@@ -0,0 +1,3584 @@
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+ yaml_simple_key_t dummy_key; /* Used to eliminate a compiler warning. */
1191+ if (parser->flow_level) {
1192+ parser->flow_level --;
1193+ dummy_key = POP(parser, parser->simple_keys);
1200+ * Push the current indentation level to the stack and set the new level
1201+ * the current column is greater than the indentation level. In this case,
1202+ * append or insert the specified token into the token queue.
1207+yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column,
1208+ ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark)
1210+ yaml_token_t token;
1212+ /* In the flow context, do nothing. */
1214+ if (parser->flow_level)
1217+ if (parser->indent < column)
1220+ * Push the current indentation level to the stack and set the new
1221+ * indentation level.
1224+ if (!PUSH(parser, parser->indents, parser->indent))
1227+ if (column > INT_MAX) {
1228+ parser->error = YAML_MEMORY_ERROR;
1232+ parser->indent = column;
1234+ /* Create a token and insert it into the queue. */
1236+ TOKEN_INIT(token, type, mark, mark);
1238+ if (number == -1) {
1239+ if (!ENQUEUE(parser, parser->tokens, token))
1243+ if (!QUEUE_INSERT(parser,
1244+ parser->tokens, number - parser->tokens_parsed, token))
1253+ * Pop indentation levels from the indents stack until the current level
1254+ * becomes less or equal to the column. For each indentation level, append
1255+ * the BLOCK-END token.
1260+yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column)
1262+ yaml_token_t token;
1264+ /* In the flow context, do nothing. */
1266+ if (parser->flow_level)
1269+ /* Loop through the indentation levels in the stack. */
1271+ while (parser->indent > column)
1273+ /* Create a token and append it to the queue. */
1275+ TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark);
1277+ if (!ENQUEUE(parser, parser->tokens, token))
1280+ /* Pop the indentation level. */
1282+ parser->indent = POP(parser, parser->indents);
1289+ * Initialize the scanner and produce the STREAM-START token.
1293+yaml_parser_fetch_stream_start(yaml_parser_t *parser)
1295+ yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } };
1296+ yaml_token_t token;
1298+ /* Set the initial indentation. */
1300+ parser->indent = -1;
1302+ /* Initialize the simple key stack. */
1304+ if (!PUSH(parser, parser->simple_keys, simple_key))
1307+ /* A simple key is allowed at the beginning of the stream. */
1309+ parser->simple_key_allowed = 1;
1311+ /* We have started. */
1313+ parser->stream_start_produced = 1;
1315+ /* Create the STREAM-START token and append it to the queue. */
1317+ STREAM_START_TOKEN_INIT(token, parser->encoding,
1318+ parser->mark, parser->mark);
1320+ if (!ENQUEUE(parser, parser->tokens, token))
1327+ * Produce the STREAM-END token and shut down the scanner.
1331+yaml_parser_fetch_stream_end(yaml_parser_t *parser)
1333+ yaml_token_t token;
1335+ /* Force new line. */
1337+ if (parser->mark.column != 0) {
1338+ parser->mark.column = 0;
1339+ parser->mark.line ++;
1342+ /* Reset the indentation level. */
1344+ if (!yaml_parser_unroll_indent(parser, -1))
1347+ /* Reset simple keys. */
1349+ if (!yaml_parser_remove_simple_key(parser))
1352+ parser->simple_key_allowed = 0;
1354+ /* Create the STREAM-END token and append it to the queue. */
1356+ STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark);
1358+ if (!ENQUEUE(parser, parser->tokens, token))
1365+ * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token.
1369+yaml_parser_fetch_directive(yaml_parser_t *parser)
1371+ yaml_token_t token;
1373+ /* Reset the indentation level. */
1375+ if (!yaml_parser_unroll_indent(parser, -1))
1378+ /* Reset simple keys. */
1380+ if (!yaml_parser_remove_simple_key(parser))
1383+ parser->simple_key_allowed = 0;
1385+ /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */
1387+ if (!yaml_parser_scan_directive(parser, &token))
1390+ /* Append the token to the queue. */
1392+ if (!ENQUEUE(parser, parser->tokens, token)) {
1393+ yaml_token_delete(&token);
1401+ * Produce the DOCUMENT-START or DOCUMENT-END token.
1405+yaml_parser_fetch_document_indicator(yaml_parser_t *parser,
1406+ yaml_token_type_t type)
1408+ yaml_mark_t start_mark, end_mark;
1409+ yaml_token_t token;
1411+ /* Reset the indentation level. */
1413+ if (!yaml_parser_unroll_indent(parser, -1))
1416+ /* Reset simple keys. */
1418+ if (!yaml_parser_remove_simple_key(parser))
1421+ parser->simple_key_allowed = 0;
1423+ /* Consume the token. */
1425+ start_mark = parser->mark;
1431+ end_mark = parser->mark;
1433+ /* Create the DOCUMENT-START or DOCUMENT-END token. */
1435+ TOKEN_INIT(token, type, start_mark, end_mark);
1437+ /* Append the token to the queue. */
1439+ if (!ENQUEUE(parser, parser->tokens, token))
1446+ * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token.
1450+yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser,
1451+ yaml_token_type_t type)
1453+ yaml_mark_t start_mark, end_mark;
1454+ yaml_token_t token;
1456+ /* The indicators '[' and '{' may start a simple key. */
1458+ if (!yaml_parser_save_simple_key(parser))
1461+ /* Increase the flow level. */
1463+ if (!yaml_parser_increase_flow_level(parser))
1466+ /* A simple key may follow the indicators '[' and '{'. */
1468+ parser->simple_key_allowed = 1;
1470+ /* Consume the token. */
1472+ start_mark = parser->mark;
1474+ end_mark = parser->mark;
1476+ /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */
1478+ TOKEN_INIT(token, type, start_mark, end_mark);
1480+ /* Append the token to the queue. */
1482+ if (!ENQUEUE(parser, parser->tokens, token))
1489+ * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token.
