@@ -1,3578 +0,0 @@
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.
10− * The process of transforming a YAML stream into a sequence of events is
11− * divided on two steps: Scanning and Parsing.
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.
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).
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.
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.
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 # '}'
45− * KEY # '?' or nothing (simple keys).
47− * ALIAS(anchor) # '*anchor'
48− * ANCHOR(anchor) # '&anchor'
49− * TAG(handle,suffix) # '!handle!suffix'
50− * SCALAR(value,style) # A scalar.
52− * The following two tokens are "virtual" tokens denoting the beginning and the
55− * STREAM-START(encoding)
58− * We pass the information about the input stream encoding with the
59− * STREAM-START token.
61− * The next two tokens are responsible for tags:
63− * VERSION-DIRECTIVE(major,minor)
64− * TAG-DIRECTIVE(handle,prefix)
70− * %TAG !yaml! tag:yaml.org,2002:
73− * The corresponding sequence of tokens:
75− * STREAM-START(utf-8)
76− * VERSION-DIRECTIVE(1,1)
77− * TAG-DIRECTIVE("!","!foo")
78− * TAG-DIRECTIVE("!yaml","tag:yaml.org,2002:")
82− * Note that the VERSION-DIRECTIVE and TAG-DIRECTIVE tokens occupy a whole
85− * The document start and end indicators are represented by:
90− * Note that if a YAML stream contains an implicit document (without '---'
91− * and '...' indicators), no DOCUMENT-START and DOCUMENT-END tokens will be
94− * In the following examples, we present whole documents together with the
97− * 1. An implicit document:
103− * STREAM-START(utf-8)
104− * SCALAR("a scalar",single-quoted)
107− * 2. An explicit document:
115− * STREAM-START(utf-8)
117− * SCALAR("a scalar",single-quoted)
121− * 3. Several documents in a stream:
127− * 'yet another scalar'
131− * STREAM-START(utf-8)
132− * SCALAR("a scalar",single-quoted)
134− * SCALAR("another scalar",single-quoted)
136− * SCALAR("yet another scalar",single-quoted)
139− * We have already introduced the SCALAR token above. The following tokens are
140− * used to describe aliases, anchors, tag, and scalars:
144− * TAG(handle,suffix)
145− * SCALAR(value,style)
147− * The following series of examples illustrate the usage of these tokens:
149− * 1. A recursive sequence:
155− * STREAM-START(utf-8)
157− * FLOW-SEQUENCE-START
162− * 2. A tagged scalar:
164− * !!float "3.14" # A good approximation.
168− * STREAM-START(utf-8)
170− * SCALAR("3.14",double-quoted)
173− * 3. Various scalar styles:
175− * --- # Implicit empty plain scalars do not produce tokens.
176− * --- a plain scalar
177− * --- 'a single-quoted scalar'
178− * --- "a double-quoted scalar"
187− * STREAM-START(utf-8)
190− * SCALAR("a plain scalar",plain)
192− * SCALAR("a single-quoted scalar",single-quoted)
194− * SCALAR("a double-quoted scalar",double-quoted)
196− * SCALAR("a literal scalar",literal)
198− * SCALAR("a folded scalar",folded)
201− * Now it's time to review collection-related tokens. We will start with
204− * FLOW-SEQUENCE-START
206− * FLOW-MAPPING-START
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.
218− * The following examples show flow collections:
220− * 1. A flow sequence:
222− * [item 1, item 2, item 3]
226− * STREAM-START(utf-8)
227− * FLOW-SEQUENCE-START
228− * SCALAR("item 1",plain)
230− * SCALAR("item 2",plain)
232− * SCALAR("item 3",plain)
236− * 2. A flow mapping:
239− * a simple key: a value, # Note that the KEY token is produced.
240− * ? a complex key: another value,
245− * STREAM-START(utf-8)
246− * FLOW-MAPPING-START
248− * SCALAR("a simple key",plain)
250− * SCALAR("a value",plain)
253− * SCALAR("a complex key",plain)
255− * SCALAR("another value",plain)
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.
263− * For scanning block collections, the following tokens are used (note that we
264− * repeat KEY and VALUE here):
266− * BLOCK-SEQUENCE-START
267− * BLOCK-MAPPING-START
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.
279− * The tokens BLOCK-ENTRY, KEY, and VALUE are used to represent the indicators
280− * '-', '?', and ':' correspondingly.
282− * The following examples show how the tokens BLOCK-SEQUENCE-START,
283− * BLOCK-MAPPING-START, and BLOCK-END are emitted by the Scanner:
285− * 1. Block sequences:
298− * STREAM-START(utf-8)
299− * BLOCK-SEQUENCE-START
301− * SCALAR("item 1",plain)
303− * SCALAR("item 2",plain)
305− * BLOCK-SEQUENCE-START
307− * SCALAR("item 3.1",plain)
309− * SCALAR("item 3.2",plain)
312− * BLOCK-MAPPING-START
314− * SCALAR("key 1",plain)
316− * SCALAR("value 1",plain)
318− * SCALAR("key 2",plain)
320− * SCALAR("value 2",plain)
325− * 2. Block mappings:
327− * a simple key: a value # The KEY token is produced here.
339− * STREAM-START(utf-8)
340− * BLOCK-MAPPING-START
342− * SCALAR("a simple key",plain)
344− * SCALAR("a value",plain)
346− * SCALAR("a complex key",plain)
348− * SCALAR("another value",plain)
350− * SCALAR("a mapping",plain)
351− * BLOCK-MAPPING-START
353− * SCALAR("key 1",plain)
355− * SCALAR("value 1",plain)
357− * SCALAR("key 2",plain)
359− * SCALAR("value 2",plain)
362− * SCALAR("a sequence",plain)
364− * BLOCK-SEQUENCE-START
366− * SCALAR("item 1",plain)
368− * SCALAR("item 2",plain)
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:
378− * 1. Collections in a sequence:
389− * STREAM-START(utf-8)
390− * BLOCK-SEQUENCE-START
392− * BLOCK-SEQUENCE-START
394− * SCALAR("item 1",plain)
396− * SCALAR("item 2",plain)
399− * BLOCK-MAPPING-START
401− * SCALAR("key 1",plain)
403− * SCALAR("value 1",plain)
405− * SCALAR("key 2",plain)
407− * SCALAR("value 2",plain)
410− * BLOCK-MAPPING-START
412− * SCALAR("complex key")
414− * SCALAR("complex value")
419− * 2. Collections in a mapping:
430− * STREAM-START(utf-8)
431− * BLOCK-MAPPING-START
433− * SCALAR("a sequence",plain)
435− * BLOCK-SEQUENCE-START
437− * SCALAR("item 1",plain)
439− * SCALAR("item 2",plain)
442− * SCALAR("a mapping",plain)
444− * BLOCK-MAPPING-START
446− * SCALAR("key 1",plain)
448− * SCALAR("value 1",plain)
450− * SCALAR("key 2",plain)
452− * SCALAR("value 2",plain)
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:
461− * - item 1 # BLOCK-SEQUENCE-START is NOT produced here.
466− * STREAM-START(utf-8)
467− * BLOCK-MAPPING-START
469− * SCALAR("key",plain)
472− * SCALAR("item 1",plain)
474− * SCALAR("item 2",plain)
478−#include "yaml_private.h"
481− * Ensure that the buffer contains the required number of characters.
482− * Return 1 on success, 0 on failure (reader error or memory error).
485−#define CACHE(parser,length) \
486− (parser->unread >= (length) \
488− : yaml_parser_update_buffer(parser, (length)))
491− * Advance the buffer pointer.
494−#define SKIP(parser) \
495− (parser->mark.index ++, \
496− parser->mark.column ++, \
497− parser->unread --, \
498− parser->buffer.pointer += WIDTH(parser->buffer))
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)
515− * Copy a character to a string buffer and advance pointers.
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 --, \
527− * Copy a line break character to a string buffer and advance pointers.
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), \
570− * Public API declarations.
574−yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token);
581−yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context,
582− yaml_mark_t context_mark, const char *problem);
585− * High-level token API.
589−yaml_parser_fetch_more_tokens(yaml_parser_t *parser);
592−yaml_parser_fetch_next_token(yaml_parser_t *parser);
595− * Potential simple keys.
599−yaml_parser_stale_simple_keys(yaml_parser_t *parser);
602−yaml_parser_save_simple_key(yaml_parser_t *parser);
605−yaml_parser_remove_simple_key(yaml_parser_t *parser);
608−yaml_parser_increase_flow_level(yaml_parser_t *parser);
611−yaml_parser_decrease_flow_level(yaml_parser_t *parser);
614− * Indentation treatment.
