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: * This class is a range that contains only surrogate characters.
087: */
088: class LowHighSurrogateRangeSet extends JointSet {
089:
090: protected AbstractCharClass surrChars;
091:
092: protected boolean alt = false;
093:
094: public LowHighSurrogateRangeSet(AbstractCharClass surrChars,
095: AbstractSet next) {
096: this .surrChars = surrChars.getInstance();
097: this .alt = surrChars.alt;
098: setNext(next);
099: }
100:
101: public LowHighSurrogateRangeSet(AbstractCharClass surrChars) {
102: this .surrChars = surrChars.getInstance();
103: this .alt = surrChars.alt;
104: }
105:
106: /**
107: * Returns the next.
108: */
109: public AbstractSet getNext() {
110: return this .next;
111: }
112:
113: /**
114: * Sets next abstract set.
115: * @param next
116: * The next to set.
117: */
118: public void setNext(AbstractSet next) {
119: this .next = next;
120: }
121:
122: /**
123: * Returns stringIndex+shift, the next position to match
124: */
125: public int matches(int stringIndex, CharSequence testString,
126: MatchResultImpl matchResult) {
127: int startStr = matchResult.getLeftBound();
128: int strLength = matchResult.getRightBound();
129:
130: if (stringIndex + 1 > strLength) {
131: matchResult.hitEnd = true;
132: return -1;
133: }
134:
135: char ch = testString.charAt(stringIndex);
136:
137: if (!surrChars.contains(ch)) {
138: return -1;
139: }
140:
141: if (Character.isHighSurrogate(ch)) {
142:
143: if (stringIndex + 1 < strLength) {
144: char low = testString.charAt(stringIndex + 1);
145:
146: if (Character.isLowSurrogate(low)) {
147: return -1;
148: }
149: }
150: } else if (Character.isLowSurrogate(ch)) {
151:
152: if (stringIndex > startStr) {
153: char high = testString.charAt(stringIndex - 1);
154:
155: if (Character.isHighSurrogate(high)) {
156: return -1;
157: }
158: }
159: }
160:
161: return next.matches(stringIndex + 1, testString, matchResult);
162: }
163:
164: protected String getName() {
165: return "range:" + (alt ? "^ " : " ") + surrChars.toString();
166: }
167:
168: public boolean first(AbstractSet set) {
169: if (set instanceof CharSet) {
170: return false;
171: } else if (set instanceof RangeSet) {
172: return false;
173: } else if (set instanceof SupplRangeSet) {
174: return false;
175: } else if (set instanceof SupplCharSet) {
176: return false;
177: }
178:
179: return true;
180: }
181:
182: protected AbstractCharClass getChars() {
183: return surrChars;
184: }
185:
186: public boolean hasConsumed(MatchResultImpl matchResult) {
187: return true;
188: }
189: }
|