1493+yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser,
1494+ yaml_token_type_t type)
1496+ yaml_mark_t start_mark, end_mark;
1497+ yaml_token_t token;
1499+ /* Reset any potential simple key on the current flow level. */
1501+ if (!yaml_parser_remove_simple_key(parser))
1504+ /* Decrease the flow level. */
1506+ if (!yaml_parser_decrease_flow_level(parser))
1509+ /* No simple keys after the indicators ']' and '}'. */
1511+ parser->simple_key_allowed = 0;
1513+ /* Consume the token. */
1515+ start_mark = parser->mark;
1517+ end_mark = parser->mark;
1519+ /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */
1521+ TOKEN_INIT(token, type, start_mark, end_mark);
1523+ /* Append the token to the queue. */
1525+ if (!ENQUEUE(parser, parser->tokens, token))
1532+ * Produce the FLOW-ENTRY token.
1536+yaml_parser_fetch_flow_entry(yaml_parser_t *parser)
1538+ yaml_mark_t start_mark, end_mark;
1539+ yaml_token_t token;
1541+ /* Reset any potential simple keys on the current flow level. */
1543+ if (!yaml_parser_remove_simple_key(parser))
1546+ /* Simple keys are allowed after ','. */
1548+ parser->simple_key_allowed = 1;
1550+ /* Consume the token. */
1552+ start_mark = parser->mark;
1554+ end_mark = parser->mark;
1556+ /* Create the FLOW-ENTRY token and append it to the queue. */
1558+ TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark);
1560+ if (!ENQUEUE(parser, parser->tokens, token))
1567+ * Produce the BLOCK-ENTRY token.
1571+yaml_parser_fetch_block_entry(yaml_parser_t *parser)
1573+ yaml_mark_t start_mark, end_mark;
1574+ yaml_token_t token;
1576+ /* Check if the scanner is in the block context. */
1578+ if (!parser->flow_level)
1580+ /* Check if we are allowed to start a new entry. */
1582+ if (!parser->simple_key_allowed) {
1583+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1584+ "block sequence entries are not allowed in this context");
1587+ /* Add the BLOCK-SEQUENCE-START token if needed. */
1589+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1590+ YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark))
1596+ * It is an error for the '-' indicator to occur in the flow context,
1597+ * but we let the Parser detect and report about it because the Parser
1598+ * is able to point to the context.
1602+ /* Reset any potential simple keys on the current flow level. */
1604+ if (!yaml_parser_remove_simple_key(parser))
1607+ /* Simple keys are allowed after '-'. */
1609+ parser->simple_key_allowed = 1;
1611+ /* Consume the token. */
1613+ start_mark = parser->mark;
1615+ end_mark = parser->mark;
1617+ /* Create the BLOCK-ENTRY token and append it to the queue. */
1619+ TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark);
1621+ if (!ENQUEUE(parser, parser->tokens, token))
1628+ * Produce the KEY token.
1632+yaml_parser_fetch_key(yaml_parser_t *parser)
1634+ yaml_mark_t start_mark, end_mark;
1635+ yaml_token_t token;
1637+ /* In the block context, additional checks are required. */
1639+ if (!parser->flow_level)
1641+ /* Check if we are allowed to start a new key (not nessesary simple). */
1643+ if (!parser->simple_key_allowed) {
1644+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1645+ "mapping keys are not allowed in this context");
1648+ /* Add the BLOCK-MAPPING-START token if needed. */
1650+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1651+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1655+ /* Reset any potential simple keys on the current flow level. */
1657+ if (!yaml_parser_remove_simple_key(parser))
1660+ /* Simple keys are allowed after '?' in the block context. */
1662+ parser->simple_key_allowed = (!parser->flow_level);
1664+ /* Consume the token. */
1666+ start_mark = parser->mark;
1668+ end_mark = parser->mark;
1670+ /* Create the KEY token and append it to the queue. */
1672+ TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark);
1674+ if (!ENQUEUE(parser, parser->tokens, token))
1681+ * Produce the VALUE token.
1685+yaml_parser_fetch_value(yaml_parser_t *parser)
1687+ yaml_mark_t start_mark, end_mark;
1688+ yaml_token_t token;
1689+ yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1691+ /* Have we found a simple key? */
1693+ if (simple_key->possible)
1696+ /* Create the KEY token and insert it into the queue. */
1698+ TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark);
1700+ if (!QUEUE_INSERT(parser, parser->tokens,
1701+ simple_key->token_number - parser->tokens_parsed, token))
1704+ /* In the block context, we may need to add the BLOCK-MAPPING-START token. */
1706+ if (!yaml_parser_roll_indent(parser, simple_key->mark.column,
1707+ simple_key->token_number,
1708+ YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark))
1711+ /* Remove the simple key. */
1713+ simple_key->possible = 0;
1715+ /* A simple key cannot follow another simple key. */
1717+ parser->simple_key_allowed = 0;
1721+ /* The ':' indicator follows a complex key. */
1723+ /* In the block context, extra checks are required. */
1725+ if (!parser->flow_level)
1727+ /* Check if we are allowed to start a complex value. */
1729+ if (!parser->simple_key_allowed) {
1730+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1731+ "mapping values are not allowed in this context");
1734+ /* Add the BLOCK-MAPPING-START token if needed. */
1736+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1737+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1741+ /* Simple keys after ':' are allowed in the block context. */
1743+ parser->simple_key_allowed = (!parser->flow_level);
1746+ /* Consume the token. */
1748+ start_mark = parser->mark;
1750+ end_mark = parser->mark;
1752+ /* Create the VALUE token and append it to the queue. */
1754+ TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark);
1756+ if (!ENQUEUE(parser, parser->tokens, token))
1763+ * Produce the ALIAS or ANCHOR token.
1767+yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type)
1769+ yaml_token_t token;
1771+ /* An anchor or an alias could be a simple key. */
1773+ if (!yaml_parser_save_simple_key(parser))
1776+ /* A simple key cannot follow an anchor or an alias. */
1778+ parser->simple_key_allowed = 0;
1780+ /* Create the ALIAS or ANCHOR token and append it to the queue. */
1782+ if (!yaml_parser_scan_anchor(parser, &token, type))
1785+ if (!ENQUEUE(parser, parser->tokens, token)) {
1786+ yaml_token_delete(&token);
1793+ * Produce the TAG token.
