entity references.<a name="line.472"></a>
<FONT color="green">473</FONT> *<a name="line.473"></a>
<FONT color="green">474</FONT> * Resource files must be encoded in UTF-8 and have a format like:<a name="line.474"></a>
<FONT color="green">475</FONT> * &lt;pre&gt;<a name="line.475"></a>
<FONT color="green">476</FONT> * # First char # is a comment<a name="line.476"></a>
<FONT color="green">477</FONT> * Entity numericValue<a name="line.477"></a>
<FONT color="green">478</FONT> * quot 34<a name="line.478"></a>
<FONT color="green">479</FONT> * amp 38<a name="line.479"></a>
<FONT color="green">480</FONT> * &lt;/pre&gt;<a name="line.480"></a>
<FONT color="green">481</FONT> * (Note: Why don't we just switch to .properties files? Oct-01 -sc)<a name="line.481"></a>
<FONT color="green">482</FONT> *<a name="line.482"></a>
<FONT color="green">483</FONT> * @param entitiesResource Name of entities resource file that should<a name="line.483"></a>
<FONT color="green">484</FONT> * be loaded, which describes that mapping of characters to entity references.<a name="line.484"></a>
<FONT color="green">485</FONT> * @param method the output method type, which should be one of "xml", "html", "text"...<a name="line.485"></a>
<FONT color="green">486</FONT> * <a name="line.486"></a>
<FONT color="green">487</FONT> * @xsl.usage internal<a name="line.487"></a>
<FONT color="green">488</FONT> */<a name="line.488"></a>
<FONT color="green">489</FONT> static CharInfo getCharInfo(String entitiesFileName, String method)<a name="line.489"></a>
<FONT color="green">490</FONT> {<a name="line.490"></a>
<FONT color="green">491</FONT> CharInfo charInfo = (CharInfo) m_getCharInfoCache.get(entitiesFileName);<a name="line.491"></a>
<FONT color="green">492</FONT> if (charInfo != null) {<a name="line.492"></a>
<FONT color="green">493</FONT> return mutableCopyOf(charInfo);<a name="line.493"></a>
<FONT color="green">494</FONT> }<a name="line.494"></a>
<FONT color="green">495</FONT> <a name="line.495"></a>
<FONT color="green">496</FONT> // try to load it internally - cache<a name="line.496"></a>
<FONT color="green">497</FONT> try {<a name="line.497"></a>
<FONT color="green">498</FONT> charInfo = getCharInfoBasedOnPrivilege(entitiesFileName, <a name="line.498"></a>
<FONT color="green">499</FONT> method, true);<a name="line.499"></a>
<FONT color="green">500</FONT> // Put the common copy of charInfo in the cache, but return<a name="line.500"></a>
<FONT color="green">501</FONT> // a copy of it.<a name="line.501"></a>
<FONT color="green">502</FONT> m_getCharInfoCache.put(entitiesFileName, charInfo);<a name="line.502"></a>
<FONT color="green">503</FONT> return mutableCopyOf(charInfo);<a name="line.503"></a>
<FONT color="green">504</FONT> } catch (Exception e) {}<a name="line.504"></a>
<FONT color="green">505</FONT> <a name="line.505"></a>
<FONT color="green">506</FONT> // try to load it externally - do not cache<a name="line.506"></a>
<FONT color="green">507</FONT> try {<a name="line.507"></a>
<FONT color="green">508</FONT> return getCharInfoBasedOnPrivilege(entitiesFileName, <a name="line.508"></a>
<FONT color="green">509</FONT> method, false);<a name="line.509"></a>
<FONT color="green">510</FONT> } catch (Exception e) {}<a name="line.510"></a>
<FONT color="green">511</FONT> <a name="line.511"></a>
<FONT color="green">512</FONT> String absoluteEntitiesFileName;<a name="line.512"></a>
<FONT color="green">513</FONT> <a name="line.513"></a>
<FONT color="green">514</FONT> if (entitiesFileName.indexOf(':') &lt; 0) {<a name="line.514"></a>
<FONT color="green">515</FONT> absoluteEntitiesFileName =<a name="line.515"></a>
<FONT color="green">516</FONT> SystemIDResolver.getAbsoluteURIFromRelative(entitiesFileName);<a name="line.516"></a>
