]>
Commit | Line | Data |
---|---|---|
03be97ab KS |
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 | #if HAVE_CONFIG_H | |
479 | #include <config.h> | |
480 | #endif | |
481 | ||
482 | #include <yaml/yaml.h> | |
483 | ||
484 | #include <assert.h> | |
485 | ||
f2b59d4d KS |
486 | /* |
487 | * Ensure that the buffer contains the required number of characters. | |
488 | * Return 1 on success, 0 on failure (reader error or memory error). | |
489 | */ | |
490 | ||
491 | #define UPDATE(parser,length) \ | |
492 | (parser->unread >= (length) \ | |
493 | ? 1 \ | |
494 | : yaml_parser_update_buffer(parser, (length))) | |
495 | ||
496 | /* | |
497 | * Check the octet at the specified position. | |
498 | */ | |
499 | ||
500 | #define CHECK_AT(parser,octet,offset) \ | |
eb9cceb5 | 501 | (parser->pointer[offset] == (yaml_char_t)(octet)) |
f2b59d4d KS |
502 | |
503 | /* | |
504 | * Check the current octet in the buffer. | |
505 | */ | |
506 | ||
507 | #define CHECK(parser,octet) CHECK_AT(parser,(octet),0) | |
508 | ||
509 | /* | |
510 | * Check if the character at the specified position is NUL. | |
511 | */ | |
512 | ||
513 | #define IS_Z_AT(parser,offset) CHECK_AT(parser,'\0',(offset)) | |
514 | ||
515 | #define IS_Z(parser) IS_Z_AT(parser,0) | |
516 | ||
517 | /* | |
518 | * Check if the character at the specified position is space. | |
519 | */ | |
520 | ||
521 | #define IS_SPACE_AT(parser,offset) CHECK_AT(parser,' ',(offset)) | |
522 | ||
523 | #define IS_SPACE(parser) IS_SPACE_AT(parser,0) | |
524 | ||
525 | /* | |
526 | * Check if the character at the specified position is tab. | |
527 | */ | |
528 | ||
529 | #define IS_TAB_AT(parser,offset) CHECK_AT(parser,'\t',(offset)) | |
530 | ||
531 | #define IS_TAB(parser) IS_TAB_AT(parser,0) | |
532 | ||
533 | /* | |
534 | * Check if the character at the specified position is blank (space or tab). | |
535 | */ | |
536 | ||
537 | #define IS_BLANK_AT(parser,offset) \ | |
538 | (IS_SPACE_AT(parser,(offset)) || IS_TAB_AT(parser,(offset))) | |
539 | ||
540 | #define IS_BLANK(parser) IS_BLANK_AT(parser,0) | |
541 | ||
542 | /* | |
543 | * Check if the character at the specified position is a line break. | |
544 | */ | |
545 | ||
546 | #define IS_BREAK_AT(parser,offset) \ | |
547 | (CHECK_AT(parser,'\r',(offset)) /* CR (#xD)*/ \ | |
548 | || CHECK_AT(parser,'\n',(offset)) /* LF (#xA) */ \ | |
549 | || (CHECK_AT(parser,'\xC2',(offset)) \ | |
550 | && CHECK_AT(parser,'\x85',(offset+1))) /* NEL (#x85) */ \ | |
551 | || (CHECK_AT(parser,'\xE2',(offset)) \ | |
552 | && CHECK_AT(parser,'\x80',(offset+1)) \ | |
553 | && CHECK_AT(parser,'\xA8',(offset+2))) /* LS (#x2028) */ \ | |
554 | || (CHECK_AT(parser,'\xE2',(offset)) \ | |
555 | && CHECK_AT(parser,'\x80',(offset+1)) \ | |
556 | && CHECK_AT(parser,'\xA9',(offset+2)))) /* LS (#x2029) */ | |
557 | ||
558 | #define IS_BREAK(parser) IS_BREAK_AT(parser,0) | |
559 | ||
eb9cceb5 KS |
560 | #define IS_CRLF_AT(parser,offset) \ |
561 | (CHECK_AT(parser,'\r',(offset)) && CHECK_AT(parser,'\n',(offset)+1)) | |
562 | ||
563 | #define IS_CRLF(parser) IS_CRLF_AT(parser,0) | |
564 | ||
f2b59d4d KS |
565 | /* |
566 | * Check if the character is a line break or NUL. | |
567 | */ | |
568 | ||
569 | #define IS_BREAKZ_AT(parser,offset) \ | |
570 | (IS_BREAK_AT(parser,(offset)) || IS_Z_AT(parser,(offset))) | |
571 | ||
572 | #define IS_BREAKZ(parser) IS_BREAKZ_AT(parser,0) | |
573 | ||
574 | /* | |
575 | * Check if the character is a line break, space, or NUL. | |
576 | */ | |
577 | ||
578 | #define IS_SPACEZ_AT(parser,offset) \ | |
579 | (IS_SPACE_AT(parser,(offset)) || IS_BREAKZ_AT(parser,(offset))) | |
580 | ||
581 | #define IS_SPACEZ(parser) IS_SPACEZ_AT(parser,0) | |
582 | ||
583 | /* | |
584 | * Check if the character is a line break, space, tab, or NUL. | |
585 | */ | |
586 | ||
587 | #define IS_BLANKZ_AT(parser,offset) \ | |
588 | (IS_BLANK_AT(parser,(offset)) || IS_BREAKZ_AT(parser,(offset))) | |
589 | ||
590 | #define IS_BLANKZ(parser) IS_BLANKZ_AT(parser,0) | |
591 | ||
eb9cceb5 KS |
592 | /* |
593 | * Determine the width of the character. | |
594 | */ | |
595 | ||
596 | #define WIDTH_AT(parser,offset) \ | |
597 | ((parser->pointer[(offset)] & 0x80) == 0x00 ? 1 : \ | |
598 | (parser->pointer[(offset)] & 0xE0) == 0xC0 ? 2 : \ | |
599 | (parser->pointer[(offset)] & 0xF0) == 0xE0 ? 3 : \ | |
600 | (parser->pointer[(offset)] & 0xF8) == 0xF0 ? 4 : 0) | |
601 | ||
602 | #define WIDTH(parser) WIDTH_AT(parser,0) | |
603 | ||
604 | /* | |
605 | * Advance the buffer pointer. | |
606 | */ | |
607 | ||
608 | #define FORWARD(parser) \ | |
609 | (parser->index ++, \ | |
610 | ((IS_BREAK(parser) && !IS_CRLF(parser)) ? \ | |
611 | (parser->line ++, parser->column = 0) : \ | |
612 | (parser->column ++)), \ | |
613 | parser->unread --, \ | |
614 | parser->pointer += WIDTH(parser)) | |
615 | ||
03be97ab KS |
616 | /* |
617 | * Public API declarations. | |
618 | */ | |
619 | ||
620 | YAML_DECLARE(yaml_token_t *) | |
621 | yaml_parser_get_token(yaml_parser_t *parser); | |
622 | ||
623 | YAML_DECLARE(yaml_token_t *) | |
624 | yaml_parser_peek_token(yaml_parser_t *parser); | |
625 | ||
f2b59d4d KS |
626 | /* |
627 | * Error handling. | |
628 | */ | |
629 | ||
630 | static int | |
631 | yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, | |
632 | yaml_mark_t context_mark, const char *problem); | |
633 | ||
634 | static yaml_mark_t | |
635 | yaml_parser_get_mark(yaml_parser_t *parser); | |
636 | ||
03be97ab KS |
637 | /* |
638 | * High-level token API. | |
639 | */ | |
640 | ||
641 | static int | |
642 | yaml_parser_fetch_more_tokens(yaml_parser_t *parser); | |
643 | ||
644 | static int | |
645 | yaml_parser_fetch_next_token(yaml_parser_t *parser); | |
646 | ||
647 | /* | |
648 | * Potential simple keys. | |
649 | */ | |
650 | ||
651 | static int | |
652 | yaml_parser_stale_simple_keys(yaml_parser_t *parser); | |
653 | ||
654 | static int | |
655 | yaml_parser_save_simple_key(yaml_parser_t *parser); | |
656 | ||
657 | static int | |
658 | yaml_parser_remove_simple_key(yaml_parser_t *parser); | |
659 | ||
eb9cceb5 KS |
660 | static int |
661 | yaml_parser_increase_flow_level(yaml_parser_t *parser); | |
662 | ||
663 | static int | |
664 | yaml_parser_decrease_flow_level(yaml_parser_t *parser); | |
665 | ||
666 | /* | |
667 | * Token manipulation. | |
668 | */ | |
669 | ||
670 | static int | |
671 | yaml_parser_append_token(yaml_parser_t *parser, yaml_token_t *token); | |
672 | ||
673 | static int | |
674 | yaml_parser_insert_token(yaml_parser_t *parser, | |
675 | int number, yaml_token_t *token); | |
676 | ||
03be97ab KS |
677 | /* |
678 | * Indentation treatment. | |
679 | */ | |
680 | ||
681 | static int | |
