forked from simdjson/simdjson
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathfallback.cpp
More file actions
523 lines (479 loc) · 20.1 KB
/
fallback.cpp
File metadata and controls
523 lines (479 loc) · 20.1 KB
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
#ifndef SIMDJSON_SRC_FALLBACK_CPP
#define SIMDJSON_SRC_FALLBACK_CPP
#ifndef SIMDJSON_CONDITIONAL_INCLUDE
#include <base.h>
#endif // SIMDJSON_CONDITIONAL_INCLUDE
#include <simdjson/fallback.h>
#include <simdjson/fallback/implementation.h>
#include <simdjson/fallback/begin.h>
#include <generic/stage1/find_next_document_index.h>
#include <generic/stage2/stringparsing.h>
#include <generic/stage2/logger.h>
#include <generic/stage2/json_iterator.h>
#include <generic/stage2/tape_writer.h>
#include <generic/stage2/tape_builder.h>
//
// Stage 1
//
namespace simdjson {
namespace fallback {
simdjson_warn_unused error_code implementation::create_dom_parser_implementation(
size_t capacity,
size_t max_depth,
std::unique_ptr<internal::dom_parser_implementation>& dst
) const noexcept {
dst.reset( new (std::nothrow) SIMDJSON_IMPLEMENTATION::dom_parser_implementation() );
if (!dst) { return MEMALLOC; }
if (auto err = dst->set_capacity(capacity))
return err;
if (auto err = dst->set_max_depth(max_depth))
return err;
return SUCCESS;
}
namespace {
namespace stage1 {
class structural_scanner {
public:
simdjson_inline structural_scanner(dom_parser_implementation &_parser, stage1_mode _partial)
: buf{_parser.buf},
next_structural_index{_parser.structural_indexes.get()},
parser{_parser},
len{static_cast<uint32_t>(_parser.len)},
partial{_partial} {
}
simdjson_inline void add_structural() {
*next_structural_index = idx;
next_structural_index++;
}
simdjson_inline bool is_continuation(uint8_t c) {
return (c & 0xc0) == 0x80;
}
simdjson_inline void validate_utf8_character() {
// Continuation
if (simdjson_unlikely((buf[idx] & 0x40) == 0)) {
// extra continuation
error = UTF8_ERROR;
idx++;
return;
}
// 2-byte
if ((buf[idx] & 0x20) == 0) {
// missing continuation
if (simdjson_unlikely(idx+1 > len || !is_continuation(buf[idx+1]))) {
if (idx+1 > len && is_streaming(partial)) { idx = len; return; }
error = UTF8_ERROR;
idx++;
return;
}
// overlong: 1100000_ 10______
if (buf[idx] <= 0xc1) { error = UTF8_ERROR; }
idx += 2;
return;
}
// 3-byte
if ((buf[idx] & 0x10) == 0) {
// missing continuation
if (simdjson_unlikely(idx+2 > len || !is_continuation(buf[idx+1]) || !is_continuation(buf[idx+2]))) {
if (idx+2 > len && is_streaming(partial)) { idx = len; return; }
error = UTF8_ERROR;
idx++;
return;
}
// overlong: 11100000 100_____ ________
if (buf[idx] == 0xe0 && buf[idx+1] <= 0x9f) { error = UTF8_ERROR; }
// surrogates: U+D800-U+DFFF 11101101 101_____
if (buf[idx] == 0xed && buf[idx+1] >= 0xa0) { error = UTF8_ERROR; }
idx += 3;
return;
}
// 4-byte
// missing continuation
if (simdjson_unlikely(idx+3 > len || !is_continuation(buf[idx+1]) || !is_continuation(buf[idx+2]) || !is_continuation(buf[idx+3]))) {
if (idx+2 > len && is_streaming(partial)) { idx = len; return; }
error = UTF8_ERROR;
idx++;
return;
}
// overlong: 11110000 1000____ ________ ________
if (buf[idx] == 0xf0 && buf[idx+1] <= 0x8f) { error = UTF8_ERROR; }
// too large: > U+10FFFF:
// 11110100 (1001|101_)____
// 1111(1___|011_|0101) 10______
// also includes 5, 6, 7 and 8 byte characters:
// 11111___
if (buf[idx] == 0xf4 && buf[idx+1] >= 0x90) { error = UTF8_ERROR; }
if (buf[idx] >= 0xf5) { error = UTF8_ERROR; }
idx += 4;
}
static const uint8_t CHAR_TYPE_SPACE = 1 << 0;
static const uint8_t CHAR_TYPE_OPERATOR = 1 << 1;
static const uint8_t CHAR_TYPE_ESC_ASCII = 1 << 2;
static const uint8_t CHAR_TYPE_NON_ASCII = 1 << 3;
const uint8_t char_table[256] = {
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x01, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x02, 0x04, 0x02, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x02, 0x00, 0x02, 0x00, 0x00,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08
};
simdjson_inline bool char_is_type(uint8_t c, uint8_t type) {
return (char_table[c] & type);
}
simdjson_inline bool char_is_space(uint8_t c) {
return char_is_type(c, CHAR_TYPE_SPACE);
}
simdjson_inline bool char_is_operator(uint8_t c) {
return char_is_type(c, CHAR_TYPE_OPERATOR);
}
simdjson_inline bool char_is_space_or_operator(uint8_t c) {
return char_is_type(c, CHAR_TYPE_SPACE | CHAR_TYPE_OPERATOR);
}
simdjson_inline bool char_is_ascii_stop(uint8_t c) {
return char_is_type(c, CHAR_TYPE_ESC_ASCII | CHAR_TYPE_NON_ASCII);
}
// Returns true if the string is unclosed.