618−yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column,
619− ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark);
622−yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column);
629−yaml_parser_fetch_stream_start(yaml_parser_t *parser);
632−yaml_parser_fetch_stream_end(yaml_parser_t *parser);
635−yaml_parser_fetch_directive(yaml_parser_t *parser);
638−yaml_parser_fetch_document_indicator(yaml_parser_t *parser,
639− yaml_token_type_t type);
642−yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser,
643− yaml_token_type_t type);
646−yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser,
647− yaml_token_type_t type);
650−yaml_parser_fetch_flow_entry(yaml_parser_t *parser);
653−yaml_parser_fetch_block_entry(yaml_parser_t *parser);
656−yaml_parser_fetch_key(yaml_parser_t *parser);
659−yaml_parser_fetch_value(yaml_parser_t *parser);
662−yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type);
665−yaml_parser_fetch_tag(yaml_parser_t *parser);
668−yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal);
671−yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single);
674−yaml_parser_fetch_plain_scalar(yaml_parser_t *parser);
681−yaml_parser_scan_to_next_token(yaml_parser_t *parser);
684−yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token);
687−yaml_parser_scan_directive_name(yaml_parser_t *parser,
688− yaml_mark_t start_mark, yaml_char_t **name);
691−yaml_parser_scan_version_directive_value(yaml_parser_t *parser,
692− yaml_mark_t start_mark, int *major, int *minor);
695−yaml_parser_scan_version_directive_number(yaml_parser_t *parser,
696− yaml_mark_t start_mark, int *number);
699−yaml_parser_scan_tag_directive_value(yaml_parser_t *parser,
700− yaml_mark_t mark, yaml_char_t **handle, yaml_char_t **prefix);
703−yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token,
704− yaml_token_type_t type);
707−yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token);
710−yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive,
711− yaml_mark_t start_mark, yaml_char_t **handle);
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);
718−yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive,
719− yaml_mark_t start_mark, yaml_string_t *string);
722−yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token,
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);
731−yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token,
735−yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token);
738− * Get the next token.
742−yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token)
744− assert(parser); /* Non-NULL parser object is expected. */
745− assert(token); /* Non-NULL token object is expected. */
747− /* Erase the token object. */
749− memset(token, 0, sizeof(yaml_token_t));
751− /* No tokens after STREAM-END or error. */
753− if (parser->stream_end_produced || parser->error) {
757− /* Ensure that the tokens queue contains enough tokens. */
759− if (!parser->token_available) {
760− if (!yaml_parser_fetch_more_tokens(parser))
764− /* Fetch the next token from the queue. */
766− *token = DEQUEUE(parser, parser->tokens);
767− parser->token_available = 0;
768− parser->tokens_parsed ++;
770− if (token->type == YAML_STREAM_END_TOKEN) {
771− parser->stream_end_produced = 1;
778− * Set the scanner error and return 0.
782−yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context,
783− yaml_mark_t context_mark, const char *problem)
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;
795− * Ensure that the tokens queue contains at least one token which can be
796− * returned to the Parser.
800−yaml_parser_fetch_more_tokens(yaml_parser_t *parser)
802− int need_more_tokens;
804− /* While we need more tokens to fetch, do it. */
809− * Check if we really need to fetch more tokens.
812− need_more_tokens = 0;
814− if (parser->tokens.head == parser->tokens.tail)
816− /* Queue is empty. */
818− need_more_tokens = 1;
822− yaml_simple_key_t *simple_key;
824− /* Check if any potential simple key may occupy the head position. */
826− if (!yaml_parser_stale_simple_keys(parser))
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;
839− /* We are finished. */
841− if (!need_more_tokens)
844− /* Fetch the next token. */
846− if (!yaml_parser_fetch_next_token(parser))
850− parser->token_available = 1;
856− * The dispatcher for token fetchers.
860−yaml_parser_fetch_next_token(yaml_parser_t *parser)
862− /* Ensure that the buffer is initialized. */
864− if (!CACHE(parser, 1))
867− /* Check if we just started scanning. Fetch STREAM-START then. */
869− if (!parser->stream_start_produced)
870− return yaml_parser_fetch_stream_start(parser);
872− /* Eat whitespaces and comments until we reach the next token. */
874− if (!yaml_parser_scan_to_next_token(parser))
877− /* Remove obsolete potential simple keys. */
879− if (!yaml_parser_stale_simple_keys(parser))
882− /* Check the indentation level against the current column. */
884− if (!yaml_parser_unroll_indent(parser, parser->mark.column))
888− * Ensure that the buffer contains at least 4 characters. 4 is the length
889− * of the longest indicators ('--- ' and '... ').
892− if (!CACHE(parser, 4))
895− /* Is it the end of the stream? */
897− if (IS_Z(parser->buffer))
898− return yaml_parser_fetch_stream_end(parser);
900− /* Is it a directive? */
902− if (parser->mark.column == 0 && CHECK(parser->buffer, '%'))
903− return yaml_parser_fetch_directive(parser);
905− /* Is it the document start indicator? */
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);
915− /* Is it the document end indicator? */
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);
925− /* Is it the flow sequence start indicator? */
927− if (CHECK(parser->buffer, '['))
928− return yaml_parser_fetch_flow_collection_start(parser,
929− YAML_FLOW_SEQUENCE_START_TOKEN);
931− /* Is it the flow mapping start indicator? */
933− if (CHECK(parser->buffer, '{'))
934− return yaml_parser_fetch_flow_collection_start(parser,
935− YAML_FLOW_MAPPING_START_TOKEN);
937− /* Is it the flow sequence end indicator? */
939− if (CHECK(parser->buffer, ']'))
940− return yaml_parser_fetch_flow_collection_end(parser,
941− YAML_FLOW_SEQUENCE_END_TOKEN);
943− /* Is it the flow mapping end indicator? */
945− if (CHECK(parser->buffer, '}'))
946− return yaml_parser_fetch_flow_collection_end(parser,
947− YAML_FLOW_MAPPING_END_TOKEN);
949− /* Is it the flow entry indicator? */
951− if (CHECK(parser->buffer, ','))
952− return yaml_parser_fetch_flow_entry(parser);
954− /* Is it the block entry indicator? */
956− if (CHECK(parser->buffer, '-') && IS_BLANKZ_AT(parser->buffer, 1))
957− return yaml_parser_fetch_block_entry(parser);
959− /* Is it the key indicator? */
961− if (CHECK(parser->buffer, '?')
962− && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1)))
963− return yaml_parser_fetch_key(parser);
965− /* Is it the value indicator? */
967− if (CHECK(parser->buffer, ':')
968− && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1)))
969− return yaml_parser_fetch_value(parser);
971− /* Is it an alias? */
973− if (CHECK(parser->buffer, '*'))
974− return yaml_parser_fetch_anchor(parser, YAML_ALIAS_TOKEN);
976− /* Is it an anchor? */
978− if (CHECK(parser->buffer, '&'))
979− return yaml_parser_fetch_anchor(parser, YAML_ANCHOR_TOKEN);
983− if (CHECK(parser->buffer, '!'))
984− return yaml_parser_fetch_tag(parser);
986− /* Is it a literal scalar? */
988− if (CHECK(parser->buffer, '|') && !parser->flow_level)
989− return yaml_parser_fetch_block_scalar(parser, 1);
991− /* Is it a folded scalar? */
993− if (CHECK(parser->buffer, '>') && !parser->flow_level)
994− return yaml_parser_fetch_block_scalar(parser, 0);
996− /* Is it a single-quoted scalar? */
998− if (CHECK(parser->buffer, '\''))
999− return yaml_parser_fetch_flow_scalar(parser, 1);
1001− /* Is it a double-quoted scalar? */
1003− if (CHECK(parser->buffer, '"'))
1004− return yaml_parser_fetch_flow_scalar(parser, 0);
1007− * Is it a plain scalar?
1009− * A plain scalar may start with any non-blank characters except
1011− * '-', '?', ':', ',', '[', ']', '{', '}',
1012− * '#', '&', '*', '!', '|', '>', '\'', '\"',
1015− * In the block context (and, for the '-' indicator, in the flow context
1016− * too), it may also start with the characters
1020− * if it is followed by a non-space character.
1022− * The last rule is more restrictive than the specification requires.
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);
1042− * If we don't determine the token type so far, it is an error.
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");
1051− * Check the list of potential simple keys and remove the positions that
1052− * cannot contain simple keys anymore.
