1 /*
2 * Copyright (c) 2015, 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.Arrays;
29 import java.util.Locale;
30 import java.util.Objects;
31 import java.util.Spliterator;
32 import java.util.function.IntConsumer;
33 import java.util.stream.IntStream;
34 import jdk.internal.HotSpotIntrinsicCandidate;
35
36 import static java.lang.String.LATIN1;
37 import static java.lang.String.UTF16;
38 import static java.lang.String.checkOffset;
39 import static java.lang.String.checkBoundsOffCount;
40
41 final class StringLatin1 {
42
43 public static char charAt(byte[] value, int index) {
44 if (index < 0 || index >= value.length) {
45 throw new StringIndexOutOfBoundsException(index);
46 }
47 return (char)(value[index] & 0xff);
48 }
49
50 public static boolean canEncode(int cp) {
51 return cp >>> 8 == 0;
52 }
53
54 public static int length(byte[] value) {
55 return value.length;
56 }
57
58 public static int codePointAt(byte[] value, int index, int end) {
59 return value[index] & 0xff;
60 }
61
62 public static int codePointBefore(byte[] value, int index) {
63 return value[index - 1] & 0xff;
64 }
65
66 public static int codePointCount(byte[] value, int beginIndex, int endIndex) {
67 return endIndex - beginIndex;
68 }
69
70 public static char[] toChars(byte[] value) {
71 char[] dst = new char[value.length];
72 inflate(value, 0, dst, 0, value.length);
73 return dst;
74 }
75
76 public static byte[] inflate(byte[] value, int off, int len) {
77 byte[] ret = StringUTF16.newBytesFor(len);
78 inflate(value, off, ret, 0, len);
79 return ret;
80 }
81
82 public static void getChars(byte[] value, int srcBegin, int srcEnd, char dst[], int dstBegin) {
83 inflate(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
84 }
85
86 public static void getBytes(byte[] value, int srcBegin, int srcEnd, byte dst[], int dstBegin) {
87 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
88 }
89
90 @HotSpotIntrinsicCandidate
91 public static boolean equals(byte[] value, byte[] other) {
92 if (value.length == other.length) {
93 for (int i = 0; i < value.length; i++) {
94 if (value[i] != other[i]) {
95 return false;
96 }
97 }
98 return true;
99 }
100 return false;
101 }
102
103 @HotSpotIntrinsicCandidate
104 public static int compareTo(byte[] value, byte[] other) {
105 int len1 = value.length;
106 int len2 = other.length;
107 int lim = Math.min(len1, len2);
108 for (int k = 0; k < lim; k++) {
109 if (value[k] != other[k]) {
110 return getChar(value, k) - getChar(other, k);
111 }
112 }
113 return len1 - len2;
114 }
115
116 @HotSpotIntrinsicCandidate
117 public static int compareToUTF16(byte[] value, byte[] other) {
118 int len1 = length(value);
119 int len2 = StringUTF16.length(other);
120 int lim = Math.min(len1, len2);
121 for (int k = 0; k < lim; k++) {
122 char c1 = getChar(value, k);
123 char c2 = StringUTF16.getChar(other, k);
124 if (c1 != c2) {
125 return c1 - c2;
126 }
127 }
128 return len1 - len2;
129 }
130
131 public static int compareToCI(byte[] value, byte[] other) {
132 int len1 = value.length;
133 int len2 = other.length;
134 int lim = Math.min(len1, len2);
135 for (int k = 0; k < lim; k++) {
136 if (value[k] != other[k]) {
137 char c1 = Character.toUpperCase(getChar(value, k));
138 char c2 = Character.toUpperCase(getChar(other, k));
139 if (c1 != c2) {
140 c1 = Character.toLowerCase(c1);
141 c2 = Character.toLowerCase(c2);
142 if (c1 != c2) {
143 return c1 - c2;
144 }
145 }
146 }
147 }