simdjson_inline bool validate_string() {
idx++; // skip first quote
while (idx < len) {
do {
if (char_is_ascii_stop(buf[idx])) { break; }
idx++;
} while (idx < len);
if (idx >= len) { return true; }
if (buf[idx] == '"') {
return false;
}
if (buf[idx] == '\\') {
idx += 2;
} else if (simdjson_unlikely(buf[idx] & 0x80)) {
validate_utf8_character();
} else {
if (buf[idx] < 0x20) { error = UNESCAPED_CHARS; }
idx++;
}
}
if (idx >= len) { return true; }
return false;
}
//
// Parse the entire input in STEP_SIZE-byte chunks.
//
simdjson_warn_unused simdjson_inline error_code scan() {
bool unclosed_string = false;
for (;idx<len;idx++) {
do {
if (!char_is_space(buf[idx])) { break; }
idx++;
} while (idx < len);
if (idx >= len) { break; }
// String
if (buf[idx] == '"') {
add_structural();
unclosed_string |= validate_string();
// Operator
} else if (char_is_operator(buf[idx])) {
add_structural();
// Primitive or invalid character (invalid characters will be checked in stage 2)
} else {
// Anything else, add the structural and go until we find the next one.
// We also stop on RS (0x1E) so that RFC 7464 json_sequence inputs
// like `\x1e"a"\x1e"b"` produce a separate structural for each RS
// rather than being absorbed into a single primitive run. RS is a
// control character that is invalid in normal JSON, so breaking
// the run here has no effect on well-formed non-json_sequence
// inputs.
add_structural();
while (idx+1<len && !char_is_space_or_operator(buf[idx+1]) && buf[idx+1] != 0x1e) {
idx++;
};
}
}
// We pad beyond.
// https://github.com/simdjson/simdjson/issues/906
// See json_structural_indexer.h for an explanation.
*next_structural_index = len; // assumed later in partial == stage1_mode::streaming_final
next_structural_index[1] = len;
next_structural_index[2] = 0;
parser.n_structural_indexes = uint32_t(next_structural_index - parser.structural_indexes.get());
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return EMPTY; }
parser.next_structural_index = 0;
if (partial == stage1_mode::streaming_partial) {
if(unclosed_string) {
parser.n_structural_indexes--;
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return CAPACITY; }
}
// We truncate the input to the end of the last complete document (or zero).
auto new_structural_indexes = find_next_document_index(parser);
if (new_structural_indexes == 0 && parser.n_structural_indexes > 0) {
if(parser.structural_indexes[0] == 0) {
// If the buffer is partial and we started at index 0 but the document is
// incomplete, it's too big to parse.
return CAPACITY;
} else {
// It is possible that the document could be parsed, we just had a lot
// of white space.
parser.n_structural_indexes = 0;
return EMPTY;
}
}
parser.n_structural_indexes = new_structural_indexes;
} else if(partial == stage1_mode::streaming_final) {
if(unclosed_string) { parser.n_structural_indexes--; }
// We truncate the input to the end of the last complete document (or zero).