1056−yaml_parser_stale_simple_keys(yaml_parser_t *parser)
1058− yaml_simple_key_t *simple_key;
1060− /* Check for a potential simple key for each flow level. */
1062− for (simple_key = parser->simple_keys.start;
1063− simple_key != parser->simple_keys.top; simple_key ++)
1066− * The specification requires that a simple key
1068− * - is limited to a single line,
1069− * - is shorter than 1024 characters.
1072− if (simple_key->possible
1073− && (simple_key->mark.line < parser->mark.line
1074− || simple_key->mark.index+1024 < parser->mark.index)) {
1076− /* Check if the potential simple key to be removed is required. */
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 find expected ':'");
1084− simple_key->possible = 0;
1092− * Check if a simple key may start at the current position and add it if
1097−yaml_parser_save_simple_key(yaml_parser_t *parser)
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
1105− int required = (!parser->flow_level
1106− && parser->indent == (ptrdiff_t)parser->mark.column);
1109− * If the current position may start a simple key, save it.
1112− if (parser->simple_key_allowed)
1114− yaml_simple_key_t simple_key;
1115− simple_key.possible = 1;
1116− simple_key.required = required;
1117− simple_key.token_number =
1118− parser->tokens_parsed + (parser->tokens.tail - parser->tokens.head);
1119− simple_key.mark = parser->mark;
1121− if (!yaml_parser_remove_simple_key(parser)) return 0;
1123− *(parser->simple_keys.top-1) = simple_key;
1130− * Remove a potential simple key at the current flow level.
1134−yaml_parser_remove_simple_key(yaml_parser_t *parser)
1136− yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1138− if (simple_key->possible)
1140− /* If the key is required, it is an error. */
1142− if (simple_key->required) {
1143− return yaml_parser_set_scanner_error(parser,
1144− "while scanning a simple key", simple_key->mark,
1145− "could not find expected ':'");
1149− /* Remove the key from the stack. */
1151− simple_key->possible = 0;
1157− * Increase the flow level and resize the simple key list if needed.
1161−yaml_parser_increase_flow_level(yaml_parser_t *parser)
1163− yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } };
1165− /* Reset the simple key on the next level. */
1167− if (!PUSH(parser, parser->simple_keys, empty_simple_key))
1170− /* Increase the flow level. */
1172− if (parser->flow_level == INT_MAX) {
1173− parser->error = YAML_MEMORY_ERROR;
1177− parser->flow_level++;
1183− * Decrease the flow level.
1187−yaml_parser_decrease_flow_level(yaml_parser_t *parser)
1189− if (parser->flow_level) {
1190− parser->flow_level --;
1191− (void)POP(parser, parser->simple_keys);
1198− * Push the current indentation level to the stack and set the new level
1199− * the current column is greater than the indentation level. In this case,
1200− * append or insert the specified token into the token queue.
1205−yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column,
1206− ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark)
1208− yaml_token_t token;
1210− /* In the flow context, do nothing. */
1212− if (parser->flow_level)
1215− if (parser->indent < column)
1218− * Push the current indentation level to the stack and set the new
1219− * indentation level.
1222− if (!PUSH(parser, parser->indents, parser->indent))
1225− if (column > INT_MAX) {
1226− parser->error = YAML_MEMORY_ERROR;
1230− parser->indent = column;
1232− /* Create a token and insert it into the queue. */
1234− TOKEN_INIT(token, type, mark, mark);
1236− if (number == -1) {
1237− if (!ENQUEUE(parser, parser->tokens, token))
1241− if (!QUEUE_INSERT(parser,
1242− parser->tokens, number - parser->tokens_parsed, token))
1251− * Pop indentation levels from the indents stack until the current level
1252− * becomes less or equal to the column. For each indentation level, append
1253− * the BLOCK-END token.
1258−yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column)
1260− yaml_token_t token;
1262− /* In the flow context, do nothing. */
1264− if (parser->flow_level)
1267− /* Loop through the indentation levels in the stack. */
1269− while (parser->indent > column)
1271− /* Create a token and append it to the queue. */
1273− TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark);
1275− if (!ENQUEUE(parser, parser->tokens, token))
1278− /* Pop the indentation level. */
1280− parser->indent = POP(parser, parser->indents);
1287− * Initialize the scanner and produce the STREAM-START token.
1291−yaml_parser_fetch_stream_start(yaml_parser_t *parser)
1293− yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } };
1294− yaml_token_t token;
1296− /* Set the initial indentation. */
1298− parser->indent = -1;
1300− /* Initialize the simple key stack. */
1302− if (!PUSH(parser, parser->simple_keys, simple_key))
1305− /* A simple key is allowed at the beginning of the stream. */
1307− parser->simple_key_allowed = 1;
1309− /* We have started. */
1311− parser->stream_start_produced = 1;
1313− /* Create the STREAM-START token and append it to the queue. */
1315− STREAM_START_TOKEN_INIT(token, parser->encoding,
1316− parser->mark, parser->mark);
1318− if (!ENQUEUE(parser, parser->tokens, token))
1325− * Produce the STREAM-END token and shut down the scanner.
1329−yaml_parser_fetch_stream_end(yaml_parser_t *parser)
1331− yaml_token_t token;
1333− /* Force new line. */
1335− if (parser->mark.column != 0) {
1336− parser->mark.column = 0;
1337− parser->mark.line ++;
1340− /* Reset the indentation level. */
1342− if (!yaml_parser_unroll_indent(parser, -1))
1345− /* Reset simple keys. */
1347− if (!yaml_parser_remove_simple_key(parser))
1350− parser->simple_key_allowed = 0;
1352− /* Create the STREAM-END token and append it to the queue. */
1354− STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark);
1356− if (!ENQUEUE(parser, parser->tokens, token))
1363− * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token.
1367−yaml_parser_fetch_directive(yaml_parser_t *parser)
1369− yaml_token_t token;
1371− /* Reset the indentation level. */
1373− if (!yaml_parser_unroll_indent(parser, -1))
1376− /* Reset simple keys. */
1378− if (!yaml_parser_remove_simple_key(parser))
1381− parser->simple_key_allowed = 0;
1383− /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */
1385− if (!yaml_parser_scan_directive(parser, &token))
1388− /* Append the token to the queue. */
1390− if (!ENQUEUE(parser, parser->tokens, token)) {
1391− yaml_token_delete(&token);
1399− * Produce the DOCUMENT-START or DOCUMENT-END token.
1403−yaml_parser_fetch_document_indicator(yaml_parser_t *parser,
1404− yaml_token_type_t type)
1406− yaml_mark_t start_mark, end_mark;
1407− yaml_token_t token;
1409− /* Reset the indentation level. */
1411− if (!yaml_parser_unroll_indent(parser, -1))
1414− /* Reset simple keys. */
1416− if (!yaml_parser_remove_simple_key(parser))
1419− parser->simple_key_allowed = 0;
1421− /* Consume the token. */
1423− start_mark = parser->mark;
1429− end_mark = parser->mark;
1431− /* Create the DOCUMENT-START or DOCUMENT-END token. */
1433− TOKEN_INIT(token, type, start_mark, end_mark);
1435− /* Append the token to the queue. */
1437− if (!ENQUEUE(parser, parser->tokens, token))
1444− * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token.
1448−yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser,
1449− yaml_token_type_t type)
1451− yaml_mark_t start_mark, end_mark;
1452− yaml_token_t token;
1454− /* The indicators '[' and '{' may start a simple key. */
1456− if (!yaml_parser_save_simple_key(parser))
1459− /* Increase the flow level. */
1461− if (!yaml_parser_increase_flow_level(parser))
1464− /* A simple key may follow the indicators '[' and '{'. */
1466− parser->simple_key_allowed = 1;
1468− /* Consume the token. */
1470− start_mark = parser->mark;
1472− end_mark = parser->mark;
1474− /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */
1476− TOKEN_INIT(token, type, start_mark, end_mark);
1478− /* Append the token to the queue. */
1480− if (!ENQUEUE(parser, parser->tokens, token))
1487− * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token.
1491−yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser,
1492− yaml_token_type_t type)
1494− yaml_mark_t start_mark, end_mark;
1495− yaml_token_t token;
1497− /* Reset any potential simple key on the current flow level. */
1499− if (!yaml_parser_remove_simple_key(parser))
1502− /* Decrease the flow level. */
1504− if (!yaml_parser_decrease_flow_level(parser))
1507− /* No simple keys after the indicators ']' and '}'. */
1509− parser->simple_key_allowed = 0;
1511− /* Consume the token. */
1513− start_mark = parser->mark;
1515− end_mark = parser->mark;
1517− /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */
1519− TOKEN_INIT(token, type, start_mark, end_mark);
1521− /* Append the token to the queue. */
1523− if (!ENQUEUE(parser, parser->tokens, token))
1530− * Produce the FLOW-ENTRY token.