1797+yaml_parser_fetch_tag(yaml_parser_t *parser)
1799+ yaml_token_t token;
1801+ /* A tag could be a simple key. */
1803+ if (!yaml_parser_save_simple_key(parser))
1806+ /* A simple key cannot follow a tag. */
1808+ parser->simple_key_allowed = 0;
1810+ /* Create the TAG token and append it to the queue. */
1812+ if (!yaml_parser_scan_tag(parser, &token))
1815+ if (!ENQUEUE(parser, parser->tokens, token)) {
1816+ yaml_token_delete(&token);
1824+ * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens.
1828+yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal)
1830+ yaml_token_t token;
1832+ /* Remove any potential simple keys. */
1834+ if (!yaml_parser_remove_simple_key(parser))
1837+ /* A simple key may follow a block scalar. */
1839+ parser->simple_key_allowed = 1;
1841+ /* Create the SCALAR token and append it to the queue. */
1843+ if (!yaml_parser_scan_block_scalar(parser, &token, literal))
1846+ if (!ENQUEUE(parser, parser->tokens, token)) {
1847+ yaml_token_delete(&token);
1855+ * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens.
1859+yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single)
1861+ yaml_token_t token;
1863+ /* A plain scalar could be a simple key. */
1865+ if (!yaml_parser_save_simple_key(parser))
1868+ /* A simple key cannot follow a flow scalar. */
1870+ parser->simple_key_allowed = 0;
1872+ /* Create the SCALAR token and append it to the queue. */
1874+ if (!yaml_parser_scan_flow_scalar(parser, &token, single))
1877+ if (!ENQUEUE(parser, parser->tokens, token)) {
1878+ yaml_token_delete(&token);
1886+ * Produce the SCALAR(...,plain) token.
1890+yaml_parser_fetch_plain_scalar(yaml_parser_t *parser)
1892+ yaml_token_t token;
1894+ /* A plain scalar could be a simple key. */
1896+ if (!yaml_parser_save_simple_key(parser))
1899+ /* A simple key cannot follow a flow scalar. */
1901+ parser->simple_key_allowed = 0;
1903+ /* Create the SCALAR token and append it to the queue. */
1905+ if (!yaml_parser_scan_plain_scalar(parser, &token))
1908+ if (!ENQUEUE(parser, parser->tokens, token)) {
1909+ yaml_token_delete(&token);
1917+ * Eat whitespaces and comments until the next token is found.
1921+yaml_parser_scan_to_next_token(yaml_parser_t *parser)
1923+ /* Until the next token is not found. */
1927+ /* Allow the BOM mark to start a line. */
1929+ if (!CACHE(parser, 1)) return 0;
1931+ if (parser->mark.column == 0 && IS_BOM(parser->buffer))
1937+ * Tabs are allowed:
1939+ * - in the flow context;
1940+ * - in the block context, but not at the beginning of the line or
1941+ * after '-', '?', or ':' (complex value).
1944+ if (!CACHE(parser, 1)) return 0;
1946+ while (CHECK(parser->buffer,' ') ||
1947+ ((parser->flow_level || !parser->simple_key_allowed) &&
1948+ CHECK(parser->buffer, '\t'))) {
1950+ if (!CACHE(parser, 1)) return 0;
1953+ /* Eat a comment until a line break. */
1955+ if (CHECK(parser->buffer, '#')) {
1956+ while (!IS_BREAKZ(parser->buffer)) {
1958+ if (!CACHE(parser, 1)) return 0;
1962+ /* If it is a line break, eat it. */
1964+ if (IS_BREAK(parser->buffer))
1966+ if (!CACHE(parser, 2)) return 0;
1969+ /* In the block context, a new line may start a simple key. */
1971+ if (!parser->flow_level) {
1972+ parser->simple_key_allowed = 1;
1977+ /* We have found a token. */
1987+ * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token.
1990+ * %YAML 1.1 # a comment \n
1991+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1992+ * %TAG !yaml! tag:yaml.org,2002: \n
1993+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1997+yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token)
1999+ yaml_mark_t start_mark, end_mark;
2000+ yaml_char_t *name = NULL;
2002+ yaml_char_t *handle = NULL, *prefix = NULL;
2006+ start_mark = parser->mark;
2010+ /* Scan the directive name. */
2012+ if (!yaml_parser_scan_directive_name(parser, start_mark, &name))
2015+ /* Is it a YAML directive? */
2017+ if (strcmp((char *)name, "YAML") == 0)
2019+ /* Scan the VERSION directive value. */
2021+ if (!yaml_parser_scan_version_directive_value(parser, start_mark,
2025+ end_mark = parser->mark;
2027+ /* Create a VERSION-DIRECTIVE token. */
2029+ VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor,
2030+ start_mark, end_mark);
2033+ /* Is it a TAG directive? */
2035+ else if (strcmp((char *)name, "TAG") == 0)
2037+ /* Scan the TAG directive value. */
2039+ if (!yaml_parser_scan_tag_directive_value(parser, start_mark,
2043+ end_mark = parser->mark;
2045+ /* Create a TAG-DIRECTIVE token. */
2047+ TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix,
2048+ start_mark, end_mark);
2051+ /* Unknown directive. */
2055+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2056+ start_mark, "found unknown directive name");
2060+ /* Eat the rest of the line including any comments. */
2062+ if (!CACHE(parser, 1)) goto error;
2064+ while (IS_BLANK(parser->buffer)) {
2066+ if (!CACHE(parser, 1)) goto error;
2069+ if (CHECK(parser->buffer, '#')) {
2070+ while (!IS_BREAKZ(parser->buffer)) {
2072+ if (!CACHE(parser, 1)) goto error;
2076+ /* Check if we are at the end of the line. */
2078+ if (!IS_BREAKZ(parser->buffer)) {
2079+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2080+ start_mark, "did not find expected comment or line break");
2084+ /* Eat a line break. */
2086+ if (IS_BREAK(parser->buffer)) {
2087+ if (!CACHE(parser, 2)) goto error;
2103+ * Scan the directive name.
