Modified: websites/production/commons/content/proper/commons-text/apidocs/src-html/org/apache/commons/text/translate/EntityArrays.html ============================================================================== --- websites/production/commons/content/proper/commons-text/apidocs/src-html/org/apache/commons/text/translate/EntityArrays.html (original) +++ websites/production/commons/content/proper/commons-text/apidocs/src-html/org/apache/commons/text/translate/EntityArrays.html Mon Jan 23 12:35:12 2017 @@ -24,412 +24,430 @@ <span class="sourceLineNo">016</span> */<a name="line.16"></a> <span class="sourceLineNo">017</span>package org.apache.commons.text.translate;<a name="line.17"></a> <span class="sourceLineNo">018</span><a name="line.18"></a> -<span class="sourceLineNo">019</span>/**<a name="line.19"></a> -<span class="sourceLineNo">020</span> * Class holding various entity data for HTML and XML - generally for use with<a name="line.20"></a> -<span class="sourceLineNo">021</span> * the LookupTranslator.<a name="line.21"></a> -<span class="sourceLineNo">022</span> * All arrays are of length [*][2].<a name="line.22"></a> -<span class="sourceLineNo">023</span> *<a name="line.23"></a> -<span class="sourceLineNo">024</span> * @since 1.0<a name="line.24"></a> -<span class="sourceLineNo">025</span> */<a name="line.25"></a> -<span class="sourceLineNo">026</span>public class EntityArrays {<a name="line.26"></a> -<span class="sourceLineNo">027</span><a name="line.27"></a> -<span class="sourceLineNo">028</span> /**<a name="line.28"></a> -<span class="sourceLineNo">029</span> * Mapping to escape <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1">ISO-8859-1</a><a name="line.29"></a> -<span class="sourceLineNo">030</span> * characters to their named HTML 3.x equivalents.<a name="line.30"></a> -<span class="sourceLineNo">031</span> * @return the mapping table<a name="line.31"></a> -<span class="sourceLineNo">032</span> */<a name="line.32"></a> -<span class="sourceLineNo">033</span> public static String[][] ISO8859_1_ESCAPE() { return ISO8859_1_ESCAPE.clone(); }<a name="line.33"></a> -<span class="sourceLineNo">034</span> private static final String[][] ISO8859_1_ESCAPE = {<a name="line.34"></a> -<span class="sourceLineNo">035</span> {"\u00A0", "&nbsp;"}, // non-breaking space<a name="line.35"></a> -<span class="sourceLineNo">036</span> {"\u00A1", "&iexcl;"}, // inverted exclamation mark<a name="line.36"></a> -<span class="sourceLineNo">037</span> {"\u00A2", "&cent;"}, // cent sign<a name="line.37"></a> -<span class="sourceLineNo">038</span> {"\u00A3", "&pound;"}, // pound sign<a name="line.38"></a> -<span class="sourceLineNo">039</span> {"\u00A4", "&curren;"}, // currency sign<a name="line.39"></a> -<span class="sourceLineNo">040</span> {"\u00A5", "&yen;"}, // yen sign = yuan sign<a name="line.40"></a> -<span class="sourceLineNo">041</span> {"\u00A6", "&brvbar;"}, // broken bar = broken vertical bar<a name="line.41"></a> -<span class="sourceLineNo">042</span> {"\u00A7", "&sect;"}, // section sign<a name="line.42"></a> -<span class="sourceLineNo">043</span> {"\u00A8", "&uml;"}, // diaeresis = spacing diaeresis<a name="line.43"></a> -<span class="sourceLineNo">044</span> {"\u00A9", "&copy;"}, // © - copyright sign<a name="line.44"></a> -<span class="sourceLineNo">045</span> {"\u00AA", "&ordf;"}, // feminine ordinal indicator<a name="line.45"></a> -<span class="sourceLineNo">046</span> {"\u00AB", "&laquo;"}, // left-pointing double angle quotation mark = left pointing guillemet<a name="line.46"></a> -<span class="sourceLineNo">047</span> {"\u00AC", "&not;"}, // not sign<a name="line.47"></a> -<span class="sourceLineNo">048</span> {"\u00AD", "&shy;"}, // soft hyphen = discretionary hyphen<a name="line.48"></a> -<span class="sourceLineNo">049</span> {"\u00AE", "&reg;"}, // ® - registered trademark sign<a name="line.49"></a> -<span class="sourceLineNo">050</span> {"\u00AF", "&macr;"}, // macron = spacing macron = overline = APL overbar<a name="line.50"></a> -<span class="sourceLineNo">051</span> {"\u00B0", "&deg;"}, // degree sign<a name="line.51"></a> -<span class="sourceLineNo">052</span> {"\u00B1", "&plusmn;"}, // plus-minus sign = plus-or-minus sign<a name="line.52"></a> -<span class="sourceLineNo">053</span> {"\u00B2", "&sup2;"}, // superscript two = superscript digit two = squared<a name="line.53"></a> -<span class="sourceLineNo">054</span> {"\u00B3", "&sup3;"}, // superscript three = superscript digit three = cubed<a name="line.54"></a> -<span class="sourceLineNo">055</span> {"\u00B4", "&acute;"}, // acute accent = spacing acute<a name="line.55"></a> -<span class="sourceLineNo">056</span> {"\u00B5", "&micro;"}, // micro sign<a name="line.56"></a> -<span class="sourceLineNo">057</span> {"\u00B6", "&para;"}, // pilcrow sign = paragraph sign<a name="line.57"></a> -<span class="sourceLineNo">058</span> {"\u00B7", "&middot;"}, // middle dot = Georgian comma = Greek middle dot<a name="line.58"></a> -<span class="sourceLineNo">059</span> {"\u00B8", "&cedil;"}, // cedilla = spacing cedilla<a name="line.59"></a> -<span class="sourceLineNo">060</span> {"\u00B9", "&sup1;"}, // superscript one = superscript digit one<a name="line.60"></a> -<span class="sourceLineNo">061</span> {"\u00BA", "&ordm;"}, // masculine ordinal indicator<a name="line.61"></a> -<span class="sourceLineNo">062</span> {"\u00BB", "&raquo;"}, // right-pointing double angle quotation mark = right pointing guillemet<a name="line.62"></a> -<span class="sourceLineNo">063</span> {"\u00BC", "&frac14;"}, // vulgar fraction one quarter = fraction one quarter<a name="line.63"></a> -<span class="sourceLineNo">064</span> {"\u00BD", "&frac12;"}, // vulgar fraction one half = fraction one half<a name="line.64"></a> -<span class="sourceLineNo">065</span> {"\u00BE", "&frac34;"}, // vulgar fraction three quarters = fraction three quarters<a name="line.65"></a> -<span class="sourceLineNo">066</span> {"\u00BF", "&iquest;"}, // inverted question mark = turned question mark<a name="line.66"></a> -<span class="sourceLineNo">067</span> {"\u00C0", "&Agrave;"}, // à - uppercase A, grave accent<a name="line.67"></a> -<span class="sourceLineNo">068</span> {"\u00C1", "&Aacute;"}, // à - uppercase A, acute accent<a name="line.68"></a> -<span class="sourceLineNo">069</span> {"\u00C2", "&Acirc;"}, // à - uppercase A, circumflex accent<a name="line.69"></a> -<span class="sourceLineNo">070</span> {"\u00C3", "&Atilde;"}, // à - uppercase A, tilde<a name="line.70"></a> -<span class="sourceLineNo">071</span> {"\u00C4", "&Auml;"}, // à - uppercase A, umlaut<a name="line.71"></a> -<span class="sourceLineNo">072</span> {"\u00C5", "&Aring;"}, // à - uppercase A, ring<a name="line.72"></a> -<span class="sourceLineNo">073</span> {"\u00C6", "&AElig;"}, // à - uppercase AE<a name="line.73"></a> -<span class="sourceLineNo">074</span> {"\u00C7", "&Ccedil;"}, // à - uppercase C, cedilla<a name="line.74"></a> -<span class="sourceLineNo">075</span> {"\u00C8", "&Egrave;"}, // à - uppercase E, grave accent<a name="line.75"></a> -<span class="sourceLineNo">076</span> {"\u00C9", "&Eacute;"}, // à - uppercase E, acute accent<a name="line.76"></a> -<span class="sourceLineNo">077</span> {"\u00CA", "&Ecirc;"}, // à - uppercase E, circumflex accent<a name="line.77"></a> -<span class="sourceLineNo">078</span> {"\u00CB", "&Euml;"}, // à - uppercase E, umlaut<a name="line.78"></a> -<span class="sourceLineNo">079</span> {"\u00CC", "&Igrave;"}, // à - uppercase I, grave accent<a name="line.79"></a> -<span class="sourceLineNo">080</span> {"\u00CD", "&Iacute;"}, // à - uppercase I, acute accent<a name="line.80"></a> -<span class="sourceLineNo">081</span> {"\u00CE", "&Icirc;"}, // à - uppercase I, circumflex accent<a name="line.81"></a> -<span class="sourceLineNo">082</span> {"\u00CF", "&Iuml;"}, // à - uppercase I, umlaut<a name="line.82"></a> -<span class="sourceLineNo">083</span> {"\u00D0", "&ETH;"}, // à - uppercase Eth, Icelandic<a name="line.83"></a> -<span class="sourceLineNo">084</span> {"\u00D1", "&Ntilde;"}, // à - uppercase N, tilde<a name="line.84"></a> -<span class="sourceLineNo">085</span> {"\u00D2", "&Ograve;"}, // à - uppercase O, grave accent<a name="line.85"></a> -<span class="sourceLineNo">086</span> {"\u00D3", "&Oacute;"}, // à - uppercase O, acute accent<a name="line.86"></a> -<span class="sourceLineNo">087</span> {"\u00D4", "&Ocirc;"}, // à - uppercase O, circumflex accent<a name="line.87"></a> -<span class="sourceLineNo">088</span> {"\u00D5", "&Otilde;"}, // à - uppercase O, tilde<a name="line.88"></a> -<span class="sourceLineNo">089</span> {"\u00D6", "&Ouml;"}, // à - uppercase O, umlaut<a name="line.89"></a> -<span class="sourceLineNo">090</span> {"\u00D7", "&times;"}, // multiplication sign<a name="line.90"></a> -<span class="sourceLineNo">091</span> {"\u00D8", "&Oslash;"}, // à - uppercase O, slash<a name="line.91"></a> -<span class="sourceLineNo">092</span> {"\u00D9", "&Ugrave;"}, // à - uppercase U, grave accent<a name="line.92"></a> -<span class="sourceLineNo">093</span> {"\u00DA", "&Uacute;"}, // à - uppercase U, acute accent<a name="line.93"></a> -<span class="sourceLineNo">094</span> {"\u00DB", "&Ucirc;"}, // à - uppercase U, circumflex accent<a name="line.94"></a> -<span class="sourceLineNo">095</span> {"\u00DC", "&Uuml;"}, // à - uppercase U, umlaut<a name="line.95"></a> -<span class="sourceLineNo">096</span> {"\u00DD", "&Yacute;"}, // à - uppercase Y, acute accent<a name="line.96"></a> -<span class="sourceLineNo">097</span> {"\u00DE", "&THORN;"}, // à - uppercase THORN, Icelandic<a name="line.97"></a> -<span class="sourceLineNo">098</span> {"\u00DF", "&szlig;"}, // à - lowercase sharps, German<a name="line.98"></a> -<span class="sourceLineNo">099</span> {"\u00E0", "&agrave;"}, // à - lowercase a, grave accent<a name="line.99"></a> -<span class="sourceLineNo">100</span> {"\u00E1", "&aacute;"}, // á - lowercase a, acute accent<a name="line.100"></a> -<span class="sourceLineNo">101</span> {"\u00E2", "&acirc;"}, // â - lowercase a, circumflex accent<a name="line.101"></a> -<span class="sourceLineNo">102</span> {"\u00E3", "&atilde;"}, // ã - lowercase a, tilde<a name="line.102"></a> -<span class="sourceLineNo">103</span> {"\u00E4", "&auml;"}, // ä - lowercase a, umlaut<a name="line.103"></a> -<span class="sourceLineNo">104</span> {"\u00E5", "&aring;"}, // å - lowercase a, ring<a name="line.104"></a> -<span class="sourceLineNo">105</span> {"\u00E6", "&aelig;"}, // æ - lowercase ae<a name="line.105"></a> -<span class="sourceLineNo">106</span> {"\u00E7", "&ccedil;"}, // ç - lowercase c, cedilla<a name="line.106"></a> -<span class="sourceLineNo">107</span> {"\u00E8", "&egrave;"}, // è - lowercase e, grave accent<a name="line.107"></a> -<span class="sourceLineNo">108</span> {"\u00E9", "&eacute;"}, // é - lowercase e, acute accent<a name="line.108"></a> -<span class="sourceLineNo">109</span> {"\u00EA", "&ecirc;"}, // ê - lowercase e, circumflex accent<a name="line.109"></a> -<span class="sourceLineNo">110</span> {"\u00EB", "&euml;"}, // ë - lowercase e, umlaut<a name="line.110"></a> -<span class="sourceLineNo">111</span> {"\u00EC", "&igrave;"}, // ì - lowercase i, grave accent<a name="line.111"></a> -<span class="sourceLineNo">112</span> {"\u00ED", "&iacute;"}, // à - lowercase i, acute accent<a name="line.112"></a> -<span class="sourceLineNo">113</span> {"\u00EE", "&icirc;"}, // î - lowercase i, circumflex accent<a name="line.113"></a> -<span class="sourceLineNo">114</span> {"\u00EF", "&iuml;"}, // ï - lowercase i, umlaut<a name="line.114"></a> -<span class="sourceLineNo">115</span> {"\u00F0", "&eth;"}, // ð - lowercase eth, Icelandic<a name="line.115"></a> -<span class="sourceLineNo">116</span> {"\u00F1", "&ntilde;"}, // ñ - lowercase n, tilde<a name="line.116"></a> -<span class="sourceLineNo">117</span> {"\u00F2", "&ograve;"}, // ò - lowercase o, grave accent<a name="line.117"></a> -<span class="sourceLineNo">118</span> {"\u00F3", "&oacute;"}, // ó - lowercase o, acute accent<a name="line.118"></a> -<span class="sourceLineNo">119</span> {"\u00F4", "&ocirc;"}, // ô - lowercase o, circumflex accent<a name="line.119"></a> -<span class="sourceLineNo">120</span> {"\u00F5", "&otilde;"}, // õ - lowercase o, tilde<a name="line.120"></a> -<span class="sourceLineNo">121</span> {"\u00F6", "&ouml;"}, // ö - lowercase o, umlaut<a name="line.121"></a> -<span class="sourceLineNo">122</span> {"\u00F7", "&divide;"}, // division sign<a name="line.122"></a> -<span class="sourceLineNo">123</span> {"\u00F8", "&oslash;"}, // ø - lowercase o, slash<a name="line.123"></a> -<span class="sourceLineNo">124</span> {"\u00F9", "&ugrave;"}, // ù - lowercase u, grave accent<a name="line.124"></a> -<span class="sourceLineNo">125</span> {"\u00FA", "&uacute;"}, // ú - lowercase u, acute accent<a name="line.125"></a> -<span class="sourceLineNo">126</span> {"\u00FB", "&ucirc;"}, // û - lowercase u, circumflex accent<a name="line.126"></a> -<span class="sourceLineNo">127</span> {"\u00FC", "&uuml;"}, // ü - lowercase u, umlaut<a name="line.127"></a> -<span class="sourceLineNo">128</span> {"\u00FD", "&yacute;"}, // ý - lowercase y, acute accent<a name="line.128"></a> -<span class="sourceLineNo">129</span> {"\u00FE", "&thorn;"}, // þ - lowercase thorn, Icelandic<a name="line.129"></a> -<span class="sourceLineNo">130</span> {"\u00FF", "&yuml;"}, // ÿ - lowercase y, umlaut<a name="line.130"></a> -<span class="sourceLineNo">131</span> };<a name="line.131"></a> -<span class="sourceLineNo">132</span><a name="line.132"></a> -<span class="sourceLineNo">133</span> /**<a name="line.133"></a> -<span class="sourceLineNo">134</span> * Reverse of {@link #ISO8859_1_ESCAPE()} for unescaping purposes.<a name="line.134"></a> -<span class="sourceLineNo">135</span> * @return the mapping table<a name="line.135"></a> -<span class="sourceLineNo">136</span> */<a name="line.136"></a> -<span class="sourceLineNo">137</span> public static String[][] ISO8859_1_UNESCAPE() { return ISO8859_1_UNESCAPE.clone(); }<a name="line.137"></a> -<span class="sourceLineNo">138</span> private static final String[][] ISO8859_1_UNESCAPE = invert(ISO8859_1_ESCAPE);<a name="line.138"></a> -<span class="sourceLineNo">139</span><a name="line.139"></a> -<span class="sourceLineNo">140</span> /**<a name="line.140"></a> -<span class="sourceLineNo">141</span> * Mapping to escape additional <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">character entity<a name="line.141"></a> -<span class="sourceLineNo">142</span> * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE()} to get the full list of<a name="line.142"></a> -<span class="sourceLineNo">143</span> * HTML 4.0 character entities.<a name="line.143"></a> -<span class="sourceLineNo">144</span> * @return the mapping table<a name="line.144"></a> -<span class="sourceLineNo">145</span> */<a name="line.145"></a> -<span class="sourceLineNo">146</span> public static String[][] HTML40_EXTENDED_ESCAPE() { return HTML40_EXTENDED_ESCAPE.clone(); }<a name="line.146"></a> -<span class="sourceLineNo">147</span> private static final String[][] HTML40_EXTENDED_ESCAPE = {<a name="line.147"></a> -<span class="sourceLineNo">148</span> // <!-- Latin Extended-B --><a name="line.148"></a> -<span class="sourceLineNo">149</span> {"\u0192", "&fnof;"}, // latin small f with hook = function= florin, U+0192 ISOtech --><a name="line.149"></a> -<span class="sourceLineNo">150</span> // <!-- Greek --><a name="line.150"></a> -<span class="sourceLineNo">151</span> {"\u0391", "&Alpha;"}, // greek capital letter alpha, U+0391 --><a name="line.151"></a> -<span class="sourceLineNo">152</span> {"\u0392", "&Beta;"}, // greek capital letter beta, U+0392 --><a name="line.152"></a> -<span class="sourceLineNo">153</span> {"\u0393", "&Gamma;"}, // greek capital letter gamma,U+0393 ISOgrk3 --><a name="line.153"></a> -<span class="sourceLineNo">154</span> {"\u0394", "&Delta;"}, // greek capital letter delta,U+0394 ISOgrk3 --><a name="line.154"></a> -<span class="sourceLineNo">155</span> {"\u0395", "&Epsilon;"}, // greek capital letter epsilon, U+0395 --><a name="line.155"></a> -<span class="sourceLineNo">156</span> {"\u0396", "&Zeta;"}, // greek capital letter zeta, U+0396 --><a name="line.156"></a> -<span class="sourceLineNo">157</span> {"\u0397", "&Eta;"}, // greek capital letter eta, U+0397 --><a name="line.157"></a> -<span class="sourceLineNo">158</span> {"\u0398", "&Theta;"}, // greek capital letter theta,U+0398 ISOgrk3 --><a name="line.158"></a> -<span class="sourceLineNo">159</span> {"\u0399", "&Iota;"}, // greek capital letter iota, U+0399 --><a name="line.159"></a> -<span class="sourceLineNo">160</span> {"\u039A", "&Kappa;"}, // greek capital letter kappa, U+039A --><a name="line.160"></a> -<span class="sourceLineNo">161</span> {"\u039B", "&Lambda;"}, // greek capital letter lambda,U+039B ISOgrk3 --><a name="line.161"></a> -<span class="sourceLineNo">162</span> {"\u039C", "&Mu;"}, // greek capital letter mu, U+039C --><a name="line.162"></a> -<span class="sourceLineNo">163</span> {"\u039D", "&Nu;"}, // greek capital letter nu, U+039D --><a name="line.163"></a> -<span class="sourceLineNo">164</span> {"\u039E", "&Xi;"}, // greek capital letter xi, U+039E ISOgrk3 --><a name="line.164"></a> -<span class="sourceLineNo">165</span> {"\u039F", "&Omicron;"}, // greek capital letter omicron, U+039F --><a name="line.165"></a> -<span class="sourceLineNo">166</span> {"\u03A0", "&Pi;"}, // greek capital letter pi, U+03A0 ISOgrk3 --><a name="line.166"></a> -<span class="sourceLineNo">167</span> {"\u03A1", "&Rho;"}, // greek capital letter rho, U+03A1 --><a name="line.167"></a> -<span class="sourceLineNo">168</span> // <!-- there is no Sigmaf, and no U+03A2 character either --><a name="line.168"></a> -<span class="sourceLineNo">169</span> {"\u03A3", "&Sigma;"}, // greek capital letter sigma,U+03A3 ISOgrk3 --><a name="line.169"></a> -<span class="sourceLineNo">170</span> {"\u03A4", "&Tau;"}, // greek capital letter tau, U+03A4 --><a name="line.170"></a> -<span class="sourceLineNo">171</span> {"\u03A5", "&Upsilon;"}, // greek capital letter upsilon,U+03A5 ISOgrk3 --><a name="line.171"></a> -<span class="sourceLineNo">172</span> {"\u03A6", "&Phi;"}, // greek capital letter phi,U+03A6 ISOgrk3 --><a name="line.172"></a> -<span class="sourceLineNo">173</span> {"\u03A7", "&Chi;"}, // greek capital letter chi, U+03A7 --><a name="line.173"></a> -<span class="sourceLineNo">174</span> {"\u03A8", "&Psi;"}, // greek capital letter psi,U+03A8 ISOgrk3 --><a name="line.174"></a> -<span class="sourceLineNo">175</span> {"\u03A9", "&Omega;"}, // greek capital letter omega,U+03A9 ISOgrk3 --><a name="line.175"></a> -<span class="sourceLineNo">176</span> {"\u03B1", "&alpha;"}, // greek small letter alpha,U+03B1 ISOgrk3 --><a name="line.176"></a> -<span class="sourceLineNo">177</span> {"\u03B2", "&beta;"}, // greek small letter beta, U+03B2 ISOgrk3 --><a name="line.177"></a> -<span class="sourceLineNo">178</span> {"\u03B3", "&gamma;"}, // greek small letter gamma,U+03B3 ISOgrk3 --><a name="line.178"></a> -<span class="sourceLineNo">179</span> {"\u03B4", "&delta;"}, // greek small letter delta,U+03B4 ISOgrk3 --><a name="line.179"></a> -<span class="sourceLineNo">180</span> {"\u03B5", "&epsilon;"}, // greek small letter epsilon,U+03B5 ISOgrk3 --><a name="line.180"></a> -<span class="sourceLineNo">181</span> {"\u03B6", "&zeta;"}, // greek small letter zeta, U+03B6 ISOgrk3 --><a name="line.181"></a> -<span class="sourceLineNo">182</span> {"\u03B7", "&eta;"}, // greek small letter eta, U+03B7 ISOgrk3 --><a name="line.182"></a> -<span class="sourceLineNo">183</span> {"\u03B8", "&theta;"}, // greek small letter theta,U+03B8 ISOgrk3 --><a name="line.183"></a> -<span class="sourceLineNo">184</span> {"\u03B9", "&iota;"}, // greek small letter iota, U+03B9 ISOgrk3 --><a name="line.184"></a> -<span class="sourceLineNo">185</span> {"\u03BA", "&kappa;"}, // greek small letter kappa,U+03BA ISOgrk3 --><a name="line.185"></a> -<span class="sourceLineNo">186</span> {"\u03BB", "&lambda;"}, // greek small letter lambda,U+03BB ISOgrk3 --><a name="line.186"></a> -<span class="sourceLineNo">187</span> {"\u03BC", "&mu;"}, // greek small letter mu, U+03BC ISOgrk3 --><a name="line.187"></a> -<span class="sourceLineNo">188</span> {"\u03BD", "&nu;"}, // greek small letter nu, U+03BD ISOgrk3 --><a name="line.188"></a> -<span class="sourceLineNo">189</span> {"\u03BE", "&xi;"}, // greek small letter xi, U+03BE ISOgrk3 --><a name="line.189"></a> -<span class="sourceLineNo">190</span> {"\u03BF", "&omicron;"}, // greek small letter omicron, U+03BF NEW --><a name="line.190"></a> -<span class="sourceLineNo">191</span> {"\u03C0", "&pi;"}, // greek small letter pi, U+03C0 ISOgrk3 --><a name="line.191"></a> -<span class="sourceLineNo">192</span> {"\u03C1", "&rho;"}, // greek small letter rho, U+03C1 ISOgrk3 --><a name="line.192"></a> -<span class="sourceLineNo">193</span> {"\u03C2", "&sigmaf;"}, // greek small letter final sigma,U+03C2 ISOgrk3 --><a name="line.193"></a> -<span class="sourceLineNo">194</span> {"\u03C3", "&sigma;"}, // greek small letter sigma,U+03C3 ISOgrk3 --><a name="line.194"></a> -<span class="sourceLineNo">195</span> {"\u03C4", "&tau;"}, // greek small letter tau, U+03C4 ISOgrk3 --><a name="line.195"></a> -<span class="sourceLineNo">196</span> {"\u03C5", "&upsilon;"}, // greek small letter upsilon,U+03C5 ISOgrk3 --><a name="line.196"></a> -<span class="sourceLineNo">197</span> {"\u03C6", "&phi;"}, // greek small letter phi, U+03C6 ISOgrk3 --><a name="line.197"></a> -<span class="sourceLineNo">198</span> {"\u03C7", "&chi;"}, // greek small letter chi, U+03C7 ISOgrk3 --><a name="line.198"></a> -<span class="sourceLineNo">199</span> {"\u03C8", "&psi;"}, // greek small letter psi, U+03C8 ISOgrk3 --><a name="line.199"></a> -<span class="sourceLineNo">200</span> {"\u03C9", "&omega;"}, // greek small letter omega,U+03C9 ISOgrk3 --><a name="line.200"></a> -<span class="sourceLineNo">201</span> {"\u03D1", "&thetasym;"}, // greek small letter theta symbol,U+03D1 NEW --><a name="line.201"></a> -<span class="sourceLineNo">202</span> {"\u03D2", "&upsih;"}, // greek upsilon with hook symbol,U+03D2 NEW --><a name="line.202"></a> -<span class="sourceLineNo">203</span> {"\u03D6", "&piv;"}, // greek pi symbol, U+03D6 ISOgrk3 --><a name="line.203"></a> -<span class="sourceLineNo">204</span> // <!-- General Punctuation --><a name="line.204"></a> -<span class="sourceLineNo">205</span> {"\u2022", "&bull;"}, // bullet = black small circle,U+2022 ISOpub --><a name="line.205"></a> -<span class="sourceLineNo">206</span> // <!-- bullet is NOT the same as bullet operator, U+2219 --><a name="line.206"></a> -<span class="sourceLineNo">207</span> {"\u2026", "&hellip;"}, // horizontal ellipsis = three dot leader,U+2026 ISOpub --><a name="line.207"></a> -<span class="sourceLineNo">208</span> {"\u2032", "&prime;"}, // prime = minutes = feet, U+2032 ISOtech --><a name="line.208"></a> -<span class="sourceLineNo">209</span> {"\u2033", "&Prime;"}, // double prime = seconds = inches,U+2033 ISOtech --><a name="line.209"></a> -<span class="sourceLineNo">210</span> {"\u203E", "&oline;"}, // overline = spacing overscore,U+203E NEW --><a name="line.210"></a> -<span class="sourceLineNo">211</span> {"\u2044", "&frasl;"}, // fraction slash, U+2044 NEW --><a name="line.211"></a> -<span class="sourceLineNo">212</span> // <!-- Letterlike Symbols --><a name="line.212"></a> -<span class="sourceLineNo">213</span> {"\u2118", "&weierp;"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso --><a name="line.213"></a> -<span class="sourceLineNo">214</span> {"\u2111", "&image;"}, // blackletter capital I = imaginary part,U+2111 ISOamso --><a name="line.214"></a> -<span class="sourceLineNo">215</span> {"\u211C", "&real;"}, // blackletter capital R = real part symbol,U+211C ISOamso --><a name="line.215"></a> -<span class="sourceLineNo">216</span> {"\u2122", "&trade;"}, // trade mark sign, U+2122 ISOnum --><a name="line.216"></a> -<span class="sourceLineNo">217</span> {"\u2135", "&alefsym;"}, // alef symbol = first transfinite cardinal,U+2135 NEW --><a name="line.217"></a> -<span class="sourceLineNo">218</span> // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the<a name="line.218"></a> -<span class="sourceLineNo">219</span> // same glyph could be used to depict both characters --><a name="line.219"></a> -<span class="sourceLineNo">220</span> // <!-- Arrows --><a name="line.220"></a> -<span class="sourceLineNo">221</span> {"\u2190", "&larr;"}, // leftwards arrow, U+2190 ISOnum --><a name="line.221"></a> -<span class="sourceLineNo">222</span> {"\u2191", "&uarr;"}, // upwards arrow, U+2191 ISOnum--><a name="line.222"></a> -<span class="sourceLineNo">223</span> {"\u2192", "&rarr;"}, // rightwards arrow, U+2192 ISOnum --><a name="line.223"></a> -<span class="sourceLineNo">224</span> {"\u2193", "&darr;"}, // downwards arrow, U+2193 ISOnum --><a name="line.224"></a> -<span class="sourceLineNo">225</span> {"\u2194", "&harr;"}, // left right arrow, U+2194 ISOamsa --><a name="line.225"></a> -<span class="sourceLineNo">226</span> {"\u21B5", "&crarr;"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW --><a name="line.226"></a> -<span class="sourceLineNo">227</span> {"\u21D0", "&lArr;"}, // leftwards double arrow, U+21D0 ISOtech --><a name="line.227"></a> -<span class="sourceLineNo">228</span> // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'<a name="line.228"></a> -<span class="sourceLineNo">229</span> // arrow but also does not have any other character for that function.<a name="line.229"></a> -<span class="sourceLineNo">230</span> // So ? lArr canbe used for 'is implied by' as ISOtech suggests --><a name="line.230"></a> -<span class="sourceLineNo">231</span> {"\u21D1", "&uArr;"}, // upwards double arrow, U+21D1 ISOamsa --><a name="line.231"></a> -<span class="sourceLineNo">232</span> {"\u21D2", "&rArr;"}, // rightwards double arrow,U+21D2 ISOtech --><a name="line.232"></a> -<span class="sourceLineNo">233</span> // <!-- ISO 10646 does not say this is the 'implies' character but does not<a name="line.233"></a> -<span class="sourceLineNo">234</span> // have another character with this function so ?rArr can be used for<a name="line.234"></a> -<span class="sourceLineNo">235</span> // 'implies' as ISOtech suggests --><a name="line.235"></a> -<span class="sourceLineNo">236</span> {"\u21D3", "&dArr;"}, // downwards double arrow, U+21D3 ISOamsa --><a name="line.236"></a> -<span class="sourceLineNo">237</span> {"\u21D4", "&hArr;"}, // left right double arrow,U+21D4 ISOamsa --><a name="line.237"></a> -<span class="sourceLineNo">238</span> // <!-- Mathematical Operators --><a name="line.238"></a> -<span class="sourceLineNo">239</span> {"\u2200", "&forall;"}, // for all, U+2200 ISOtech --><a name="line.239"></a> -<span class="sourceLineNo">240</span> {"\u2202", "&part;"}, // partial differential, U+2202 ISOtech --><a name="line.240"></a> -<span class="sourceLineNo">241</span> {"\u2203", "&exist;"}, // there exists, U+2203 ISOtech --><a name="line.241"></a> -<span class="sourceLineNo">242</span> {"\u2205", "&empty;"}, // empty set = null set = diameter,U+2205 ISOamso --><a name="line.242"></a> -<span class="sourceLineNo">243</span> {"\u2207", "&nabla;"}, // nabla = backward difference,U+2207 ISOtech --><a name="line.243"></a> -<span class="sourceLineNo">244</span> {"\u2208", "&isin;"}, // element of, U+2208 ISOtech --><a name="line.244"></a> -<span class="sourceLineNo">245</span> {"\u2209", "&notin;"}, // not an element of, U+2209 ISOtech --><a name="line.245"></a> -<span class="sourceLineNo">246</span> {"\u220B", "&ni;"}, // contains as member, U+220B ISOtech --><a name="line.246"></a> -<span class="sourceLineNo">247</span> // <!-- should there be a more memorable name than 'ni'? --><a name="line.247"></a> -<span class="sourceLineNo">248</span> {"\u220F", "&prod;"}, // n-ary product = product sign,U+220F ISOamsb --><a name="line.248"></a> -<span class="sourceLineNo">249</span> // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'<a name="line.249"></a> -<span class="sourceLineNo">250</span> // though the same glyph might be used for both --><a name="line.250"></a> -<span class="sourceLineNo">251</span> {"\u2211", "&sum;"}, // n-ary summation, U+2211 ISOamsb --><a name="line.251"></a> -<span class="sourceLineNo">252</span> // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'<a name="line.252"></a> -<span class="sourceLineNo">253</span> // though the same glyph might be used for both --><a name="line.253"></a> -<span class="sourceLineNo">254</span> {"\u2212", "&minus;"}, // minus sign, U+2212 ISOtech --><a name="line.254"></a> -<span class="sourceLineNo">255</span> {"\u2217", "&lowast;"}, // asterisk operator, U+2217 ISOtech --><a name="line.255"></a> -<span class="sourceLineNo">256</span> {"\u221A", "&radic;"}, // square root = radical sign,U+221A ISOtech --><a name="line.256"></a> -<span class="sourceLineNo">257</span> {"\u221D", "&prop;"}, // proportional to, U+221D ISOtech --><a name="line.257"></a> -<span class="sourceLineNo">258</span> {"\u221E", "&infin;"}, // infinity, U+221E ISOtech --><a name="line.258"></a> -<span class="sourceLineNo">259</span> {"\u2220", "&ang;"}, // angle, U+2220 ISOamso --><a name="line.259"></a> -<span class="sourceLineNo">260</span> {"\u2227", "&and;"}, // logical and = wedge, U+2227 ISOtech --><a name="line.260"></a> -<span class="sourceLineNo">261</span> {"\u2228", "&or;"}, // logical or = vee, U+2228 ISOtech --><a name="line.261"></a> -<span class="sourceLineNo">262</span> {"\u2229", "&cap;"}, // intersection = cap, U+2229 ISOtech --><a name="line.262"></a> -<span class="sourceLineNo">263</span> {"\u222A", "&cup;"}, // union = cup, U+222A ISOtech --><a name="line.263"></a> -<span class="sourceLineNo">264</span> {"\u222B", "&int;"}, // integral, U+222B ISOtech --><a name="line.264"></a> -<span class="sourceLineNo">265</span> {"\u2234", "&there4;"}, // therefore, U+2234 ISOtech --><a name="line.265"></a> -<span class="sourceLineNo">266</span> {"\u223C", "&sim;"}, // tilde operator = varies with = similar to,U+223C ISOtech --><a name="line.266"></a> -<span class="sourceLineNo">267</span> // <!