J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1996-2000 Sun Microsystems, Inc. All Rights Reserved. |
| 3 | * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
| 4 | * |
| 5 | * This code is free software; you can redistribute it and/or modify it |
| 6 | * under the terms of the GNU General Public License version 2 only, as |
| 7 | * published by the Free Software Foundation. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun in the LICENSE file that accompanied this code. |
| 10 | * |
| 11 | * This code is distributed in the hope that it will be useful, but WITHOUT |
| 12 | * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
| 13 | * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
| 14 | * version 2 for more details (a copy is included in the LICENSE file that |
| 15 | * accompanied this code). |
| 16 | * |
| 17 | * You should have received a copy of the GNU General Public License version |
| 18 | * 2 along with this work; if not, write to the Free Software Foundation, |
| 19 | * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
| 20 | * |
| 21 | * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | /* |
| 27 | * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved |
| 28 | * (C) Copyright IBM Corp. 1996, 1997 - All Rights Reserved |
| 29 | * |
| 30 | * The original version of this source code and documentation is copyrighted |
| 31 | * and owned by Taligent, Inc., a wholly-owned subsidiary of IBM. These |
| 32 | * materials are provided under terms of a License Agreement between Taligent |
| 33 | * and Sun. This technology is protected by multiple US and International |
| 34 | * patents. This notice and attribution to Taligent may not be removed. |
| 35 | * Taligent is a registered trademark of Taligent, Inc. |
| 36 | * |
| 37 | */ |
| 38 | |
| 39 | package java.text; |
| 40 | |
| 41 | import java.lang.Character; |
| 42 | |
| 43 | /** |
| 44 | * Utility class for normalizing and merging patterns for collation. |
| 45 | * This is to be used with MergeCollation for adding patterns to an |
| 46 | * existing rule table. |
| 47 | * @see MergeCollation |
| 48 | * @author Mark Davis, Helena Shih |
| 49 | */ |
| 50 | |
| 51 | class PatternEntry { |
| 52 | /** |
| 53 | * Gets the current extension, quoted |
| 54 | */ |
| 55 | public void appendQuotedExtension(StringBuffer toAddTo) { |
| 56 | appendQuoted(extension,toAddTo); |
| 57 | } |
| 58 | |
| 59 | /** |
| 60 | * Gets the current chars, quoted |
| 61 | */ |
| 62 | public void appendQuotedChars(StringBuffer toAddTo) { |
| 63 | appendQuoted(chars,toAddTo); |
| 64 | } |
| 65 | |
| 66 | /** |
| 67 | * WARNING this is used for searching in a Vector. |
| 68 | * Because Vector.indexOf doesn't take a comparator, |
| 69 | * this method is ill-defined and ignores strength. |
| 70 | */ |
| 71 | public boolean equals(Object obj) { |
| 72 | if (obj == null) return false; |
| 73 | PatternEntry other = (PatternEntry) obj; |
| 74 | boolean result = chars.equals(other.chars); |
| 75 | return result; |
| 76 | } |
| 77 | |
| 78 | public int hashCode() { |
| 79 | return chars.hashCode(); |
| 80 | } |
| 81 | |
| 82 | /** |
| 83 | * For debugging. |
| 84 | */ |
| 85 | public String toString() { |
| 86 | StringBuffer result = new StringBuffer(); |
| 87 | addToBuffer(result, true, false, null); |
| 88 | return result.toString(); |
| 89 | } |
| 90 | |
| 91 | /** |
| 92 | * Gets the strength of the entry. |
| 93 | */ |