// Because partial == stage1_mode::streaming_final, it means that we may
// silently ignore trailing garbage. Though it sounds bad, we do it
// deliberately because many people who have streams of JSON documents
// will truncate them for processing. E.g., imagine that you are uncompressing
// the data from a size file or receiving it in chunks from the network. You
// may not know where exactly the last document will be. Meanwhile the
// document_stream instances allow people to know the JSON documents they are
// parsing (see the iterator.source() method).
parser.n_structural_indexes = find_next_document_index(parser);
// We store the initial n_structural_indexes so that the client can see
// whether we used truncation. If initial_n_structural_indexes == parser.n_structural_indexes,
// then this will query parser.structural_indexes[parser.n_structural_indexes] which is len,
// otherwise, it will copy some prior index.
parser.structural_indexes[parser.n_structural_indexes + 1] = parser.structural_indexes[parser.n_structural_indexes];
// This next line is critical, do not change it unless you understand what you are
// doing.
parser.structural_indexes[parser.n_structural_indexes] = uint32_t(len);
if (parser.n_structural_indexes == 0) { return EMPTY; }
} else if (partial == stage1_mode::json_sequence_partial) {
// RFC 7464: use RS positions for batch boundaries
if(unclosed_string) {
parser.n_structural_indexes--;
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return CAPACITY; }
}
uint32_t next_batch_start = uint32_t(len);
auto new_structural_indexes = find_next_document_index_json_sequence(parser, len, false, next_batch_start);
if (new_structural_indexes == DOCUMENT_TOO_LARGE) {
return CAPACITY;
}
if (new_structural_indexes == 0) {
parser.n_structural_indexes = 0;
return EMPTY;
}
parser.n_structural_indexes = new_structural_indexes;
parser.structural_indexes[parser.n_structural_indexes] = next_batch_start;
} else if (partial == stage1_mode::json_sequence_final) {
// RFC 7464: final batch, last document extends to EOF
if(unclosed_string) { parser.n_structural_indexes--; }
uint32_t next_batch_start = uint32_t(len);
parser.n_structural_indexes = find_next_document_index_json_sequence(parser, len, true, next_batch_start);
parser.structural_indexes[parser.n_structural_indexes + 1] = parser.structural_indexes[parser.n_structural_indexes];
parser.structural_indexes[parser.n_structural_indexes] = uint32_t(len);
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return EMPTY; }
} else if (partial == stage1_mode::comma_delimited_partial) {
// Comma-delimited: filter root-level commas, use comma positions for batch boundaries
if(unclosed_string) {
parser.n_structural_indexes--;
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return CAPACITY; }
}
uint32_t next_batch_start = uint32_t(len);
auto new_structural_indexes = filter_comma_delimited(parser, len, false, next_batch_start);
if (new_structural_indexes == DOCUMENT_TOO_LARGE) {
return CAPACITY;
}
if (new_structural_indexes == 0) {
parser.n_structural_indexes = 0;
return EMPTY;
}
parser.n_structural_indexes = new_structural_indexes;
parser.structural_indexes[parser.n_structural_indexes] = next_batch_start;
} else if (partial == stage1_mode::comma_delimited_final) {
// Comma-delimited: final batch, last document extends to EOF
if(unclosed_string) { parser.n_structural_indexes--; }
uint32_t next_batch_start = uint32_t(len);
parser.n_structural_indexes = filter_comma_delimited(parser, len, true, next_batch_start);
parser.structural_indexes[parser.n_structural_indexes + 1] = parser.structural_indexes[parser.n_structural_indexes];
parser.structural_indexes[parser.n_structural_indexes] = uint32_t(len);
if (simdjson_unlikely(parser.n_structural_indexes == 0)) { return EMPTY; }
} else if(unclosed_string) { error = UNCLOSED_STRING; }
return error;
}
private:
const uint8_t *buf;
uint32_t *next_structural_index;
dom_parser_implementation &parser;
uint32_t len;
uint32_t idx{0};
error_code error{SUCCESS};
stage1_mode partial;
}; // structural_scanner
} // namespace stage1
} // unnamed namespace
simdjson_warn_unused error_code dom_parser_implementation::stage1(const uint8_t *_buf, size_t _len, stage1_mode partial) noexcept {
this->buf = _buf;
this->len = _len;
stage1::structural_scanner scanner(*this, partial);
return scanner.scan();
}
// big table for the minifier
static uint8_t jump_table[256 * 3] = {
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0,
1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0,
1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1,
};
simdjson_warn_unused error_code implementation::minify(const uint8_t *buf, size_t len, uint8_t *dst, size_t &dst_len) const noexcept {
size_t i = 0, pos = 0;
uint8_t quote = 0;
uint8_t nonescape = 1;
while (i < len) {
unsigned char c = buf[i];
uint8_t *meta = jump_table + 3 * c;
quote = quote ^ (meta[0] & nonescape);
dst[pos] = c;
pos += meta[2] | quote;
i += 1;
nonescape = uint8_t(~nonescape) | (meta[1]);
}
dst_len = pos; // we intentionally do not work with a reference
// for fear of aliasing
return quote ? UNCLOSED_STRING : SUCCESS;
}
// credit: based on code from Google Fuchsia (Apache Licensed)
simdjson_warn_unused bool implementation::validate_utf8(const char *buf, size_t len) const noexcept {
const uint8_t *data = reinterpret_cast<const uint8_t *>(buf);
uint64_t pos = 0;
uint32_t code_point = 0;
while (pos < len) {
// check of the next 8 bytes are ascii.