-- tilde operator is NOT the same character as the tilde, U+007E,although<a name="line.267"></a> -<span class="sourceLineNo">268</span> // the same glyph might be used to represent both --><a name="line.268"></a> -<span class="sourceLineNo">269</span> {"\u2245", "&cong;"}, // approximately equal to, U+2245 ISOtech --><a name="line.269"></a> -<span class="sourceLineNo">270</span> {"\u2248", "&asymp;"}, // almost equal to = asymptotic to,U+2248 ISOamsr --><a name="line.270"></a> -<span class="sourceLineNo">271</span> {"\u2260", "&ne;"}, // not equal to, U+2260 ISOtech --><a name="line.271"></a> -<span class="sourceLineNo">272</span> {"\u2261", "&equiv;"}, // identical to, U+2261 ISOtech --><a name="line.272"></a> -<span class="sourceLineNo">273</span> {"\u2264", "&le;"}, // less-than or equal to, U+2264 ISOtech --><a name="line.273"></a> -<span class="sourceLineNo">274</span> {"\u2265", "&ge;"}, // greater-than or equal to,U+2265 ISOtech --><a name="line.274"></a> -<span class="sourceLineNo">275</span> {"\u2282", "&sub;"}, // subset of, U+2282 ISOtech --><a name="line.275"></a> -<span class="sourceLineNo">276</span> {"\u2283", "&sup;"}, // superset of, U+2283 ISOtech --><a name="line.276"></a> -<span class="sourceLineNo">277</span> // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the<a name="line.277"></a> -<span class="sourceLineNo">278</span> // Symbol font encoding and is not included. Should it be, for symmetry?<a name="line.278"></a> -<span class="sourceLineNo">279</span> // It is in ISOamsn -->,<a name="line.279"></a> -<span class="sourceLineNo">280</span> {"\u2284", "&nsub;"}, // not a subset of, U+2284 ISOamsn --><a name="line.280"></a> -<span class="sourceLineNo">281</span> {"\u2286", "&sube;"}, // subset of or equal to, U+2286 ISOtech --><a name="line.281"></a> -<span class="sourceLineNo">282</span> {"\u2287", "&supe;"}, // superset of or equal to,U+2287 ISOtech --><a name="line.282"></a> -<span class="sourceLineNo">283</span> {"\u2295", "&oplus;"}, // circled plus = direct sum,U+2295 ISOamsb --><a name="line.283"></a> -<span class="sourceLineNo">284</span> {"\u2297", "&otimes;"}, // circled times = vector product,U+2297 ISOamsb --><a name="line.284"></a> -<span class="sourceLineNo">285</span> {"\u22A5", "&perp;"}, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech --><a name="line.285"></a> -<span class="sourceLineNo">286</span> {"\u22C5", "&sdot;"}, // dot operator, U+22C5 ISOamsb --><a name="line.286"></a> -<span class="sourceLineNo">287</span> // <!-- dot operator is NOT the same character as U+00B7 middle dot --><a name="line.287"></a> -<span class="sourceLineNo">288</span> // <!-- Miscellaneous Technical --><a name="line.288"></a> -<span class="sourceLineNo">289</span> {"\u2308", "&lceil;"}, // left ceiling = apl upstile,U+2308 ISOamsc --><a name="line.289"></a> -<span class="sourceLineNo">290</span> {"\u2309", "&rceil;"}, // right ceiling, U+2309 ISOamsc --><a name="line.290"></a> -<span class="sourceLineNo">291</span> {"\u230A", "&lfloor;"}, // left floor = apl downstile,U+230A ISOamsc --><a name="line.291"></a> -<span class="sourceLineNo">292</span> {"\u230B", "&rfloor;"}, // right floor, U+230B ISOamsc --><a name="line.292"></a> -<span class="sourceLineNo">293</span> {"\u2329", "&lang;"}, // left-pointing angle bracket = bra,U+2329 ISOtech --><a name="line.293"></a> -<span class="sourceLineNo">294</span> // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation<a name="line.294"></a> -<span class="sourceLineNo">295</span> // mark' --><a name="line.295"></a> -<span class="sourceLineNo">296</span> {"\u232A", "&rang;"}, // right-pointing angle bracket = ket,U+232A ISOtech --><a name="line.296"></a> -<span class="sourceLineNo">297</span> // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A<a name="line.297"></a> -<span class="sourceLineNo">298</span> // 'single right-pointing angle quotation mark' --><a name="line.298"></a> -<span class="sourceLineNo">299</span> // <!-- Geometric Shapes --><a name="line.299"></a> -<span class="sourceLineNo">300</span> {"\u25CA", "&loz;"}, // lozenge, U+25CA ISOpub --><a name="line.300"></a> -<span class="sourceLineNo">301</span> // <!-- Miscellaneous Symbols --><a name="line.301"></a> -<span class="sourceLineNo">302</span> {"\u2660", "&spades;"}, // black spade suit, U+2660 ISOpub --><a name="line.302"></a> -<span class="sourceLineNo">303</span> // <!-- black here seems to mean filled as opposed to hollow --><a name="line.303"></a> -<span class="sourceLineNo">304</span> {"\u2663", "&clubs;"}, // black club suit = shamrock,U+2663 ISOpub --><a name="line.304"></a> -<span class="sourceLineNo">305</span> {"\u2665", "&hearts;"}, // black heart suit = valentine,U+2665 ISOpub --><a name="line.305"></a> -<span class="sourceLineNo">306</span> {"\u2666", "&diams;"}, // black diamond suit, U+2666 ISOpub --><a name="line.306"></a> -<span class="sourceLineNo">307</span><a name="line.307"></a> -<span class="sourceLineNo">308</span> // <!-- Latin Extended-A --><a name="line.308"></a> -<span class="sourceLineNo">309</span> {"\u0152", "&OElig;"}, // -- latin capital ligature OE,U+0152 ISOlat2 --><a name="line.309"></a> -<span class="sourceLineNo">310</span> {"\u0153", "&oelig;"}, // -- latin small ligature oe, U+0153 ISOlat2 --><a name="line.310"></a> -<span class="sourceLineNo">311</span> // <!-- ligature is a misnomer, this is a separate character in some languages --><a name="line.311"></a> -<span class="sourceLineNo">312</span> {"\u0160", "&Scaron;"}, // -- latin capital letter S with caron,U+0160 ISOlat2 --><a name="line.312"></a> -<span class="sourceLineNo">313</span> {"\u0161", "&scaron;"}, // -- latin small letter s with caron,U+0161 ISOlat2 --><a name="line.313"></a> -<span class="sourceLineNo">314</span> {"\u0178", "&Yuml;"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 --><a name="line.314"></a> -<span class="sourceLineNo">315</span> // <!-- Spacing Modifier Letters --><a name="line.315"></a> -<span class="sourceLineNo">316</span> {"\u02C6", "&circ;"}, // -- modifier letter circumflex accent,U+02C6 ISOpub --><a name="line.316"></a> -<span class="sourceLineNo">317</span> {"\u02DC", "&tilde;"}, // small tilde, U+02DC ISOdia --><a name="line.317"></a> -<span class="sourceLineNo">318</span> // <!-- General Punctuation --><a name="line.318"></a> -<span class="sourceLineNo">319</span> {"\u2002", "&ensp;"}, // en space, U+2002 ISOpub --><a name="line.319"></a> -<span class="sourceLineNo">320</span> {"\u2003", "&emsp;"}, // em space, U+2003 ISOpub --><a name="line.320"></a> -<span class="sourceLineNo">321</span> {"\u2009", "&thinsp;"}, // thin space, U+2009 ISOpub --><a name="line.321"></a> -<span class="sourceLineNo">322</span> {"\u200C", "&zwnj;"}, // zero width non-joiner,U+200C NEW RFC 2070 --><a name="line.322"></a> -<span class="sourceLineNo">323</span> {"\u200D", "&zwj;"}, // zero width joiner, U+200D NEW RFC 2070 --><a name="line.323"></a> -<span class="sourceLineNo">324</span> {"\u200E", "&lrm;"}, // left-to-right mark, U+200E NEW RFC 2070 --><a name="line.324"></a> -<span class="sourceLineNo">325</span> {"\u200F", "&rlm;"}, // right-to-left mark, U+200F NEW RFC 2070 --><a name="line.325"></a> -<span class="sourceLineNo">326</span> {"\u2013", "&ndash;"}, // en dash, U+2013 ISOpub --><a name="line.326"></a> -<span class="sourceLineNo">327</span> {"\u2014", "&mdash;"}, // em dash, U+2014 ISOpub --><a name="line.327"></a> -<span class="sourceLineNo">328</span> {"\u2018", "&lsquo;"}, // left single quotation mark,U+2018 ISOnum --><a name="line.328"></a> -<span class="sourceLineNo">329</span> {"\u2019", "&rsquo;"}, // right single quotation mark,U+2019 ISOnum --><a name="line.329"></a> -<span class="sourceLineNo">330</span> {"\u201A", "&sbquo;"}, // single low-9 quotation mark, U+201A NEW --><a name="line.330"></a> -<span class="sourceLineNo">331</span> {"\u201C", "&ldquo;"}, // left double quotation mark,U+201C ISOnum --><a name="line.331"></a> -<span class="sourceLineNo">332</span> {"\u201D", "&rdquo;"}, // right double quotation mark,U+201D ISOnum --><a name="line.332"></a> -<span class="sourceLineNo">333</span> {"\u201E", "&bdquo;"}, // double low-9 quotation mark, U+201E NEW --><a name="line.333"></a> -<span class="sourceLineNo">334</span> {"\u2020", "&dagger;"}, // dagger, U+2020 ISOpub --><a name="line.334"></a> -<span class="sourceLineNo">335</span> {"\u2021", "&Dagger;"}, // double dagger, U+2021 ISOpub --><a name="line.335"></a> -<span class="sourceLineNo">336</span> {"\u2030", "&permil;"}, // per mille sign, U+2030 ISOtech --><a name="line.336"></a> -<span class="sourceLineNo">337</span> {"\u2039", "&lsaquo;"}, // single left-pointing angle quotation mark,U+2039 ISO proposed --><a name="line.337"></a> -<span class="sourceLineNo">338</span> // <!-- lsaquo is proposed but not yet ISO standardized --><a name="line.338"></a> -<span class="sourceLineNo">339</span> {"\u203A", "&rsaquo;"}, // single right-pointing angle quotation mark,U+203A ISO proposed --><a name="line.339"></a> -<span class="sourceLineNo">340</span> // <!-- rsaquo is proposed but not yet ISO standardized --><a name="line.340"></a> -<span class="sourceLineNo">341</span> {"\u20AC", "&euro;"}, // -- euro sign, U+20AC NEW --><a name="line.341"></a> -<span class="sourceLineNo">342</span> };<a name="line.342"></a> -<span class="sourceLineNo">343</span><a name="line.343"></a> -<span class="sourceLineNo">344</span> /**<a name="line.344"></a> -<span class="sourceLineNo">345</span> * Reverse of {@link #HTML40_EXTENDED_ESCAPE()} for unescaping purposes.<a name="line.345"></a> -<span class="sourceLineNo">346</span> * @return the mapping table<a name="line.346"></a> -<span class="sourceLineNo">347</span> */<a name="line.347"></a> -<span class="sourceLineNo">348</span> public static String[][] HTML40_EXTENDED_UNESCAPE() { return HTML40_EXTENDED_UNESCAPE.clone(); }<a name="line.348"></a> -<span class="sourceLineNo">349</span> private static final String[][] HTML40_EXTENDED_UNESCAPE = invert(HTML40_EXTENDED_ESCAPE);<a name="line.349"></a> -<span class="sourceLineNo">350</span><a name="line.350"></a> -<span class="sourceLineNo">351</span> /**<a name="line.351"></a> -<span class="sourceLineNo">352</span> * Mapping to escape the basic XML and HTML character entities.