blob: ef0f808310b8ffbcc6333583a352f7fa9990b990 [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: Encodings.java 1225414 2011-12-29 02:38:30Z mrglavas $<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.InputStream;<a name="line.23"></a>
<FONT color="green">024</FONT> import java.io.OutputStream;<a name="line.24"></a>
<FONT color="green">025</FONT> import java.io.OutputStreamWriter;<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.io.Writer;<a name="line.27"></a>
<FONT color="green">028</FONT> import java.util.ArrayList;<a name="line.28"></a>
<FONT color="green">029</FONT> import java.util.Enumeration;<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.List;<a name="line.31"></a>
<FONT color="green">032</FONT> import java.util.Properties;<a name="line.32"></a>
<FONT color="green">033</FONT> import java.util.StringTokenizer;<a name="line.33"></a>
<FONT color="green">034</FONT> <a name="line.34"></a>
<FONT color="green">035</FONT> <a name="line.35"></a>
<FONT color="green">036</FONT> /**<a name="line.36"></a>
<FONT color="green">037</FONT> * Provides information about encodings. Depends on the Java runtime<a name="line.37"></a>
<FONT color="green">038</FONT> * to provides writers for the different encodings.<a name="line.38"></a>
<FONT color="green">039</FONT> * &lt;p&gt;<a name="line.39"></a>
<FONT color="green">040</FONT> * This class is not a public API. It is only public because it<a name="line.40"></a>
<FONT color="green">041</FONT> * is used outside of this package.<a name="line.41"></a>
<FONT color="green">042</FONT> * <a name="line.42"></a>
<FONT color="green">043</FONT> * @xsl.usage internal<a name="line.43"></a>
<FONT color="green">044</FONT> */<a name="line.44"></a>
<FONT color="green">045</FONT> <a name="line.45"></a>
<FONT color="green">046</FONT> public final class Encodings extends Object<a name="line.46"></a>
<FONT color="green">047</FONT> {<a name="line.47"></a>
<FONT color="green">048</FONT> /**<a name="line.48"></a>
<FONT color="green">049</FONT> * Standard filename for properties file with encodings data.<a name="line.49"></a>
<FONT color="green">050</FONT> */<a name="line.50"></a>
<FONT color="green">051</FONT> private static final String ENCODINGS_FILE = SerializerBase.PKG_PATH+"/Encodings.properties";<a name="line.51"></a>
<FONT color="green">052</FONT> <a name="line.52"></a>
<FONT color="green">053</FONT> /**<a name="line.53"></a>
<FONT color="green">054</FONT> * Returns a writer for the specified encoding based on<a name="line.54"></a>
<FONT color="green">055</FONT> * an output stream.<a name="line.55"></a>
<FONT color="green">056</FONT> * &lt;p&gt;<a name="line.56"></a>
<FONT color="green">057</FONT> * This is not a public API.<a name="line.57"></a>
<FONT color="green">058</FONT> * @param output The output stream<a name="line.58"></a>
<FONT color="green">059</FONT> * @param encoding The encoding MIME name, not a Java name for the encoding.<a name="line.59"></a>
<FONT color="green">060</FONT> * @return A suitable writer<a name="line.60"></a>
<FONT color="green">061</FONT> * @throws UnsupportedEncodingException There is no convertor<a name="line.61"></a>
<FONT color="green">062</FONT> * to support this encoding<a name="line.62"></a>
<FONT color="green">063</FONT> * @xsl.usage internal<a name="line.63"></a>
<FONT color="green">064</FONT> */<a name="line.64"></a>
<FONT color="green">065</FONT> static Writer getWriter(OutputStream output, String encoding)<a name="line.65"></a>
<FONT color="green">066</FONT> throws UnsupportedEncodingException<a name="line.66"></a>
<FONT color="green">067</FONT> {<a name="line.67"></a>
<FONT color="green">068</FONT> <a name="line.68"></a>
<FONT color="green">069</FONT> for (int i = 0; i &lt; _encodings.length; ++i)<a name="line.69"></a>
<FONT color="green">070</FONT> {<a name="line.70"></a>
<FONT color="green">071</FONT> if (_encodings[i].name.equalsIgnoreCase(encoding))<a name="line.71"></a>
<FONT color="green">072</FONT> {<a name="line.72"></a>
<FONT color="green">073</FONT> try<a name="line.73"></a>
<FONT color="green">074</FONT> {<a name="line.74"></a>
<FONT color="green">075</FONT> String javaName = _encodings[i].javaName;<a name="line.75"></a>
<FONT color="green">076</FONT> OutputStreamWriter osw = new OutputStreamWriter(output,javaName);<a name="line.76"></a>
<FONT color="green">077</FONT> return osw; <a name="line.77"></a>
<FONT color="green">078</FONT> }<a name="line.78"></a>
<FONT color="green">079</FONT> catch (java.lang.IllegalArgumentException iae) // java 1.1.8<a name="line.79"></a>
<FONT color="green">080</FONT> {<a name="line.80"></a>
<FONT color="green">081</FONT> // keep trying<a name="line.81"></a>
<FONT color="green">082</FONT> }<a name="line.82"></a>