| 94 | final int getStrength() { |
| 95 | return strength; |
| 96 | } |
| 97 | |
| 98 | /** |
| 99 | * Gets the expanding characters of the entry. |
| 100 | */ |
| 101 | final String getExtension() { |
| 102 | return extension; |
| 103 | } |
| 104 | |
| 105 | /** |
| 106 | * Gets the core characters of the entry. |
| 107 | */ |
| 108 | final String getChars() { |
| 109 | return chars; |
| 110 | } |
| 111 | |
| 112 | // ===== privates ===== |
| 113 | |
| 114 | void addToBuffer(StringBuffer toAddTo, |
| 115 | boolean showExtension, |
| 116 | boolean showWhiteSpace, |
| 117 | PatternEntry lastEntry) |
| 118 | { |
| 119 | if (showWhiteSpace && toAddTo.length() > 0) |
| 120 | if (strength == Collator.PRIMARY || lastEntry != null) |
| 121 | toAddTo.append('\n'); |
| 122 | else |
| 123 | toAddTo.append(' '); |
| 124 | if (lastEntry != null) { |
| 125 | toAddTo.append('&'); |
| 126 | if (showWhiteSpace) |
| 127 | toAddTo.append(' '); |
| 128 | lastEntry.appendQuotedChars(toAddTo); |
| 129 | appendQuotedExtension(toAddTo); |
| 130 | if (showWhiteSpace) |
| 131 | toAddTo.append(' '); |
| 132 | } |
| 133 | switch (strength) { |
| 134 | case Collator.IDENTICAL: toAddTo.append('='); break; |
| 135 | case Collator.TERTIARY: toAddTo.append(','); break; |
| 136 | case Collator.SECONDARY: toAddTo.append(';'); break; |
| 137 | case Collator.PRIMARY: toAddTo.append('<'); break; |
| 138 | case RESET: toAddTo.append('&'); break; |
| 139 | case UNSET: toAddTo.append('?'); break; |
| 140 | } |
| 141 | if (showWhiteSpace) |
| 142 | toAddTo.append(' '); |
| 143 | appendQuoted(chars,toAddTo); |
| 144 | if (showExtension && extension.length() != 0) { |
| 145 | toAddTo.append('/'); |
| 146 | appendQuoted(extension,toAddTo); |
| 147 | } |
| 148 | } |
| 149 | |
| 150 | static void appendQuoted(String chars, StringBuffer toAddTo) { |
| 151 | boolean inQuote = false; |
| 152 | char ch = chars.charAt(0); |
| 153 | if (Character.isSpaceChar(ch)) { |
| 154 | inQuote = true; |
| 155 | toAddTo.append('\''); |
| 156 | } else { |
| 157 | if (PatternEntry.isSpecialChar(ch)) { |
| 158 | inQuote = true; |
| 159 | toAddTo.append('\''); |
| 160 | } else { |
| 161 | switch (ch) { |
| 162 | case 0x0010: case '\f': case '\r': |
| 163 | case '\t': case '\n': case '@': |
| 164 | inQuote = true; |
| 165 | toAddTo.append('\''); |
| 166 | break; |
| 167 | case '\'': |
| 168 | inQuote = true; |
| 169 | toAddTo.append('\''); |
| 170 | break; |
| 171 | default: |
| 172 | if (inQuote) { |
| 173 | inQuote = false; toAddTo.append('\''); |
| 174 | } |
| 175 | break; |
| 176 | } |
| 177 | } |
| 178 | } |
| 179 | toAddTo.append(chars); |
| 180 | if (inQuote) |
| 181 | toAddTo.append('\''); |
| 182 | } |
| 183 | |
| 184 | //======================================================================== |
| 185 | // Parsing a pattern into a list of PatternEntries.... |
| 186 | //======================================================================== |
| 187 | |
| 188 | PatternEntry(int strength, |
| 189 | StringBuffer chars, |
| 190 | StringBuffer extension) |
| 191 | { |
| 192 | this.strength = strength; |
| 193 | this.chars = chars.toString(); |
| 194 | this.extension = (extension.length() > 0) ? extension.toString() |
| 195 | : ""; |
| 196 | } |
| 197 | |
| 198 | static class Parser { |
| 199 | private String pattern; |
| 200 | private int i; |
| 201 | |
| 202 | public Parser(String pattern) { |
| 203 | this.pattern = pattern; |
| 204 | this.i = 0; |