<a name="line.352"></a> -<span class="sourceLineNo">353</span> *<a name="line.353"></a> -<span class="sourceLineNo">354</span> * Namely: {@code " & < >}<a name="line.354"></a> -<span class="sourceLineNo">355</span> * @return the mapping table<a name="line.355"></a> -<span class="sourceLineNo">356</span> */<a name="line.356"></a> -<span class="sourceLineNo">357</span> public static String[][] BASIC_ESCAPE() { return BASIC_ESCAPE.clone(); }<a name="line.357"></a> -<span class="sourceLineNo">358</span> private static final String[][] BASIC_ESCAPE = {<a name="line.358"></a> -<span class="sourceLineNo">359</span> {"\"", "&quot;"}, // " - double-quote<a name="line.359"></a> -<span class="sourceLineNo">360</span> {"&", "&amp;"}, // & - ampersand<a name="line.360"></a> -<span class="sourceLineNo">361</span> {"<", "&lt;"}, // < - less-than<a name="line.361"></a> -<span class="sourceLineNo">362</span> {">", "&gt;"}, // > - greater-than<a name="line.362"></a> -<span class="sourceLineNo">363</span> };<a name="line.363"></a> -<span class="sourceLineNo">364</span><a name="line.364"></a> -<span class="sourceLineNo">365</span> /**<a name="line.365"></a> -<span class="sourceLineNo">366</span> * Reverse of {@link #BASIC_ESCAPE()} for unescaping purposes.<a name="line.366"></a> -<span class="sourceLineNo">367</span> * @return the mapping table<a name="line.367"></a> -<span class="sourceLineNo">368</span> */<a name="line.368"></a> -<span class="sourceLineNo">369</span> public static String[][] BASIC_UNESCAPE() { return BASIC_UNESCAPE.clone(); }<a name="line.369"></a> -<span class="sourceLineNo">370</span> private static final String[][] BASIC_UNESCAPE = invert(BASIC_ESCAPE);<a name="line.370"></a> -<span class="sourceLineNo">371</span><a name="line.371"></a> -<span class="sourceLineNo">372</span> /**<a name="line.372"></a> -<span class="sourceLineNo">373</span> * Mapping to escape the apostrophe character to its XML character entity.<a name="line.373"></a> -<span class="sourceLineNo">374</span> * @return the mapping table<a name="line.374"></a> -<span class="sourceLineNo">375</span> */<a name="line.375"></a> -<span class="sourceLineNo">376</span> public static String[][] APOS_ESCAPE() { return APOS_ESCAPE.clone(); }<a name="line.376"></a> -<span class="sourceLineNo">377</span> private static final String[][] APOS_ESCAPE = {<a name="line.377"></a> -<span class="sourceLineNo">378</span> {"'", "&apos;"}, // XML apostrophe<a name="line.378"></a> -<span class="sourceLineNo">379</span> };<a name="line.379"></a> -<span class="sourceLineNo">380</span><a name="line.380"></a> -<span class="sourceLineNo">381</span> /**<a name="line.381"></a> -<span class="sourceLineNo">382</span> * Reverse of {@link #APOS_ESCAPE()} for unescaping purposes.<a name="line.382"></a> -<span class="sourceLineNo">383</span> * @return the mapping table<a name="line.383"></a> -<span class="sourceLineNo">384</span> */<a name="line.384"></a> -<span class="sourceLineNo">385</span> public static String[][] APOS_UNESCAPE() { return APOS_UNESCAPE.clone(); }<a name="line.385"></a> -<span class="sourceLineNo">386</span> private static final String[][] APOS_UNESCAPE = invert(APOS_ESCAPE);<a name="line.386"></a> -<span class="sourceLineNo">387</span><a name="line.387"></a> -<span class="sourceLineNo">388</span> /**<a name="line.388"></a> -<span class="sourceLineNo">389</span> * Mapping to escape the Java control characters.<a name="line.389"></a> -<span class="sourceLineNo">390</span> *<a name="line.390"></a> -<span class="sourceLineNo">391</span> * Namely: {@code \b \n \t \f \r}<a name="line.391"></a> -<span class="sourceLineNo">392</span> * @return the mapping table<a name="line.392"></a> -<span class="sourceLineNo">393</span> */<a name="line.393"></a> -<span class="sourceLineNo">394</span> public static String[][] JAVA_CTRL_CHARS_ESCAPE() { return JAVA_CTRL_CHARS_ESCAPE.clone(); }<a name="line.394"></a> -<span class="sourceLineNo">395</span> private static final String[][] JAVA_CTRL_CHARS_ESCAPE = {<a name="line.395"></a> -<span class="sourceLineNo">396</span> {"\b", "\\b"},<a name="line.396"></a> -<span class="sourceLineNo">397</span> {"\n", "\\n"},<a name="line.397"></a> -<span class="sourceLineNo">398</span> {"\t", "\\t"},<a name="line.398"></a> -<span class="sourceLineNo">399</span> {"\f", "\\f"},<a name="line.399"></a> -<span class="sourceLineNo">400</span> {"\r", "\\r"}<a name="line.400"></a> -<span class="sourceLineNo">401</span> };<a name="line.401"></a> -<span class="sourceLineNo">402</span><a name="line.402"></a> -<span class="sourceLineNo">403</span> /**<a name="line.403"></a> -<span class="sourceLineNo">404</span> * Reverse of {@link #JAVA_CTRL_CHARS_ESCAPE()} for unescaping purposes.<a name="line.404"></a> -<span class="sourceLineNo">405</span> * @return the mapping table<a name="line.405"></a> -<span class="sourceLineNo">406</span> */<a name="line.406"></a> -<span class="sourceLineNo">407</span> public static String[][] JAVA_CTRL_CHARS_UNESCAPE() { return JAVA_CTRL_CHARS_UNESCAPE.clone(); }<a name="line.407"></a> -<span class="sourceLineNo">408</span> private static final String[][] JAVA_CTRL_CHARS_UNESCAPE = invert(JAVA_CTRL_CHARS_ESCAPE);<a name="line.408"></a> -<span class="sourceLineNo">409</span><a name="line.409"></a> -<span class="sourceLineNo">410</span> /**<a name="line.410"></a> -<span class="sourceLineNo">411</span> * Used to invert an escape array into an unescape array<a name="line.411"></a> -<span class="sourceLineNo">412</span> * @param array String[][] to be inverted<a name="line.412"></a> -<span class="sourceLineNo">413</span> * @return String[][] inverted array<a name="line.413"></a> -<span class="sourceLineNo">414</span> */<a name="line.414"></a> -<span class="sourceLineNo">415</span> public static String[][] invert(final String[][] array) {<a name="line.415"></a> -<span class="sourceLineNo">416</span> final String[][] newarray = new String[array.length][2];<a name="line.416"></a> -<span class="sourceLineNo">417</span> for(int i = 0; i<array.length; i++) {<a name="line.417"></a> -<span class="sourceLineNo">418</span> newarray[i][0] = array[i][1];<a name="line.418"></a> -<span class="sourceLineNo">419</span> newarray[i][1] = array[i][0];<a name="line.419"></a> -<span class="sourceLineNo">420</span> }<a name="line.420"></a> -<span class="sourceLineNo">421</span> return newarray;<a name="line.421"></a> -<span class="sourceLineNo">422</span> }<a name="line.422"></a> -<span class="sourceLineNo">423</span><a name="line.423"></a> -<span class="sourceLineNo">424</span>}<a name="line.424"></a> +<span class="sourceLineNo">019</span>import java.util.Collections;<a name="line.19"></a> +<span class="sourceLineNo">020</span>import java.util.HashMap;<a name="line.20"></a> +<span class="sourceLineNo">021</span>import java.util.Map;<a name="line.21"></a> +<span class="sourceLineNo">022</span><a name="line.22"></a> +<span class="sourceLineNo">023</span>/**<a name="line.23"></a> +<span class="sourceLineNo">024</span> * Class holding various entity data for HTML and XML - generally for use with<a name="line.24"></a> +<span class="sourceLineNo">025</span> * the LookupTranslator.<a name="line.25"></a> +<span class="sourceLineNo">026</span> * All Maps are generated using <code>java.util.Collections.unmodifiableMap()</code>.<a name="line.26"></a> +<span class="sourceLineNo">027</span> *<a name="line.27"></a> +<span class="sourceLineNo">028</span> * @since 1.0<a name="line.28"></a> +<span class="sourceLineNo">029</span> */<a name="line.29"></a> +<span class="sourceLineNo">030</span>public class EntityArrays {<a name="line.30"></a> +<span class="sourceLineNo">031</span><a name="line.31"></a> +<span class="sourceLineNo">032</span> /**<a name="line.32"></a> +<span class="sourceLineNo">033</span> * A Map&lt;CharSequence, CharSequence&gt; to to escape<a name="line.33"></a> +<span class="sourceLineNo">034</span> * <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1">ISO-8859-1</a><a name="line.34"></a> +<span class="sourceLineNo">035</span> * characters to their named HTML 3.x equivalents.<a name="line.35"></a> +<span class="sourceLineNo">036</span> */<a name="line.36"></a> +<span class="sourceLineNo">037</span> public static final Map<CharSequence, CharSequence> ISO8859_1_ESCAPE;<a name="line.37"></a> +<span class="sourceLineNo">038</span> static {<a name="line.38"></a> +<span class="sourceLineNo">039</span> Map<CharSequence, CharSequence> initialMap = new HashMap<>();<a name="line.39"></a> +<span class="sourceLineNo">040</span> initialMap.put("\u00A0", "&nbsp;"); // non-breaking space<a name="line.40"></a> +<span class="sourceLineNo">041</span> initialMap.put("\u00A1", "&iexcl;"); // inverted exclamation mark<a name="line.41"></a> +<span class="sourceLineNo">042</span> initialMap.put("\u00A2", "&cent;"); // cent sign<a name="line.42"></a> +<span class="sourceLineNo">043</span> initialMap.put("\u00A3", "&pound;"); // pound sign<a name="line.43"></a> +<span class="sourceLineNo">044</span> initialMap.put("\u00A4", "&curren;"); // currency sign<a name="line.44"></a> +<span class="sourceLineNo">045</span> initialMap.put("\u00A5", "&yen;"); // yen sign = yuan sign<a name="line.45"></a> +<span class="sourceLineNo">046</span> initialMap.put("\u00A6", "&brvbar;"); // broken bar = broken vertical bar<a name="line.46"></a> +<span class="sourceLineNo">047</span> initialMap.put("\u00A7", "&sect;"); // section sign<a name="line.47"></a> +<span class="sourceLineNo">048</span> initialMap.put("\u00A8", "&uml;"); // diaeresis = spacing diaeresis<a name="line.48"></a> +<span class="sourceLineNo">049</span> initialMap.put("\u00A9", "&copy;"); // © - copyright sign<a name="line.49"></a> +<span class="sourceLineNo">050</span> initialMap.put("\u00AA", "&ordf;"); // feminine ordinal indicator<a name="line.50"></a> +<span class="sourceLineNo">051</span> initialMap.put("\u00AB", "&laquo;"); // left-pointing double angle quotation mark = left pointing guillemet<a name="line.51"></a> +<span class="sourceLineNo">052</span> initialMap.put("\u00AC", "&not;"); // not sign<a name="line.52"></a> +<span class="sourceLineNo">053</span> initialMap.put("\u00AD", "&shy;"); // soft hyphen = discretionary hyphen<a name="line.53"></a> +<span class="sourceLineNo">054</span> initialMap.put("\u00AE", "&reg;"); // ® - registered trademark sign<a name="line.54"></a> +<span class="sourceLineNo">055</span> initialMap.put("\u00AF", "&macr;"); // macron = spacing macron = overline = APL overbar<a name="line.55"></a> +<span class="sourceLineNo">056</span> initialMap.put("\u00B0", "&deg;"); // degree sign<a name="line.56"></a> +<span class="sourceLineNo">057</span> initialMap.put("\u00B1", "&plusmn;"); // plus-minus