eb9cceb5 KS |
682 | yaml_parser_roll_indent(yaml_parser_t *parser, int column, |
683 | int number, yaml_token_type_t type, yaml_mark_t mark); | |
03be97ab KS |
684 | |
685 | static int | |
f2b59d4d | 686 | yaml_parser_unroll_indent(yaml_parser_t *parser, int column); |
03be97ab KS |
687 | |
688 | /* | |
689 | * Token fetchers. | |
690 | */ | |
691 | ||
692 | static int | |
693 | yaml_parser_fetch_stream_start(yaml_parser_t *parser); | |
694 | ||
695 | static int | |
696 | yaml_parser_fetch_stream_end(yaml_parser_t *parser); | |
697 | ||
698 | static int | |
699 | yaml_parser_fetch_directive(yaml_parser_t *parser); | |
700 | ||
03be97ab KS |
701 | static int |
702 | yaml_parser_fetch_document_indicator(yaml_parser_t *parser, | |
703 | yaml_token_type_t type); | |
704 | ||
03be97ab KS |
705 | static int |
706 | yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, | |
707 | yaml_token_type_t type); | |
708 | ||
03be97ab KS |
709 | static int |
710 | yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, | |
711 | yaml_token_type_t type); | |
712 | ||
713 | static int | |
714 | yaml_parser_fetch_flow_entry(yaml_parser_t *parser); | |
715 | ||
716 | static int | |
717 | yaml_parser_fetch_block_entry(yaml_parser_t *parser); | |
718 | ||
719 | static int | |
720 | yaml_parser_fetch_key(yaml_parser_t *parser); | |
721 | ||
722 | static int | |
723 | yaml_parser_fetch_value(yaml_parser_t *parser); | |
724 | ||
725 | static int | |
eb9cceb5 | 726 | yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type); |
03be97ab KS |
727 | |
728 | static int | |
729 | yaml_parser_fetch_tag(yaml_parser_t *parser); | |
730 | ||
03be97ab KS |
731 | static int |
732 | yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal); | |
733 | ||
03be97ab KS |
734 | static int |
735 | yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single); | |
736 | ||
737 | static int | |
738 | yaml_parser_fetch_plain_scalar(yaml_parser_t *parser); | |
739 | ||
740 | /* | |
741 | * Token scanners. | |
742 | */ | |
743 | ||
744 | static int | |
745 | yaml_parser_scan_to_next_token(yaml_parser_t *parser); | |
746 | ||
747 | static yaml_token_t * | |
748 | yaml_parser_scan_directive(yaml_parser_t *parser); | |
749 | ||
750 | static int | |
751 | yaml_parser_scan_directive_name(yaml_parser_t *parser, | |
752 | yaml_mark_t start_mark, yaml_char_t **name); | |
753 | ||
754 | static int | |
755 | yaml_parser_scan_yaml_directive_value(yaml_parser_t *parser, | |
756 | yaml_mark_t start_mark, int *major, int *minor); | |
757 | ||
758 | static int | |
759 | yaml_parser_scan_yaml_directive_number(yaml_parser_t *parser, | |
760 | yaml_mark_t start_mark, int *number); | |
761 | ||
762 | static int | |
763 | yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, | |
764 | yaml_char_t **handle, yaml_char_t **prefix); | |
765 | ||
766 | static yaml_token_t * | |
767 | yaml_parser_scan_anchor(yaml_parser_t *parser, | |
768 | yaml_token_type_t type); | |
769 | ||
770 | static yaml_token_t * | |
771 | yaml_parser_scan_tag(yaml_parser_t *parser); | |
772 | ||
773 | static int | |
774 | yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, | |
775 | yaml_mark_t start_mark, yaml_char_t **handle); | |
776 | ||
777 | static int | |
778 | yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, | |
779 | yaml_mark_t start_mark, yaml_char_t **url); | |
780 | ||
781 | static yaml_token_t * | |
782 | yaml_parser_scan_block_scalar(yaml_parser_t *parser, int literal); | |
783 | ||
784 | static int | |
785 | yaml_parser_scan_block_scalar_indicators(yaml_parser_t *parser, | |
786 | yaml_mark_t start_mark, int *chomping, int *increment); | |
787 | ||
788 | static yaml_token_t * | |
789 | yaml_parser_scan_flow_scalar(yaml_parser_t *parser, int single); | |
790 | ||
791 | static yaml_token_t * | |
792 | yaml_parser_scan_plain_scalar(yaml_parser_t *parser); | |
793 | ||
f2b59d4d KS |
794 | /* |
795 | * Get the next token and remove it from the tokens queue. | |
796 | */ | |
797 | ||
798 | YAML_DECLARE(yaml_token_t *) | |
799 | yaml_parser_get_token(yaml_parser_t *parser) | |
800 | { | |
801 | yaml_token_t *token; | |
802 | ||
803 | assert(parser); /* Non-NULL parser object is expected. */ | |
804 | assert(!parser->stream_end_produced); /* No tokens after STREAM-END. */ | |
805 | ||
806 | /* Ensure that the tokens queue contains enough tokens. */ | |
807 | ||
808 | if (!yaml_parser_fetch_more_tokens(parser)) return NULL; | |
809 | ||
810 | /* Fetch the next token from the queue. */ | |
811 | ||
812 | token = parser->tokens[parser->tokens_head]; | |
813 | ||
814 | /* Move the queue head. */ | |
815 | ||
816 | parser->tokens[parser->tokens_head++] = NULL; | |
817 | if (parser->tokens_head == parser->tokens_size) | |
818 | parser->tokens_head = 0; | |
819 | ||
820 | parser->tokens_parsed++; | |
821 | ||
822 | return token; | |
823 | } | |
824 | ||
825 | /* | |
826 | * Get the next token, but don't remove it from the queue. | |
827 | */ | |
828 | ||
829 | YAML_DECLARE(yaml_token_t *) | |
830 | yaml_parser_peek_token(yaml_parser_t *parser) | |
831 | { | |
832 | assert(parser); /* Non-NULL parser object is expected. */ | |
833 | assert(!parser->stream_end_produced); /* No tokens after STREAM-END. */ | |
834 | ||
835 | /* Ensure that the tokens queue contains enough tokens. */ | |
836 | ||
837 | if (!yaml_parser_fetch_more_tokens(parser)) return NULL; | |
838 | ||
839 | /* Fetch the next token from the queue. */ | |
840 | ||
841 | return parser->tokens[parser->tokens_head]; | |
842 | } | |
843 | ||
844 | /* | |
845 | * Set the scanner error and return 0. | |
846 | */ | |
847 | ||
848 | static int | |
849 | yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, | |
850 | yaml_mark_t context_mark, const char *problem) | |
851 | { | |
852 | parser->error = YAML_SCANNER_ERROR; | |
853 | parser->context = context; | |
854 | parser->context_mark = context_mark; | |
855 | parser->problem = problem; | |
856 | parser->problem_mark = yaml_parser_get_mark(parser); | |
857 | } | |
858 | ||
859 | /* | |
860 | * Get the mark for the current buffer position. | |
861 | */ | |
862 | ||
863 | static yaml_mark_t | |
864 | yaml_parser_get_mark(yaml_parser_t *parser) | |
865 | { | |
866 | yaml_mark_t mark = { parser->index, parser->line, parser->column }; | |
867 | ||
868 | return mark; | |
869 | } | |
870 | ||
871 | ||
872 | /* | |
873 | * Ensure that the tokens queue contains at least one token which can be | |
874 | * returned to the Parser. | |
875 | */ | |
876 | ||
877 | static int | |
878 | yaml_parser_fetch_more_tokens(yaml_parser_t *parser) | |
879 | { | |
880 | int need_more_tokens; | |
881 | int k; | |
882 | ||
883 | /* While we need more tokens to fetch, do it. */ | |