| 205 | } |
| 206 | |
| 207 | public PatternEntry next() throws ParseException { |
| 208 | int newStrength = UNSET; |
| 209 | |
| 210 | newChars.setLength(0); |
| 211 | newExtension.setLength(0); |
| 212 | |
| 213 | boolean inChars = true; |
| 214 | boolean inQuote = false; |
| 215 | mainLoop: |
| 216 | while (i < pattern.length()) { |
| 217 | char ch = pattern.charAt(i); |
| 218 | if (inQuote) { |
| 219 | if (ch == '\'') { |
| 220 | inQuote = false; |
| 221 | } else { |
| 222 | if (newChars.length() == 0) newChars.append(ch); |
| 223 | else if (inChars) newChars.append(ch); |
| 224 | else newExtension.append(ch); |
| 225 | } |
| 226 | } else switch (ch) { |
| 227 | case '=': if (newStrength != UNSET) break mainLoop; |
| 228 | newStrength = Collator.IDENTICAL; break; |
| 229 | case ',': if (newStrength != UNSET) break mainLoop; |
| 230 | newStrength = Collator.TERTIARY; break; |
| 231 | case ';': if (newStrength != UNSET) break mainLoop; |
| 232 | newStrength = Collator.SECONDARY; break; |
| 233 | case '<': if (newStrength != UNSET) break mainLoop; |
| 234 | newStrength = Collator.PRIMARY; break; |
| 235 | case '&': if (newStrength != UNSET) break mainLoop; |
| 236 | newStrength = RESET; break; |
| 237 | case '\t': |
| 238 | case '\n': |
| 239 | case '\f': |
| 240 | case '\r': |
| 241 | case ' ': break; // skip whitespace TODO use Character |
| 242 | case '/': inChars = false; break; |
| 243 | case '\'': |
| 244 | inQuote = true; |
| 245 | ch = pattern.charAt(++i); |
| 246 | if (newChars.length() == 0) newChars.append(ch); |
| 247 | else if (inChars) newChars.append(ch); |
| 248 | else newExtension.append(ch); |
| 249 | break; |
| 250 | default: |
| 251 | if (newStrength == UNSET) { |
| 252 | throw new ParseException |
| 253 | ("missing char (=,;<&) : " + |
| 254 | pattern.substring(i, |
| 255 | (i+10 < pattern.length()) ? |
| 256 | i+10 : pattern.length()), |
| 257 | i); |
| 258 | } |
| 259 | if (PatternEntry.isSpecialChar(ch) && (inQuote == false)) |
| 260 | throw new ParseException |
| 261 | ("Unquoted punctuation character : " + Integer.toString(ch, 16), i); |
| 262 | if (inChars) { |
| 263 | newChars.append(ch); |
| 264 | } else { |
| 265 | newExtension.append(ch); |
| 266 | } |
| 267 | break; |
| 268 | } |
| 269 | i++; |
| 270 | } |
| 271 | if (newStrength == UNSET) |
| 272 | return null; |
| 273 | if (newChars.length() == 0) { |
| 274 | throw new ParseException |
| 275 | ("missing chars (=,;<&): " + |
| 276 | pattern.substring(i, |
| 277 | (i+10 < pattern.length()) ? |
| 278 | i+10 : pattern.length()), |
| 279 | i); |
| 280 | } |
| 281 | |
| 282 | return new PatternEntry(newStrength, newChars, newExtension); |
| 283 | } |
| 284 | |
| 285 | // We re-use these objects in order to improve performance |
| 286 | private StringBuffer newChars = new StringBuffer(); |
| 287 | private StringBuffer newExtension = new StringBuffer(); |
| 288 | |
| 289 | } |
| 290 | |
| 291 | static boolean isSpecialChar(char ch) { |
| 292 | return ((ch == '\u0020') || |
| 293 | ((ch <= '\u002F') && (ch >= '\u0022')) || |
| 294 | ((ch <= '\u003F') && (ch >= '\u003A')) || |
| 295 | ((ch <= '\u0060') && (ch >= '\u005B')) || |
| 296 | ((ch <= '\u007E') && (ch >= '\u007B'))); |
| 297 | } |
| 298 | |
| 299 | |
| 300 | static final int RESET = -2; |
| 301 | static final int UNSET = -1; |
| 302 | |
| 303 | int strength = UNSET; |
| 304 | String chars = ""; |
| 305 | String extension = ""; |
| 306 | } |