<FONT color="green">517</FONT> } else {<a name="line.517"></a>
<FONT color="green">518</FONT> try {<a name="line.518"></a>
<FONT color="green">519</FONT> absoluteEntitiesFileName =<a name="line.519"></a>
<FONT color="green">520</FONT> SystemIDResolver.getAbsoluteURI(entitiesFileName, null);<a name="line.520"></a>
<FONT color="green">521</FONT> } catch (TransformerException te) {<a name="line.521"></a>
<FONT color="green">522</FONT> throw new WrappedRuntimeException(te);<a name="line.522"></a>
<FONT color="green">523</FONT> }<a name="line.523"></a>
<FONT color="green">524</FONT> }<a name="line.524"></a>
<FONT color="green">525</FONT> <a name="line.525"></a>
<FONT color="green">526</FONT> return getCharInfoBasedOnPrivilege(entitiesFileName, <a name="line.526"></a>
<FONT color="green">527</FONT> method, false);<a name="line.527"></a>
<FONT color="green">528</FONT> }<a name="line.528"></a>
<FONT color="green">529</FONT> <a name="line.529"></a>
<FONT color="green">530</FONT> /**<a name="line.530"></a>
<FONT color="green">531</FONT> * Create a mutable copy of the cached one.<a name="line.531"></a>
<FONT color="green">532</FONT> * @param charInfo The cached one.<a name="line.532"></a>
<FONT color="green">533</FONT> * @return<a name="line.533"></a>
<FONT color="green">534</FONT> */<a name="line.534"></a>
<FONT color="green">535</FONT> private static CharInfo mutableCopyOf(CharInfo charInfo) {<a name="line.535"></a>
<FONT color="green">536</FONT> CharInfo copy = new CharInfo();<a name="line.536"></a>
<FONT color="green">537</FONT> <a name="line.537"></a>
<FONT color="green">538</FONT> int max = charInfo.array_of_bits.length;<a name="line.538"></a>
<FONT color="green">539</FONT> System.arraycopy(charInfo.array_of_bits,0,copy.array_of_bits,0,max);<a name="line.539"></a>
<FONT color="green">540</FONT> <a name="line.540"></a>
<FONT color="green">541</FONT> copy.firstWordNotUsed = charInfo.firstWordNotUsed;<a name="line.541"></a>
<FONT color="green">542</FONT> <a name="line.542"></a>
<FONT color="green">543</FONT> max = charInfo.shouldMapAttrChar_ASCII.length;<a name="line.543"></a>
<FONT color="green">544</FONT> System.arraycopy(charInfo.shouldMapAttrChar_ASCII,0,copy.shouldMapAttrChar_ASCII,0,max);<a name="line.544"></a>
<FONT color="green">545</FONT> <a name="line.545"></a>
<FONT color="green">546</FONT> max = charInfo.shouldMapTextChar_ASCII.length;<a name="line.546"></a>
<FONT color="green">547</FONT> System.arraycopy(charInfo.shouldMapTextChar_ASCII,0,copy.shouldMapTextChar_ASCII,0,max);<a name="line.547"></a>
<FONT color="green">548</FONT> <a name="line.548"></a>
<FONT color="green">549</FONT> // utility field copy.m_charKey is already created in the default constructor <a name="line.549"></a>
<FONT color="green">550</FONT> <a name="line.550"></a>
<FONT color="green">551</FONT> copy.m_charToString = (HashMap) charInfo.m_charToString.clone();<a name="line.551"></a>
<FONT color="green">552</FONT> <a name="line.552"></a>
<FONT color="green">553</FONT> copy.onlyQuotAmpLtGt = charInfo.onlyQuotAmpLtGt;<a name="line.553"></a>
<FONT color="green">554</FONT> <a name="line.554"></a>
<FONT color="green">555</FONT> return copy;<a name="line.555"></a>
<FONT color="green">556</FONT> }<a name="line.556"></a>
<FONT color="green">557</FONT> <a name="line.557"></a>
<FONT color="green">558</FONT> /** <a name="line.558"></a>
<FONT color="green">559</FONT> * Table of user-specified char infos.<a name="line.559"></a>
<FONT color="green">560</FONT> * The table maps entify file names (the name of the<a name="line.560"></a>
<FONT color="green">561</FONT> * property file without the .properties extension)<a name="line.561"></a>
<FONT color="green">562</FONT> * to CharInfo objects populated with entities defined in <a name="line.562"></a>