1534−yaml_parser_fetch_flow_entry(yaml_parser_t *parser)
1536− yaml_mark_t start_mark, end_mark;
1537− yaml_token_t token;
1539− /* Reset any potential simple keys on the current flow level. */
1541− if (!yaml_parser_remove_simple_key(parser))
1544− /* Simple keys are allowed after ','. */
1546− parser->simple_key_allowed = 1;
1548− /* Consume the token. */
1550− start_mark = parser->mark;
1552− end_mark = parser->mark;
1554− /* Create the FLOW-ENTRY token and append it to the queue. */
1556− TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark);
1558− if (!ENQUEUE(parser, parser->tokens, token))
1565− * Produce the BLOCK-ENTRY token.
1569−yaml_parser_fetch_block_entry(yaml_parser_t *parser)
1571− yaml_mark_t start_mark, end_mark;
1572− yaml_token_t token;
1574− /* Check if the scanner is in the block context. */
1576− if (!parser->flow_level)
1578− /* Check if we are allowed to start a new entry. */
1580− if (!parser->simple_key_allowed) {
1581− return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1582− "block sequence entries are not allowed in this context");
1585− /* Add the BLOCK-SEQUENCE-START token if needed. */
1587− if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1588− YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark))
1594− * It is an error for the '-' indicator to occur in the flow context,
1595− * but we let the Parser detect and report about it because the Parser
1596− * is able to point to the context.
1600− /* Reset any potential simple keys on the current flow level. */
1602− if (!yaml_parser_remove_simple_key(parser))
1605− /* Simple keys are allowed after '-'. */
1607− parser->simple_key_allowed = 1;
1609− /* Consume the token. */
1611− start_mark = parser->mark;
1613− end_mark = parser->mark;
1615− /* Create the BLOCK-ENTRY token and append it to the queue. */
1617− TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark);
1619− if (!ENQUEUE(parser, parser->tokens, token))
1626− * Produce the KEY token.
1630−yaml_parser_fetch_key(yaml_parser_t *parser)
1632− yaml_mark_t start_mark, end_mark;
1633− yaml_token_t token;
1635− /* In the block context, additional checks are required. */
1637− if (!parser->flow_level)
1639− /* Check if we are allowed to start a new key (not nessesary simple). */
1641− if (!parser->simple_key_allowed) {
1642− return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1643− "mapping keys are not allowed in this context");
1646− /* Add the BLOCK-MAPPING-START token if needed. */
1648− if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1649− YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1653− /* Reset any potential simple keys on the current flow level. */
1655− if (!yaml_parser_remove_simple_key(parser))
1658− /* Simple keys are allowed after '?' in the block context. */
1660− parser->simple_key_allowed = (!parser->flow_level);
1662− /* Consume the token. */
1664− start_mark = parser->mark;
1666− end_mark = parser->mark;
1668− /* Create the KEY token and append it to the queue. */
1670− TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark);
1672− if (!ENQUEUE(parser, parser->tokens, token))
1679− * Produce the VALUE token.
1683−yaml_parser_fetch_value(yaml_parser_t *parser)
1685− yaml_mark_t start_mark, end_mark;
1686− yaml_token_t token;
1687− yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1689− /* Have we found a simple key? */
1691− if (simple_key->possible)
1694− /* Create the KEY token and insert it into the queue. */
1696− TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark);
1698− if (!QUEUE_INSERT(parser, parser->tokens,
1699− simple_key->token_number - parser->tokens_parsed, token))
1702− /* In the block context, we may need to add the BLOCK-MAPPING-START token. */
1704− if (!yaml_parser_roll_indent(parser, simple_key->mark.column,
1705− simple_key->token_number,
1706− YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark))
1709− /* Remove the simple key. */
1711− simple_key->possible = 0;
1713− /* A simple key cannot follow another simple key. */
1715− parser->simple_key_allowed = 0;
1719− /* The ':' indicator follows a complex key. */
1721− /* In the block context, extra checks are required. */
1723− if (!parser->flow_level)
1725− /* Check if we are allowed to start a complex value. */
1727− if (!parser->simple_key_allowed) {
1728− return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1729− "mapping values are not allowed in this context");
1732− /* Add the BLOCK-MAPPING-START token if needed. */
1734− if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1735− YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1739− /* Simple keys after ':' are allowed in the block context. */
1741− parser->simple_key_allowed = (!parser->flow_level);
1744− /* Consume the token. */
1746− start_mark = parser->mark;
1748− end_mark = parser->mark;
1750− /* Create the VALUE token and append it to the queue. */
1752− TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark);
1754− if (!ENQUEUE(parser, parser->tokens, token))
1761− * Produce the ALIAS or ANCHOR token.
1765−yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type)
1767− yaml_token_t token;
1769− /* An anchor or an alias could be a simple key. */
1771− if (!yaml_parser_save_simple_key(parser))
1774− /* A simple key cannot follow an anchor or an alias. */
1776− parser->simple_key_allowed = 0;
1778− /* Create the ALIAS or ANCHOR token and append it to the queue. */
1780− if (!yaml_parser_scan_anchor(parser, &token, type))
1783− if (!ENQUEUE(parser, parser->tokens, token)) {
1784− yaml_token_delete(&token);
1791− * Produce the TAG token.
1795−yaml_parser_fetch_tag(yaml_parser_t *parser)
1797− yaml_token_t token;
1799− /* A tag could be a simple key. */
1801− if (!yaml_parser_save_simple_key(parser))
1804− /* A simple key cannot follow a tag. */
1806− parser->simple_key_allowed = 0;
1808− /* Create the TAG token and append it to the queue. */
1810− if (!yaml_parser_scan_tag(parser, &token))
1813− if (!ENQUEUE(parser, parser->tokens, token)) {
1814− yaml_token_delete(&token);
1822− * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens.
1826−yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal)
1828− yaml_token_t token;
1830− /* Remove any potential simple keys. */
1832− if (!yaml_parser_remove_simple_key(parser))
1835− /* A simple key may follow a block scalar. */
1837− parser->simple_key_allowed = 1;
1839− /* Create the SCALAR token and append it to the queue. */
1841− if (!yaml_parser_scan_block_scalar(parser, &token, literal))
1844− if (!ENQUEUE(parser, parser->tokens, token)) {
1845− yaml_token_delete(&token);
1853− * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens.
1857−yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single)
1859− yaml_token_t token;
1861− /* A plain scalar could be a simple key. */
1863− if (!yaml_parser_save_simple_key(parser))
1866− /* A simple key cannot follow a flow scalar. */
1868− parser->simple_key_allowed = 0;
1870− /* Create the SCALAR token and append it to the queue. */
1872− if (!yaml_parser_scan_flow_scalar(parser, &token, single))
1875− if (!ENQUEUE(parser, parser->tokens, token)) {
1876− yaml_token_delete(&token);
1884− * Produce the SCALAR(...,plain) token.
1888−yaml_parser_fetch_plain_scalar(yaml_parser_t *parser)
1890− yaml_token_t token;
1892− /* A plain scalar could be a simple key. */
1894− if (!yaml_parser_save_simple_key(parser))
1897− /* A simple key cannot follow a flow scalar. */
1899− parser->simple_key_allowed = 0;
1901− /* Create the SCALAR token and append it to the queue. */
1903− if (!yaml_parser_scan_plain_scalar(parser, &token))
1906− if (!ENQUEUE(parser, parser->tokens, token)) {
1907− yaml_token_delete(&token);
1915− * Eat whitespaces and comments until the next token is found.
1919−yaml_parser_scan_to_next_token(yaml_parser_t *parser)
1921− /* Until the next token is not found. */
1925− /* Allow the BOM mark to start a line. */
1927− if (!CACHE(parser, 1)) return 0;
1929− if (parser->mark.column == 0 && IS_BOM(parser->buffer))
1935− * Tabs are allowed:
1937− * - in the flow context;
1938− * - in the block context, but not at the beginning of the line or
1939− * after '-', '?', or ':' (complex value).
