| <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: WriterToUTF8Buffered.java 469356 2006-10-31 03:20:34Z 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.IOException;<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.UnsupportedEncodingException;<a name="line.25"></a> |
| <FONT color="green">026</FONT> import java.io.Writer;<a name="line.26"></a> |
| <FONT color="green">027</FONT> <a name="line.27"></a> |
| <FONT color="green">028</FONT> <a name="line.28"></a> |
| <FONT color="green">029</FONT> /**<a name="line.29"></a> |
| <FONT color="green">030</FONT> * This class writes unicode characters to a byte stream (java.io.OutputStream)<a name="line.30"></a> |
| <FONT color="green">031</FONT> * as quickly as possible. It buffers the output in an internal<a name="line.31"></a> |
| <FONT color="green">032</FONT> * buffer which must be flushed to the OutputStream when done. This flushing<a name="line.32"></a> |
| <FONT color="green">033</FONT> * is done via the close() flush() or flushBuffer() method. <a name="line.33"></a> |
| <FONT color="green">034</FONT> * <a name="line.34"></a> |
| <FONT color="green">035</FONT> * This class is only used internally within Xalan.<a name="line.35"></a> |
| <FONT color="green">036</FONT> * <a name="line.36"></a> |
| <FONT color="green">037</FONT> * @xsl.usage internal<a name="line.37"></a> |
| <FONT color="green">038</FONT> */<a name="line.38"></a> |
| <FONT color="green">039</FONT> final class WriterToUTF8Buffered extends Writer implements WriterChain<a name="line.39"></a> |
| <FONT color="green">040</FONT> {<a name="line.40"></a> |
| <FONT color="green">041</FONT> <a name="line.41"></a> |
| <FONT color="green">042</FONT> /** number of bytes that the byte buffer can hold.<a name="line.42"></a> |
| <FONT color="green">043</FONT> * This is a fixed constant is used rather than m_outputBytes.lenght for performance.<a name="line.43"></a> |
| <FONT color="green">044</FONT> */<a name="line.44"></a> |
| <FONT color="green">045</FONT> private static final int BYTES_MAX=16*1024;<a name="line.45"></a> |
| <FONT color="green">046</FONT> /** number of characters that the character buffer can hold.<a name="line.46"></a> |
| <FONT color="green">047</FONT> * This is 1/3 of the number of bytes because UTF-8 encoding<a name="line.47"></a> |
| <FONT color="green">048</FONT> * can expand one unicode character by up to 3 bytes.<a name="line.48"></a> |
| <FONT color="green">049</FONT> */<a name="line.49"></a> |
| <FONT color="green">050</FONT> private static final int CHARS_MAX=(BYTES_MAX/3);<a name="line.50"></a> |
| <FONT color="green">051</FONT> <a name="line.51"></a> |
| <FONT color="green">052</FONT> // private static final int <a name="line.52"></a> |
| <FONT color="green">053</FONT> <a name="line.53"></a> |
| <FONT color="green">054</FONT> /** The byte stream to write to. (sc & sb remove final to compile in JDK 1.1.8) */<a name="line.54"></a> |
| <FONT color="green">055</FONT> private final OutputStream m_os;<a name="line.55"></a> |
| <FONT color="green">056</FONT> <a name="line.56"></a> |
| <FONT color="green">057</FONT> /**<a name="line.57"></a> |
| <FONT color="green">058</FONT> * The internal buffer where data is stored.<a name="line.58"></a> |
| <FONT color="green">059</FONT> * (sc & sb remove final to compile in JDK 1.1.8)<a name="line.59"></a> |
| <FONT color="green">060</FONT> */<a name="line.60"></a> |
| <FONT color="green">061</FONT> private final byte m_outputBytes[];<a name="line.61"></a> |
| <FONT color="green">062</FONT> <a name="line.62"></a> |
| <FONT color="green">063</FONT> private final char m_inputChars[];<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 number of valid bytes in the buffer. This value is always<a name="line.66"></a> |
| <FONT color="green">067</FONT> * in the range <tt>0</tt> through <tt>m_outputBytes.length</tt>; elements<a name="line.67"></a> |
| <FONT color="green">068</FONT> * <tt>m_outputBytes[0]</tt> through <tt>m_outputBytes[count-1]</tt> contain valid<a name="line.68"></a> |
| <FONT color="green">069</FONT> * byte data.<a name="line.69"></a> |
| <FONT color="green">070</FONT> */<a name="line.70"></a> |
| <FONT color="green">071</FONT> private int count;<a name="line.71"></a> |
| <FONT color="green">072</FONT> <a name="line.72"></a> |
| <FONT color="green">073</FONT> /**<a name="line.73"></a> |
| <FONT color="green">074</FONT> * Create an buffered UTF-8 writer.<a name="line.74"></a> |
| <FONT color="green">075</FONT> *<a name="line.75"></a> |
| <FONT color="green">076</FONT> *<a name="line.76"></a> |
| <FONT color="green">077</FONT> * @param out the underlying output stream.<a name="line.77"></a> |
| <FONT color="green">078</FONT> *<a name="line.78"></a> |
| <FONT color="green">079</FONT> * @throws UnsupportedEncodingException<a name="line.79"></a> |
| <FONT color="green">080</FONT> */<a name="line.80"></a> |
| <FONT color="green">081</FONT> public WriterToUTF8Buffered(OutputStream out)<a name="line.81"></a> |
