1 | |
---|
2 | /* |
---|
3 | * Introduction |
---|
4 | * ************ |
---|
5 | * |
---|
6 | * The following notes assume that you are familiar with the YAML specification |
---|
7 | * (http://yaml.org/spec/cvs/current.html). We mostly follow it, although in |
---|
8 | * some cases we are less restrictive that it requires. |
---|
9 | * |
---|
10 | * The process of transforming a YAML stream into a sequence of events is |
---|
11 | * divided on two steps: Scanning and Parsing. |
---|
12 | * |
---|
13 | * The Scanner transforms the input stream into a sequence of tokens, while the |
---|
14 | * parser transform the sequence of tokens produced by the Scanner into a |
---|
15 | * sequence of parsing events. |
---|
16 | * |
---|
17 | * The Scanner is rather clever and complicated. The Parser, on the contrary, |
---|
18 | * is a straightforward implementation of a recursive-descendant parser (or, |
---|
19 | * LL(1) parser, as it is usually called). |
---|
20 | * |
---|
21 | * Actually there are two issues of Scanning that might be called "clever", the |
---|
22 | * rest is quite straightforward. The issues are "block collection start" and |
---|
23 | * "simple keys". Both issues are explained below in details. |
---|
24 | * |
---|
25 | * Here the Scanning step is explained and implemented. We start with the list |
---|
26 | * of all the tokens produced by the Scanner together with short descriptions. |
---|
27 | * |
---|
28 | * Now, tokens: |
---|
29 | * |
---|
30 | * STREAM-START(encoding) # The stream start. |
---|
31 | * STREAM-END # The stream end. |
---|
32 | * VERSION-DIRECTIVE(major,minor) # The '%YAML' directive. |
---|
33 | * TAG-DIRECTIVE(handle,prefix) # The '%TAG' directive. |
---|
34 | * DOCUMENT-START # '---' |
---|
35 | * DOCUMENT-END # '...' |
---|
36 | * BLOCK-SEQUENCE-START # Indentation increase denoting a block |
---|
37 | * BLOCK-MAPPING-START # sequence or a block mapping. |
---|
38 | * BLOCK-END # Indentation decrease. |
---|
39 | * FLOW-SEQUENCE-START # '[' |
---|
40 | * FLOW-SEQUENCE-END # ']' |
---|
41 | * BLOCK-SEQUENCE-START # '{' |
---|
42 | * BLOCK-SEQUENCE-END # '}' |
---|
43 | * BLOCK-ENTRY # '-' |
---|
44 | * FLOW-ENTRY # ',' |
---|
45 | * KEY # '?' or nothing (simple keys). |
---|
46 | * VALUE # ':' |
---|
47 | * ALIAS(anchor) # '*anchor' |
---|
48 | * ANCHOR(anchor) # '&anchor' |
---|
49 | * TAG(handle,suffix) # '!handle!suffix' |
---|
50 | * SCALAR(value,style) # A scalar. |
---|
51 | * |
---|
52 | * The following two tokens are "virtual" tokens denoting the beginning and the |
---|
53 | * end of the stream: |
---|
54 | * |
---|
55 | * STREAM-START(encoding) |
---|
56 | * STREAM-END |
---|
57 | * |
---|
58 | * We pass the information about the input stream encoding with the |
---|
59 | * STREAM-START token. |
---|
60 | * |
---|
61 | * The next two tokens are responsible for tags: |
---|
62 | * |
---|
63 | * VERSION-DIRECTIVE(major,minor) |
---|
64 | * TAG-DIRECTIVE(handle,prefix) |
---|
65 | * |
---|
66 | * Example: |
---|
67 | * |
---|
68 | * %YAML 1.1 |
---|
69 | * %TAG ! !foo |
---|
70 | * %TAG !yaml! tag:yaml.org,2002: |
---|
71 | * --- |
---|
72 | * |
---|
73 | * The correspoding sequence of tokens: |
---|
74 | * |
---|
75 | * STREAM-START(utf-8) |
---|
76 | * VERSION-DIRECTIVE(1,1) |
---|
77 | * TAG-DIRECTIVE("!","!foo") |
---|
78 | * TAG-DIRECTIVE("!yaml","tag:yaml.org,2002:") |
---|
79 | * DOCUMENT-START |
---|
80 | * STREAM-END |
---|
81 | * |
---|
82 | * Note that the VERSION-DIRECTIVE and TAG-DIRECTIVE tokens occupy a whole |
---|
83 | * line. |
---|
84 | * |
---|
85 | * The document start and end indicators are represented by: |
---|
86 | * |
---|
87 | * DOCUMENT-START |
---|
88 | * DOCUMENT-END |
---|
89 | * |
---|
90 | * Note that if a YAML stream contains an implicit document (without '---' |
---|
91 | * and '...' indicators), no DOCUMENT-START and DOCUMENT-END tokens will be |
---|
92 | * produced. |
---|
93 | * |
---|
94 | * In the following examples, we present whole documents together with the |
---|
95 | * produced tokens. |
---|
96 | * |
---|
97 | * 1. An implicit document: |
---|
98 | * |
---|
99 | * 'a scalar' |
---|
100 | * |
---|
101 | * Tokens: |
---|
102 | * |
---|
103 | * STREAM-START(utf-8) |
---|
104 | * SCALAR("a scalar",single-quoted) |
---|
105 | * STREAM-END |
---|
106 | * |
---|
107 | * 2. An explicit document: |
---|
108 | * |
---|
109 | * --- |
---|
110 | * 'a scalar' |
---|
111 | * ... |
---|
112 | * |
---|
113 | * Tokens: |
---|
114 | * |
---|
115 | * STREAM-START(utf-8) |
---|
116 | * DOCUMENT-START |
---|
117 | * SCALAR("a scalar",single-quoted) |
---|
118 | * DOCUMENT-END |
---|
119 | * STREAM-END |
---|
120 | * |
---|
121 | * 3. Several documents in a stream: |
---|
122 | * |
---|
123 | * 'a scalar' |
---|
124 | * --- |
---|
125 | * 'another scalar' |
---|
126 | * --- |
---|
127 | * 'yet another scalar' |
---|
128 | * |
---|
129 | * Tokens: |
---|
130 | * |
---|
131 | * STREAM-START(utf-8) |
---|
132 | * SCALAR("a scalar",single-quoted) |
---|
133 | * DOCUMENT-START |
---|
134 | * SCALAR("another scalar",single-quoted) |
---|
135 | * DOCUMENT-START |
---|
136 | * SCALAR("yet another scalar",single-quoted) |
---|
137 | * STREAM-END |
---|
138 | * |
---|
139 | * We have already introduced the SCALAR token above. The following tokens are |
---|
140 | * used to describe aliases, anchors, tag, and scalars: |
---|
141 | * |
---|
142 | * ALIAS(anchor) |
---|
143 | * ANCHOR(anchor) |
---|
144 | * TAG(handle,suffix) |
---|
145 | * SCALAR(value,style) |
---|
146 | * |
---|
147 | * The following series of examples illustrate the usage of these tokens: |
---|
148 | * |
---|
149 | * 1. A recursive sequence: |
---|
150 | * |
---|
151 | * &A [ *A ] |
---|
152 | * |
---|
153 | * Tokens: |
---|
154 | * |
---|
155 | * STREAM-START(utf-8) |
---|
156 | * ANCHOR("A") |
---|
157 | * FLOW-SEQUENCE-START |
---|
158 | * ALIAS("A") |
---|
159 | * FLOW-SEQUENCE-END |
---|
160 | * STREAM-END |
---|
161 | * |
---|
162 | * 2. A tagged scalar: |
---|
163 | * |
---|
164 | * !!float "3.14" # A good approximation. |
---|
165 | * |
---|
166 | * Tokens: |
---|
167 | * |
---|
168 | * STREAM-START(utf-8) |
---|
169 | * TAG("!!","float") |
---|
170 | * SCALAR("3.14",double-quoted) |
---|
171 | * STREAM-END |
---|
172 | * |
---|
173 | * 3. Various scalar styles: |
---|
174 | * |
---|
175 | * --- # Implicit empty plain scalars do not produce tokens. |
---|
176 | * --- a plain scalar |
---|
177 | * --- 'a single-quoted scalar' |
---|
178 | * --- "a double-quoted scalar" |
---|
179 | * --- |- |
---|
180 | * a literal scalar |
---|
181 | * --- >- |
---|
182 | * a folded |
---|
183 | * scalar |
---|
184 | * |
---|
185 | * Tokens: |
---|
186 | * |
---|
187 | * STREAM-START(utf-8) |
---|
188 | * DOCUMENT-START |
---|
189 | * DOCUMENT-START |
---|
190 | * SCALAR("a plain scalar",plain) |
---|
191 | * DOCUMENT-START |
---|
192 | * SCALAR("a single-quoted scalar",single-quoted) |
---|
193 | * DOCUMENT-START |
---|
194 | * SCALAR("a double-quoted scalar",double-quoted) |
---|
195 | * DOCUMENT-START |
---|
196 | * SCALAR("a literal scalar",literal) |
---|
197 | * DOCUMENT-START |
---|
198 | * SCALAR("a folded scalar",folded) |
---|
199 | * STREAM-END |
---|
200 | * |
---|
201 | * Now it's time to review collection-related tokens. We will start with |
---|
202 | * flow collections: |
---|
203 | * |
---|
204 | * FLOW-SEQUENCE-START |
---|
205 | * FLOW-SEQUENCE-END |
---|
206 | * FLOW-MAPPING-START |
---|
207 | * FLOW-MAPPING-END |
---|
208 | * FLOW-ENTRY |
---|
209 | * KEY |
---|
210 | * VALUE |
---|
211 | * |
---|
212 | * The tokens FLOW-SEQUENCE-START, FLOW-SEQUENCE-END, FLOW-MAPPING-START, and |
---|
213 | * FLOW-MAPPING-END represent the indicators '[', ']', '{', and '}' |
---|
214 | * correspondingly. FLOW-ENTRY represent the ',' indicator. Finally the |
---|
215 | * indicators '?' and ':', which are used for denoting mapping keys and values, |
---|
216 | * are represented by the KEY and VALUE tokens. |
---|
217 | * |
---|
218 | * The following examples show flow collections: |
---|
219 | * |
---|
220 | * 1. A flow sequence: |
---|
221 | * |
---|
222 | * [item 1, item 2, item 3] |
---|
223 | * |
---|
224 | * Tokens: |
---|
225 | * |
---|
226 | * STREAM-START(utf-8) |
---|
227 | * FLOW-SEQUENCE-START |
---|
228 | * SCALAR("item 1",plain) |
---|
229 | * FLOW-ENTRY |
---|
230 | * SCALAR("item 2",plain) |
---|
231 | * FLOW-ENTRY |
---|
232 | * SCALAR("item 3",plain) |
---|
233 | * FLOW-SEQUENCE-END |
---|
234 | * STREAM-END |
---|
235 | * |
---|
236 | * 2. A flow mapping: |
---|
237 | * |
---|
238 | * { |
---|
239 | * a simple key: a value, # Note that the KEY token is produced. |
---|
240 | * ? a complex key: another value, |
---|
241 | * } |
---|
242 | * |
---|
243 | * Tokens: |
---|
244 | * |
---|
245 | * STREAM-START(utf-8) |
---|
246 | * FLOW-MAPPING-START |
---|
247 | * KEY |
---|
248 | * SCALAR("a simple key",plain) |
---|
249 | * VALUE |
---|
250 | * SCALAR("a value",plain) |
---|
251 | * FLOW-ENTRY |
---|
252 | * KEY |
---|
253 | * SCALAR("a complex key",plain) |
---|
254 | * VALUE |
---|
255 | * SCALAR("another value",plain) |
---|
256 | * FLOW-ENTRY |
---|
257 | * FLOW-MAPPING-END |
---|
258 | * STREAM-END |
---|
259 | * |
---|
260 | * A simple key is a key which is not denoted by the '?' indicator. Note that |
---|
261 | * the Scanner still produce the KEY token whenever it encounters a simple key. |
---|
262 | * |
---|
263 | * For scanning block collections, the following tokens are used (note that we |
---|
264 | * repeat KEY and VALUE here): |
---|
265 | * |
---|
266 | * BLOCK-SEQUENCE-START |
---|
267 | * BLOCK-MAPPING-START |
---|
268 | * BLOCK-END |
---|
269 | * BLOCK-ENTRY |
---|
270 | * KEY |
---|
271 | * VALUE |
---|
272 | * |
---|
273 | * The tokens BLOCK-SEQUENCE-START and BLOCK-MAPPING-START denote indentation |
---|
274 | * increase that precedes a block collection (cf. the INDENT token in Python). |
---|
275 | * The token BLOCK-END denote indentation decrease that ends a block collection |
---|
276 | * (cf. the DEDENT token in Python). However YAML has some syntax pecularities |
---|
277 | * that makes detections of these tokens more complex. |
---|
278 | * |
---|
279 | * The tokens BLOCK-ENTRY, KEY, and VALUE are used to represent the indicators |
---|
280 | * '-', '?', and ':' correspondingly. |
---|
281 | * |
---|
282 | * The following examples show how the tokens BLOCK-SEQUENCE-START, |
---|
283 | * BLOCK-MAPPING-START, and BLOCK-END are emitted by the Scanner: |
---|
284 | * |
---|
285 | * 1. Block sequences: |
---|
286 | * |
---|
287 | * - item 1 |
---|
288 | * - item 2 |
---|
289 | * - |
---|
290 | * - item 3.1 |
---|
291 | * - item 3.2 |
---|
292 | * - |
---|
293 | * key 1: value 1 |
---|
294 | * key 2: value 2 |
---|
295 | * |
---|
296 | * Tokens: |
---|
297 | * |
---|
298 | * STREAM-START(utf-8) |
---|
299 | * BLOCK-SEQUENCE-START |
---|
300 | * BLOCK-ENTRY |
---|
301 | * SCALAR("item 1",plain) |
---|
302 | * BLOCK-ENTRY |
---|
303 | * SCALAR("item 2",plain) |
---|
304 | * BLOCK-ENTRY |
---|
305 | * BLOCK-SEQUENCE-START |
---|
306 | * BLOCK-ENTRY |
---|
307 | * SCALAR("item 3.1",plain) |
---|
308 | * BLOCK-ENTRY |
---|
309 | * SCALAR("item 3.2",plain) |
---|
310 | * BLOCK-END |
---|
311 | * BLOCK-ENTRY |
---|
312 | * BLOCK-MAPPING-START |
---|
313 | * KEY |
---|
314 | * SCALAR("key 1",plain) |
---|
315 | * VALUE |
---|
316 | * SCALAR("value 1",plain) |
---|
317 | * KEY |
---|
318 | * SCALAR("key 2",plain) |
---|
319 | * VALUE |
---|
320 | * SCALAR("value 2",plain) |
---|
321 | * BLOCK-END |
---|
322 | * BLOCK-END |
---|
323 | * STREAM-END |
---|
324 | * |
---|
325 | * 2. Block mappings: |
---|
326 | * |
---|
327 | * a simple key: a value # The KEY token is produced here. |
---|
328 | * ? a complex key |
---|
329 | * : another value |
---|
330 | * a mapping: |
---|
331 | * key 1: value 1 |
---|
332 | * key 2: value 2 |
---|
333 | * a sequence: |
---|
334 | * - item 1 |
---|
335 | * - item 2 |
---|
336 | * |
---|
337 | * Tokens: |
---|
338 | * |
---|
339 | * STREAM-START(utf-8) |
---|
340 | * BLOCK-MAPPING-START |
---|
341 | * KEY |
---|
342 | * SCALAR("a simple key",plain) |
---|
343 | * VALUE |
---|
344 | * SCALAR("a value",plain) |
---|
345 | * KEY |
---|
346 | * SCALAR("a complex key",plain) |
---|
347 | * VALUE |
---|
348 | * SCALAR("another value",plain) |
---|
349 | * KEY |
---|
350 | * SCALAR("a mapping",plain) |
---|
351 | * BLOCK-MAPPING-START |
---|
352 | * KEY |
---|
353 | * SCALAR("key 1",plain) |
---|
354 | * VALUE |
---|
355 | * SCALAR("value 1",plain) |
---|
356 | * KEY |
---|
357 | * SCALAR("key 2",plain) |
---|
358 | * VALUE |
---|
359 | * SCALAR("value 2",plain) |
---|
360 | * BLOCK-END |
---|
361 | * KEY |
---|
362 | * SCALAR("a sequence",plain) |
---|
363 | * VALUE |
---|
364 | * BLOCK-SEQUENCE-START |
---|
365 | * BLOCK-ENTRY |
---|
366 | * SCALAR("item 1",plain) |
---|
367 | * BLOCK-ENTRY |
---|
368 | * SCALAR("item 2",plain) |
---|
369 | * BLOCK-END |
---|
370 | * BLOCK-END |
---|
371 | * STREAM-END |
---|
372 | * |
---|
373 | * YAML does not always require to start a new block collection from a new |
---|
374 | * line. If the current line contains only '-', '?', and ':' indicators, a new |
---|
375 | * block collection may start at the current line. The following examples |
---|
376 | * illustrate this case: |
---|
377 | * |
---|
378 | * 1. Collections in a sequence: |
---|
379 | * |
---|
380 | * - - item 1 |
---|
381 | * - item 2 |
---|
382 | * - key 1: value 1 |
---|
383 | * key 2: value 2 |
---|
384 | * - ? complex key |
---|
385 | * : complex value |
---|
386 | * |
---|
387 | * Tokens: |
---|
388 | * |
---|
389 | * STREAM-START(utf-8) |
---|
390 | * BLOCK-SEQUENCE-START |
---|
391 | * BLOCK-ENTRY |
---|
392 | * BLOCK-SEQUENCE-START |
---|
393 | * BLOCK-ENTRY |
---|
394 | * SCALAR("item 1",plain) |
---|
395 | * BLOCK-ENTRY |
---|
396 | * SCALAR("item 2",plain) |
---|
397 | * BLOCK-END |
---|
398 | * BLOCK-ENTRY |
---|
399 | * BLOCK-MAPPING-START |
---|
400 | * KEY |
---|
401 | * SCALAR("key 1",plain) |
---|
402 | * VALUE |
---|
403 | * SCALAR("value 1",plain) |
---|
404 | * KEY |
---|
405 | * SCALAR("key 2",plain) |
---|
406 | * VALUE |
---|
407 | * SCALAR("value 2",plain) |
---|
408 | * BLOCK-END |
---|
409 | * BLOCK-ENTRY |
---|
410 | * BLOCK-MAPPING-START |
---|
411 | * KEY |
---|
412 | * SCALAR("complex key") |
---|
413 | * VALUE |
---|
414 | * SCALAR("complex value") |
---|
415 | * BLOCK-END |
---|
416 | * BLOCK-END |
---|
417 | * STREAM-END |
---|
418 | * |
---|
419 | * 2. Collections in a mapping: |
---|
420 | * |
---|
421 | * ? a sequence |
---|
422 | * : - item 1 |
---|
423 | * - item 2 |
---|
424 | * ? a mapping |
---|
425 | * : key 1: value 1 |
---|
426 | * key 2: value 2 |
---|
427 | * |
---|
428 | * Tokens: |
---|
429 | * |
---|
430 | * STREAM-START(utf-8) |
---|
431 | * BLOCK-MAPPING-START |
---|
432 | * KEY |
---|
433 | * SCALAR("a sequence",plain) |
---|
434 | * VALUE |
---|
435 | * BLOCK-SEQUENCE-START |
---|
436 | * BLOCK-ENTRY |
---|
437 | * SCALAR("item 1",plain) |
---|
438 | * BLOCK-ENTRY |
---|
439 | * SCALAR("item 2",plain) |
---|
440 | * BLOCK-END |
---|
441 | * KEY |
---|
442 | * SCALAR("a mapping",plain) |
---|
443 | * VALUE |
---|
444 | * BLOCK-MAPPING-START |