2106+ * %YAML 1.1 # a comment \n
2108+ * %TAG !yaml! tag:yaml.org,2002: \n
2113+yaml_parser_scan_directive_name(yaml_parser_t *parser,
2114+ yaml_mark_t start_mark, yaml_char_t **name)
2116+ yaml_string_t string = NULL_STRING;
2118+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2120+ /* Consume the directive name. */
2122+ if (!CACHE(parser, 1)) goto error;
2124+ while (IS_ALPHA(parser->buffer))
2126+ if (!READ(parser, string)) goto error;
2127+ if (!CACHE(parser, 1)) goto error;
2130+ /* Check if the name is empty. */
2132+ if (string.start == string.pointer) {
2133+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2134+ start_mark, "could not find expected directive name");
2138+ /* Check for an blank character after the name. */
2140+ if (!IS_BLANKZ(parser->buffer)) {
2141+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2142+ start_mark, "found unexpected non-alphabetical character");
2146+ *name = string.start;
2151+ STRING_DEL(parser, string);
2156+ * Scan the value of VERSION-DIRECTIVE.
2159+ * %YAML 1.1 # a comment \n
2164+yaml_parser_scan_version_directive_value(yaml_parser_t *parser,
2165+ yaml_mark_t start_mark, int *major, int *minor)
2167+ /* Eat whitespaces. */
2169+ if (!CACHE(parser, 1)) return 0;
2171+ while (IS_BLANK(parser->buffer)) {
2173+ if (!CACHE(parser, 1)) return 0;
2176+ /* Consume the major version number. */
2178+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, major))
2183+ if (!CHECK(parser->buffer, '.')) {
2184+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2185+ start_mark, "did not find expected digit or '.' character");
2190+ /* Consume the minor version number. */
2192+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor))
2198+#define MAX_NUMBER_LENGTH 9
2201+ * Scan the version number of VERSION-DIRECTIVE.
2204+ * %YAML 1.1 # a comment \n
2206+ * %YAML 1.1 # a comment \n
2211+yaml_parser_scan_version_directive_number(yaml_parser_t *parser,
2212+ yaml_mark_t start_mark, int *number)
2217+ /* Repeat while the next character is digit. */
2219+ if (!CACHE(parser, 1)) return 0;
2221+ while (IS_DIGIT(parser->buffer))
2223+ /* Check if the number is too long. */
2225+ if (++length > MAX_NUMBER_LENGTH) {
2226+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2227+ start_mark, "found extremely long version number");
2230+ value = value*10 + AS_DIGIT(parser->buffer);
2234+ if (!CACHE(parser, 1)) return 0;
2237+ /* Check if the number was present. */
2240+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2241+ start_mark, "did not find expected version number");
2250+ * Scan the value of a TAG-DIRECTIVE token.
2253+ * %TAG !yaml! tag:yaml.org,2002: \n
2254+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2258+yaml_parser_scan_tag_directive_value(yaml_parser_t *parser,
2259+ yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix)
2261+ yaml_char_t *handle_value = NULL;
2262+ yaml_char_t *prefix_value = NULL;
2264+ /* Eat whitespaces. */
2266+ if (!CACHE(parser, 1)) goto error;
2268+ while (IS_BLANK(parser->buffer)) {
2270+ if (!CACHE(parser, 1)) goto error;
2273+ /* Scan a handle. */
2275+ if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value))
2278+ /* Expect a whitespace. */
2280+ if (!CACHE(parser, 1)) goto error;
2282+ if (!IS_BLANK(parser->buffer)) {
2283+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2284+ start_mark, "did not find expected whitespace");
2288+ /* Eat whitespaces. */
2290+ while (IS_BLANK(parser->buffer)) {
2292+ if (!CACHE(parser, 1)) goto error;
2295+ /* Scan a prefix. */
2297+ if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value))
2300+ /* Expect a whitespace or line break. */
2302+ if (!CACHE(parser, 1)) goto error;
2304+ if (!IS_BLANKZ(parser->buffer)) {
2305+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2306+ start_mark, "did not find expected whitespace or line break");
2310+ *handle = handle_value;
2311+ *prefix = prefix_value;
2316+ yaml_free(handle_value);
2317+ yaml_free(prefix_value);
2322+yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token,
2323+ yaml_token_type_t type)
2326+ yaml_mark_t start_mark, end_mark;
2327+ yaml_string_t string = NULL_STRING;
2329+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2331+ /* Eat the indicator character. */
2333+ start_mark = parser->mark;
2337+ /* Consume the value. */
2339+ if (!CACHE(parser, 1)) goto error;
2341+ while (IS_ALPHA(parser->buffer)) {
2342+ if (!READ(parser, string)) goto error;
2343+ if (!CACHE(parser, 1)) goto error;
2347+ end_mark = parser->mark;
2350+ * Check if length of the anchor is greater than 0 and it is followed by
2351+ * a whitespace character or one of the indicators:
2353+ * '?', ':', ',', ']', '}', '%', '@', '`'.
2356+ if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?')
2357+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',')
2358+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}')
2359+ || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@')
2360+ || CHECK(parser->buffer, '`'))) {
2361+ yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ?
2362+ "while scanning an anchor" : "while scanning an alias", start_mark,
2363+ "did not find expected alphabetic or numeric character");
2367+ /* Create a token. */
2369+ if (type == YAML_ANCHOR_TOKEN) {
2370+ ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2373+ ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2379+ STRING_DEL(parser, string);
2384+ * Scan a TAG token.
2388+yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token)
2390+ yaml_char_t *handle = NULL;
2391+ yaml_char_t *suffix = NULL;
2392+ yaml_mark_t start_mark, end_mark;
2394+ start_mark = parser->mark;
2396+ /* Check if the tag is in the canonical form. */
2398+ if (!CACHE(parser, 2)) goto error;
2400+ if (CHECK_AT(parser->buffer, '<', 1))
2402+ /* Set the handle to '' */
2404+ handle = yaml_malloc(1);
2405+ if (!handle) goto error;
2413+ /* Consume the tag value. */
2415+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2418+ /* Check for '>' and eat it. */
2420+ if (!CHECK(parser->buffer, '>')) {
2421+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2422+ start_mark, "did not find the expected '>'");
2430+ /* The tag has either the '!suffix' or the '!handle!suffix' form. */
2432+ /* First, try to scan a handle. */
2434+ if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle))
2437+ /* Check if it is, indeed, handle. */
2439+ if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!')