| <FONT color="green">082</FONT> {<a name="line.82"></a> |
| <FONT color="green">083</FONT> m_os = out;<a name="line.83"></a> |
| <FONT color="green">084</FONT> // get 3 extra bytes to make buffer overflow checking simpler and faster<a name="line.84"></a> |
| <FONT color="green">085</FONT> // we won't have to keep checking for a few extra characters<a name="line.85"></a> |
| <FONT color="green">086</FONT> m_outputBytes = new byte[BYTES_MAX + 3];<a name="line.86"></a> |
| <FONT color="green">087</FONT> <a name="line.87"></a> |
| <FONT color="green">088</FONT> // Big enough to hold the input chars that will be transformed<a name="line.88"></a> |
| <FONT color="green">089</FONT> // into output bytes in m_ouputBytes.<a name="line.89"></a> |
| <FONT color="green">090</FONT> m_inputChars = new char[CHARS_MAX + 2];<a name="line.90"></a> |
| <FONT color="green">091</FONT> count = 0;<a name="line.91"></a> |
| <FONT color="green">092</FONT> <a name="line.92"></a> |
| <FONT color="green">093</FONT> // the old body of this constructor, before the buffersize was changed to a constant <a name="line.93"></a> |
| <FONT color="green">094</FONT> // this(out, 8*1024);<a name="line.94"></a> |
| <FONT color="green">095</FONT> }<a name="line.95"></a> |
| <FONT color="green">096</FONT> <a name="line.96"></a> |
| <FONT color="green">097</FONT> /**<a name="line.97"></a> |
| <FONT color="green">098</FONT> * Create an buffered UTF-8 writer to write data to the<a name="line.98"></a> |
| <FONT color="green">099</FONT> * specified underlying output stream with the specified buffer<a name="line.99"></a> |
| <FONT color="green">100</FONT> * size.<a name="line.100"></a> |
| <FONT color="green">101</FONT> *<a name="line.101"></a> |
| <FONT color="green">102</FONT> * @param out the underlying output stream.<a name="line.102"></a> |
| <FONT color="green">103</FONT> * @param size the buffer size.<a name="line.103"></a> |
| <FONT color="green">104</FONT> * @exception IllegalArgumentException if size <= 0.<a name="line.104"></a> |
| <FONT color="green">105</FONT> */<a name="line.105"></a> |
| <FONT color="green">106</FONT> // public WriterToUTF8Buffered(final OutputStream out, final int size)<a name="line.106"></a> |
| <FONT color="green">107</FONT> // {<a name="line.107"></a> |
| <FONT color="green">108</FONT> //<a name="line.108"></a> |
| <FONT color="green">109</FONT> // m_os = out;<a name="line.109"></a> |
| <FONT color="green">110</FONT> //<a name="line.110"></a> |
| <FONT color="green">111</FONT> // if (size <= 0)<a name="line.111"></a> |
| <FONT color="green">112</FONT> // {<a name="line.112"></a> |
| <FONT color="green">113</FONT> // throw new IllegalArgumentException(<a name="line.113"></a> |
| <FONT color="green">114</FONT> // SerializerMessages.createMessage(SerializerErrorResources.ER_BUFFER_SIZE_LESSTHAN_ZERO, null)); //"Buffer size <= 0");<a name="line.114"></a> |
| <FONT color="green">115</FONT> // }<a name="line.115"></a> |
| <FONT color="green">116</FONT> //<a name="line.116"></a> |
| <FONT color="green">117</FONT> // m_outputBytes = new byte[size];<a name="line.117"></a> |
| <FONT color="green">118</FONT> // count = 0;<a name="line.118"></a> |
| <FONT color="green">119</FONT> // }<a name="line.119"></a> |
| <FONT color="green">120</FONT> <a name="line.120"></a> |
| <FONT color="green">121</FONT> /**<a name="line.121"></a> |
| <FONT color="green">122</FONT> * Write a single character. The character to be written is contained in<a name="line.122"></a> |
| <FONT color="green">123</FONT> * the 16 low-order bits of the given integer value; the 16 high-order bits<a name="line.123"></a> |
| <FONT color="green">124</FONT> * are ignored.<a name="line.124"></a> |
| <FONT color="green">125</FONT> *<a name="line.125"></a> |
| <FONT color="green">126</FONT> * <p> Subclasses that intend to support efficient single-character output<a name="line.126"></a> |
| <FONT color="green">127</FONT> * should override this method.<a name="line.127"></a> |
| <FONT color="green">128</FONT> *<a name="line.128"></a> |
| <FONT color="green">129</FONT> * @param c int specifying a character to be written.<a name="line.129"></a> |
| <FONT color="green">130</FONT> * @exception IOException If an I/O error occurs<a name="line.130"></a> |
| <FONT color="green">131</FONT> */<a name="line.131"></a> |
| <FONT color="green">132</FONT> public void write(final int c) throws IOException<a name="line.132"></a> |
| <FONT color="green">133</FONT> {<a name="line.133"></a> |
| <FONT color="green">134</FONT> <a name="line.134"></a> |
| <FONT color="green">135</FONT> /* If we are close to the end of the buffer then flush it.<a name="line.135"></a> |
| <FONT color="green">136</FONT> * Remember the buffer can hold a few more bytes than BYTES_MAX<a name="line.136"></a> |
| <FONT color="green">137</FONT> */ <a name="line.137"></a> |
| <FONT color="green">138</FONT> if (count >= BYTES_MAX)<a name="line.138"></a> |
| <FONT color="green">139</FONT> flushBuffer();<a name="line.139"></a> |
