1 /* Copyright 2002, 2003 Elliotte Rusty Harold 2 3 This library is free software; you can redistribute it and/or modify 4 it under the terms of version 2.1 of the GNU Lesser General Public 5 License as published by the Free Software Foundation. 6 7 This library is distributed in the hope that it will be useful, 8 but WITHOUT ANY WARRANTY; without even the implied warranty of 9 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 10 GNU Lesser General Public License for more details. 11 12 You should have received a copy of the GNU Lesser General Public 13 License along with this library; if not, write to the 14 Free Software Foundation, Inc., 59 Temple Place, Suite 330, 15 Boston, MA 02111-1307 USA 16 17 You can contact Elliotte Rusty Harold by sending e-mail to 18 elharo@ibiblio.org. Please include the word "XOM" in the 19 subject line. The XOM home page is located at http://www.xom.nu/ 20 */ 21 22 package nu.xom; 23 24 import java.io.Writer; 25 26 /** 27 * <p> 28 * ISO 8859-9 for Western Europe. Includes the Euro sign and 29 * several uncommon French letters. otherwise the same as 30 * Latin-1. 31 * </p> 32 * 33 * @author Elliotte Rusty Harold 34 * @version 1.0 35 * 36 */ 37 class Latin9Writer extends TextWriter { 38 39 /** 40 * <p> 41 * Creates a new <code>TextWriter</code> for the 42 * ISO-8859-15 (Latin-9) character encoding. 43 * </p> 44 * 45 * @param out the <code>Writer</code> on which the text will be written 46 * @param encoding the character set used by the <code>Writer</code> 47 */ Latin9Writer(Writer out, String encoding)48 Latin9Writer(Writer out, String encoding) { 49 super(out, encoding); 50 } 51 52 /** 53 * <p> 54 * Returns true if and only if this character 55 * needs to be replaced by a character reference when 56 * output in this encoding. 57 * </p> 58 * 59 * 60 * @see nu.xom.TextWriter#needsEscaping(char) 61 */ needsEscaping(char c)62 boolean needsEscaping(char c) { 63 if (c <= 0xA3 ) return false; 64 if (c == 0x20AC) return false; // EURO SIGN 65 66 switch (c) { // Latin-1 overlap 67 case 0x00A5: return false; // YEN SIGN 68 case 0x00A6: return true; // place holder to enable table lookup 69 case 0x00A7: return false; // SECTION SIGN 70 case 0x00A8: return true; // place holder to enable table lookup 71 case 0x00A9: return false; // COPYRIGHT SIGN 72 case 0x00AA: return false; // FEMININE ORDINAL INDICATOR 73 case 0x00AB: return false; // LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 74 case 0x00AC: return false; // NOT SIGN 75 case 0x00AD: return false; // SOFT HYPHEN 76 case 0x00AE: return false; // REGISTERED SIGN 77 case 0x00AF: return false; // MACRON 78 case 0x00B0: return false; // DEGREE SIGN 79 case 0x00B1: return false; // PLUS-MINUS SIGN 80 case 0x00B2: return false; // SUPERSCRIPT TWO 81 case 0x00B3: return false; // SUPERSCRIPT THREE 82 case 0x00B4: return true; // place holder to enable table lookup 83 case 0x00B5: return false; // MICRO SIGN 84 case 0x00B6: return false; // PILCROW SIGN 85 case 0x00B7: return false; // MIDDLE DOT 86 case 0x00B8: return true; // place holder to enable table lookup 87 case 0x00B9: return false; // SUPERSCRIPT ONE 88 case 0x00BA: return false; // MASCULINE ORDINAL INDICATOR 89 case 0x00BB: return false; // RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 90 case 0x00BC: return true; // place holder to enable table lookup 91 case 0x00BD: return true; // place holder to enable table lookup 92 case 0x00BE: return true; // place holder to enable table lookup 93 case 0x00BF: return false; // INVERTED QUESTION MARK 94 case 0x00C0: return