<FONT color="green">083</FONT> catch (UnsupportedEncodingException usee)<a name="line.83"></a>
<FONT color="green">084</FONT> {<a name="line.84"></a>
<FONT color="green">085</FONT> <a name="line.85"></a>
<FONT color="green">086</FONT> // keep trying<a name="line.86"></a>
<FONT color="green">087</FONT> }<a name="line.87"></a>
<FONT color="green">088</FONT> }<a name="line.88"></a>
<FONT color="green">089</FONT> }<a name="line.89"></a>
<FONT color="green">090</FONT> <a name="line.90"></a>
<FONT color="green">091</FONT> try<a name="line.91"></a>
<FONT color="green">092</FONT> {<a name="line.92"></a>
<FONT color="green">093</FONT> return new OutputStreamWriter(output, encoding);<a name="line.93"></a>
<FONT color="green">094</FONT> }<a name="line.94"></a>
<FONT color="green">095</FONT> catch (java.lang.IllegalArgumentException iae) // java 1.1.8<a name="line.95"></a>
<FONT color="green">096</FONT> {<a name="line.96"></a>
<FONT color="green">097</FONT> throw new UnsupportedEncodingException(encoding);<a name="line.97"></a>
<FONT color="green">098</FONT> }<a name="line.98"></a>
<FONT color="green">099</FONT> }<a name="line.99"></a>
<FONT color="green">100</FONT> <a name="line.100"></a>
<FONT color="green">101</FONT> /**<a name="line.101"></a>
<FONT color="green">102</FONT> * Returns the EncodingInfo object for the specified<a name="line.102"></a>
<FONT color="green">103</FONT> * encoding, never null, although the encoding name <a name="line.103"></a>
<FONT color="green">104</FONT> * inside the returned EncodingInfo object will be if<a name="line.104"></a>
<FONT color="green">105</FONT> * we can't find a "real" EncodingInfo for the encoding.<a name="line.105"></a>
<FONT color="green">106</FONT> * &lt;p&gt;<a name="line.106"></a>
<FONT color="green">107</FONT> * This is not a public API.<a name="line.107"></a>
<FONT color="green">108</FONT> *<a name="line.108"></a>
<FONT color="green">109</FONT> * @param encoding The encoding<a name="line.109"></a>
<FONT color="green">110</FONT> * @return The object that is used to determine if <a name="line.110"></a>
<FONT color="green">111</FONT> * characters are in the given encoding.<a name="line.111"></a>
<FONT color="green">112</FONT> * @xsl.usage internal<a name="line.112"></a>
<FONT color="green">113</FONT> */<a name="line.113"></a>
<FONT color="green">114</FONT> static EncodingInfo getEncodingInfo(String encoding)<a name="line.114"></a>
<FONT color="green">115</FONT> {<a name="line.115"></a>
<FONT color="green">116</FONT> EncodingInfo ei;<a name="line.116"></a>
<FONT color="green">117</FONT> <a name="line.117"></a>
<FONT color="green">118</FONT> String normalizedEncoding = toUpperCaseFast(encoding);<a name="line.118"></a>
<FONT color="green">119</FONT> ei = (EncodingInfo) _encodingTableKeyJava.get(normalizedEncoding);<a name="line.119"></a>
<FONT color="green">120</FONT> if (ei == null)<a name="line.120"></a>
<FONT color="green">121</FONT> ei = (EncodingInfo) _encodingTableKeyMime.get(normalizedEncoding);<a name="line.121"></a>
<FONT color="green">122</FONT> if (ei == null) {<a name="line.122"></a>
<FONT color="green">123</FONT> // We shouldn't have to do this, but just in case.<a name="line.123"></a>
<FONT color="green">124</FONT> ei = new EncodingInfo(null,null, '\u0000');<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> return ei;<a name="line.127"></a>
<FONT color="green">128</FONT> }<a name="line.128"></a>
<FONT color="green">129</FONT> <a name="line.129"></a>
<FONT color="green">130</FONT> /**<a name="line.130"></a>
<FONT color="green">131</FONT> * Determines if the encoding specified was recognized by the<a name="line.131"></a>
<FONT color="green">132</FONT> * serializer or not.<a name="line.132"></a>
<FONT color="green">133</FONT> *<a name="line.133"></a>
<FONT color="green">134</FONT> * @param encoding The encoding<a name="line.134"></a>
<FONT color="green">135</FONT> * @return boolean - true if the encoding was recognized else false<a name="line.135"></a>
<FONT color="green">136</FONT> */<a name="line.136"></a>
<FONT color="green">137</FONT> public static boolean isRecognizedEncoding(String encoding)<a name="line.137"></a>
<FONT color="green">138</FONT> {<a name="line.138"></a>
<FONT color="green">139</FONT> EncodingInfo ei;<a name="line.139"></a>
<FONT color="green">140</FONT> <a name="line.140"></a>
<FONT color="green">141</FONT> String normalizedEncoding = encoding.toUpperCase();<a name="line.141"></a>
<FONT color="green">142</FONT> ei = (EncodingInfo) _encodingTableKeyJava.get(normalizedEncoding);<a name="line.142"></a>
<FONT color="green">143</FONT> if (ei == null)<a name="line.143"></a>
<FONT color="green">144</FONT> ei = (EncodingInfo) _encodingTableKeyMime.get(normalizedEncoding);<a name="line.144"></a>