| <FONT color="green">140</FONT> <a name="line.140"></a> |
| <FONT color="green">141</FONT> if (c < 0x80)<a name="line.141"></a> |
| <FONT color="green">142</FONT> {<a name="line.142"></a> |
| <FONT color="green">143</FONT> m_outputBytes[count++] = (byte) (c);<a name="line.143"></a> |
| <FONT color="green">144</FONT> }<a name="line.144"></a> |
| <FONT color="green">145</FONT> else if (c < 0x800)<a name="line.145"></a> |
| <FONT color="green">146</FONT> {<a name="line.146"></a> |
| <FONT color="green">147</FONT> m_outputBytes[count++] = (byte) (0xc0 + (c >> 6));<a name="line.147"></a> |
| <FONT color="green">148</FONT> m_outputBytes[count++] = (byte) (0x80 + (c & 0x3f));<a name="line.148"></a> |
| <FONT color="green">149</FONT> }<a name="line.149"></a> |
| <FONT color="green">150</FONT> else if (c < 0x10000)<a name="line.150"></a> |
| <FONT color="green">151</FONT> {<a name="line.151"></a> |
| <FONT color="green">152</FONT> m_outputBytes[count++] = (byte) (0xe0 + (c >> 12));<a name="line.152"></a> |
| <FONT color="green">153</FONT> m_outputBytes[count++] = (byte) (0x80 + ((c >> 6) & 0x3f));<a name="line.153"></a> |
| <FONT color="green">154</FONT> m_outputBytes[count++] = (byte) (0x80 + (c & 0x3f));<a name="line.154"></a> |
| <FONT color="green">155</FONT> }<a name="line.155"></a> |
| <FONT color="green">156</FONT> else<a name="line.156"></a> |
| <FONT color="green">157</FONT> {<a name="line.157"></a> |
| <FONT color="green">158</FONT> m_outputBytes[count++] = (byte) (0xf0 + (c >> 18));<a name="line.158"></a> |
| <FONT color="green">159</FONT> m_outputBytes[count++] = (byte) (0x80 + ((c >> 12) & 0x3f));<a name="line.159"></a> |
| <FONT color="green">160</FONT> m_outputBytes[count++] = (byte) (0x80 + ((c >> 6) & 0x3f));<a name="line.160"></a> |
| <FONT color="green">161</FONT> m_outputBytes[count++] = (byte) (0x80 + (c & 0x3f));<a name="line.161"></a> |
| <FONT color="green">162</FONT> }<a name="line.162"></a> |
| <FONT color="green">163</FONT> <a name="line.163"></a> |
| <FONT color="green">164</FONT> }<a name="line.164"></a> |
| <FONT color="green">165</FONT> <a name="line.165"></a> |
| <FONT color="green">166</FONT> <a name="line.166"></a> |
| <FONT color="green">167</FONT> /**<a name="line.167"></a> |
| <FONT color="green">168</FONT> * Write a portion of an array of characters.<a name="line.168"></a> |
| <FONT color="green">169</FONT> *<a name="line.169"></a> |
| <FONT color="green">170</FONT> * @param chars Array of characters<a name="line.170"></a> |
| <FONT color="green">171</FONT> * @param start Offset from which to start writing characters<a name="line.171"></a> |
| <FONT color="green">172</FONT> * @param length Number of characters to write<a name="line.172"></a> |
| <FONT color="green">173</FONT> *<a name="line.173"></a> |
| <FONT color="green">174</FONT> * @exception IOException If an I/O error occurs<a name="line.174"></a> |
| <FONT color="green">175</FONT> *<a name="line.175"></a> |
| <FONT color="green">176</FONT> * @throws java.io.IOException<a name="line.176"></a> |
| <FONT color="green">177</FONT> */<a name="line.177"></a> |
| <FONT color="green">178</FONT> public void write(final char chars[], final int start, final int length)<a name="line.178"></a> |
| <FONT color="green">179</FONT> throws java.io.IOException<a name="line.179"></a> |
| <FONT color="green">180</FONT> {<a name="line.180"></a> |
| <FONT color="green">181</FONT> <a name="line.181"></a> |
| <FONT color="green">182</FONT> // We multiply the length by three since this is the maximum length<a name="line.182"></a> |
| <FONT color="green">183</FONT> // of the characters that we can put into the buffer. It is possible<a name="line.183"></a> |
| <FONT color="green">184</FONT> // for each Unicode character to expand to three bytes.<a name="line.184"></a> |
| <FONT color="green">185</FONT> <a name="line.185"></a> |
| <FONT color="green">186</FONT> int lengthx3 = 3*length;<a name="line.186"></a> |
| <FONT color="green">187</FONT> <a name="line.187"></a> |
| <FONT color="green">188</FONT> if (lengthx3 >= BYTES_MAX - count)<a name="line.188"></a> |
| <FONT color="green">189</FONT> {<a name="line.189"></a> |
| <FONT color="green">190</FONT> // The requested length is greater than the unused part of the buffer<a name="line.190"></a> |
| <FONT color="green">191</FONT> flushBuffer();<a name="line.191"></a> |
| <FONT color="green">192</FONT> <a name="line.192"></a> |
| <FONT color="green">193</FONT> if (lengthx3 > BYTES_MAX)<a name="line.193"></a> |
| <FONT color="green">194</FONT> {<a name="line.194"></a> |
| <FONT color="green">195</FONT> /*<a name="line.195"></a> |
| <FONT color="green">196</FONT> * The requested length exceeds the size of the buffer.<a name="line.196"></a> |
| <FONT color="green">197</FONT> * Cut the buffer up into chunks, each of which will<a name="line.197"></a> |
| <FONT color="green">198</FONT> * not cause an overflow to the output buffer m_outputBytes,<a name="line.198"></a> |