false; // LATIN CAPITAL LETTER A WITH GRAVE 95 case 0x00C1: return false; // LATIN CAPITAL LETTER A WITH ACUTE 96 case 0x00C2: return false; // LATIN CAPITAL LETTER A WITH CIRCUMFLEX 97 case 0x00C3: return false; // LATIN CAPITAL LETTER A WITH TILDE 98 case 0x00C4: return false; // LATIN CAPITAL LETTER A WITH DIAERESIS 99 case 0x00C5: return false; // LATIN CAPITAL LETTER A WITH RING ABOVE 100 case 0x00C6: return false; // LATIN CAPITAL LETTER AE 101 case 0x00C7: return false; // LATIN CAPITAL LETTER C WITH CEDILLA 102 case 0x00C8: return false; // LATIN CAPITAL LETTER E WITH GRAVE 103 case 0x00C9: return false; // LATIN CAPITAL LETTER E WITH ACUTE 104 case 0x00CA: return false; // LATIN CAPITAL LETTER E WITH CIRCUMFLEX 105 case 0x00CB: return false; // LATIN CAPITAL LETTER E WITH DIAERESIS 106 case 0x00CC: return false; // LATIN CAPITAL LETTER I WITH GRAVE 107 case 0x00CD: return false; // LATIN CAPITAL LETTER I WITH ACUTE 108 case 0x00CE: return false; // LATIN CAPITAL LETTER I WITH CIRCUMFLEX 109 case 0x00CF: return false; // LATIN CAPITAL LETTER I WITH DIAERESIS 110 case 0x00D0: return false; // LATIN CAPITAL LETTER ETH 111 case 0x00D1: return false; // LATIN CAPITAL LETTER N WITH TILDE 112 case 0x00D2: return false; // LATIN CAPITAL LETTER O WITH GRAVE 113 case 0x00D3: return false; // LATIN CAPITAL LETTER O WITH ACUTE 114 case 0x00D4: return false; // LATIN CAPITAL LETTER O WITH CIRCUMFLEX 115 case 0x00D5: return false; // LATIN CAPITAL LETTER O WITH TILDE 116 case 0x00D6: return false; // LATIN CAPITAL LETTER O WITH DIAERESIS 117 case 0x00D7: return false; // MULTIPLICATION SIGN 118 case 0x00D8: return false; // LATIN CAPITAL LETTER O WITH STROKE 119 case 0x00D9: return false; // LATIN CAPITAL LETTER U WITH GRAVE 120 case 0x00DA: return false; // LATIN CAPITAL LETTER U WITH ACUTE 121 case 0x00DB: return false; // LATIN CAPITAL LETTER U WITH CIRCUMFLEX 122 case 0x00DC: return false; // LATIN CAPITAL LETTER U WITH DIAERESIS 123 case 0x00DD: return false; // LATIN CAPITAL LETTER Y WITH ACUTE 124 case 0x00DE: return false; // LATIN CAPITAL LETTER THORN 125 case 0x00DF: return false; // LATIN SMALL LETTER SHARP S 126 case 0x00E0: return false; // LATIN SMALL LETTER A WITH GRAVE 127 case 0x00E1: return false; // LATIN SMALL LETTER A WITH ACUTE 128 case 0x00E2: return false; // LATIN SMALL LETTER A WITH CIRCUMFLEX 129 case 0x00E3: return false; // LATIN SMALL LETTER A WITH TILDE 130 case 0x00E4: return false; // LATIN SMALL LETTER A WITH DIAERESIS 131 case 0x00E5: return false; // LATIN SMALL LETTER A WITH RING ABOVE 132 case 0x00E6: return false; // LATIN SMALL LETTER AE 133 case 0x00E7: return false; // LATIN SMALL LETTER C WITH CEDILLA 134 case 0x00E8: return false; // LATIN SMALL LETTER E WITH GRAVE 135 case 0x00E9: return false; // LATIN SMALL LETTER E WITH ACUTE 136 case 0x00EA: return false; // LATIN SMALL LETTER E WITH CIRCUMFLEX 137 case 0x00EB: return false; // LATIN SMALL LETTER E WITH DIAERESIS 138 case 0x00EC: return false; // LATIN SMALL LETTER I WITH GRAVE 139 case 0x00ED: return false; // LATIN SMALL LETTER I WITH ACUTE 140 case 0x00EE: return false; // LATIN SMALL LETTER I WITH CIRCUMFLEX 141 case 0x00EF: return false; // LATIN SMALL LETTER I WITH DIAERESIS 142 case 0x00F0: return false; // LATIN SMALL LETTER ETH 143 case 0x00F1: return false; // LATIN SMALL LETTER N WITH TILDE 144 case 0x00F2: return false; // LATIN SMALL LETTER O WITH GRAVE 145 case 0x00F3: return false; // LATIN SMALL LETTER O WITH ACUTE 146 case 0x00F4: return false; // LATIN SMALL LETTER O WITH CIRCUMFLEX 147 case 0x00F5: return false; // LATIN