148 return len1 - len2;
149 }
150
151 public static int compareToCI_UTF16(byte[] value, byte[] other) {
152 int len1 = length(value);
153 int len2 = StringUTF16.length(other);
154 int lim = Math.min(len1, len2);
155 for (int k = 0; k < lim; k++) {
156 char c1 = getChar(value, k);
157 char c2 = StringUTF16.getChar(other, k);
158 if (c1 != c2) {
159 c1 = Character.toUpperCase(c1);
160 c2 = Character.toUpperCase(c2);
161 if (c1 != c2) {
162 c1 = Character.toLowerCase(c1);
163 c2 = Character.toLowerCase(c2);
164 if (c1 != c2) {
165 return c1 - c2;
166 }
167 }
168 }
169 }
170 return len1 - len2;
171 }
172
173 public static int hashCode(byte[] value) {
174 int h = 0;
175 for (byte v : value) {
176 h = 31 * h + (v & 0xff);
177 }
178 return h;
179 }
180
181 public static int indexOf(byte[] value, int ch, int fromIndex) {
182 if (!canEncode(ch)) {
183 return -1;
184 }
185 int max = value.length;
186 if (fromIndex < 0) {
187 fromIndex = 0;
188 } else if (fromIndex >= max) {
189 // Note: fromIndex might be near -1>>>1.
190 return -1;
191 }
192 byte c = (byte)ch;
193 for (int i = fromIndex; i < max; i++) {
194 if (value[i] == c) {
195 return i;
196 }
197 }
198 return -1;
199 }
200
201 @HotSpotIntrinsicCandidate
202 public static int indexOf(byte[] value, byte[] str) {
203 if (str.length == 0) {
204 return 0;
205 }
206 if (value.length == 0) {
207 return -1;
208 }
209 return indexOf(value, value.length, str, str.length, 0);
210 }
211
212 @HotSpotIntrinsicCandidate
213 public static int indexOf(byte[] value, int valueCount, byte[] str, int strCount, int fromIndex) {
214 byte first = str[0];
215 int max = (valueCount - strCount);
216 for (int i = fromIndex; i <= max; i++) {
217 // Look for first character.
218 if (value[i] != first) {
219 while (++i <= max && value[i] != first);
220 }
221 // Found first character, now look at the rest of value
222 if (i <= max) {
223 int j = i + 1;
224 int end = j + strCount - 1;
225 for (int k = 1; j < end && value[j] == str[k]; j++, k++);
226 if (j == end) {
227 // Found whole string.
228 return i;
229 }
230 }
231 }
232 return -1;
233 }
234
235 public static int lastIndexOf(byte[] src, int srcCount,
236 byte[] tgt, int tgtCount, int fromIndex) {
237 int min = tgtCount - 1;
238 int i = min + fromIndex;
239 int strLastIndex = tgtCount - 1;
240 char strLastChar = (char)(tgt[strLastIndex] & 0xff);
241
242 startSearchForLastChar:
243 while (true) {
244 while (i >= min && (src[i] & 0xff) != strLastChar) {
245 i--;
246 }
247 if (i < min) {
248 return -1;
249 }
250 int j = i - 1;
251 int start = j - strLastIndex;
252 int k = strLastIndex - 1;
253 while (j > start) {
254 if ((src[j--] & 0xff) != (tgt[k--] & 0xff)) {
255 i--;
256 continue startSearchForLastChar;
257 }
258 }
259 return start + 1;
260 }
261 }
262
263 public static int lastIndexOf(final byte[] value, int ch, int fromIndex) {
264 if (!canEncode(ch)) {
265 return -1;
266 }
267 int off = Math.min(fromIndex, value.length - 1);
268 for (; off >= 0; off--) {
269 if (value[off] == (byte)ch) {
270 return off;
271 }
272 }
273 return -1;
274 }
275
276 public static String replace(byte[] value, char oldChar, char newChar) {
277 if (canEncode(oldChar)) {
278 int len = value.length;
279 int i = -1;
280 while (++i < len) {
281 if (value[i] == (byte)oldChar) {
282 break;
283 }
284 }
285 if (i < len) {
286 if (canEncode(newChar)) {
287 byte buf[] = new byte[len];
288 for (int j = 0; j < i; j++) { // TBD arraycopy?