884 | ||
885 | while (1) | |
886 | { | |
887 | /* | |
888 | * Check if we really need to fetch more tokens. | |
889 | */ | |
890 | ||
891 | need_more_tokens = 0; | |
892 | ||
893 | if (parser->tokens_head == parser->tokens_tail) | |
894 | { | |
895 | /* Queue is empty. */ | |
896 | ||
897 | need_more_tokens = 1; | |
898 | } | |
899 | else | |
900 | { | |
901 | /* Check if any potential simple key may occupy the head position. */ | |
902 | ||
903 | for (k = 0; k <= parser->flow_level; k++) { | |
904 | yaml_simple_key_t *simple_key = parser->simple_keys[k]; | |
905 | if (simple_key | |
906 | && (simple_key->token_number == parser->tokens_parsed)) { | |
907 | need_more_tokens = 1; | |
908 | break; | |
909 | } | |
910 | } | |
911 | } | |
912 | ||
913 | /* We are finished. */ | |
914 | ||
915 | if (!need_more_tokens) | |
916 | break; | |
917 | ||
918 | /* Fetch the next token. */ | |
919 | ||
920 | if (!yaml_parser_fetch_next_token(parser)) | |
921 | return 0; | |
922 | } | |
923 | ||
924 | return 1; | |
925 | } | |
926 | ||
927 | /* | |
928 | * The dispatcher for token fetchers. | |
929 | */ | |
930 | ||
931 | static int | |
932 | yaml_parser_fetch_next_token(yaml_parser_t *parser) | |
933 | { | |
934 | /* Ensure that the buffer is initialized. */ | |
935 | ||
936 | if (!UPDATE(parser, 1)) | |
937 | return 0; | |
938 | ||
939 | /* Check if we just started scanning. Fetch STREAM-START then. */ | |
940 | ||
941 | if (!parser->stream_start_produced) | |
942 | return yaml_parser_fetch_stream_start(parser); | |
943 | ||
944 | /* Eat whitespaces and comments until we reach the next token. */ | |
945 | ||
946 | if (!yaml_parser_scan_to_next_token(parser)) | |
947 | return 0; | |
948 | ||
949 | /* Check the indentation level against the current column. */ | |
950 | ||
951 | if (!yaml_parser_unroll_indent(parser, parser->column)) | |
952 | return 0; | |
953 | ||
954 | /* | |
955 | * Ensure that the buffer contains at least 4 characters. 4 is the length | |
956 | * of the longest indicators ('--- ' and '... '). | |
957 | */ | |
958 | ||
959 | if (!UPDATE(parser, 4)) | |
960 | return 0; | |
961 | ||
962 | /* Is it the end of the stream? */ | |
963 | ||
964 | if (IS_Z(parser)) | |
965 | return yaml_parser_fetch_stream_end(parser); | |
966 | ||
967 | /* Is it a directive? */ | |
968 | ||
969 | if (parser->column == 0 && CHECK(parser, '%')) | |
970 | return yaml_parser_fetch_directive(parser); | |
971 | ||
972 | /* Is it the document start indicator? */ | |
973 | ||
974 | if (parser->column == 0 | |
975 | && CHECK_AT(parser, '-', 0) | |
976 | && CHECK_AT(parser, '-', 1) | |
977 | && CHECK_AT(parser, '-', 2) | |
978 | && IS_BLANKZ_AT(parser, 3)) | |
eb9cceb5 KS |
979 | return yaml_parser_fetch_document_indicator(parser, |
980 | YAML_DOCUMENT_START_TOKEN); | |
f2b59d4d KS |
981 | |
982 | /* Is it the document end indicator? */ | |
983 | ||
984 | if (parser->column == 0 | |
985 | && CHECK_AT(parser, '.', 0) | |
986 | && CHECK_AT(parser, '.', 1) | |
987 | && CHECK_AT(parser, '.', 2) | |
988 | && IS_BLANKZ_AT(parser, 3)) | |
eb9cceb5 KS |
989 | return yaml_parser_fetch_document_indicator(parser, |
990 | YAML_DOCUMENT_END_TOKEN); | |
f2b59d4d KS |
991 | |
992 | /* Is it the flow sequence start indicator? */ | |
993 | ||
994 | if (CHECK(parser, '[')) | |
eb9cceb5 KS |
995 | return yaml_parser_fetch_flow_collection_start(parser, |
996 | YAML_FLOW_SEQUENCE_START_TOKEN); | |
f2b59d4d KS |
997 | |
998 | /* Is it the flow mapping start indicator? */ | |
999 | ||
1000 | if (CHECK(parser, '{')) | |
eb9cceb5 KS |
1001 | return yaml_parser_fetch_flow_collection_start(parser, |
1002 | YAML_FLOW_MAPPING_START_TOKEN); | |
f2b59d4d KS |
1003 | |
1004 | /* Is it the flow sequence end indicator? */ | |
1005 | ||
1006 | if (CHECK(parser, ']')) | |
eb9cceb5 KS |
1007 | return yaml_parser_fetch_flow_collection_end(parser, |
1008 | YAML_FLOW_SEQUENCE_END_TOKEN); | |
f2b59d4d KS |
1009 | |
1010 | /* Is it the flow mapping end indicator? */ | |
1011 | ||
1012 | if (CHECK(parser, '}')) | |
eb9cceb5 KS |
1013 | return yaml_parser_fetch_flow_collection_end(parser, |
1014 | YAML_FLOW_MAPPING_END_TOKEN); | |
f2b59d4d KS |
1015 | |
1016 | /* Is it the flow entry indicator? */ | |
1017 | ||
1018 | if (CHECK(parser, ',')) | |
1019 | return yaml_parser_fetch_flow_entry(parser); | |
1020 | ||
1021 | /* Is it the block entry indicator? */ | |
1022 | ||
1023 | if (CHECK(parser, '-') && IS_BLANKZ_AT(parser, 1)) | |
1024 | return yaml_parser_fetch_block_entry(parser); | |
1025 | ||
1026 | /* Is it the key indicator? */ | |
1027 | ||
1028 | if (CHECK(parser, '?') && (!parser->flow_level || IS_BLANKZ_AT(parser, 1))) | |
1029 | return yaml_parser_fetch_key(parser); | |
1030 | ||
1031 | /* Is it the value indicator? */ | |
1032 | ||
1033 | if (CHECK(parser, ':') && (!parser->flow_level || IS_BLANKZ_AT(parser, 1))) | |
1034 | return yaml_parser_fetch_value(parser); | |
1035 | ||
1036 | /* Is it an alias? */ | |
1037 | ||
1038 | if (CHECK(parser, '*')) | |
eb9cceb5 | 1039 | return yaml_parser_fetch_anchor(parser, YAML_ALIAS_TOKEN); |
f2b59d4d KS |
1040 | |
1041 | /* Is it an anchor? */ | |
1042 | ||
1043 | if (CHECK(parser, '&')) | |
eb9cceb5 | 1044 | return yaml_parser_fetch_anchor(parser, YAML_ANCHOR_TOKEN); |
f2b59d4d KS |
1045 | |
1046 | /* Is it a tag? */ | |
1047 | ||
1048 | if (CHECK(parser, '!')) | |
1049 | return yaml_parser_fetch_tag(parser); | |
1050 | ||
1051 | /* Is it a literal scalar? */ | |
1052 | ||
1053 | if (CHECK(parser, '|') && !parser->flow_level) | |
1054 | return yaml_parser_fetch_block_scalar(parser, 1); | |
1055 | ||
1056 | /* Is it a folded scalar? */ | |
1057 | ||
1058 | if (CHECK(parser, '>') && !parser->flow_level) | |
1059 | return yaml_parser_fetch_block_scalar(parser, 0); | |
1060 | ||
1061 | /* Is it a single-quoted scalar? */ | |
1062 | ||
1063 | if (CHECK(parser, '\'')) | |
1064 | return yaml_parser_fetch_flow_scalar(parser, 1); | |
1065 | ||
1066 | /* Is it a double-quoted scalar? */ | |
1067 | ||
1068 | if (CHECK(parser, '"')) | |
1069 | return yaml_parser_fetch_flow_scalar(parser, 0); | |
1070 | ||
1071 | /* | |
1072 | * Is it a plain scalar? | |
1073 | * | |
1074 | * A plain scalar may start with any non-blank characters except | |
1075 | * | |
1076 | * '-', '?', ':', ',', '[', ']', '{', '}', | |
1077 | * '#', '&', '*', '!', '|', '>', '\'', '\"', | |
1078 | * '%', '@', '`'. | |
1079 | * | |
1080 | * In the block context, it may also start with the characters | |
1081 | * | |
1082 | * '-', '?', ':' | |
1083 | * | |
1084 | * if it is followed by a non-space character. | |
1085 | * | |
1086 | * The last rule is more restrictive than the specification requires. | |
