1 /*
2 * Copyright (c) 2000, 2018, 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.Objects;
30 import java.util.PrimitiveIterator;
31 import java.util.Spliterator;
32 import java.util.Spliterators;
33 import java.util.function.IntConsumer;
34 import java.util.stream.IntStream;
35 import java.util.stream.StreamSupport;
36
37 /**
38 * A {@code CharSequence} is a readable sequence of {@code char} values. This
39 * interface provides uniform, read-only access to many different kinds of
40 * {@code char} sequences.
41 * A {@code char} value represents a character in the <i>Basic
42 * Multilingual Plane (BMP)</i> or a surrogate. Refer to <a
43 * href="Character.html#unicode">Unicode Character Representation</a> for details.
44 *
45 * <p> This interface does not refine the general contracts of the {@link
46 * java.lang.Object#equals(java.lang.Object) equals} and {@link
47 * java.lang.Object#hashCode() hashCode} methods. The result of testing two objects
48 * that implement {@code CharSequence} for equality is therefore, in general, undefined.
49 * Each object may be implemented by a different class, and there
50 * is no guarantee that each class will be capable of testing its instances
51 * for equality with those of the other. It is therefore inappropriate to use
52 * arbitrary {@code CharSequence} instances as elements in a set or as keys in
53 * a map. </p>
54 *
55 * @author Mike McCloskey
56 * @since 1.4
57 * @spec JSR-51
58 */
59
60 public interface CharSequence {
61
62 /**
63 * Returns the length of this character sequence. The length is the number
64 * of 16-bit {@code char}s in the sequence.
65 *
66 * @return the number of {@code char}s in this sequence
67 */
68 int length();
69
70 /**
71 * Returns the {@code char} value at the specified index. An index ranges from zero
72 * to {@code length() - 1}. The first {@code char} value of the sequence is at
73 * index zero, the next at index one, and so on, as for array
74 * indexing.
75 *
76 * <p>If the {@code char} value specified by the index is a
77 * <a href="{@docRoot}/java/lang/Character.html#unicode">surrogate</a>, the surrogate
78 * value is returned.
79 *
80 * @param index the index of the {@code char} value to be returned
81 *
82 * @return the specified {@code char} value
83 *
84 * @throws IndexOutOfBoundsException
85 * if the {@code index} argument is negative or not less than
86 * {@code length()}
87 */
88 char charAt(int index);
89
90 /**
91 * Returns a {@code CharSequence} that is a subsequence of this sequence.
92 * The subsequence starts with the {@code char} value at the specified index and
93 * ends with the {@code char} value at index {@code end - 1}. The length
94 * (in {@code char}s) of the
95 * returned sequence is {@code end - start}, so if {@code start == end}
96 * then an empty sequence is returned.
97 *
98 * @param start the start index, inclusive
99 * @param end the end index, exclusive
100 *
101 * @return the specified subsequence
102 *
103 * @throws IndexOutOfBoundsException
104 * if {@code start} or {@code end} are negative,
105 * if {@code end} is greater than {@code length()},
106 * or if {@code start} is greater than {@code end}
107 */
108 CharSequence subSequence(int start, int end);
109
110 /**
111 * Returns a string containing the characters in this sequence in the same
112 * order as this sequence. The length of the string will be the length of
113 * this sequence.
114 *
115 * @return a string consisting of exactly this sequence of characters
116 */
117 public String toString();
118
119 /**
120 * Returns a stream of {@code int} zero-extending the {@code char} values
121 * from this sequence. Any char which maps to a <a
122 * href="{@docRoot}/java/lang/Character.html#unicode">surrogate code
123 * point</a> is passed through uninterpreted.
124 *
125 * <p>The stream binds to this sequence when the terminal stream operation
126 * commences (specifically, for mutable sequences the spliterator for the
127 * stream is <a href="../util/Spliterator.html#binding"><em>late-binding</em></a>).
128 * If the sequence is modified during that operation then the result is
129 * undefined.
130 *
131 * @return an IntStream of char values from this sequence
132 * @since 1.8
133 */
134 public default IntStream chars() {
135 class CharIterator implements PrimitiveIterator.OfInt {
136 int cur = 0;
137
138 public boolean hasNext() {
139 return cur < length();
140 }
141
142 public int nextInt() {
143 if (hasNext()) {
144 return charAt(cur++);
145 } else {
146 throw new NoSuchElementException();
147 }
148 }
149
150 @Override
151 public void forEachRemaining(IntConsumer block) {
152 for (; cur < length(); cur++) {
153 block.accept(charAt(cur));
154 }
155 }
156 }
157
158 return StreamSupport.intStream(() ->
159 Spliterators.spliterator(
160 new CharIterator(),
161 length(),
162 Spliterator.ORDERED),
163 Spliterator.SUBSIZED | Spliterator.SIZED | Spliterator.ORDERED,
164 false);
165 }
166
167 /**
168 * Returns a stream of code point values from this sequence. Any surrogate
169 * pairs encountered in the sequence are combined as if by {@linkplain
170 * Character#toCodePoint Character.toCodePoint} and the result is passed
171 * to the stream. Any other code units, including ordinary BMP characters,
172 * unpaired surrogates, and undefined code units, are zero-extended to
173 * {@code int} values which are then passed to the stream.