289 buf[j] = value[j];
290 }
291 while (i < len) {
292 byte c = value[i];
293 buf[i] = (c == (byte)oldChar) ? (byte)newChar : c;
294 i++;
295 }
296 return new String(buf, LATIN1);
297 } else {
298 byte[] buf = StringUTF16.newBytesFor(len);
299 // inflate from latin1 to UTF16
300 inflate(value, 0, buf, 0, i);
301 while (i < len) {
302 char c = (char)(value[i] & 0xff);
303 StringUTF16.putChar(buf, i, (c == oldChar) ? newChar : c);
304 i++;
305 }
306 return new String(buf, UTF16);
307 }
308 }
309 }
310 return null; // for string to return this;
311 }
312
313 // case insensitive
314 public static boolean regionMatchesCI(byte[] value, int toffset,
315 byte[] other, int ooffset, int len) {
316 int last = toffset + len;
317 while (toffset < last) {
318 char c1 = (char)(value[toffset++] & 0xff);
319 char c2 = (char)(other[ooffset++] & 0xff);
320 if (c1 == c2) {
321 continue;
322 }
323 char u1 = Character.toUpperCase(c1);
324 char u2 = Character.toUpperCase(c2);
325 if (u1 == u2) {
326 continue;
327 }
328 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
329 continue;
330 }
331 return false;
332 }
333 return true;
334 }
335
336 public static boolean regionMatchesCI_UTF16(byte[] value, int toffset,
337 byte[] other, int ooffset, int len) {
338 int last = toffset + len;
339 while (toffset < last) {
340 char c1 = (char)(value[toffset++] & 0xff);
341 char c2 = StringUTF16.getChar(other, ooffset++);
342 if (c1 == c2) {
343 continue;
344 }
345 char u1 = Character.toUpperCase(c1);
346 char u2 = Character.toUpperCase(c2);
347 if (u1 == u2) {
348 continue;
349 }
350 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
351 continue;
352 }
353 return false;
354 }
355 return true;
356 }
357
358 public static String toLowerCase(String str, byte[] value, Locale locale) {
359 if (locale == null) {
360 throw new NullPointerException();
361 }
362 int first;
363 final int len = value.length;
364 // Now check if there are any characters that need to be changed, or are surrogate
365 for (first = 0 ; first < len; first++) {
366 int cp = value[first] & 0xff;
367 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
368 break;
369 }
370 }
371 if (first == len)
372 return str;
373 String lang = locale.getLanguage();
374 if (lang == "tr" || lang == "az" || lang == "lt") {
375 return toLowerCaseEx(str, value, first, locale, true);
376 }
377 byte[] result = new byte[len];
378 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
379 // lowerCase characters.
