@@ -0,0 +1,3568 @@
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 correspoding 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, int column,
619+ int number, yaml_token_type_t type, yaml_mark_t mark);
622+yaml_parser_unroll_indent(yaml_parser_t *parser, int 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 == (int)parser->mark.column);
1109+ * A simple key is required only when it is the first token in the current
1110+ * line. Therefore it is always allowed. But we add a check anyway.
1113+ assert(parser->simple_key_allowed || !required); /* Impossible. */
1116+ * If the current position may start a simple key, save it.
1119+ if (parser->simple_key_allowed)
1121+ yaml_simple_key_t simple_key = { 1, required,
1122+ parser->tokens_parsed + parser->tokens.tail - parser->tokens.head,
1124+ simple_key.mark = parser->mark;
1126+ if (!yaml_parser_remove_simple_key(parser)) return 0;
1128+ *(parser->simple_keys.top-1) = simple_key;
1135+ * Remove a potential simple key at the current flow level.
1139+yaml_parser_remove_simple_key(yaml_parser_t *parser)
1141+ yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1143+ if (simple_key->possible)
1145+ /* If the key is required, it is an error. */
1147+ if (simple_key->required) {
1148+ return yaml_parser_set_scanner_error(parser,
1149+ "while scanning a simple key", simple_key->mark,
1150+ "could not find expected ':'");
1154+ /* Remove the key from the stack. */
1156+ simple_key->possible = 0;
1162+ * Increase the flow level and resize the simple key list if needed.
1166+yaml_parser_increase_flow_level(yaml_parser_t *parser)
1168+ yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } };
1170+ /* Reset the simple key on the next level. */
1172+ if (!PUSH(parser, parser->simple_keys, empty_simple_key))
1175+ /* Increase the flow level. */
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, int column,
1208+ int 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+ parser->indent = column;
1229+ /* Create a token and insert it into the queue. */
1231+ TOKEN_INIT(token, type, mark, mark);
1233+ if (number == -1) {
1234+ if (!ENQUEUE(parser, parser->tokens, token))
1238+ if (!QUEUE_INSERT(parser,
1239+ parser->tokens, number - parser->tokens_parsed, token))
1248+ * Pop indentation levels from the indents stack until the current level
1249+ * becomes less or equal to the column. For each intendation level, append
1250+ * the BLOCK-END token.
1255+yaml_parser_unroll_indent(yaml_parser_t *parser, int column)
1257+ yaml_token_t token;
1259+ /* In the flow context, do nothing. */
1261+ if (parser->flow_level)
1264+ /* Loop through the intendation levels in the stack. */
1266+ while (parser->indent > column)
1268+ /* Create a token and append it to the queue. */
1270+ TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark);
1272+ if (!ENQUEUE(parser, parser->tokens, token))
1275+ /* Pop the indentation level. */
1277+ parser->indent = POP(parser, parser->indents);
1284+ * Initialize the scanner and produce the STREAM-START token.
1288+yaml_parser_fetch_stream_start(yaml_parser_t *parser)
1290+ yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } };
1291+ yaml_token_t token;
1293+ /* Set the initial indentation. */
1295+ parser->indent = -1;
1297+ /* Initialize the simple key stack. */
1299+ if (!PUSH(parser, parser->simple_keys, simple_key))
1302+ /* A simple key is allowed at the beginning of the stream. */
1304+ parser->simple_key_allowed = 1;
1306+ /* We have started. */
1308+ parser->stream_start_produced = 1;
1310+ /* Create the STREAM-START token and append it to the queue. */
1312+ STREAM_START_TOKEN_INIT(token, parser->encoding,
1313+ parser->mark, parser->mark);
1315+ if (!ENQUEUE(parser, parser->tokens, token))
1322+ * Produce the STREAM-END token and shut down the scanner.