| <FONT color="green">199</FONT> * and make multiple recursive calls.<a name="line.199"></a> |
| <FONT color="green">200</FONT> * Be careful about integer overflows in multiplication.<a name="line.200"></a> |
| <FONT color="green">201</FONT> */<a name="line.201"></a> |
| <FONT color="green">202</FONT> int split = length/CHARS_MAX; <a name="line.202"></a> |
| <FONT color="green">203</FONT> final int chunks;<a name="line.203"></a> |
| <FONT color="green">204</FONT> if (length % CHARS_MAX > 0) <a name="line.204"></a> |
| <FONT color="green">205</FONT> chunks = split + 1;<a name="line.205"></a> |
| <FONT color="green">206</FONT> else<a name="line.206"></a> |
| <FONT color="green">207</FONT> chunks = split;<a name="line.207"></a> |
| <FONT color="green">208</FONT> int end_chunk = start;<a name="line.208"></a> |
| <FONT color="green">209</FONT> for (int chunk = 1; chunk <= chunks; chunk++)<a name="line.209"></a> |
| <FONT color="green">210</FONT> {<a name="line.210"></a> |
| <FONT color="green">211</FONT> int start_chunk = end_chunk;<a name="line.211"></a> |
| <FONT color="green">212</FONT> end_chunk = start + (int) ((((long) length) * chunk) / chunks);<a name="line.212"></a> |
| <FONT color="green">213</FONT> <a name="line.213"></a> |
| <FONT color="green">214</FONT> // Adjust the end of the chunk if it ends on a high char <a name="line.214"></a> |
| <FONT color="green">215</FONT> // of a Unicode surrogate pair and low char of the pair<a name="line.215"></a> |
| <FONT color="green">216</FONT> // is not going to be in the same chunk<a name="line.216"></a> |
| <FONT color="green">217</FONT> final char c = chars[end_chunk - 1]; <a name="line.217"></a> |
| <FONT color="green">218</FONT> int ic = chars[end_chunk - 1];<a name="line.218"></a> |
| <FONT color="green">219</FONT> if (c >= 0xD800 && c <= 0xDBFF) {<a name="line.219"></a> |
| <FONT color="green">220</FONT> // The last Java char that we were going<a name="line.220"></a> |
| <FONT color="green">221</FONT> // to process is the first of a<a name="line.221"></a> |
| <FONT color="green">222</FONT> // Java surrogate char pair that<a name="line.222"></a> |
| <FONT color="green">223</FONT> // represent a Unicode character.<a name="line.223"></a> |
| <FONT color="green">224</FONT> <a name="line.224"></a> |
| <FONT color="green">225</FONT> if (end_chunk < start + length) {<a name="line.225"></a> |
| <FONT color="green">226</FONT> // Avoid spanning by including the low<a name="line.226"></a> |
| <FONT color="green">227</FONT> // char in the current chunk of chars.<a name="line.227"></a> |
| <FONT color="green">228</FONT> end_chunk++;<a name="line.228"></a> |
| <FONT color="green">229</FONT> } else {<a name="line.229"></a> |
| <FONT color="green">230</FONT> /* This is the last char of the last chunk,<a name="line.230"></a> |
| <FONT color="green">231</FONT> * and it is the high char of a high/low pair with<a name="line.231"></a> |
| <FONT color="green">232</FONT> * no low char provided.<a name="line.232"></a> |
| <FONT color="green">233</FONT> * TODO: error message needed.<a name="line.233"></a> |
| <FONT color="green">234</FONT> * The char array incorrectly ends in a high char<a name="line.234"></a> |
| <FONT color="green">235</FONT> * of a high/low surrogate pair, but there is<a name="line.235"></a> |
| <FONT color="green">236</FONT> * no corresponding low as the high is the last char <a name="line.236"></a> |
| <FONT color="green">237</FONT> */<a name="line.237"></a> |
| <FONT color="green">238</FONT> end_chunk--;<a name="line.238"></a> |
| <FONT color="green">239</FONT> }<a name="line.239"></a> |
| <FONT color="green">240</FONT> }<a name="line.240"></a> |
| <FONT color="green">241</FONT> <a name="line.241"></a> |
| <FONT color="green">242</FONT> <a name="line.242"></a> |
| <FONT color="green">243</FONT> int len_chunk = (end_chunk - start_chunk);<a name="line.243"></a> |
| <FONT color="green">244</FONT> this.write(chars,start_chunk, len_chunk);<a name="line.244"></a> |
| <FONT color="green">245</FONT> }<a name="line.245"></a> |
| <FONT color="green">246</FONT> return;<a name="line.246"></a> |
| <FONT color="green">247</FONT> }<a name="line.247"></a> |
| <FONT color="green">248</FONT> }<a name="line.248"></a> |
| <FONT color="green">249</FONT> <a name="line.249"></a> |
| <FONT color="green">250</FONT> <a name="line.250"></a> |
| <FONT color="green">251</FONT> <a name="line.251"></a> |
| <FONT color="green">252</FONT> final int n = length+start;<a name="line.252"></a> |
| <FONT color="green">253</FONT> final byte[] buf_loc = m_outputBytes; // local reference for faster access<a name="line.253"></a> |
| <FONT color="green">254</FONT> int count_loc = count; // local integer for faster access<a name="line.254"></a> |
| <FONT color="green">255</FONT> int i = start;<a name="line.255"></a> |
| <FONT color="green">256</FONT> {<a name="line.256"></a> |
| <FONT color="green">257</FONT> /* This block could be omitted and the code would produce<a name="line.257"></a> |
