146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
-
+
-
+
|
char *buffer;
size_t i = 0;
char delimiter = **pointer;
if (++(*pointer) + 1 >= stop)
return nil;
buffer = of_alloc(stop - *pointer, 1);
buffer = OFAllocMemory(stop - *pointer, 1);
while (*pointer < stop) {
/* Parse escape codes */
if (**pointer == '\\') {
if (++(*pointer) >= stop) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
switch (**pointer) {
case '"':
case '\\':
case '/':
|
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
|
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
|
-
+
-
+
-
+
-
+
-
+
|
case 'u':;
OFChar16 c1, c2;
OFUnichar c;
size_t l;
c1 = parseUnicodeEscape(*pointer - 1, stop);
if (c1 == 0xFFFF) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
/* Low surrogate */
if ((c1 & 0xFC00) == 0xDC00) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
/* Normal character */
if ((c1 & 0xFC00) != 0xD800) {
l = of_string_utf8_encode(c1,
buffer + i);
if (l == 0) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
i += l;
*pointer += 5;
break;
}
/*
* If we are still here, we only got one UTF-16
* surrogate and now need to get the other one
* in order to produce UTF-8 and not CESU-8.
*/
c2 = parseUnicodeEscape(*pointer + 5, stop);
if (c2 == 0xFFFF) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
c = (((c1 & 0x3FF) << 10) |
(c2 & 0x3FF)) + 0x10000;
l = of_string_utf8_encode(c, buffer + i);
if (l == 0) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
i += l;
*pointer += 11;
break;
|
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
|
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
|
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
|
break;
case '\n':
(*pointer)++;
(*line)++;
break;
default:
free(buffer);
OFFreeMemory(buffer);
return nil;
}
/* End of string found */
} else if (**pointer == delimiter) {
OFString *ret;
@try {
ret = [OFString stringWithUTF8String: buffer
length: i];
} @finally {
free(buffer);
OFFreeMemory(buffer);
}
(*pointer)++;
return ret;
/* Newlines in strings are disallowed */
} else if (**pointer == '\n' || **pointer == '\r') {
(*line)++;
free(buffer);
OFFreeMemory(buffer);
return nil;
} else {
buffer[i++] = **pointer;
(*pointer)++;
}
}
free(buffer);
OFFreeMemory(buffer);
return nil;
}
static inline OFString *
parseIdentifier(const char **pointer, const char *stop)
{
char *buffer;
size_t i = 0;
buffer = of_alloc(stop - *pointer, 1);
buffer = OFAllocMemory(stop - *pointer, 1);
while (*pointer < stop) {
if ((**pointer >= 'a' && **pointer <= 'z') ||
(**pointer >= 'A' && **pointer <= 'Z') ||
(**pointer >= '0' && **pointer <= '9') ||
**pointer == '_' || **pointer == '$' ||
(**pointer & 0x80)) {
buffer[i++] = **pointer;
(*pointer)++;
} else if (**pointer == '\\') {
OFChar16 c1, c2;
OFUnichar c;
size_t l;
if (++(*pointer) >= stop || **pointer != 'u') {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
c1 = parseUnicodeEscape(*pointer - 1, stop);
if (c1 == 0xFFFF) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
/* Low surrogate */
if ((c1 & 0xFC00) == 0xDC00) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
/* Normal character */
if ((c1 & 0xFC00) != 0xD800) {
l = of_string_utf8_encode(c1, buffer + i);
if (l == 0) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
i += l;
*pointer += 5;
continue;
}
/*
* If we are still here, we only got one UTF-16
* surrogate and now need to get the other one in order
* to produce UTF-8 and not CESU-8.
*/
c2 = parseUnicodeEscape(*pointer + 5, stop);
if (c2 == 0xFFFF) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
c = (((c1 & 0x3FF) << 10) | (c2 & 0x3FF)) + 0x10000;
l = of_string_utf8_encode(c, buffer + i);
if (l == 0) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
i += l;
*pointer += 11;
} else {
OFString *ret;
if (i == 0 || (buffer[0] >= '0' && buffer[0] <= '9')) {
free(buffer);
OFFreeMemory(buffer);
return nil;
}
@try {
ret = [OFString stringWithUTF8String: buffer
length: i];
} @finally {
free(buffer);
OFFreeMemory(buffer);
}
return ret;
}
}
/*
* It is never possible to end with an identifier, thus we should never
* reach stop.
*/
free(buffer);
OFFreeMemory(buffer);
return nil;
}
static inline OFMutableArray *
parseArray(const char **pointer, const char *stop, size_t *line,
size_t depthLimit)
{
|