我是靠谱客的博主 长情外套,这篇文章主要介绍JAVA 的 UTF-8 相关有一个 sun.nio.cs.UTF_8 类,现在分享给大家,希望可以做个参考。

记录一些Java 与 utf-8 相关的知识

有一个 sun.nio.cs.UTF_8 类

源码

复制代码
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
/* * Copyright (c) 2000, 2021, Oracle and/or its affiliates. All rights reserved. * ORACLE PROPRIETARY/CONFIDENTIAL. Use is subject to license terms. * * */ package sun.nio.cs; import jdk.internal.access.JavaLangAccess; import jdk.internal.access.SharedSecrets; import java.nio.Buffer; import java.nio.ByteBuffer; import java.nio.CharBuffer; import java.nio.charset.Charset; import java.nio.charset.CharsetDecoder; import java.nio.charset.CharsetEncoder; import java.nio.charset.CoderResult; import java.nio.charset.CodingErrorAction; /* Legal UTF-8 Byte Sequences * * # Code Points Bits Bit/Byte pattern * 1 7 0xxxxxxx * U+0000..U+007F 00..7F * * 2 11 110xxxxx 10xxxxxx * U+0080..U+07FF C2..DF 80..BF * * 3 16 1110xxxx 10xxxxxx 10xxxxxx * U+0800..U+0FFF E0 A0..BF 80..BF * U+1000..U+FFFF E1..EF 80..BF 80..BF * * 4 21 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx * U+10000..U+3FFFF F0 90..BF 80..BF 80..BF * U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF * U+100000..U10FFFF F4 80..8F 80..BF 80..BF * */ public final class UTF_8 extends Unicode { public static final UTF_8 INSTANCE = new UTF_8(); public UTF_8() { super("UTF-8", StandardCharsets.aliases_UTF_8()); } public String historicalName() { return "UTF8"; } public CharsetDecoder newDecoder() { return new Decoder(this); } public CharsetEncoder newEncoder() { return new Encoder(this); } static final void updatePositions(Buffer src, int sp, Buffer dst, int dp) { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } private static final JavaLangAccess JLA = SharedSecrets.getJavaLangAccess(); private static class Decoder extends CharsetDecoder { private Decoder(Charset cs) { super(cs, 1.0f, 1.0f); } private static boolean isNotContinuation(int b) { return (b & 0xc0) != 0x80; } // [E0] [A0..BF] [80..BF] // [E1..EF] [80..BF] [80..BF] private static boolean isMalformed3(int b1, int b2, int b3) { return (b1 == (byte)0xe0 && (b2 & 0xe0) == 0x80) || (b2 & 0xc0) != 0x80 || (b3 & 0xc0) != 0x80; } // only used when there is only one byte left in src buffer private static boolean isMalformed3_2(int b1, int b2) { return (b1 == (byte)0xe0 && (b2 & 0xe0) == 0x80) || (b2 & 0xc0) != 0x80; } // [F0] [90..BF] [80..BF] [80..BF] // [F1..F3] [80..BF] [80..BF] [80..BF] // [F4] [80..8F] [80..BF] [80..BF] // only check 80-be range here, the [0xf0,0x80...] and [0xf4,0x90-...] // will be checked by Character.isSupplementaryCodePoint(uc) private static boolean isMalformed4(int b2, int b3, int b4) { return (b2 & 0xc0) != 0x80 || (b3 & 0xc0) != 0x80 || (b4 & 0xc0) != 0x80; } // only used when there is less than 4 bytes left in src buffer. // both b1 and b2 should be "& 0xff" before passed in. private static boolean isMalformed4_2(int b1, int b2) { return (b1 == 0xf0 && (b2 < 0x90 || b2 > 0xbf)) || (b1 == 0xf4 && (b2 & 0xf0) != 0x80) || (b2 & 0xc0) != 0x80; } // tests if b1 and b2 are malformed as the first 2 bytes of a // legal`4-byte utf-8 byte sequence. // only used when there is less than 4 bytes left in src buffer, // after isMalformed4_2 has been invoked. private static boolean isMalformed4_3(int b3) { return (b3 & 0xc0) != 0x80; } private static CoderResult malformedN(ByteBuffer src, int nb) { switch (nb) { case 1: case 2: // always 1 return CoderResult.malformedForLength(1); case 3: int b1 = src.get(); int b2 = src.get(); // no need to lookup b3 return CoderResult.malformedForLength( ((b1 == (byte)0xe0 && (b2 & 0xe0) == 0x80) || isNotContinuation(b2)) ? 