sign = plus-or-minus sign<a name="line.57"></a> +<span class="sourceLineNo">058</span> initialMap.put("\u00B2", "&sup2;"); // superscript two = superscript digit two = squared<a name="line.58"></a> +<span class="sourceLineNo">059</span> initialMap.put("\u00B3", "&sup3;"); // superscript three = superscript digit three = cubed<a name="line.59"></a> +<span class="sourceLineNo">060</span> initialMap.put("\u00B4", "&acute;"); // acute accent = spacing acute<a name="line.60"></a> +<span class="sourceLineNo">061</span> initialMap.put("\u00B5", "&micro;"); // micro sign<a name="line.61"></a> +<span class="sourceLineNo">062</span> initialMap.put("\u00B6", "&para;"); // pilcrow sign = paragraph sign<a name="line.62"></a> +<span class="sourceLineNo">063</span> initialMap.put("\u00B7", "&middot;"); // middle dot = Georgian comma = Greek middle dot<a name="line.63"></a> +<span class="sourceLineNo">064</span> initialMap.put("\u00B8", "&cedil;"); // cedilla = spacing cedilla<a name="line.64"></a> +<span class="sourceLineNo">065</span> initialMap.put("\u00B9", "&sup1;"); // superscript one = superscript digit one<a name="line.65"></a> +<span class="sourceLineNo">066</span> initialMap.put("\u00BA", "&ordm;"); // masculine ordinal indicator<a name="line.66"></a> +<span class="sourceLineNo">067</span> initialMap.put("\u00BB", "&raquo;"); // right-pointing double angle quotation mark = right pointing guillemet<a name="line.67"></a> +<span class="sourceLineNo">068</span> initialMap.put("\u00BC", "&frac14;"); // vulgar fraction one quarter = fraction one quarter<a name="line.68"></a> +<span class="sourceLineNo">069</span> initialMap.put("\u00BD", "&frac12;"); // vulgar fraction one half = fraction one half<a name="line.69"></a> +<span class="sourceLineNo">070</span> initialMap.put("\u00BE", "&frac34;"); // vulgar fraction three quarters = fraction three quarters<a name="line.70"></a> +<span class="sourceLineNo">071</span> initialMap.put("\u00BF", "&iquest;"); // inverted question mark = turned question mark<a name="line.71"></a> +<span class="sourceLineNo">072</span> initialMap.put("\u00C0", "&Agrave;"); // à - uppercase A, grave accent<a name="line.72"></a> +<span class="sourceLineNo">073</span> initialMap.put("\u00C1", "&Aacute;"); // à - uppercase A, acute accent<a name="line.73"></a> +<span class="sourceLineNo">074</span> initialMap.put("\u00C2", "&Acirc;"); // à - uppercase A, circumflex accent<a name="line.74"></a> +<span class="sourceLineNo">075</span> initialMap.put("\u00C3", "&Atilde;"); // à - uppercase A, tilde<a name="line.75"></a> +<span class="sourceLineNo">076</span> initialMap.put("\u00C4", "&Auml;"); // à - uppercase A, umlaut<a name="line.76"></a> +<span class="sourceLineNo">077</span> initialMap.put("\u00C5", "&Aring;"); // à - uppercase A, ring<a name="line.77"></a> +<span class="sourceLineNo">078</span> initialMap.put("\u00C6", "&AElig;"); // à - uppercase AE<a name="line.78"></a> +<span class="sourceLineNo">079</span> initialMap.put("\u00C7", "&Ccedil;"); // à - uppercase C, cedilla<a name="line.79"></a> +<span class="sourceLineNo">080</span> initialMap.put("\u00C8", "&Egrave;"); // à - uppercase E, grave accent<a name="line.80"></a> +<span class="sourceLineNo">081</span> initialMap.put("\u00C9", "&Eacute;"); // à - uppercase E, acute accent<a name="line.81"></a> +<span class="sourceLineNo">082</span> initialMap.put("\u00CA", "&Ecirc;"); // à - uppercase E, circumflex accent<a name="line.82"></a> +<span class="sourceLineNo">083</span> initialMap.put("\u00CB", "&Euml;"); // à - uppercase E, umlaut<a name="line.83"></a> +<span class="sourceLineNo">084</span> initialMap.put("\u00CC", "&Igrave;"); // à - uppercase I, grave accent<a name="line.84"></a> +<span class="sourceLineNo">085</span> initialMap.put("\u00CD", "&Iacute;"); // à - uppercase I, acute accent<a name="line.85"></a> +<span class="sourceLineNo">086</span> initialMap.put("\u00CE", "&Icirc;"); // à - uppercase I, circumflex accent<a name="line.86"></a> +<span class="sourceLineNo">087</span> initialMap.put("\u00CF", "&Iuml;"); // à - uppercase I, umlaut<a name="line.87"></a> +<span class="sourceLineNo">088</span> initialMap.put("\u00D0", "&ETH;"); // à - uppercase Eth, Icelandic<a name="line.88"></a> +<span class="sourceLineNo">089</span> initialMap.put("\u00D1", "&Ntilde;"); // à - uppercase N, tilde<a name="line.89"></a> +<span class="sourceLineNo">090</span> initialMap.put("\u00D2", "&Ograve;"); // à - uppercase O, grave accent<a name="line.90"></a> +<span class="sourceLineNo">091</span> initialMap.put("\u00D3", "&Oacute;"); // à - uppercase O, acute accent<a name="line.91"></a> +<span class="sourceLineNo">092</span> initialMap.put("\u00D4", "&Ocirc;"); // à - uppercase O, circumflex accent<a name="line.92"></a> +<span class="sourceLineNo">093</span> initialMap.put("\u00D5", "&Otilde;"); // à - uppercase O, tilde<a name="line.93"></a> +<span class="sourceLineNo">094</span> initialMap.put("\u00D6", "&Ouml;"); // à - uppercase O, umlaut<a name="line.94"></a> +<span class="sourceLineNo">095</span> initialMap.put("\u00D7", "&times;"); // multiplication sign<a name="line.95"></a> +<span class="sourceLineNo">096</span> initialMap.put("\u00D8", "&Oslash;"); // à - uppercase O, slash<a name="line.96"></a> +<span class="sourceLineNo">097</span> initialMap.put("\u00D9", "&Ugrave;"); // à - uppercase U, grave accent<a name="line.97"></a> +<span class="sourceLineNo">098</span> initialMap.put("\u00DA", "&Uacute;"); // à - uppercase U, acute accent<a name="line.98"></a> +<span class="sourceLineNo">099</span> initialMap.put("\u00DB", "&Ucirc;"); // à - uppercase U, circumflex accent<a name="line.99"></a> +<span class="sourceLineNo">100</span> initialMap.put("\u00DC", "&Uuml;"); // à - uppercase U, umlaut<a name="line.100"></a> +<span class="sourceLineNo">101</span> initialMap.put("\u00DD", "&Yacute;"); // à - uppercase Y, acute accent<a name="line.101"></a> +<span class="sourceLineNo">102</span> initialMap.put("\u00DE", "&THORN;"); // à - uppercase THORN, Icelandic<a name="line.102"></a> +<span class="sourceLineNo">103</span> initialMap.put("\u00DF", "&szlig;"); // à - lowercase sharps, German<a name="line.103"></a> +<span class="sourceLineNo">104</span> initialMap.put("\u00E0", "&agrave;"); // à - lowercase a, grave accent<a name="line.104"></a> +<span class="sourceLineNo">105</span> initialMap.put("\u00E1", "&aacute;"); // á - lowercase a, acute accent<a name="line.105"></a> +<span class="sourceLineNo">106</span> initialMap.put("\u00E2", "&acirc;"); // â - lowercase a, circumflex accent<a name="line.106"></a> +<span class="sourceLineNo">107</span> initialMap.put("\u00E3", "&atilde;"); // ã - lowercase a, tilde<a name="line.107"></a> +<span class="sourceLineNo">108</span> initialMap.put("\u00E4", "&auml;"); // ä - lowercase a, umlaut<a name="line.108"></a> +<span class="sourceLineNo">109</span> initialMap.put("\u00E5", "&aring;"); // å - lowercase a, ring<a name="line.109"></a> +<span class="sourceLineNo">110</span> initialMap.put("\u00E6", "&aelig;"); // æ - lowercase ae<a name="line.110"></a> +<span class="sourceLineNo">111</span> initialMap.put("\u00E7", "&ccedil;"); // ç - lowercase c, cedilla<a name="line.111"></a> +<span class="sourceLineNo">112</span> initialMap.put("\u00E8", "&egrave;"); // è - lowercase e, grave accent<a name="line.112"></a> +<span class="sourceLineNo">113</span> initialMap.put("\u00E9", "&eacute;"); // é - lowercase e, acute accent<a name="line.113"></a> +<span class="sourceLineNo">114</span> initialMap.put("\u00EA", "&ecirc;"); // ê - lowercase e, circumflex accent<a name="line.114"></a> +<span class="sourceLineNo">115</span> initialMap.put("\u00EB", "&euml;"); // ë - lowercase e, umlaut<a name="line.115"></a> +<span class="sourceLineNo">116</span> initialMap.put("\u00EC", "&igrave;"); // ì - lowercase i, grave accent<a name="line.116"></a> +<span class="sourceLineNo">117</span> initialMap.put("\u00ED", "&iacute;"); // à - lowercase i, acute accent<a name="line.117"></a> +<span class="sourceLineNo">118</span> initialMap.put("\u00EE", "&icirc;"); // î - lowercase i, circumflex accent<a name="line.118"></a> +<span class="sourceLineNo">119</span> initialMap.put("\u00EF", "&iuml;"); // ï - lowercase i, umlaut<a name="line.119"></a> +<span class="sourceLineNo">120</span> initialMap.put("\u00F0", "&eth;"); // ð - lowercase eth, Icelandic<a name="line.120"></a> +<span class="sourceLineNo">121</span> initialMap.put("\u00F1", "&ntilde;"); // ñ - lowercase n, tilde<a name="line.121"></a> +<span class="sourceLineNo">122</span> initialMap.put("\u00F2", "&ograve;"); // ò - lowercase o, grave accent<a name="line.122"></a> +<span class="sourceLineNo">123</span> initialMap.put("\u00F3", "&oacute;"); // ó - lowercase o, acute accent<a name="line.123"></a> +<span class="sourceLineNo">124</span> initialMap.put("\u00F4", "&ocirc;"); // ô - lowercase o, circumflex accent<a name="line.124"></a> +<span class="sourceLineNo">125</span> initialMap.put("\u00F5", "&otilde;"); // õ - lowercase o, tilde<a name="line.125"></a> +<span class="sourceLineNo">126</span> initialMap.put("\u00F6", "&ouml;"); // ö - lowercase o, umlaut<a name="line.126"></a> +<span class="sourceLineNo">127</span> initialMap.put("\u00F7", "&divide;"); // division sign<a name="line.127"></a> +<span class="sourceLineNo">128</span> initialMap.put("\u00F8", "&oslash;"); // ø - lowercase o, slash<a name="line.128"></a> +<span class="sourceLineNo">129</span> initialMap.put("\u00F9", "&ugrave;"); // ù - lowercase u, grave accent<a name="line.129"></a> +<span class="sourceLineNo">130</span> initialMap.put("\u00FA", "&uacute;"); // ú - lowercase u, acute accent<a name="line.130"></a> +<span class="sourceLineNo">131</span> initialMap.put("\u00FB", "&ucirc;"); // û - lowercase u, circumflex accent<a name="line.131"></a> +<span class="sourceLineNo">132</span> initialMap.put("\u00FC", "&uuml;"); // ü - lowercase u, umlaut<a name="line.132"></a> +<span class="sourceLineNo">133</span> initialMap.put("\u00FD", "&yacute;"); // ý - lowercase y, acute accent<a name="line.133"></a> +<span class="sourceLineNo">134</span> initialMap.put("\u00FE", "&thorn;"); // þ - lowercase thorn, Icelandic<a name="line.134"></a> +<span class="sourceLineNo">135</span> initialMap.put("\u00FF", "&yuml;"); // ÿ - lowercase y, umlaut<a name="line.135"></a> +<span class="sourceLineNo">136</span> ISO8859_1_ESCAPE = Collections.unmodifiableMap(initialMap);<a name="line.136"></a> +<span class="sourceLineNo">137</span> }<a name="line.137"></a> +<span class="sourceLineNo">138</span><a name="line.138"></a> +<span class="sourceLineNo">139</span> /**<a name="line.139"></a> +<span class="sourceLineNo">140</span> * Reverse of {@link #ISO8859_1_ESCAPE} for unescaping purposes.