1326+yaml_parser_fetch_stream_end(yaml_parser_t *parser)
1328+ yaml_token_t token;
1330+ /* Force new line. */
1332+ if (parser->mark.column != 0) {
1333+ parser->mark.column = 0;
1334+ parser->mark.line ++;
1337+ /* Reset the indentation level. */
1339+ if (!yaml_parser_unroll_indent(parser, -1))
1342+ /* Reset simple keys. */
1344+ if (!yaml_parser_remove_simple_key(parser))
1347+ parser->simple_key_allowed = 0;
1349+ /* Create the STREAM-END token and append it to the queue. */
1351+ STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark);
1353+ if (!ENQUEUE(parser, parser->tokens, token))
1360+ * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token.
1364+yaml_parser_fetch_directive(yaml_parser_t *parser)
1366+ yaml_token_t token;
1368+ /* Reset the indentation level. */
1370+ if (!yaml_parser_unroll_indent(parser, -1))
1373+ /* Reset simple keys. */
1375+ if (!yaml_parser_remove_simple_key(parser))
1378+ parser->simple_key_allowed = 0;
1380+ /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */
1382+ if (!yaml_parser_scan_directive(parser, &token))
1385+ /* Append the token to the queue. */
1387+ if (!ENQUEUE(parser, parser->tokens, token)) {
1388+ yaml_token_delete(&token);
1396+ * Produce the DOCUMENT-START or DOCUMENT-END token.
1400+yaml_parser_fetch_document_indicator(yaml_parser_t *parser,
1401+ yaml_token_type_t type)
1403+ yaml_mark_t start_mark, end_mark;
1404+ yaml_token_t token;
1406+ /* Reset the indentation level. */
1408+ if (!yaml_parser_unroll_indent(parser, -1))
1411+ /* Reset simple keys. */
1413+ if (!yaml_parser_remove_simple_key(parser))
1416+ parser->simple_key_allowed = 0;
1418+ /* Consume the token. */
1420+ start_mark = parser->mark;
1426+ end_mark = parser->mark;
1428+ /* Create the DOCUMENT-START or DOCUMENT-END token. */
1430+ TOKEN_INIT(token, type, start_mark, end_mark);
1432+ /* Append the token to the queue. */
1434+ if (!ENQUEUE(parser, parser->tokens, token))
1441+ * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token.
1445+yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser,
1446+ yaml_token_type_t type)
1448+ yaml_mark_t start_mark, end_mark;
1449+ yaml_token_t token;
1451+ /* The indicators '[' and '{' may start a simple key. */
1453+ if (!yaml_parser_save_simple_key(parser))
1456+ /* Increase the flow level. */
1458+ if (!yaml_parser_increase_flow_level(parser))
1461+ /* A simple key may follow the indicators '[' and '{'. */
1463+ parser->simple_key_allowed = 1;
1465+ /* Consume the token. */
1467+ start_mark = parser->mark;
1469+ end_mark = parser->mark;
1471+ /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */
1473+ TOKEN_INIT(token, type, start_mark, end_mark);
1475+ /* Append the token to the queue. */
1477+ if (!ENQUEUE(parser, parser->tokens, token))
1484+ * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token.
1488+yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser,
1489+ yaml_token_type_t type)
1491+ yaml_mark_t start_mark, end_mark;
1492+ yaml_token_t token;
1494+ /* Reset any potential simple key on the current flow level. */
1496+ if (!yaml_parser_remove_simple_key(parser))
1499+ /* Decrease the flow level. */
1501+ if (!yaml_parser_decrease_flow_level(parser))
1504+ /* No simple keys after the indicators ']' and '}'. */
1506+ parser->simple_key_allowed = 0;
1508+ /* Consume the token. */
1510+ start_mark = parser->mark;
1512+ end_mark = parser->mark;
1514+ /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */
1516+ TOKEN_INIT(token, type, start_mark, end_mark);
1518+ /* Append the token to the queue. */
1520+ if (!ENQUEUE(parser, parser->tokens, token))
1527+ * Produce the FLOW-ENTRY token.
