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 character from the given char class.
087: * This character can be supplementary (2 chars needed to represent) or from
088: * basic multilingual pane (1 needed char to represent it).
089: */
090: class SupplRangeSet extends JointSet {
091:
092: protected AbstractCharClass chars;
093:
094: protected boolean alt = false;
095:
096: public SupplRangeSet(AbstractCharClass cs, AbstractSet next) {
097: this .chars = cs.getInstance();
098: this .alt = cs.alt;
099: this .next = next;
100: }
101:
102: public SupplRangeSet(AbstractCharClass cc) {
103: this .chars = cc.getInstance();
104: this .alt = cc.alt;
105: }
106:
107: public int matches(int stringIndex, CharSequence testString,
108: MatchResultImpl matchResult) {
109: int strLength = matchResult.getRightBound();
110: int offset = -1;
111:
112: if (stringIndex < strLength) {
113: char high = testString.charAt(stringIndex++);
114:
115: if (contains(high)
116: && (offset = next.matches(stringIndex, testString,
117: matchResult)) > 0) {
118: return offset;
119: }
120:
121: if (stringIndex < strLength) {
122: char low = testString.charAt(stringIndex++);
123:
124: if (Character.isSurrogatePair(high, low)
125: && contains(Character.toCodePoint(high, low))) {
126: return next.matches(stringIndex, testString,
127: matchResult);
128: }
129: }
130: }
131:
132: return -1;
133: }
134:
135: protected String getName() {
136: return "range:" + (alt ? "^ " : " ") + chars.toString();
137: }
138:
139: public boolean contains(int ch) {
140: return chars.contains(ch);
141: }
142:
143: public boolean first(AbstractSet set) {
144: if (set instanceof SupplCharSet) {
145: return AbstractCharClass.intersects(chars,
146: ((SupplCharSet) set).getCodePoint());
147: } else if (set instanceof CharSet) {
148: return AbstractCharClass.intersects(chars, ((CharSet) set)
149: .getChar());
150: } else if (set instanceof SupplRangeSet) {
151: return AbstractCharClass.intersects(chars,
152: ((SupplRangeSet) set).chars);
153: } else if (set instanceof RangeSet) {
154: return AbstractCharClass.intersects(chars, ((RangeSet) set)
155: .getChars());
156: }
157:
158: return true;
159: }
160:
161: protected AbstractCharClass getChars() {
162: return chars;
163: }
164:
165: public AbstractSet getNext() {
166: return next;
167: }
168:
169: public void setNext(AbstractSet next) {
170: this .next = next;
171: }
172:
173: public boolean hasConsumed(MatchResultImpl mr) {
174: return true;
175: }
176: }
|