<FONT color="green">563</FONT> * corresponding property file. <a name="line.563"></a>
<FONT color="green">564</FONT> */<a name="line.564"></a>
<FONT color="green">565</FONT> private static Hashtable m_getCharInfoCache = new Hashtable();<a name="line.565"></a>
<FONT color="green">566</FONT> <a name="line.566"></a>
<FONT color="green">567</FONT> /**<a name="line.567"></a>
<FONT color="green">568</FONT> * Returns the array element holding the bit value for the<a name="line.568"></a>
<FONT color="green">569</FONT> * given integer<a name="line.569"></a>
<FONT color="green">570</FONT> * @param i the integer that might be in the set of integers<a name="line.570"></a>
<FONT color="green">571</FONT> * <a name="line.571"></a>
<FONT color="green">572</FONT> */<a name="line.572"></a>
<FONT color="green">573</FONT> private static int arrayIndex(int i) {<a name="line.573"></a>
<FONT color="green">574</FONT> return (i &gt;&gt; SHIFT_PER_WORD);<a name="line.574"></a>
<FONT color="green">575</FONT> }<a name="line.575"></a>
<FONT color="green">576</FONT> <a name="line.576"></a>
<FONT color="green">577</FONT> /**<a name="line.577"></a>
<FONT color="green">578</FONT> * For a given integer in the set it returns the single bit<a name="line.578"></a>
<FONT color="green">579</FONT> * value used within a given word that represents whether<a name="line.579"></a>
<FONT color="green">580</FONT> * the integer is in the set or not.<a name="line.580"></a>
<FONT color="green">581</FONT> */<a name="line.581"></a>
<FONT color="green">582</FONT> private static int bit(int i) {<a name="line.582"></a>
<FONT color="green">583</FONT> int ret = (1 &lt;&lt; (i &amp; LOW_ORDER_BITMASK));<a name="line.583"></a>
<FONT color="green">584</FONT> return ret;<a name="line.584"></a>
<FONT color="green">585</FONT> }<a name="line.585"></a>
<FONT color="green">586</FONT> <a name="line.586"></a>
<FONT color="green">587</FONT> /**<a name="line.587"></a>
<FONT color="green">588</FONT> * Creates a new empty set of integers (characters)<a name="line.588"></a>
<FONT color="green">589</FONT> * @param max the maximum integer to be in the set.<a name="line.589"></a>
<FONT color="green">590</FONT> */<a name="line.590"></a>
<FONT color="green">591</FONT> private int[] createEmptySetOfIntegers(int max) {<a name="line.591"></a>
<FONT color="green">592</FONT> firstWordNotUsed = 0; // an optimization <a name="line.592"></a>
<FONT color="green">593</FONT> <a name="line.593"></a>
<FONT color="green">594</FONT> int[] arr = new int[arrayIndex(max - 1) + 1];<a name="line.594"></a>
<FONT color="green">595</FONT> return arr;<a name="line.595"></a>
<FONT color="green">596</FONT> <a name="line.596"></a>
<FONT color="green">597</FONT> }<a name="line.597"></a>
<FONT color="green">598</FONT> <a name="line.598"></a>
<FONT color="green">599</FONT> /**<a name="line.599"></a>
<FONT color="green">600</FONT> * Adds the integer (character) to the set of integers.<a name="line.600"></a>
<FONT color="green">601</FONT> * @param i the integer to add to the set, valid values are <a name="line.601"></a>
<FONT color="green">602</FONT> * 0, 1, 2 ... up to the maximum that was specified at<a name="line.602"></a>
<FONT color="green">603</FONT> * the creation of the set.<a name="line.603"></a>
<FONT color="green">604</FONT> */<a name="line.604"></a>
<FONT color="green">605</FONT> private final void set(int i) { <a name="line.605"></a>
<FONT color="green">606</FONT> setASCIItextDirty(i);<a name="line.606"></a>
<FONT color="green">607</FONT> setASCIIattrDirty(i); <a name="line.607"></a>
<FONT color="green">608</FONT> <a name="line.608"></a>
<FONT color="green">609</FONT> int j = (i &gt;&gt; SHIFT_PER_WORD); // this word is used<a name="line.609"></a>