380 for (int i = first; i < len; i++) {
381 int cp = value[i] & 0xff;
382 cp = Character.toLowerCase(cp);
383 if (!canEncode(cp)) { // not a latin1 character
384 return toLowerCaseEx(str, value, first, locale, false);
385 }
386 result[i] = (byte)cp;
387 }
388 return new String(result, LATIN1);
389 }
390
391 private static String toLowerCaseEx(String str, byte[] value,
392 int first, Locale locale, boolean localeDependent)
393 {
394 byte[] result = StringUTF16.newBytesFor(value.length);
395 int resultOffset = 0;
396 for (int i = 0; i < first; i++) {
397 StringUTF16.putChar(result, resultOffset++, value[i] & 0xff);
398 }
399 for (int i = first; i < value.length; i++) {
400 int srcChar = value[i] & 0xff;
401 int lowerChar;
402 char[] lowerCharArray;
403 if (localeDependent) {
404 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(str, i, locale);
405 } else {
406 lowerChar = Character.toLowerCase(srcChar);
407 }
408 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
409 StringUTF16.putChar(result, resultOffset++, lowerChar);
410 } else {
411 if (lowerChar == Character.ERROR) {
412 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(str, i, locale);
413 } else {
414 lowerCharArray = Character.toChars(lowerChar);
415 }
416 /* Grow result if needed */
417 int mapLen = lowerCharArray.length;
418 if (mapLen > 1) {
419 byte[] result2 = StringUTF16.newBytesFor((result.length >> 1) + mapLen - 1);
420 System.arraycopy(result, 0, result2, 0, resultOffset << 1);
421 result = result2;
422 }
423 for (int x = 0; x < mapLen; ++x) {
424 StringUTF16.putChar(result, resultOffset++, lowerCharArray[x]);
425 }
426 }
427 }
428 return StringUTF16.newString(result, 0, resultOffset);
429 }
430
431 public static String toUpperCase(String str, byte[] value, Locale locale) {
432 if (locale == null) {
433 throw new NullPointerException();
434 }
435 int first;
436 final int len = value.length;
437
438 // Now check if there are any characters that need to be changed, or are surrogate
439 for (first = 0 ; first < len; first++ ) {
440 int cp = value[first] & 0xff;
441 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
442 break;
443 }
444 }
445 if (first == len) {
446 return str;
447 }
448 String lang = locale.getLanguage();
449 if (lang == "tr" || lang == "az" || lang == "lt") {
450 return toUpperCaseEx(str, value, first, locale, true);
451 }
452 byte[] result = new byte[len];
453 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
454 // upperCase characters.
455 for (int i = first; i < len; i++) {
456 int cp = value[i] & 0xff;
457 cp = Character.toUpperCaseEx(cp);
458 if (!canEncode(cp)) { // not a latin1 character
459 return toUpperCaseEx(str, value, first, locale, false);
460 }
461 result[i] = (byte)cp;
462 }
463 return new String(result, LATIN1);
464 }
465
466 private static String toUpperCaseEx(String str, byte[] value,
467 int first, Locale locale, boolean localeDependent)
468 {
469 byte[] result = StringUTF16.newBytesFor(value.length);
470 int resultOffset = 0;
471 for (int i = 0; i < first; i++) {
472 StringUTF16.putChar(result, resultOffset++, value[i] & 0xff);
473 }
474 for (int i = first; i < value.length; i++) {
475 int srcChar = value[i] & 0xff;
476 int upperChar;
477 char[] upperCharArray;
478 if (localeDependent) {
479 upperChar = ConditionalSpecialCasing.toUpperCaseEx(str, i, locale);
480 } else {
481 upperChar = Character.toUpperCaseEx(srcChar);
482 }
483 if (Character.isBmpCodePoint(upperChar)) {
484 StringUTF16.putChar(result, resultOffset++, upperChar);
485 } else {
486 if (upperChar == Character.ERROR) {
487 if (localeDependent) {
488 upperCharArray =
489 ConditionalSpecialCasing.toUpperCaseCharArray(str, i, locale);
490 } else {
491 upperCharArray = Character.toUpperCaseCharArray(srcChar);
492 }
493 } else {
494 upperCharArray = Character.toChars(upperChar);
495 }
496 /* Grow result if needed */
497 int mapLen = upperCharArray.length;
498 if (mapLen > 1) {
499 byte[] result2 = StringUTF16.newBytesFor((result.length >> 1) + mapLen - 1);
500 System.arraycopy(result, 0, result2, 0, resultOffset << 1);
501 result = result2;
502 }
503 for (int x = 0; x < mapLen; ++x) {
504 StringUTF16.putChar(result, resultOffset++, upperCharArray[x]);
505 }
506 }
507 }
508 return StringUTF16.newString(result, 0, resultOffset);
509 }
510
511 public static String trim(byte[] value) {
512 int len = value.length;
513 int st = 0;
514 while ((st < len) && ((value[st] & 0xff) <= ' ')) {
515 st++;
516 }
517 while ((st < len) && ((value[len - 1] & 0xff) <= ' ')) {
518 len--;
519 }
520 return ((st > 0) || (len < value.length)) ?