1942− if (!CACHE(parser, 1)) return 0;
1944− while (CHECK(parser->buffer,' ') ||
1945− ((parser->flow_level || !parser->simple_key_allowed) &&
1946− CHECK(parser->buffer, '\t'))) {
1948− if (!CACHE(parser, 1)) return 0;
1951− /* Eat a comment until a line break. */
1953− if (CHECK(parser->buffer, '#')) {
1954− while (!IS_BREAKZ(parser->buffer)) {
1956− if (!CACHE(parser, 1)) return 0;
1960− /* If it is a line break, eat it. */
1962− if (IS_BREAK(parser->buffer))
1964− if (!CACHE(parser, 2)) return 0;
1967− /* In the block context, a new line may start a simple key. */
1969− if (!parser->flow_level) {
1970− parser->simple_key_allowed = 1;
1975− /* We have found a token. */
1985− * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token.
1988− * %YAML 1.1 # a comment \n
1989− * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1990− * %TAG !yaml! tag:yaml.org,2002: \n
1991− * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1995−yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token)
1997− yaml_mark_t start_mark, end_mark;
1998− yaml_char_t *name = NULL;
2000− yaml_char_t *handle = NULL, *prefix = NULL;
2004− start_mark = parser->mark;
2008− /* Scan the directive name. */
2010− if (!yaml_parser_scan_directive_name(parser, start_mark, &name))
2013− /* Is it a YAML directive? */
2015− if (strcmp((char *)name, "YAML") == 0)
2017− /* Scan the VERSION directive value. */
2019− if (!yaml_parser_scan_version_directive_value(parser, start_mark,
2023− end_mark = parser->mark;
2025− /* Create a VERSION-DIRECTIVE token. */
2027− VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor,
2028− start_mark, end_mark);
2031− /* Is it a TAG directive? */
2033− else if (strcmp((char *)name, "TAG") == 0)
2035− /* Scan the TAG directive value. */
2037− if (!yaml_parser_scan_tag_directive_value(parser, start_mark,
2041− end_mark = parser->mark;
2043− /* Create a TAG-DIRECTIVE token. */
2045− TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix,
2046− start_mark, end_mark);
2049− /* Unknown directive. */
2053− yaml_parser_set_scanner_error(parser, "while scanning a directive",
2054− start_mark, "found unknown directive name");
2058− /* Eat the rest of the line including any comments. */
2060− if (!CACHE(parser, 1)) goto error;
2062− while (IS_BLANK(parser->buffer)) {
2064− if (!CACHE(parser, 1)) goto error;
2067− if (CHECK(parser->buffer, '#')) {
2068− while (!IS_BREAKZ(parser->buffer)) {
2070− if (!CACHE(parser, 1)) goto error;
2074− /* Check if we are at the end of the line. */
2076− if (!IS_BREAKZ(parser->buffer)) {
2077− yaml_parser_set_scanner_error(parser, "while scanning a directive",
2078− start_mark, "did not find expected comment or line break");
2082− /* Eat a line break. */
2084− if (IS_BREAK(parser->buffer)) {
2085− if (!CACHE(parser, 2)) goto error;
2101− * Scan the directive name.
2104− * %YAML 1.1 # a comment \n
2106− * %TAG !yaml! tag:yaml.org,2002: \n
2111−yaml_parser_scan_directive_name(yaml_parser_t *parser,
2112− yaml_mark_t start_mark, yaml_char_t **name)
2114− yaml_string_t string = NULL_STRING;
2116− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2118− /* Consume the directive name. */
2120− if (!CACHE(parser, 1)) goto error;
2122− while (IS_ALPHA(parser->buffer))
2124− if (!READ(parser, string)) goto error;
2125− if (!CACHE(parser, 1)) goto error;
2128− /* Check if the name is empty. */
2130− if (string.start == string.pointer) {
2131− yaml_parser_set_scanner_error(parser, "while scanning a directive",
2132− start_mark, "could not find expected directive name");
2136− /* Check for an blank character after the name. */
2138− if (!IS_BLANKZ(parser->buffer)) {
2139− yaml_parser_set_scanner_error(parser, "while scanning a directive",
2140− start_mark, "found unexpected non-alphabetical character");
2144− *name = string.start;
2149− STRING_DEL(parser, string);
2154− * Scan the value of VERSION-DIRECTIVE.
2157− * %YAML 1.1 # a comment \n
2162−yaml_parser_scan_version_directive_value(yaml_parser_t *parser,
2163− yaml_mark_t start_mark, int *major, int *minor)
2165− /* Eat whitespaces. */
2167− if (!CACHE(parser, 1)) return 0;
2169− while (IS_BLANK(parser->buffer)) {
2171− if (!CACHE(parser, 1)) return 0;
2174− /* Consume the major version number. */
2176− if (!yaml_parser_scan_version_directive_number(parser, start_mark, major))
2181− if (!CHECK(parser->buffer, '.')) {
2182− return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2183− start_mark, "did not find expected digit or '.' character");
2188− /* Consume the minor version number. */
2190− if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor))
2196−#define MAX_NUMBER_LENGTH 9
2199− * Scan the version number of VERSION-DIRECTIVE.
2202− * %YAML 1.1 # a comment \n
2204− * %YAML 1.1 # a comment \n
2209−yaml_parser_scan_version_directive_number(yaml_parser_t *parser,
2210− yaml_mark_t start_mark, int *number)
2215− /* Repeat while the next character is digit. */
2217− if (!CACHE(parser, 1)) return 0;
2219− while (IS_DIGIT(parser->buffer))
2221− /* Check if the number is too long. */
2223− if (++length > MAX_NUMBER_LENGTH) {
2224− return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2225− start_mark, "found extremely long version number");
2228− value = value*10 + AS_DIGIT(parser->buffer);
2232− if (!CACHE(parser, 1)) return 0;
2235− /* Check if the number was present. */
2238− return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2239− start_mark, "did not find expected version number");
2248− * Scan the value of a TAG-DIRECTIVE token.
2251− * %TAG !yaml! tag:yaml.org,2002: \n
2252− * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2256−yaml_parser_scan_tag_directive_value(yaml_parser_t *parser,
2257− yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix)
2259− yaml_char_t *handle_value = NULL;
2260− yaml_char_t *prefix_value = NULL;
2262− /* Eat whitespaces. */
2264− if (!CACHE(parser, 1)) goto error;
2266− while (IS_BLANK(parser->buffer)) {
2268− if (!CACHE(parser, 1)) goto error;
2271− /* Scan a handle. */
2273− if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value))
2276− /* Expect a whitespace. */
2278− if (!CACHE(parser, 1)) goto error;
2280− if (!IS_BLANK(parser->buffer)) {
2281− yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2282− start_mark, "did not find expected whitespace");
2286− /* Eat whitespaces. */
2288− while (IS_BLANK(parser->buffer)) {
2290− if (!CACHE(parser, 1)) goto error;
2293− /* Scan a prefix. */
2295− if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value))
2298− /* Expect a whitespace or line break. */
2300− if (!CACHE(parser, 1)) goto error;
2302− if (!IS_BLANKZ(parser->buffer)) {
2303− yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2304− start_mark, "did not find expected whitespace or line break");
2308− *handle = handle_value;
2309− *prefix = prefix_value;
2314− yaml_free(handle_value);
2315− yaml_free(prefix_value);
2320−yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token,
2321− yaml_token_type_t type)
2324− yaml_mark_t start_mark, end_mark;
2325− yaml_string_t string = NULL_STRING;
2327− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2329− /* Eat the indicator character. */
2331− start_mark = parser->mark;
2335− /* Consume the value. */
2337− if (!CACHE(parser, 1)) goto error;
2339− while (IS_ALPHA(parser->buffer)) {
2340− if (!READ(parser, string)) goto error;
2341− if (!CACHE(parser, 1)) goto error;
2345− end_mark = parser->mark;
2348− * Check if length of the anchor is greater than 0 and it is followed by
2349− * a whitespace character or one of the indicators:
2351− * '?', ':', ',', ']', '}', '%', '@', '`'.
2354− if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?')
2355− || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',')
2356− || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}')
2357− || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@')
2358− || CHECK(parser->buffer, '`'))) {
2359− yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ?
2360− "while scanning an anchor" : "while scanning an alias", start_mark,
2361− "did not find expected alphabetic or numeric character");
2365− /* Create a token. */
2367− if (type == YAML_ANCHOR_TOKEN) {
2368− ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2371− ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2377− STRING_DEL(parser, string);
2382− * Scan a TAG token.