<FONT color="green">610</FONT> int k = j + 1; <a name="line.610"></a>
<FONT color="green">611</FONT> <a name="line.611"></a>
<FONT color="green">612</FONT> if(firstWordNotUsed &lt; k) // for optimization purposes.<a name="line.612"></a>
<FONT color="green">613</FONT> firstWordNotUsed = k;<a name="line.613"></a>
<FONT color="green">614</FONT> <a name="line.614"></a>
<FONT color="green">615</FONT> array_of_bits[j] |= (1 &lt;&lt; (i &amp; LOW_ORDER_BITMASK));<a name="line.615"></a>
<FONT color="green">616</FONT> }<a name="line.616"></a>
<FONT color="green">617</FONT> <a name="line.617"></a>
<FONT color="green">618</FONT> <a name="line.618"></a>
<FONT color="green">619</FONT> /**<a name="line.619"></a>
<FONT color="green">620</FONT> * Return true if the integer (character)is in the set of integers.<a name="line.620"></a>
<FONT color="green">621</FONT> * <a name="line.621"></a>
<FONT color="green">622</FONT> * This implementation uses an array of integers with 32 bits per<a name="line.622"></a>
<FONT color="green">623</FONT> * integer. If a bit is set to 1 the corresponding integer is <a name="line.623"></a>
<FONT color="green">624</FONT> * in the set of integers.<a name="line.624"></a>
<FONT color="green">625</FONT> * <a name="line.625"></a>
<FONT color="green">626</FONT> * @param i an integer that is tested to see if it is the<a name="line.626"></a>
<FONT color="green">627</FONT> * set of integers, or not.<a name="line.627"></a>
<FONT color="green">628</FONT> */<a name="line.628"></a>
<FONT color="green">629</FONT> private final boolean get(int i) {<a name="line.629"></a>
<FONT color="green">630</FONT> <a name="line.630"></a>
<FONT color="green">631</FONT> boolean in_the_set = false;<a name="line.631"></a>
<FONT color="green">632</FONT> int j = (i &gt;&gt; SHIFT_PER_WORD); // wordIndex(i)<a name="line.632"></a>
<FONT color="green">633</FONT> // an optimization here, ... a quick test to see<a name="line.633"></a>
<FONT color="green">634</FONT> // if this integer is beyond any of the words in use<a name="line.634"></a>
<FONT color="green">635</FONT> if(j &lt; firstWordNotUsed)<a name="line.635"></a>
<FONT color="green">636</FONT> in_the_set = (array_of_bits[j] &amp; <a name="line.636"></a>
<FONT color="green">637</FONT> (1 &lt;&lt; (i &amp; LOW_ORDER_BITMASK))<a name="line.637"></a>
<FONT color="green">638</FONT> ) != 0; // 0L for 64 bit words<a name="line.638"></a>
<FONT color="green">639</FONT> return in_the_set;<a name="line.639"></a>
<FONT color="green">640</FONT> }<a name="line.640"></a>
<FONT color="green">641</FONT> <a name="line.641"></a>
<FONT color="green">642</FONT> /**<a name="line.642"></a>
<FONT color="green">643</FONT> * This method returns true if there are some non-standard mappings to<a name="line.643"></a>
<FONT color="green">644</FONT> * entities other than quot, amp, lt, gt, and its only purpose is for<a name="line.644"></a>
<FONT color="green">645</FONT> * performance.<a name="line.645"></a>
<FONT color="green">646</FONT> * @param charToMap The value of the character that is mapped to a String<a name="line.646"></a>
<FONT color="green">647</FONT> * @param outputString The String to which the character is mapped, usually<a name="line.647"></a>
<FONT color="green">648</FONT> * an entity reference such as "&amp;lt;".<a name="line.648"></a>
<FONT color="green">649</FONT> * @return true if the mapping is not one of:<a name="line.649"></a>
<FONT color="green">650</FONT> * &lt;ul&gt;<a name="line.650"></a>
<FONT color="green">651</FONT> * &lt;li&gt; '&lt;' to "&amp;lt;"<a name="line.651"></a>
<FONT color="green">652</FONT> * &lt;li&gt; '&gt;' to "&amp;gt;"<a name="line.652"></a>
<FONT color="green">653</FONT> * &lt;li&gt; '&amp;' to "&amp;amp;"<a name="line.653"></a>