<FONT color="green">145</FONT> if (ei != null)<a name="line.145"></a>
<FONT color="green">146</FONT> return true;<a name="line.146"></a>
<FONT color="green">147</FONT> return false;<a name="line.147"></a>
<FONT color="green">148</FONT> }<a name="line.148"></a>
<FONT color="green">149</FONT> <a name="line.149"></a>
<FONT color="green">150</FONT> /**<a name="line.150"></a>
<FONT color="green">151</FONT> * A fast and cheap way to uppercase a String that is<a name="line.151"></a>
<FONT color="green">152</FONT> * only made of printable ASCII characters.<a name="line.152"></a>
<FONT color="green">153</FONT> * &lt;p&gt;<a name="line.153"></a>
<FONT color="green">154</FONT> * This is not a public API.<a name="line.154"></a>
<FONT color="green">155</FONT> * @param s a String of ASCII characters<a name="line.155"></a>
<FONT color="green">156</FONT> * @return an uppercased version of the input String,<a name="line.156"></a>
<FONT color="green">157</FONT> * possibly the same String.<a name="line.157"></a>
<FONT color="green">158</FONT> * @xsl.usage internal<a name="line.158"></a>
<FONT color="green">159</FONT> */<a name="line.159"></a>
<FONT color="green">160</FONT> static private String toUpperCaseFast(final String s) {<a name="line.160"></a>
<FONT color="green">161</FONT> <a name="line.161"></a>
<FONT color="green">162</FONT> boolean different = false;<a name="line.162"></a>
<FONT color="green">163</FONT> final int mx = s.length();<a name="line.163"></a>
<FONT color="green">164</FONT> char[] chars = new char[mx];<a name="line.164"></a>
<FONT color="green">165</FONT> for (int i=0; i &lt; mx; i++) {<a name="line.165"></a>
<FONT color="green">166</FONT> char ch = s.charAt(i);<a name="line.166"></a>
<FONT color="green">167</FONT> // is the character a lower case ASCII one?<a name="line.167"></a>
<FONT color="green">168</FONT> if ('a' &lt;= ch &amp;&amp; ch &lt;= 'z') {<a name="line.168"></a>
<FONT color="green">169</FONT> // a cheap and fast way to uppercase that is good enough<a name="line.169"></a>
<FONT color="green">170</FONT> ch = (char) (ch + ('A' - 'a'));<a name="line.170"></a>
<FONT color="green">171</FONT> different = true; // the uppercased String is different<a name="line.171"></a>
<FONT color="green">172</FONT> }<a name="line.172"></a>
<FONT color="green">173</FONT> chars[i] = ch;<a name="line.173"></a>
<FONT color="green">174</FONT> }<a name="line.174"></a>
<FONT color="green">175</FONT> <a name="line.175"></a>
<FONT color="green">176</FONT> // A little optimization, don't call String.valueOf() if<a name="line.176"></a>
<FONT color="green">177</FONT> // the uppercased string is the same as the input string.<a name="line.177"></a>
<FONT color="green">178</FONT> final String upper;<a name="line.178"></a>
<FONT color="green">179</FONT> if (different) <a name="line.179"></a>
<FONT color="green">180</FONT> upper = String.valueOf(chars);<a name="line.180"></a>
<FONT color="green">181</FONT> else<a name="line.181"></a>
<FONT color="green">182</FONT> upper = s;<a name="line.182"></a>
<FONT color="green">183</FONT> <a name="line.183"></a>
<FONT color="green">184</FONT> return upper;<a name="line.184"></a>
<FONT color="green">185</FONT> }<a name="line.185"></a>
<FONT color="green">186</FONT> <a name="line.186"></a>
<FONT color="green">187</FONT> /** The default encoding, ISO style, ISO style. */<a name="line.187"></a>
<FONT color="green">188</FONT> static final String DEFAULT_MIME_ENCODING = "UTF-8";<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> * Get the proper mime encoding. From the XSLT recommendation: "The encoding<a name="line.191"></a>
<FONT color="green">192</FONT> * attribute specifies the preferred encoding to use for outputting the result<a name="line.192"></a>
<FONT color="green">193</FONT> * tree. XSLT processors are required to respect values of UTF-8 and UTF-16.<a name="line.193"></a>
<FONT color="green">194</FONT> * For other values, if the XSLT processor does not support the specified<a name="line.194"></a>
<FONT color="green">195</FONT> * encoding it may signal an error; if it does not signal an error it should<a name="line.195"></a>
<FONT color="green">196</FONT> * use UTF-8 or UTF-16 instead. The XSLT processor must not use an encoding<a name="line.196"></a>
<FONT color="green">197</FONT> * whose name does not match the EncName production of the XML Recommendation<a name="line.197"></a>
<FONT color="green">198</FONT> * [XML]. If no encoding attribute is specified, then the XSLT processor should<a name="line.198"></a>
<FONT color="green">199</FONT> * use either UTF-8 or UTF-16."<a name="line.199"></a>
<FONT color="green">200</FONT> * &lt;p&gt;<a name="line.200"></a>
