1 /*
2 * Copyright (c) 2003, 2020, 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 *******************************************************************************
28 * Copyright (C) 1996-2014, International Business Machines Corporation and *
29 * others. All Rights Reserved. *
30 *******************************************************************************
31 */
32
33 package jdk.internal.icu.text;
34
35 import jdk.internal.icu.impl.CharacterIteratorWrapper;
36 import jdk.internal.icu.impl.ReplaceableUCharacterIterator;
37 import jdk.internal.icu.impl.UCharacterProperty;
38
39 import java.text.CharacterIterator;
40
41 /**
42 * Abstract class that defines an API for iteration on text objects.This is an
43 * interface for forward and backward iteration and random access into a text
44 * object. Forward iteration is done with post-increment and backward iteration
45 * is done with pre-decrement semantics, while the
46 * <code>java.text.CharacterIterator</code> interface methods provided forward
47 * iteration with "pre-increment" and backward iteration with pre-decrement
48 * semantics. This API is more efficient for forward iteration over code points.
49 * The other major difference is that this API can do both code unit and code point
50 * iteration, <code>java.text.CharacterIterator</code> can only iterate over
51 * code units and is limited to BMP (0 - 0xFFFF)
52 * @author Ram
53 * @stable ICU 2.4
54 */
55 public abstract class UCharacterIterator
56 implements Cloneable {
57
58 /**
59 * Protected default constructor for the subclasses
60 * @stable ICU 2.4
61 */
62 protected UCharacterIterator(){
63 }
64
65 /**
66 * Indicator that we have reached the ends of the UTF16 text.
67 * Moved from UForwardCharacterIterator.java
68 * @stable ICU 2.4
69 */
70 public static final int DONE = -1;
71
72 // static final methods ----------------------------------------------------
73
74 /**
75 * Returns a <code>UCharacterIterator</code> object given a
76 * source string.
77 * @param source a string
78 * @return UCharacterIterator object
79 * @exception IllegalArgumentException if the argument is null
80 * @stable ICU 2.4
81 */
82 public static final UCharacterIterator getInstance(String source){
83 return new ReplaceableUCharacterIterator(source);
84 }
85
86 /**
87 * Returns a <code>UCharacterIterator</code> object given a
88 * source StringBuffer.
89 * @param source an string buffer of UTF-16 code units
90 * @return UCharacterIterator object
91 * @exception IllegalArgumentException if the argument is null
92 * @stable ICU 2.4
93 */
94 public static final UCharacterIterator getInstance(StringBuffer source){
95 return new ReplaceableUCharacterIterator(source);
96 }
97
98 /**
99 * Returns a <code>UCharacterIterator</code> object given a
100 * CharacterIterator.
101 * @param source a valid CharacterIterator object.
102 * @return UCharacterIterator object
103 * @exception IllegalArgumentException if the argument is null
104 * @stable ICU 2.4
105 */
106 public static final UCharacterIterator getInstance(CharacterIterator source){
107 return new CharacterIteratorWrapper(source);
108 }
109
110 // public methods ----------------------------------------------------------
111
112 /**
113 * Returns the length of the text
114 * @return length of the text
115 * @stable ICU 2.4
116 */
117 public abstract int getLength();
118
119 /**
120 * Gets the current index in text.
121 * @return current index in text.
122 * @stable ICU 2.4
123 */
124 public abstract int getIndex();
125
126 /**
127 * Returns the UTF16 code unit at index, and increments to the next
128 * code unit (post-increment semantics). If index is out of
129 * range, DONE is returned, and the iterator is reset to the limit
130 * of the text.
131 * @return the next UTF16 code unit, or DONE if the index is at the limit
132 * of the text.
133 * @stable ICU 2.4
134 */
135 public abstract int next();
136
137 /**
138 * Returns the code point at index, and increments to the next code
139 * point (post-increment semantics). If index does not point to a
140 * valid surrogate pair, the behavior is the same as
141 * <code>next()</code>. Otherwise the iterator is incremented past
142 * the surrogate pair, and the code point represented by the pair
143 * is returned.
144 * @return the next codepoint in text, or DONE if the index is at
145 * the limit of the text.
146 * @stable ICU 2.4
147 */
148 public int nextCodePoint(){
149 int ch1 = next();
150 if(UTF16.isLeadSurrogate((char)ch1)){
151 int ch2 = next();
152 if(UTF16.isTrailSurrogate((char)ch2)){
153 return UCharacterProperty.getRawSupplementary((char)ch1,
154 (char)ch2);
155 }else if (ch2 != DONE) {
156 // unmatched surrogate so back out
157 previous();
158 }
159 }
160 return ch1;
161 }
162
163 /**
164 * Decrement to the position of the previous code unit in the
165 * text, and return it (pre-decrement semantics). If the
166 * resulting index is less than 0, the index is reset to 0 and
167 * DONE is returned.