<FONT color="green">654</FONT> * &lt;li&gt; '"' to "&amp;quot;"<a name="line.654"></a>
<FONT color="green">655</FONT> * &lt;/ul&gt;<a name="line.655"></a>
<FONT color="green">656</FONT> */<a name="line.656"></a>
<FONT color="green">657</FONT> private boolean extraEntity(String outputString, int charToMap)<a name="line.657"></a>
<FONT color="green">658</FONT> {<a name="line.658"></a>
<FONT color="green">659</FONT> boolean extra = false;<a name="line.659"></a>
<FONT color="green">660</FONT> if (charToMap &lt; ASCII_MAX)<a name="line.660"></a>
<FONT color="green">661</FONT> {<a name="line.661"></a>
<FONT color="green">662</FONT> switch (charToMap)<a name="line.662"></a>
<FONT color="green">663</FONT> {<a name="line.663"></a>
<FONT color="green">664</FONT> case '"' : // quot<a name="line.664"></a>
<FONT color="green">665</FONT> if (!outputString.equals("&amp;quot;"))<a name="line.665"></a>
<FONT color="green">666</FONT> extra = true; <a name="line.666"></a>
<FONT color="green">667</FONT> break;<a name="line.667"></a>
<FONT color="green">668</FONT> case '&amp;' : // amp<a name="line.668"></a>
<FONT color="green">669</FONT> if (!outputString.equals("&amp;amp;"))<a name="line.669"></a>
<FONT color="green">670</FONT> extra = true;<a name="line.670"></a>
<FONT color="green">671</FONT> break;<a name="line.671"></a>
<FONT color="green">672</FONT> case '&lt;' : // lt<a name="line.672"></a>
<FONT color="green">673</FONT> if (!outputString.equals("&amp;lt;"))<a name="line.673"></a>
<FONT color="green">674</FONT> extra = true;<a name="line.674"></a>
<FONT color="green">675</FONT> break;<a name="line.675"></a>
<FONT color="green">676</FONT> case '&gt;' : // gt<a name="line.676"></a>
<FONT color="green">677</FONT> if (!outputString.equals("&amp;gt;"))<a name="line.677"></a>
<FONT color="green">678</FONT> extra = true;<a name="line.678"></a>
<FONT color="green">679</FONT> break;<a name="line.679"></a>
<FONT color="green">680</FONT> default : // other entity in range 0 to 127 <a name="line.680"></a>
<FONT color="green">681</FONT> extra = true;<a name="line.681"></a>
<FONT color="green">682</FONT> }<a name="line.682"></a>
<FONT color="green">683</FONT> }<a name="line.683"></a>
<FONT color="green">684</FONT> return extra;<a name="line.684"></a>
<FONT color="green">685</FONT> } <a name="line.685"></a>
<FONT color="green">686</FONT> <a name="line.686"></a>
<FONT color="green">687</FONT> /**<a name="line.687"></a>
<FONT color="green">688</FONT> * If the character is in the ASCII range then<a name="line.688"></a>
<FONT color="green">689</FONT> * mark it as needing replacement with<a name="line.689"></a>
<FONT color="green">690</FONT> * a String on output if it occurs in a text node.<a name="line.690"></a>
<FONT color="green">691</FONT> * @param ch<a name="line.691"></a>
<FONT color="green">692</FONT> */<a name="line.692"></a>
<FONT color="green">693</FONT> private void setASCIItextDirty(int j) <a name="line.693"></a>
<FONT color="green">694</FONT> {<a name="line.694"></a>
<FONT color="green">695</FONT> if (0 &lt;= j &amp;&amp; j &lt; ASCII_MAX) <a name="line.695"></a>
<FONT color="green">696</FONT> {<a name="line.696"></a>
<FONT color="green">697</FONT> shouldMapTextChar_ASCII[j] = true;<a name="line.697"></a>
<FONT color="green">698</FONT> } <a name="line.698"></a>
<FONT color="green">699</FONT> }<a name="line.699"></a>
<FONT color="green">700</FONT> <a name="line.700"></a>
<FONT color="green">701</FONT> /**<a name="line.701"></a>
<FONT color="green">702</FONT> * If the character is in the ASCII range then<a name="line.702"></a>
<FONT color="green">703</FONT> * mark it as needing replacement with<a name="line.703"></a>
