GNU Classpath (0.92) | |
Frames | No Frames |
1: /* Collator.java -- Perform locale dependent String comparisons. 2: Copyright (C) 1998, 1999, 2000, 2001, 2004, 2005 Free Software Foundation, Inc. 3: 4: This file is part of GNU Classpath. 5: 6: GNU Classpath is free software; you can redistribute it and/or modify 7: it under the terms of the GNU General Public License as published by 8: the Free Software Foundation; either version 2, or (at your option) 9: any later version. 10: 11: GNU Classpath is distributed in the hope that it will be useful, but 12: WITHOUT ANY WARRANTY; without even the implied warranty of 13: MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14: General Public License for more details. 15: 16: You should have received a copy of the GNU General Public License 17: along with GNU Classpath; see the file COPYING. If not, write to the 18: Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 19: 02110-1301 USA. 20: 21: Linking this library statically or dynamically with other modules is 22: making a combined work based on this library. Thus, the terms and 23: conditions of the GNU General Public License cover the whole 24: combination. 25: 26: As a special exception, the copyright holders of this library give you 27: permission to link this library with independent modules to produce an 28: executable, regardless of the license terms of these independent 29: modules, and to copy and distribute the resulting executable under 30: terms of your choice, provided that you also meet, for each linked 31: independent module, the terms and conditions of the license of that 32: module. An independent module is a module which is not derived from 33: or based on this library. If you modify this library, you may extend 34: this exception to your version of the library, but you are not 35: obligated to do so. If you do not wish to do so, delete this 36: exception statement from your version. */ 37: 38: 39: package java.text; 40: 41: import gnu.java.locale.LocaleHelper; 42: 43: import java.util.Comparator; 44: import java.util.Locale; 45: import java.util.MissingResourceException; 46: import java.util.ResourceBundle; 47: 48: /** 49: * This class is the abstract superclass of classes which perform 50: * locale dependent <code>String</code> comparisons. A caller requests 51: * an instance of <code>Collator</code> for a particular locale using 52: * the <code>getInstance()</code> static method in this class. That method 53: * will return a locale specific subclass of <code>Collator</code> which 54: * can be used to perform <code>String</code> comparisons for that locale. 55: * If a subclass of <code>Collator</code> cannot be located for a particular 56: * locale, a default instance for the current locale will be returned. 57: * 58: * In addition to setting the correct locale, there are two additional 59: * settings that can be adjusted to affect <code>String</code> comparisons: 60: * strength and decomposition. The strength value determines the level 61: * of signficance of character differences required for them to sort 62: * differently. (For example, whether or not capital letters are considered 63: * different from lower case letters). The decomposition value affects how 64: * variants of the same character are treated for sorting purposes. (For 65: * example, whether or not an accent is signficant or not). These settings 66: * are described in detail in the documentation for the methods and values 67: * that are related to them. 68: * 69: * @author Tom Tromey (tromey@cygnus.com) 70: * @author Aaron M. Renn (arenn@urbanophile.com) 71: * @date March 18, 1999 72: */ 73: public abstract class Collator implements Comparator, Cloneable 74: { 75: /** 76: * This constant is a strength value which indicates that only primary 77: * differences between characters will be considered signficant. As an 78: * example, two completely different English letters such as 'a' and 'b' 79: * are considered to have a primary difference. 80: */ 81: public static final int PRIMARY = 0; 82: 83: /** 84: * This constant is a strength value which indicates that only secondary 85: * or primary differences between characters will be considered 86: * significant. An example of a secondary difference between characters 87: * are instances of the same letter with different accented forms. 88: */ 89: public static final int SECONDARY = 1; 90: 91: /** 92: * This constant is a strength value which indicates that tertiary, 93: * secondary, and primary differences will be considered during sorting. 94: * An example of a tertiary difference is capitalization of a given letter. 95: * This is the default value for the strength setting. 96: */ 97: public static final int TERTIARY = 2; 98: 99: /** 100: * This constant is a strength value which indicates that any difference 101: * at all between character values are considered significant. 