2386−yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token)
2388− yaml_char_t *handle = NULL;
2389− yaml_char_t *suffix = NULL;
2390− yaml_mark_t start_mark, end_mark;
2392− start_mark = parser->mark;
2394− /* Check if the tag is in the canonical form. */
2396− if (!CACHE(parser, 2)) goto error;
2398− if (CHECK_AT(parser->buffer, '<', 1))
2400− /* Set the handle to '' */
2402− handle = YAML_MALLOC(1);
2403− if (!handle) goto error;
2411− /* Consume the tag value. */
2413− if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2416− /* Check for '>' and eat it. */
2418− if (!CHECK(parser->buffer, '>')) {
2419− yaml_parser_set_scanner_error(parser, "while scanning a tag",
2420− start_mark, "did not find the expected '>'");
2428− /* The tag has either the '!suffix' or the '!handle!suffix' form. */
2430− /* First, try to scan a handle. */
2432− if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle))
2435− /* Check if it is, indeed, handle. */
2437− if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!')
2439− /* Scan the suffix now. */
2441− if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2446− /* It wasn't a handle after all. Scan the rest of the tag. */
2448− if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix))
2451− /* Set the handle to '!'. */
2454− handle = YAML_MALLOC(2);
2455− if (!handle) goto error;
2460− * A special case: the '!' tag. Set the handle to '' and the
2464− if (suffix[0] == '\0') {
2465− yaml_char_t *tmp = handle;
2472− /* Check the character which ends the tag. */
2474− if (!CACHE(parser, 1)) goto error;
2476− if (!IS_BLANKZ(parser->buffer)) {
2477− yaml_parser_set_scanner_error(parser, "while scanning a tag",
2478− start_mark, "did not find expected whitespace or line break");
2482− end_mark = parser->mark;
2484− /* Create a token. */
2486− TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark);
2497− * Scan a tag handle.
2501−yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive,
2502− yaml_mark_t start_mark, yaml_char_t **handle)
2504− yaml_string_t string = NULL_STRING;
2506− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2508− /* Check the initial '!' character. */
2510− if (!CACHE(parser, 1)) goto error;
2512− if (!CHECK(parser->buffer, '!')) {
2513− yaml_parser_set_scanner_error(parser, directive ?
2514− "while scanning a tag directive" : "while scanning a tag",
2515− start_mark, "did not find expected '!'");
2519− /* Copy the '!' character. */
2521− if (!READ(parser, string)) goto error;
2523− /* Copy all subsequent alphabetical and numerical characters. */
2525− if (!CACHE(parser, 1)) goto error;
2527− while (IS_ALPHA(parser->buffer))
2529− if (!READ(parser, string)) goto error;
2530− if (!CACHE(parser, 1)) goto error;
2533− /* Check if the trailing character is '!' and copy it. */
2535− if (CHECK(parser->buffer, '!'))
2537− if (!READ(parser, string)) goto error;
2542− * It's either the '!' tag or not really a tag handle. If it's a %TAG
2543− * directive, it's an error. If it's a tag token, it must be a part of
2547− if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) {
2548− yaml_parser_set_scanner_error(parser, "while parsing a tag directive",
2549− start_mark, "did not find expected '!'");
2554− *handle = string.start;
2559− STRING_DEL(parser, string);
2568−yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive,
2569− yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri)
2571− size_t length = head ? strlen((char *)head) : 0;
2572− yaml_string_t string = NULL_STRING;
2574− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2576− /* Resize the string to include the head. */
2578− while ((size_t)(string.end - string.start) <= length) {
2579− if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) {
2580− parser->error = YAML_MEMORY_ERROR;
2586− * Copy the head if needed.
2588− * Note that we don't copy the leading '!' character.
2592− memcpy(string.start, head+1, length-1);
2593− string.pointer += length-1;
2596− /* Scan the tag. */
2598− if (!CACHE(parser, 1)) goto error;
2601− * The set of characters that may appear in URI is as follows:
2603− * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&',
2604− * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']',
2608− while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';')
2609− || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?')
2610− || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@')
2611− || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=')
2612− || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$')
2613− || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.')
2614− || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~')
2615− || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'')
2616− || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')')
2617− || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']')
2618− || CHECK(parser->buffer, '%'))
2620− /* Check if it is a URI-escape sequence. */
2622− if (CHECK(parser->buffer, '%')) {
2623− if (!STRING_EXTEND(parser, string))
2626− if (!yaml_parser_scan_uri_escapes(parser,
2627− directive, start_mark, &string)) goto error;
2630− if (!READ(parser, string)) goto error;
2634− if (!CACHE(parser, 1)) goto error;
2637− /* Check if the tag is non-empty. */
2640− if (!STRING_EXTEND(parser, string))
2643− yaml_parser_set_scanner_error(parser, directive ?
2644− "while parsing a %TAG directive" : "while parsing a tag",
2645− start_mark, "did not find expected tag URI");
2649− *uri = string.start;
2654− STRING_DEL(parser, string);
2659− * Decode an URI-escape sequence corresponding to a single UTF-8 character.
2663−yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive,
2664− yaml_mark_t start_mark, yaml_string_t *string)
2668− /* Decode the required number of characters. */
2672− unsigned char octet = 0;
2674− /* Check for a URI-escaped octet. */
2676− if (!CACHE(parser, 3)) return 0;
2678− if (!(CHECK(parser->buffer, '%')
2679− && IS_HEX_AT(parser->buffer, 1)
2680− && IS_HEX_AT(parser->buffer, 2))) {
2681− return yaml_parser_set_scanner_error(parser, directive ?
2682− "while parsing a %TAG directive" : "while parsing a tag",
2683− start_mark, "did not find URI escaped octet");
2686− /* Get the octet. */
2688− octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2);
2690− /* If it is the leading octet, determine the length of the UTF-8 sequence. */
2694− width = (octet & 0x80) == 0x00 ? 1 :
2695− (octet & 0xE0) == 0xC0 ? 2 :
2696− (octet & 0xF0) == 0xE0 ? 3 :
2697− (octet & 0xF8) == 0xF0 ? 4 : 0;
2699− return yaml_parser_set_scanner_error(parser, directive ?
2700− "while parsing a %TAG directive" : "while parsing a tag",
2701− start_mark, "found an incorrect leading UTF-8 octet");
2706− /* Check if the trailing octet is correct. */
2708− if ((octet & 0xC0) != 0x80) {
2709− return yaml_parser_set_scanner_error(parser, directive ?
2710− "while parsing a %TAG directive" : "while parsing a tag",
2711− start_mark, "found an incorrect trailing UTF-8 octet");
2715− /* Copy the octet and move the pointers. */
2717− *(string->pointer++) = octet;
2728− * Scan a block scalar.
2732−yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token,
2735− yaml_mark_t start_mark;
2736− yaml_mark_t end_mark;
2737− yaml_string_t string = NULL_STRING;
2738− yaml_string_t leading_break = NULL_STRING;
2739− yaml_string_t trailing_breaks = NULL_STRING;
2743− int leading_blank = 0;
2744− int trailing_blank = 0;
2746− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2747− if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
2748− if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
2750− /* Eat the indicator '|' or '>'. */
2752− start_mark = parser->mark;
2756− /* Scan the additional block scalar indicators. */
2758− if (!CACHE(parser, 1)) goto error;
2760− /* Check for a chomping indicator. */
2762− if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-'))
2764− /* Set the chomping method and eat the indicator. */
2766− chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2770− /* Check for an indentation indicator. */
2772− if (!CACHE(parser, 1)) goto error;
2774− if (IS_DIGIT(parser->buffer))
2776− /* Check that the indentation is greater than 0. */
2778− if (CHECK(parser->buffer, '0')) {
2779− yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2780− start_mark, "found an indentation indicator equal to 0");
2784− /* Get the indentation level and eat the indicator. */
2786− increment = AS_DIGIT(parser->buffer);
2792− /* Do the same as above, but in the opposite order. */
2794− else if (IS_DIGIT(parser->buffer))
2796− if (CHECK(parser->buffer, '0')) {
2797− yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2798− start_mark, "found an indentation indicator equal to 0");
2802− increment = AS_DIGIT(parser->buffer);
2806− if (!CACHE(parser, 1)) goto error;
2808− if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) {
2809− chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2815− /* Eat whitespaces and comments to the end of the line. */
2817− if (!CACHE(parser, 1)) goto error;
2819− while (IS_BLANK(parser->buffer)) {
2821− if (!CACHE(parser, 1)) goto error;
2824− if (CHECK(parser->buffer, '#')) {
2825− while (!IS_BREAKZ(parser->buffer)) {
2827− if (!CACHE(parser, 1)) goto error;
2831− /* Check if we are at the end of the line. */
2833− if (!IS_BREAKZ(parser->buffer)) {
2834− yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2835− start_mark, "did not find expected comment or line break");
2839− /* Eat a line break. */
2841− if (IS_BREAK(parser->buffer)) {
2842− if (!CACHE(parser, 2)) goto error;
2846− end_mark = parser->mark;
2848− /* Set the indentation level if it was specified. */
2851− indent = parser->indent >= 0 ? parser->indent+increment : increment;
2854− /* Scan the leading line breaks and determine the indentation level if needed. */
2856− if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks,
2857− start_mark, &end_mark)) goto error;
2859− /* Scan the block scalar content. */
2861− if (!CACHE(parser, 1)) goto error;
2863− while ((int)parser->mark.column == indent && !IS_Z(parser->buffer))
2866− * We are at the beginning of a non-empty line.
