1 /*
2 * Copyright (c) 2000, 2017, 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 package java.lang;
27
28 import java.util.NoSuchElementException;
29 import java.util.PrimitiveIterator;
30 import java.util.Spliterator;
31 import java.util.Spliterators;
32 import java.util.function.IntConsumer;
33 import java.util.stream.IntStream;
34 import java.util.stream.StreamSupport;
35
36 /**
37 * A {@code CharSequence} is a readable sequence of {@code char} values. This
38 * interface provides uniform, read-only access to many different kinds of
39 * {@code char} sequences.
40 * A {@code char} value represents a character in the <i>Basic
41 * Multilingual Plane (BMP)</i> or a surrogate. Refer to <a
42 * href="Character.html#unicode">Unicode Character Representation</a> for details.
43 *
44 * <p> This interface does not refine the general contracts of the {@link
45 * java.lang.Object#equals(java.lang.Object) equals} and {@link
46 * java.lang.Object#hashCode() hashCode} methods. The result of comparing two
47 * objects that implement {@code CharSequence} is therefore, in general,
48 * undefined. Each object may be implemented by a different class, and there
49 * is no guarantee that each class will be capable of testing its instances
50 * for equality with those of the other. It is therefore inappropriate to use
51 * arbitrary {@code CharSequence} instances as elements in a set or as keys in
52 * a map. </p>
53 *
54 * @author Mike McCloskey
55 * @since 1.4
56 * @spec JSR-51
57 */
58
59 public interface CharSequence {
60
61 /**
62 * Returns the length of this character sequence. The length is the number
63 * of 16-bit {@code char}s in the sequence.
64 *
65 * @return the number of {@code char}s in this sequence
66 */
67 int length();
68
69 /**
70 * Returns the {@code char} value at the specified index. An index ranges from zero
71 * to {@code length() - 1}. The first {@code char} value of the sequence is at
72 * index zero, the next at index one, and so on, as for array
73 * indexing.
74 *
75 * <p>If the {@code char} value specified by the index is a
76 * <a href="{@docRoot}/java/lang/Character.html#unicode">surrogate</a>, the surrogate
77 * value is returned.
78 *
79 * @param index the index of the {@code char} value to be returned
80 *
81 * @return the specified {@code char} value
82 *
83 * @throws IndexOutOfBoundsException
84 * if the {@code index} argument is negative or not less than
85 * {@code length()}
86 */
87 char charAt(int index);
88
89 /**
90 * Returns a {@code CharSequence} that is a subsequence of this sequence.
91 * The subsequence starts with the {@code char} value at the specified index and
92 * ends with the {@code char} value at index {@code end - 1}. The length
93 * (in {@code char}s) of the
94 * returned sequence is {@code end - start}, so if {@code start == end}
95 * then an empty sequence is returned.
96 *
97 * @param start the start index, inclusive
98 * @param end the end index, exclusive
99 *
100 * @return the specified subsequence
101 *
102 * @throws IndexOutOfBoundsException
103 * if {@code start} or {@code end} are negative,
104 * if {@code end} is greater than {@code length()},
105 * or if {@code start} is greater than {@code end}
106 */
107 CharSequence subSequence(int start, int end);
108
109 /**
110 * Returns a string containing the characters in this sequence in the same
111 * order as this sequence. The length of the string will be the length of
112 * this sequence.
113 *
114 * @return a string consisting of exactly this sequence of characters
115 */
116 public String toString();
117
118 /**
119 * Returns a stream of {@code int} zero-extending the {@code char} values
120 * from this sequence. Any char which maps to a <a
121 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
122 * point</a> is passed through uninterpreted.
123 *
124 * <p>The stream binds to this sequence when the terminal stream operation
125 * commences (specifically, for mutable sequences the spliterator for the
126 * stream is <a href="../util/Spliterator.html#binding"><em>late-binding</em></a>).
127 * If the sequence is modified during that operation then the result is
128 * undefined.
129 *
130 * @return an IntStream of char values from this sequence
131 * @since 1.8
132 */
133 public default IntStream chars() {
134 class CharIterator implements PrimitiveIterator.OfInt {
135 int cur = 0;
136
137 public boolean hasNext() {
138 return cur < length();
139 }
140
141 public int nextInt() {
142 if (hasNext()) {
143 return charAt(cur++);
144 } else {
145 throw new NoSuchElementException();
146 }
147 }
148
149 @Override
150 public void forEachRemaining(IntConsumer block) {
151 for (; cur < length(); cur++) {
152 block.accept(charAt(cur));
153 }
154 }
155 }
156
157 return StreamSupport.intStream(() ->
158 Spliterators.spliterator(
159 new CharIterator(),
160 length(),
161 Spliterator.ORDERED),
162 Spliterator.SUBSIZED | Spliterator.SIZED | Spliterator.ORDERED,
163 false);
164 }
165
166 /**
167 * Returns a stream of code point values from this sequence. Any surrogate
168 * pairs encountered in the sequence are combined as if by {@linkplain
169 * Character#toCodePoint Character.toCodePoint} and the result is passed
170 * to the stream. Any other code units, including ordinary BMP characters,
171 * unpaired surrogates, and undefined code units, are zero-extended to
172 * {@code int} values which are then passed to the stream.
173 *
174 * <p>The stream binds to this sequence when the terminal stream operation
175 * commences (specifically, for mutable sequences the spliterator for the
176 * stream is <a href="../util/Spliterator.html#binding"><em>late-binding</em></a>).
177 * If the sequence is modified during that operation then the result is
178 * undefined.
179 *
180 * @return an IntStream of Unicode code points from this sequence
181 * @since 1.8
182 */
183 public default IntStream codePoints() {
184 class CodePointIterator implements PrimitiveIterator.OfInt {
185 int cur = 0;
186
187 @Override
188 public void forEachRemaining(IntConsumer block) {
189 final int length = length();
190 int i = cur;
191 try {
192 while (i < length) {
193 char c1 = charAt(i++);
194 if (!Character.isHighSurrogate(c1) || i >= length) {
195 block.accept(c1);
196 } else {
197 char c2 = charAt(i);
198 if (Character.isLowSurrogate(c2)) {
199 i++;
200 block.accept(Character.toCodePoint(c1, c2));
201 } else {
202 block.accept(c1);
203 }
204 }
205 }
206 } finally {
207 cur = i;
208 }
209 }
210
211 public boolean hasNext() {
212 return cur < length();
213 }
214
215 public int nextInt() {
216 final int length = length();
217
218 if (cur >= length) {
219 throw new NoSuchElementException();
220 }
221 char c1 = charAt(cur++);
222 if (Character.isHighSurrogate(c1) && cur < length) {
223 char c2 = charAt(cur);
224 if (Character.isLowSurrogate(c2)) {
225 cur++;
226 return Character.toCodePoint(c1, c2);
227 }
228 }
229 return c1;
230 }
231 }
232
233 return StreamSupport.intStream(() ->
234 Spliterators.spliteratorUnknownSize(
235 new CodePointIterator(),
236 Spliterator.ORDERED),
237 Spliterator.ORDERED,
238 false);
239 }
240 }