102: */ 103: public static final int IDENTICAL = 3; 104: 105: /** 106: * This constant indicates that accented characters won't be decomposed 107: * when performing comparisons. This will yield the fastest results, but 108: * will only work correctly in call cases for languages which do not 109: * use accents such as English. 110: */ 111: public static final int NO_DECOMPOSITION = 0; 112: 113: /** 114: * This constant indicates that only characters which are canonical variants 115: * in Unicode 2.0 will be decomposed prior to performing comparisons. This 116: * will cause accented languages to be sorted correctly. This is the 117: * default decomposition value. 118: */ 119: public static final int CANONICAL_DECOMPOSITION = 1; 120: 121: /** 122: * This constant indicates that both canonical variants and compatibility 123: * variants in Unicode 2.0 will be decomposed prior to performing 124: * comparisons. This is the slowest mode, but is required to get the 125: * correct sorting for certain languages with certain special formats. 126: */ 127: public static final int FULL_DECOMPOSITION = 2; 128: 129: /** 130: * This method initializes a new instance of <code>Collator</code> to have 131: * the default strength (TERTIARY) and decomposition 132: * (CANONICAL_DECOMPOSITION) settings. This constructor is protected and 133: * is for use by subclasses only. Non-subclass callers should use the 134: * static <code>getInstance()</code> methods of this class to instantiate 135: * <code>Collation</code> objects for the desired locale. 136: */ 137: protected Collator () 138: { 139: strength = TERTIARY; 140: decmp = CANONICAL_DECOMPOSITION; 141: } 142: 143: /** 144: * This method compares the two <code>String</code>'s and returns an 145: * integer indicating whether or not the first argument is less than, 146: * equal to, or greater than the second argument. The comparison is 147: * performed according to the rules of the locale for this 148: * <code>Collator</code> and the strength and decomposition rules in 149: * effect. 150: * 151: * @param source The first object to compare 152: * @param target The second object to compare 153: * 154: * @return A negative integer if str1 < str2, 0 if str1 == str2, or 155: * a positive integer if str1 > str2. 156: */ 157: public abstract int compare (String source, String target); 158: 159: /** 160: * This method compares the two <code>Object</code>'s and returns an 161: * integer indicating whether or not the first argument is less than, 162: * equal to, or greater than the second argument. These two objects 163: * must be <code>String</code>'s or an exception will be thrown. 164: * 165: * @param o1 The first object to compare 166: * @param o2 The second object to compare 167: * 168: * @return A negative integer if obj1 < obj2, 0 if obj1 == obj2, or 169: * a positive integer if obj1 > obj2. 170: * 171: * @exception ClassCastException If the arguments are not instances 172: * of <code>String</code>. 173: */ 174: public int compare (Object o1, Object o2) 175: { 176: return compare ((String) o1, (String) o2); 177: } 178: 179: /** 180: * This method tests the specified object for equality against this 181: * object. This will be true if and only if the following conditions are 182: * met: 183: * <ul> 184: * <li>The specified object is not <code>null</code>.</li> 185: * <li>The specified object is an instance of <code>Collator</code>.</li> 186: * <li>The specified object has the same strength and decomposition 187: * settings as this object.</li> 188: * </ul> 189: * 190: * @param obj The <code>Object</code> to test for equality against 191: * this object. 192: * 193: * @return <code>true</code> if the specified object is equal to 194: * this one, <code>false</code> otherwise. 195: */ 196: public boolean equals (Object obj) 197: { 198: if (! (obj instanceof Collator)) 199: return false; 200: Collator c = (Collator) obj; 201: return decmp == c.decmp && strength == c.strength; 202: } 203: 204: /** 205: * This method tests whether the specified <code>String</code>'s are equal 206: * according to the collation rules for the locale of this object and 207: * the current strength and decomposition settings. 208: * 209: * @param source The first <code>String</code> to compare 210: * @param target The second <code>String</code> to compare 211: * 212: * @return <code>true</code> if the two strings are equal, 213: * <code>false</code> otherwise. 214: */ 215: public boolean equals (String source, String target) 216: { 217: return compare (source, target) == 0; 218: } 219: 220: /** 221: * This method returns a copy of this <code>Collator</code> object. 222: * 223: * @return A duplicate of this object. 224: */ 225: public Object clone () 226: { 227: try 228: { 229: return super.clone (); 230: } 231: catch (CloneNotSupportedException _) 232: { 233: return null; 234: } 235: } 236: 237: /** 238: * This method returns an array of <code>Locale</code> objects which is 239: * the list of locales for which <code>Collator</code> objects exist. 240: * 241: * @return The list of locales for which <code>Collator</code>'s exist. 