uint64_t next_pos = pos + 16;
if (next_pos <= len) { // if it is safe to read 8 more bytes, check that they are ascii
uint64_t v1;
memcpy(&v1, data + pos, sizeof(uint64_t));
uint64_t v2;
memcpy(&v2, data + pos + sizeof(uint64_t), sizeof(uint64_t));
uint64_t v{v1 | v2};
if ((v & 0x8080808080808080) == 0) {
pos = next_pos;
continue;
}
}
unsigned char byte = data[pos];
if (byte < 0x80) {
pos++;
continue;
} else if ((byte & 0xe0) == 0xc0) {
next_pos = pos + 2;
if (next_pos > len) { return false; }
if ((data[pos + 1] & 0xc0) != 0x80) { return false; }
// range check
code_point = (byte & 0x1f) << 6 | (data[pos + 1] & 0x3f);
if (code_point < 0x80 || 0x7ff < code_point) { return false; }
} else if ((byte & 0xf0) == 0xe0) {
next_pos = pos + 3;
if (next_pos > len) { return false; }
if ((data[pos + 1] & 0xc0) != 0x80) { return false; }
if ((data[pos + 2] & 0xc0) != 0x80) { return false; }
// range check
code_point = (byte & 0x0f) << 12 |
(data[pos + 1] & 0x3f) << 6 |
(data[pos + 2] & 0x3f);
if (code_point < 0x800 || 0xffff < code_point ||
(0xd7ff < code_point && code_point < 0xe000)) {
return false;
}
} else if ((byte & 0xf8) == 0xf0) { // 0b11110000
next_pos = pos + 4;
if (next_pos > len) { return false; }
if ((data[pos + 1] & 0xc0) != 0x80) { return false; }
if ((data[pos + 2] & 0xc0) != 0x80) { return false; }
if ((data[pos + 3] & 0xc0) != 0x80) { return false; }
// range check
code_point =
(byte & 0x07) << 18 | (data[pos + 1] & 0x3f) << 12 |
(data[pos + 2] & 0x3f) << 6 | (data[pos + 3] & 0x3f);
if (code_point <= 0xffff || 0x10ffff < code_point) { return false; }
} else {
// we may have a continuation
return false;
}
pos = next_pos;
}
return true;
}
} // namespace fallback
} // namespace simdjson
//
// Stage 2
//
namespace simdjson {
namespace fallback {
simdjson_warn_unused error_code dom_parser_implementation::stage2(dom::document &_doc) noexcept {
return stage2::tape_builder::parse_document<false>(*this, _doc);
}
simdjson_warn_unused error_code dom_parser_implementation::stage2_next(dom::document &_doc) noexcept {
return stage2::tape_builder::parse_document<true>(*this, _doc);
}
SIMDJSON_NO_SANITIZE_MEMORY
simdjson_warn_unused uint8_t *dom_parser_implementation::parse_string(const uint8_t *src, uint8_t *dst, bool replacement_char) const noexcept {
return fallback::stringparsing::parse_string(src, dst, replacement_char);
}
simdjson_warn_unused uint8_t *dom_parser_implementation::parse_wobbly_string(const uint8_t *src, uint8_t *dst) const noexcept {
return fallback::stringparsing::parse_wobbly_string(src, dst);
}
simdjson_warn_unused error_code dom_parser_implementation::parse(const uint8_t *_buf, size_t _len, dom::document &_doc) noexcept {
auto error = stage1(_buf, _len, stage1_mode::regular);
if (error) { return error; }
return stage2(_doc);
}
} // namespace fallback
} // namespace simdjson
#include <simdjson/fallback/end.h>
#endif // SIMDJSON_SRC_FALLBACK_CPP