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
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
|
#include "yarp.h"
/******************************************************************************/
/* Character checks */
/******************************************************************************/
static inline bool
yp_char_is_hexadecimal_digits(const char *c, size_t length) {
for (size_t index = 0; index < length; index++) {
if (!yp_char_is_hexadecimal_digit(c[index])) {
return false;
}
}
return true;
}
/******************************************************************************/
/* Lookup tables for characters */
/******************************************************************************/
// This is a lookup table for unescapes that only take up a single character.
static const unsigned char unescape_chars[] = {
['\''] = '\'',
['\\'] = '\\',
['a'] = '\a',
['b'] = '\b',
['e'] = '\033',
['f'] = '\f',
['n'] = '\n',
['r'] = '\r',
['s'] = ' ',
['t'] = '\t',
['v'] = '\v'
};
// This is a lookup table for whether or not an ASCII character is printable.
static const bool ascii_printable_chars[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0
};
static inline bool
char_is_ascii_printable(const char c) {
unsigned char v = (unsigned char) c;
return (v < 0x80) && ascii_printable_chars[v];
}
/******************************************************************************/
/* Unescaping for segments */
/******************************************************************************/
// Scan the 1-3 digits of octal into the value. Returns the number of digits
// scanned.
static inline size_t
unescape_octal(const char *backslash, unsigned char *value) {
*value = (unsigned char) (backslash[1] - '0');
if (!yp_char_is_octal_digit(backslash[2])) {
return 2;
}
*value = (unsigned char) ((*value << 3) | (backslash[2] - '0'));
if (!yp_char_is_octal_digit(backslash[3])) {
return 3;
}
*value = (unsigned char) ((*value << 3) | (backslash[3] - '0'));
return 4;
}
// Convert a hexadecimal digit into its equivalent value.
static inline unsigned char
unescape_hexadecimal_digit(const char value) {
return (unsigned char) ((value <= '9') ? (value - '0') : (value & 0x7) + 9);
}
// Scan the 1-2 digits of hexadecimal into the value. Returns the number of
// digits scanned.
static inline size_t
unescape_hexadecimal(const char *backslash, unsigned char *value) {
*value = unescape_hexadecimal_digit(backslash[2]);
if (!yp_char_is_hexadecimal_digit(backslash[3])) {
return 3;
}
*value = (unsigned char) ((*value << 4) | unescape_hexadecimal_digit(backslash[3]));
return 4;
}
// Scan the 4 digits of a Unicode escape into the value. Returns the number of
// digits scanned. This function assumes that the characters have already been
// validated.
static inline void
unescape_unicode(const char *string, size_t length, uint32_t *value) {
*value = 0;
for (size_t index = 0; index < length; index++) {
if (index != 0) *value <<= 4;
*value |= unescape_hexadecimal_digit(string[index]);
}
}
// Accepts the pointer to the string to write the unicode value along with the
// 32-bit value to write. Writes the UTF-8 representation of the value to the
// string and returns the number of bytes written.
static inline size_t
unescape_unicode_write(char *dest, uint32_t value, const char *start, const char *end, yp_list_t *error_list) {
unsigned char *bytes = (unsigned char *) dest;
if (value <= 0x7F) {
// 0xxxxxxx
bytes[0] = (unsigned char) value;
return 1;
}
if (value <= 0x7FF) {
// 110xxxxx 10xxxxxx
bytes[0] = (unsigned char) (0xC0 | (value >> 6));
bytes[1] = (unsigned char) (0x80 | (value & 0x3F));
return 2;
}
if (value <= 0xFFFF) {
// 1110xxxx 10xxxxxx 10xxxxxx
bytes[0] = (unsigned char) (0xE0 | (value >> 12));
bytes[1] = (unsigned char) (0x80 | ((value >> 6) & 0x3F));
bytes[2] = (unsigned char) (0x80 | (value & 0x3F));
return 3;
}
// At this point it must be a 4 digit UTF-8 representation. If it's not, then
// the input is invalid.
if (value <= 0x10FFFF) {
// 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
bytes[0] = (unsigned char) (0xF0 | (value >> 18));
bytes[1] = (unsigned char) (0x80 | ((value >> 12) & 0x3F));
bytes[2] = (unsigned char) (0x80 | ((value >> 6) & 0x3F));
bytes[3] = (unsigned char) (0x80 | (value & 0x3F));
return 4;
}
// If we get here, then the value is too big. This is an error, but we don't
// want to just crash, so instead we'll add an error to the error list and put
// in a replacement character instead.