1 : 2); case 4: // we don't care the speed here b1 = src.get() & 0xff; b2 = src.get() & 0xff; if (b1 > 0xf4 || (b1 == 0xf0 && (b2 < 0x90 || b2 > 0xbf)) || (b1 == 0xf4 && (b2 & 0xf0) != 0x80) || isNotContinuation(b2)) return CoderResult.malformedForLength(1); if (isNotContinuation(src.get())) return CoderResult.malformedForLength(2); return CoderResult.malformedForLength(3); default: assert false; return null; } } private static CoderResult malformed(ByteBuffer src, int sp, CharBuffer dst, int dp, int nb) { src.position(sp - src.arrayOffset()); CoderResult cr = malformedN(src, nb); updatePositions(src, sp, dst, dp); return cr; } private static CoderResult malformed(ByteBuffer src, int mark, int nb) { src.position(mark); CoderResult cr = malformedN(src, nb); src.position(mark); return cr; } private static CoderResult malformedForLength(ByteBuffer src, int sp, CharBuffer dst, int dp, int malformedNB) { updatePositions(src, sp, dst, dp); return CoderResult.malformedForLength(malformedNB); } private static CoderResult malformedForLength(ByteBuffer src, int mark, int malformedNB) { src.position(mark); return CoderResult.malformedForLength(malformedNB); } private static CoderResult xflow(Buffer src, int sp, int sl, Buffer dst, int dp, int nb) { updatePositions(src, sp, dst, dp); return (nb == 0 || sl - sp < nb) ? CoderResult.UNDERFLOW : CoderResult.OVERFLOW; } private static CoderResult xflow(Buffer src, int mark, int nb) { src.position(mark); return (nb == 0 || src.remaining() < nb) ? CoderResult.UNDERFLOW : CoderResult.OVERFLOW; } private CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { // This method is optimized for ASCII input. byte[] sa = src.array(); int soff = src.arrayOffset(); int sp = soff + src.position(); int sl = soff + src.limit(); char[] da = dst.array(); int doff = dst.arrayOffset(); int dp = doff + dst.position(); int dl = doff + dst.limit(); int n = JLA.decodeASCII(sa, sp, da, dp, Math.min(sl - sp, dl - dp)); sp += n; dp += n; while (sp < sl) { int b1 = sa[sp]; if (b1 >= 0) { // 1 byte, 7 bits: 0xxxxxxx if (dp >= dl) return xflow(src, sp, sl, dst, dp, 1); da[dp++] = (char) b1; sp++; } else if ((b1 >> 5) == -2 && (b1 & 0x1e) != 0) { // 2 bytes, 11 bits: 110xxxxx 10xxxxxx // [C2..DF] [80..BF] if (sl - sp < 2 || dp >= dl) return xflow(src, sp, sl, dst, dp, 2); int b2 = sa[sp + 1]; // Now we check the first byte of 2-byte sequence as // if ((b1 >> 5) == -2 && (b1 & 0x1e) != 0) // no longer need to check b1 against c1 & c0 for // malformed as we did in previous version // (b1 & 0x1e) == 0x0 || (b2 & 0xc0) != 0x80; // only need to check the second byte b2. if (isNotContinuation(b2)) return malformedForLength(src, sp, dst, dp, 1); da[dp++] = (char) (((b1 << 6) ^ b2) ^ (((byte) 0xC0 << 6) ^ ((byte) 0x80 << 0))); sp += 2; } else if ((b1 >> 4) == -2) { // 3 bytes, 16 bits: 1110xxxx 10xxxxxx 10xxxxxx int srcRemaining = sl - sp; if (srcRemaining < 3 || dp >= dl) { if (srcRemaining > 1 && isMalformed3_2(b1, sa[sp + 1])) return malformedForLength(src, sp, dst, dp, 1); return xflow(src, sp, sl, dst, dp, 3); } int b2 = sa[sp + 1]; int b3 = sa[sp + 2]; if (isMalformed3(b1, b2, b3)) return malformed(src, sp, dst, dp, 3); char c = (char) ((b1 << 12) ^ (b2 << 6) ^ (b3 ^ (((byte) 0xE0 << 12) ^ ((byte) 0x80 << 6) ^ ((byte) 0x80 << 0)))); if (Character.isSurrogate(c)) return malformedForLength(src, sp, dst, dp, 3); da[dp++] = c; sp += 3; } else