---|
445 | * KEY |
---|
446 | * SCALAR("key 1",plain) |
---|
447 | * VALUE |
---|
448 | * SCALAR("value 1",plain) |
---|
449 | * KEY |
---|
450 | * SCALAR("key 2",plain) |
---|
451 | * VALUE |
---|
452 | * SCALAR("value 2",plain) |
---|
453 | * BLOCK-END |
---|
454 | * BLOCK-END |
---|
455 | * STREAM-END |
---|
456 | * |
---|
457 | * YAML also permits non-indented sequences if they are included into a block |
---|
458 | * mapping. In this case, the token BLOCK-SEQUENCE-START is not produced: |
---|
459 | * |
---|
460 | * key: |
---|
461 | * - item 1 # BLOCK-SEQUENCE-START is NOT produced here. |
---|
462 | * - item 2 |
---|
463 | * |
---|
464 | * Tokens: |
---|
465 | * |
---|
466 | * STREAM-START(utf-8) |
---|
467 | * BLOCK-MAPPING-START |
---|
468 | * KEY |
---|
469 | * SCALAR("key",plain) |
---|
470 | * VALUE |
---|
471 | * BLOCK-ENTRY |
---|
472 | * SCALAR("item 1",plain) |
---|
473 | * BLOCK-ENTRY |
---|
474 | * SCALAR("item 2",plain) |
---|
475 | * BLOCK-END |
---|
476 | */ |
---|
477 | |
---|
478 | #include "yaml_private.h" |
---|
479 | |
---|
480 | /* |
---|
481 | * Ensure that the buffer contains the required number of characters. |
---|
482 | * Return 1 on success, 0 on failure (reader error or memory error). |
---|
483 | */ |
---|
484 | |
---|
485 | #define CACHE(parser,length) \ |
---|
486 | (parser->unread >= (length) \ |
---|
487 | ? 1 \ |
---|
488 | : yaml_parser_update_buffer(parser, (length))) |
---|
489 | |
---|
490 | /* |
---|
491 | * Advance the buffer pointer. |
---|
492 | */ |
---|
493 | |
---|
494 | #define SKIP(parser) \ |
---|
495 | (parser->mark.index ++, \ |
---|
496 | parser->mark.column ++, \ |
---|
497 | parser->unread --, \ |
---|
498 | parser->buffer.pointer += WIDTH(parser->buffer)) |
---|
499 | |
---|
500 | #define SKIP_LINE(parser) \ |
---|
501 | (IS_CRLF(parser->buffer) ? \ |
---|
502 | (parser->mark.index += 2, \ |
---|
503 | parser->mark.column = 0, \ |
---|
504 | parser->mark.line ++, \ |
---|
505 | parser->unread -= 2, \ |
---|
506 | parser->buffer.pointer += 2) : \ |
---|
507 | IS_BREAK(parser->buffer) ? \ |
---|
508 | (parser->mark.index ++, \ |
---|
509 | parser->mark.column = 0, \ |
---|
510 | parser->mark.line ++, \ |
---|
511 | parser->unread --, \ |
---|
512 | parser->buffer.pointer += WIDTH(parser->buffer)) : 0) |
---|
513 | |
---|
514 | /* |
---|
515 | * Copy a character to a string buffer and advance pointers. |
---|
516 | */ |
---|
517 | |
---|
518 | #define READ(parser,string) \ |
---|
519 | (STRING_EXTEND(parser,string) ? \ |
---|
520 | (COPY(string,parser->buffer), \ |
---|
521 | parser->mark.index ++, \ |
---|
522 | parser->mark.column ++, \ |
---|
523 | parser->unread --, \ |
---|
524 | 1) : 0) |
---|
525 | |
---|
526 | /* |
---|
527 | * Copy a line break character to a string buffer and advance pointers. |
---|
528 | */ |
---|
529 | |
---|
530 | #define READ_LINE(parser,string) \ |
---|
531 | (STRING_EXTEND(parser,string) ? \ |
---|
532 | (((CHECK_AT(parser->buffer,'\r',0) \ |
---|
533 | && CHECK_AT(parser->buffer,'\n',1)) ? /* CR LF -> LF */ \ |
---|
534 | (*((string).pointer++) = (yaml_char_t) '\n', \ |
---|
535 | parser->buffer.pointer += 2, \ |
---|
536 | parser->mark.index += 2, \ |
---|
537 | parser->mark.column = 0, \ |
---|
538 | parser->mark.line ++, \ |
---|
539 | parser->unread -= 2) : \ |
---|
540 | (CHECK_AT(parser->buffer,'\r',0) \ |
---|
541 | || CHECK_AT(parser->buffer,'\n',0)) ? /* CR|LF -> LF */ \ |
---|
542 | (*((string).pointer++) = (yaml_char_t) '\n', \ |
---|
543 | parser->buffer.pointer ++, \ |
---|
544 | parser->mark.index ++, \ |
---|
545 | parser->mark.column = 0, \ |
---|
546 | parser->mark.line ++, \ |
---|
547 | parser->unread --) : \ |
---|
548 | (CHECK_AT(parser->buffer,'\xC2',0) \ |
---|
549 | && CHECK_AT(parser->buffer,'\x85',1)) ? /* NEL -> LF */ \ |
---|
550 | (*((string).pointer++) = (yaml_char_t) '\n', \ |
---|
551 | parser->buffer.pointer += 2, \ |
---|
552 | parser->mark.index ++, \ |
---|
553 | parser->mark.column = 0, \ |
---|
554 | parser->mark.line ++, \ |
---|
555 | parser->unread --) : \ |
---|
556 | (CHECK_AT(parser->buffer,'\xE2',0) && \ |
---|
557 | CHECK_AT(parser->buffer,'\x80',1) && \ |
---|
558 | (CHECK_AT(parser->buffer,'\xA8',2) || \ |
---|
559 | CHECK_AT(parser->buffer,'\xA9',2))) ? /* LS|PS -> LS|PS */ \ |
---|
560 | (*((string).pointer++) = *(parser->buffer.pointer++), \ |
---|
561 | *((string).pointer++) = *(parser->buffer.pointer++), \ |
---|
562 | *((string).pointer++) = *(parser->buffer.pointer++), \ |
---|
563 | parser->mark.index ++, \ |
---|
564 | parser->mark.column = 0, \ |
---|
565 | parser->mark.line ++, \ |
---|
566 | parser->unread --) : 0), \ |
---|
567 | 1) : 0) |
---|
568 | |
---|
569 | /* |
---|
570 | * Public API declarations. |
---|
571 | */ |
---|
572 | |
---|
573 | YAML_DECLARE(int) |
---|
574 | yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token); |
---|
575 | |
---|
576 | /* |
---|
577 | * Error handling. |
---|
578 | */ |
---|
579 | |
---|
580 | static int |
---|
581 | yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, |
---|
582 | yaml_mark_t context_mark, const char *problem); |
---|
583 | |
---|
584 | /* |
---|
585 | * High-level token API. |
---|
586 | */ |
---|
587 | |
---|
588 | YAML_DECLARE(int) |
---|
589 | yaml_parser_fetch_more_tokens(yaml_parser_t *parser); |
---|
590 | |
---|
591 | static int |
---|
592 | yaml_parser_fetch_next_token(yaml_parser_t *parser); |
---|
593 | |
---|
594 | /* |
---|
595 | * Potential simple keys. |
---|
596 | */ |
---|
597 | |
---|
598 | static int |
---|
599 | yaml_parser_stale_simple_keys(yaml_parser_t *parser); |
---|
600 | |
---|
601 | static int |
---|
602 | yaml_parser_save_simple_key(yaml_parser_t *parser); |
---|
603 | |
---|
604 | static int |
---|
605 | yaml_parser_remove_simple_key(yaml_parser_t *parser); |
---|
606 | |
---|
607 | static int |
---|
608 | yaml_parser_increase_flow_level(yaml_parser_t *parser); |
---|
609 | |
---|
610 | static int |
---|
611 | yaml_parser_decrease_flow_level(yaml_parser_t *parser); |
---|
612 | |
---|
613 | /* |
---|
614 | * Indentation treatment. |
---|
615 | */ |
---|
616 | |
---|
617 | static int |
---|
618 | yaml_parser_roll_indent(yaml_parser_t *parser, int column, |
---|
619 | int number, yaml_token_type_t type, yaml_mark_t mark); |
---|
620 | |
---|
621 | static int |
---|
622 | yaml_parser_unroll_indent(yaml_parser_t *parser, int column); |
---|
623 | |
---|
624 | /* |
---|
625 | * Token fetchers. |
---|
626 | */ |
---|
627 | |
---|
628 | static int |
---|
629 | yaml_parser_fetch_stream_start(yaml_parser_t *parser); |
---|
630 | |
---|
631 | static int |
---|
632 | yaml_parser_fetch_stream_end(yaml_parser_t *parser); |
---|
633 | |
---|
634 | static int |
---|
635 | yaml_parser_fetch_directive(yaml_parser_t *parser); |
---|
636 | |
---|
637 | static int |
---|
638 | yaml_parser_fetch_document_indicator(yaml_parser_t *parser, |
---|
639 | yaml_token_type_t type); |
---|
640 | |
---|
641 | static int |
---|
642 | yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, |
---|
643 | yaml_token_type_t type); |
---|
644 | |
---|
645 | static int |
---|
646 | yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, |
---|
647 | yaml_token_type_t type); |
---|
648 | |
---|
649 | static int |
---|
650 | yaml_parser_fetch_flow_entry(yaml_parser_t *parser); |
---|
651 | |
---|
652 | static int |
---|
653 | yaml_parser_fetch_block_entry(yaml_parser_t *parser); |
---|
654 | |
---|
655 | static int |
---|
656 | yaml_parser_fetch_key(yaml_parser_t *parser); |
---|
657 | |
---|
658 | static int |
---|
659 | yaml_parser_fetch_value(yaml_parser_t *parser); |
---|
660 | |
---|
661 | static int |
---|
662 | yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type); |
---|
663 | |
---|
664 | static int |
---|
665 | yaml_parser_fetch_tag(yaml_parser_t *parser); |
---|
666 | |
---|
667 | static int |
---|
668 | yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal); |
---|
669 | |
---|
670 | static int |
---|
671 | yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single); |
---|
672 | |
---|
673 | static int |
---|
674 | yaml_parser_fetch_plain_scalar(yaml_parser_t *parser); |
---|
675 | |
---|
676 | /* |
---|
677 | * Token scanners. |
---|
678 | */ |
---|
679 | |
---|
680 | static int |
---|
681 | yaml_parser_scan_to_next_token(yaml_parser_t *parser); |
---|
682 | |
---|
683 | static int |
---|
684 | yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token); |
---|
685 | |
---|
686 | static int |
---|
687 | yaml_parser_scan_directive_name(yaml_parser_t *parser, |
---|
688 | yaml_mark_t start_mark, yaml_char_t **name); |
---|
689 | |
---|
690 | static int |
---|
691 | yaml_parser_scan_version_directive_value(yaml_parser_t *parser, |
---|
692 | yaml_mark_t start_mark, int *major, int *minor); |
---|
693 | |
---|
694 | static int |
---|
695 | yaml_parser_scan_version_directive_number(yaml_parser_t *parser, |
---|
696 | yaml_mark_t start_mark, int *number); |
---|
697 | |
---|
698 | static int |
---|
699 | yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, |
---|
700 | yaml_mark_t mark, yaml_char_t **handle, yaml_char_t **prefix); |
---|
701 | |
---|
702 | static int |
---|
703 | yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, |
---|
704 | yaml_token_type_t type); |
---|
705 | |
---|
706 | static int |
---|
707 | yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token); |
---|
708 | |
---|
709 | static int |
---|
710 | yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, |
---|
711 | yaml_mark_t start_mark, yaml_char_t **handle); |
---|
712 | |
---|
713 | static int |
---|
714 | yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, |
---|
715 | yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri); |
---|
716 | |
---|
717 | static int |
---|
718 | yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, |
---|
719 | yaml_mark_t start_mark, yaml_string_t *string); |
---|
720 | |
---|
721 | static int |
---|
722 | yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, |
---|
723 | int literal); |
---|
724 | |
---|
725 | static int |
---|
726 | yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, |
---|
727 | int *indent, yaml_string_t *breaks, |
---|
728 | yaml_mark_t start_mark, yaml_mark_t *end_mark); |
---|
729 | |
---|
730 | static int |
---|
731 | yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, |
---|
732 | int single); |
---|
733 | |
---|
734 | static int |
---|
735 | yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token); |
---|
736 | |
---|
737 | /* |
---|
738 | * Get the next token. |
---|
739 | */ |
---|
740 | |
---|
741 | YAML_DECLARE(int) |
---|
742 | yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token) |
---|
743 | { |
---|
744 | assert(parser); /* Non-NULL parser object is expected. */ |
---|
745 | assert(token); /* Non-NULL token object is expected. */ |
---|
746 | |
---|
747 | /* Erase the token object. */ |
---|
748 | |
---|
749 | memset(token, 0, sizeof(yaml_token_t)); |
---|
750 | |
---|
751 | /* No tokens after STREAM-END or error. */ |
---|
752 | |
---|
753 | if (parser->stream_end_produced || parser->error) { |
---|
754 | return 1; |
---|
755 | } |
---|
756 | |
---|
757 | /* Ensure that the tokens queue contains enough tokens. */ |
---|
758 | |
---|
759 | if (!parser->token_available) { |
---|
760 | if (!yaml_parser_fetch_more_tokens(parser)) |
---|
761 | return 0; |
---|
762 | } |
---|
763 | |
---|
764 | /* Fetch the next token from the queue. */ |
---|
765 | |
---|
766 | *token = DEQUEUE(parser, parser->tokens); |
---|
767 | parser->token_available = 0; |
---|
768 | parser->tokens_parsed ++; |
---|
769 | |
---|
770 | if (token->type == YAML_STREAM_END_TOKEN) { |
---|
771 | parser->stream_end_produced = 1; |
---|
772 | } |
---|
773 | |
---|
774 | return 1; |
---|
775 | } |
---|
776 | |
---|
777 | /* |
---|
778 | * Set the scanner error and return 0. |
---|
779 | */ |
---|
780 | |
---|
781 | static int |
---|
782 | yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, |
---|
783 | yaml_mark_t context_mark, const char *problem) |
---|
784 | { |
---|
785 | parser->error = YAML_SCANNER_ERROR; |
---|
786 | parser->context = context; |
---|
787 | parser->context_mark = context_mark; |
---|
788 | parser->problem = problem; |
---|
789 | parser->problem_mark = parser->mark; |
---|
790 | |
---|
791 | return 0; |
---|
792 | } |
---|
793 | |
---|
794 | /* |
---|
795 | * Ensure that the tokens queue contains at least one token which can be |
---|
796 | * returned to the Parser. |
---|
797 | */ |
---|
798 | |
---|
799 | YAML_DECLARE(int) |
---|
800 | yaml_parser_fetch_more_tokens(yaml_parser_t *parser) |
---|
801 | { |
---|
802 | int need_more_tokens; |
---|
803 | |
---|
804 | /* While we need more tokens to fetch, do it. */ |
---|
805 | |
---|
806 | while (1) |
---|
807 | { |
---|
808 | /* |
---|
809 | * Check if we really need to fetch more tokens. |
---|
810 | */ |
---|
811 | |
---|
812 | need_more_tokens = 0; |
---|
813 | |
---|
814 | if (parser->tokens.head == parser->tokens.tail) |
---|
815 | { |
---|
816 | /* Queue is empty. */ |
---|
817 | |
---|
818 | need_more_tokens = 1; |
---|
819 | } |
---|
820 | else |
---|
821 | { |
---|
822 | yaml_simple_key_t *simple_key; |
---|
823 | |
---|
824 | /* Check if any potential simple key may occupy the head position. */ |
---|
825 | |
---|
826 | if (!yaml_parser_stale_simple_keys(parser)) |
---|
827 | return 0; |
---|
828 | |
---|
829 | for (simple_key = parser->simple_keys.start; |
---|
830 | simple_key != parser->simple_keys.top; simple_key++) { |
---|
831 | if (simple_key->possible |
---|
832 | && simple_key->token_number == parser->tokens_parsed) { |
---|
833 | need_more_tokens = 1; |
---|
834 | break; |
---|
835 | } |
---|
836 | } |
---|
837 | } |
---|
838 | |
---|
839 | /* We are finished. */ |
---|
840 | |
---|
841 | if (!need_more_tokens) |
---|
842 | break; |
---|
843 | |
---|
844 | /* Fetch the next token. */ |
---|
845 | |
---|
846 | if (!yaml_parser_fetch_next_token(parser)) |
---|
847 | return 0; |
---|
848 | } |
---|
849 | |
---|
850 | parser->token_available = 1; |
---|
851 | |
---|
852 | return 1; |
---|
853 | } |
---|
854 | |
---|
855 | /* |
---|
856 | * The dispatcher for token fetchers. |
---|
857 | */ |
---|
858 | |
---|
859 | static int |
---|
860 | yaml_parser_fetch_next_token(yaml_parser_t *parser) |
---|
861 | { |
---|
862 | /* Ensure that the buffer is initialized. */ |
---|
863 | |
---|
864 | if (!CACHE(parser, 1)) |
---|
865 | return 0; |
---|
866 | |
---|
867 | /* Check if we just started scanning. Fetch STREAM-START then. */ |
---|
868 | |
---|
869 | if (!parser->stream_start_produced) |
---|
870 | return yaml_parser_fetch_stream_start(parser); |
---|
871 | |
---|
872 | /* Eat whitespaces and comments until we reach the next token. */ |
---|
873 | |
---|
874 | if (!yaml_parser_scan_to_next_token(parser)) |
---|
875 | return 0; |
---|
876 | |
---|
877 | /* Remove obsolete potential simple keys. */ |
---|
878 | |
---|
879 | if (!yaml_parser_stale_simple_keys(parser)) |
---|
880 | return 0; |
---|
881 | |
---|
882 | /* Check the indentation level against the current column. */ |
---|
883 | |
---|
884 | if (!yaml_parser_unroll_indent(parser, parser->mark.column)) |
---|
885 | return 0; |
---|
886 | |
---|