2441+ /* Scan the suffix now. */
2443+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2448+ /* It wasn't a handle after all. Scan the rest of the tag. */
2450+ if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix))
2453+ /* Set the handle to '!'. */
2456+ handle = yaml_malloc(2);
2457+ if (!handle) goto error;
2462+ * A special case: the '!' tag. Set the handle to '' and the
2466+ if (suffix[0] == '\0') {
2467+ yaml_char_t *tmp = handle;
2474+ /* Check the character which ends the tag. */
2476+ if (!CACHE(parser, 1)) goto error;
2478+ if (!IS_BLANKZ(parser->buffer)) {
2479+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2480+ start_mark, "did not find expected whitespace or line break");
2484+ end_mark = parser->mark;
2486+ /* Create a token. */
2488+ TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark);
2499+ * Scan a tag handle.
2503+yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive,
2504+ yaml_mark_t start_mark, yaml_char_t **handle)
2506+ yaml_string_t string = NULL_STRING;
2508+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2510+ /* Check the initial '!' character. */
2512+ if (!CACHE(parser, 1)) goto error;
2514+ if (!CHECK(parser->buffer, '!')) {
2515+ yaml_parser_set_scanner_error(parser, directive ?
2516+ "while scanning a tag directive" : "while scanning a tag",
2517+ start_mark, "did not find expected '!'");
2521+ /* Copy the '!' character. */
2523+ if (!READ(parser, string)) goto error;
2525+ /* Copy all subsequent alphabetical and numerical characters. */
2527+ if (!CACHE(parser, 1)) goto error;
2529+ while (IS_ALPHA(parser->buffer))
2531+ if (!READ(parser, string)) goto error;
2532+ if (!CACHE(parser, 1)) goto error;
2535+ /* Check if the trailing character is '!' and copy it. */
2537+ if (CHECK(parser->buffer, '!'))
2539+ if (!READ(parser, string)) goto error;
2544+ * It's either the '!' tag or not really a tag handle. If it's a %TAG
2545+ * directive, it's an error. If it's a tag token, it must be a part of
2549+ if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) {
2550+ yaml_parser_set_scanner_error(parser, "while parsing a tag directive",
2551+ start_mark, "did not find expected '!'");
2556+ *handle = string.start;
2561+ STRING_DEL(parser, string);
2570+yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive,
2571+ yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri)
2573+ size_t length = head ? strlen((char *)head) : 0;
2574+ yaml_string_t string = NULL_STRING;
2576+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2578+ /* Resize the string to include the head. */
2580+ while ((size_t)(string.end - string.start) <= length) {
2581+ if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) {
2582+ parser->error = YAML_MEMORY_ERROR;
2588+ * Copy the head if needed.
2590+ * Note that we don't copy the leading '!' character.
2594+ memcpy(string.start, head+1, length-1);
2595+ string.pointer += length-1;
2598+ /* Scan the tag. */
2600+ if (!CACHE(parser, 1)) goto error;
2603+ * The set of characters that may appear in URI is as follows:
2605+ * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&',
2606+ * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']',
2610+ while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';')
2611+ || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?')
2612+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@')
2613+ || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=')
2614+ || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$')
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, '(') || CHECK(parser->buffer, ')')
2619+ || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']')
2620+ || CHECK(parser->buffer, '%'))
2622+ /* Check if it is a URI-escape sequence. */
2624+ if (CHECK(parser->buffer, '%')) {
2625+ if (!STRING_EXTEND(parser, string))
2628+ if (!yaml_parser_scan_uri_escapes(parser,
2629+ directive, start_mark, &string)) goto error;
2632+ if (!READ(parser, string)) goto error;
2636+ if (!CACHE(parser, 1)) goto error;
2639+ /* Check if the tag is non-empty. */
2642+ if (!STRING_EXTEND(parser, string))
2645+ yaml_parser_set_scanner_error(parser, directive ?
2646+ "while parsing a %TAG directive" : "while parsing a tag",
2647+ start_mark, "did not find expected tag URI");
2651+ *uri = string.start;
2656+ STRING_DEL(parser, string);
2661+ * Decode an URI-escape sequence corresponding to a single UTF-8 character.
2665+yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive,
2666+ yaml_mark_t start_mark, yaml_string_t *string)
2670+ /* Decode the required number of characters. */
2674+ unsigned char octet = 0;
2676+ /* Check for a URI-escaped octet. */
2678+ if (!CACHE(parser, 3)) return 0;
2680+ if (!(CHECK(parser->buffer, '%')
2681+ && IS_HEX_AT(parser->buffer, 1)
2682+ && IS_HEX_AT(parser->buffer, 2))) {
2683+ return yaml_parser_set_scanner_error(parser, directive ?
2684+ "while parsing a %TAG directive" : "while parsing a tag",
2685+ start_mark, "did not find URI escaped octet");
2688+ /* Get the octet. */
2690+ octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2);
2692+ /* If it is the leading octet, determine the length of the UTF-8 sequence. */
2696+ width = (octet & 0x80) == 0x00 ? 1 :
2697+ (octet & 0xE0) == 0xC0 ? 2 :
2698+ (octet & 0xF0) == 0xE0 ? 3 :
2699+ (octet & 0xF8) == 0xF0 ? 4 : 0;
2701+ return yaml_parser_set_scanner_error(parser, directive ?
2702+ "while parsing a %TAG directive" : "while parsing a tag",
2703+ start_mark, "found an incorrect leading UTF-8 octet");
2708+ /* Check if the trailing octet is correct. */
2710+ if ((octet & 0xC0) != 0x80) {
2711+ return yaml_parser_set_scanner_error(parser, directive ?
2712+ "while parsing a %TAG directive" : "while parsing a tag",
2713+ start_mark, "found an incorrect trailing UTF-8 octet");
2717+ /* Copy the octet and move the pointers. */
2719+ *(string->pointer++) = octet;
2730+ * Scan a block scalar.