1087 | */ | |
1088 | ||
1089 | if (!(IS_BLANKZ(parser) || CHECK(parser, '-') || CHECK(parser, '?') | |
1090 | || CHECK(parser, ':') || CHECK(parser, ',') || CHECK(parser, '[') | |
1091 | || CHECK(parser, ']') || CHECK(parser, '{') || CHECK(parser, '}') | |
1092 | || CHECK(parser, '#') || CHECK(parser, '&') || CHECK(parser, '*') | |
1093 | || CHECK(parser, '!') || CHECK(parser, '|') || CHECK(parser, '>') | |
1094 | || CHECK(parser, '\'') || CHECK(parser, '"') || CHECK(parser, '%') | |
1095 | || CHECK(parser, '@') || CHECK(parser, '`')) || | |
1096 | (!parser->flow_level && | |
1097 | (CHECK(parser, '-') || CHECK(parser, '?') || CHECK(parser, ':')) && | |
1098 | IS_BLANKZ_AT(parser, 1))) | |
1099 | return yaml_parser_fetch_plain_scalar(parser); | |
1100 | ||
1101 | /* | |
1102 | * If we don't determine the token type so far, it is an error. | |
1103 | */ | |
1104 | ||
1105 | return yaml_parser_set_scanner_error(parser, "while scanning for the next token", | |
1106 | yaml_parser_get_mark(parser), "found character that cannot start any token"); | |
1107 | } | |
1108 | ||
eb9cceb5 KS |
1109 | /* |
1110 | * Check the list of potential simple keys and remove the positions that | |
1111 | * cannot contain simple keys anymore. | |
1112 | */ | |
1113 | ||
1114 | static int | |
1115 | yaml_parser_stale_simple_keys(yaml_parser_t *parser) | |
1116 | { | |
1117 | int level; | |
1118 | ||
1119 | /* Check for a potential simple key for each flow level. */ | |
1120 | ||
1121 | for (level = 0; level <= parser->flow_level; level++) | |
1122 | { | |
1123 | yaml_simple_key_t *simple_key = parser->simple_keys[level]; | |
1124 | ||
1125 | /* | |
1126 | * The specification requires that a simple key | |
1127 | * | |
1128 | * - is limited to a single line, | |
1129 | * - is shorter than 1024 characters. | |
1130 | */ | |
1131 | ||
1132 | if (simple_key && (simple_key->line < parser->line || | |
1133 | simple_key->index < parser->index+1024)) { | |
1134 | ||
1135 | /* Check if the potential simple key to be removed is required. */ | |
1136 | ||
1137 | if (simple_key->required) { | |
1138 | return yaml_parser_set_scanner_error(parser, | |
1139 | "while scanning a simple key", simple_key->mark, | |
1140 | "could not found expected ':'"); | |
1141 | } | |
1142 | ||
1143 | yaml_free(simple_key); | |
1144 | parser->simple_keys[level] = NULL; | |
1145 | } | |
1146 | } | |
1147 | ||
1148 | return 1; | |
1149 | } | |
1150 | ||
1151 | /* | |
1152 | * Check if a simple key may start at the current position and add it if | |
1153 | * needed. | |
1154 | */ | |
1155 | ||
1156 | static int | |
1157 | yaml_parser_save_simple_key(yaml_parser_t *parser) | |
1158 | { | |
1159 | /* | |
1160 | * A simple key is required at the current position if the scanner is in | |
1161 | * the block context and the current column coincides with the indentation | |
1162 | * level. | |
1163 | */ | |
1164 | ||
1165 | int required = (!parser->flow_level && parser->indent == parser->column); | |
1166 | ||
1167 | /* | |
1168 | * A simple key is required only when it is the first token in the current | |
1169 | * line. Therefore it is always allowed. But we add a check anyway. | |
1170 | */ | |
1171 | ||
1172 | assert(parser->simple_key_allowed || !required); /* Impossible. */ | |
1173 | ||
1174 | /* | |
1175 | * If the current position may start a simple key, save it. | |
1176 | */ | |
1177 | ||
1178 | if (parser->simple_key_allowed) | |
1179 | { | |
1180 | yaml_simple_key_t simple_key = { required, | |
1181 | parser->tokens_parsed + parser->tokens_tail - parser->tokens_head, | |
1182 | parser->index, parser->line, parser->column, | |
1183 | yaml_parser_get_mark(parser) }; | |
1184 | ||
1185 | if (!yaml_parser_remove_simple_key(parser)) return 0; | |
1186 | ||
1187 | parser->simple_keys[parser->flow_level] = | |
1188 | yaml_malloc(sizeof(yaml_simple_key_t)); | |
1189 | if (!parser->simple_keys[parser->flow_level]) { | |
1190 | parser->error = YAML_MEMORY_ERROR; | |
1191 | return 0; | |
1192 | } | |
1193 | ||
1194 | *(parser->simple_keys[parser->flow_level]) = simple_key; | |
1195 | } | |
1196 | ||
1197 | return 1; | |
1198 | } | |
1199 | ||
1200 | /* | |
1201 | * Remove a potential simple key at the current flow level. | |
1202 | */ | |
1203 | ||
1204 | static int | |
1205 | yaml_parser_remove_simple_key(yaml_parser_t *parser) | |
1206 | { | |
1207 | yaml_simple_key_t *simple_key = parser->simple_keys[parser->flow_level]; | |
1208 | ||
1209 | if (simple_key) | |
1210 | { | |
1211 | /* If the key is required, it is an error. */ | |
1212 | ||
1213 | if (simple_key->required) { | |
1214 | return yaml_parser_set_scanner_error(parser, | |
1215 | "while scanning a simple key", simple_key->mark, | |
1216 | "could not found expected ':'"); | |
1217 | } | |
1218 | ||
1219 | /* Remove the key from the list. */ | |
1220 | ||
1221 | yaml_free(simple_key); | |
1222 | parser->simple_keys[parser->flow_level] = NULL; | |
1223 | } | |
1224 | ||
1225 | return 1; | |
1226 | } | |
1227 | ||
1228 | /* | |
1229 | * Increase the flow level and resize the simple key list if needed. | |
1230 | */ | |
1231 | ||
1232 | static int | |
1233 | yaml_parser_increase_flow_level(yaml_parser_t *parser) | |
1234 | { | |
1235 | /* Check if we need to resize the list. */ | |
1236 | ||
1237 | if (parser->flow_level == parser->simple_keys_size-1) | |
1238 | { | |
1239 | yaml_simple_key_t **new_simple_keys = | |
1240 | yaml_realloc(parser->simple_keys, | |
1241 | sizeof(yaml_simple_key_t *) * parser->simple_keys_size * 2); | |
1242 | ||
1243 | if (!new_simple_keys) { | |
1244 | parser->error = YAML_MEMORY_ERROR; | |
1245 | return 0; | |
1246 | } | |
1247 | ||
1248 | memset(new_simple_keys+parser->simple_keys_size, 0, | |
1249 | sizeof(yaml_simple_key_t *)*parser->simple_keys_size); | |
1250 | ||
1251 | parser->simple_keys = new_simple_keys; | |
1252 | parser->simple_keys_size *= 2; | |
1253 | } | |
1254 | ||
1255 | /* Increase the flow level and reset the simple key. */ | |
1256 | ||
1257 | parser->simple_keys[++parser->flow_level] = NULL; | |
1258 | ||
1259 | return 1; | |
1260 | } | |
1261 | ||
1262 | /* | |
1263 | * Decrease the flow level. | |
1264 | */ | |
1265 | ||
1266 | static int | |
1267 | yaml_parser_decrease_flow_level(yaml_parser_t *parser) | |
1268 | { | |
1269 | assert(parser->flow_level); /* Greater than 0. */ | |
1270 | assert(!parser->simple_keys[parser->flow_level]); /* Must be removed. */ | |
1271 | ||
1272 | parser->flow_level --; | |
1273 | ||
1274 | return 1; | |
1275 | } | |
1276 | ||
1277 | /* | |
1278 | * Add a token to the tail of the tokens queue. | |
1279 | */ | |
1280 | ||
1281 | static int | |