yp_diagnostic_list_append(error_list, start, end, "Invalid Unicode escape sequence.");
bytes[0] = 0xEF;
bytes[1] = 0xBF;
bytes[2] = 0xBD;
return 3;
}
typedef enum {
YP_UNESCAPE_FLAG_NONE = 0,
YP_UNESCAPE_FLAG_CONTROL = 1,
YP_UNESCAPE_FLAG_META = 2,
YP_UNESCAPE_FLAG_EXPECT_SINGLE = 4
} yp_unescape_flag_t;
// Unescape a single character value based on the given flags.
static inline unsigned char
unescape_char(const unsigned char value, const unsigned char flags) {
unsigned char unescaped = value;
if (flags & YP_UNESCAPE_FLAG_CONTROL) {
unescaped &= 0x1f;
}
if (flags & YP_UNESCAPE_FLAG_META) {
unescaped |= 0x80;
}
return unescaped;
}
// Read a specific escape sequence into the given destination.
static const char *
unescape(char *dest, size_t *dest_length, const char *backslash, const char *end, yp_list_t *error_list, const unsigned char flags, bool write_to_str) {
switch (backslash[1]) {
case 'a':
case 'b':
case 'e':
case 'f':
case 'n':
case 'r':
case 's':
case 't':
case 'v':
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char(unescape_chars[(unsigned char) backslash[1]], flags);
}
return backslash + 2;
// \nnn octal bit pattern, where nnn is 1-3 octal digits ([0-7])
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9': {
unsigned char value;
const char *cursor = backslash + unescape_octal(backslash, &value);
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char(value, flags);
}
return cursor;
}
// \xnn hexadecimal bit pattern, where nn is 1-2 hexadecimal digits ([0-9a-fA-F])
case 'x': {
unsigned char value;
const char *cursor = backslash + unescape_hexadecimal(backslash, &value);
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char(value, flags);
}
return cursor;
}
// \u{nnnn ...} Unicode character(s), where each nnnn is 1-6 hexadecimal digits ([0-9a-fA-F])
// \unnnn Unicode character, where nnnn is exactly 4 hexadecimal digits ([0-9a-fA-F])
case 'u': {
if ((flags & YP_UNESCAPE_FLAG_CONTROL) | (flags & YP_UNESCAPE_FLAG_META)) {
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Unicode escape sequence cannot be used with control or meta flags.");
return backslash + 2;
}
if ((backslash + 3) < end && backslash[2] == '{') {
const char *unicode_cursor = backslash + 3;
const char *extra_codepoints_start = NULL;
int codepoints_count = 0;
unicode_cursor += yp_strspn_whitespace(unicode_cursor, end - unicode_cursor);
while ((*unicode_cursor != '}') && (unicode_cursor < end)) {
const char *unicode_start = unicode_cursor;
size_t hexadecimal_length = yp_strspn_hexadecimal_digit(unicode_cursor, end - unicode_cursor);
// \u{nnnn} character literal allows only 1-6 hexadecimal digits
if (hexadecimal_length > 6)
yp_diagnostic_list_append(error_list, unicode_cursor, unicode_cursor + hexadecimal_length, "invalid Unicode escape.");
// there are not hexadecimal characters
if (hexadecimal_length == 0) {
yp_diagnostic_list_append(error_list, unicode_cursor, unicode_cursor + hexadecimal_length, "unterminated Unicode escape");
return unicode_cursor;
}
unicode_cursor += hexadecimal_length;
codepoints_count++;
if (flags & YP_UNESCAPE_FLAG_EXPECT_SINGLE && codepoints_count == 2)
extra_codepoints_start = unicode_start;
uint32_t value;
unescape_unicode(unicode_start, (size_t) (unicode_cursor - unicode_start), &value);
if (write_to_str) {
*dest_length += unescape_unicode_write(dest + *dest_length, value, unicode_start, unicode_cursor, error_list);
}
unicode_cursor += yp_strspn_whitespace(unicode_cursor, end - unicode_cursor);
}
// ?\u{nnnn} character literal should contain only one codepoint and cannot be like ?\u{nnnn mmmm}
if (flags & YP_UNESCAPE_FLAG_EXPECT_SINGLE && codepoints_count > 1)
yp_diagnostic_list_append(error_list, extra_codepoints_start, unicode_cursor - 1, "Multiple codepoints at single character literal");
return unicode_cursor + 1;
}
if ((backslash + 2) < end && yp_char_is_hexadecimal_digits(backslash + 2, 4)) {
uint32_t value;
unescape_unicode(backslash + 2, 4, &value);
if (write_to_str) {
*dest_length += unescape_unicode_write(dest + *dest_length, value, backslash + 2, backslash + 6, error_list);
}
return backslash + 6;
}
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Invalid Unicode escape sequence");
return backslash + 2;
}
// \c\M-x meta control character, where x is an ASCII printable character
// \c? delete, ASCII 7Fh (DEL)
// \cx control character, where x is an ASCII printable character
case 'c':
if (backslash + 2 >= end) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Invalid control escape sequence");
return end;
}
if (flags & YP_UNESCAPE_FLAG_CONTROL) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Control escape sequence cannot be doubled.");
return backslash + 2;
}