2734+yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token,
2737+ yaml_mark_t start_mark;
2738+ yaml_mark_t end_mark;
2739+ yaml_string_t string = NULL_STRING;
2740+ yaml_string_t leading_break = NULL_STRING;
2741+ yaml_string_t trailing_breaks = NULL_STRING;
2745+ int leading_blank = 0;
2746+ int trailing_blank = 0;
2748+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2749+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
2750+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
2752+ /* Eat the indicator '|' or '>'. */
2754+ start_mark = parser->mark;
2758+ /* Scan the additional block scalar indicators. */
2760+ if (!CACHE(parser, 1)) goto error;
2762+ /* Check for a chomping indicator. */
2764+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-'))
2766+ /* Set the chomping method and eat the indicator. */
2768+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2772+ /* Check for an indentation indicator. */
2774+ if (!CACHE(parser, 1)) goto error;
2776+ if (IS_DIGIT(parser->buffer))
2778+ /* Check that the indentation is greater than 0. */
2780+ if (CHECK(parser->buffer, '0')) {
2781+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2782+ start_mark, "found an indentation indicator equal to 0");
2786+ /* Get the indentation level and eat the indicator. */
2788+ increment = AS_DIGIT(parser->buffer);
2794+ /* Do the same as above, but in the opposite order. */
2796+ else if (IS_DIGIT(parser->buffer))
2798+ if (CHECK(parser->buffer, '0')) {
2799+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2800+ start_mark, "found an indentation indicator equal to 0");
2804+ increment = AS_DIGIT(parser->buffer);
2808+ if (!CACHE(parser, 1)) goto error;
2810+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) {
2811+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2817+ /* Eat whitespaces and comments to the end of the line. */
2819+ if (!CACHE(parser, 1)) goto error;
2821+ while (IS_BLANK(parser->buffer)) {
2823+ if (!CACHE(parser, 1)) goto error;
2826+ if (CHECK(parser->buffer, '#')) {
2827+ while (!IS_BREAKZ(parser->buffer)) {
2829+ if (!CACHE(parser, 1)) goto error;
2833+ /* Check if we are at the end of the line. */
2835+ if (!IS_BREAKZ(parser->buffer)) {
2836+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2837+ start_mark, "did not find expected comment or line break");
2841+ /* Eat a line break. */
2843+ if (IS_BREAK(parser->buffer)) {
2844+ if (!CACHE(parser, 2)) goto error;
2848+ end_mark = parser->mark;
2850+ /* Set the indentation level if it was specified. */
2853+ indent = parser->indent >= 0 ? parser->indent+increment : increment;
2856+ /* Scan the leading line breaks and determine the indentation level if needed. */
2858+ if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks,
2859+ start_mark, &end_mark)) goto error;
2861+ /* Scan the block scalar content. */
2863+ if (!CACHE(parser, 1)) goto error;
2865+ while ((int)parser->mark.column == indent && !IS_Z(parser->buffer))
2868+ * We are at the beginning of a non-empty line.
2871+ /* Is it a trailing whitespace? */
2873+ trailing_blank = IS_BLANK(parser->buffer);
2875+ /* Check if we need to fold the leading line break. */
2877+ if (!literal && (*leading_break.start == '\n')
2878+ && !leading_blank && !trailing_blank)
2880+ /* Do we need to join the lines by space? */
2882+ if (*trailing_breaks.start == '\0') {
2883+ if (!STRING_EXTEND(parser, string)) goto error;
2884+ *(string.pointer ++) = ' ';
2887+ CLEAR(parser, leading_break);
2890+ if (!JOIN(parser, string, leading_break)) goto error;
2891+ CLEAR(parser, leading_break);
2894+ /* Append the remaining line breaks. */
2896+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2897+ CLEAR(parser, trailing_breaks);
2899+ /* Is it a leading whitespace? */
2901+ leading_blank = IS_BLANK(parser->buffer);
2903+ /* Consume the current line. */
2905+ while (!IS_BREAKZ(parser->buffer)) {
2906+ if (!READ(parser, string)) goto error;
2907+ if (!CACHE(parser, 1)) goto error;
2910+ /* Consume the line break. */
2912+ if (!CACHE(parser, 2)) goto error;
2914+ if (!READ_LINE(parser, leading_break)) goto error;
2916+ /* Eat the following indentation spaces and line breaks. */
2918+ if (!yaml_parser_scan_block_scalar_breaks(parser,
2919+ &indent, &trailing_breaks, start_mark, &end_mark)) goto error;
2922+ /* Chomp the tail. */
2924+ if (chomping != -1) {
2925+ if (!JOIN(parser, string, leading_break)) goto error;
2927+ if (chomping == 1) {
2928+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2931+ /* Create a token. */
2933+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
2934+ literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE,
2935+ start_mark, end_mark);
2937+ STRING_DEL(parser, leading_break);
2938+ STRING_DEL(parser, trailing_breaks);
2943+ STRING_DEL(parser, string);
2944+ STRING_DEL(parser, leading_break);
2945+ STRING_DEL(parser, trailing_breaks);
2951+ * Scan indentation spaces and line breaks for a block scalar. Determine the
2952+ * indentation level if needed.
2956+yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser,
2957+ int *indent, yaml_string_t *breaks,
2958+ yaml_mark_t start_mark, yaml_mark_t *end_mark)
2960+ int max_indent = 0;
2962+ *end_mark = parser->mark;
2964+ /* Eat the indentation spaces and line breaks. */
2968+ /* Eat the indentation spaces. */
2970+ if (!CACHE(parser, 1)) return 0;
2972+ while ((!*indent || (int)parser->mark.column < *indent)
2973+ && IS_SPACE(parser->buffer)) {
2975+ if (!CACHE(parser, 1)) return 0;
2978+ if ((int)parser->mark.column > max_indent)
2979+ max_indent = (int)parser->mark.column;
2981+ /* Check for a tab character messing the indentation. */
2983+ if ((!*indent || (int)parser->mark.column < *indent)
2984+ && IS_TAB(parser->buffer)) {
2985+ return yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2986+ start_mark, "found a tab character where an indentation space is expected");
2989+ /* Have we found a non-empty line? */
2991+ if (!IS_BREAK(parser->buffer)) break;
2993+ /* Consume the line break. */
2995+ if (!CACHE(parser, 2)) return 0;
2996+ if (!READ_LINE(parser, *breaks)) return 0;
2997+ *end_mark = parser->mark;
3000+ /* Determine the indentation level if needed. */
3003+ *indent = max_indent;
3004+ if (*indent < parser->indent + 1)
3005+ *indent = parser->indent + 1;
3014+ * Scan a quoted scalar.