1282 | yaml_parser_append_token(yaml_parser_t *parser, yaml_token_t *token) | |
1283 | { | |
1284 | return yaml_parser_insert_token(parser, -1, token); | |
1285 | } | |
1286 | ||
1287 | /* | |
1288 | * Insert the token into the tokens queue. The number parameter is the | |
1289 | * ordinal number of the token. If the number is equal to -1, add the token | |
1290 | * to the tail of the queue. | |
1291 | */ | |
1292 | ||
1293 | static int | |
1294 | yaml_parser_insert_token(yaml_parser_t *parser, | |
1295 | int number, yaml_token_t *token) | |
1296 | { | |
1297 | /* The index of the token in the queue. */ | |
1298 | ||
1299 | int index = (number == -1) | |
1300 | ? parser->tokens_tail - parser->tokens_head | |
1301 | : number - parser->tokens_parsed; | |
1302 | ||
1303 | assert(index >= 0 && index <= (parser->tokens_tail-parser->tokens_head)); | |
1304 | ||
1305 | /* Check if we need to resize the queue. */ | |
1306 | ||
1307 | if (parser->tokens_head == 0 && parser->tokens_tail == parser->tokens_size) | |
1308 | { | |
1309 | yaml_token_t **new_tokens = yaml_realloc(parser->tokens, | |
1310 | sizeof(yaml_token_t *) * parser->tokens_size * 2); | |
1311 | ||
1312 | if (!new_tokens) { | |
1313 | parser->error = YAML_MEMORY_ERROR; | |
1314 | return 0; | |
1315 | } | |
1316 | ||
1317 | memset(new_tokens+parser->tokens_size, 0, | |
1318 | sizeof(yaml_token_t *)*parser->tokens_size); | |
1319 | ||
1320 | parser->tokens = new_tokens; | |
1321 | parser->tokens_size *= 2; | |
1322 | } | |
1323 | ||
1324 | /* Check if we need to move the queue to the beginning of the buffer. */ | |
1325 | ||
1326 | if (parser->tokens_tail == parser->tokens_size) | |
1327 | { | |
1328 | if (parser->tokens_head < parser->tokens_tail) { | |
1329 | memmove(parser->tokens, parser->tokens+parser->tokens_head, | |
1330 | sizeof(yaml_token_t *)*(parser->tokens_tail-parser->tokens_head)); | |
1331 | } | |
1332 | parser->tokens_tail -= parser->tokens_head; | |
1333 | parser->tokens_head = 0; | |
1334 | } | |
1335 | ||
1336 | /* Check if we need to free space within the queue. */ | |
1337 | ||
1338 | if (index < (parser->tokens_tail-parser->tokens_head)) { | |
1339 | memmove(parser->tokens+parser->tokens_head+index+1, | |
1340 | parser->tokens+parser->tokens_head+index, | |
1341 | sizeof(yaml_token_t *)*(parser->tokens_tail-parser->tokens_head-index)); | |
1342 | } | |
1343 | ||
1344 | /* Insert the token. */ | |
1345 | ||
1346 | parser->tokens[parser->tokens_head+index] = token; | |
1347 | parser->tokens_tail ++; | |
1348 | ||
1349 | return 1; | |
1350 | } | |
1351 | ||
1352 | /* | |
1353 | * Push the current indentation level to the stack and set the new level | |
1354 | * the current column is greater than the indentation level. In this case, | |
1355 | * append or insert the specified token into the token queue. | |
1356 | * | |
1357 | */ | |
1358 | ||
1359 | static int | |
1360 | yaml_parser_roll_indent(yaml_parser_t *parser, int column, | |
1361 | int number, yaml_token_type_t type, yaml_mark_t mark) | |
1362 | { | |
1363 | yaml_token_t *token; | |
1364 | ||
1365 | /* In the flow context, do nothing. */ | |
1366 | ||
1367 | if (parser->flow_level) | |
1368 | return 1; | |
1369 | ||
1370 | if (parser->indent < column) | |
1371 | { | |
1372 | /* Check if we need to expand the indents stack. */ | |
1373 | ||
1374 | if (parser->indents_length == parser->indents_size) | |
1375 | { | |
1376 | int *new_indents = yaml_realloc(parser->indents, | |
1377 | sizeof(int) * parser->indents_size * 2); | |
1378 | ||
1379 | if (!new_indents) { | |
1380 | parser->error = YAML_MEMORY_ERROR; | |
1381 | return 0; | |
1382 | } | |
1383 | ||
1384 | memset(new_indents+parser->indents_size, 0, | |
1385 | sizeof(int)*parser->indents_size); | |
1386 | ||
1387 | parser->indents = new_indents; | |
1388 | parser->indents_size *= 2; | |
1389 | } | |
1390 | ||
1391 | /* | |
1392 | * Push the current indentation level to the stack and set the new | |
1393 | * indentation level. | |
1394 | */ | |
1395 | ||
1396 | parser->indents[parser->indents_length++] = parser->indent; | |
1397 | parser->indent = column; | |
1398 | ||
1399 | /* Create a token. */ | |
1400 | ||
1401 | token = yaml_token_new(type, mark, mark); | |
1402 | if (!token) { | |
1403 | parser->error = YAML_MEMORY_ERROR; | |
1404 | return 0; | |
1405 | } | |
1406 | ||
1407 | /* Insert the token into the queue. */ | |
1408 | ||
1409 | if (!yaml_parser_insert_token(parser, number, token)) { | |
1410 | yaml_token_delete(token); | |
1411 | return 0; | |
1412 | } | |
1413 | } | |
1414 | ||
1415 | return 1; | |
1416 | } | |
1417 | ||
1418 | /* | |
1419 | * Pop indentation levels from the indents stack until the current level | |
1420 | * becomes less or equal to the column. For each intendation level, append | |
1421 | * the BLOCK-END token. | |
1422 | */ | |
1423 | ||
1424 | ||
1425 | static int | |
1426 | yaml_parser_unroll_indent(yaml_parser_t *parser, int column) | |
1427 | { | |
1428 | yaml_token_t *token; | |
1429 | ||
1430 | /* In the flow context, do nothing. */ | |
1431 | ||
1432 | if (parser->flow_level) | |
1433 | return 1; | |
1434 | ||
1435 | /* Loop through the intendation levels in the stack. */ | |
1436 | ||
1437 | while (parser->indent > column) | |
1438 | { | |
1439 | yaml_mark_t mark = yaml_parser_get_mark(parser); | |
1440 | ||
1441 | /* Create a token. */ | |
1442 | ||
1443 | token = yaml_token_new(YAML_BLOCK_END_TOKEN, mark, mark); | |
1444 | if (!token) { | |
1445 | parser->error = YAML_MEMORY_ERROR; | |
1446 | return 0; | |
1447 | } | |
1448 | ||
1449 | /* Append the token to the queue. */ | |
1450 | ||
1451 | if (!yaml_parser_append_token(parser, token)) { | |
1452 | yaml_token_delete(token); | |
1453 | return 0; | |
1454 | } | |
1455 | ||
1456 | /* Pop the indentation level. */ | |
1457 | ||
1458 | assert(parser->indents_length); /* Non-empty stack expected. */ | |
1459 | ||
1460 | parser->indent = parser->indents[--parser->indents_length]; | |
1461 | } | |
1462 | ||
1463 | return 1; | |
1464 | } | |
1465 | ||
1466 | /* | |
1467 | * Initialize the scanner and produce the STREAM-START token. | |
1468 | */ | |
1469 | ||
1470 | static int | |
1471 | yaml_parser_fetch_stream_start(yaml_parser_t *parser) | |
1472 | { | |
1473 | yaml_mark_t mark = yaml_parser_get_mark(parser); | |
1474 | yaml_token_t *token; | |
1475 | ||
1476 | /* Set the initial indentation. */ | |
1477 | ||
1478 | parser->indent = -1; | |
1479 | ||
1480 | /* A simple key is allowed at the beginning of the stream. */ | |
1481 | ||
1482 | parser->simple_key_allowed = 1; | |
1483 | ||
1484 | /* We have started. */ | |
1485 | ||
1486 | parser->stream_start_produced = 1; | |
1487 | ||
1488 | /* Create the STREAM-START token. */ | |