switch (backslash[2]) {
case '\\':
return unescape(dest, dest_length, backslash + 2, end, error_list, flags | YP_UNESCAPE_FLAG_CONTROL, write_to_str);
case '?':
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char(0x7f, flags);
}
return backslash + 3;
default: {
if (!char_is_ascii_printable(backslash[2])) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Invalid control escape sequence");
return backslash + 2;
}
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char((const unsigned char) backslash[2], flags | YP_UNESCAPE_FLAG_CONTROL);
}
return backslash + 3;
}
}
// \C-x control character, where x is an ASCII printable character
// \C-? delete, ASCII 7Fh (DEL)
case 'C':
if (backslash + 3 >= end) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Invalid control escape sequence");
return end;
}
if (flags & YP_UNESCAPE_FLAG_CONTROL) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Control escape sequence cannot be doubled.");
return backslash + 2;
}
if (backslash[2] != '-') {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Invalid control escape sequence");
return backslash + 2;
}
switch (backslash[3]) {
case '\\':
return unescape(dest, dest_length, backslash + 3, end, error_list, flags | YP_UNESCAPE_FLAG_CONTROL, write_to_str);
case '?':
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char(0x7f, flags);
}
return backslash + 4;
default:
if (!char_is_ascii_printable(backslash[3])) {
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Invalid control escape sequence");
return backslash + 2;
}
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char((const unsigned char) backslash[3], flags | YP_UNESCAPE_FLAG_CONTROL);
}
return backslash + 4;
}
// \M-\C-x meta control character, where x is an ASCII printable character
// \M-\cx meta control character, where x is an ASCII printable character
// \M-x meta character, where x is an ASCII printable character
case 'M': {
if (backslash + 3 >= end) {
yp_diagnostic_list_append(error_list, backslash, backslash + 1, "Invalid control escape sequence");
return end;
}
if (flags & YP_UNESCAPE_FLAG_META) {
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Meta escape sequence cannot be doubled.");
return backslash + 2;
}
if (backslash[2] != '-') {
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Invalid meta escape sequence");
return backslash + 2;
}
if (backslash[3] == '\\') {
return unescape(dest, dest_length, backslash + 3, end, error_list, flags | YP_UNESCAPE_FLAG_META, write_to_str);
}
if (char_is_ascii_printable(backslash[3])) {
if (write_to_str) {
dest[(*dest_length)++] = (char) unescape_char((const unsigned char) backslash[3], flags | YP_UNESCAPE_FLAG_META);
}
return backslash + 4;
}
yp_diagnostic_list_append(error_list, backslash, backslash + 2, "Invalid meta escape sequence");
return backslash + 3;
}
// \n
case '\n':
return backslash + 2;
// \r
case '\r':
if (backslash + 2 < end && backslash[2] == '\n') {
return backslash + 3;
}
/* fallthrough */
// In this case we're escaping something that doesn't need escaping.
default: {
if (write_to_str) {
dest[(*dest_length)++] = backslash[1];
}
return backslash + 2;
}
}
}
/******************************************************************************/
/* Public functions and entrypoints */
/******************************************************************************/
// Unescape the contents of the given token into the given string using the
// given unescape mode. The supported escapes are:
//
// \a bell, ASCII 07h (BEL)
// \b backspace, ASCII 08h (BS)
// \t horizontal tab, ASCII 09h (TAB)
// \n newline (line feed), ASCII 0Ah (LF)
// \v vertical tab, ASCII 0Bh (VT)
// \f form feed, ASCII 0Ch (FF)
// \r carriage return, ASCII 0Dh (CR)
// \e escape, ASCII 1Bh (ESC)
// \s space, ASCII 20h (SPC)
// \\ backslash
// \nnn octal bit pattern, where nnn is 1-3 octal digits ([0-7])
// \xnn hexadecimal bit pattern, where nn is 1-2 hexadecimal digits ([0-9a-fA-F])
// \unnnn Unicode character, where nnnn is exactly 4 hexadecimal digits ([0-9a-fA-F])
// \u{nnnn ...} Unicode character(s), where each nnnn is 1-6 hexadecimal digits ([0-9a-fA-F])
// \cx or \C-x control character, where x is an ASCII printable character
// \M-x meta character, where x is an ASCII printable character
// \M-\C-x meta control character, where x is an ASCII printable character
// \M-\cx same as above
// \c\M-x same as above
// \c? or \C-? delete, ASCII 7Fh (DEL)
//
YP_EXPORTED_FUNCTION void
yp_unescape_manipulate_string(yp_parser_t *parser, yp_string_t *string, yp_unescape_type_t unescape_type, yp_list_t *error_list) {
if (unescape_type == YP_UNESCAPE_NONE) {
// If we're not unescaping then we can reference the source directly.