887 | /* |
---|
888 | * Ensure that the buffer contains at least 4 characters. 4 is the length |
---|
889 | * of the longest indicators ('--- ' and '... '). |
---|
890 | */ |
---|
891 | |
---|
892 | if (!CACHE(parser, 4)) |
---|
893 | return 0; |
---|
894 | |
---|
895 | /* Is it the end of the stream? */ |
---|
896 | |
---|
897 | if (IS_Z(parser->buffer)) |
---|
898 | return yaml_parser_fetch_stream_end(parser); |
---|
899 | |
---|
900 | /* Is it a directive? */ |
---|
901 | |
---|
902 | if (parser->mark.column == 0 && CHECK(parser->buffer, '%')) |
---|
903 | return yaml_parser_fetch_directive(parser); |
---|
904 | |
---|
905 | /* Is it the document start indicator? */ |
---|
906 | |
---|
907 | if (parser->mark.column == 0 |
---|
908 | && CHECK_AT(parser->buffer, '-', 0) |
---|
909 | && CHECK_AT(parser->buffer, '-', 1) |
---|
910 | && CHECK_AT(parser->buffer, '-', 2) |
---|
911 | && IS_BLANKZ_AT(parser->buffer, 3)) |
---|
912 | return yaml_parser_fetch_document_indicator(parser, |
---|
913 | YAML_DOCUMENT_START_TOKEN); |
---|
914 | |
---|
915 | /* Is it the document end indicator? */ |
---|
916 | |
---|
917 | if (parser->mark.column == 0 |
---|
918 | && CHECK_AT(parser->buffer, '.', 0) |
---|
919 | && CHECK_AT(parser->buffer, '.', 1) |
---|
920 | && CHECK_AT(parser->buffer, '.', 2) |
---|
921 | && IS_BLANKZ_AT(parser->buffer, 3)) |
---|
922 | return yaml_parser_fetch_document_indicator(parser, |
---|
923 | YAML_DOCUMENT_END_TOKEN); |
---|
924 | |
---|
925 | /* Is it the flow sequence start indicator? */ |
---|
926 | |
---|
927 | if (CHECK(parser->buffer, '[')) |
---|
928 | return yaml_parser_fetch_flow_collection_start(parser, |
---|
929 | YAML_FLOW_SEQUENCE_START_TOKEN); |
---|
930 | |
---|
931 | /* Is it the flow mapping start indicator? */ |
---|
932 | |
---|
933 | if (CHECK(parser->buffer, '{')) |
---|
934 | return yaml_parser_fetch_flow_collection_start(parser, |
---|
935 | YAML_FLOW_MAPPING_START_TOKEN); |
---|
936 | |
---|
937 | /* Is it the flow sequence end indicator? */ |
---|
938 | |
---|
939 | if (CHECK(parser->buffer, ']')) |
---|
940 | return yaml_parser_fetch_flow_collection_end(parser, |
---|
941 | YAML_FLOW_SEQUENCE_END_TOKEN); |
---|
942 | |
---|
943 | /* Is it the flow mapping end indicator? */ |
---|
944 | |
---|
945 | if (CHECK(parser->buffer, '}')) |
---|
946 | return yaml_parser_fetch_flow_collection_end(parser, |
---|
947 | YAML_FLOW_MAPPING_END_TOKEN); |
---|
948 | |
---|
949 | /* Is it the flow entry indicator? */ |
---|
950 | |
---|
951 | if (CHECK(parser->buffer, ',')) |
---|
952 | return yaml_parser_fetch_flow_entry(parser); |
---|
953 | |
---|
954 | /* Is it the block entry indicator? */ |
---|
955 | |
---|
956 | if (CHECK(parser->buffer, '-') && IS_BLANKZ_AT(parser->buffer, 1)) |
---|
957 | return yaml_parser_fetch_block_entry(parser); |
---|
958 | |
---|
959 | /* Is it the key indicator? */ |
---|
960 | |
---|
961 | if (CHECK(parser->buffer, '?') |
---|
962 | && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) |
---|
963 | return yaml_parser_fetch_key(parser); |
---|
964 | |
---|
965 | /* Is it the value indicator? */ |
---|
966 | |
---|
967 | if (CHECK(parser->buffer, ':') |
---|
968 | && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) |
---|
969 | return yaml_parser_fetch_value(parser); |
---|
970 | |
---|
971 | /* Is it an alias? */ |
---|
972 | |
---|
973 | if (CHECK(parser->buffer, '*')) |
---|
974 | return yaml_parser_fetch_anchor(parser, YAML_ALIAS_TOKEN); |
---|
975 | |
---|
976 | /* Is it an anchor? */ |
---|
977 | |
---|
978 | if (CHECK(parser->buffer, '&')) |
---|
979 | return yaml_parser_fetch_anchor(parser, YAML_ANCHOR_TOKEN); |
---|
980 | |
---|
981 | /* Is it a tag? */ |
---|
982 | |
---|
983 | if (CHECK(parser->buffer, '!')) |
---|
984 | return yaml_parser_fetch_tag(parser); |
---|
985 | |
---|
986 | /* Is it a literal scalar? */ |
---|
987 | |
---|
988 | if (CHECK(parser->buffer, '|') && !parser->flow_level) |
---|
989 | return yaml_parser_fetch_block_scalar(parser, 1); |
---|
990 | |
---|
991 | /* Is it a folded scalar? */ |
---|
992 | |
---|
993 | if (CHECK(parser->buffer, '>') && !parser->flow_level) |
---|
994 | return yaml_parser_fetch_block_scalar(parser, 0); |
---|
995 | |
---|
996 | /* Is it a single-quoted scalar? */ |
---|
997 | |
---|
998 | if (CHECK(parser->buffer, '\'')) |
---|
999 | return yaml_parser_fetch_flow_scalar(parser, 1); |
---|
1000 | |
---|
1001 | /* Is it a double-quoted scalar? */ |
---|
1002 | |
---|
1003 | if (CHECK(parser->buffer, '"')) |
---|
1004 | return yaml_parser_fetch_flow_scalar(parser, 0); |
---|
1005 | |
---|
1006 | /* |
---|
1007 | * Is it a plain scalar? |
---|
1008 | * |
---|
1009 | * A plain scalar may start with any non-blank characters except |
---|
1010 | * |
---|
1011 | * '-', '?', ':', ',', '[', ']', '{', '}', |
---|
1012 | * '#', '&', '*', '!', '|', '>', '\'', '\"', |
---|
1013 | * '%', '@', '`'. |
---|
1014 | * |
---|
1015 | * In the block context (and, for the '-' indicator, in the flow context |
---|
1016 | * too), it may also start with the characters |
---|
1017 | * |
---|
1018 | * '-', '?', ':' |
---|
1019 | * |
---|
1020 | * if it is followed by a non-space character. |
---|
1021 | * |
---|
1022 | * The last rule is more restrictive than the specification requires. |
---|
1023 | */ |
---|
1024 | |
---|
1025 | if (!(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '-') |
---|
1026 | || CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':') |
---|
1027 | || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '[') |
---|
1028 | || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') |
---|
1029 | || CHECK(parser->buffer, '}') || CHECK(parser->buffer, '#') |
---|
1030 | || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '*') |
---|
1031 | || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '|') |
---|
1032 | || CHECK(parser->buffer, '>') || CHECK(parser->buffer, '\'') |
---|
1033 | || CHECK(parser->buffer, '"') || CHECK(parser->buffer, '%') |
---|
1034 | || CHECK(parser->buffer, '@') || CHECK(parser->buffer, '`')) || |
---|
1035 | (CHECK(parser->buffer, '-') && !IS_BLANK_AT(parser->buffer, 1)) || |
---|
1036 | (!parser->flow_level && |
---|
1037 | (CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':')) |
---|
1038 | && !IS_BLANKZ_AT(parser->buffer, 1))) |
---|
1039 | return yaml_parser_fetch_plain_scalar(parser); |
---|
1040 | |
---|
1041 | /* |
---|
1042 | * If we don't determine the token type so far, it is an error. |
---|
1043 | */ |
---|
1044 | |
---|
1045 | return yaml_parser_set_scanner_error(parser, |
---|
1046 | "while scanning for the next token", parser->mark, |
---|
1047 | "found character that cannot start any token"); |
---|
1048 | } |
---|
1049 | |
---|
1050 | /* |
---|
1051 | * Check the list of potential simple keys and remove the positions that |
---|
1052 | * cannot contain simple keys anymore. |
---|
1053 | */ |
---|
1054 | |
---|
1055 | static int |
---|
1056 | yaml_parser_stale_simple_keys(yaml_parser_t *parser) |
---|
1057 | { |
---|
1058 | yaml_simple_key_t *simple_key; |
---|
1059 | |
---|
1060 | /* Check for a potential simple key for each flow level. */ |
---|
1061 | |
---|
1062 | for (simple_key = parser->simple_keys.start; |
---|
1063 | simple_key != parser->simple_keys.top; simple_key ++) |
---|
1064 | { |
---|
1065 | /* |
---|
1066 | * The specification requires that a simple key |
---|
1067 | * |
---|
1068 | * - is limited to a single line, |
---|
1069 | * - is shorter than 1024 characters. |
---|
1070 | */ |
---|
1071 | |
---|
1072 | if (simple_key->possible |
---|
1073 | && (simple_key->mark.line < parser->mark.line |
---|
1074 | || simple_key->mark.index+1024 < parser->mark.index)) { |
---|
1075 | |
---|
1076 | /* Check if the potential simple key to be removed is required. */ |
---|
1077 | |
---|
1078 | if (simple_key->required) { |
---|
1079 | return yaml_parser_set_scanner_error(parser, |
---|
1080 | "while scanning a simple key", simple_key->mark, |
---|
1081 | "could not found expected ':'"); |
---|
1082 | } |
---|
1083 | |
---|
1084 | simple_key->possible = 0; |
---|
1085 | } |
---|
1086 | } |
---|
1087 | |
---|
1088 | return 1; |
---|
1089 | } |
---|
1090 | |
---|
1091 | /* |
---|
1092 | * Check if a simple key may start at the current position and add it if |
---|
1093 | * needed. |
---|
1094 | */ |
---|
1095 | |
---|
1096 | static int |
---|
1097 | yaml_parser_save_simple_key(yaml_parser_t *parser) |
---|
1098 | { |
---|
1099 | /* |
---|
1100 | * A simple key is required at the current position if the scanner is in |
---|
1101 | * the block context and the current column coincides with the indentation |
---|
1102 | * level. |
---|
1103 | */ |
---|
1104 | |
---|
1105 | int required = (!parser->flow_level |
---|
1106 | && parser->indent == (int)parser->mark.column); |
---|
1107 | |
---|
1108 | /* |
---|
1109 | * A simple key is required only when it is the first token in the current |
---|
1110 | * line. Therefore it is always allowed. But we add a check anyway. |
---|
1111 | */ |
---|
1112 | |
---|
1113 | assert(parser->simple_key_allowed || !required); /* Impossible. */ |
---|
1114 | |
---|
1115 | /* |
---|
1116 | * If the current position may start a simple key, save it. |
---|
1117 | */ |
---|
1118 | |
---|
1119 | if (parser->simple_key_allowed) |
---|
1120 | { |
---|
1121 | yaml_simple_key_t simple_key = { 1, required, |
---|
1122 | parser->tokens_parsed + parser->tokens.tail - parser->tokens.head, |
---|
1123 | { 0, 0, 0 } }; |
---|
1124 | simple_key.mark = parser->mark; |
---|
1125 | |
---|
1126 | if (!yaml_parser_remove_simple_key(parser)) return 0; |
---|
1127 | |
---|
1128 | *(parser->simple_keys.top-1) = simple_key; |
---|
1129 | } |
---|
1130 | |
---|
1131 | return 1; |
---|
1132 | } |
---|
1133 | |
---|
1134 | /* |
---|
1135 | * Remove a potential simple key at the current flow level. |
---|
1136 | */ |
---|
1137 | |
---|
1138 | static int |
---|
1139 | yaml_parser_remove_simple_key(yaml_parser_t *parser) |
---|
1140 | { |
---|
1141 | yaml_simple_key_t *simple_key = parser->simple_keys.top-1; |
---|
1142 | |
---|
1143 | if (simple_key->possible) |
---|
1144 | { |
---|
1145 | /* If the key is required, it is an error. */ |
---|
1146 | |
---|
1147 | if (simple_key->required) { |
---|
1148 | return yaml_parser_set_scanner_error(parser, |
---|
1149 | "while scanning a simple key", simple_key->mark, |
---|
1150 | "could not found expected ':'"); |
---|
1151 | } |
---|
1152 | } |
---|
1153 | |
---|
1154 | /* Remove the key from the stack. */ |
---|
1155 | |
---|
1156 | simple_key->possible = 0; |
---|
1157 | |
---|
1158 | return 1; |
---|
1159 | } |
---|
1160 | |
---|
1161 | /* |
---|
1162 | * Increase the flow level and resize the simple key list if needed. |
---|
1163 | */ |
---|
1164 | |
---|
1165 | static int |
---|
1166 | yaml_parser_increase_flow_level(yaml_parser_t *parser) |
---|
1167 | { |
---|
1168 | yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } }; |
---|
1169 | |
---|
1170 | /* Reset the simple key on the next level. */ |
---|
1171 | |
---|
1172 | if (!PUSH(parser, parser->simple_keys, empty_simple_key)) |
---|
1173 | return 0; |
---|
1174 | |
---|
1175 | /* Increase the flow level. */ |
---|
1176 | |
---|
1177 | parser->flow_level++; |
---|
1178 | |
---|
1179 | return 1; |
---|
1180 | } |
---|
1181 | |
---|
1182 | /* |
---|
1183 | * Decrease the flow level. |
---|
1184 | */ |
---|
1185 | |
---|
1186 | static int |
---|
1187 | yaml_parser_decrease_flow_level(yaml_parser_t *parser) |
---|
1188 | { |
---|
1189 | yaml_simple_key_t dummy_key; /* Used to eliminate a compiler warning. */ |
---|
1190 | |
---|
1191 | if (parser->flow_level) { |
---|
1192 | parser->flow_level --; |
---|
1193 | dummy_key = POP(parser, parser->simple_keys); |
---|
1194 | } |
---|
1195 | |
---|
1196 | return 1; |
---|
1197 | } |
---|
1198 | |
---|
1199 | /* |
---|
1200 | * Push the current indentation level to the stack and set the new level |
---|
1201 | * the current column is greater than the indentation level. In this case, |
---|
1202 | * append or insert the specified token into the token queue. |
---|
1203 | * |
---|
1204 | */ |
---|
1205 | |
---|
1206 | static int |
---|
1207 | yaml_parser_roll_indent(yaml_parser_t *parser, int column, |
---|
1208 | int number, yaml_token_type_t type, yaml_mark_t mark) |
---|
1209 | { |
---|
1210 | yaml_token_t token; |
---|
1211 | |
---|
1212 | /* In the flow context, do nothing. */ |
---|
1213 | |
---|
1214 | if (parser->flow_level) |
---|
1215 | return 1; |
---|
1216 | |
---|
1217 | if (parser->indent < column) |
---|
1218 | { |
---|
1219 | /* |
---|
1220 | * Push the current indentation level to the stack and set the new |
---|
1221 | * indentation level. |
---|
1222 | */ |
---|
1223 | |
---|
1224 | if (!PUSH(parser, parser->indents, parser->indent)) |
---|
1225 | return 0; |
---|
1226 | |
---|
1227 | parser->indent = column; |
---|
1228 | |
---|
1229 | /* Create a token and insert it into the queue. */ |
---|
1230 | |
---|
1231 | TOKEN_INIT(token, type, mark, mark); |
---|
1232 | |
---|
1233 | if (number == -1) { |
---|
1234 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1235 | return 0; |
---|
1236 | } |
---|
1237 | else { |
---|
1238 | if (!QUEUE_INSERT(parser, |
---|
1239 | parser->tokens, number - parser->tokens_parsed, token)) |
---|
1240 | return 0; |
---|
1241 | } |
---|
1242 | } |
---|
1243 | |
---|
1244 | return 1; |
---|
1245 | } |
---|
1246 | |
---|
1247 | /* |
---|
1248 | * Pop indentation levels from the indents stack until the current level |
---|
1249 | * becomes less or equal to the column. For each intendation level, append |
---|
1250 | * the BLOCK-END token. |
---|
1251 | */ |
---|
1252 | |
---|
1253 | |
---|
1254 | static int |
---|
1255 | yaml_parser_unroll_indent(yaml_parser_t *parser, int column) |
---|
1256 | { |
---|
1257 | yaml_token_t token; |
---|
1258 | |
---|
1259 | /* In the flow context, do nothing. */ |
---|
1260 | |
---|
1261 | if (parser->flow_level) |
---|
1262 | return 1; |
---|
1263 | |
---|
1264 | /* Loop through the intendation levels in the stack. */ |
---|
1265 | |
---|
1266 | while (parser->indent > column) |
---|
1267 | { |
---|
1268 | /* Create a token and append it to the queue. */ |
---|
1269 | |
---|
1270 | TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark); |
---|
1271 | |
---|
1272 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1273 | return 0; |
---|
1274 | |
---|
1275 | /* Pop the indentation level. */ |
---|
1276 | |
---|
1277 | parser->indent = POP(parser, parser->indents); |
---|
1278 | } |
---|
1279 | |
---|
1280 | return 1; |
---|
1281 | } |
---|
1282 | |
---|
1283 | /* |
---|
1284 | * Initialize the scanner and produce the STREAM-START token. |
---|
1285 | */ |
---|
1286 | |
---|
1287 | static int |
---|
1288 | yaml_parser_fetch_stream_start(yaml_parser_t *parser) |
---|
1289 | { |
---|
1290 | yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } }; |
---|
1291 | yaml_token_t token; |
---|
1292 | |
---|
1293 | /* Set the initial indentation. */ |
---|
1294 | |
---|
1295 | parser->indent = -1; |
---|
1296 | |
---|
1297 | /* Initialize the simple key stack. */ |
---|
1298 | |
---|
1299 | if (!PUSH(parser, parser->simple_keys, simple_key)) |
---|
1300 | return 0; |