168 * @return the previous code unit in the text, or DONE if the new
169 * index is before the start of the text.
170 * @stable ICU 2.4
171 */
172 public abstract int previous();
173
174
175 /**
176 * Retreat to the start of the previous code point in the text,
177 * and return it (pre-decrement semantics). If the index is not
178 * preceeded by a valid surrogate pair, the behavior is the same
179 * as <code>previous()</code>. Otherwise the iterator is
180 * decremented to the start of the surrogate pair, and the code
181 * point represented by the pair is returned.
182 * @return the previous code point in the text, or DONE if the new
183 * index is before the start of the text.
184 * @stable ICU 2.4
185 */
186 public int previousCodePoint(){
187 int ch1 = previous();
188 if(UTF16.isTrailSurrogate((char)ch1)){
189 int ch2 = previous();
190 if(UTF16.isLeadSurrogate((char)ch2)){
191 return UCharacterProperty.getRawSupplementary((char)ch2,
192 (char)ch1);
193 }else if (ch2 != DONE) {
194 //unmatched trail surrogate so back out
195 next();
196 }
197 }
198 return ch1;
199 }
200
201 /**
202 * Sets the index to the specified index in the text.
203 * @param index the index within the text.
204 * @exception IndexOutOfBoundsException is thrown if an invalid index is
205 * supplied
206 * @stable ICU 2.4
207 */
208 public abstract void setIndex(int index);
209
210 /**
211 * Sets the current index to the start.
212 * @stable ICU 2.4
213 */
214 public void setToStart() {
215 setIndex(0);
216 }
217
218 /**
219 * Fills the buffer with the underlying text storage of the iterator
220 * If the buffer capacity is not enough a exception is thrown. The capacity
221 * of the fill in buffer should at least be equal to length of text in the
222 * iterator obtained by calling <code>getLength()</code>.
223 * <b>Usage:</b>
224 *
225 * <pre>{@code
226 * UChacterIterator iter = new UCharacterIterator.getInstance(text);
227 * char[] buf = new char[iter.getLength()];
228 * iter.getText(buf);
229 *
230 * OR
231 * char[] buf= new char[1];
232 * int len = 0;
233 * for(;;){
234 * try{
235 * len = iter.getText(buf);
236 * break;
237 * }catch(IndexOutOfBoundsException e){
238 * buf = new char[iter.getLength()];
239 * }
240 * }
241 * }</pre>
242 *
243 * @param fillIn an array of chars to fill with the underlying UTF-16 code
244 * units.
245 * @param offset the position within the array to start putting the data.
246 * @return the number of code units added to fillIn, as a convenience
247 * @exception IndexOutOfBoundsException exception if there is not enough
248 * room after offset in the array, or if offset < 0.
249 * @stable ICU 2.4
250 */
251 public abstract int getText(char[] fillIn, int offset);
252
253 /**
254 * Convenience override for <code>getText(char[], int)</code> that provides
255 * an offset of 0.
256 * @param fillIn an array of chars to fill with the underlying UTF-16 code
257 * units.
258 * @return the number of code units added to fillIn, as a convenience
259 * @exception IndexOutOfBoundsException exception if there is not enough
260 * room in the array.
261 * @stable ICU 2.4
262 */
263 public final int getText(char[] fillIn) {
264 return getText(fillIn, 0);
265 }
266
267 /**
268 * Convenience method for returning the underlying text storage as a string
269 * @return the underlying text storage in the iterator as a string
270 * @stable ICU 2.4
271 */
272 public String getText() {
273 char[] text = new char[getLength()];
274 getText(text);
275 return new String(text);
276 }
277
278 /**
279 * Moves the current position by the number of code points
280 * specified, either forward or backward depending on the sign of
281 * delta (positive or negative respectively). If the current index
282 * is at a trail surrogate then the first adjustment is by code
283 * unit, and the remaining adjustments are by code points. If the
284 * resulting index would be less than zero, the index is set to
285 * zero, and if the resulting index would be greater than limit,
286 * the index is set to limit.
287 * @param delta the number of code units to move the current index.
288 * @return the new index
289 * @exception IndexOutOfBoundsException is thrown if an invalid delta is
290 * supplied
291 * @stable ICU 2.4
292 *
293 */
294 public int moveCodePointIndex(int delta){
295 if(delta>0){
296 while(delta>0 && nextCodePoint() != DONE){delta--;}
297 }else{
298 while(delta<0 && previousCodePoint() != DONE){delta++;}
299 }
300 if(delta!=0){
301 throw new IndexOutOfBoundsException();
302 }
303
304 return getIndex();
305 }
306
307 /**
308 * Creates a copy of this iterator, independent from other iterators.
309 * If it is not possible to clone the iterator, returns null.
310 * @return copy of this iterator
311 * @stable ICU 2.4
312 */
313 public Object clone() throws CloneNotSupportedException{
314 return super.clone();
315 }
316
317 }