<FONT color="green">201</FONT> * This is not a public API.<a name="line.201"></a>
<FONT color="green">202</FONT> *<a name="line.202"></a>
<FONT color="green">203</FONT> * @param encoding Reference to java-style encoding string, which may be null,<a name="line.203"></a>
<FONT color="green">204</FONT> * in which case a default will be found.<a name="line.204"></a>
<FONT color="green">205</FONT> *<a name="line.205"></a>
<FONT color="green">206</FONT> * @return The ISO-style encoding string, or null if failure.<a name="line.206"></a>
<FONT color="green">207</FONT> * @xsl.usage internal<a name="line.207"></a>
<FONT color="green">208</FONT> */<a name="line.208"></a>
<FONT color="green">209</FONT> static String getMimeEncoding(String encoding)<a name="line.209"></a>
<FONT color="green">210</FONT> {<a name="line.210"></a>
<FONT color="green">211</FONT> <a name="line.211"></a>
<FONT color="green">212</FONT> if (null == encoding)<a name="line.212"></a>
<FONT color="green">213</FONT> {<a name="line.213"></a>
<FONT color="green">214</FONT> try<a name="line.214"></a>
<FONT color="green">215</FONT> {<a name="line.215"></a>
<FONT color="green">216</FONT> <a name="line.216"></a>
<FONT color="green">217</FONT> // Get the default system character encoding. This may be<a name="line.217"></a>
<FONT color="green">218</FONT> // incorrect if they passed in a writer, but right now there<a name="line.218"></a>
<FONT color="green">219</FONT> // seems to be no way to get the encoding from a writer.<a name="line.219"></a>
<FONT color="green">220</FONT> encoding = System.getProperty("file.encoding", "UTF8");<a name="line.220"></a>
<FONT color="green">221</FONT> <a name="line.221"></a>
<FONT color="green">222</FONT> if (null != encoding)<a name="line.222"></a>
<FONT color="green">223</FONT> {<a name="line.223"></a>
<FONT color="green">224</FONT> <a name="line.224"></a>
<FONT color="green">225</FONT> /*<a name="line.225"></a>
<FONT color="green">226</FONT> * See if the mime type is equal to UTF8. If you don't<a name="line.226"></a>
<FONT color="green">227</FONT> * do that, then convertJava2MimeEncoding will convert<a name="line.227"></a>
<FONT color="green">228</FONT> * 8859_1 to "ISO-8859-1", which is not what we want,<a name="line.228"></a>
<FONT color="green">229</FONT> * I think, and I don't think I want to alter the tables<a name="line.229"></a>
<FONT color="green">230</FONT> * to convert everything to UTF-8.<a name="line.230"></a>
<FONT color="green">231</FONT> */<a name="line.231"></a>
<FONT color="green">232</FONT> String jencoding =<a name="line.232"></a>
<FONT color="green">233</FONT> (encoding.equalsIgnoreCase("Cp1252")<a name="line.233"></a>
<FONT color="green">234</FONT> || encoding.equalsIgnoreCase("ISO8859_1")<a name="line.234"></a>
<FONT color="green">235</FONT> || encoding.equalsIgnoreCase("8859_1")<a name="line.235"></a>
<FONT color="green">236</FONT> || encoding.equalsIgnoreCase("UTF8"))<a name="line.236"></a>
<FONT color="green">237</FONT> ? DEFAULT_MIME_ENCODING<a name="line.237"></a>
<FONT color="green">238</FONT> : convertJava2MimeEncoding(encoding);<a name="line.238"></a>
<FONT color="green">239</FONT> <a name="line.239"></a>
<FONT color="green">240</FONT> encoding =<a name="line.240"></a>
<FONT color="green">241</FONT> (null != jencoding) ? jencoding : DEFAULT_MIME_ENCODING;<a name="line.241"></a>
<FONT color="green">242</FONT> }<a name="line.242"></a>
<FONT color="green">243</FONT> else<a name="line.243"></a>
<FONT color="green">244</FONT> {<a name="line.244"></a>
<FONT color="green">245</FONT> encoding = DEFAULT_MIME_ENCODING;<a name="line.245"></a>
<FONT color="green">246</FONT> }<a name="line.246"></a>
<FONT color="green">247</FONT> }<a name="line.247"></a>
<FONT color="green">248</FONT> catch (SecurityException se)<a name="line.248"></a>
<FONT color="green">249</FONT> {<a name="line.249"></a>
<FONT color="green">250</FONT> encoding = DEFAULT_MIME_ENCODING;<a name="line.250"></a>
<FONT color="green">251</FONT> }<a name="line.251"></a>
<FONT color="green">252</FONT> }<a name="line.252"></a>
<FONT color="green">253</FONT> else<a name="line.253"></a>
<FONT color="green">254</FONT> {<a name="line.254"></a>
<FONT color="green">255</FONT> encoding = convertJava2MimeEncoding(encoding);<a name="line.255"></a>
<FONT color="green">256</FONT> }<a name="line.256"></a>
<FONT color="green">257</FONT> <a name="line.257"></a>
<FONT color="green">258</FONT> return encoding;<a name="line.258"></a>
<FONT color="green">259</FONT> }<a name="line.259"></a>
<FONT color="green">260</FONT> <a name="line.260"></a>
<FONT color="green">261</FONT> /**<a name="line.261"></a>
<FONT color="green">262</FONT> * Try the best we can to convert a Java encoding to a XML-style encoding.<a name="line.262"></a>