if ((b1 >> 3) == -2) { // 4 bytes, 21 bits: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx int srcRemaining = sl - sp; if (srcRemaining < 4 || dl - dp < 2) { b1 &= 0xff; if (b1 > 0xf4 || srcRemaining > 1 && isMalformed4_2(b1, sa[sp + 1] & 0xff)) return malformedForLength(src, sp, dst, dp, 1); if (srcRemaining > 2 && isMalformed4_3(sa[sp + 2])) return malformedForLength(src, sp, dst, dp, 2); return xflow(src, sp, sl, dst, dp, 4); } int b2 = sa[sp + 1]; int b3 = sa[sp + 2]; int b4 = sa[sp + 3]; int uc = ((b1 << 18) ^ (b2 << 12) ^ (b3 << 6) ^ (b4 ^ (((byte) 0xF0 << 18) ^ ((byte) 0x80 << 12) ^ ((byte) 0x80 << 6) ^ ((byte) 0x80 << 0)))); if (isMalformed4(b2, b3, b4) || // shortest form check !Character.isSupplementaryCodePoint(uc)) { return malformed(src, sp, dst, dp, 4); } da[dp++] = Character.highSurrogate(uc); da[dp++] = Character.lowSurrogate(uc); sp += 4; } else return malformed(src, sp, dst, dp, 1); } return xflow(src, sp, sl, dst, dp, 0); } private CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { int mark = src.position(); int limit = src.limit(); while (mark < limit) { int b1 = src.get(); if (b1 >= 0) { // 1 byte, 7 bits: 0xxxxxxx if (dst.remaining() < 1) return xflow(src, mark, 1); // overflow dst.put((char) b1); mark++; } else if ((b1 >> 5) == -2 && (b1 & 0x1e) != 0) { // 2 bytes, 11 bits: 110xxxxx 10xxxxxx if (limit - mark < 2|| dst.remaining() < 1) return xflow(src, mark, 2); int b2 = src.get(); if (isNotContinuation(b2)) return malformedForLength(src, mark, 1); dst.put((char) (((b1 << 6) ^ b2) ^ (((byte) 0xC0 << 6) ^ ((byte) 0x80 << 0)))); mark += 2; } else if ((b1 >> 4) == -2) { // 3 bytes, 16 bits: 1110xxxx 10xxxxxx 10xxxxxx int srcRemaining = limit - mark; if (srcRemaining < 3 || dst.remaining() < 1) { if (srcRemaining > 1 && isMalformed3_2(b1, src.get())) return malformedForLength(src, mark, 1); return xflow(src, mark, 3); } int b2 = src.get(); int b3 = src.get(); if (isMalformed3(b1, b2, b3)) return malformed(src, mark, 3); char c = (char) ((b1 << 12) ^ (b2 << 6) ^ (b3 ^ (((byte) 0xE0 << 12) ^ ((byte) 0x80 << 6) ^ ((byte) 0x80 << 0)))); if (Character.isSurrogate(c)) return malformedForLength(src, mark, 3); dst.put(c); mark += 3; } else if ((b1 >> 3) == -2) { // 4 bytes, 21 bits: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx int srcRemaining = limit - mark; if (srcRemaining < 4 || dst.remaining() < 2) { b1 &= 0xff; if (b1 > 0xf4 || srcRemaining > 1 && isMalformed4_2(b1, src.get() & 0xff)) return malformedForLength(src, mark, 1); if (srcRemaining > 2 && isMalformed4_3(src.get())) return malformedForLength(src, mark, 2); return xflow(src, mark, 4); } int b2 = src.get(); int b3 = src.get(); int b4 = src.get(); int uc = ((b1 << 18) ^ (b2 << 12) ^ (b3 << 6) ^ (b4 ^ (((byte) 0xF0 << 18) ^ ((byte) 0x80 << 12) ^ ((byte) 0x80 << 6) ^ ((byte) 0x80 << 0)))); if (isMalformed4(b2, b3, b4) || // shortest form check !Character.isSupplementaryCodePoint(uc)) { return malformed(src, mark, 4); } dst.put(Character.highSurrogate(uc)); dst.put(Character.lowSurrogate(uc)); mark += 4; } else { return malformed(src, mark, 1); } } return xflow(src, mark, 0); } protected CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { if (src.hasArray() && dst.hasArray()) return decodeArrayLoop(src, dst); else return decodeBufferLoop(src, dst); } } private static final class Encoder extends CharsetEncoder { private Encoder(Charset cs) { super(cs, 1.1f, 3.0f); } public boolean canEncode(char c) { return !Character.isSurrogate(c); } public boolean