SMALL LETTER O WITH TILDE 148 case 0x00F6: return false; // LATIN SMALL LETTER O WITH DIAERESIS 149 case 0x00F7: return false; // DIVISION SIGN 150 case 0x00F8: return false; // LATIN SMALL LETTER O WITH STROKE 151 case 0x00F9: return false; // LATIN SMALL LETTER U WITH GRAVE 152 case 0x00FA: return false; // LATIN SMALL LETTER U WITH ACUTE 153 case 0x00FB: return false; // LATIN SMALL LETTER U WITH CIRCUMFLEX 154 case 0x00FC: return false; // LATIN SMALL LETTER U WITH DIAERESIS 155 case 0x00FD: return false; // LATIN SMALL LETTER Y WITH ACUTE 156 case 0x00FE: return false; // LATIN SMALL LETTER THORN 157 case 0x00FF: return false; // LATIN SMALL LETTER Y WITH DIAERESIS 158 } 159 switch (c) { // uncommon French letters 160 case 0x0152: return false; // LATIN CAPITAL LIGATURE OE 161 case 0x0153: return false; // LATIN SMALL LIGATURE OE 162 case 0x0154: return true; // place holder to enable table lookup 163 case 0x0155: return true; // place holder to enable table lookup 164 case 0x0156: return true; // place holder to enable table lookup 165 case 0x0157: return true; // place holder to enable table lookup 166 case 0x0158: return true; // place holder to enable table lookup 167 case 0x0159: return true; // place holder to enable table lookup 168 case 0x015A: return true; // place holder to enable table lookup 169 case 0x015B: return true; // place holder to enable table lookup 170 case 0x015C: return true; // place holder to enable table lookup 171 case 0x015D: return true; // place holder to enable table lookup 172 case 0x015E: return true; // place holder to enable table lookup 173 case 0x015F: return true; // place holder to enable table lookup 174 case 0x0160: return false; // LATIN CAPITAL LETTER S WITH CARON 175 case 0x0161: return false; // LATIN SMALL LETTER S WITH CARON 176 case 0x0162: return true; // place holder to enable table lookup 177 case 0x0163: return true; // place holder to enable table lookup 178 case 0x0164: return true; // place holder to enable table lookup 179 case 0x0165: return true; // place holder to enable table lookup 180 case 0x0166: return true; // place holder to enable table lookup 181 case 0x0167: return true; // place holder to enable table lookup 182 case 0x0168: return true; // place holder to enable table lookup 183 case 0x0169: return true; // place holder to enable table lookup 184 case 0x016A: return true; // place holder to enable table lookup 185 case 0x016B: return true; // place holder to enable table lookup 186 case 0x016C: return true; // place holder to enable table lookup 187 case 0x016D: return true; // place holder to enable table lookup 188 case 0x016E: return true; // place holder to enable table lookup 189 case 0x016F: return true; // place holder to enable table lookup 190 case 0x0170: return true; // place holder to enable table lookup 191 case 0x0171: return true; // place holder to enable table lookup 192 case 0x0172: return true; // place holder to enable table lookup 193 case 0x0173: return true; // place holder to enable table lookup 194 case 0x0174: return true; // place holder to enable table lookup 195 case 0x0175: return true; // place holder to enable table lookup 196 case 0x0176: return true; // place holder to enable table lookup 197 case 0x0177: return true; // place holder to enable table lookup 198 case 0x0178: return false; // LATIN CAPITAL LETTER Y WITH DIAERESIS 199 case 0x017D: return false; // LATIN CAPITAL LETTER Z WITH CARON 200 case 0x017E: return false; // LATIN SMALL LETTER Z WITH CARON 201 } 202 203 return true; 204 205 } 206 207 }