<a name="line.140"></a> +<span class="sourceLineNo">141</span> */<a name="line.141"></a> +<span class="sourceLineNo">142</span> public static final Map<CharSequence, CharSequence> ISO8859_1_UNESCAPE;<a name="line.142"></a> +<span class="sourceLineNo">143</span> static {<a name="line.143"></a> +<span class="sourceLineNo">144</span> ISO8859_1_UNESCAPE = Collections.unmodifiableMap(invert(ISO8859_1_ESCAPE));<a name="line.144"></a> +<span class="sourceLineNo">145</span> }<a name="line.145"></a> +<span class="sourceLineNo">146</span><a name="line.146"></a> +<span class="sourceLineNo">147</span> /**<a name="line.147"></a> +<span class="sourceLineNo">148</span> * A Map&lt;CharSequence, CharSequence&gt; to escape additional<a name="line.148"></a> +<span class="sourceLineNo">149</span> * <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">character entity<a name="line.149"></a> +<span class="sourceLineNo">150</span> * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE} to get the full list of<a name="line.150"></a> +<span class="sourceLineNo">151</span> * HTML 4.0 character entities.<a name="line.151"></a> +<span class="sourceLineNo">152</span> */<a name="line.152"></a> +<span class="sourceLineNo">153</span> public static final Map<CharSequence, CharSequence> HTML40_EXTENDED_ESCAPE;<a name="line.153"></a> +<span class="sourceLineNo">154</span> static {<a name="line.154"></a> +<span class="sourceLineNo">155</span> Map<CharSequence, CharSequence> initialMap = new HashMap<>();<a name="line.155"></a> +<span class="sourceLineNo">156</span> // <!-- Latin Extended-B --><a name="line.156"></a> +<span class="sourceLineNo">157</span> initialMap.put("\u0192", "&fnof;"); // latin small f with hook = function= florin, U+0192 ISOtech --><a name="line.157"></a> +<span class="sourceLineNo">158</span> // <!-- Greek --><a name="line.158"></a> +<span class="sourceLineNo">159</span> initialMap.put("\u0391", "&Alpha;"); // greek capital letter alpha, U+0391 --><a name="line.159"></a> +<span class="sourceLineNo">160</span> initialMap.put("\u0392", "&Beta;"); // greek capital letter beta, U+0392 --><a name="line.160"></a> +<span class="sourceLineNo">161</span> initialMap.put("\u0393", "&Gamma;"); // greek capital letter gamma,U+0393 ISOgrk3 --><a name="line.161"></a> +<span class="sourceLineNo">162</span> initialMap.put("\u0394", "&Delta;"); // greek capital letter delta,U+0394 ISOgrk3 --><a name="line.162"></a> +<span class="sourceLineNo">163</span> initialMap.put("\u0395", "&Epsilon;"); // greek capital letter epsilon, U+0395 --><a name="line.163"></a> +<span class="sourceLineNo">164</span> initialMap.put("\u0396", "&Zeta;"); // greek capital letter zeta, U+0396 --><a name="line.164"></a> +<span class="sourceLineNo">165</span> initialMap.put("\u0397", "&Eta;"); // greek capital letter eta, U+0397 --><a name="line.165"></a> +<span class="sourceLineNo">166</span> initialMap.put("\u0398", "&Theta;"); // greek capital letter theta,U+0398 ISOgrk3 --><a name="line.166"></a> +<span class="sourceLineNo">167</span> initialMap.put("\u0399", "&Iota;"); // greek capital letter iota, U+0399 --><a name="line.167"></a> +<span class="sourceLineNo">168</span> initialMap.put("\u039A", "&Kappa;"); // greek capital letter kappa, U+039A --><a name="line.168"></a> +<span class="sourceLineNo">169</span> initialMap.put("\u039B", "&Lambda;"); // greek capital letter lambda,U+039B ISOgrk3 --><a name="line.169"></a> +<span class="sourceLineNo">170</span> initialMap.put("\u039C", "&Mu;"); // greek capital letter mu, U+039C --><a name="line.170"></a> +<span class="sourceLineNo">171</span> initialMap.put("\u039D", "&Nu;"); // greek capital letter nu, U+039D --><a name="line.171"></a> +<span class="sourceLineNo">172</span> initialMap.put("\u039E", "&Xi;"); // greek capital letter xi, U+039E ISOgrk3 --><a name="line.172"></a> +<span class="sourceLineNo">173</span> initialMap.put("\u039F", "&Omicron;"); // greek capital letter omicron, U+039F --><a name="line.173"></a> +<span class="sourceLineNo">174</span> initialMap.put("\u03A0", "&Pi;"); // greek capital letter pi, U+03A0 ISOgrk3 --><a name="line.174"></a> +<span class="sourceLineNo">175</span> initialMap.put("\u03A1", "&Rho;"); // greek capital letter rho, U+03A1 --><a name="line.175"></a> +<span class="sourceLineNo">176</span> // <!-- there is no Sigmaf, and no U+03A2 character either --><a name="line.176"></a> +<span class="sourceLineNo">177</span> initialMap.put("\u03A3", "&Sigma;"); // greek capital letter sigma,U+03A3 ISOgrk3 --><a name="line.177"></a> +<span class="sourceLineNo">178</span> initialMap.put("\u03A4", "&Tau;"); // greek capital letter tau, U+03A4 --><a name="line.178"></a> +<span class="sourceLineNo">179</span> initialMap.put("\u03A5", "&Upsilon;"); // greek capital letter upsilon,U+03A5 ISOgrk3 --><a name="line.179"></a> +<span class="sourceLineNo">180</span> initialMap.put("\u03A6", "&Phi;"); // greek capital letter phi,U+03A6 ISOgrk3 --><a name="line.180"></a> +<span class="sourceLineNo">181</span> initialMap.put("\u03A7", "&Chi;"); // greek capital letter chi, U+03A7 --><a name="line.181"></a> +<span class="sourceLineNo">182</span> initialMap.put("\u03A8", "&Psi;"); // greek capital letter psi,U+03A8 ISOgrk3 --><a name="line.182"></a> +<span class="sourceLineNo">183</span> initialMap.put("\u03A9", "&Omega;"); // greek capital letter omega,U+03A9 ISOgrk3 --><a name="line.183"></a> +<span class="sourceLineNo">184</span> initialMap.put("\u03B1", "&alpha;"); // greek small letter alpha,U+03B1 ISOgrk3 --><a name="line.184"></a> +<span class="sourceLineNo">185</span> initialMap.put("\u03B2", "&beta;"); // greek small letter beta, U+03B2 ISOgrk3 --><a name="line.185"></a> +<span class="sourceLineNo">186</span> initialMap.put("\u03B3", "&gamma;"); // greek small letter gamma,U+03B3 ISOgrk3 --><a name="line.186"></a> +<span class="sourceLineNo">187</span> initialMap.put("\u03B4", "&delta;"); // greek small letter delta,U+03B4 ISOgrk3 --><a name="line.187"></a> +<span class="sourceLineNo">188</span> initialMap.put("\u03B5", "&epsilon;"); // greek small letter epsilon,U+03B5 ISOgrk3 --><a name="line.188"></a> +<span class="sourceLineNo">189</span> initialMap.put("\u03B6", "&zeta;"); // greek small letter zeta, U+03B6 ISOgrk3 --><a name="line.189"></a> +<span class="sourceLineNo">190</span> initialMap.put("\u03B7", "&eta;"); // greek small letter eta, U+03B7 ISOgrk3 --><a name="line.190"></a> +<span class="sourceLineNo">191</span> initialMap.put("\u03B8", "&theta;"); // greek small letter theta,U+03B8 ISOgrk3 --><a name="line.191"></a> +<span class="sourceLineNo">192</span> initialMap.put("\u03B9", "&iota;"); // greek small letter iota, U+03B9 ISOgrk3 --><a name="line.192"></a> +<span class="sourceLineNo">193</span> initialMap.put("\u03BA", "&kappa;"); // greek small letter kappa,U+03BA ISOgrk3 --><a name="line.193"></a> +<span class="sourceLineNo">194</span> initialMap.put("\u03BB", "&lambda;"); // greek small letter lambda,U+03BB ISOgrk3 --><a name="line.194"></a> +<span class="sourceLineNo">195</span> initialMap.put("\u03BC", "&mu;"); // greek small letter mu, U+03BC ISOgrk3 --><a name="line.195"></a> +<span class="sourceLineNo">196</span> initialMap.put("\u03BD", "&nu;"); // greek small letter nu, U+03BD ISOgrk3 --><a name="line.196"></a> +<span class="sourceLineNo">197</span> initialMap.put("\u03BE", "&xi;"); // greek small letter xi, U+03BE ISOgrk3 --><a name="line.197"></a> +<span class="sourceLineNo">198</span> initialMap.put("\u03BF", "&omicron;"); // greek small letter omicron, U+03BF NEW --><a name="line.198"></a> +<span class="sourceLineNo">199</span> initialMap.put("\u03C0", "&pi;"); // greek small letter pi, U+03C0 ISOgrk3 --><a name="line.199"></a> +<span class="sourceLineNo">200</span> initialMap.put("\u03C1", "&rho;"); // greek small letter rho, U+03C1 ISOgrk3 --><a name="line.200"></a> +<span class="sourceLineNo">201</span> initialMap.put("\u03C2", "&sigmaf;"); // greek small letter final sigma,U+03C2 ISOgrk3 --><a name="line.201"></a> +<span class="sourceLineNo">202</span> initialMap.put("\u03C3", "&sigma;"); // greek small letter sigma,U+03C3 ISOgrk3 --><a name="line.202"></a> +<span class="sourceLineNo">203</span> initialMap.put("\u03C4", "&tau;"); // greek small letter tau, U+03C4 ISOgrk3 --><a name="line.203"></a> +<span class="sourceLineNo">204</span> initialMap.put("\u03C5", "&upsilon;"); // greek small letter upsilon,U+03C5 ISOgrk3 --><a name="line.204"></a> +<span class="sourceLineNo">205</span> initialMap.put("\u03C6", "&phi;"); // greek small letter phi, U+03C6 ISOgrk3 --><a name="line.205"></a> +<span class="sourceLineNo">206</span> initialMap.put("\u03C7", "&chi;"); // greek small letter chi, U+03C7 ISOgrk3 --><a name="line.206"></a> +<span class="sourceLineNo">207</span> initialMap.put("\u03C8", "&psi;"); // greek small letter psi, U+03C8 ISOgrk3 --><a name="line.207"></a> +<span class="sourceLineNo">208</span> initialMap.put("\u03C9", "&omega;"); // greek small letter omega,U+03C9 ISOgrk3 --><a name="line.208"></a> +<span class="sourceLineNo">209</span> initialMap.put("\u03D1", "&thetasym;"); // greek small letter theta symbol,U+03D1 NEW --><a name="line.209"></a> +<span class="sourceLineNo">210</span> initialMap.put("\u03D2", "&upsih;"); // greek upsilon with hook symbol,U+03D2 NEW --><a name="line.210"></a> +<span class="sourceLineNo">211</span> initialMap.put("\u03D6", "&piv;"); // greek pi symbol, U+03D6 ISOgrk3 --><a name="line.211"></a> +<span class="sourceLineNo">212</span> // <!-- General Punctuation --><a name="line.212"></a> +<span class="sourceLineNo">213</span> initialMap.put("\u2022", "&bull;"); // bullet = black small circle,U+2022 ISOpub --><a name="line.213"></a> +<span class="sourceLineNo">214</span> // <!