<FONT color="green">263</FONT> * &lt;p&gt;<a name="line.263"></a>
<FONT color="green">264</FONT> * This is not a public API.<a name="line.264"></a>
<FONT color="green">265</FONT> * @param encoding non-null reference to encoding string, java style.<a name="line.265"></a>
<FONT color="green">266</FONT> *<a name="line.266"></a>
<FONT color="green">267</FONT> * @return ISO-style encoding string.<a name="line.267"></a>
<FONT color="green">268</FONT> * @xsl.usage internal<a name="line.268"></a>
<FONT color="green">269</FONT> */<a name="line.269"></a>
<FONT color="green">270</FONT> private static String convertJava2MimeEncoding(String encoding)<a name="line.270"></a>
<FONT color="green">271</FONT> {<a name="line.271"></a>
<FONT color="green">272</FONT> EncodingInfo enc =<a name="line.272"></a>
<FONT color="green">273</FONT> (EncodingInfo) _encodingTableKeyJava.get(toUpperCaseFast(encoding));<a name="line.273"></a>
<FONT color="green">274</FONT> if (null != enc)<a name="line.274"></a>
<FONT color="green">275</FONT> return enc.name;<a name="line.275"></a>
<FONT color="green">276</FONT> return encoding;<a name="line.276"></a>
<FONT color="green">277</FONT> }<a name="line.277"></a>
<FONT color="green">278</FONT> <a name="line.278"></a>
<FONT color="green">279</FONT> /**<a name="line.279"></a>
<FONT color="green">280</FONT> * Try the best we can to convert a Java encoding to a XML-style encoding.<a name="line.280"></a>
<FONT color="green">281</FONT> * &lt;p&gt;<a name="line.281"></a>
<FONT color="green">282</FONT> * This is not a public API.<a name="line.282"></a>
<FONT color="green">283</FONT> *<a name="line.283"></a>
<FONT color="green">284</FONT> * @param encoding non-null reference to encoding string, java style.<a name="line.284"></a>
<FONT color="green">285</FONT> *<a name="line.285"></a>
<FONT color="green">286</FONT> * @return ISO-style encoding string.<a name="line.286"></a>
<FONT color="green">287</FONT> * &lt;p&gt;<a name="line.287"></a>
<FONT color="green">288</FONT> * This method is not a public API.<a name="line.288"></a>
<FONT color="green">289</FONT> * @xsl.usage internal<a name="line.289"></a>
<FONT color="green">290</FONT> */<a name="line.290"></a>
<FONT color="green">291</FONT> public static String convertMime2JavaEncoding(String encoding)<a name="line.291"></a>
<FONT color="green">292</FONT> {<a name="line.292"></a>
<FONT color="green">293</FONT> <a name="line.293"></a>
<FONT color="green">294</FONT> for (int i = 0; i &lt; _encodings.length; ++i)<a name="line.294"></a>
<FONT color="green">295</FONT> {<a name="line.295"></a>
<FONT color="green">296</FONT> if (_encodings[i].name.equalsIgnoreCase(encoding))<a name="line.296"></a>
<FONT color="green">297</FONT> {<a name="line.297"></a>
<FONT color="green">298</FONT> return _encodings[i].javaName;<a name="line.298"></a>
<FONT color="green">299</FONT> }<a name="line.299"></a>
<FONT color="green">300</FONT> }<a name="line.300"></a>
<FONT color="green">301</FONT> <a name="line.301"></a>
<FONT color="green">302</FONT> return encoding;<a name="line.302"></a>
<FONT color="green">303</FONT> }<a name="line.303"></a>
<FONT color="green">304</FONT> <a name="line.304"></a>
<FONT color="green">305</FONT> /**<a name="line.305"></a>
<FONT color="green">306</FONT> * Load a list of all the supported encodings.<a name="line.306"></a>
<FONT color="green">307</FONT> *<a name="line.307"></a>
<FONT color="green">308</FONT> * System property "encodings" formatted using URL syntax may define an<a name="line.308"></a>
<FONT color="green">309</FONT> * external encodings list. Thanks to Sergey Ushakov for the code<a name="line.309"></a>
<FONT color="green">310</FONT> * contribution!<a name="line.310"></a>
<FONT color="green">311</FONT> * @xsl.usage internal<a name="line.311"></a>
<FONT color="green">312</FONT> */<a name="line.312"></a>
<FONT color="green">313</FONT> private static EncodingInfo[] loadEncodingInfo()<a name="line.313"></a>
<FONT color="green">314</FONT> {<a name="line.314"></a>
<FONT color="green">315</FONT> try<a name="line.315"></a>
<FONT color="green">316</FONT> {<a name="line.316"></a>
<FONT color="green">317</FONT> final InputStream is;<a name="line.317"></a>
<FONT color="green">318</FONT> is = SecuritySupport.getResourceAsStream(ObjectFactory.findClassLoader(),<a name="line.318"></a>
<FONT color="green">319</FONT> ENCODINGS_FILE);<a name="line.319"></a>
<FONT color="green">320</FONT> <a name="line.320"></a>
<FONT color="green">321</FONT> Properties props = new Properties();<a name="line.321"></a>
<FONT color="green">322</FONT> if (is != null) {<a name="line.322"></a>
<FONT color="green">323</FONT> props.load(is);<a name="line.323"></a>