<FONT color="green">704</FONT> * a String on output if it occurs in a attribute value.<a name="line.704"></a>
<FONT color="green">705</FONT> * @param ch<a name="line.705"></a>
<FONT color="green">706</FONT> */<a name="line.706"></a>
<FONT color="green">707</FONT> private void setASCIIattrDirty(int j) <a name="line.707"></a>
<FONT color="green">708</FONT> {<a name="line.708"></a>
<FONT color="green">709</FONT> if (0 &lt;= j &amp;&amp; j &lt; ASCII_MAX) <a name="line.709"></a>
<FONT color="green">710</FONT> {<a name="line.710"></a>
<FONT color="green">711</FONT> shouldMapAttrChar_ASCII[j] = true;<a name="line.711"></a>
<FONT color="green">712</FONT> } <a name="line.712"></a>
<FONT color="green">713</FONT> }<a name="line.713"></a>
<FONT color="green">714</FONT> <a name="line.714"></a>
<FONT color="green">715</FONT> <a name="line.715"></a>
<FONT color="green">716</FONT> /**<a name="line.716"></a>
<FONT color="green">717</FONT> * Call this method to register a char to String mapping, for example<a name="line.717"></a>
<FONT color="green">718</FONT> * to map '&lt;' to "&amp;lt;".<a name="line.718"></a>
<FONT color="green">719</FONT> * @param outputString The String to map to.<a name="line.719"></a>
<FONT color="green">720</FONT> * @param inputChar The char to map from.<a name="line.720"></a>
<FONT color="green">721</FONT> * @return true if the mapping is not one of:<a name="line.721"></a>
<FONT color="green">722</FONT> * &lt;ul&gt;<a name="line.722"></a>
<FONT color="green">723</FONT> * &lt;li&gt; '&lt;' to "&amp;lt;"<a name="line.723"></a>
<FONT color="green">724</FONT> * &lt;li&gt; '&gt;' to "&amp;gt;"<a name="line.724"></a>
<FONT color="green">725</FONT> * &lt;li&gt; '&amp;' to "&amp;amp;"<a name="line.725"></a>
<FONT color="green">726</FONT> * &lt;li&gt; '"' to "&amp;quot;"<a name="line.726"></a>
<FONT color="green">727</FONT> * &lt;/ul&gt;<a name="line.727"></a>
<FONT color="green">728</FONT> */<a name="line.728"></a>
<FONT color="green">729</FONT> boolean defineChar2StringMapping(String outputString, char inputChar) <a name="line.729"></a>
<FONT color="green">730</FONT> {<a name="line.730"></a>
<FONT color="green">731</FONT> CharKey character = new CharKey(inputChar);<a name="line.731"></a>
<FONT color="green">732</FONT> m_charToString.put(character, outputString);<a name="line.732"></a>
<FONT color="green">733</FONT> set(inputChar); // mark the character has having a mapping to a String<a name="line.733"></a>
<FONT color="green">734</FONT> <a name="line.734"></a>
<FONT color="green">735</FONT> boolean extraMapping = extraEntity(outputString, inputChar);<a name="line.735"></a>
<FONT color="green">736</FONT> return extraMapping;<a name="line.736"></a>
<FONT color="green">737</FONT> <a name="line.737"></a>
<FONT color="green">738</FONT> }<a name="line.738"></a>
<FONT color="green">739</FONT> <a name="line.739"></a>
<FONT color="green">740</FONT> /**<a name="line.740"></a>
<FONT color="green">741</FONT> * Simple class for fast lookup of char values, when used with<a name="line.741"></a>
<FONT color="green">742</FONT> * hashtables. You can set the char, then use it as a key.<a name="line.742"></a>
<FONT color="green">743</FONT> * <a name="line.743"></a>
<FONT color="green">744</FONT> * @xsl.usage internal<a name="line.744"></a>
<FONT color="green">745</FONT> */<a name="line.745"></a>
<FONT color="green">746</FONT> private static class CharKey extends Object<a name="line.746"></a>
<FONT color="green">747</FONT> {<a name="line.747"></a>
<FONT color="green">748</FONT> <a name="line.748"></a>
<FONT color="green">749</FONT> /** String value */<a name="line.749"></a>
<FONT color="green">750</FONT> private char m_char;<a name="line.750"></a>
<FONT color="green">751</FONT> <a name="line.751"></a>
<FONT color="green">752</FONT> /**<a name="line.752"></a>