---|
1301 | |
---|
1302 | /* A simple key is allowed at the beginning of the stream. */ |
---|
1303 | |
---|
1304 | parser->simple_key_allowed = 1; |
---|
1305 | |
---|
1306 | /* We have started. */ |
---|
1307 | |
---|
1308 | parser->stream_start_produced = 1; |
---|
1309 | |
---|
1310 | /* Create the STREAM-START token and append it to the queue. */ |
---|
1311 | |
---|
1312 | STREAM_START_TOKEN_INIT(token, parser->encoding, |
---|
1313 | parser->mark, parser->mark); |
---|
1314 | |
---|
1315 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1316 | return 0; |
---|
1317 | |
---|
1318 | return 1; |
---|
1319 | } |
---|
1320 | |
---|
1321 | /* |
---|
1322 | * Produce the STREAM-END token and shut down the scanner. |
---|
1323 | */ |
---|
1324 | |
---|
1325 | static int |
---|
1326 | yaml_parser_fetch_stream_end(yaml_parser_t *parser) |
---|
1327 | { |
---|
1328 | yaml_token_t token; |
---|
1329 | |
---|
1330 | /* Force new line. */ |
---|
1331 | |
---|
1332 | if (parser->mark.column != 0) { |
---|
1333 | parser->mark.column = 0; |
---|
1334 | parser->mark.line ++; |
---|
1335 | } |
---|
1336 | |
---|
1337 | /* Reset the indentation level. */ |
---|
1338 | |
---|
1339 | if (!yaml_parser_unroll_indent(parser, -1)) |
---|
1340 | return 0; |
---|
1341 | |
---|
1342 | /* Reset simple keys. */ |
---|
1343 | |
---|
1344 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1345 | return 0; |
---|
1346 | |
---|
1347 | parser->simple_key_allowed = 0; |
---|
1348 | |
---|
1349 | /* Create the STREAM-END token and append it to the queue. */ |
---|
1350 | |
---|
1351 | STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark); |
---|
1352 | |
---|
1353 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1354 | return 0; |
---|
1355 | |
---|
1356 | return 1; |
---|
1357 | } |
---|
1358 | |
---|
1359 | /* |
---|
1360 | * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token. |
---|
1361 | */ |
---|
1362 | |
---|
1363 | static int |
---|
1364 | yaml_parser_fetch_directive(yaml_parser_t *parser) |
---|
1365 | { |
---|
1366 | yaml_token_t token; |
---|
1367 | |
---|
1368 | /* Reset the indentation level. */ |
---|
1369 | |
---|
1370 | if (!yaml_parser_unroll_indent(parser, -1)) |
---|
1371 | return 0; |
---|
1372 | |
---|
1373 | /* Reset simple keys. */ |
---|
1374 | |
---|
1375 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1376 | return 0; |
---|
1377 | |
---|
1378 | parser->simple_key_allowed = 0; |
---|
1379 | |
---|
1380 | /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */ |
---|
1381 | |
---|
1382 | if (!yaml_parser_scan_directive(parser, &token)) |
---|
1383 | return 0; |
---|
1384 | |
---|
1385 | /* Append the token to the queue. */ |
---|
1386 | |
---|
1387 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1388 | yaml_token_delete(&token); |
---|
1389 | return 0; |
---|
1390 | } |
---|
1391 | |
---|
1392 | return 1; |
---|
1393 | } |
---|
1394 | |
---|
1395 | /* |
---|
1396 | * Produce the DOCUMENT-START or DOCUMENT-END token. |
---|
1397 | */ |
---|
1398 | |
---|
1399 | static int |
---|
1400 | yaml_parser_fetch_document_indicator(yaml_parser_t *parser, |
---|
1401 | yaml_token_type_t type) |
---|
1402 | { |
---|
1403 | yaml_mark_t start_mark, end_mark; |
---|
1404 | yaml_token_t token; |
---|
1405 | |
---|
1406 | /* Reset the indentation level. */ |
---|
1407 | |
---|
1408 | if (!yaml_parser_unroll_indent(parser, -1)) |
---|
1409 | return 0; |
---|
1410 | |
---|
1411 | /* Reset simple keys. */ |
---|
1412 | |
---|
1413 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1414 | return 0; |
---|
1415 | |
---|
1416 | parser->simple_key_allowed = 0; |
---|
1417 | |
---|
1418 | /* Consume the token. */ |
---|
1419 | |
---|
1420 | start_mark = parser->mark; |
---|
1421 | |
---|
1422 | SKIP(parser); |
---|
1423 | SKIP(parser); |
---|
1424 | SKIP(parser); |
---|
1425 | |
---|
1426 | end_mark = parser->mark; |
---|
1427 | |
---|
1428 | /* Create the DOCUMENT-START or DOCUMENT-END token. */ |
---|
1429 | |
---|
1430 | TOKEN_INIT(token, type, start_mark, end_mark); |
---|
1431 | |
---|
1432 | /* Append the token to the queue. */ |
---|
1433 | |
---|
1434 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1435 | return 0; |
---|
1436 | |
---|
1437 | return 1; |
---|
1438 | } |
---|
1439 | |
---|
1440 | /* |
---|
1441 | * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token. |
---|
1442 | */ |
---|
1443 | |
---|
1444 | static int |
---|
1445 | yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, |
---|
1446 | yaml_token_type_t type) |
---|
1447 | { |
---|
1448 | yaml_mark_t start_mark, end_mark; |
---|
1449 | yaml_token_t token; |
---|
1450 | |
---|
1451 | /* The indicators '[' and '{' may start a simple key. */ |
---|
1452 | |
---|
1453 | if (!yaml_parser_save_simple_key(parser)) |
---|
1454 | return 0; |
---|
1455 | |
---|
1456 | /* Increase the flow level. */ |
---|
1457 | |
---|
1458 | if (!yaml_parser_increase_flow_level(parser)) |
---|
1459 | return 0; |
---|
1460 | |
---|
1461 | /* A simple key may follow the indicators '[' and '{'. */ |
---|
1462 | |
---|
1463 | parser->simple_key_allowed = 1; |
---|
1464 | |
---|
1465 | /* Consume the token. */ |
---|
1466 | |
---|
1467 | start_mark = parser->mark; |
---|
1468 | SKIP(parser); |
---|
1469 | end_mark = parser->mark; |
---|
1470 | |
---|
1471 | /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */ |
---|
1472 | |
---|
1473 | TOKEN_INIT(token, type, start_mark, end_mark); |
---|
1474 | |
---|
1475 | /* Append the token to the queue. */ |
---|
1476 | |
---|
1477 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1478 | return 0; |
---|
1479 | |
---|
1480 | return 1; |
---|
1481 | } |
---|
1482 | |
---|
1483 | /* |
---|
1484 | * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token. |
---|
1485 | */ |
---|
1486 | |
---|
1487 | static int |
---|
1488 | yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, |
---|
1489 | yaml_token_type_t type) |
---|
1490 | { |
---|
1491 | yaml_mark_t start_mark, end_mark; |
---|
1492 | yaml_token_t token; |
---|
1493 | |
---|
1494 | /* Reset any potential simple key on the current flow level. */ |
---|
1495 | |
---|
1496 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1497 | return 0; |
---|
1498 | |
---|
1499 | /* Decrease the flow level. */ |
---|
1500 | |
---|
1501 | if (!yaml_parser_decrease_flow_level(parser)) |
---|
1502 | return 0; |
---|
1503 | |
---|
1504 | /* No simple keys after the indicators ']' and '}'. */ |
---|
1505 | |
---|
1506 | parser->simple_key_allowed = 0; |
---|
1507 | |
---|
1508 | /* Consume the token. */ |
---|
1509 | |
---|
1510 | start_mark = parser->mark; |
---|
1511 | SKIP(parser); |
---|
1512 | end_mark = parser->mark; |
---|
1513 | |
---|
1514 | /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */ |
---|
1515 | |
---|
1516 | TOKEN_INIT(token, type, start_mark, end_mark); |
---|
1517 | |
---|
1518 | /* Append the token to the queue. */ |
---|
1519 | |
---|
1520 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1521 | return 0; |
---|
1522 | |
---|
1523 | return 1; |
---|
1524 | } |
---|
1525 | |
---|
1526 | /* |
---|
1527 | * Produce the FLOW-ENTRY token. |
---|
1528 | */ |
---|
1529 | |
---|
1530 | static int |
---|
1531 | yaml_parser_fetch_flow_entry(yaml_parser_t *parser) |
---|
1532 | { |
---|
1533 | yaml_mark_t start_mark, end_mark; |
---|
1534 | yaml_token_t token; |
---|
1535 | |
---|
1536 | /* Reset any potential simple keys on the current flow level. */ |
---|
1537 | |
---|
1538 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1539 | return 0; |
---|
1540 | |
---|
1541 | /* Simple keys are allowed after ','. */ |
---|
1542 | |
---|
1543 | parser->simple_key_allowed = 1; |
---|
1544 | |
---|
1545 | /* Consume the token. */ |
---|
1546 | |
---|
1547 | start_mark = parser->mark; |
---|
1548 | SKIP(parser); |
---|
1549 | end_mark = parser->mark; |
---|
1550 | |
---|
1551 | /* Create the FLOW-ENTRY token and append it to the queue. */ |
---|
1552 | |
---|
1553 | TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark); |
---|
1554 | |
---|
1555 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1556 | return 0; |
---|
1557 | |
---|
1558 | return 1; |
---|
1559 | } |
---|
1560 | |
---|
1561 | /* |
---|
1562 | * Produce the BLOCK-ENTRY token. |
---|
1563 | */ |
---|
1564 | |
---|
1565 | static int |
---|
1566 | yaml_parser_fetch_block_entry(yaml_parser_t *parser) |
---|
1567 | { |
---|
1568 | yaml_mark_t start_mark, end_mark; |
---|
1569 | yaml_token_t token; |
---|
1570 | |
---|
1571 | /* Check if the scanner is in the block context. */ |
---|
1572 | |
---|
1573 | if (!parser->flow_level) |
---|
1574 | { |
---|
1575 | /* Check if we are allowed to start a new entry. */ |
---|
1576 | |
---|
1577 | if (!parser->simple_key_allowed) { |
---|
1578 | return yaml_parser_set_scanner_error(parser, NULL, parser->mark, |
---|
1579 | "block sequence entries are not allowed in this context"); |
---|
1580 | } |
---|
1581 | |
---|
1582 | /* Add the BLOCK-SEQUENCE-START token if needed. */ |
---|
1583 | |
---|
1584 | if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, |
---|
1585 | YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark)) |
---|
1586 | return 0; |
---|
1587 | } |
---|
1588 | else |
---|
1589 | { |
---|
1590 | /* |
---|
1591 | * It is an error for the '-' indicator to occur in the flow context, |
---|
1592 | * but we let the Parser detect and report about it because the Parser |
---|
1593 | * is able to point to the context. |
---|
1594 | */ |
---|
1595 | } |
---|
1596 | |
---|
1597 | /* Reset any potential simple keys on the current flow level. */ |
---|
1598 | |
---|
1599 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1600 | return 0; |
---|
1601 | |
---|
1602 | /* Simple keys are allowed after '-'. */ |
---|
1603 | |
---|
1604 | parser->simple_key_allowed = 1; |
---|
1605 | |
---|
1606 | /* Consume the token. */ |
---|
1607 | |
---|
1608 | start_mark = parser->mark; |
---|
1609 | SKIP(parser); |
---|
1610 | end_mark = parser->mark; |
---|
1611 | |
---|
1612 | /* Create the BLOCK-ENTRY token and append it to the queue. */ |
---|
1613 | |
---|
1614 | TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark); |
---|
1615 | |
---|
1616 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1617 | return 0; |
---|
1618 | |
---|
1619 | return 1; |
---|
1620 | } |
---|
1621 | |
---|
1622 | /* |
---|
1623 | * Produce the KEY token. |
---|
1624 | */ |
---|
1625 | |
---|
1626 | static int |
---|
1627 | yaml_parser_fetch_key(yaml_parser_t *parser) |
---|
1628 | { |
---|
1629 | yaml_mark_t start_mark, end_mark; |
---|
1630 | yaml_token_t token; |
---|
1631 | |
---|
1632 | /* In the block context, additional checks are required. */ |
---|
1633 | |
---|
1634 | if (!parser->flow_level) |
---|
1635 | { |
---|
1636 | /* Check if we are allowed to start a new key (not nessesary simple). */ |
---|
1637 | |
---|
1638 | if (!parser->simple_key_allowed) { |
---|
1639 | return yaml_parser_set_scanner_error(parser, NULL, parser->mark, |
---|
1640 | "mapping keys are not allowed in this context"); |
---|
1641 | } |
---|
1642 | |
---|
1643 | /* Add the BLOCK-MAPPING-START token if needed. */ |
---|
1644 | |
---|
1645 | if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, |
---|
1646 | YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) |
---|
1647 | return 0; |
---|
1648 | } |
---|
1649 | |
---|
1650 | /* Reset any potential simple keys on the current flow level. */ |
---|
1651 | |
---|
1652 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1653 | return 0; |
---|
1654 | |
---|
1655 | /* Simple keys are allowed after '?' in the block context. */ |
---|
1656 | |
---|
1657 | parser->simple_key_allowed = (!parser->flow_level); |
---|
1658 | |
---|
1659 | /* Consume the token. */ |
---|
1660 | |
---|
1661 | start_mark = parser->mark; |
---|
1662 | SKIP(parser); |
---|
1663 | end_mark = parser->mark; |
---|
1664 | |
---|
1665 | /* Create the KEY token and append it to the queue. */ |
---|
1666 | |
---|
1667 | TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark); |
---|
1668 | |
---|
1669 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1670 | return 0; |
---|
1671 | |
---|
1672 | return 1; |
---|
1673 | } |
---|
1674 | |
---|
1675 | /* |
---|
1676 | * Produce the VALUE token. |
---|
1677 | */ |
---|
1678 | |
---|
1679 | static int |
---|
1680 | yaml_parser_fetch_value(yaml_parser_t *parser) |
---|
1681 | { |
---|
1682 | yaml_mark_t start_mark, end_mark; |
---|
1683 | yaml_token_t token; |
---|
1684 | yaml_simple_key_t *simple_key = parser->simple_keys.top-1; |
---|
1685 | |
---|
1686 | /* Have we found a simple key? */ |
---|
1687 | |
---|
1688 | if (simple_key->possible) |
---|
1689 | { |
---|
1690 | |
---|
1691 | /* Create the KEY token and insert it into the queue. */ |
---|
1692 | |
---|
1693 | TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark); |
---|
1694 | |
---|
1695 | if (!QUEUE_INSERT(parser, parser->tokens, |
---|
1696 | simple_key->token_number - parser->tokens_parsed, token)) |
---|
1697 | return 0; |
---|
1698 | |
---|
1699 | /* In the block context, we may need to add the BLOCK-MAPPING-START token. */ |
---|
1700 | |
---|
1701 | if (!yaml_parser_roll_indent(parser, simple_key->mark.column, |
---|
1702 | simple_key->token_number, |
---|
1703 | YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark)) |
---|
1704 | return 0; |
---|
1705 | |
---|
1706 | /* Remove the simple key. */ |
---|
1707 | |
---|
1708 | simple_key->possible = 0; |
---|
1709 | |
---|
1710 | /* A simple key cannot follow another simple key. */ |
---|
1711 | |
---|
1712 | parser->simple_key_allowed = 0; |
---|
1713 | } |
---|
1714 | else |
---|
1715 | { |
---|
1716 | /* The ':' indicator follows a complex key. */ |
---|
1717 | |
---|
1718 | /* In the block context, extra checks are required. */ |
---|
1719 | |
---|
1720 | if (!parser->flow_level) |
---|
1721 | { |
---|
1722 | /* Check if we are allowed to start a complex value. */ |
---|
1723 | |
---|
1724 | if (!parser->simple_key_allowed) { |
---|
1725 | return yaml_parser_set_scanner_error(parser, NULL, parser->mark, |
---|
1726 | "mapping values are not allowed in this context"); |
---|
1727 | } |
---|
1728 | |
---|
1729 | /* Add the BLOCK-MAPPING-START token if needed. */ |
---|
1730 | |
---|
1731 | if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, |
---|
1732 | YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) |
---|
1733 | return 0; |
---|
1734 | } |
---|
1735 | |
---|
1736 | /* Simple keys after ':' are allowed in the block context. */ |
---|
1737 | |
---|
1738 | parser->simple_key_allowed = (!parser->flow_level); |
---|
1739 | } |
---|
1740 | |
---|
1741 | /* Consume the token. */ |
---|
1742 | |
---|
1743 | start_mark = parser->mark; |
---|
1744 | SKIP(parser); |
---|
1745 | end_mark = parser->mark; |
---|
1746 | |
---|
1747 | /* Create the VALUE token and append it to the queue. */ |
---|
1748 | |
---|
1749 | TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark); |
---|
1750 | |
---|
1751 | if (!ENQUEUE(parser, parser->tokens, token)) |
---|
1752 | return 0; |
---|
1753 | |
---|
1754 | return 1; |
---|
1755 | } |
---|
1756 | |
---|
1757 | /* |
---|
1758 | * Produce the ALIAS or ANCHOR token. |
---|
1759 | */ |
---|
1760 | |