<FONT color="green">324</FONT> is.close();<a name="line.324"></a>
<FONT color="green">325</FONT> } else {<a name="line.325"></a>
<FONT color="green">326</FONT> // Seems to be no real need to force failure here, let the<a name="line.326"></a>
<FONT color="green">327</FONT> // system do its best... The issue is not really very critical,<a name="line.327"></a>
<FONT color="green">328</FONT> // and the output will be in any case _correct_ though maybe not<a name="line.328"></a>
<FONT color="green">329</FONT> // always human-friendly... :)<a name="line.329"></a>
<FONT color="green">330</FONT> // But maybe report/log the resource problem?<a name="line.330"></a>
<FONT color="green">331</FONT> // Any standard ways to report/log errors (in static context)?<a name="line.331"></a>
<FONT color="green">332</FONT> }<a name="line.332"></a>
<FONT color="green">333</FONT> <a name="line.333"></a>
<FONT color="green">334</FONT> int totalEntries = props.size();<a name="line.334"></a>
<FONT color="green">335</FONT> <a name="line.335"></a>
<FONT color="green">336</FONT> List encodingInfo_list = new ArrayList();<a name="line.336"></a>
<FONT color="green">337</FONT> Enumeration keys = props.keys();<a name="line.337"></a>
<FONT color="green">338</FONT> for (int i = 0; i &lt; totalEntries; ++i)<a name="line.338"></a>
<FONT color="green">339</FONT> {<a name="line.339"></a>
<FONT color="green">340</FONT> String javaName = (String) keys.nextElement();<a name="line.340"></a>
<FONT color="green">341</FONT> String val = props.getProperty(javaName);<a name="line.341"></a>
<FONT color="green">342</FONT> int len = lengthOfMimeNames(val);<a name="line.342"></a>
<FONT color="green">343</FONT> <a name="line.343"></a>
<FONT color="green">344</FONT> String mimeName;<a name="line.344"></a>
<FONT color="green">345</FONT> char highChar;<a name="line.345"></a>
<FONT color="green">346</FONT> if (len == 0)<a name="line.346"></a>
<FONT color="green">347</FONT> {<a name="line.347"></a>
<FONT color="green">348</FONT> // There is no property value, only the javaName, so try and recover<a name="line.348"></a>
<FONT color="green">349</FONT> mimeName = javaName;<a name="line.349"></a>
<FONT color="green">350</FONT> highChar = '\u0000'; // don't know the high code point, will need to test every character<a name="line.350"></a>
<FONT color="green">351</FONT> }<a name="line.351"></a>
<FONT color="green">352</FONT> else<a name="line.352"></a>
<FONT color="green">353</FONT> {<a name="line.353"></a>
<FONT color="green">354</FONT> try {<a name="line.354"></a>
<FONT color="green">355</FONT> // Get the substring after the Mime names<a name="line.355"></a>
<FONT color="green">356</FONT> final String highVal = val.substring(len).trim();<a name="line.356"></a>
<FONT color="green">357</FONT> highChar = (char) Integer.decode(highVal).intValue();<a name="line.357"></a>
<FONT color="green">358</FONT> }<a name="line.358"></a>
<FONT color="green">359</FONT> catch( NumberFormatException e) {<a name="line.359"></a>
<FONT color="green">360</FONT> highChar = 0;<a name="line.360"></a>
<FONT color="green">361</FONT> }<a name="line.361"></a>
<FONT color="green">362</FONT> String mimeNames = val.substring(0, len);<a name="line.362"></a>
<FONT color="green">363</FONT> StringTokenizer st =<a name="line.363"></a>
<FONT color="green">364</FONT> new StringTokenizer(mimeNames, ",");<a name="line.364"></a>
<FONT color="green">365</FONT> for (boolean first = true;<a name="line.365"></a>
<FONT color="green">366</FONT> st.hasMoreTokens();<a name="line.366"></a>
<FONT color="green">367</FONT> first = false)<a name="line.367"></a>
<FONT color="green">368</FONT> {<a name="line.368"></a>
<FONT color="green">369</FONT> mimeName = st.nextToken();<a name="line.369"></a>
<FONT color="green">370</FONT> EncodingInfo ei = new EncodingInfo(mimeName, javaName, highChar);<a name="line.370"></a>
<FONT color="green">371</FONT> encodingInfo_list.add(ei);<a name="line.371"></a>
<FONT color="green">372</FONT> _encodingTableKeyMime.put(mimeName.toUpperCase(), ei);<a name="line.372"></a>
<FONT color="green">373</FONT> if (first)<a name="line.373"></a>
<FONT color="green">374</FONT> _encodingTableKeyJava.put(javaName.toUpperCase(), ei);<a name="line.374"></a>
<FONT color="green">375</FONT> }<a name="line.375"></a>
<FONT color="green">376</FONT> }<a name="line.376"></a>
<FONT color="green">377</FONT> }<a name="line.377"></a>
<FONT color="green">378</FONT> // Convert the Vector of EncodingInfo objects into an array of them,<a name="line.378"></a>
<FONT color="green">379</FONT> // as that is the kind of thing this method returns.<a name="line.379"></a>
<FONT color="green">380</FONT> EncodingInfo[] ret_ei = new EncodingInfo[encodingInfo_list.size()];<a name="line.380"></a>