-- bullet is NOT the same as bullet operator, U+2219 --><a name="line.214"></a> +<span class="sourceLineNo">215</span> initialMap.put("\u2026", "&hellip;"); // horizontal ellipsis = three dot leader,U+2026 ISOpub --><a name="line.215"></a> +<span class="sourceLineNo">216</span> initialMap.put("\u2032", "&prime;"); // prime = minutes = feet, U+2032 ISOtech --><a name="line.216"></a> +<span class="sourceLineNo">217</span> initialMap.put("\u2033", "&Prime;"); // double prime = seconds = inches,U+2033 ISOtech --><a name="line.217"></a> +<span class="sourceLineNo">218</span> initialMap.put("\u203E", "&oline;"); // overline = spacing overscore,U+203E NEW --><a name="line.218"></a> +<span class="sourceLineNo">219</span> initialMap.put("\u2044", "&frasl;"); // fraction slash, U+2044 NEW --><a name="line.219"></a> +<span class="sourceLineNo">220</span> // <!-- Letterlike Symbols --><a name="line.220"></a> +<span class="sourceLineNo">221</span> initialMap.put("\u2118", "&weierp;"); // script capital P = power set= Weierstrass p, U+2118 ISOamso --><a name="line.221"></a> +<span class="sourceLineNo">222</span> initialMap.put("\u2111", "&image;"); // blackletter capital I = imaginary part,U+2111 ISOamso --><a name="line.222"></a> +<span class="sourceLineNo">223</span> initialMap.put("\u211C", "&real;"); // blackletter capital R = real part symbol,U+211C ISOamso --><a name="line.223"></a> +<span class="sourceLineNo">224</span> initialMap.put("\u2122", "&trade;"); // trade mark sign, U+2122 ISOnum --><a name="line.224"></a> +<span class="sourceLineNo">225</span> initialMap.put("\u2135", "&alefsym;"); // alef symbol = first transfinite cardinal,U+2135 NEW --><a name="line.225"></a> +<span class="sourceLineNo">226</span> // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the<a name="line.226"></a> +<span class="sourceLineNo">227</span> // same glyph could be used to depict both characters --><a name="line.227"></a> +<span class="sourceLineNo">228</span> // <!-- Arrows --><a name="line.228"></a> +<span class="sourceLineNo">229</span> initialMap.put("\u2190", "&larr;"); // leftwards arrow, U+2190 ISOnum --><a name="line.229"></a> +<span class="sourceLineNo">230</span> initialMap.put("\u2191", "&uarr;"); // upwards arrow, U+2191 ISOnum--><a name="line.230"></a> +<span class="sourceLineNo">231</span> initialMap.put("\u2192", "&rarr;"); // rightwards arrow, U+2192 ISOnum --><a name="line.231"></a> +<span class="sourceLineNo">232</span> initialMap.put("\u2193", "&darr;"); // downwards arrow, U+2193 ISOnum --><a name="line.232"></a> +<span class="sourceLineNo">233</span> initialMap.put("\u2194", "&harr;"); // left right arrow, U+2194 ISOamsa --><a name="line.233"></a> +<span class="sourceLineNo">234</span> initialMap.put("\u21B5", "&crarr;"); // downwards arrow with corner leftwards= carriage return, U+21B5 NEW --><a name="line.234"></a> +<span class="sourceLineNo">235</span> initialMap.put("\u21D0", "&lArr;"); // leftwards double arrow, U+21D0 ISOtech --><a name="line.235"></a> +<span class="sourceLineNo">236</span> // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'<a name="line.236"></a> +<span class="sourceLineNo">237</span> // arrow but also does not have any other character for that function.<a name="line.237"></a> +<span class="sourceLineNo">238</span> // So ? lArr canbe used for 'is implied by' as ISOtech suggests --><a name="line.238"></a> +<span class="sourceLineNo">239</span> initialMap.put("\u21D1", "&uArr;"); // upwards double arrow, U+21D1 ISOamsa --><a name="line.239"></a> +<span class="sourceLineNo">240</span> initialMap.put("\u21D2", "&rArr;"); // rightwards double arrow,U+21D2 ISOtech --><a name="line.240"></a> +<span class="sourceLineNo">241</span> // <!-- ISO 10646 does not say this is the 'implies' character but does not<a name="line.241"></a> +<span class="sourceLineNo">242</span> // have another character with this function so ?rArr can be used for<a name="line.242"></a> +<span class="sourceLineNo">243</span> // 'implies' as ISOtech suggests --><a name="line.243"></a> +<span class="sourceLineNo">244</span> initialMap.put("\u21D3", "&dArr;"); // downwards double arrow, U+21D3 ISOamsa --><a name="line.244"></a> +<span class="sourceLineNo">245</span> initialMap.put("\u21D4", "&hArr;"); // left right double arrow,U+21D4 ISOamsa --><a name="line.245"></a> +<span class="sourceLineNo">246</span> // <!-- Mathematical Operators --><a name="line.246"></a> +<span class="sourceLineNo">247</span> initialMap.put("\u2200", "&forall;"); // for all, U+2200 ISOtech --><a name="line.247"></a> +<span class="sourceLineNo">248</span> initialMap.put("\u2202", "&part;"); // partial differential, U+2202 ISOtech --><a name="line.248"></a> +<span class="sourceLineNo">249</span> initialMap.put("\u2203", "&exist;"); // there exists, U+2203 ISOtech --><a name="line.249"></a> +<span class="sourceLineNo">250</span> initialMap.put("\u2205", "&empty;"); // empty set = null set = diameter,U+2205 ISOamso --><a name="line.250"></a> +<span class="sourceLineNo">251</span> initialMap.put("\u2207", "&nabla;"); // nabla = backward difference,U+2207 ISOtech --><a name="line.251"></a> +<span class="sourceLineNo">252</span> initialMap.put("\u2208", "&isin;"); // element of, U+2208 ISOtech --><a name="line.252"></a> +<span class="sourceLineNo">253</span> initialMap.put("\u2209", "&notin;"); // not an element of, U+2209 ISOtech --><a name="line.253"></a> +<span class="sourceLineNo">254</span> initialMap.put("\u220B", "&ni;"); // contains as member, U+220B ISOtech --><a name="line.254"></a> +<span class="sourceLineNo">255</span> // <!-- should there be a more memorable name than 'ni'? --><a name="line.255"></a> +<span class="sourceLineNo">256</span> initialMap.put("\u220F", "&prod;"); // n-ary product = product sign,U+220F ISOamsb --><a name="line.256"></a> +<span class="sourceLineNo">257</span> // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'<a name="line.257"></a> +<span class="sourceLineNo">258</span> // though the same glyph might be used for both --><a name="line.258"></a> +<span class="sourceLineNo">259</span> initialMap.put("\u2211", "&sum;"); // n-ary summation, U+2211 ISOamsb --><a name="line.259"></a> +<span class="sourceLineNo">260</span> // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'<a name="line.260"></a> +<span class="sourceLineNo">261</span> // though the same glyph might be used for both --><a name="line.261"></a> +<span class="sourceLineNo">262</span> initialMap.put("\u2212", "&minus;"); // minus sign, U+2212 ISOtech --><a name="line.262"></a> +<span class="sourceLineNo">263</span> initialMap.put("\u2217", "&lowast;"); // asterisk operator, U+2217 ISOtech --><a name="line.263"></a> +<span class="sourceLineNo">264</span> initialMap.put("\u221A", "&radic;"); // square root = radical sign,U+221A ISOtech --><a name="line.264"></a> +<span class="sourceLineNo">265</span> initialMap.put("\u221D", "&prop;"); // proportional to, U+221D ISOtech --><a name="line.265"></a> +<span class="sourceLineNo">266</span> initialMap.put("\u221E", "&infin;"); // infinity, U+221E ISOtech --><a name="line.266"></a> +<span class="sourceLineNo">267</span> initialMap.put("\u2220", "&ang;"); // angle, U+2220 ISOamso --><a name="line.267"></a> +<span class="sourceLineNo">268</span> initialMap.put("\u2227", "&and;"); // logical and = wedge, U+2227 ISOtech --><a name="line.268"></a> +<span class="sourceLineNo">269</span> initialMap.put("\u2228", "&or;"); // logical or = vee, U+2228 ISOtech --><a name="line.269"></a> +<span class="sourceLineNo">270</span> initialMap.put("\u2229", "&cap;"); // intersection = cap, U+2229 ISOtech --><a name="line.270"></a> +<span class="sourceLineNo">271</span> initialMap.put("\u222A", "&cup;"); // union = cup, U+222A ISOtech --><a name="line.271"></a> +<span class="sourceLineNo">272</span> initialMap.put("\u222B", "&int;"); // integral, U+222B ISOtech --><a name="line.272"></a> +<span class="sourceLineNo">273</span> initialMap.put("\u2234", "&there4;"); // therefore, U+2234 ISOtech --><a name="line.273"></a> +<span class="sourceLineNo">274</span> initialMap.put("\u223C", "&sim;"); // tilde operator = varies with = similar to,U+223C ISOtech --><a name="line.274"></a> +<span class="sourceLineNo">275</span> // <!-- tilde operator is NOT the same character as the tilde, U+007E,although<a name="line.275"></a> +<span class="sourceLineNo">276</span> // the same glyph might be used to represent both --><a name="line.276"></a> +<span class="sourceLineNo">277</span> initialMap.put("\u2245", "&cong;"); // approximately equal to, U+2245 ISOtech --><a name="line.277"></a> +<span class="sourceLineNo">278</span> initialMap.put("\u2248", "&asymp;"); // almost equal to = asymptotic to,U+2248 ISOamsr --><a name="line.278"></a> +<span class="sourceLineNo">279</span> initialMap.put("\u2260", "&ne;"); // not equal to, U+2260 ISOtech --><a name="line.279"></a> +<span class="sourceLineNo">280</span> initialMap.put("\u2261", "&equiv;"); // identical to, U+2261 ISOtech --><a name="line.280"></a> +<span class="sourceLineNo">281</span> initialMap.put("\u2264", "&le;"); // less-than or equal to, U+2264 ISOtech --><a name="line.281"></a> +<span class="sourceLineNo">282</span> initialMap.put("\u2265", "&ge;"); // greater-than or equal to,U+2265 ISOtech --><a name="line.282"></a> +<span class="sourceLineNo">283</span> initialMap.put("\u2282", "&sub;"); // subset of, U+2282 ISOtech --><a name="line.283"></a> +<span class="sourceLineNo">284</span> initialMap.put("\u2283", "&sup;"); // superset of, U+2283 ISOtech --><a name="line.284"></a> +<span class="sourceLineNo">285</span> // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the<a name="line.285"></a> +<span class="sourceLineNo">286</span> // Symbol font encoding and is not included. Should it be, for symmetry?<a name="line.286"></a> +<span class="sourceLineNo">287</span> // It is in ISOamsn -->,<a name="line.287"></a> +<span class="sourceLineNo">288</span> initialMap.put("\u2284", "&nsub;"); // not a subset of, U+2284 ISOamsn --><a name="line.288"></a> +<span class="sourceLineNo">289</span> initialMap.put("\u2286", "&sube;"); // subset of or equal to, U+2286 ISOtech --><a name="line.289"></a>
[... 157 lines stripped ...]