1531+yaml_parser_fetch_flow_entry(yaml_parser_t *parser)
1533+ yaml_mark_t start_mark, end_mark;
1534+ yaml_token_t token;
1536+ /* Reset any potential simple keys on the current flow level. */
1538+ if (!yaml_parser_remove_simple_key(parser))
1541+ /* Simple keys are allowed after ','. */
1543+ parser->simple_key_allowed = 1;
1545+ /* Consume the token. */
1547+ start_mark = parser->mark;
1549+ end_mark = parser->mark;
1551+ /* Create the FLOW-ENTRY token and append it to the queue. */
1553+ TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark);
1555+ if (!ENQUEUE(parser, parser->tokens, token))
1562+ * Produce the BLOCK-ENTRY token.
1566+yaml_parser_fetch_block_entry(yaml_parser_t *parser)
1568+ yaml_mark_t start_mark, end_mark;
1569+ yaml_token_t token;
1571+ /* Check if the scanner is in the block context. */
1573+ if (!parser->flow_level)
1575+ /* Check if we are allowed to start a new entry. */
1577+ if (!parser->simple_key_allowed) {
1578+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1579+ "block sequence entries are not allowed in this context");
1582+ /* Add the BLOCK-SEQUENCE-START token if needed. */
1584+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1585+ YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark))
1591+ * It is an error for the '-' indicator to occur in the flow context,
1592+ * but we let the Parser detect and report about it because the Parser
1593+ * is able to point to the context.
1597+ /* Reset any potential simple keys on the current flow level. */
1599+ if (!yaml_parser_remove_simple_key(parser))
1602+ /* Simple keys are allowed after '-'. */
1604+ parser->simple_key_allowed = 1;
1606+ /* Consume the token. */
1608+ start_mark = parser->mark;
1610+ end_mark = parser->mark;
1612+ /* Create the BLOCK-ENTRY token and append it to the queue. */
1614+ TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark);
1616+ if (!ENQUEUE(parser, parser->tokens, token))
1623+ * Produce the KEY token.
1627+yaml_parser_fetch_key(yaml_parser_t *parser)
1629+ yaml_mark_t start_mark, end_mark;
1630+ yaml_token_t token;
1632+ /* In the block context, additional checks are required. */
1634+ if (!parser->flow_level)
1636+ /* Check if we are allowed to start a new key (not nessesary simple). */
1638+ if (!parser->simple_key_allowed) {
1639+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1640+ "mapping keys are not allowed in this context");
1643+ /* Add the BLOCK-MAPPING-START token if needed. */
1645+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1646+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1650+ /* Reset any potential simple keys on the current flow level. */
1652+ if (!yaml_parser_remove_simple_key(parser))
1655+ /* Simple keys are allowed after '?' in the block context. */
1657+ parser->simple_key_allowed = (!parser->flow_level);
1659+ /* Consume the token. */
1661+ start_mark = parser->mark;
1663+ end_mark = parser->mark;
1665+ /* Create the KEY token and append it to the queue. */
1667+ TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark);
1669+ if (!ENQUEUE(parser, parser->tokens, token))
1676+ * Produce the VALUE token.