return;
}
const char *backslash = yp_memchr(string->source, '\\', string->length, parser->encoding_changed, &parser->encoding);
if (backslash == NULL) {
// Here there are no escapes, so we can reference the source directly.
return;
}
// Here we have found an escape character, so we need to handle all escapes
// within the string.
char *allocated = malloc(string->length);
if (allocated == NULL) {
yp_diagnostic_list_append(error_list, string->source, string->source + string->length, "Failed to allocate memory for unescaping.");
return;
}
// This is the memory address where we're putting the unescaped string.
char *dest = allocated;
size_t dest_length = 0;
// This is the current position in the source string that we're looking at.
// It's going to move along behind the backslash so that we can copy each
// segment of the string that doesn't contain an escape.
const char *cursor = string->source;
const char *end = string->source + string->length;
// For each escape found in the source string, we will handle it and update
// the moving cursor->backslash window.
while (backslash != NULL && backslash + 1 < end) {
assert(dest_length < string->length);
// This is the size of the segment of the string from the previous escape
// or the start of the string to the current escape.
size_t segment_size = (size_t) (backslash - cursor);
// Here we're going to copy everything up until the escape into the
// destination buffer.
memcpy(dest + dest_length, cursor, segment_size);
dest_length += segment_size;
switch (backslash[1]) {
case '\\':
case '\'':
dest[dest_length++] = (char) unescape_chars[(unsigned char) backslash[1]];
cursor = backslash + 2;
break;
default:
if (unescape_type == YP_UNESCAPE_MINIMAL) {
// In this case we're escaping something that doesn't need escaping.
dest[dest_length++] = '\\';
cursor = backslash + 1;
break;
}
// This is the only type of unescaping left. In this case we need to
// handle all of the different unescapes.
assert(unescape_type == YP_UNESCAPE_ALL);
cursor = unescape(dest, &dest_length, backslash, end, error_list, YP_UNESCAPE_FLAG_NONE, true);
break;
}
if (end > cursor) {
backslash = yp_memchr(cursor, '\\', (size_t) (end - cursor), parser->encoding_changed, &parser->encoding);
} else {
backslash = NULL;
}
}
// We need to copy the final segment of the string after the last escape.
if (end > cursor) {
memcpy(dest + dest_length, cursor, (size_t) (end - cursor));
} else {
cursor = end;
}
// If the string was already allocated, then we need to free that memory
// here. That's because we're about to override it with the escaped string.
yp_string_free(string);
// We also need to update the length at the end. This is because every escape
// reduces the length of the final string, and we don't want garbage at the
// end.
yp_string_owned_init(string, allocated, dest_length + ((size_t) (end - cursor)));
}
YP_EXPORTED_FUNCTION bool
yp_unescape_string(const char *start, size_t length, yp_unescape_type_t unescape_type, yp_string_t *result) {
bool success;
yp_parser_t parser;
yp_parser_init(&parser, start, length, "");
yp_list_t error_list = YP_LIST_EMPTY;
yp_string_shared_init(result, start, start + length);
yp_unescape_manipulate_string(&parser, result, unescape_type, &error_list);
success = yp_list_empty_p(&error_list);
yp_list_free(&error_list);
yp_parser_free(&parser);
return success;
}
// This function is similar to yp_unescape_manipulate_string, except it doesn't
// actually perform any string manipulations. Instead, it calculates how long
// the unescaped character is, and returns that value
YP_EXPORTED_FUNCTION size_t
yp_unescape_calculate_difference(const char *backslash, const char *end, yp_unescape_type_t unescape_type, bool expect_single_codepoint, yp_list_t *error_list) {
assert(unescape_type != YP_UNESCAPE_NONE);
switch (backslash[1]) {
case '\\':
case '\'':
return 2;
default: {
if (unescape_type == YP_UNESCAPE_MINIMAL) return 2;
// This is the only type of unescaping left. In this case we need to
// handle all of the different unescapes.
assert(unescape_type == YP_UNESCAPE_ALL);
unsigned char flags = YP_UNESCAPE_FLAG_NONE;
if (expect_single_codepoint)
flags |= YP_UNESCAPE_FLAG_EXPECT_SINGLE;
const char *cursor = unescape(NULL, 0, backslash, end, error_list, flags, false);
assert(cursor > backslash);
return (size_t) (cursor - backslash);
}
}
}
|