---|
1761 | static int |
---|
1762 | yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type) |
---|
1763 | { |
---|
1764 | yaml_token_t token; |
---|
1765 | |
---|
1766 | /* An anchor or an alias could be a simple key. */ |
---|
1767 | |
---|
1768 | if (!yaml_parser_save_simple_key(parser)) |
---|
1769 | return 0; |
---|
1770 | |
---|
1771 | /* A simple key cannot follow an anchor or an alias. */ |
---|
1772 | |
---|
1773 | parser->simple_key_allowed = 0; |
---|
1774 | |
---|
1775 | /* Create the ALIAS or ANCHOR token and append it to the queue. */ |
---|
1776 | |
---|
1777 | if (!yaml_parser_scan_anchor(parser, &token, type)) |
---|
1778 | return 0; |
---|
1779 | |
---|
1780 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1781 | yaml_token_delete(&token); |
---|
1782 | return 0; |
---|
1783 | } |
---|
1784 | return 1; |
---|
1785 | } |
---|
1786 | |
---|
1787 | /* |
---|
1788 | * Produce the TAG token. |
---|
1789 | */ |
---|
1790 | |
---|
1791 | static int |
---|
1792 | yaml_parser_fetch_tag(yaml_parser_t *parser) |
---|
1793 | { |
---|
1794 | yaml_token_t token; |
---|
1795 | |
---|
1796 | /* A tag could be a simple key. */ |
---|
1797 | |
---|
1798 | if (!yaml_parser_save_simple_key(parser)) |
---|
1799 | return 0; |
---|
1800 | |
---|
1801 | /* A simple key cannot follow a tag. */ |
---|
1802 | |
---|
1803 | parser->simple_key_allowed = 0; |
---|
1804 | |
---|
1805 | /* Create the TAG token and append it to the queue. */ |
---|
1806 | |
---|
1807 | if (!yaml_parser_scan_tag(parser, &token)) |
---|
1808 | return 0; |
---|
1809 | |
---|
1810 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1811 | yaml_token_delete(&token); |
---|
1812 | return 0; |
---|
1813 | } |
---|
1814 | |
---|
1815 | return 1; |
---|
1816 | } |
---|
1817 | |
---|
1818 | /* |
---|
1819 | * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens. |
---|
1820 | */ |
---|
1821 | |
---|
1822 | static int |
---|
1823 | yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal) |
---|
1824 | { |
---|
1825 | yaml_token_t token; |
---|
1826 | |
---|
1827 | /* Remove any potential simple keys. */ |
---|
1828 | |
---|
1829 | if (!yaml_parser_remove_simple_key(parser)) |
---|
1830 | return 0; |
---|
1831 | |
---|
1832 | /* A simple key may follow a block scalar. */ |
---|
1833 | |
---|
1834 | parser->simple_key_allowed = 1; |
---|
1835 | |
---|
1836 | /* Create the SCALAR token and append it to the queue. */ |
---|
1837 | |
---|
1838 | if (!yaml_parser_scan_block_scalar(parser, &token, literal)) |
---|
1839 | return 0; |
---|
1840 | |
---|
1841 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1842 | yaml_token_delete(&token); |
---|
1843 | return 0; |
---|
1844 | } |
---|
1845 | |
---|
1846 | return 1; |
---|
1847 | } |
---|
1848 | |
---|
1849 | /* |
---|
1850 | * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens. |
---|
1851 | */ |
---|
1852 | |
---|
1853 | static int |
---|
1854 | yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single) |
---|
1855 | { |
---|
1856 | yaml_token_t token; |
---|
1857 | |
---|
1858 | /* A plain scalar could be a simple key. */ |
---|
1859 | |
---|
1860 | if (!yaml_parser_save_simple_key(parser)) |
---|
1861 | return 0; |
---|
1862 | |
---|
1863 | /* A simple key cannot follow a flow scalar. */ |
---|
1864 | |
---|
1865 | parser->simple_key_allowed = 0; |
---|
1866 | |
---|
1867 | /* Create the SCALAR token and append it to the queue. */ |
---|
1868 | |
---|
1869 | if (!yaml_parser_scan_flow_scalar(parser, &token, single)) |
---|
1870 | return 0; |
---|
1871 | |
---|
1872 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1873 | yaml_token_delete(&token); |
---|
1874 | return 0; |
---|
1875 | } |
---|
1876 | |
---|
1877 | return 1; |
---|
1878 | } |
---|
1879 | |
---|
1880 | /* |
---|
1881 | * Produce the SCALAR(...,plain) token. |
---|
1882 | */ |
---|
1883 | |
---|
1884 | static int |
---|
1885 | yaml_parser_fetch_plain_scalar(yaml_parser_t *parser) |
---|
1886 | { |
---|
1887 | yaml_token_t token; |
---|
1888 | |
---|
1889 | /* A plain scalar could be a simple key. */ |
---|
1890 | |
---|
1891 | if (!yaml_parser_save_simple_key(parser)) |
---|
1892 | return 0; |
---|
1893 | |
---|
1894 | /* A simple key cannot follow a flow scalar. */ |
---|
1895 | |
---|
1896 | parser->simple_key_allowed = 0; |
---|
1897 | |
---|
1898 | /* Create the SCALAR token and append it to the queue. */ |
---|
1899 | |
---|
1900 | if (!yaml_parser_scan_plain_scalar(parser, &token)) |
---|
1901 | return 0; |
---|
1902 | |
---|
1903 | if (!ENQUEUE(parser, parser->tokens, token)) { |
---|
1904 | yaml_token_delete(&token); |
---|
1905 | return 0; |
---|
1906 | } |
---|
1907 | |
---|
1908 | return 1; |
---|
1909 | } |
---|
1910 | |
---|
1911 | /* |
---|
1912 | * Eat whitespaces and comments until the next token is found. |
---|
1913 | */ |
---|
1914 | |
---|
1915 | static int |
---|
1916 | yaml_parser_scan_to_next_token(yaml_parser_t *parser) |
---|
1917 | { |
---|
1918 | /* Until the next token is not found. */ |
---|
1919 | |
---|
1920 | while (1) |
---|
1921 | { |
---|
1922 | /* Allow the BOM mark to start a line. */ |
---|
1923 | |
---|
1924 | if (!CACHE(parser, 1)) return 0; |
---|
1925 | |
---|
1926 | if (parser->mark.column == 0 && IS_BOM(parser->buffer)) |
---|
1927 | SKIP(parser); |
---|
1928 | |
---|
1929 | /* |
---|
1930 | * Eat whitespaces. |
---|
1931 | * |
---|
1932 | * Tabs are allowed: |
---|
1933 | * |
---|
1934 | * - in the flow context; |
---|
1935 | * - in the block context, but not at the beginning of the line or |
---|
1936 | * after '-', '?', or ':' (complex value). |
---|
1937 | */ |
---|
1938 | |
---|
1939 | if (!CACHE(parser, 1)) return 0; |
---|
1940 | |
---|
1941 | while (CHECK(parser->buffer,' ') || |
---|
1942 | ((parser->flow_level || !parser->simple_key_allowed) && |
---|
1943 | CHECK(parser->buffer, '\t'))) { |
---|
1944 | SKIP(parser); |
---|
1945 | if (!CACHE(parser, 1)) return 0; |
---|
1946 | } |
---|
1947 | |
---|
1948 | /* Eat a comment until a line break. */ |
---|
1949 | |
---|
1950 | if (CHECK(parser->buffer, '#')) { |
---|
1951 | while (!IS_BREAKZ(parser->buffer)) { |
---|
1952 | SKIP(parser); |
---|
1953 | if (!CACHE(parser, 1)) return 0; |
---|
1954 | } |
---|
1955 | } |
---|
1956 | |
---|
1957 | /* If it is a line break, eat it. */ |
---|
1958 | |
---|
1959 | if (IS_BREAK(parser->buffer)) |
---|
1960 | { |
---|
1961 | if (!CACHE(parser, 2)) return 0; |
---|
1962 | SKIP_LINE(parser); |
---|
1963 | |
---|
1964 | /* In the block context, a new line may start a simple key. */ |
---|
1965 | |
---|
1966 | if (!parser->flow_level) { |
---|
1967 | parser->simple_key_allowed = 1; |
---|
1968 | } |
---|
1969 | } |
---|
1970 | else |
---|
1971 | { |
---|
1972 | /* We have found a token. */ |
---|
1973 | |
---|
1974 | break; |
---|
1975 | } |
---|
1976 | } |
---|
1977 | |
---|
1978 | return 1; |
---|
1979 | } |
---|
1980 | |
---|
1981 | /* |
---|
1982 | * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token. |
---|
1983 | * |
---|
1984 | * Scope: |
---|
1985 | * %YAML 1.1 # a comment \n |
---|
1986 | * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
---|
1987 | * %TAG !yaml! tag:yaml.org,2002: \n |
---|
1988 | * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
---|
1989 | */ |
---|
1990 | |
---|
1991 | int |
---|
1992 | yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token) |
---|
1993 | { |
---|
1994 | yaml_mark_t start_mark, end_mark; |
---|
1995 | yaml_char_t *name = NULL; |
---|
1996 | int major, minor; |
---|
1997 | yaml_char_t *handle = NULL, *prefix = NULL; |
---|
1998 | |
---|
1999 | /* Eat '%'. */ |
---|
2000 | |
---|
2001 | start_mark = parser->mark; |
---|
2002 | |
---|
2003 | SKIP(parser); |
---|
2004 | |
---|
2005 | /* Scan the directive name. */ |
---|
2006 | |
---|
2007 | if (!yaml_parser_scan_directive_name(parser, start_mark, &name)) |
---|
2008 | goto error; |
---|
2009 | |
---|
2010 | /* Is it a YAML directive? */ |
---|
2011 | |
---|
2012 | if (strcmp((char *)name, "YAML") == 0) |
---|
2013 | { |
---|
2014 | /* Scan the VERSION directive value. */ |
---|
2015 | |
---|
2016 | if (!yaml_parser_scan_version_directive_value(parser, start_mark, |
---|
2017 | &major, &minor)) |
---|
2018 | goto error; |
---|
2019 | |
---|
2020 | end_mark = parser->mark; |
---|
2021 | |
---|
2022 | /* Create a VERSION-DIRECTIVE token. */ |
---|
2023 | |
---|
2024 | VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor, |
---|
2025 | start_mark, end_mark); |
---|
2026 | } |
---|
2027 | |
---|
2028 | /* Is it a TAG directive? */ |
---|
2029 | |
---|
2030 | else if (strcmp((char *)name, "TAG") == 0) |
---|
2031 | { |
---|
2032 | /* Scan the TAG directive value. */ |
---|
2033 | |
---|
2034 | if (!yaml_parser_scan_tag_directive_value(parser, start_mark, |
---|
2035 | &handle, &prefix)) |
---|
2036 | goto error; |
---|
2037 | |
---|
2038 | end_mark = parser->mark; |
---|
2039 | |
---|
2040 | /* Create a TAG-DIRECTIVE token. */ |
---|
2041 | |
---|
2042 | TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix, |
---|
2043 | start_mark, end_mark); |
---|
2044 | } |
---|
2045 | |
---|
2046 | /* Unknown directive. */ |
---|
2047 | |
---|
2048 | else |
---|
2049 | { |
---|
2050 | yaml_parser_set_scanner_error(parser, "while scanning a directive", |
---|
2051 | start_mark, "found uknown directive name"); |
---|
2052 | goto error; |
---|
2053 | } |
---|
2054 | |
---|
2055 | /* Eat the rest of the line including any comments. */ |
---|
2056 | |
---|
2057 | if (!CACHE(parser, 1)) goto error; |
---|
2058 | |
---|
2059 | while (IS_BLANK(parser->buffer)) { |
---|
2060 | SKIP(parser); |
---|
2061 | if (!CACHE(parser, 1)) goto error; |
---|
2062 | } |
---|
2063 | |
---|
2064 | if (CHECK(parser->buffer, '#')) { |
---|
2065 | while (!IS_BREAKZ(parser->buffer)) { |
---|
2066 | SKIP(parser); |
---|
2067 | if (!CACHE(parser, 1)) goto error; |
---|
2068 | } |
---|
2069 | } |
---|
2070 | |
---|
2071 | /* Check if we are at the end of the line. */ |
---|
2072 | |
---|
2073 | if (!IS_BREAKZ(parser->buffer)) { |
---|
2074 | yaml_parser_set_scanner_error(parser, "while scanning a directive", |
---|
2075 | start_mark, "did not found expected comment or line break"); |
---|
2076 | goto error; |
---|
2077 | } |
---|
2078 | |
---|
2079 | /* Eat a line break. */ |
---|
2080 | |
---|
2081 | if (IS_BREAK(parser->buffer)) { |
---|
2082 | if (!CACHE(parser, 2)) goto error; |
---|
2083 | SKIP_LINE(parser); |
---|
2084 | } |
---|
2085 | |
---|
2086 | yaml_free(name); |
---|
2087 | |
---|
2088 | return 1; |
---|
2089 | |
---|
2090 | error: |
---|
2091 | yaml_free(prefix); |
---|
2092 | yaml_free(handle); |
---|
2093 | yaml_free(name); |
---|
2094 | return 0; |
---|
2095 | } |
---|
2096 | |
---|
2097 | /* |
---|
2098 | * Scan the directive name. |
---|
2099 | * |
---|
2100 | * Scope: |
---|
2101 | * %YAML 1.1 # a comment \n |
---|
2102 | * ^^^^ |
---|
2103 | * %TAG !yaml! tag:yaml.org,2002: \n |
---|
2104 | * ^^^ |
---|
2105 | */ |
---|
2106 | |
---|
2107 | static int |
---|
2108 | yaml_parser_scan_directive_name(yaml_parser_t *parser, |
---|
2109 | yaml_mark_t start_mark, yaml_char_t **name) |
---|
2110 | { |
---|
2111 | yaml_string_t string = NULL_STRING; |
---|
2112 | |
---|
2113 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
2114 | |
---|
2115 | /* Consume the directive name. */ |
---|
2116 | |
---|
2117 | if (!CACHE(parser, 1)) goto error; |
---|
2118 | |
---|
2119 | while (IS_ALPHA(parser->buffer)) |
---|
2120 | { |
---|
2121 | if (!READ(parser, string)) goto error; |
---|
2122 | if (!CACHE(parser, 1)) goto error; |
---|
2123 | } |
---|
2124 | |
---|
2125 | /* Check if the name is empty. */ |
---|
2126 | |
---|
2127 | if (string.start == string.pointer) { |
---|
2128 | yaml_parser_set_scanner_error(parser, "while scanning a directive", |
---|
2129 | start_mark, "cannot found expected directive name"); |
---|
2130 | goto error; |
---|
2131 | } |
---|
2132 | |
---|
2133 | /* Check for an blank character after the name. */ |
---|
2134 | |
---|
2135 | if (!IS_BLANKZ(parser->buffer)) { |
---|
2136 | yaml_parser_set_scanner_error(parser, "while scanning a directive", |
---|
2137 | start_mark, "found unexpected non-alphabetical character"); |
---|
2138 | goto error; |
---|
2139 | } |
---|
2140 | |
---|
2141 | *name = string.start; |
---|
2142 | |
---|
2143 | return 1; |
---|
2144 | |
---|
2145 | error: |
---|
2146 | STRING_DEL(parser, string); |
---|
2147 | return 0; |
---|
2148 | } |
---|
2149 | |
---|
2150 | /* |
---|
2151 | * Scan the value of VERSION-DIRECTIVE. |
---|
2152 | * |
---|
2153 | * Scope: |
---|
2154 | * %YAML 1.1 # a comment \n |
---|
2155 | * ^^^^^^ |
---|
2156 | */ |
---|
2157 | |
---|
2158 | static int |
---|
2159 | yaml_parser_scan_version_directive_value(yaml_parser_t *parser, |
---|
2160 | yaml_mark_t start_mark, int *major, int *minor) |
---|
2161 | { |
---|
2162 | /* Eat whitespaces. */ |
---|
2163 | |
---|
2164 | if (!CACHE(parser, 1)) return 0; |
---|
2165 | |
---|
2166 | while (IS_BLANK(parser->buffer)) { |
---|
2167 | SKIP(parser); |
---|
2168 | if (!CACHE(parser, 1)) return 0; |
---|
2169 | } |
---|
2170 | |
---|
2171 | /* Consume the major version number. */ |
---|
2172 | |
---|
2173 | if (!yaml_parser_scan_version_directive_number(parser, start_mark, major)) |
---|
2174 | return 0; |
---|
2175 | |
---|
2176 | /* Eat '.'. */ |
---|
2177 | |
---|
2178 | if (!CHECK(parser->buffer, '.')) { |
---|
2179 | return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", |
---|
2180 | start_mark, "did not find expected digit or '.' character"); |
---|
2181 | } |
---|
2182 | |
---|
2183 | SKIP(parser); |
---|
2184 | |
---|
2185 | /* Consume the minor version number. */ |
---|
2186 | |
---|
2187 | if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor)) |
---|
2188 | return 0; |
---|
2189 | |
---|
2190 | return 1; |
---|
2191 | } |
---|
2192 | |
---|
2193 | #define MAX_NUMBER_LENGTH 9 |
---|
2194 | |
---|
2195 | /* |
---|
2196 | * Scan the version number of VERSION-DIRECTIVE. |
---|
2197 | * |
---|
2198 | * Scope: |
---|
2199 | * %YAML 1.1 # a comment \n |
---|
2200 | * ^ |
---|
2201 | * %YAML 1.1 # a comment \n |
---|
2202 | * ^ |
---|
2203 | */ |
---|
2204 | |
---|
2205 | static int |
---|
2206 | yaml_parser_scan_version_directive_number(yaml_parser_t *parser, |
---|
2207 | yaml_mark_t start_mark, int *number) |
---|
2208 | { |
---|
2209 | int value = 0; |
---|
2210 | size_t length = 0; |
---|
2211 | |
---|
2212 | /* Repeat while the next character is digit. */ |
---|
2213 | |
---|
2214 | if (!CACHE(parser, 1)) return 0; |
---|
2215 | |
---|
2216 | while (IS_DIGIT(parser->buffer)) |
---|
2217 | { |
---|
2218 | /* Check if the number is too long. */ |
---|
2219 | |
---|
2220 | if (++length > MAX_NUMBER_LENGTH) { |
---|
2221 | return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", |
---|
2222 | start_mark, "found extremely long version number"); |
---|
2223 | } |
---|
2224 | |
---|
2225 | value = value*10 + AS_DIGIT(parser->buffer); |
---|
2226 | |
---|
2227 | SKIP(parser); |
---|
2228 | |
---|
2229 | if (!CACHE(parser, 1)) return 0; |
---|
2230 | } |
---|
2231 | |
---|
2232 | /* Check if the number was present. */ |
---|
2233 | |
---|
2234 | if (!length) { |
---|
2235 | return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", |