| <FONT color="green">258</FONT> * the same result. But this block exists to give the JIT<a name="line.258"></a> |
| <FONT color="green">259</FONT> * a better chance of optimizing a tight and common loop which<a name="line.259"></a> |
| <FONT color="green">260</FONT> * occurs when writing out ASCII characters. <a name="line.260"></a> |
| <FONT color="green">261</FONT> */ <a name="line.261"></a> |
| <FONT color="green">262</FONT> char c;<a name="line.262"></a> |
| <FONT color="green">263</FONT> for(; i < n && (c = chars[i])< 0x80 ; i++ )<a name="line.263"></a> |
| <FONT color="green">264</FONT> buf_loc[count_loc++] = (byte)c;<a name="line.264"></a> |
| <FONT color="green">265</FONT> }<a name="line.265"></a> |
| <FONT color="green">266</FONT> for (; i < n; i++)<a name="line.266"></a> |
| <FONT color="green">267</FONT> {<a name="line.267"></a> |
| <FONT color="green">268</FONT> <a name="line.268"></a> |
| <FONT color="green">269</FONT> final char c = chars[i];<a name="line.269"></a> |
| <FONT color="green">270</FONT> <a name="line.270"></a> |
| <FONT color="green">271</FONT> if (c < 0x80)<a name="line.271"></a> |
| <FONT color="green">272</FONT> buf_loc[count_loc++] = (byte) (c);<a name="line.272"></a> |
| <FONT color="green">273</FONT> else if (c < 0x800)<a name="line.273"></a> |
| <FONT color="green">274</FONT> {<a name="line.274"></a> |
| <FONT color="green">275</FONT> buf_loc[count_loc++] = (byte) (0xc0 + (c >> 6));<a name="line.275"></a> |
| <FONT color="green">276</FONT> buf_loc[count_loc++] = (byte) (0x80 + (c & 0x3f));<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> * The following else if condition is added to support XML 1.1 Characters for <a name="line.279"></a> |
| <FONT color="green">280</FONT> * UTF-8: [1111 0uuu] [10uu zzzz] [10yy yyyy] [10xx xxxx]*<a name="line.280"></a> |
| <FONT color="green">281</FONT> * Unicode: [1101 10ww] [wwzz zzyy] (high surrogate)<a name="line.281"></a> |
| <FONT color="green">282</FONT> * [1101 11yy] [yyxx xxxx] (low surrogate)<a name="line.282"></a> |
| <FONT color="green">283</FONT> * * uuuuu = wwww + 1<a name="line.283"></a> |
| <FONT color="green">284</FONT> */<a name="line.284"></a> |
| <FONT color="green">285</FONT> else if (c >= 0xD800 && c <= 0xDBFF) <a name="line.285"></a> |
| <FONT color="green">286</FONT> {<a name="line.286"></a> |
| <FONT color="green">287</FONT> char high, low;<a name="line.287"></a> |
| <FONT color="green">288</FONT> high = c;<a name="line.288"></a> |
| <FONT color="green">289</FONT> i++;<a name="line.289"></a> |
| <FONT color="green">290</FONT> low = chars[i];<a name="line.290"></a> |
| <FONT color="green">291</FONT> <a name="line.291"></a> |
| <FONT color="green">292</FONT> buf_loc[count_loc++] = (byte) (0xF0 | (((high + 0x40) >> 8) & 0xf0));<a name="line.292"></a> |
| <FONT color="green">293</FONT> buf_loc[count_loc++] = (byte) (0x80 | (((high + 0x40) >> 2) & 0x3f));<a name="line.293"></a> |
| <FONT color="green">294</FONT> buf_loc[count_loc++] = (byte) (0x80 | ((low >> 6) & 0x0f) + ((high << 4) & 0x30));<a name="line.294"></a> |
| <FONT color="green">295</FONT> buf_loc[count_loc++] = (byte) (0x80 | (low & 0x3f));<a name="line.295"></a> |
| <FONT color="green">296</FONT> }<a name="line.296"></a> |
| <FONT color="green">297</FONT> else<a name="line.297"></a> |
| <FONT color="green">298</FONT> {<a name="line.298"></a> |
| <FONT color="green">299</FONT> buf_loc[count_loc++] = (byte) (0xe0 + (c >> 12));<a name="line.299"></a> |
| <FONT color="green">300</FONT> buf_loc[count_loc++] = (byte) (0x80 + ((c >> 6) & 0x3f));<a name="line.300"></a> |
| <FONT color="green">301</FONT> buf_loc[count_loc++] = (byte) (0x80 + (c & 0x3f));<a name="line.301"></a> |
| <FONT color="green">302</FONT> }<a name="line.302"></a> |
| <FONT color="green">303</FONT> }<a name="line.303"></a> |
| <FONT color="green">304</FONT> // Store the local integer back into the instance variable<a name="line.304"></a> |
| <FONT color="green">305</FONT> count = count_loc;<a name="line.305"></a> |
| <FONT color="green">306</FONT> <a name="line.306"></a> |
| <FONT color="green">307</FONT> }<a name="line.307"></a> |
| <FONT color="green">308</FONT> <a name="line.308"></a> |
| <FONT color="green">309</FONT> /**<a name="line.309"></a> |
| <FONT color="green">310</FONT> * Write a string.<a name="line.310"></a> |
| <FONT color="green">311</FONT> *<a name="line.311"></a> |
| <FONT color="green">312</FONT> * @param s String to be written<a name="line.312"></a> |
| <FONT color="green">313</FONT> *<a name="line.313"></a> |
| <FONT color="green">314</FONT> * @exception IOException If an I/O error occurs<a name="line.314"></a> |
| <FONT color="green">315</FONT> */<a name="line.315"></a> |
| <FONT color="green">316</FONT> public void write(final String s) throws IOException<a name="line.316"></a> |
| <FONT color="green">317</FONT> {<a name="line.317"></a> |
| <FONT color="green">318</FONT> <a name="line.318"></a> |
| <FONT color="green">319</FONT> // We multiply the length by three since this is the maximum length<a name="line.319"></a> |