521 newString(value, st, len - st) : null;
522 }
523
524 public static void putChar(byte[] val, int index, int c) {
525 //assert (canEncode(c));
526 val[index] = (byte)(c);
527 }
528
529 public static char getChar(byte[] val, int index) {
530 return (char)(val[index] & 0xff);
531 }
532
533 public static byte[] toBytes(int[] val, int off, int len) {
534 byte[] ret = new byte[len];
535 for (int i = 0; i < len; i++) {
536 int cp = val[off++];
537 if (!canEncode(cp)) {
538 return null;
539 }
540 ret[i] = (byte)cp;
541 }
542 return ret;
543 }
544
545 public static byte[] toBytes(char c) {
546 return new byte[] { (byte)c };
547 }
548
549 public static String newString(byte[] val, int index, int len) {
550 return new String(Arrays.copyOfRange(val, index, index + len),
551 LATIN1);
552 }
553
554 public static void fillNull(byte[] val, int index, int end) {
555 Arrays.fill(val, index, end, (byte)0);
556 }
557
558 // inflatedCopy byte[] -> char[]
559 @HotSpotIntrinsicCandidate
560 private static void inflate(byte[] src, int srcOff, char[] dst, int dstOff, int len) {
561 for (int i = 0; i < len; i++) {
562 dst[dstOff++] = (char)(src[srcOff++] & 0xff);
563 }
564 }
565
566 // inflatedCopy byte[] -> byte[]
567 @HotSpotIntrinsicCandidate
568 public static void inflate(byte[] src, int srcOff, byte[] dst, int dstOff, int len) {
569 // We need a range check here because 'putChar' has no checks
570 checkBoundsOffCount(dstOff, len, dst.length);
571 for (int i = 0; i < len; i++) {
572 StringUTF16.putChar(dst, dstOff++, src[srcOff++] & 0xff);
573 }
574 }
575
576 static class CharsSpliterator implements Spliterator.OfInt {
577 private final byte[] array;
578 private int index; // current index, modified on advance/split
579 private final int fence; // one past last index
580 private final int cs;
581
582 CharsSpliterator(byte[] array, int acs) {
583 this(array, 0, array.length, acs);
584 }
585
586 CharsSpliterator(byte[] array, int origin, int fence, int acs) {
587 this.array = array;
588 this.index = origin;
589 this.fence = fence;
590 this.cs = acs | Spliterator.ORDERED | Spliterator.SIZED
591 | Spliterator.SUBSIZED;
592 }
593
594 @Override
595 public OfInt trySplit() {
596 int lo = index, mid = (lo + fence) >>> 1;
597 return (lo >= mid)
598 ? null
599 : new CharsSpliterator(array, lo, index = mid, cs);
600 }
601
602 @Override
603 public void forEachRemaining(IntConsumer action) {
604 byte[] a; int i, hi; // hoist accesses and checks from loop
605 if (action == null)
606 throw new NullPointerException();
607 if ((a = array).length >= (hi = fence) &&
608 (i = index) >= 0 && i < (index = hi)) {
609 do { action.accept(a[i] & 0xff); } while (++i < hi);
610 }
611 }
612
613 @Override
614 public boolean tryAdvance(IntConsumer action) {
615 if (action == null)
616 throw new NullPointerException();
617 if (index >= 0 && index < fence) {
618 action.accept(array[index++] & 0xff);
619 return true;
620 }
621 return false;
622 }
623
624 @Override
625 public long estimateSize() { return (long)(fence - index); }
626
627 @Override
628 public int characteristics() {
629 return cs;
630 }
631 }
632 }