1489 | ||
1490 | token = yaml_stream_start_token_new(parser->encoding, mark, mark); | |
1491 | if (!token) { | |
1492 | parser->error = YAML_MEMORY_ERROR; | |
1493 | return 0; | |
1494 | } | |
1495 | ||
1496 | /* Append the token to the queue. */ | |
1497 | ||
1498 | if (!yaml_parser_append_token(parser, token)) { | |
1499 | yaml_token_delete(token); | |
1500 | return 0; | |
1501 | } | |
1502 | ||
1503 | return 1; | |
1504 | } | |
1505 | ||
1506 | /* | |
1507 | * Produce the STREAM-END token and shut down the scanner. | |
1508 | */ | |
1509 | ||
1510 | static int | |
1511 | yaml_parser_fetch_stream_end(yaml_parser_t *parser) | |
1512 | { | |
1513 | yaml_mark_t mark = yaml_parser_get_mark(parser); | |
1514 | yaml_token_t *token; | |
1515 | ||
1516 | /* Reset the indentation level. */ | |
1517 | ||
1518 | if (!yaml_parser_unroll_indent(parser, -1)) | |
1519 | return 0; | |
1520 | ||
1521 | /* We have finished. */ | |
1522 | ||
1523 | parser->stream_end_produced = 1; | |
1524 | ||
1525 | /* Create the STREAM-END token. */ | |
1526 | ||
1527 | token = yaml_stream_end_token_new(mark, mark); | |
1528 | if (!token) { | |
1529 | parser->error = YAML_MEMORY_ERROR; | |
1530 | return 0; | |
1531 | } | |
1532 | ||
1533 | /* Append the token to the queue. */ | |
1534 | ||
1535 | if (!yaml_parser_append_token(parser, token)) { | |
1536 | yaml_token_delete(token); | |
1537 | return 0; | |
1538 | } | |
1539 | ||
1540 | return 1; | |
1541 | } | |
1542 | ||
1543 | /* | |
1544 | * Produce the YAML-DIRECTIVE or TAG-DIRECTIVE token. | |
1545 | */ | |
1546 | ||
1547 | static int | |
1548 | yaml_parser_fetch_directive(yaml_parser_t *parser) | |
1549 | { | |
1550 | yaml_token_t *token; | |
1551 | ||
1552 | /* Reset the indentation level. */ | |
1553 | ||
1554 | if (!yaml_parser_unroll_indent(parser, -1)) | |
1555 | return 0; | |
1556 | ||
1557 | /* Reset simple keys. */ | |
1558 | ||
1559 | if (!yaml_parser_remove_simple_key(parser)) | |
1560 | return 0; | |
1561 | ||
1562 | parser->simple_key_allowed = 0; | |
1563 | ||
1564 | /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */ | |
1565 | ||
1566 | token = yaml_parser_scan_directive(parser); | |
1567 | if (!token) return 0; | |
1568 | ||
1569 | /* Append the token to the queue. */ | |
1570 | ||
1571 | if (!yaml_parser_append_token(parser, token)) { | |
1572 | yaml_token_delete(token); | |
1573 | return 0; | |
1574 | } | |
1575 | ||
1576 | return 1; | |
1577 | } | |
1578 | ||
1579 | /* | |
1580 | * Produce the DOCUMENT-START or DOCUMENT-END token. | |
1581 | */ | |
1582 | ||
1583 | static int | |
1584 | yaml_parser_fetch_document_indicator(yaml_parser_t *parser, | |
1585 | yaml_token_type_t type) | |
1586 | { | |
1587 | yaml_mark_t start_mark, end_mark; | |
1588 | yaml_token_t *token; | |
1589 | ||
1590 | /* Reset the indentation level. */ | |
1591 | ||
1592 | if (!yaml_parser_unroll_indent(parser, -1)) | |
1593 | return 0; | |
1594 | ||
1595 | /* Reset simple keys. */ | |
1596 | ||
1597 | if (!yaml_parser_remove_simple_key(parser)) | |
1598 | return 0; | |
1599 | ||
1600 | parser->simple_key_allowed = 0; | |
1601 | ||
1602 | /* Consume the token. */ | |
1603 | ||
1604 | start_mark = yaml_parser_get_mark(parser); | |
1605 | ||
1606 | FORWARD(parser); | |
1607 | FORWARD(parser); | |
1608 | FORWARD(parser); | |
1609 | ||
1610 | end_mark = yaml_parser_get_mark(parser); | |
1611 | ||
1612 | /* Create the DOCUMENT-START or DOCUMENT-END token. */ | |
1613 | ||
1614 | token = yaml_token_new(type, start_mark, end_mark); | |
1615 | if (!token) { | |
1616 | parser->error = YAML_MEMORY_ERROR; | |
1617 | return 0; | |
1618 | } | |
1619 | ||
1620 | /* Append the token to the queue. */ | |
1621 | ||
1622 | if (!yaml_parser_append_token(parser, token)) { | |
1623 | yaml_token_delete(token); | |
1624 | return 0; | |
1625 | } | |
1626 | ||
1627 | return 1; | |
1628 | } | |
1629 | ||
1630 | /* | |
1631 | * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token. | |
1632 | */ | |
1633 | ||
1634 | static int | |
1635 | yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, | |
1636 | yaml_token_type_t type) | |
1637 | { | |
1638 | yaml_mark_t start_mark, end_mark; | |
1639 | yaml_token_t *token; | |
1640 | ||
1641 | /* The indicators '[' and '{' may start a simple key. */ | |
1642 | ||
1643 | if (!yaml_parser_save_simple_key(parser)) | |
1644 | return 0; | |
1645 | ||
1646 | /* Increase the flow level. */ | |
1647 | ||
1648 | if (!yaml_parser_increase_flow_level(parser)) | |
1649 | return 0; | |
1650 | ||
1651 | /* A simple key may follow the indicators '[' and '{'. */ | |
1652 | ||
1653 | parser->simple_key_allowed = 1; | |
1654 | ||
1655 | /* Consume the token. */ | |
1656 | ||
1657 | start_mark = yaml_parser_get_mark(parser); | |
1658 | FORWARD(parser); | |
1659 | end_mark = yaml_parser_get_mark(parser); | |
1660 | ||
1661 | /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */ | |
1662 | ||
1663 | token = yaml_token_new(type, start_mark, end_mark); | |
1664 | if (!token) { | |
1665 | parser->error = YAML_MEMORY_ERROR; | |
1666 | return 0; | |
1667 | } | |
1668 | ||
1669 | /* Append the token to the queue. */ | |
1670 | ||
1671 | if (!yaml_parser_append_token(parser, token)) { | |
1672 | yaml_token_delete(token); | |
1673 | return 0; | |
1674 | } | |
1675 | ||
1676 | return 1; | |
1677 | } | |
1678 | ||
1679 | /* | |
1680 | * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token. | |
1681 | */ | |
1682 | ||
1683 | static int | |
1684 | yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, | |
1685 | yaml_token_type_t type) | |
1686 | { | |
1687 | yaml_mark_t start_mark, end_mark; | |
1688 | yaml_token_t *token; | |
1689 | ||
1690 | /* Reset any potential simple key on the current flow level. */ | |
1691 | ||
1692 | if (!yaml_parser_remove_simple_key(parser)) | |
1693 | return 0; | |
1694 | ||
1695 | /* Decrease the flow level. */ | |
1696 | ||
1697 | if (!yaml_parser_decrease_flow_level(parser)) | |
1698 | return 0; | |
1699 | ||
1700 | /* No simple keys after the indicators ']' and '}'. */ | |
1701 | ||
1702 | parser->simple_key_allowed = 0; | |
1703 | ||
1704 | /* Consume the token. */ | |
1705 | ||
1706 | start_mark = yaml_parser_get_mark(parser); | |
1707 | FORWARD(parser); | |
1708 | end_mark = yaml_parser_get_mark(parser); | |
1709 | ||
1710 | /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */ | |
1711 | ||
1712 | token = yaml_token_new(type, start_mark, end_mark); | |
1713 | if (!token) { | |
1714 | parser->error = YAML_MEMORY_ERROR; | |
1715 | return 0; | |
1716 | } | |
1717 | ||
1718 | /* Append the token to the queue. */ | |
1719 | ||
1720 | if (!yaml_parser_append_token(parser, token)) { | |