2869− /* Is it a trailing whitespace? */
2871− trailing_blank = IS_BLANK(parser->buffer);
2873− /* Check if we need to fold the leading line break. */
2875− if (!literal && (*leading_break.start == '\n')
2876− && !leading_blank && !trailing_blank)
2878− /* Do we need to join the lines by space? */
2880− if (*trailing_breaks.start == '\0') {
2881− if (!STRING_EXTEND(parser, string)) goto error;
2882− *(string.pointer ++) = ' ';
2885− CLEAR(parser, leading_break);
2888− if (!JOIN(parser, string, leading_break)) goto error;
2889− CLEAR(parser, leading_break);
2892− /* Append the remaining line breaks. */
2894− if (!JOIN(parser, string, trailing_breaks)) goto error;
2895− CLEAR(parser, trailing_breaks);
2897− /* Is it a leading whitespace? */
2899− leading_blank = IS_BLANK(parser->buffer);
2901− /* Consume the current line. */
2903− while (!IS_BREAKZ(parser->buffer)) {
2904− if (!READ(parser, string)) goto error;
2905− if (!CACHE(parser, 1)) goto error;
2908− /* Consume the line break. */
2910− if (!CACHE(parser, 2)) goto error;
2912− if (!READ_LINE(parser, leading_break)) goto error;
2914− /* Eat the following indentation spaces and line breaks. */
2916− if (!yaml_parser_scan_block_scalar_breaks(parser,
2917− &indent, &trailing_breaks, start_mark, &end_mark)) goto error;
2920− /* Chomp the tail. */
2922− if (chomping != -1) {
2923− if (!JOIN(parser, string, leading_break)) goto error;
2925− if (chomping == 1) {
2926− if (!JOIN(parser, string, trailing_breaks)) goto error;
2929− /* Create a token. */
2931− SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
2932− literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE,
2933− start_mark, end_mark);
2935− STRING_DEL(parser, leading_break);
2936− STRING_DEL(parser, trailing_breaks);
2941− STRING_DEL(parser, string);
2942− STRING_DEL(parser, leading_break);
2943− STRING_DEL(parser, trailing_breaks);
2949− * Scan indentation spaces and line breaks for a block scalar. Determine the
2950− * indentation level if needed.
2954−yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser,
2955− int *indent, yaml_string_t *breaks,
2956− yaml_mark_t start_mark, yaml_mark_t *end_mark)
2958− int max_indent = 0;
2960− *end_mark = parser->mark;
2962− /* Eat the indentation spaces and line breaks. */
2966− /* Eat the indentation spaces. */
2968− if (!CACHE(parser, 1)) return 0;
2970− while ((!*indent || (int)parser->mark.column < *indent)
2971− && IS_SPACE(parser->buffer)) {
2973− if (!CACHE(parser, 1)) return 0;
2976− if ((int)parser->mark.column > max_indent)
2977− max_indent = (int)parser->mark.column;
2979− /* Check for a tab character messing the indentation. */
2981− if ((!*indent || (int)parser->mark.column < *indent)
2982− && IS_TAB(parser->buffer)) {
2983− return yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2984− start_mark, "found a tab character where an indentation space is expected");
2987− /* Have we found a non-empty line? */
2989− if (!IS_BREAK(parser->buffer)) break;
2991− /* Consume the line break. */
2993− if (!CACHE(parser, 2)) return 0;
2994− if (!READ_LINE(parser, *breaks)) return 0;
2995− *end_mark = parser->mark;
2998− /* Determine the indentation level if needed. */
3001− *indent = max_indent;
3002− if (*indent < parser->indent + 1)
3003− *indent = parser->indent + 1;
3012− * Scan a quoted scalar.
3016−yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token,
3019− yaml_mark_t start_mark;
3020− yaml_mark_t end_mark;
3021− yaml_string_t string = NULL_STRING;
3022− yaml_string_t leading_break = NULL_STRING;
3023− yaml_string_t trailing_breaks = NULL_STRING;
3024− yaml_string_t whitespaces = NULL_STRING;
3025− int leading_blanks;
3027− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3028− if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3029− if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3030− if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3032− /* Eat the left quote. */
3034− start_mark = parser->mark;
3038− /* Consume the content of the quoted scalar. */
3042− /* Check that there are no document indicators at the beginning of the line. */
3044− if (!CACHE(parser, 4)) goto error;
3046− if (parser->mark.column == 0 &&
3047− ((CHECK_AT(parser->buffer, '-', 0) &&
3048− CHECK_AT(parser->buffer, '-', 1) &&
3049− CHECK_AT(parser->buffer, '-', 2)) ||
3050− (CHECK_AT(parser->buffer, '.', 0) &&
3051− CHECK_AT(parser->buffer, '.', 1) &&
3052− CHECK_AT(parser->buffer, '.', 2))) &&
3053− IS_BLANKZ_AT(parser->buffer, 3))
3055− yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3056− start_mark, "found unexpected document indicator");
3060− /* Check for EOF. */
3062− if (IS_Z(parser->buffer)) {
3063− yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3064− start_mark, "found unexpected end of stream");
3068− /* Consume non-blank characters. */
3070− if (!CACHE(parser, 2)) goto error;
3072− leading_blanks = 0;
3074− while (!IS_BLANKZ(parser->buffer))
3076− /* Check for an escaped single quote. */
3078− if (single && CHECK_AT(parser->buffer, '\'', 0)
3079− && CHECK_AT(parser->buffer, '\'', 1))
3081− if (!STRING_EXTEND(parser, string)) goto error;
3082− *(string.pointer++) = '\'';
3087− /* Check for the right quote. */
3089− else if (CHECK(parser->buffer, single ? '\'' : '"'))
3094− /* Check for an escaped line break. */
3096− else if (!single && CHECK(parser->buffer, '\\')
3097− && IS_BREAK_AT(parser->buffer, 1))
3099− if (!CACHE(parser, 3)) goto error;
3102− leading_blanks = 1;
3106− /* Check for an escape sequence. */
3108− else if (!single && CHECK(parser->buffer, '\\'))
3110− size_t code_length = 0;
3112− if (!STRING_EXTEND(parser, string)) goto error;
3114− /* Check the escape character. */
3116− switch (parser->buffer.pointer[1])
3119− *(string.pointer++) = '\0';
3123− *(string.pointer++) = '\x07';
3127− *(string.pointer++) = '\x08';
3132− *(string.pointer++) = '\x09';
3136− *(string.pointer++) = '\x0A';
3140− *(string.pointer++) = '\x0B';
3144− *(string.pointer++) = '\x0C';
3148− *(string.pointer++) = '\x0D';
3152− *(string.pointer++) = '\x1B';
3156− *(string.pointer++) = '\x20';
3160− *(string.pointer++) = '"';
3164− *(string.pointer++) = '/';
3168− *(string.pointer++) = '\\';
3171− case 'N': /* NEL (#x85) */
3172− *(string.pointer++) = '\xC2';
3173− *(string.pointer++) = '\x85';
3176− case '_': /* #xA0 */
3177− *(string.pointer++) = '\xC2';
3178− *(string.pointer++) = '\xA0';
3181− case 'L': /* LS (#x2028) */
3182− *(string.pointer++) = '\xE2';
3183− *(string.pointer++) = '\x80';
3184− *(string.pointer++) = '\xA8';
3187− case 'P': /* PS (#x2029) */
3188− *(string.pointer++) = '\xE2';
3189− *(string.pointer++) = '\x80';
3190− *(string.pointer++) = '\xA9';
3206− yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3207− start_mark, "found unknown escape character");
3214− /* Consume an arbitrary escape code. */
3218− unsigned int value = 0;
3221− /* Scan the character value. */
3223− if (!CACHE(parser, code_length)) goto error;
3225− for (k = 0; k < code_length; k ++) {
3226− if (!IS_HEX_AT(parser->buffer, k)) {
3227− yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3228− start_mark, "did not find expected hexdecimal number");
3231− value = (value << 4) + AS_HEX_AT(parser->buffer, k);
3234− /* Check the value and write the character. */
3236− if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) {
3237− yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3238− start_mark, "found invalid Unicode character escape code");
3242− if (value <= 0x7F) {
3243− *(string.pointer++) = value;
3245− else if (value <= 0x7FF) {