| <FONT color="green">320</FONT> // of the characters that we can put into the buffer. It is possible<a name="line.320"></a> |
| <FONT color="green">321</FONT> // for each Unicode character to expand to three bytes.<a name="line.321"></a> |
| <FONT color="green">322</FONT> final int length = s.length();<a name="line.322"></a> |
| <FONT color="green">323</FONT> int lengthx3 = 3*length;<a name="line.323"></a> |
| <FONT color="green">324</FONT> <a name="line.324"></a> |
| <FONT color="green">325</FONT> if (lengthx3 >= BYTES_MAX - count)<a name="line.325"></a> |
| <FONT color="green">326</FONT> {<a name="line.326"></a> |
| <FONT color="green">327</FONT> // The requested length is greater than the unused part of the buffer<a name="line.327"></a> |
| <FONT color="green">328</FONT> flushBuffer();<a name="line.328"></a> |
| <FONT color="green">329</FONT> <a name="line.329"></a> |
| <FONT color="green">330</FONT> if (lengthx3 > BYTES_MAX)<a name="line.330"></a> |
| <FONT color="green">331</FONT> {<a name="line.331"></a> |
| <FONT color="green">332</FONT> /*<a name="line.332"></a> |
| <FONT color="green">333</FONT> * The requested length exceeds the size of the buffer,<a name="line.333"></a> |
| <FONT color="green">334</FONT> * so break it up in chunks that don't exceed the buffer size.<a name="line.334"></a> |
| <FONT color="green">335</FONT> */<a name="line.335"></a> |
| <FONT color="green">336</FONT> final int start = 0;<a name="line.336"></a> |
| <FONT color="green">337</FONT> int split = length/CHARS_MAX; <a name="line.337"></a> |
| <FONT color="green">338</FONT> final int chunks;<a name="line.338"></a> |
| <FONT color="green">339</FONT> if (length % CHARS_MAX > 0) <a name="line.339"></a> |
| <FONT color="green">340</FONT> chunks = split + 1;<a name="line.340"></a> |
| <FONT color="green">341</FONT> else<a name="line.341"></a> |
| <FONT color="green">342</FONT> chunks = split;<a name="line.342"></a> |
| <FONT color="green">343</FONT> int end_chunk = 0;<a name="line.343"></a> |
| <FONT color="green">344</FONT> for (int chunk = 1; chunk <= chunks; chunk++)<a name="line.344"></a> |
| <FONT color="green">345</FONT> {<a name="line.345"></a> |
| <FONT color="green">346</FONT> int start_chunk = end_chunk;<a name="line.346"></a> |
| <FONT color="green">347</FONT> end_chunk = start + (int) ((((long) length) * chunk) / chunks);<a name="line.347"></a> |
| <FONT color="green">348</FONT> s.getChars(start_chunk,end_chunk, m_inputChars,0);<a name="line.348"></a> |
| <FONT color="green">349</FONT> int len_chunk = (end_chunk - start_chunk);<a name="line.349"></a> |
| <FONT color="green">350</FONT> <a name="line.350"></a> |
| <FONT color="green">351</FONT> // Adjust the end of the chunk if it ends on a high char <a name="line.351"></a> |
| <FONT color="green">352</FONT> // of a Unicode surrogate pair and low char of the pair<a name="line.352"></a> |
| <FONT color="green">353</FONT> // is not going to be in the same chunk<a name="line.353"></a> |
| <FONT color="green">354</FONT> final char c = m_inputChars[len_chunk - 1];<a name="line.354"></a> |
| <FONT color="green">355</FONT> if (c >= 0xD800 && c <= 0xDBFF) {<a name="line.355"></a> |
| <FONT color="green">356</FONT> // Exclude char in this chunk, <a name="line.356"></a> |
| <FONT color="green">357</FONT> // to avoid spanning a Unicode character <a name="line.357"></a> |
| <FONT color="green">358</FONT> // that is in two Java chars as a high/low surrogate<a name="line.358"></a> |
| <FONT color="green">359</FONT> end_chunk--;<a name="line.359"></a> |
| <FONT color="green">360</FONT> len_chunk--;<a name="line.360"></a> |
| <FONT color="green">361</FONT> if (chunk == chunks) {<a name="line.361"></a> |
| <FONT color="green">362</FONT> /* TODO: error message needed.<a name="line.362"></a> |
| <FONT color="green">363</FONT> * The String incorrectly ends in a high char<a name="line.363"></a> |
| <FONT color="green">364</FONT> * of a high/low surrogate pair, but there is<a name="line.364"></a> |
| <FONT color="green">365</FONT> * no corresponding low as the high is the last char<a name="line.365"></a> |
| <FONT color="green">366</FONT> * Recover by ignoring this last char.<a name="line.366"></a> |
| <FONT color="green">367</FONT> */<a name="line.367"></a> |
| <FONT color="green">368</FONT> }<a name="line.368"></a> |
| <FONT color="green">369</FONT> }<a name="line.369"></a> |
| <FONT color="green">370</FONT> <a name="line.370"></a> |
| <FONT color="green">371</FONT> this.write(m_inputChars,0, len_chunk);<a name="line.371"></a> |
| <FONT color="green">372</FONT> }<a name="line.372"></a> |
| <FONT color="green">373</FONT> return;<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 name="line.376"></a> |
| <FONT color="green">377</FONT> <a name="line.377"></a> |
| <FONT color="green">378</FONT> s.getChars(0, length , m_inputChars, 0);<a name="line.378"></a> |
| <FONT color="green">379</FONT> final char[] chars = m_inputChars;<a name="line.379"></a> |
