1 /*
2 * Copyright (c) 2005, 2011, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25 /*
26 *******************************************************************************
27 * (C) Copyright IBM Corp. and others, 1996-2009 - All Rights Reserved *
28 * *
29 * The original version of this source code and documentation is copyrighted *
30 * and owned by IBM, These materials are provided under terms of a License *
31 * Agreement between IBM and Sun. This technology is protected by multiple *
32 * US and International patents. This notice and attribution to IBM may not *
33 * to removed. *
34 *******************************************************************************
35 */
36
37 package sun.text.normalizer;
38
39 import java.util.Iterator;
40
41 /**
42 * UnicodeSetIterator iterates over the contents of a UnicodeSet. It
43 * iterates over either code points or code point ranges. After all
44 * code points or ranges have been returned, it returns the
45 * multicharacter strings of the UnicodSet, if any.
46 *
47 * <p>To iterate over code points, use a loop like this:
48 * <pre>
49 * UnicodeSetIterator it(set);
50 * while (set.next()) {
51 * if (set.codepoint != UnicodeSetIterator::IS_STRING) {
52 * processCodepoint(set.codepoint);
53 * } else {
54 * processString(set.string);
55 * }
56 * }
57 * </pre>
58 *
59 * <p>To iterate over code point ranges, use a loop like this:
60 * <pre>
61 * UnicodeSetIterator it(set);
62 * while (set.nextRange()) {
63 * if (set.codepoint != UnicodeSetIterator::IS_STRING) {
64 * processCodepointRange(set.codepoint, set.codepointEnd);
65 * } else {
66 * processString(set.string);
67 * }
68 * }
69 * </pre>
70 * @author M. Davis
71 * @stable ICU 2.0
72 */
73 public class UnicodeSetIterator {
74
75 /**
76 * Value of {@code codepoint} if the iterator points to a string.
77 * If {@code codepoint == IS_STRING}, then examine
78 * {@code string} for the current iteration result.
79 * @stable ICU 2.0
80 */
81 public static int IS_STRING = -1;
82
83 /**
84 * Current code point, or the special value {@code IS_STRING}, if
85 * the iterator points to a string.
86 * @stable ICU 2.0
87 */
88 public int codepoint;
89
90 /**
91 * When iterating over ranges using {@code nextRange()},
92 * {@code codepointEnd} contains the inclusive end of the
93 * iteration range, if {@code codepoint != IS_STRING}. If
94 * iterating over code points using {@code next()}, or if
95 * {@code codepoint == IS_STRING}, then the value of
96 * {@code codepointEnd} is undefined.
97 * @stable ICU 2.0
98 */
99 public int codepointEnd;
100
101 /**
102 * If {@code codepoint == IS_STRING}, then {@code string} points
103 * to the current string. If {@code codepoint != IS_STRING}, the
104 * value of {@code string} is undefined.
105 * @stable ICU 2.0
106 */
107 public String string;
108
109 /**
110 * Create an iterator over the given set.
111 * @param set set to iterate over
112 * @stable ICU 2.0
113 */
114 public UnicodeSetIterator(UnicodeSet set) {
115 reset(set);
116 }
117
118 /**
119 * Returns the next element in the set, either a code point range
120 * or a string. If there are no more elements in the set, return
121 * false. If {@code codepoint == IS_STRING}, the value is a
122 * string in the {@code string} field. Otherwise the value is a
123 * range of one or more code points from {@code codepoint} to
124 * {@code codepointeEnd} inclusive.
125 *
126 * <p>The order of iteration is all code points ranges in sorted
127 * order, followed by all strings sorted order. Ranges are
128 * disjoint and non-contiguous. {@code string} is undefined
129 * unless {@code codepoint == IS_STRING}. Do not mix calls to
130 * {@code next()} and {@code nextRange()} without calling
131 * {@code reset()} between them. The results of doing so are
132 * undefined.
133 *
134 * @return true if there was another element in the set and this
135 * object contains the element.
136 * @stable ICU 2.0
137 */
138 public boolean nextRange() {
139 if (nextElement <= endElement) {
140 codepointEnd = endElement;
141 codepoint = nextElement;
142 nextElement = endElement+1;
143 return true;
144 }
145 if (range < endRange) {
146 loadRange(++range);
147 codepointEnd = endElement;
148 codepoint = nextElement;
149 nextElement = endElement+1;
150 return true;
151 }
152
153 // stringIterator == null iff there are no string elements remaining
154
155 if (stringIterator == null) return false;
156 codepoint = IS_STRING; // signal that value is actually a string
157 string = stringIterator.next();
158 if (!stringIterator.hasNext()) stringIterator = null;
159 return true;
160 }
161
162 /**
163 * Sets this iterator to visit the elements of the given set and
164 * resets it to the start of that set. The iterator is valid only
165 * so long as {@code set} is valid.
166 * @param uset the set to iterate over.
167 * @stable ICU 2.0
168 */
169 public void reset(UnicodeSet uset) {
170 set = uset;
171 reset();
172 }
173
174 /**
175 * Resets this iterator to the start of the set.
176 * @stable ICU 2.0
177 */
178 public void reset() {
179 endRange = set.getRangeCount() - 1;
180 range = 0;
181 endElement = -1;
182 nextElement = 0;
183 if (endRange >= 0) {
184 loadRange(range);
185 }
186 stringIterator = null;
187 if (set.strings != null) {
188 stringIterator = set.strings.iterator();
189 if (!stringIterator.hasNext()) stringIterator = null;
190 }
191 }
192
193 // ======================= PRIVATES ===========================
194
195 private UnicodeSet set;
196 private int endRange = 0;
197 private int range = 0;
198 /**
199 * @internal
200 */
201 protected int endElement;
202 /**
203 * @internal
204 */
205 protected int nextElement;
206 private Iterator<String> stringIterator = null;
207
208 /**
209 * Invariant: stringIterator is null when there are no (more) strings remaining
210 */
211
212 /**
213 * @internal
214 */
215 protected void loadRange(int aRange) {
216 nextElement = set.getRangeStart(aRange);
217 endElement = set.getRangeEnd(aRange);
218 }
219 }