3246− *(string.pointer++) = 0xC0 + (value >> 6);
3247− *(string.pointer++) = 0x80 + (value & 0x3F);
3249− else if (value <= 0xFFFF) {
3250− *(string.pointer++) = 0xE0 + (value >> 12);
3251− *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3252− *(string.pointer++) = 0x80 + (value & 0x3F);
3255− *(string.pointer++) = 0xF0 + (value >> 18);
3256− *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F);
3257− *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3258− *(string.pointer++) = 0x80 + (value & 0x3F);
3261− /* Advance the pointer. */
3263− for (k = 0; k < code_length; k ++) {
3271− /* It is a non-escaped non-blank character. */
3273− if (!READ(parser, string)) goto error;
3276− if (!CACHE(parser, 2)) goto error;
3279− /* Check if we are at the end of the scalar. */
3281− /* Fix for crash unitialized value crash
3282− * Credit for the bug and input is to OSS Fuzz
3283− * Credit for the fix to Alex Gaynor
3285− if (!CACHE(parser, 1)) goto error;
3286− if (CHECK(parser->buffer, single ? '\'' : '"'))
3289− /* Consume blank characters. */
3291− if (!CACHE(parser, 1)) goto error;
3293− while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3295− if (IS_BLANK(parser->buffer))
3297− /* Consume a space or a tab character. */
3299− if (!leading_blanks) {
3300− if (!READ(parser, whitespaces)) goto error;
3308− if (!CACHE(parser, 2)) goto error;
3310− /* Check if it is a first line break. */
3312− if (!leading_blanks)
3314− CLEAR(parser, whitespaces);
3315− if (!READ_LINE(parser, leading_break)) goto error;
3316− leading_blanks = 1;
3320− if (!READ_LINE(parser, trailing_breaks)) goto error;
3323− if (!CACHE(parser, 1)) goto error;
3326− /* Join the whitespaces or fold line breaks. */
3328− if (leading_blanks)
3330− /* Do we need to fold line breaks? */
3332− if (leading_break.start[0] == '\n') {
3333− if (trailing_breaks.start[0] == '\0') {
3334− if (!STRING_EXTEND(parser, string)) goto error;
3335− *(string.pointer++) = ' ';
3338− if (!JOIN(parser, string, trailing_breaks)) goto error;
3339− CLEAR(parser, trailing_breaks);
3341− CLEAR(parser, leading_break);
3344− if (!JOIN(parser, string, leading_break)) goto error;
3345− if (!JOIN(parser, string, trailing_breaks)) goto error;
3346− CLEAR(parser, leading_break);
3347− CLEAR(parser, trailing_breaks);
3352− if (!JOIN(parser, string, whitespaces)) goto error;
3353− CLEAR(parser, whitespaces);
3357− /* Eat the right quote. */
3361− end_mark = parser->mark;
3363− /* Create a token. */
3365− SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3366− single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE,
3367− start_mark, end_mark);
3369− STRING_DEL(parser, leading_break);
3370− STRING_DEL(parser, trailing_breaks);
3371− STRING_DEL(parser, whitespaces);
3376− STRING_DEL(parser, string);
3377− STRING_DEL(parser, leading_break);
3378− STRING_DEL(parser, trailing_breaks);
3379− STRING_DEL(parser, whitespaces);
3385− * Scan a plain scalar.
3389−yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token)
3391− yaml_mark_t start_mark;
3392− yaml_mark_t end_mark;
3393− yaml_string_t string = NULL_STRING;
3394− yaml_string_t leading_break = NULL_STRING;
3395− yaml_string_t trailing_breaks = NULL_STRING;
3396− yaml_string_t whitespaces = NULL_STRING;
3397− int leading_blanks = 0;
3398− int indent = parser->indent+1;
3400− if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3401− if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3402− if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3403− if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3405− start_mark = end_mark = parser->mark;
3407− /* Consume the content of the plain scalar. */
3411− /* Check for a document indicator. */
3413− if (!CACHE(parser, 4)) goto error;
3415− if (parser->mark.column == 0 &&
3416− ((CHECK_AT(parser->buffer, '-', 0) &&
3417− CHECK_AT(parser->buffer, '-', 1) &&
3418− CHECK_AT(parser->buffer, '-', 2)) ||
3419− (CHECK_AT(parser->buffer, '.', 0) &&
3420− CHECK_AT(parser->buffer, '.', 1) &&
3421− CHECK_AT(parser->buffer, '.', 2))) &&
3422− IS_BLANKZ_AT(parser->buffer, 3)) break;
3424− /* Check for a comment. */
3426− if (CHECK(parser->buffer, '#'))
3429− /* Consume non-blank characters. */
3431− while (!IS_BLANKZ(parser->buffer))
3433− /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */
3435− if (parser->flow_level
3436− && CHECK(parser->buffer, ':')
3437− && !IS_BLANKZ_AT(parser->buffer, 1)) {
3438− yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3439− start_mark, "found unexpected ':'");
3443− /* Check for indicators that may end a plain scalar. */
3445− if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1))
3446− || (parser->flow_level &&
3447− (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':')
3448− || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[')
3449− || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{')
3450− || CHECK(parser->buffer, '}'))))
3453− /* Check if we need to join whitespaces and breaks. */
3455− if (leading_blanks || whitespaces.start != whitespaces.pointer)
3457− if (leading_blanks)
3459− /* Do we need to fold line breaks? */
3461− if (leading_break.start[0] == '\n') {
3462− if (trailing_breaks.start[0] == '\0') {
3463− if (!STRING_EXTEND(parser, string)) goto error;
3464− *(string.pointer++) = ' ';
3467− if (!JOIN(parser, string, trailing_breaks)) goto error;
3468− CLEAR(parser, trailing_breaks);
3470− CLEAR(parser, leading_break);
3473− if (!JOIN(parser, string, leading_break)) goto error;
3474− if (!JOIN(parser, string, trailing_breaks)) goto error;
3475− CLEAR(parser, leading_break);
3476− CLEAR(parser, trailing_breaks);
3479− leading_blanks = 0;
3483− if (!JOIN(parser, string, whitespaces)) goto error;
3484− CLEAR(parser, whitespaces);
3488− /* Copy the character. */
3490− if (!READ(parser, string)) goto error;
3492− end_mark = parser->mark;
3494− if (!CACHE(parser, 2)) goto error;
3497− /* Is it the end? */
3499− if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)))
3502− /* Consume blank characters. */
3504− if (!CACHE(parser, 1)) goto error;
3506− while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3508− if (IS_BLANK(parser->buffer))
3510− /* Check for tab character that abuse indentation. */
3512− if (leading_blanks && (int)parser->mark.column < indent
3513− && IS_TAB(parser->buffer)) {
3514− yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3515− start_mark, "found a tab character that violate indentation");
3519− /* Consume a space or a tab character. */
3521− if (!leading_blanks) {
3522− if (!READ(parser, whitespaces)) goto error;
3530− if (!CACHE(parser, 2)) goto error;
3532− /* Check if it is a first line break. */
3534− if (!leading_blanks)
3536− CLEAR(parser, whitespaces);
3537− if (!READ_LINE(parser, leading_break)) goto error;
3538− leading_blanks = 1;
3542− if (!READ_LINE(parser, trailing_breaks)) goto error;
3545− if (!CACHE(parser, 1)) goto error;
3548− /* Check indentation level. */
3550− if (!parser->flow_level && (int)parser->mark.column < indent)
3554− /* Create a token. */
3556− SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3557− YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark);
3559− /* Note that we change the 'simple_key_allowed' flag. */
3561− if (leading_blanks) {
3562− parser->simple_key_allowed = 1;
3565− STRING_DEL(parser, leading_break);
3566− STRING_DEL(parser, trailing_breaks);
3567− STRING_DEL(parser, whitespaces);
3572− STRING_DEL(parser, string);
3573− STRING_DEL(parser, leading_break);
3574− STRING_DEL(parser, trailing_breaks);
3575− STRING_DEL(parser, whitespaces);