001: /*
002: * Licensed to the Apache Software Foundation (ASF) under one or more
003: * contributor license agreements. See the NOTICE file distributed with
004: * this work for additional information regarding copyright ownership.
005: * The ASF licenses this file to You under the Apache License, Version 2.0
006: * (the "License"); you may not use this file except in compliance with
007: * the License. You may obtain a copy of the License at
008: *
009: * http://www.apache.org/licenses/LICENSE-2.0
010: *
011: * Unless required by applicable law or agreed to in writing, software
012: * distributed under the License is distributed on an "AS IS" BASIS,
013: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014: * See the License for the specific language governing permissions and
015: * limitations under the License.
016: */
017:
018: /*
019: *
020: * Portions, Copyright © 1991-2005 Unicode, Inc. The following applies to Unicode.
021: *
022: * COPYRIGHT AND PERMISSION NOTICE
023: *
024: * Copyright © 1991-2005 Unicode, Inc. All rights reserved. Distributed under
025: * the Terms of Use in http://www.unicode.org/copyright.html. Permission is
026: * hereby granted, free of charge, to any person obtaining a copy of the
027: * Unicode data files and any associated documentation (the "Data Files")
028: * or Unicode software and any associated documentation (the "Software")
029: * to deal in the Data Files or Software without restriction, including without
030: * limitation the rights to use, copy, modify, merge, publish, distribute,
031: * and/or sell copies of the Data Files or Software, and to permit persons
032: * to whom the Data Files or Software are furnished to do so, provided that
033: * (a) the above copyright notice(s) and this permission notice appear with
034: * all copies of the Data Files or Software, (b) both the above copyright
035: * notice(s) and this permission notice appear in associated documentation,
036: * and (c) there is clear notice in each modified Data File or in the Software
037: * as well as in the documentation associated with the Data File(s) or Software
038: * that the data or software has been modified.
039:
040: * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
041: * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
042: * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
043: * OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
044: * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT
045: * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
046: * OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
047: * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
048: * PERFORMANCE OF THE DATA FILES OR SOFTWARE.
049: *
050: * Except as contained in this notice, the name of a copyright holder shall
051: * not be used in advertising or otherwise to promote the sale, use or other
052: * dealings in these Data Files or Software without prior written
053: * authorization of the copyright holder.
054: *
055: * 2. Additional terms from the Database:
056: *
057: * Copyright © 1995-1999 Unicode, Inc. All Rights reserved.
058: *
059: * Disclaimer
060: *
061: * The Unicode Character Database is provided as is by Unicode, Inc.
062: * No claims are made as to fitness for any particular purpose. No warranties
063: * of any kind are expressed or implied. The recipient agrees to determine
064: * applicability of information provided. If this file has been purchased
065: * on magnetic or optical media from Unicode, Inc., the sole remedy for any claim
066: * will be exchange of defective media within 90 days of receipt. This disclaimer
067: * is applicable for all other data files accompanying the Unicode Character Database,
068: * some of which have been compiled by the Unicode Consortium, and some of which
069: * have been supplied by other sources.
070: *
071: * Limitations on Rights to Redistribute This Data
072: *
073: * Recipient is granted the right to make copies in any form for internal
074: * distribution and to freely use the information supplied in the creation of
075: * products supporting the UnicodeTM Standard. The files in
076: * the Unicode Character Database can be redistributed to third parties or other
077: * organizations (whether for profit or not) as long as this notice and the disclaimer
078: * notice are retained. Information can be extracted from these files and used
079: * in documentation or programs, as long as there is an accompanying notice
080: * indicating the source.
081: */
082:
083: package java.util.regex;
084:
085: /**
086: * Represents node accepting single supplementary codepoint.
087: */
088: class SupplCharSet extends LeafSet {
089:
090: /*
091: * UTF-16 encoding of this supplementary codepoint
092: */
093: private char high = 0;
094:
095: private char low = 0;
096:
097: //int value of this supplementary codepoint
098: private int ch;
099:
100: public SupplCharSet(int ch) {
101: charCount = 2;
102: this .ch = ch;
103: char[] chUTF16 = Character.toChars(ch);
104: high = chUTF16[0];
105:
106: /*
107: * we suppose that SupplCharSet is
108: * build over supplementary codepoints only
109: */
110: low = chUTF16[1];
111: }
112:
113: public int accepts(int strIndex, CharSequence testString) {
114: char high = testString.charAt(strIndex++);
115: char low = testString.charAt(strIndex);
116: return ((this .high == high) && (this .low == low)) ? 2 : -1;
117: }
118:
119: public int find(int strIndex, CharSequence testString,
120: MatchResultImpl matchResult) {
121:
122: if (testString instanceof String) {
123: String testStr = (String) testString;
124: int strLength = matchResult.getRightBound();
125:
126: while (strIndex < strLength) {
127: strIndex = testStr.indexOf(high, strIndex);
128: if (strIndex < 0)
129: return -1;
130:
131: strIndex++;
132: if (strIndex < strLength) {
133: char ch = testStr.charAt(strIndex);
134:
135: if ((low == ch)
136: && (next.matches(strIndex + 1, testString,
137: matchResult) >= 0)) {
138: return --strIndex;
139: }
140: strIndex++;
141: }
142: }
143: return -1;
144: }
145:
146: return super .find(strIndex, testString, matchResult);
147: }
148:
149: public int findBack(int strIndex, int lastIndex,
150: CharSequence testString, MatchResultImpl matchResult) {
151:
152: if (testString instanceof String) {
153: String testStr = (String) testString;
154:
155: while (lastIndex >= strIndex) {
156: lastIndex = testStr.lastIndexOf(low, lastIndex);
157: lastIndex--;
158: if (lastIndex < 0 || lastIndex < strIndex) {
159: return -1;
160: }
161:
162: if ((high == testStr.charAt(lastIndex))
163: && next.matches(lastIndex + 2, testString,
164: matchResult) >= 0) {
165: return lastIndex;
166: }
167:
168: lastIndex--;
169: }
170: return -1;
171: }
172:
173: return super .findBack(strIndex, lastIndex, testString,
174: matchResult);
175: }
176:
177: protected String getName() {
178: return "" + high + low;
179: }
180:
181: protected int getCodePoint() {
182: return ch;
183: }
184:
185: public boolean first(AbstractSet set) {
186: if (set instanceof SupplCharSet) {
187: return ((SupplCharSet) set).getCodePoint() == ch;
188: } else if (set instanceof SupplRangeSet) {
189: return ((SupplRangeSet) set).contains(ch);
190: } else if (set instanceof CharSet) {
191: return false;
192: } else if (set instanceof RangeSet) {
193: return false;
194: }
195:
196: return true;
197: }
198: }
|