Frames | No Frames |
1: /* Provider.java -- 2: Copyright (C) 2002, 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: package gnu.java.nio.charset; 39: 40: import java.nio.charset.Charset; 41: import java.nio.charset.spi.CharsetProvider; 42: import java.util.Collections; 43: import java.util.HashMap; 44: import java.util.Iterator; 45: 46: /** 47: * Charset provider for the required charsets. Used by 48: * {@link Charset#charsetForName} and * {@link Charset#availableCharsets}. 49: * 50: * @author Jesse Rosenstock 51: * @author Robert Schuster (thebohemian@gmx.net) 52: * @see Charset 53: */ 54: public final class Provider extends CharsetProvider 55: { 56: private static Provider singleton; 57: 58: static 59: { 60: synchronized (Provider.class) 61: { 62: singleton = null; 63: } 64: } 65: 66: /** 67: * Map from charset name to charset canonical name. The strings 68: * are all lower-case to allow case-insensitive retrieval of 69: * Charset instances. 70: */ 71: private final HashMap canonicalNames; 72: 73: /** 74: * Map from lower-case canonical name to Charset. 75: * TODO: We may want to use soft references. We would then need to keep 76: * track of the class name to regenerate the object. 77: */ 78: private final HashMap charsets; 79: 80: /** 81: * We don't load all available charsets at the start 82: */ 83: private boolean extendedLoaded; 84: 85: private Provider () 86: { 87: extendedLoaded = false; 88: canonicalNames = new HashMap (); 89: charsets = new HashMap (); 90: 91: // US-ASCII aka ISO646-US 92: addCharset (new US_ASCII ()); 93: 94: // ISO-8859-1 aka ISO-LATIN-1 95: addCharset (new ISO_8859_1 ()); 96: 97: // UTF-8 98: addCharset (new UTF_8 ()); 99: 100: // UTF-16BE 101: addCharset (new UTF_16BE ()); 102: 103: // UTF-16LE 104: addCharset (new UTF_16LE ()); 105: 106: // UTF-16 107: addCharset (new UTF_16 ()); 108: 109: // UTF-16LE (marked) 110: addCharset (new UnicodeLittle ()); 111: 112: // Windows-1250 aka cp-1250 (East European) 113: addCharset (new Windows1250 ()); 114: 115: // Windows-1251 (Cyrillic) 116: addCharset (new Windows1251 ()); 117: 118: // Windows-1252 aka cp-1252 (Latin-1) 119: addCharset (new Windows1252 ()); 120: 121: // Windows-1253 (Greek) 122: addCharset (new Windows1253 ()); 123: 124: // Windows-1254 (Turkish) 125: addCharset (new Windows1254 ()); 126: 127: // Windows-1257 (Baltic) 128: addCharset (new Windows1257 ()); 129: 130: // ISO-8859-2 aka ISO-LATIN-2 131: addCharset (new ISO_8859_2 ()); 132: 133: // ISO-8859-4 aka ISO-LATIN-4 134: addCharset (new ISO_8859_4 ()); 135: 136: // ISO-8859-5 (Cyrillic) 137: addCharset (new ISO_8859_5 ()); 138: 139: // ISO-8859-7 (Greek) 140: addCharset (new ISO_8859_7 ()); 141: 142: // ISO-8859-9 aka ISO-LATIN-5 143: addCharset (new ISO_8859_9 ()); 144: 145: // ISO-8859-13 aka ISO-LATIN-7 146: addCharset (new ISO_8859_13 ()); 147: 148: // ISO-8859-15 aka ISO-LATIN-9 149: addCharset (new ISO_8859_15 ()); 150: 151: // KOI8 (Cyrillic) 152: addCharset (new KOI_8 ()); 153: } 154: 155: /** 156: * Load non-mandatory charsets. 157: */ 158: private void loadExtended () 159: { 160: if(extendedLoaded) 161: return; 162: 163: addCharset (new ISO_8859_3 ()); // ISO-8859-3 aka ISO-LATIN-3 164: addCharset (new ISO_8859_6 ()); // ISO-8859-6 (Arabic) 165: addCharset (new ISO_8859_8 ()); // ISO-8859-8 (Hebrew) 166: 167: // Some more codepages 168: addCharset (new Cp855()); // IBM Cyrillic 169: addCharset (new Cp857()); // IBM Turkish 170: addCharset (new Cp860()); // MSDOS Portugese 171: addCharset (new Cp861()); // MSDOS Icelandic 172: addCharset (new Cp862()); // PC Hebrew 173: addCharset (new Cp863()); // MSDOS Can. French 174: addCharset (new Cp864()); // PC Arabic 175: addCharset (new Cp865()); // MSDOS Nordic 176: addCharset (new Cp866()); // MSDOS Russian 177: addCharset (new Cp869()); // IBM modern Greek 178: addCharset (new Cp874()); // IBM Thai 179: extendedLoaded = true; 180: } 181: 182: public Iterator charsets () 183: { 184: loadExtended(); 185: return Collections.unmodifiableCollection (charsets.values ()) 186: .iterator (); 187: } 188: 189: /** 190: * Returns a Charset instance by converting the given 191: * name to lower-case, looking up the canonical charset 192: * name and finally looking up the Charset with that name. 193: * 194: * <p>The lookup is therefore case-insensitive.</p> 195: * 196: * @returns The Charset having <code>charsetName</code> 197: * as its alias or null if no such Charset exist. 198: */ 199: public Charset charsetForName (String charsetName) 200: { 201: Charset cs = (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase())); 202: if(cs == null && !extendedLoaded) 203: { 204: loadExtended(); 205: cs = (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase())); 206: } 207: return cs; 208: } 209: 210: /** 211: * Puts a Charset under its canonical name into the 'charsets' map. 212: * Then puts a mapping from all its alias names to the canonical name. 213: * 214: * <p>All names are converted to lower-case</p>. 215: * 216: * @param cs 217: */ 218: private void addCharset (Charset cs) 219: { 220: String canonicalName = cs.name().toLowerCase(); 221: charsets.put (canonicalName, cs); 222: 223: /* Adds a mapping between the canonical name 224: * itself making a lookup using that name 225: * no special case. 226: */ 227: canonicalNames.put(canonicalName, canonicalName); 228: 229: for (Iterator i = cs.aliases ().iterator (); i.hasNext (); ) 230: canonicalNames.put (((String) i.next()).toLowerCase(), canonicalName); 231: } 232: 233: public static synchronized Provider provider () 234: { 235: if (singleton == null) 236: singleton = new Provider (); 237: return singleton; 238: } 239: }