| <FONT color="green">380</FONT> final int n = length;<a name="line.380"></a> |
| <FONT color="green">381</FONT> final byte[] buf_loc = m_outputBytes; // local reference for faster access<a name="line.381"></a> |
| <FONT color="green">382</FONT> int count_loc = count; // local integer for faster access<a name="line.382"></a> |
| <FONT color="green">383</FONT> int i = 0;<a name="line.383"></a> |
| <FONT color="green">384</FONT> {<a name="line.384"></a> |
| <FONT color="green">385</FONT> /* This block could be omitted and the code would produce<a name="line.385"></a> |
| <FONT color="green">386</FONT> * the same result. But this block exists to give the JIT<a name="line.386"></a> |
| <FONT color="green">387</FONT> * a better chance of optimizing a tight and common loop which<a name="line.387"></a> |
| <FONT color="green">388</FONT> * occurs when writing out ASCII characters. <a name="line.388"></a> |
| <FONT color="green">389</FONT> */ <a name="line.389"></a> |
| <FONT color="green">390</FONT> char c;<a name="line.390"></a> |
| <FONT color="green">391</FONT> for(; i < n && (c = chars[i])< 0x80 ; i++ )<a name="line.391"></a> |
| <FONT color="green">392</FONT> buf_loc[count_loc++] = (byte)c;<a name="line.392"></a> |
| <FONT color="green">393</FONT> }<a name="line.393"></a> |
| <FONT color="green">394</FONT> for (; i < n; i++)<a name="line.394"></a> |
| <FONT color="green">395</FONT> {<a name="line.395"></a> |
| <FONT color="green">396</FONT> <a name="line.396"></a> |
| <FONT color="green">397</FONT> final char c = chars[i];<a name="line.397"></a> |
| <FONT color="green">398</FONT> <a name="line.398"></a> |
| <FONT color="green">399</FONT> if (c < 0x80)<a name="line.399"></a> |
| <FONT color="green">400</FONT> buf_loc[count_loc++] = (byte) (c);<a name="line.400"></a> |
| <FONT color="green">401</FONT> else if (c < 0x800)<a name="line.401"></a> |
| <FONT color="green">402</FONT> {<a name="line.402"></a> |
| <FONT color="green">403</FONT> buf_loc[count_loc++] = (byte) (0xc0 + (c >> 6));<a name="line.403"></a> |
| <FONT color="green">404</FONT> buf_loc[count_loc++] = (byte) (0x80 + (c & 0x3f));<a name="line.404"></a> |
| <FONT color="green">405</FONT> }<a name="line.405"></a> |
| <FONT color="green">406</FONT> /**<a name="line.406"></a> |
| <FONT color="green">407</FONT> * The following else if condition is added to support XML 1.1 Characters for <a name="line.407"></a> |
| <FONT color="green">408</FONT> * UTF-8: [1111 0uuu] [10uu zzzz] [10yy yyyy] [10xx xxxx]*<a name="line.408"></a> |
| <FONT color="green">409</FONT> * Unicode: [1101 10ww] [wwzz zzyy] (high surrogate)<a name="line.409"></a> |
| <FONT color="green">410</FONT> * [1101 11yy] [yyxx xxxx] (low surrogate)<a name="line.410"></a> |
| <FONT color="green">411</FONT> * * uuuuu = wwww + 1<a name="line.411"></a> |
| <FONT color="green">412</FONT> */<a name="line.412"></a> |
| <FONT color="green">413</FONT> else if (c >= 0xD800 && c <= 0xDBFF) <a name="line.413"></a> |
| <FONT color="green">414</FONT> {<a name="line.414"></a> |
| <FONT color="green">415</FONT> char high, low;<a name="line.415"></a> |
| <FONT color="green">416</FONT> high = c;<a name="line.416"></a> |
| <FONT color="green">417</FONT> i++;<a name="line.417"></a> |
| <FONT color="green">418</FONT> low = chars[i];<a name="line.418"></a> |
| <FONT color="green">419</FONT> <a name="line.419"></a> |
| <FONT color="green">420</FONT> buf_loc[count_loc++] = (byte) (0xF0 | (((high + 0x40) >> 8) & 0xf0));<a name="line.420"></a> |
| <FONT color="green">421</FONT> buf_loc[count_loc++] = (byte) (0x80 | (((high + 0x40) >> 2) & 0x3f));<a name="line.421"></a> |
| <FONT color="green">422</FONT> buf_loc[count_loc++] = (byte) (0x80 | ((low >> 6) & 0x0f) + ((high << 4) & 0x30));<a name="line.422"></a> |
| <FONT color="green">423</FONT> buf_loc[count_loc++] = (byte) (0x80 | (low & 0x3f));<a name="line.423"></a> |
| <FONT color="green">424</FONT> }<a name="line.424"></a> |
| <FONT color="green">425</FONT> else<a name="line.425"></a> |
| <FONT color="green">426</FONT> {<a name="line.426"></a> |
| <FONT color="green">427</FONT> buf_loc[count_loc++] = (byte) (0xe0 + (c >> 12));<a name="line.427"></a> |
| <FONT color="green">428</FONT> buf_loc[count_loc++] = (byte) (0x80 + ((c >> 6) & 0x3f));<a name="line.428"></a> |
| <FONT color="green">429</FONT> buf_loc[count_loc++] = (byte) (0x80 + (c & 0x3f));<a name="line.429"></a> |
| <FONT color="green">430</FONT> }<a name="line.430"></a> |
| <FONT color="green">431</FONT> }<a name="line.431"></a> |
| <FONT color="green">432</FONT> // Store the local integer back into the instance variable<a name="line.432"></a> |
| <FONT color="green">433</FONT> count = count_loc;<a name="line.433"></a> |
| <FONT color="green">434</FONT> <a name="line.434"></a> |
| <FONT color="green">435</FONT> }<a name="line.435"></a> |
| <FONT color="green">436</FONT> <a name="line.436"></a> |
| <FONT color="green">437</FONT> /**<a name="line.437"></a> |