---|
2236 | start_mark, "did not find expected version number"); |
---|
2237 | } |
---|
2238 | |
---|
2239 | *number = value; |
---|
2240 | |
---|
2241 | return 1; |
---|
2242 | } |
---|
2243 | |
---|
2244 | /* |
---|
2245 | * Scan the value of a TAG-DIRECTIVE token. |
---|
2246 | * |
---|
2247 | * Scope: |
---|
2248 | * %TAG !yaml! tag:yaml.org,2002: \n |
---|
2249 | * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
---|
2250 | */ |
---|
2251 | |
---|
2252 | static int |
---|
2253 | yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, |
---|
2254 | yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix) |
---|
2255 | { |
---|
2256 | yaml_char_t *handle_value = NULL; |
---|
2257 | yaml_char_t *prefix_value = NULL; |
---|
2258 | |
---|
2259 | /* Eat whitespaces. */ |
---|
2260 | |
---|
2261 | if (!CACHE(parser, 1)) goto error; |
---|
2262 | |
---|
2263 | while (IS_BLANK(parser->buffer)) { |
---|
2264 | SKIP(parser); |
---|
2265 | if (!CACHE(parser, 1)) goto error; |
---|
2266 | } |
---|
2267 | |
---|
2268 | /* Scan a handle. */ |
---|
2269 | |
---|
2270 | if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value)) |
---|
2271 | goto error; |
---|
2272 | |
---|
2273 | /* Expect a whitespace. */ |
---|
2274 | |
---|
2275 | if (!CACHE(parser, 1)) goto error; |
---|
2276 | |
---|
2277 | if (!IS_BLANK(parser->buffer)) { |
---|
2278 | yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", |
---|
2279 | start_mark, "did not find expected whitespace"); |
---|
2280 | goto error; |
---|
2281 | } |
---|
2282 | |
---|
2283 | /* Eat whitespaces. */ |
---|
2284 | |
---|
2285 | while (IS_BLANK(parser->buffer)) { |
---|
2286 | SKIP(parser); |
---|
2287 | if (!CACHE(parser, 1)) goto error; |
---|
2288 | } |
---|
2289 | |
---|
2290 | /* Scan a prefix. */ |
---|
2291 | |
---|
2292 | if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value)) |
---|
2293 | goto error; |
---|
2294 | |
---|
2295 | /* Expect a whitespace or line break. */ |
---|
2296 | |
---|
2297 | if (!CACHE(parser, 1)) goto error; |
---|
2298 | |
---|
2299 | if (!IS_BLANKZ(parser->buffer)) { |
---|
2300 | yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", |
---|
2301 | start_mark, "did not find expected whitespace or line break"); |
---|
2302 | goto error; |
---|
2303 | } |
---|
2304 | |
---|
2305 | *handle = handle_value; |
---|
2306 | *prefix = prefix_value; |
---|
2307 | |
---|
2308 | return 1; |
---|
2309 | |
---|
2310 | error: |
---|
2311 | yaml_free(handle_value); |
---|
2312 | yaml_free(prefix_value); |
---|
2313 | return 0; |
---|
2314 | } |
---|
2315 | |
---|
2316 | static int |
---|
2317 | yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, |
---|
2318 | yaml_token_type_t type) |
---|
2319 | { |
---|
2320 | int length = 0; |
---|
2321 | yaml_mark_t start_mark, end_mark; |
---|
2322 | yaml_string_t string = NULL_STRING; |
---|
2323 | |
---|
2324 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
2325 | |
---|
2326 | /* Eat the indicator character. */ |
---|
2327 | |
---|
2328 | start_mark = parser->mark; |
---|
2329 | |
---|
2330 | SKIP(parser); |
---|
2331 | |
---|
2332 | /* Consume the value. */ |
---|
2333 | |
---|
2334 | if (!CACHE(parser, 1)) goto error; |
---|
2335 | |
---|
2336 | while (IS_ALPHA(parser->buffer)) { |
---|
2337 | if (!READ(parser, string)) goto error; |
---|
2338 | if (!CACHE(parser, 1)) goto error; |
---|
2339 | length ++; |
---|
2340 | } |
---|
2341 | |
---|
2342 | end_mark = parser->mark; |
---|
2343 | |
---|
2344 | /* |
---|
2345 | * Check if length of the anchor is greater than 0 and it is followed by |
---|
2346 | * a whitespace character or one of the indicators: |
---|
2347 | * |
---|
2348 | * '?', ':', ',', ']', '}', '%', '@', '`'. |
---|
2349 | */ |
---|
2350 | |
---|
2351 | if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?') |
---|
2352 | || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',') |
---|
2353 | || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}') |
---|
2354 | || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@') |
---|
2355 | || CHECK(parser->buffer, '`'))) { |
---|
2356 | yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ? |
---|
2357 | "while scanning an anchor" : "while scanning an alias", start_mark, |
---|
2358 | "did not find expected alphabetic or numeric character"); |
---|
2359 | goto error; |
---|
2360 | } |
---|
2361 | |
---|
2362 | /* Create a token. */ |
---|
2363 | |
---|
2364 | if (type == YAML_ANCHOR_TOKEN) { |
---|
2365 | ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark); |
---|
2366 | } |
---|
2367 | else { |
---|
2368 | ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark); |
---|
2369 | } |
---|
2370 | |
---|
2371 | return 1; |
---|
2372 | |
---|
2373 | error: |
---|
2374 | STRING_DEL(parser, string); |
---|
2375 | return 0; |
---|
2376 | } |
---|
2377 | |
---|
2378 | /* |
---|
2379 | * Scan a TAG token. |
---|
2380 | */ |
---|
2381 | |
---|
2382 | static int |
---|
2383 | yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token) |
---|
2384 | { |
---|
2385 | yaml_char_t *handle = NULL; |
---|
2386 | yaml_char_t *suffix = NULL; |
---|
2387 | yaml_mark_t start_mark, end_mark; |
---|
2388 | |
---|
2389 | start_mark = parser->mark; |
---|
2390 | |
---|
2391 | /* Check if the tag is in the canonical form. */ |
---|
2392 | |
---|
2393 | if (!CACHE(parser, 2)) goto error; |
---|
2394 | |
---|
2395 | if (CHECK_AT(parser->buffer, '<', 1)) |
---|
2396 | { |
---|
2397 | /* Set the handle to '' */ |
---|
2398 | |
---|
2399 | handle = yaml_malloc(1); |
---|
2400 | if (!handle) goto error; |
---|
2401 | handle[0] = '\0'; |
---|
2402 | |
---|
2403 | /* Eat '!<' */ |
---|
2404 | |
---|
2405 | SKIP(parser); |
---|
2406 | SKIP(parser); |
---|
2407 | |
---|
2408 | /* Consume the tag value. */ |
---|
2409 | |
---|
2410 | if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) |
---|
2411 | goto error; |
---|
2412 | |
---|
2413 | /* Check for '>' and eat it. */ |
---|
2414 | |
---|
2415 | if (!CHECK(parser->buffer, '>')) { |
---|
2416 | yaml_parser_set_scanner_error(parser, "while scanning a tag", |
---|
2417 | start_mark, "did not find the expected '>'"); |
---|
2418 | goto error; |
---|
2419 | } |
---|
2420 | |
---|
2421 | SKIP(parser); |
---|
2422 | } |
---|
2423 | else |
---|
2424 | { |
---|
2425 | /* The tag has either the '!suffix' or the '!handle!suffix' form. */ |
---|
2426 | |
---|
2427 | /* First, try to scan a handle. */ |
---|
2428 | |
---|
2429 | if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle)) |
---|
2430 | goto error; |
---|
2431 | |
---|
2432 | /* Check if it is, indeed, handle. */ |
---|
2433 | |
---|
2434 | if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!') |
---|
2435 | { |
---|
2436 | /* Scan the suffix now. */ |
---|
2437 | |
---|
2438 | if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) |
---|
2439 | goto error; |
---|
2440 | } |
---|
2441 | else |
---|
2442 | { |
---|
2443 | /* It wasn't a handle after all. Scan the rest of the tag. */ |
---|
2444 | |
---|
2445 | if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix)) |
---|
2446 | goto error; |
---|
2447 | |
---|
2448 | /* Set the handle to '!'. */ |
---|
2449 | |
---|
2450 | yaml_free(handle); |
---|
2451 | handle = yaml_malloc(2); |
---|
2452 | if (!handle) goto error; |
---|
2453 | handle[0] = '!'; |
---|
2454 | handle[1] = '\0'; |
---|
2455 | |
---|
2456 | /* |
---|
2457 | * A special case: the '!' tag. Set the handle to '' and the |
---|
2458 | * suffix to '!'. |
---|
2459 | */ |
---|
2460 | |
---|
2461 | if (suffix[0] == '\0') { |
---|
2462 | yaml_char_t *tmp = handle; |
---|
2463 | handle = suffix; |
---|
2464 | suffix = tmp; |
---|
2465 | } |
---|
2466 | } |
---|
2467 | } |
---|
2468 | |
---|
2469 | /* Check the character which ends the tag. */ |
---|
2470 | |
---|
2471 | if (!CACHE(parser, 1)) goto error; |
---|
2472 | |
---|
2473 | if (!IS_BLANKZ(parser->buffer)) { |
---|
2474 | yaml_parser_set_scanner_error(parser, "while scanning a tag", |
---|
2475 | start_mark, "did not found expected whitespace or line break"); |
---|
2476 | goto error; |
---|
2477 | } |
---|
2478 | |
---|
2479 | end_mark = parser->mark; |
---|
2480 | |
---|
2481 | /* Create a token. */ |
---|
2482 | |
---|
2483 | TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark); |
---|
2484 | |
---|
2485 | return 1; |
---|
2486 | |
---|
2487 | error: |
---|
2488 | yaml_free(handle); |
---|
2489 | yaml_free(suffix); |
---|
2490 | return 0; |
---|
2491 | } |
---|
2492 | |
---|
2493 | /* |
---|
2494 | * Scan a tag handle. |
---|
2495 | */ |
---|
2496 | |
---|
2497 | static int |
---|
2498 | yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, |
---|
2499 | yaml_mark_t start_mark, yaml_char_t **handle) |
---|
2500 | { |
---|
2501 | yaml_string_t string = NULL_STRING; |
---|
2502 | |
---|
2503 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
2504 | |
---|
2505 | /* Check the initial '!' character. */ |
---|
2506 | |
---|
2507 | if (!CACHE(parser, 1)) goto error; |
---|
2508 | |
---|
2509 | if (!CHECK(parser->buffer, '!')) { |
---|
2510 | yaml_parser_set_scanner_error(parser, directive ? |
---|
2511 | "while scanning a tag directive" : "while scanning a tag", |
---|
2512 | start_mark, "did not find expected '!'"); |
---|
2513 | goto error; |
---|
2514 | } |
---|
2515 | |
---|
2516 | /* Copy the '!' character. */ |
---|
2517 | |
---|
2518 | if (!READ(parser, string)) goto error; |
---|
2519 | |
---|
2520 | /* Copy all subsequent alphabetical and numerical characters. */ |
---|
2521 | |
---|
2522 | if (!CACHE(parser, 1)) goto error; |
---|
2523 | |
---|
2524 | while (IS_ALPHA(parser->buffer)) |
---|
2525 | { |
---|
2526 | if (!READ(parser, string)) goto error; |
---|
2527 | if (!CACHE(parser, 1)) goto error; |
---|
2528 | } |
---|
2529 | |
---|
2530 | /* Check if the trailing character is '!' and copy it. */ |
---|
2531 | |
---|
2532 | if (CHECK(parser->buffer, '!')) |
---|
2533 | { |
---|
2534 | if (!READ(parser, string)) goto error; |
---|
2535 | } |
---|
2536 | else |
---|
2537 | { |
---|
2538 | /* |
---|
2539 | * It's either the '!' tag or not really a tag handle. If it's a %TAG |
---|
2540 | * directive, it's an error. If it's a tag token, it must be a part of |
---|
2541 | * URI. |
---|
2542 | */ |
---|
2543 | |
---|
2544 | if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) { |
---|
2545 | yaml_parser_set_scanner_error(parser, "while parsing a tag directive", |
---|
2546 | start_mark, "did not find expected '!'"); |
---|
2547 | goto error; |
---|
2548 | } |
---|
2549 | } |
---|
2550 | |
---|
2551 | *handle = string.start; |
---|
2552 | |
---|
2553 | return 1; |
---|
2554 | |
---|
2555 | error: |
---|
2556 | STRING_DEL(parser, string); |
---|
2557 | return 0; |
---|
2558 | } |
---|
2559 | |
---|
2560 | /* |
---|
2561 | * Scan a tag. |
---|
2562 | */ |
---|
2563 | |
---|
2564 | static int |
---|
2565 | yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, |
---|
2566 | yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri) |
---|
2567 | { |
---|
2568 | size_t length = head ? strlen((char *)head) : 0; |
---|
2569 | yaml_string_t string = NULL_STRING; |
---|
2570 | |
---|
2571 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
2572 | |
---|
2573 | /* Resize the string to include the head. */ |
---|
2574 | |
---|
2575 | while (string.end - string.start <= (int)length) { |
---|
2576 | if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) { |
---|
2577 | parser->error = YAML_MEMORY_ERROR; |
---|
2578 | goto error; |
---|
2579 | } |
---|
2580 | } |
---|
2581 | |
---|
2582 | /* |
---|
2583 | * Copy the head if needed. |
---|
2584 | * |
---|
2585 | * Note that we don't copy the leading '!' character. |
---|
2586 | */ |
---|
2587 | |
---|
2588 | if (length > 1) { |
---|
2589 | memcpy(string.start, head+1, length-1); |
---|
2590 | string.pointer += length-1; |
---|
2591 | } |
---|
2592 | |
---|
2593 | /* Scan the tag. */ |
---|
2594 | |
---|
2595 | if (!CACHE(parser, 1)) goto error; |
---|
2596 | |
---|
2597 | /* |
---|
2598 | * The set of characters that may appear in URI is as follows: |
---|
2599 | * |
---|
2600 | * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&', |
---|
2601 | * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']', |
---|
2602 | * '%'. |
---|
2603 | */ |
---|
2604 | |
---|
2605 | while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';') |
---|
2606 | || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?') |
---|
2607 | || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@') |
---|
2608 | || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=') |
---|
2609 | || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$') |
---|
2610 | || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.') |
---|
2611 | || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~') |
---|
2612 | || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'') |
---|
2613 | || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')') |
---|
2614 | || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']') |
---|
2615 | || CHECK(parser->buffer, '%')) |
---|
2616 | { |
---|
2617 | /* Check if it is a URI-escape sequence. */ |
---|
2618 | |
---|
2619 | if (CHECK(parser->buffer, '%')) { |
---|
2620 | if (!yaml_parser_scan_uri_escapes(parser, |
---|
2621 | directive, start_mark, &string)) goto error; |
---|
2622 | } |
---|
2623 | else { |
---|
2624 | if (!READ(parser, string)) goto error; |
---|
2625 | } |
---|
2626 | |
---|
2627 | length ++; |
---|
2628 | if (!CACHE(parser, 1)) goto error; |
---|
2629 | } |
---|
2630 | |
---|
2631 | /* Check if the tag is non-empty. */ |
---|
2632 | |
---|
2633 | if (!length) { |
---|
2634 | if (!STRING_EXTEND(parser, string)) |
---|
2635 | goto error; |
---|
2636 | |
---|
2637 | yaml_parser_set_scanner_error(parser, directive ? |
---|
2638 | "while parsing a %TAG directive" : "while parsing a tag", |
---|
2639 | start_mark, "did not find expected tag URI"); |
---|
2640 | goto error; |
---|
2641 | } |
---|
2642 | |
---|
2643 | *uri = string.start; |
---|
2644 | |
---|
2645 | return 1; |
---|
2646 | |
---|
2647 | error: |
---|
2648 | STRING_DEL(parser, string); |
---|
2649 | return 0; |
---|
2650 | } |
---|
2651 | |
---|
2652 | /* |
---|
2653 | * Decode an URI-escape sequence corresponding to a single UTF-8 character. |
---|
2654 | */ |
---|
2655 | |
---|
2656 | static int |
---|
2657 | yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, |
---|
2658 | yaml_mark_t start_mark, yaml_string_t *string) |
---|
2659 | { |
---|
2660 | int width = 0; |
---|
2661 | |
---|
2662 | /* Decode the required number of characters. */ |
---|
2663 | |
---|
2664 | do { |
---|
2665 | |
---|
2666 | unsigned char octet = 0; |
---|
2667 | |
---|
2668 | /* Check for a URI-escaped octet. */ |
---|
2669 | |
---|
2670 | if (!CACHE(parser, 3)) return 0; |
---|
2671 | |
---|
2672 | if (!(CHECK(parser->buffer, '%') |
---|
2673 | && IS_HEX_AT(parser->buffer, 1) |
---|
2674 | && IS_HEX_AT(parser->buffer, 2))) { |
---|
2675 | return yaml_parser_set_scanner_error(parser, directive ? |
---|
2676 | "while parsing a %TAG directive" : "while parsing a tag", |
---|
2677 | start_mark, "did not find URI escaped octet"); |
---|
2678 | } |
---|
2679 | |
---|
2680 | /* Get the octet. */ |