1721 | yaml_token_delete(token); | |
1722 | return 0; | |
1723 | } | |
1724 | ||
1725 | return 1; | |
1726 | } | |
1727 | ||
1728 | /* | |
1729 | * Produce the FLOW-ENTRY token. | |
1730 | */ | |
1731 | ||
1732 | static int | |
1733 | yaml_parser_fetch_flow_entry(yaml_parser_t *parser) | |
1734 | { | |
1735 | yaml_mark_t start_mark, end_mark; | |
1736 | yaml_token_t *token; | |
1737 | ||
1738 | /* Reset any potential simple keys on the current flow level. */ | |
1739 | ||
1740 | if (!yaml_parser_remove_simple_key(parser)) | |
1741 | return 0; | |
1742 | ||
1743 | /* Simple keys are allowed after ','. */ | |
1744 | ||
1745 | parser->simple_key_allowed = 1; | |
1746 | ||
1747 | /* Consume the token. */ | |
1748 | ||
1749 | start_mark = yaml_parser_get_mark(parser); | |
1750 | FORWARD(parser); | |
1751 | end_mark = yaml_parser_get_mark(parser); | |
1752 | ||
1753 | /* Create the FLOW-ENTRY token. */ | |
1754 | ||
1755 | token = yaml_token_new(YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark); | |
1756 | if (!token) { | |
1757 | parser->error = YAML_MEMORY_ERROR; | |
1758 | return 0; | |
1759 | } | |
1760 | ||
1761 | /* Append the token to the queue. */ | |
1762 | ||
1763 | if (!yaml_parser_append_token(parser, token)) { | |
1764 | yaml_token_delete(token); | |
1765 | return 0; | |
1766 | } | |
1767 | ||
1768 | return 1; | |
1769 | } | |
1770 | ||
1771 | /* | |
1772 | * Produce the BLOCK-ENTRY token. | |
1773 | */ | |
1774 | ||
1775 | static int | |
1776 | yaml_parser_fetch_block_entry(yaml_parser_t *parser) | |
1777 | { | |
1778 | yaml_mark_t start_mark, end_mark; | |
1779 | yaml_token_t *token; | |
1780 | ||
1781 | /* Check if the scanner is in the block context. */ | |
1782 | ||
1783 | if (!parser->flow_level) | |
1784 | { | |
1785 | /* Check if we are allowed to start a new entry. */ | |
1786 | ||
1787 | if (!parser->simple_key_allowed) { | |
1788 | return yaml_parser_set_scanner_error(parser, NULL, | |
1789 | yaml_parser_get_mark(parser), | |
1790 | "block sequence entries are not allowed in this context"); | |
1791 | } | |
1792 | ||
1793 | /* Add the BLOCK-SEQUENCE-START token if needed. */ | |
1794 | ||
1795 | if (!yaml_parser_roll_indent(parser, parser->column, -1, | |
1796 | YAML_BLOCK_SEQUENCE_START_TOKEN, yaml_parser_get_mark(parser))) | |
1797 | return 0; | |
1798 | } | |
1799 | else | |
1800 | { | |
1801 | /* | |
1802 | * It is an error for the '-' indicator to occur in the flow context, | |
1803 | * but we let the Parser detect and report about it because the Parser | |
1804 | * is able to point to the context. | |
1805 | */ | |
1806 | } | |
1807 | ||
1808 | /* Reset any potential simple keys on the current flow level. */ | |
1809 | ||
1810 | if (!yaml_parser_remove_simple_key(parser)) | |
1811 | return 0; | |
1812 | ||
1813 | /* Simple keys are allowed after '-'. */ | |
1814 | ||
1815 | parser->simple_key_allowed = 1; | |
1816 | ||
1817 | /* Consume the token. */ | |
1818 | ||
1819 | start_mark = yaml_parser_get_mark(parser); | |
1820 | FORWARD(parser); | |
1821 | end_mark = yaml_parser_get_mark(parser); | |
1822 | ||
1823 | /* Create the BLOCK-ENTRY token. */ | |
1824 | ||
1825 | token = yaml_token_new(YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark); | |
1826 | if (!token) { | |
1827 | parser->error = YAML_MEMORY_ERROR; | |
1828 | return 0; | |
1829 | } | |
1830 | ||
1831 | /* Append the token to the queue. */ | |
1832 | ||
1833 | if (!yaml_parser_append_token(parser, token)) { | |
1834 | yaml_token_delete(token); | |
1835 | return 0; | |
1836 | } | |
1837 | ||
1838 | return 1; | |
1839 | } | |
1840 | ||
1841 | /* | |
1842 | * Produce the KEY token. | |
1843 | */ | |
1844 | ||
1845 | static int | |
1846 | yaml_parser_fetch_key(yaml_parser_t *parser) | |
1847 | { | |
1848 | yaml_mark_t start_mark, end_mark; | |
1849 | yaml_token_t *token; | |
1850 | ||
1851 | /* In the block context, additional checks are required. */ | |
1852 | ||
1853 | if (!parser->flow_level) | |
1854 | { | |
1855 | /* Check if we are allowed to start a new key (not nessesary simple). */ | |
1856 | ||
1857 | if (!parser->simple_key_allowed) { | |
1858 | return yaml_parser_set_scanner_error(parser, NULL, | |
1859 | yaml_parser_get_mark(parser), | |
1860 | "mapping keys are not allowed in this context"); | |
1861 | } | |
1862 | ||
1863 | /* Add the BLOCK-MAPPING-START token if needed. */ | |
1864 | ||
1865 | if (!yaml_parser_roll_indent(parser, parser->column, -1, | |
1866 | YAML_BLOCK_MAPPING_START_TOKEN, yaml_parser_get_mark(parser))) | |
1867 | return 0; | |
1868 | } | |
1869 | ||
1870 | /* Reset any potential simple keys on the current flow level. */ | |
1871 | ||
1872 | if (!yaml_parser_remove_simple_key(parser)) | |
1873 | return 0; | |
1874 | ||
1875 | /* Simple keys are allowed after '?' in the block context. */ | |
1876 | ||
1877 | parser->simple_key_allowed = (!parser->flow_level); | |
1878 | ||
1879 | /* Consume the token. */ | |
1880 | ||
1881 | start_mark = yaml_parser_get_mark(parser); | |
1882 | FORWARD(parser); | |
1883 | end_mark = yaml_parser_get_mark(parser); | |
1884 | ||
1885 | /* Create the KEY token. */ | |
1886 | ||
1887 | token = yaml_token_new(YAML_KEY_TOKEN, start_mark, end_mark); | |
1888 | if (!token) { | |
1889 | parser->error = YAML_MEMORY_ERROR; | |
1890 | return 0; | |
1891 | } | |
1892 | ||
1893 | /* Append the token to the queue. */ | |
1894 | ||
1895 | if (!yaml_parser_append_token(parser, token)) { | |
1896 | yaml_token_delete(token); | |
1897 | return 0; | |
1898 | } | |
1899 | ||
1900 | return 1; | |
1901 | } | |
1902 | ||
1903 | /* | |
1904 | * Produce the VALUE token. | |
1905 | */ | |
1906 | ||
1907 | static int | |
1908 | yaml_parser_fetch_value(yaml_parser_t *parser) | |
1909 | { | |
1910 | yaml_mark_t start_mark, end_mark; | |
1911 | yaml_token_t *token; | |
1912 | ||
1913 | /* Have we found a simple key? */ | |
1914 | ||
1915 | if (parser->simple_keys[parser->flow_level]) | |
1916 | { | |
1917 | yaml_simple_key_t *simple_key = parser->simple_keys[parser->flow_level]; | |
1918 | ||
1919 | /* Create the KEY token. */ | |
1920 | ||
1921 | token = yaml_token_new(YAML_KEY_TOKEN, simple_key->mark, simple_key->mark); | |
1922 | if (!token) { | |
1923 | parser->error = YAML_MEMORY_ERROR; | |
1924 | return 0; | |
1925 | } | |
1926 | ||
1927 | /* Insert the token into the queue. */ | |
1928 | ||
1929 | if (!yaml_parser_insert_token(parser, simple_key->token_number, token)) { | |
1930 | yaml_token_delete(token); | |
1931 | return 0; | |
1932 | } | |
1933 | ||
1934 | /* In the block context, we may need to add the BLOCK-MAPPING-START token. */ | |
1935 | ||
1936 | if (!yaml_parser_roll_indent(parser, parser->column, | |
1937 | simple_key->token_number, | |