isLegalReplacement(byte[] repl) { return ((repl.length == 1 && repl[0] >= 0) || super.isLegalReplacement(repl)); } private static CoderResult overflow(CharBuffer src, int sp, ByteBuffer dst, int dp) { updatePositions(src, sp, dst, dp); return CoderResult.OVERFLOW; } private static CoderResult overflow(CharBuffer src, int mark) { src.position(mark); return CoderResult.OVERFLOW; } private Surrogate.Parser sgp; private CoderResult encodeArrayLoop(CharBuffer src, ByteBuffer dst) { char[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); byte[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); // Handle ASCII-only prefix int n = JLA.encodeASCII(sa, sp, da, dp, Math.min(sl - sp, dl - dp)); sp += n; dp += n; if (sp < sl) { return encodeArrayLoopSlow(src, sa, sp, sl, dst, da, dp, dl); } else { updatePositions(src, sp, dst, dp); return CoderResult.UNDERFLOW; } } private CoderResult encodeArrayLoopSlow(CharBuffer src, char[] sa, int sp, int sl, ByteBuffer dst, byte[] da, int dp, int dl) { while (sp < sl) { char c = sa[sp]; if (c < 0x80) { // Have at most seven bits if (dp >= dl) return overflow(src, sp, dst, dp); da[dp++] = (byte)c; } else if (c < 0x800) { // 2 bytes, 11 bits if (dl - dp < 2) return overflow(src, sp, dst, dp); da[dp++] = (byte)(0xc0 | (c >> 6)); da[dp++] = (byte)(0x80 | (c & 0x3f)); } else if (Character.isSurrogate(c)) { // Have a surrogate pair if (sgp == null) sgp = new Surrogate.Parser(); int uc = sgp.parse(c, sa, sp, sl); if (uc < 0) { updatePositions(src, sp, dst, dp); return sgp.error(); } if (dl - dp < 4) return overflow(src, sp, dst, dp); da[dp++] = (byte)(0xf0 | ((uc >> 18))); da[dp++] = (byte)(0x80 | ((uc >> 12) & 0x3f)); da[dp++] = (byte)(0x80 | ((uc >> 6) & 0x3f)); da[dp++] = (byte)(0x80 | (uc & 0x3f)); sp++; // 2 chars } else { // 3 bytes, 16 bits if (dl - dp < 3) return overflow(src, sp, dst, dp); da[dp++] = (byte)(0xe0 | ((c >> 12))); da[dp++] = (byte)(0x80 | ((c >> 6) & 0x3f)); da[dp++] = (byte)(0x80 | (c & 0x3f)); } sp++; } updatePositions(src, sp, dst, dp); return CoderResult.UNDERFLOW; } private CoderResult encodeBufferLoop(CharBuffer src, ByteBuffer dst) { int mark = src.position(); while (src.hasRemaining()) { char c = src.get(); if (c < 0x80) { // Have at most seven bits if (!dst.hasRemaining()) return overflow(src, mark); dst.put((byte)c); } else if (c < 0x800) { // 2 bytes, 11 bits if (dst.remaining() < 2) return overflow(src, mark); dst.put((byte)(0xc0 | (c >> 6))); dst.put((byte)(0x80 | (c & 0x3f))); } else if (Character.isSurrogate(c)) { // Have a surrogate pair if (sgp == null) sgp = new Surrogate.Parser(); int uc = sgp.parse(c, src); if (uc < 0) { src.position(mark); return sgp.error(); } if (dst.remaining() < 4) return overflow(src, mark); dst.put((byte)(0xf0 | ((uc >> 18)))); dst.put((byte)(0x80 | ((uc >> 12) & 0x3f))); dst.put((byte)(0x80 | ((uc >> 6) & 0x3f))); dst.put((byte)(0x80 | (uc & 0x3f))); mark++; // 2 chars } else { // 3 bytes, 16 bits if (dst.remaining() < 3) return overflow(src, mark); dst.put((byte)(0xe0 | ((c >> 12)))); dst.put((byte)(0x80 | ((c >> 6) & 0x3f))); dst.put((byte)(0x80 | (c & 0x3f))); } mark++; } src.position(mark); return CoderResult.UNDERFLOW; } protected final CoderResult encodeLoop(CharBuffer src, ByteBuffer dst) { if (src.hasArray() && dst.hasArray()) return encodeArrayLoop(src, dst); else return encodeBufferLoop(src, dst); } } }

最后

以上就是长情外套最近收集整理的关于JAVA 的 UTF-8 相关有一个 sun.nio.cs.UTF_8 类的全部内容,更多相关JAVA内容请搜索靠谱客的其他文章。

本图文内容来源于网友提供,作为学习参考使用,或来自网络收集整理,版权属于原作者所有。
点赞(88)

评论列表共有 0 条评论

立即
投稿
返回
顶部