| <FONT color="green">438</FONT> * Flush the internal buffer<a name="line.438"></a> |
| <FONT color="green">439</FONT> *<a name="line.439"></a> |
| <FONT color="green">440</FONT> * @throws IOException<a name="line.440"></a> |
| <FONT color="green">441</FONT> */<a name="line.441"></a> |
| <FONT color="green">442</FONT> public void flushBuffer() throws IOException<a name="line.442"></a> |
| <FONT color="green">443</FONT> {<a name="line.443"></a> |
| <FONT color="green">444</FONT> <a name="line.444"></a> |
| <FONT color="green">445</FONT> if (count > 0)<a name="line.445"></a> |
| <FONT color="green">446</FONT> {<a name="line.446"></a> |
| <FONT color="green">447</FONT> m_os.write(m_outputBytes, 0, count);<a name="line.447"></a> |
| <FONT color="green">448</FONT> <a name="line.448"></a> |
| <FONT color="green">449</FONT> count = 0;<a name="line.449"></a> |
| <FONT color="green">450</FONT> }<a name="line.450"></a> |
| <FONT color="green">451</FONT> }<a name="line.451"></a> |
| <FONT color="green">452</FONT> <a name="line.452"></a> |
| <FONT color="green">453</FONT> /**<a name="line.453"></a> |
| <FONT color="green">454</FONT> * Flush the stream. If the stream has saved any characters from the<a name="line.454"></a> |
| <FONT color="green">455</FONT> * various write() methods in a buffer, write them immediately to their<a name="line.455"></a> |
| <FONT color="green">456</FONT> * intended destination. Then, if that destination is another character or<a name="line.456"></a> |
| <FONT color="green">457</FONT> * byte stream, flush it. Thus one flush() invocation will flush all the<a name="line.457"></a> |
| <FONT color="green">458</FONT> * buffers in a chain of Writers and OutputStreams.<a name="line.458"></a> |
| <FONT color="green">459</FONT> *<a name="line.459"></a> |
| <FONT color="green">460</FONT> * @exception IOException If an I/O error occurs<a name="line.460"></a> |
| <FONT color="green">461</FONT> *<a name="line.461"></a> |
| <FONT color="green">462</FONT> * @throws java.io.IOException<a name="line.462"></a> |
| <FONT color="green">463</FONT> */<a name="line.463"></a> |
| <FONT color="green">464</FONT> public void flush() throws java.io.IOException<a name="line.464"></a> |
| <FONT color="green">465</FONT> {<a name="line.465"></a> |
| <FONT color="green">466</FONT> flushBuffer();<a name="line.466"></a> |
| <FONT color="green">467</FONT> m_os.flush();<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> * Close the stream, flushing it first. Once a stream has been closed,<a name="line.471"></a> |
| <FONT color="green">472</FONT> * further write() or flush() invocations will cause an IOException to be<a name="line.472"></a> |
| <FONT color="green">473</FONT> * thrown. Closing a previously-closed stream, however, has no effect.<a name="line.473"></a> |
| <FONT color="green">474</FONT> *<a name="line.474"></a> |
| <FONT color="green">475</FONT> * @exception IOException If an I/O error occurs<a name="line.475"></a> |
| <FONT color="green">476</FONT> *<a name="line.476"></a> |
| <FONT color="green">477</FONT> * @throws java.io.IOException<a name="line.477"></a> |
| <FONT color="green">478</FONT> */<a name="line.478"></a> |
| <FONT color="green">479</FONT> public void close() throws java.io.IOException<a name="line.479"></a> |
| <FONT color="green">480</FONT> {<a name="line.480"></a> |
| <FONT color="green">481</FONT> flushBuffer();<a name="line.481"></a> |
| <FONT color="green">482</FONT> m_os.close();<a name="line.482"></a> |
| <FONT color="green">483</FONT> }<a name="line.483"></a> |
| <FONT color="green">484</FONT> <a name="line.484"></a> |
| <FONT color="green">485</FONT> /**<a name="line.485"></a> |
| <FONT color="green">486</FONT> * Get the output stream where the events will be serialized to.<a name="line.486"></a> |
| <FONT color="green">487</FONT> *<a name="line.487"></a> |
| <FONT color="green">488</FONT> * @return reference to the result stream, or null of only a writer was<a name="line.488"></a> |
| <FONT color="green">489</FONT> * set.<a name="line.489"></a> |
| <FONT color="green">490</FONT> */<a name="line.490"></a> |
| <FONT color="green">491</FONT> public OutputStream getOutputStream()<a name="line.491"></a> |
| <FONT color="green">492</FONT> {<a name="line.492"></a> |
| <FONT color="green">493</FONT> return m_os;<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> public Writer getWriter()<a name="line.496"></a> |
| <FONT color="green">497</FONT> {<a name="line.497"></a> |
| <FONT color="green">498</FONT> // Only one of getWriter() or getOutputStream() can return null<a name="line.498"></a> |
| <FONT color="green">499</FONT> // This type of writer wraps an OutputStream, not a Writer.<a name="line.499"></a> |
| <FONT color="green">500</FONT> return null;<a name="line.500"></a> |
| <FONT color="green">501</FONT> }<a name="line.501"></a> |
| <FONT color="green">502</FONT> }<a name="line.502"></a> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </PRE> |
| </BODY> |
| </HTML> |