174 *
175 * <p>The stream binds to this sequence when the terminal stream operation
176 * commences (specifically, for mutable sequences the spliterator for the
177 * stream is <a href="../util/Spliterator.html#binding"><em>late-binding</em></a>).
178 * If the sequence is modified during that operation then the result is
179 * undefined.
180 *
181 * @return an IntStream of Unicode code points from this sequence
182 * @since 1.8
183 */
184 public default IntStream codePoints() {
185 class CodePointIterator implements PrimitiveIterator.OfInt {
186 int cur = 0;
187
188 @Override
189 public void forEachRemaining(IntConsumer block) {
190 final int length = length();
191 int i = cur;
192 try {
193 while (i < length) {
194 char c1 = charAt(i++);
195 if (!Character.isHighSurrogate(c1) || i >= length) {
196 block.accept(c1);
197 } else {
198 char c2 = charAt(i);
199 if (Character.isLowSurrogate(c2)) {
200 i++;
201 block.accept(Character.toCodePoint(c1, c2));
202 } else {
203 block.accept(c1);
204 }
205 }
206 }
207 } finally {
208 cur = i;
209 }
210 }
211
212 public boolean hasNext() {
213 return cur < length();
214 }
215
216 public int nextInt() {
217 final int length = length();
218
219 if (cur >= length) {
220 throw new NoSuchElementException();
221 }
222 char c1 = charAt(cur++);
223 if (Character.isHighSurrogate(c1) && cur < length) {
224 char c2 = charAt(cur);
225 if (Character.isLowSurrogate(c2)) {
226 cur++;
227 return Character.toCodePoint(c1, c2);
228 }
229 }
230 return c1;
231 }
232 }
233
234 return StreamSupport.intStream(() ->
235 Spliterators.spliteratorUnknownSize(
236 new CodePointIterator(),
237 Spliterator.ORDERED),
238 Spliterator.ORDERED,
239 false);
240 }
241
242 /**
243 * Compares two {@code CharSequence} instances lexicographically. Returns a
244 * negative value, zero, or a positive value if the first sequence is lexicographically
245 * less than, equal to, or greater than the second, respectively.
246 *
247 * <p>
248 * The lexicographical ordering of {@code CharSequence} is defined as follows.
249 * Consider a {@code CharSequence} <i>cs</i> of length <i>len</i> to be a
250 * sequence of char values, <i>cs[0]</i> to <i>cs[len-1]</i>. Suppose <i>k</i>
251 * is the lowest index at which the corresponding char values from each sequence
252 * differ. The lexicographic ordering of the sequences is determined by a numeric
253 * comparison of the char values <i>cs1[k]</i> with <i>cs2[k]</i>. If there is
254 * no such index <i>k</i>, the shorter sequence is considered lexicographically
255 * less than the other. If the sequences have the same length, the sequences are
256 * considered lexicographically equal.
257 *
258 *
259 * @param cs1 the first {@code CharSequence}
260 * @param cs2 the second {@code CharSequence}
261 *
262 * @return the value {@code 0} if the two {@code CharSequence} are equal;
263 * a negative integer if the first {@code CharSequence}
264 * is lexicographically less than the second; or a
265 * positive integer if the first {@code CharSequence} is
266 * lexicographically greater than the second.
267 *
268 * @since 11
269 */
270 @SuppressWarnings("unchecked")
271 public static int compare(CharSequence cs1, CharSequence cs2) {
272 if (Objects.requireNonNull(cs1) == Objects.requireNonNull(cs2)) {
273 return 0;
274 }
275
276 if (cs1.getClass() == cs2.getClass() && cs1 instanceof Comparable) {
277 return ((Comparable<Object>) cs1).compareTo(cs2);
278 }
279
280 for (int i = 0, len = Math.min(cs1.length(), cs2.length()); i < len; i++) {
281 char a = cs1.charAt(i);
282 char b = cs2.charAt(i);
283 if (a != b) {
284 return a - b;
285 }
286 }
287
288 return cs1.length() - cs2.length();
289 }
290
291 }