<FONT color="green">753</FONT> * Constructor CharKey<a name="line.753"></a>
<FONT color="green">754</FONT> *<a name="line.754"></a>
<FONT color="green">755</FONT> * @param key char value of this object.<a name="line.755"></a>
<FONT color="green">756</FONT> */<a name="line.756"></a>
<FONT color="green">757</FONT> public CharKey(char key)<a name="line.757"></a>
<FONT color="green">758</FONT> {<a name="line.758"></a>
<FONT color="green">759</FONT> m_char = key;<a name="line.759"></a>
<FONT color="green">760</FONT> }<a name="line.760"></a>
<FONT color="green">761</FONT> <a name="line.761"></a>
<FONT color="green">762</FONT> /**<a name="line.762"></a>
<FONT color="green">763</FONT> * Default constructor for a CharKey.<a name="line.763"></a>
<FONT color="green">764</FONT> *<a name="line.764"></a>
<FONT color="green">765</FONT> * @param key char value of this object.<a name="line.765"></a>
<FONT color="green">766</FONT> */<a name="line.766"></a>
<FONT color="green">767</FONT> public CharKey()<a name="line.767"></a>
<FONT color="green">768</FONT> {<a name="line.768"></a>
<FONT color="green">769</FONT> }<a name="line.769"></a>
<FONT color="green">770</FONT> <a name="line.770"></a>
<FONT color="green">771</FONT> /**<a name="line.771"></a>
<FONT color="green">772</FONT> * Get the hash value of the character. <a name="line.772"></a>
<FONT color="green">773</FONT> *<a name="line.773"></a>
<FONT color="green">774</FONT> * @return hash value of the character.<a name="line.774"></a>
<FONT color="green">775</FONT> */<a name="line.775"></a>
<FONT color="green">776</FONT> public final void setChar(char c)<a name="line.776"></a>
<FONT color="green">777</FONT> {<a name="line.777"></a>
<FONT color="green">778</FONT> m_char = c;<a name="line.778"></a>
<FONT color="green">779</FONT> }<a name="line.779"></a>
<FONT color="green">780</FONT> <a name="line.780"></a>
<FONT color="green">781</FONT> <a name="line.781"></a>
<FONT color="green">782</FONT> <a name="line.782"></a>
<FONT color="green">783</FONT> /**<a name="line.783"></a>
<FONT color="green">784</FONT> * Get the hash value of the character. <a name="line.784"></a>
<FONT color="green">785</FONT> *<a name="line.785"></a>
<FONT color="green">786</FONT> * @return hash value of the character.<a name="line.786"></a>
<FONT color="green">787</FONT> */<a name="line.787"></a>
<FONT color="green">788</FONT> public final int hashCode()<a name="line.788"></a>
<FONT color="green">789</FONT> {<a name="line.789"></a>
<FONT color="green">790</FONT> return (int)m_char;<a name="line.790"></a>
<FONT color="green">791</FONT> }<a name="line.791"></a>
<FONT color="green">792</FONT> <a name="line.792"></a>
<FONT color="green">793</FONT> /**<a name="line.793"></a>
<FONT color="green">794</FONT> * Override of equals() for this object <a name="line.794"></a>
<FONT color="green">795</FONT> *<a name="line.795"></a>
<FONT color="green">796</FONT> * @param obj to compare to<a name="line.796"></a>
<FONT color="green">797</FONT> *<a name="line.797"></a>
<FONT color="green">798</FONT> * @return True if this object equals this string value <a name="line.798"></a>
<FONT color="green">799</FONT> */<a name="line.799"></a>
<FONT color="green">800</FONT> public final boolean equals(Object obj)<a name="line.800"></a>
<FONT color="green">801</FONT> {<a name="line.801"></a>
<FONT color="green">802</FONT> return ((CharKey)obj).m_char == m_char;<a name="line.802"></a>
<FONT color="green">803</FONT> }<a name="line.803"></a>
<FONT color="green">804</FONT> }<a name="line.804"></a>
<FONT color="green">805</FONT> <a name="line.805"></a>
<FONT color="green">806</FONT> <a name="line.806"></a>
<FONT color="green">807</FONT> }<a name="line.807"></a>
</PRE>
</BODY>
</HTML>