---|
2681 | |
---|
2682 | octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2); |
---|
2683 | |
---|
2684 | /* If it is the leading octet, determine the length of the UTF-8 sequence. */ |
---|
2685 | |
---|
2686 | if (!width) |
---|
2687 | { |
---|
2688 | width = (octet & 0x80) == 0x00 ? 1 : |
---|
2689 | (octet & 0xE0) == 0xC0 ? 2 : |
---|
2690 | (octet & 0xF0) == 0xE0 ? 3 : |
---|
2691 | (octet & 0xF8) == 0xF0 ? 4 : 0; |
---|
2692 | if (!width) { |
---|
2693 | return yaml_parser_set_scanner_error(parser, directive ? |
---|
2694 | "while parsing a %TAG directive" : "while parsing a tag", |
---|
2695 | start_mark, "found an incorrect leading UTF-8 octet"); |
---|
2696 | } |
---|
2697 | } |
---|
2698 | else |
---|
2699 | { |
---|
2700 | /* Check if the trailing octet is correct. */ |
---|
2701 | |
---|
2702 | if ((octet & 0xC0) != 0x80) { |
---|
2703 | return yaml_parser_set_scanner_error(parser, directive ? |
---|
2704 | "while parsing a %TAG directive" : "while parsing a tag", |
---|
2705 | start_mark, "found an incorrect trailing UTF-8 octet"); |
---|
2706 | } |
---|
2707 | } |
---|
2708 | |
---|
2709 | /* Copy the octet and move the pointers. */ |
---|
2710 | |
---|
2711 | *(string->pointer++) = octet; |
---|
2712 | SKIP(parser); |
---|
2713 | SKIP(parser); |
---|
2714 | SKIP(parser); |
---|
2715 | |
---|
2716 | } while (--width); |
---|
2717 | |
---|
2718 | return 1; |
---|
2719 | } |
---|
2720 | |
---|
2721 | /* |
---|
2722 | * Scan a block scalar. |
---|
2723 | */ |
---|
2724 | |
---|
2725 | static int |
---|
2726 | yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, |
---|
2727 | int literal) |
---|
2728 | { |
---|
2729 | yaml_mark_t start_mark; |
---|
2730 | yaml_mark_t end_mark; |
---|
2731 | yaml_string_t string = NULL_STRING; |
---|
2732 | yaml_string_t leading_break = NULL_STRING; |
---|
2733 | yaml_string_t trailing_breaks = NULL_STRING; |
---|
2734 | int chomping = 0; |
---|
2735 | int increment = 0; |
---|
2736 | int indent = 0; |
---|
2737 | int leading_blank = 0; |
---|
2738 | int trailing_blank = 0; |
---|
2739 | |
---|
2740 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
2741 | if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; |
---|
2742 | if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; |
---|
2743 | |
---|
2744 | /* Eat the indicator '|' or '>'. */ |
---|
2745 | |
---|
2746 | start_mark = parser->mark; |
---|
2747 | |
---|
2748 | SKIP(parser); |
---|
2749 | |
---|
2750 | /* Scan the additional block scalar indicators. */ |
---|
2751 | |
---|
2752 | if (!CACHE(parser, 1)) goto error; |
---|
2753 | |
---|
2754 | /* Check for a chomping indicator. */ |
---|
2755 | |
---|
2756 | if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) |
---|
2757 | { |
---|
2758 | /* Set the chomping method and eat the indicator. */ |
---|
2759 | |
---|
2760 | chomping = CHECK(parser->buffer, '+') ? +1 : -1; |
---|
2761 | |
---|
2762 | SKIP(parser); |
---|
2763 | |
---|
2764 | /* Check for an indentation indicator. */ |
---|
2765 | |
---|
2766 | if (!CACHE(parser, 1)) goto error; |
---|
2767 | |
---|
2768 | if (IS_DIGIT(parser->buffer)) |
---|
2769 | { |
---|
2770 | /* Check that the intendation is greater than 0. */ |
---|
2771 | |
---|
2772 | if (CHECK(parser->buffer, '0')) { |
---|
2773 | yaml_parser_set_scanner_error(parser, "while scanning a block scalar", |
---|
2774 | start_mark, "found an intendation indicator equal to 0"); |
---|
2775 | goto error; |
---|
2776 | } |
---|
2777 | |
---|
2778 | /* Get the intendation level and eat the indicator. */ |
---|
2779 | |
---|
2780 | increment = AS_DIGIT(parser->buffer); |
---|
2781 | |
---|
2782 | SKIP(parser); |
---|
2783 | } |
---|
2784 | } |
---|
2785 | |
---|
2786 | /* Do the same as above, but in the opposite order. */ |
---|
2787 | |
---|
2788 | else if (IS_DIGIT(parser->buffer)) |
---|
2789 | { |
---|
2790 | if (CHECK(parser->buffer, '0')) { |
---|
2791 | yaml_parser_set_scanner_error(parser, "while scanning a block scalar", |
---|
2792 | start_mark, "found an intendation indicator equal to 0"); |
---|
2793 | goto error; |
---|
2794 | } |
---|
2795 | |
---|
2796 | increment = AS_DIGIT(parser->buffer); |
---|
2797 | |
---|
2798 | SKIP(parser); |
---|
2799 | |
---|
2800 | if (!CACHE(parser, 1)) goto error; |
---|
2801 | |
---|
2802 | if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) { |
---|
2803 | chomping = CHECK(parser->buffer, '+') ? +1 : -1; |
---|
2804 | |
---|
2805 | SKIP(parser); |
---|
2806 | } |
---|
2807 | } |
---|
2808 | |
---|
2809 | /* Eat whitespaces and comments to the end of the line. */ |
---|
2810 | |
---|
2811 | if (!CACHE(parser, 1)) goto error; |
---|
2812 | |
---|
2813 | while (IS_BLANK(parser->buffer)) { |
---|
2814 | SKIP(parser); |
---|
2815 | if (!CACHE(parser, 1)) goto error; |
---|
2816 | } |
---|
2817 | |
---|
2818 | if (CHECK(parser->buffer, '#')) { |
---|
2819 | while (!IS_BREAKZ(parser->buffer)) { |
---|
2820 | SKIP(parser); |
---|
2821 | if (!CACHE(parser, 1)) goto error; |
---|
2822 | } |
---|
2823 | } |
---|
2824 | |
---|
2825 | /* Check if we are at the end of the line. */ |
---|
2826 | |
---|
2827 | if (!IS_BREAKZ(parser->buffer)) { |
---|
2828 | yaml_parser_set_scanner_error(parser, "while scanning a block scalar", |
---|
2829 | start_mark, "did not found expected comment or line break"); |
---|
2830 | goto error; |
---|
2831 | } |
---|
2832 | |
---|
2833 | /* Eat a line break. */ |
---|
2834 | |
---|
2835 | if (IS_BREAK(parser->buffer)) { |
---|
2836 | if (!CACHE(parser, 2)) goto error; |
---|
2837 | SKIP_LINE(parser); |
---|
2838 | } |
---|
2839 | |
---|
2840 | end_mark = parser->mark; |
---|
2841 | |
---|
2842 | /* Set the intendation level if it was specified. */ |
---|
2843 | |
---|
2844 | if (increment) { |
---|
2845 | indent = parser->indent >= 0 ? parser->indent+increment : increment; |
---|
2846 | } |
---|
2847 | |
---|
2848 | /* Scan the leading line breaks and determine the indentation level if needed. */ |
---|
2849 | |
---|
2850 | if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks, |
---|
2851 | start_mark, &end_mark)) goto error; |
---|
2852 | |
---|
2853 | /* Scan the block scalar content. */ |
---|
2854 | |
---|
2855 | if (!CACHE(parser, 1)) goto error; |
---|
2856 | |
---|
2857 | while ((int)parser->mark.column == indent && !IS_Z(parser->buffer)) |
---|
2858 | { |
---|
2859 | /* |
---|
2860 | * We are at the beginning of a non-empty line. |
---|
2861 | */ |
---|
2862 | |
---|
2863 | /* Is it a trailing whitespace? */ |
---|
2864 | |
---|
2865 | trailing_blank = IS_BLANK(parser->buffer); |
---|
2866 | |
---|
2867 | /* Check if we need to fold the leading line break. */ |
---|
2868 | |
---|
2869 | if (!literal && (*leading_break.start == '\n') |
---|
2870 | && !leading_blank && !trailing_blank) |
---|
2871 | { |
---|
2872 | /* Do we need to join the lines by space? */ |
---|
2873 | |
---|
2874 | if (*trailing_breaks.start == '\0') { |
---|
2875 | if (!STRING_EXTEND(parser, string)) goto error; |
---|
2876 | *(string.pointer ++) = ' '; |
---|
2877 | } |
---|
2878 | |
---|
2879 | CLEAR(parser, leading_break); |
---|
2880 | } |
---|
2881 | else { |
---|
2882 | if (!JOIN(parser, string, leading_break)) goto error; |
---|
2883 | CLEAR(parser, leading_break); |
---|
2884 | } |
---|
2885 | |
---|
2886 | /* Append the remaining line breaks. */ |
---|
2887 | |
---|
2888 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
2889 | CLEAR(parser, trailing_breaks); |
---|
2890 | |
---|
2891 | /* Is it a leading whitespace? */ |
---|
2892 | |
---|
2893 | leading_blank = IS_BLANK(parser->buffer); |
---|
2894 | |
---|
2895 | /* Consume the current line. */ |
---|
2896 | |
---|
2897 | while (!IS_BREAKZ(parser->buffer)) { |
---|
2898 | if (!READ(parser, string)) goto error; |
---|
2899 | if (!CACHE(parser, 1)) goto error; |
---|
2900 | } |
---|
2901 | |
---|
2902 | /* Consume the line break. */ |
---|
2903 | |
---|
2904 | if (!CACHE(parser, 2)) goto error; |
---|
2905 | |
---|
2906 | if (!READ_LINE(parser, leading_break)) goto error; |
---|
2907 | |
---|
2908 | /* Eat the following intendation spaces and line breaks. */ |
---|
2909 | |
---|
2910 | if (!yaml_parser_scan_block_scalar_breaks(parser, |
---|
2911 | &indent, &trailing_breaks, start_mark, &end_mark)) goto error; |
---|
2912 | } |
---|
2913 | |
---|
2914 | /* Chomp the tail. */ |
---|
2915 | |
---|
2916 | if (chomping != -1) { |
---|
2917 | if (!JOIN(parser, string, leading_break)) goto error; |
---|
2918 | } |
---|
2919 | if (chomping == 1) { |
---|
2920 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
2921 | } |
---|
2922 | |
---|
2923 | /* Create a token. */ |
---|
2924 | |
---|
2925 | SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, |
---|
2926 | literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE, |
---|
2927 | start_mark, end_mark); |
---|
2928 | |
---|
2929 | STRING_DEL(parser, leading_break); |
---|
2930 | STRING_DEL(parser, trailing_breaks); |
---|
2931 | |
---|
2932 | return 1; |
---|
2933 | |
---|
2934 | error: |
---|
2935 | STRING_DEL(parser, string); |
---|
2936 | STRING_DEL(parser, leading_break); |
---|
2937 | STRING_DEL(parser, trailing_breaks); |
---|
2938 | |
---|
2939 | return 0; |
---|
2940 | } |
---|
2941 | |
---|
2942 | /* |
---|
2943 | * Scan intendation spaces and line breaks for a block scalar. Determine the |
---|
2944 | * intendation level if needed. |
---|
2945 | */ |
---|
2946 | |
---|
2947 | static int |
---|
2948 | yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, |
---|
2949 | int *indent, yaml_string_t *breaks, |
---|
2950 | yaml_mark_t start_mark, yaml_mark_t *end_mark) |
---|
2951 | { |
---|
2952 | int max_indent = 0; |
---|
2953 | |
---|
2954 | *end_mark = parser->mark; |
---|
2955 | |
---|
2956 | /* Eat the intendation spaces and line breaks. */ |
---|
2957 | |
---|
2958 | while (1) |
---|
2959 | { |
---|
2960 | /* Eat the intendation spaces. */ |
---|
2961 | |
---|
2962 | if (!CACHE(parser, 1)) return 0; |
---|
2963 | |
---|
2964 | while ((!*indent || (int)parser->mark.column < *indent) |
---|
2965 | && IS_SPACE(parser->buffer)) { |
---|
2966 | SKIP(parser); |
---|
2967 | if (!CACHE(parser, 1)) return 0; |
---|
2968 | } |
---|
2969 | |
---|
2970 | if ((int)parser->mark.column > max_indent) |
---|
2971 | max_indent = (int)parser->mark.column; |
---|
2972 | |
---|
2973 | /* Check for a tab character messing the intendation. */ |
---|
2974 | |
---|
2975 | if ((!*indent || (int)parser->mark.column < *indent) |
---|
2976 | && IS_TAB(parser->buffer)) { |
---|
2977 | return yaml_parser_set_scanner_error(parser, "while scanning a block scalar", |
---|
2978 | start_mark, "found a tab character where an intendation space is expected"); |
---|
2979 | } |
---|
2980 | |
---|
2981 | /* Have we found a non-empty line? */ |
---|
2982 | |
---|
2983 | if (!IS_BREAK(parser->buffer)) break; |
---|
2984 | |
---|
2985 | /* Consume the line break. */ |
---|
2986 | |
---|
2987 | if (!CACHE(parser, 2)) return 0; |
---|
2988 | if (!READ_LINE(parser, *breaks)) return 0; |
---|
2989 | *end_mark = parser->mark; |
---|
2990 | } |
---|
2991 | |
---|
2992 | /* Determine the indentation level if needed. */ |
---|
2993 | |
---|
2994 | if (!*indent) { |
---|
2995 | *indent = max_indent; |
---|
2996 | if (*indent < parser->indent + 1) |
---|
2997 | *indent = parser->indent + 1; |
---|
2998 | if (*indent < 1) |
---|
2999 | *indent = 1; |
---|
3000 | } |
---|
3001 | |
---|
3002 | return 1; |
---|
3003 | } |
---|
3004 | |
---|
3005 | /* |
---|
3006 | * Scan a quoted scalar. |
---|
3007 | */ |
---|
3008 | |
---|
3009 | static int |
---|
3010 | yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, |
---|
3011 | int single) |
---|
3012 | { |
---|
3013 | yaml_mark_t start_mark; |
---|
3014 | yaml_mark_t end_mark; |
---|
3015 | yaml_string_t string = NULL_STRING; |
---|
3016 | yaml_string_t leading_break = NULL_STRING; |
---|
3017 | yaml_string_t trailing_breaks = NULL_STRING; |
---|
3018 | yaml_string_t whitespaces = NULL_STRING; |
---|
3019 | int leading_blanks; |
---|
3020 | |
---|
3021 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
3022 | if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; |
---|
3023 | if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; |
---|
3024 | if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; |
---|
3025 | |
---|
3026 | /* Eat the left quote. */ |
---|
3027 | |
---|
3028 | start_mark = parser->mark; |
---|
3029 | |
---|
3030 | SKIP(parser); |
---|
3031 | |
---|
3032 | /* Consume the content of the quoted scalar. */ |
---|
3033 | |
---|
3034 | while (1) |
---|
3035 | { |
---|
3036 | /* Check that there are no document indicators at the beginning of the line. */ |
---|
3037 | |
---|
3038 | if (!CACHE(parser, 4)) goto error; |
---|
3039 | |
---|
3040 | if (parser->mark.column == 0 && |
---|
3041 | ((CHECK_AT(parser->buffer, '-', 0) && |
---|
3042 | CHECK_AT(parser->buffer, '-', 1) && |
---|
3043 | CHECK_AT(parser->buffer, '-', 2)) || |
---|
3044 | (CHECK_AT(parser->buffer, '.', 0) && |
---|
3045 | CHECK_AT(parser->buffer, '.', 1) && |
---|
3046 | CHECK_AT(parser->buffer, '.', 2))) && |
---|
3047 | IS_BLANKZ_AT(parser->buffer, 3)) |
---|
3048 | { |
---|
3049 | yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", |
---|
3050 | start_mark, "found unexpected document indicator"); |
---|
3051 | goto error; |
---|
3052 | } |
---|
3053 | |
---|
3054 | /* Check for EOF. */ |
---|
3055 | |
---|
3056 | if (IS_Z(parser->buffer)) { |
---|
3057 | yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", |
---|
3058 | start_mark, "found unexpected end of stream"); |
---|
3059 | goto error; |
---|
3060 | } |
---|
3061 | |
---|
3062 | /* Consume non-blank characters. */ |
---|
3063 | |
---|
3064 | if (!CACHE(parser, 2)) goto error; |
---|
3065 | |
---|
3066 | leading_blanks = 0; |
---|
3067 | |
---|
3068 | while (!IS_BLANKZ(parser->buffer)) |
---|
3069 | { |
---|
3070 | /* Check for an escaped single quote. */ |
---|
3071 | |
---|
3072 | if (single && CHECK_AT(parser->buffer, '\'', 0) |
---|
3073 | && CHECK_AT(parser->buffer, '\'', 1)) |
---|
3074 | { |
---|
3075 | if (!STRING_EXTEND(parser, string)) goto error; |
---|
3076 | *(string.pointer++) = '\''; |
---|
3077 | SKIP(parser); |
---|
3078 | SKIP(parser); |
---|
3079 | } |
---|
3080 | |
---|
3081 | /* Check for the right quote. */ |
---|
3082 | |
---|
3083 | else if (CHECK(parser->buffer, single ? '\'' : '"')) |
---|
3084 | { |
---|
3085 | break; |
---|
3086 | } |
---|
3087 | |
---|
3088 | /* Check for an escaped line break. */ |
---|
3089 | |
---|
3090 | else if (!single && CHECK(parser->buffer, '\\') |
---|
3091 | && IS_BREAK_AT(parser->buffer, 1)) |
---|
3092 | { |
---|
3093 | if (!CACHE(parser, 3)) goto error; |
---|
3094 | SKIP(parser); |
---|
3095 | SKIP_LINE(parser); |
---|
3096 | leading_blanks = 1; |
---|
3097 | break; |
---|
3098 | } |
---|
3099 | |
---|
3100 | /* Check for an escape sequence. */ |
---|
3101 | |
---|
3102 | else if (!single && CHECK(parser->buffer, '\\')) |
---|
3103 | { |
---|
3104 | size_t code_length = 0; |
---|
3105 | |
---|
3106 | if (!STRING_EXTEND(parser, string)) goto error; |
---|
3107 | |
---|
3108 | /* Check the escape character. */ |
---|
3109 | |
---|
3110 | switch (parser->buffer.pointer[1]) |
---|
3111 | { |
---|