1938 | YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark)) | |
1939 | return 0; | |
1940 | ||
1941 | /* Remove the simple key from the list. */ | |
1942 | ||
1943 | if (!yaml_parser_remove_simple_key(parser)) return 0; | |
1944 | ||
1945 | /* A simple key cannot follow another simple key. */ | |
1946 | ||
1947 | parser->simple_key_allowed = 0; | |
1948 | } | |
1949 | else | |
1950 | { | |
1951 | /* The ':' indicator follows a complex key. */ | |
1952 | ||
1953 | /* In the block context, extra checks are required. */ | |
1954 | ||
1955 | if (!parser->flow_level) | |
1956 | { | |
1957 | /* Check if we are allowed to start a complex value. */ | |
1958 | ||
1959 | if (!parser->simple_key_allowed) { | |
1960 | return yaml_parser_set_scanner_error(parser, NULL, | |
1961 | yaml_parser_get_mark(parser), | |
1962 | "mapping values are not allowed in this context"); | |
1963 | } | |
1964 | ||
1965 | /* Add the BLOCK-MAPPING-START token if needed. */ | |
1966 | ||
1967 | if (!yaml_parser_roll_indent(parser, parser->column, -1, | |
1968 | YAML_BLOCK_MAPPING_START_TOKEN, yaml_parser_get_mark(parser))) | |
1969 | return 0; | |
1970 | } | |
1971 | ||
1972 | /* Remove a potential simple key from the list. */ | |
1973 | ||
1974 | if (!yaml_parser_remove_simple_key(parser)) return 0; | |
1975 | ||
1976 | /* Simple keys after ':' are allowed in the block context. */ | |
1977 | ||
1978 | parser->simple_key_allowed = (!parser->flow_level); | |
1979 | } | |
1980 | ||
1981 | /* Consume the token. */ | |
1982 | ||
1983 | start_mark = yaml_parser_get_mark(parser); | |
1984 | FORWARD(parser); | |
1985 | end_mark = yaml_parser_get_mark(parser); | |
1986 | ||
1987 | /* Create the VALUE token. */ | |
1988 | ||
1989 | token = yaml_token_new(YAML_VALUE_TOKEN, start_mark, end_mark); | |
1990 | if (!token) { | |
1991 | parser->error = YAML_MEMORY_ERROR; | |
1992 | return 0; | |
1993 | } | |
1994 | ||
1995 | /* Append the token to the queue. */ | |
1996 | ||
1997 | if (!yaml_parser_append_token(parser, token)) { | |
1998 | yaml_token_delete(token); | |
1999 | return 0; | |
2000 | } | |
2001 | ||
2002 | return 1; | |
2003 | } | |
2004 | ||
2005 | /* | |
2006 | * Produce the ALIAS or ANCHOR token. | |
2007 | */ | |
2008 | ||
2009 | static int | |
2010 | yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type) | |
2011 | { | |
2012 | yaml_token_t *token; | |
2013 | ||
2014 | /* An anchor or an alias could be a simple key. */ | |
2015 | ||
2016 | if (!yaml_parser_save_simple_key(parser)) | |
2017 | return 0; | |
2018 | ||
2019 | /* A simple key cannot follow an anchor or an alias. */ | |
2020 | ||
2021 | parser->simple_key_allowed = 0; | |
2022 | ||
2023 | /* Create the ALIAS or ANCHOR token. */ | |
2024 | ||
2025 | token = yaml_parser_scan_anchor(parser, type); | |
2026 | if (!token) return 0; | |
2027 | ||
2028 | /* Append the token to the queue. */ | |
2029 | ||
2030 | if (!yaml_parser_append_token(parser, token)) { | |
2031 | yaml_token_delete(token); | |
2032 | return 0; | |
2033 | } | |
2034 | ||
2035 | return 1; | |
2036 | } | |
2037 | ||
2038 | /* | |
2039 | * Produce the TAG token. | |
2040 | */ | |
2041 | ||
2042 | static int | |
2043 | yaml_parser_fetch_tag(yaml_parser_t *parser) | |
2044 | { | |
2045 | yaml_token_t *token; | |
2046 | ||
2047 | /* A tag could be a simple key. */ | |
2048 | ||
2049 | if (!yaml_parser_save_simple_key(parser)) | |
2050 | return 0; | |
2051 | ||
2052 | /* A simple key cannot follow a tag. */ | |
2053 | ||
2054 | parser->simple_key_allowed = 0; | |
2055 | ||
2056 | /* Create the TAG token. */ | |
2057 | ||
2058 | token = yaml_parser_scan_tag(parser); | |
2059 | if (!token) return 0; | |
2060 | ||
2061 | /* Append the token to the queue. */ | |
2062 | ||
2063 | if (!yaml_parser_append_token(parser, token)) { | |
2064 | yaml_token_delete(token); | |
2065 | return 0; | |
2066 | } | |
2067 | ||
2068 | return 1; | |
2069 | } | |
2070 | ||
2071 | /* | |
2072 | * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens. | |
2073 | */ | |
2074 | ||
2075 | static int | |
2076 | yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal) | |
2077 | { | |
2078 | yaml_token_t *token; | |
2079 | ||
2080 | /* Remove any potential simple keys. */ | |
2081 | ||
2082 | if (!yaml_parser_remove_simple_key(parser)) | |
2083 | return 0; | |
2084 | ||
2085 | /* A simple key may follow a block scalar. */ | |
2086 | ||
2087 | parser->simple_key_allowed = 1; | |
2088 | ||
2089 | /* Create the SCALAR token. */ | |
2090 | ||
2091 | token = yaml_parser_scan_block_scalar(parser, literal); | |
2092 | if (!token) return 0; | |
2093 | ||
2094 | /* Append the token to the queue. */ | |
2095 | ||
2096 | if (!yaml_parser_append_token(parser, token)) { | |
2097 | yaml_token_delete(token); | |
2098 | return 0; | |
2099 | } | |
2100 | ||
2101 | return 1; | |
2102 | } | |
2103 | ||
2104 | /* | |
2105 | * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens. | |
2106 | */ | |
2107 | ||
2108 | static int | |
2109 | yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single) | |
2110 | { | |
2111 | yaml_token_t *token; | |
2112 | ||
2113 | /* A plain scalar could be a simple key. */ | |
2114 | ||
2115 | if (!yaml_parser_save_simple_key(parser)) | |
2116 | return 0; | |
2117 | ||
2118 | /* A simple key cannot follow a flow scalar. */ | |
2119 | ||
2120 | parser->simple_key_allowed = 0; | |
2121 | ||
2122 | /* Create the SCALAR token. */ | |
2123 | ||
2124 | token = yaml_parser_scan_flow_scalar(parser, single); | |
2125 | if (!token) return 0; | |
2126 | ||
2127 | /* Append the token to the queue. */ | |
2128 | ||
2129 | if (!yaml_parser_append_token(parser, token)) { | |
2130 | yaml_token_delete(token); | |
2131 | return 0; | |
2132 | } | |
2133 | ||
2134 | return 1; | |
2135 | } | |
2136 | ||
2137 | /* | |
2138 | * Produce the SCALAR(...,plain) token. | |
2139 | */ | |
2140 | ||
2141 | static int | |
2142 | yaml_parser_fetch_plain_scalar(yaml_parser_t *parser) | |
2143 | { | |
2144 | yaml_token_t *token; | |
2145 | ||
2146 | /* A plain scalar could be a simple key. */ | |
2147 | ||
2148 | if (!yaml_parser_save_simple_key(parser)) | |
2149 | return 0; | |
2150 | ||
2151 | /* A simple key cannot follow a flow scalar. */ | |
2152 | ||
2153 | parser->simple_key_allowed = 0; | |
2154 | ||
2155 | /* Create the SCALAR token. */ | |
2156 | ||
2157 | token = yaml_parser_scan_plain_scalar(parser); | |
2158 | if (!token) return 0; | |
2159 | ||
2160 | /* Append the token to the queue. */ | |
2161 | ||
2162 | if (!yaml_parser_append_token(parser, token)) { | |
2163 | yaml_token_delete(token); | |
2164 | return 0; | |
2165 | } | |
2166 | ||
2167 | return 1; | |
2168 | } | |
2169 |