3018+yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token,
3021+ yaml_mark_t start_mark;
3022+ yaml_mark_t end_mark;
3023+ yaml_string_t string = NULL_STRING;
3024+ yaml_string_t leading_break = NULL_STRING;
3025+ yaml_string_t trailing_breaks = NULL_STRING;
3026+ yaml_string_t whitespaces = NULL_STRING;
3027+ int leading_blanks;
3029+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3030+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3031+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3032+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3034+ /* Eat the left quote. */
3036+ start_mark = parser->mark;
3040+ /* Consume the content of the quoted scalar. */
3044+ /* Check that there are no document indicators at the beginning of the line. */
3046+ if (!CACHE(parser, 4)) goto error;
3048+ if (parser->mark.column == 0 &&
3049+ ((CHECK_AT(parser->buffer, '-', 0) &&
3050+ CHECK_AT(parser->buffer, '-', 1) &&
3051+ CHECK_AT(parser->buffer, '-', 2)) ||
3052+ (CHECK_AT(parser->buffer, '.', 0) &&
3053+ CHECK_AT(parser->buffer, '.', 1) &&
3054+ CHECK_AT(parser->buffer, '.', 2))) &&
3055+ IS_BLANKZ_AT(parser->buffer, 3))
3057+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3058+ start_mark, "found unexpected document indicator");
3062+ /* Check for EOF. */
3064+ if (IS_Z(parser->buffer)) {
3065+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3066+ start_mark, "found unexpected end of stream");
3070+ /* Consume non-blank characters. */
3072+ if (!CACHE(parser, 2)) goto error;
3074+ leading_blanks = 0;
3076+ while (!IS_BLANKZ(parser->buffer))
3078+ /* Check for an escaped single quote. */
3080+ if (single && CHECK_AT(parser->buffer, '\'', 0)
3081+ && CHECK_AT(parser->buffer, '\'', 1))
3083+ if (!STRING_EXTEND(parser, string)) goto error;
3084+ *(string.pointer++) = '\'';
3089+ /* Check for the right quote. */
3091+ else if (CHECK(parser->buffer, single ? '\'' : '"'))
3096+ /* Check for an escaped line break. */
3098+ else if (!single && CHECK(parser->buffer, '\\')
3099+ && IS_BREAK_AT(parser->buffer, 1))
3101+ if (!CACHE(parser, 3)) goto error;
3104+ leading_blanks = 1;
3108+ /* Check for an escape sequence. */
3110+ else if (!single && CHECK(parser->buffer, '\\'))
3112+ size_t code_length = 0;
3114+ if (!STRING_EXTEND(parser, string)) goto error;
3116+ /* Check the escape character. */
3118+ switch (parser->buffer.pointer[1])
3121+ *(string.pointer++) = '\0';
3125+ *(string.pointer++) = '\x07';
3129+ *(string.pointer++) = '\x08';
3134+ *(string.pointer++) = '\x09';
3138+ *(string.pointer++) = '\x0A';
3142+ *(string.pointer++) = '\x0B';
3146+ *(string.pointer++) = '\x0C';
3150+ *(string.pointer++) = '\x0D';
3154+ *(string.pointer++) = '\x1B';
3158+ *(string.pointer++) = '\x20';
3162+ *(string.pointer++) = '"';
3166+ *(string.pointer++) = '/';
3170+ *(string.pointer++) = '\'';
3174+ *(string.pointer++) = '\\';
3177+ case 'N': /* NEL (#x85) */
3178+ *(string.pointer++) = '\xC2';
3179+ *(string.pointer++) = '\x85';
3182+ case '_': /* #xA0 */
3183+ *(string.pointer++) = '\xC2';
3184+ *(string.pointer++) = '\xA0';
3187+ case 'L': /* LS (#x2028) */
3188+ *(string.pointer++) = '\xE2';
3189+ *(string.pointer++) = '\x80';
3190+ *(string.pointer++) = '\xA8';
3193+ case 'P': /* PS (#x2029) */
3194+ *(string.pointer++) = '\xE2';
3195+ *(string.pointer++) = '\x80';
3196+ *(string.pointer++) = '\xA9';
3212+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3213+ start_mark, "found unknown escape character");
3220+ /* Consume an arbitrary escape code. */
3224+ unsigned int value = 0;
3227+ /* Scan the character value. */
3229+ if (!CACHE(parser, code_length)) goto error;
3231+ for (k = 0; k < code_length; k ++) {
3232+ if (!IS_HEX_AT(parser->buffer, k)) {
3233+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3234+ start_mark, "did not find expected hexdecimal number");
3237+ value = (value << 4) + AS_HEX_AT(parser->buffer, k);
3240+ /* Check the value and write the character. */
3242+ if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) {
3243+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3244+ start_mark, "found invalid Unicode character escape code");
3248+ if (value <= 0x7F) {
3249+ *(string.pointer++) = value;
3251+ else if (value <= 0x7FF) {
3252+ *(string.pointer++) = 0xC0 + (value >> 6);
3253+ *(string.pointer++) = 0x80 + (value & 0x3F);
3255+ else if (value <= 0xFFFF) {
3256+ *(string.pointer++) = 0xE0 + (value >> 12);
3257+ *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3258+ *(string.pointer++) = 0x80 + (value & 0x3F);
3261+ *(string.pointer++) = 0xF0 + (value >> 18);
3262+ *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F);
3263+ *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3264+ *(string.pointer++) = 0x80 + (value & 0x3F);
3267+ /* Advance the pointer. */
3269+ for (k = 0; k < code_length; k ++) {
3277+ /* It is a non-escaped non-blank character. */
3279+ if (!READ(parser, string)) goto error;
3282+ if (!CACHE(parser, 2)) goto error;
3285+ /* Check if we are at the end of the scalar. */
3287+ /* Fix for crash unitialized value crash
3288+ * Credit for the bug and input is to OSS Fuzz
3289+ * Credit for the fix to Alex Gaynor
3291+ if (!CACHE(parser, 1)) goto error;
3292+ if (CHECK(parser->buffer, single ? '\'' : '"'))
3295+ /* Consume blank characters. */
3297+ if (!CACHE(parser, 1)) goto error;
3299+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3301+ if (IS_BLANK(parser->buffer))
3303+ /* Consume a space or a tab character. */
3305+ if (!leading_blanks) {
3306+ if (!READ(parser, whitespaces)) goto error;
3314+ if (!CACHE(parser, 2)) goto error;
3316+ /* Check if it is a first line break. */
3318+ if (!leading_blanks)
3320+ CLEAR(parser, whitespaces);
3321+ if (!READ_LINE(parser, leading_break)) goto error;
3322+ leading_blanks = 1;
3326+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3329+ if (!CACHE(parser, 1)) goto error;
3332+ /* Join the whitespaces or fold line breaks. */
3334+ if (leading_blanks)
3336+ /* Do we need to fold line breaks? */
3338+ if (leading_break.start[0] == '\n') {
3339+ if (trailing_breaks.start[0] == '\0') {
3340+ if (!STRING_EXTEND(parser, string)) goto error;
3341+ *(string.pointer++) = ' ';
3344+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3345+ CLEAR(parser, trailing_breaks);
3347+ CLEAR(parser, leading_break);
3350+ if (!JOIN(parser, string, leading_break)) goto error;
3351+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3352+ CLEAR(parser, leading_break);
3353+ CLEAR(parser, trailing_breaks);
3358+ if (!JOIN(parser, string, whitespaces)) goto error;
3359+ CLEAR(parser, whitespaces);
3363+ /* Eat the right quote. */
3367+ end_mark = parser->mark;
3369+ /* Create a token. */
3371+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3372+ single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE,
3373+ start_mark, end_mark);
3375+ STRING_DEL(parser, leading_break);
3376+ STRING_DEL(parser, trailing_breaks);
3377+ STRING_DEL(parser, whitespaces);
3382+ STRING_DEL(parser, string);
3383+ STRING_DEL(parser, leading_break);
3384+ STRING_DEL(parser, trailing_breaks);
3385+ STRING_DEL(parser, whitespaces);
3391+ * Scan a plain scalar.