242: */ 243: public static synchronized Locale[] getAvailableLocales () 244: { 245: return LocaleHelper.getCollatorLocales(); 246: } 247: 248: /** 249: * This method transforms the specified <code>String</code> into a 250: * <code>CollationKey</code> for faster comparisons. This is useful when 251: * comparisons against a string might be performed multiple times, such 252: * as during a sort operation. 253: * 254: * @param source The <code>String</code> to convert. 255: * 256: * @return A <code>CollationKey</code> for the specified <code>String</code>. 257: */ 258: public abstract CollationKey getCollationKey (String source); 259: 260: /** 261: * This method returns the current decomposition setting for this 262: * object. This * will be one of NO_DECOMPOSITION, 263: * CANONICAL_DECOMPOSITION, or * FULL_DECOMPOSITION. See the 264: * documentation for those constants for an * explanation of this 265: * setting. 266: * 267: * @return The current decomposition setting. 268: */ 269: public synchronized int getDecomposition () 270: { 271: return decmp; 272: } 273: 274: /** 275: * This method returns an instance of <code>Collator</code> for the 276: * default locale. 277: * 278: * @return A <code>Collator</code> for the default locale. 279: */ 280: public static Collator getInstance () 281: { 282: return getInstance (Locale.getDefault()); 283: } 284: 285: /** 286: * This method returns an instance of <code>Collator</code> for the 287: * specified locale. If no <code>Collator</code> exists for the desired 288: * locale, a <code>Collator</code> for the default locale will be returned. 289: * 290: * @param loc The desired locale to load a <code>Collator</code> for. 291: * 292: * @return A <code>Collator</code> for the requested locale 293: */ 294: public static Collator getInstance (Locale loc) 295: { 296: ResourceBundle res; 297: String pattern; 298: try 299: { 300: res = ResourceBundle.getBundle("gnu.java.locale.LocaleInformation", 301: loc, ClassLoader.getSystemClassLoader()); 302: pattern = res.getString("collation_rules"); 303: } 304: catch (MissingResourceException x) 305: { 306: pattern = "<0<1<2<3<4<5<6<7<8<9<A,a<b,B<c,C<d,D<e,E<f,F<g,G<h,H<i,I<j,J<k,K" + 307: "<l,L<m,M<n,N<o,O<p,P<q,Q<r,R<s,S<t,T<u,U<v,V<w,W<x,X<y,Y<z,Z"; 308: } 309: try 310: { 311: return new RuleBasedCollator (pattern); 312: } 313: catch (ParseException x) 314: { 315: throw (InternalError)new InternalError().initCause(x); 316: } 317: } 318: 319: /** 320: * This method returns the current strength setting for this object. This 321: * will be one of PRIMARY, SECONDARY, TERTIARY, or IDENTICAL. See the 322: * documentation for those constants for an explanation of this setting. 323: * 324: * @return The current strength setting. 325: */ 326: public synchronized int getStrength () 327: { 328: return strength; 329: } 330: 331: /** 332: * This method returns a hash code value for this object. 333: * 334: * @return A hash value for this object. 335: */ 336: public abstract int hashCode (); 337: 338: /** 339: * This method sets the decomposition setting for this object to the 340: * specified value. This must be one of NO_DECOMPOSITION, 341: * CANONICAL_DECOMPOSITION, or FULL_DECOMPOSITION. Otherwise an 342: * exception will be thrown. See the documentation for those 343: * contants for an explanation of this setting. 344: * 345: * @param mode The new decomposition setting. 346: * 347: * @exception IllegalArgumentException If the requested 348: * decomposition setting is not valid. 349: */ 350: public synchronized void setDecomposition (int mode) 351: { 352: if (mode != NO_DECOMPOSITION 353: && mode != CANONICAL_DECOMPOSITION 354: && mode != FULL_DECOMPOSITION) 355: throw new IllegalArgumentException (); 356: decmp = mode; 357: } 358: 359: /** 360: * This method sets the strength setting for this object to the specified 361: * value. This must be one of PRIMARY, SECONDARY, TERTIARY, or IDENTICAL. 362: * Otherwise an exception is thrown. See the documentation for these 363: * constants for an explanation of this setting. 364: * 365: * @param strength The new strength setting. 366: * 367: * @exception IllegalArgumentException If the requested strength 368: * setting value is not valid. 369: */ 370: public synchronized void setStrength (int strength) 371: { 372: if (strength != PRIMARY && strength != SECONDARY 373: && strength != TERTIARY && strength != IDENTICAL) 374: throw new IllegalArgumentException (); 375: this.strength = strength; 376: } 377: 378: // Decompose a single character and append results to the buffer. 379: // FIXME: for libgcj this is a native method which handles 380: // decomposition. For Classpath, for now, it does nothing. 381: final void decomposeCharacter (char c, StringBuffer buf) 382: { 383: buf.append (c); 384: } 385: 386: /** 387: * This is the current collation decomposition setting. 388: */ 389: int decmp; 390: 391: /** 392: * This is the current collation strength setting. 393: */ 394: int strength; 395: }
GNU Classpath (0.92) |