<FONT color="green">381</FONT> encodingInfo_list.toArray(ret_ei);<a name="line.381"></a>
<FONT color="green">382</FONT> return ret_ei;<a name="line.382"></a>
<FONT color="green">383</FONT> }<a name="line.383"></a>
<FONT color="green">384</FONT> catch (java.net.MalformedURLException mue)<a name="line.384"></a>
<FONT color="green">385</FONT> {<a name="line.385"></a>
<FONT color="green">386</FONT> throw new org.apache.xml.serializer.utils.WrappedRuntimeException(mue);<a name="line.386"></a>
<FONT color="green">387</FONT> }<a name="line.387"></a>
<FONT color="green">388</FONT> catch (java.io.IOException ioe)<a name="line.388"></a>
<FONT color="green">389</FONT> {<a name="line.389"></a>
<FONT color="green">390</FONT> throw new org.apache.xml.serializer.utils.WrappedRuntimeException(ioe);<a name="line.390"></a>
<FONT color="green">391</FONT> }<a name="line.391"></a>
<FONT color="green">392</FONT> }<a name="line.392"></a>
<FONT color="green">393</FONT> <a name="line.393"></a>
<FONT color="green">394</FONT> /**<a name="line.394"></a>
<FONT color="green">395</FONT> * Get the length of the Mime names within the property value<a name="line.395"></a>
<FONT color="green">396</FONT> * @param val The value of the property, which should contain a comma<a name="line.396"></a>
<FONT color="green">397</FONT> * separated list of Mime names, followed optionally by a space and the<a name="line.397"></a>
<FONT color="green">398</FONT> * high char value<a name="line.398"></a>
<FONT color="green">399</FONT> * @return<a name="line.399"></a>
<FONT color="green">400</FONT> */<a name="line.400"></a>
<FONT color="green">401</FONT> private static int lengthOfMimeNames(String val) {<a name="line.401"></a>
<FONT color="green">402</FONT> // look for the space preceding the optional high char<a name="line.402"></a>
<FONT color="green">403</FONT> int len = val.indexOf(' ');<a name="line.403"></a>
<FONT color="green">404</FONT> // If len is zero it means the optional part is not there, so<a name="line.404"></a>
<FONT color="green">405</FONT> // the value must be all Mime names, so set the length appropriately<a name="line.405"></a>
<FONT color="green">406</FONT> if (len &lt; 0) <a name="line.406"></a>
<FONT color="green">407</FONT> len = val.length();<a name="line.407"></a>
<FONT color="green">408</FONT> <a name="line.408"></a>
<FONT color="green">409</FONT> return len;<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> * Return true if the character is the high member of a surrogate pair.<a name="line.413"></a>
<FONT color="green">414</FONT> * &lt;p&gt;<a name="line.414"></a>
<FONT color="green">415</FONT> * This is not a public API.<a name="line.415"></a>
<FONT color="green">416</FONT> * @param ch the character to test<a name="line.416"></a>
<FONT color="green">417</FONT> * @xsl.usage internal<a name="line.417"></a>
<FONT color="green">418</FONT> */<a name="line.418"></a>
<FONT color="green">419</FONT> static boolean isHighUTF16Surrogate(char ch) {<a name="line.419"></a>
<FONT color="green">420</FONT> return ('\uD800' &lt;= ch &amp;&amp; ch &lt;= '\uDBFF');<a name="line.420"></a>
<FONT color="green">421</FONT> }<a name="line.421"></a>
<FONT color="green">422</FONT> /**<a name="line.422"></a>
<FONT color="green">423</FONT> * Return true if the character is the low member of a surrogate pair.<a name="line.423"></a>
<FONT color="green">424</FONT> * &lt;p&gt;<a name="line.424"></a>
<FONT color="green">425</FONT> * This is not a public API.<a name="line.425"></a>
<FONT color="green">426</FONT> * @param ch the character to test<a name="line.426"></a>
<FONT color="green">427</FONT> * @xsl.usage internal<a name="line.427"></a>
<FONT color="green">428</FONT> */<a name="line.428"></a>
<FONT color="green">429</FONT> static boolean isLowUTF16Surrogate(char ch) {<a name="line.429"></a>
<FONT color="green">430</FONT> return ('\uDC00' &lt;= ch &amp;&amp; ch &lt;= '\uDFFF');<a name="line.430"></a>
<FONT color="green">431</FONT> }<a name="line.431"></a>
<FONT color="green">432</FONT> /**<a name="line.432"></a>
<FONT color="green">433</FONT> * Return the unicode code point represented by the high/low surrogate pair.<a name="line.433"></a>
<FONT color="green">434</FONT> * &lt;p&gt;<a name="line.434"></a>
<FONT color="green">435</FONT> * This is not a public API.<a name="line.435"></a>
<FONT color="green">436</FONT> * @param highSurrogate the high char of the high/low pair<a name="line.436"></a>
<FONT color="green">437</FONT> * @param lowSurrogate the low char of the high/low pair<a name="line.437"></a>
<FONT color="green">438</FONT> * @xsl.usage internal<a name="line.438"></a>
<FONT color="green">439</FONT> */<a name="line.439"></a>