3395+yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token)
3397+ yaml_mark_t start_mark;
3398+ yaml_mark_t end_mark;
3399+ yaml_string_t string = NULL_STRING;
3400+ yaml_string_t leading_break = NULL_STRING;
3401+ yaml_string_t trailing_breaks = NULL_STRING;
3402+ yaml_string_t whitespaces = NULL_STRING;
3403+ int leading_blanks = 0;
3404+ int indent = parser->indent+1;
3406+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3407+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3408+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3409+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3411+ start_mark = end_mark = parser->mark;
3413+ /* Consume the content of the plain scalar. */
3417+ /* Check for a document indicator. */
3419+ if (!CACHE(parser, 4)) goto error;
3421+ if (parser->mark.column == 0 &&
3422+ ((CHECK_AT(parser->buffer, '-', 0) &&
3423+ CHECK_AT(parser->buffer, '-', 1) &&
3424+ CHECK_AT(parser->buffer, '-', 2)) ||
3425+ (CHECK_AT(parser->buffer, '.', 0) &&
3426+ CHECK_AT(parser->buffer, '.', 1) &&
3427+ CHECK_AT(parser->buffer, '.', 2))) &&
3428+ IS_BLANKZ_AT(parser->buffer, 3)) break;
3430+ /* Check for a comment. */
3432+ if (CHECK(parser->buffer, '#'))
3435+ /* Consume non-blank characters. */
3437+ while (!IS_BLANKZ(parser->buffer))
3439+ /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */
3441+ if (parser->flow_level
3442+ && CHECK(parser->buffer, ':')
3443+ && !IS_BLANKZ_AT(parser->buffer, 1)) {
3444+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3445+ start_mark, "found unexpected ':'");
3449+ /* Check for indicators that may end a plain scalar. */
3451+ if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1))
3452+ || (parser->flow_level &&
3453+ (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':')
3454+ || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[')
3455+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{')
3456+ || CHECK(parser->buffer, '}'))))
3459+ /* Check if we need to join whitespaces and breaks. */
3461+ if (leading_blanks || whitespaces.start != whitespaces.pointer)
3463+ if (leading_blanks)
3465+ /* Do we need to fold line breaks? */
3467+ if (leading_break.start[0] == '\n') {
3468+ if (trailing_breaks.start[0] == '\0') {
3469+ if (!STRING_EXTEND(parser, string)) goto error;
3470+ *(string.pointer++) = ' ';
3473+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3474+ CLEAR(parser, trailing_breaks);
3476+ CLEAR(parser, leading_break);
3479+ if (!JOIN(parser, string, leading_break)) goto error;
3480+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3481+ CLEAR(parser, leading_break);
3482+ CLEAR(parser, trailing_breaks);
3485+ leading_blanks = 0;
3489+ if (!JOIN(parser, string, whitespaces)) goto error;
3490+ CLEAR(parser, whitespaces);
3494+ /* Copy the character. */
3496+ if (!READ(parser, string)) goto error;
3498+ end_mark = parser->mark;
3500+ if (!CACHE(parser, 2)) goto error;
3503+ /* Is it the end? */
3505+ if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)))
3508+ /* Consume blank characters. */
3510+ if (!CACHE(parser, 1)) goto error;
3512+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3514+ if (IS_BLANK(parser->buffer))
3516+ /* Check for tab character that abuse indentation. */
3518+ if (leading_blanks && (int)parser->mark.column < indent
3519+ && IS_TAB(parser->buffer)) {
3520+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3521+ start_mark, "found a tab character that violate indentation");
3525+ /* Consume a space or a tab character. */
3527+ if (!leading_blanks) {
3528+ if (!READ(parser, whitespaces)) goto error;
3536+ if (!CACHE(parser, 2)) goto error;
3538+ /* Check if it is a first line break. */
3540+ if (!leading_blanks)
3542+ CLEAR(parser, whitespaces);
3543+ if (!READ_LINE(parser, leading_break)) goto error;
3544+ leading_blanks = 1;
3548+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3551+ if (!CACHE(parser, 1)) goto error;
3554+ /* Check indentation level. */
3556+ if (!parser->flow_level && (int)parser->mark.column < indent)
3560+ /* Create a token. */
3562+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3563+ YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark);
3565+ /* Note that we change the 'simple_key_allowed' flag. */
3567+ if (leading_blanks) {
3568+ parser->simple_key_allowed = 1;
3571+ STRING_DEL(parser, leading_break);
3572+ STRING_DEL(parser, trailing_breaks);
3573+ STRING_DEL(parser, whitespaces);
3578+ STRING_DEL(parser, string);
3579+ STRING_DEL(parser, leading_break);
3580+ STRING_DEL(parser, trailing_breaks);
3581+ STRING_DEL(parser, whitespaces);