3112 | case '0': |
---|
3113 | *(string.pointer++) = '\0'; |
---|
3114 | break; |
---|
3115 | |
---|
3116 | case 'a': |
---|
3117 | *(string.pointer++) = '\x07'; |
---|
3118 | break; |
---|
3119 | |
---|
3120 | case 'b': |
---|
3121 | *(string.pointer++) = '\x08'; |
---|
3122 | break; |
---|
3123 | |
---|
3124 | case 't': |
---|
3125 | case '\t': |
---|
3126 | *(string.pointer++) = '\x09'; |
---|
3127 | break; |
---|
3128 | |
---|
3129 | case 'n': |
---|
3130 | *(string.pointer++) = '\x0A'; |
---|
3131 | break; |
---|
3132 | |
---|
3133 | case 'v': |
---|
3134 | *(string.pointer++) = '\x0B'; |
---|
3135 | break; |
---|
3136 | |
---|
3137 | case 'f': |
---|
3138 | *(string.pointer++) = '\x0C'; |
---|
3139 | break; |
---|
3140 | |
---|
3141 | case 'r': |
---|
3142 | *(string.pointer++) = '\x0D'; |
---|
3143 | break; |
---|
3144 | |
---|
3145 | case 'e': |
---|
3146 | *(string.pointer++) = '\x1B'; |
---|
3147 | break; |
---|
3148 | |
---|
3149 | case ' ': |
---|
3150 | *(string.pointer++) = '\x20'; |
---|
3151 | break; |
---|
3152 | |
---|
3153 | case '"': |
---|
3154 | *(string.pointer++) = '"'; |
---|
3155 | break; |
---|
3156 | |
---|
3157 | case '\'': |
---|
3158 | *(string.pointer++) = '\''; |
---|
3159 | break; |
---|
3160 | |
---|
3161 | case '\\': |
---|
3162 | *(string.pointer++) = '\\'; |
---|
3163 | break; |
---|
3164 | |
---|
3165 | case 'N': /* NEL (#x85) */ |
---|
3166 | *(string.pointer++) = '\xC2'; |
---|
3167 | *(string.pointer++) = '\x85'; |
---|
3168 | break; |
---|
3169 | |
---|
3170 | case '_': /* #xA0 */ |
---|
3171 | *(string.pointer++) = '\xC2'; |
---|
3172 | *(string.pointer++) = '\xA0'; |
---|
3173 | break; |
---|
3174 | |
---|
3175 | case 'L': /* LS (#x2028) */ |
---|
3176 | *(string.pointer++) = '\xE2'; |
---|
3177 | *(string.pointer++) = '\x80'; |
---|
3178 | *(string.pointer++) = '\xA8'; |
---|
3179 | break; |
---|
3180 | |
---|
3181 | case 'P': /* PS (#x2029) */ |
---|
3182 | *(string.pointer++) = '\xE2'; |
---|
3183 | *(string.pointer++) = '\x80'; |
---|
3184 | *(string.pointer++) = '\xA9'; |
---|
3185 | break; |
---|
3186 | |
---|
3187 | case 'x': |
---|
3188 | code_length = 2; |
---|
3189 | break; |
---|
3190 | |
---|
3191 | case 'u': |
---|
3192 | code_length = 4; |
---|
3193 | break; |
---|
3194 | |
---|
3195 | case 'U': |
---|
3196 | code_length = 8; |
---|
3197 | break; |
---|
3198 | |
---|
3199 | default: |
---|
3200 | yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", |
---|
3201 | start_mark, "found unknown escape character"); |
---|
3202 | goto error; |
---|
3203 | } |
---|
3204 | |
---|
3205 | SKIP(parser); |
---|
3206 | SKIP(parser); |
---|
3207 | |
---|
3208 | /* Consume an arbitrary escape code. */ |
---|
3209 | |
---|
3210 | if (code_length) |
---|
3211 | { |
---|
3212 | unsigned int value = 0; |
---|
3213 | size_t k; |
---|
3214 | |
---|
3215 | /* Scan the character value. */ |
---|
3216 | |
---|
3217 | if (!CACHE(parser, code_length)) goto error; |
---|
3218 | |
---|
3219 | for (k = 0; k < code_length; k ++) { |
---|
3220 | if (!IS_HEX_AT(parser->buffer, k)) { |
---|
3221 | yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", |
---|
3222 | start_mark, "did not find expected hexdecimal number"); |
---|
3223 | goto error; |
---|
3224 | } |
---|
3225 | value = (value << 4) + AS_HEX_AT(parser->buffer, k); |
---|
3226 | } |
---|
3227 | |
---|
3228 | /* Check the value and write the character. */ |
---|
3229 | |
---|
3230 | if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) { |
---|
3231 | yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", |
---|
3232 | start_mark, "found invalid Unicode character escape code"); |
---|
3233 | goto error; |
---|
3234 | } |
---|
3235 | |
---|
3236 | if (value <= 0x7F) { |
---|
3237 | *(string.pointer++) = value; |
---|
3238 | } |
---|
3239 | else if (value <= 0x7FF) { |
---|
3240 | *(string.pointer++) = 0xC0 + (value >> 6); |
---|
3241 | *(string.pointer++) = 0x80 + (value & 0x3F); |
---|
3242 | } |
---|
3243 | else if (value <= 0xFFFF) { |
---|
3244 | *(string.pointer++) = 0xE0 + (value >> 12); |
---|
3245 | *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); |
---|
3246 | *(string.pointer++) = 0x80 + (value & 0x3F); |
---|
3247 | } |
---|
3248 | else { |
---|
3249 | *(string.pointer++) = 0xF0 + (value >> 18); |
---|
3250 | *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F); |
---|
3251 | *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); |
---|
3252 | *(string.pointer++) = 0x80 + (value & 0x3F); |
---|
3253 | } |
---|
3254 | |
---|
3255 | /* Advance the pointer. */ |
---|
3256 | |
---|
3257 | for (k = 0; k < code_length; k ++) { |
---|
3258 | SKIP(parser); |
---|
3259 | } |
---|
3260 | } |
---|
3261 | } |
---|
3262 | |
---|
3263 | else |
---|
3264 | { |
---|
3265 | /* It is a non-escaped non-blank character. */ |
---|
3266 | |
---|
3267 | if (!READ(parser, string)) goto error; |
---|
3268 | } |
---|
3269 | |
---|
3270 | if (!CACHE(parser, 2)) goto error; |
---|
3271 | } |
---|
3272 | |
---|
3273 | /* Check if we are at the end of the scalar. */ |
---|
3274 | |
---|
3275 | if (CHECK(parser->buffer, single ? '\'' : '"')) |
---|
3276 | break; |
---|
3277 | |
---|
3278 | /* Consume blank characters. */ |
---|
3279 | |
---|
3280 | if (!CACHE(parser, 1)) goto error; |
---|
3281 | |
---|
3282 | while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) |
---|
3283 | { |
---|
3284 | if (IS_BLANK(parser->buffer)) |
---|
3285 | { |
---|
3286 | /* Consume a space or a tab character. */ |
---|
3287 | |
---|
3288 | if (!leading_blanks) { |
---|
3289 | if (!READ(parser, whitespaces)) goto error; |
---|
3290 | } |
---|
3291 | else { |
---|
3292 | SKIP(parser); |
---|
3293 | } |
---|
3294 | } |
---|
3295 | else |
---|
3296 | { |
---|
3297 | if (!CACHE(parser, 2)) goto error; |
---|
3298 | |
---|
3299 | /* Check if it is a first line break. */ |
---|
3300 | |
---|
3301 | if (!leading_blanks) |
---|
3302 | { |
---|
3303 | CLEAR(parser, whitespaces); |
---|
3304 | if (!READ_LINE(parser, leading_break)) goto error; |
---|
3305 | leading_blanks = 1; |
---|
3306 | } |
---|
3307 | else |
---|
3308 | { |
---|
3309 | if (!READ_LINE(parser, trailing_breaks)) goto error; |
---|
3310 | } |
---|
3311 | } |
---|
3312 | if (!CACHE(parser, 1)) goto error; |
---|
3313 | } |
---|
3314 | |
---|
3315 | /* Join the whitespaces or fold line breaks. */ |
---|
3316 | |
---|
3317 | if (leading_blanks) |
---|
3318 | { |
---|
3319 | /* Do we need to fold line breaks? */ |
---|
3320 | |
---|
3321 | if (leading_break.start[0] == '\n') { |
---|
3322 | if (trailing_breaks.start[0] == '\0') { |
---|
3323 | if (!STRING_EXTEND(parser, string)) goto error; |
---|
3324 | *(string.pointer++) = ' '; |
---|
3325 | } |
---|
3326 | else { |
---|
3327 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
3328 | CLEAR(parser, trailing_breaks); |
---|
3329 | } |
---|
3330 | CLEAR(parser, leading_break); |
---|
3331 | } |
---|
3332 | else { |
---|
3333 | if (!JOIN(parser, string, leading_break)) goto error; |
---|
3334 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
3335 | CLEAR(parser, leading_break); |
---|
3336 | CLEAR(parser, trailing_breaks); |
---|
3337 | } |
---|
3338 | } |
---|
3339 | else |
---|
3340 | { |
---|
3341 | if (!JOIN(parser, string, whitespaces)) goto error; |
---|
3342 | CLEAR(parser, whitespaces); |
---|
3343 | } |
---|
3344 | } |
---|
3345 | |
---|
3346 | /* Eat the right quote. */ |
---|
3347 | |
---|
3348 | SKIP(parser); |
---|
3349 | |
---|
3350 | end_mark = parser->mark; |
---|
3351 | |
---|
3352 | /* Create a token. */ |
---|
3353 | |
---|
3354 | SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, |
---|
3355 | single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE, |
---|
3356 | start_mark, end_mark); |
---|
3357 | |
---|
3358 | STRING_DEL(parser, leading_break); |
---|
3359 | STRING_DEL(parser, trailing_breaks); |
---|
3360 | STRING_DEL(parser, whitespaces); |
---|
3361 | |
---|
3362 | return 1; |
---|
3363 | |
---|
3364 | error: |
---|
3365 | STRING_DEL(parser, string); |
---|
3366 | STRING_DEL(parser, leading_break); |
---|
3367 | STRING_DEL(parser, trailing_breaks); |
---|
3368 | STRING_DEL(parser, whitespaces); |
---|
3369 | |
---|
3370 | return 0; |
---|
3371 | } |
---|
3372 | |
---|
3373 | /* |
---|
3374 | * Scan a plain scalar. |
---|
3375 | */ |
---|
3376 | |
---|
3377 | static int |
---|
3378 | yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token) |
---|
3379 | { |
---|
3380 | yaml_mark_t start_mark; |
---|
3381 | yaml_mark_t end_mark; |
---|
3382 | yaml_string_t string = NULL_STRING; |
---|
3383 | yaml_string_t leading_break = NULL_STRING; |
---|
3384 | yaml_string_t trailing_breaks = NULL_STRING; |
---|
3385 | yaml_string_t whitespaces = NULL_STRING; |
---|
3386 | int leading_blanks = 0; |
---|
3387 | int indent = parser->indent+1; |
---|
3388 | |
---|
3389 | if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; |
---|
3390 | if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; |
---|
3391 | if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; |
---|
3392 | if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; |
---|
3393 | |
---|
3394 | start_mark = end_mark = parser->mark; |
---|
3395 | |
---|
3396 | /* Consume the content of the plain scalar. */ |
---|
3397 | |
---|
3398 | while (1) |
---|
3399 | { |
---|
3400 | /* Check for a document indicator. */ |
---|
3401 | |
---|
3402 | if (!CACHE(parser, 4)) goto error; |
---|
3403 | |
---|
3404 | if (parser->mark.column == 0 && |
---|
3405 | ((CHECK_AT(parser->buffer, '-', 0) && |
---|
3406 | CHECK_AT(parser->buffer, '-', 1) && |
---|
3407 | CHECK_AT(parser->buffer, '-', 2)) || |
---|
3408 | (CHECK_AT(parser->buffer, '.', 0) && |
---|
3409 | CHECK_AT(parser->buffer, '.', 1) && |
---|
3410 | CHECK_AT(parser->buffer, '.', 2))) && |
---|
3411 | IS_BLANKZ_AT(parser->buffer, 3)) break; |
---|
3412 | |
---|
3413 | /* Check for a comment. */ |
---|
3414 | |
---|
3415 | if (CHECK(parser->buffer, '#')) |
---|
3416 | break; |
---|
3417 | |
---|
3418 | /* Consume non-blank characters. */ |
---|
3419 | |
---|
3420 | while (!IS_BLANKZ(parser->buffer)) |
---|
3421 | { |
---|
3422 | /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */ |
---|
3423 | |
---|
3424 | if (parser->flow_level |
---|
3425 | && CHECK(parser->buffer, ':') |
---|
3426 | && !IS_BLANKZ_AT(parser->buffer, 1)) { |
---|
3427 | yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", |
---|
3428 | start_mark, "found unexpected ':'"); |
---|
3429 | goto error; |
---|
3430 | } |
---|
3431 | |
---|
3432 | /* Check for indicators that may end a plain scalar. */ |
---|
3433 | |
---|
3434 | if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1)) |
---|
3435 | || (parser->flow_level && |
---|
3436 | (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':') |
---|
3437 | || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[') |
---|
3438 | || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') |
---|
3439 | || CHECK(parser->buffer, '}')))) |
---|
3440 | break; |
---|
3441 | |
---|
3442 | /* Check if we need to join whitespaces and breaks. */ |
---|
3443 | |
---|
3444 | if (leading_blanks || whitespaces.start != whitespaces.pointer) |
---|
3445 | { |
---|
3446 | if (leading_blanks) |
---|
3447 | { |
---|
3448 | /* Do we need to fold line breaks? */ |
---|
3449 | |
---|
3450 | if (leading_break.start[0] == '\n') { |
---|
3451 | if (trailing_breaks.start[0] == '\0') { |
---|
3452 | if (!STRING_EXTEND(parser, string)) goto error; |
---|
3453 | *(string.pointer++) = ' '; |
---|
3454 | } |
---|
3455 | else { |
---|
3456 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
3457 | CLEAR(parser, trailing_breaks); |
---|
3458 | } |
---|
3459 | CLEAR(parser, leading_break); |
---|
3460 | } |
---|
3461 | else { |
---|
3462 | if (!JOIN(parser, string, leading_break)) goto error; |
---|
3463 | if (!JOIN(parser, string, trailing_breaks)) goto error; |
---|
3464 | CLEAR(parser, leading_break); |
---|
3465 | CLEAR(parser, trailing_breaks); |
---|
3466 | } |
---|
3467 | |
---|
3468 | leading_blanks = 0; |
---|
3469 | } |
---|
3470 | else |
---|
3471 | { |
---|
3472 | if (!JOIN(parser, string, whitespaces)) goto error; |
---|
3473 | CLEAR(parser, whitespaces); |
---|
3474 | } |
---|
3475 | } |
---|
3476 | |
---|
3477 | /* Copy the character. */ |
---|
3478 | |
---|
3479 | if (!READ(parser, string)) goto error; |
---|
3480 | |
---|
3481 | end_mark = parser->mark; |
---|
3482 | |
---|
3483 | if (!CACHE(parser, 2)) goto error; |
---|
3484 | } |
---|
3485 | |
---|
3486 | /* Is it the end? */ |
---|
3487 | |
---|
3488 | if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))) |
---|
3489 | break; |
---|
3490 | |
---|
3491 | /* Consume blank characters. */ |
---|
3492 | |
---|
3493 | if (!CACHE(parser, 1)) goto error; |
---|
3494 | |
---|
3495 | while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) |
---|
3496 | { |
---|
3497 | if (IS_BLANK(parser->buffer)) |
---|
3498 | { |
---|
3499 | /* Check for tab character that abuse intendation. */ |
---|
3500 | |
---|
3501 | if (leading_blanks && (int)parser->mark.column < indent |
---|
3502 | && IS_TAB(parser->buffer)) { |
---|
3503 | yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", |
---|
3504 | start_mark, "found a tab character that violate intendation"); |
---|
3505 | goto error; |
---|
3506 | } |
---|
3507 | |
---|
3508 | /* Consume a space or a tab character. */ |
---|
3509 | |
---|
3510 | if (!leading_blanks) { |
---|
3511 | if (!READ(parser, whitespaces)) goto error; |
---|
3512 | } |
---|
3513 | else { |
---|
3514 | SKIP(parser); |
---|
3515 | } |
---|
3516 | } |
---|
3517 | else |
---|
3518 | { |
---|
3519 | if (!CACHE(parser, 2)) goto error; |
---|
3520 | |
---|
3521 | /* Check if it is a first line break. */ |
---|
3522 | |
---|
3523 | if (!leading_blanks) |
---|
3524 | { |
---|
3525 | CLEAR(parser, whitespaces); |
---|
3526 | if (!READ_LINE(parser, leading_break)) goto error; |
---|
3527 | leading_blanks = 1; |
---|
3528 | } |
---|
3529 | else |
---|
3530 | { |
---|
3531 | if (!READ_LINE(parser, trailing_breaks)) goto error; |
---|
3532 | } |
---|
3533 | } |
---|
3534 | if (!CACHE(parser, 1)) goto error; |
---|
3535 | } |
---|
3536 | |
---|
3537 | /* Check intendation level. */ |
---|
3538 | |
---|
3539 | if (!parser->flow_level && (int)parser->mark.column < indent) |
---|
3540 | break; |
---|
3541 | } |
---|
3542 | |
---|
3543 | /* Create a token. */ |
---|
3544 | |
---|
3545 | SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, |
---|
3546 | YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark); |
---|
3547 | |
---|
3548 | /* Note that we change the 'simple_key_allowed' flag. */ |
---|
3549 | |
---|
3550 | if (leading_blanks) { |
---|
3551 | parser->simple_key_allowed = 1; |
---|
3552 | } |
---|
3553 | |
---|
3554 | STRING_DEL(parser, leading_break); |
---|
3555 | STRING_DEL(parser, trailing_breaks); |
---|
3556 | STRING_DEL(parser, whitespaces); |
---|
3557 | |
---|
3558 | return 1; |
---|
3559 | |
---|
3560 | error: |
---|
3561 | STRING_DEL(parser, string); |
---|
3562 | STRING_DEL(parser, leading_break); |
---|
3563 | STRING_DEL(parser, trailing_breaks); |
---|
3564 | STRING_DEL(parser, whitespaces); |
---|
3565 | |
---|
3566 | return 0; |
---|
3567 | } |
---|
3568 | |
---|