<FONT color="green">440</FONT> static int toCodePoint(char highSurrogate, char lowSurrogate) {<a name="line.440"></a>
<FONT color="green">441</FONT> int codePoint =<a name="line.441"></a>
<FONT color="green">442</FONT> ((highSurrogate - 0xd800) &lt;&lt; 10)<a name="line.442"></a>
<FONT color="green">443</FONT> + (lowSurrogate - 0xdc00)<a name="line.443"></a>
<FONT color="green">444</FONT> + 0x10000;<a name="line.444"></a>
<FONT color="green">445</FONT> return codePoint;<a name="line.445"></a>
<FONT color="green">446</FONT> }<a name="line.446"></a>
<FONT color="green">447</FONT> /**<a name="line.447"></a>
<FONT color="green">448</FONT> * Return the unicode code point represented by the char.<a name="line.448"></a>
<FONT color="green">449</FONT> * A bit of a dummy method, since all it does is return the char,<a name="line.449"></a>
<FONT color="green">450</FONT> * but as an int value.<a name="line.450"></a>
<FONT color="green">451</FONT> * &lt;p&gt;<a name="line.451"></a>
<FONT color="green">452</FONT> * This is not a public API.<a name="line.452"></a>
<FONT color="green">453</FONT> * @param ch the char.<a name="line.453"></a>
<FONT color="green">454</FONT> * @xsl.usage internal<a name="line.454"></a>
<FONT color="green">455</FONT> */<a name="line.455"></a>
<FONT color="green">456</FONT> static int toCodePoint(char ch) {<a name="line.456"></a>
<FONT color="green">457</FONT> int codePoint = ch;<a name="line.457"></a>
<FONT color="green">458</FONT> return codePoint;<a name="line.458"></a>
<FONT color="green">459</FONT> }<a name="line.459"></a>
<FONT color="green">460</FONT> <a name="line.460"></a>
<FONT color="green">461</FONT> /**<a name="line.461"></a>
<FONT color="green">462</FONT> * Characters with values at or below the high code point are<a name="line.462"></a>
<FONT color="green">463</FONT> * in the encoding. Code point values above this one may or may<a name="line.463"></a>
<FONT color="green">464</FONT> * not be in the encoding, but lower ones certainly are.<a name="line.464"></a>
<FONT color="green">465</FONT> * &lt;p&gt;<a name="line.465"></a>
<FONT color="green">466</FONT> * This is for performance.<a name="line.466"></a>
<FONT color="green">467</FONT> *<a name="line.467"></a>
<FONT color="green">468</FONT> * @param encoding The encoding<a name="line.468"></a>
<FONT color="green">469</FONT> * @return The code point for which characters at or below this code point<a name="line.469"></a>
<FONT color="green">470</FONT> * are in the encoding. Characters with higher code point may or may not be<a name="line.470"></a>
<FONT color="green">471</FONT> * in the encoding. A value of zero is returned if the high code point is unknown.<a name="line.471"></a>
<FONT color="green">472</FONT> * &lt;p&gt;<a name="line.472"></a>
<FONT color="green">473</FONT> * This method is not a public API.<a name="line.473"></a>
<FONT color="green">474</FONT> * @xsl.usage internal<a name="line.474"></a>
<FONT color="green">475</FONT> */<a name="line.475"></a>
<FONT color="green">476</FONT> static public char getHighChar(String encoding)<a name="line.476"></a>
<FONT color="green">477</FONT> {<a name="line.477"></a>
<FONT color="green">478</FONT> final char highCodePoint;<a name="line.478"></a>
<FONT color="green">479</FONT> EncodingInfo ei;<a name="line.479"></a>
<FONT color="green">480</FONT> <a name="line.480"></a>
<FONT color="green">481</FONT> String normalizedEncoding = toUpperCaseFast(encoding);<a name="line.481"></a>
<FONT color="green">482</FONT> ei = (EncodingInfo) _encodingTableKeyJava.get(normalizedEncoding);<a name="line.482"></a>
<FONT color="green">483</FONT> if (ei == null)<a name="line.483"></a>
<FONT color="green">484</FONT> ei = (EncodingInfo) _encodingTableKeyMime.get(normalizedEncoding);<a name="line.484"></a>
<FONT color="green">485</FONT> if (ei != null)<a name="line.485"></a>
<FONT color="green">486</FONT> highCodePoint = ei.getHighChar();<a name="line.486"></a>
<FONT color="green">487</FONT> else<a name="line.487"></a>
<FONT color="green">488</FONT> highCodePoint = 0;<a name="line.488"></a>
<FONT color="green">489</FONT> return highCodePoint;<a name="line.489"></a>
<FONT color="green">490</FONT> }<a name="line.490"></a>
<FONT color="green">491</FONT> <a name="line.491"></a>
<FONT color="green">492</FONT> private static final Hashtable _encodingTableKeyJava = new Hashtable();<a name="line.492"></a>
<FONT color="green">493</FONT> private static final Hashtable _encodingTableKeyMime = new Hashtable();<a name="line.493"></a>
<FONT color="green">494</FONT> private static final EncodingInfo[] _encodings = loadEncodingInfo();<a name="line.494"></a>
<FONT color="green">495</FONT> }<a name="line.495"></a>
</PRE>
</BODY>
</HTML>