1680+yaml_parser_fetch_value(yaml_parser_t *parser)
1682+ yaml_mark_t start_mark, end_mark;
1683+ yaml_token_t token;
1684+ yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1686+ /* Have we found a simple key? */
1688+ if (simple_key->possible)
1691+ /* Create the KEY token and insert it into the queue. */
1693+ TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark);
1695+ if (!QUEUE_INSERT(parser, parser->tokens,
1696+ simple_key->token_number - parser->tokens_parsed, token))
1699+ /* In the block context, we may need to add the BLOCK-MAPPING-START token. */
1701+ if (!yaml_parser_roll_indent(parser, simple_key->mark.column,
1702+ simple_key->token_number,
1703+ YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark))
1706+ /* Remove the simple key. */
1708+ simple_key->possible = 0;
1710+ /* A simple key cannot follow another simple key. */
1712+ parser->simple_key_allowed = 0;
1716+ /* The ':' indicator follows a complex key. */
1718+ /* In the block context, extra checks are required. */
1720+ if (!parser->flow_level)
1722+ /* Check if we are allowed to start a complex value. */
1724+ if (!parser->simple_key_allowed) {
1725+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1726+ "mapping values are not allowed in this context");
1729+ /* Add the BLOCK-MAPPING-START token if needed. */
1731+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1732+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1736+ /* Simple keys after ':' are allowed in the block context. */
1738+ parser->simple_key_allowed = (!parser->flow_level);
1741+ /* Consume the token. */
1743+ start_mark = parser->mark;
1745+ end_mark = parser->mark;
1747+ /* Create the VALUE token and append it to the queue. */
1749+ TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark);
1751+ if (!ENQUEUE(parser, parser->tokens, token))
1758+ * Produce the ALIAS or ANCHOR token.
1762+yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type)
1764+ yaml_token_t token;
1766+ /* An anchor or an alias could be a simple key. */
1768+ if (!yaml_parser_save_simple_key(parser))
1771+ /* A simple key cannot follow an anchor or an alias. */
1773+ parser->simple_key_allowed = 0;
1775+ /* Create the ALIAS or ANCHOR token and append it to the queue. */
1777+ if (!yaml_parser_scan_anchor(parser, &token, type))
1780+ if (!ENQUEUE(parser, parser->tokens, token)) {
1781+ yaml_token_delete(&token);
1788+ * Produce the TAG token.
1792+yaml_parser_fetch_tag(yaml_parser_t *parser)
1794+ yaml_token_t token;
1796+ /* A tag could be a simple key. */
1798+ if (!yaml_parser_save_simple_key(parser))
1801+ /* A simple key cannot follow a tag. */
1803+ parser->simple_key_allowed = 0;
1805+ /* Create the TAG token and append it to the queue. */
1807+ if (!yaml_parser_scan_tag(parser, &token))
1810+ if (!ENQUEUE(parser, parser->tokens, token)) {
1811+ yaml_token_delete(&token);
1819+ * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens.
1823+yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal)
1825+ yaml_token_t token;
1827+ /* Remove any potential simple keys. */
1829+ if (!yaml_parser_remove_simple_key(parser))
1832+ /* A simple key may follow a block scalar. */
1834+ parser->simple_key_allowed = 1;
1836+ /* Create the SCALAR token and append it to the queue. */
1838+ if (!yaml_parser_scan_block_scalar(parser, &token, literal))
1841+ if (!ENQUEUE(parser, parser->tokens, token)) {
1842+ yaml_token_delete(&token);
1850+ * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens.
1854+yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single)
1856+ yaml_token_t token;
1858+ /* A plain scalar could be a simple key. */
1860+ if (!yaml_parser_save_simple_key(parser))
1863+ /* A simple key cannot follow a flow scalar. */
1865+ parser->simple_key_allowed = 0;
1867+ /* Create the SCALAR token and append it to the queue. */
1869+ if (!yaml_parser_scan_flow_scalar(parser, &token, single))
1872+ if (!ENQUEUE(parser, parser->tokens, token)) {
1873+ yaml_token_delete(&token);
1881+ * Produce the SCALAR(...,plain) token.
1885+yaml_parser_fetch_plain_scalar(yaml_parser_t *parser)
1887+ yaml_token_t token;
1889+ /* A plain scalar could be a simple key. */
1891+ if (!yaml_parser_save_simple_key(parser))
1894+ /* A simple key cannot follow a flow scalar. */
1896+ parser->simple_key_allowed = 0;
1898+ /* Create the SCALAR token and append it to the queue. */
1900+ if (!yaml_parser_scan_plain_scalar(parser, &token))
1903+ if (!ENQUEUE(parser, parser->tokens, token)) {
1904+ yaml_token_delete(&token);
1912+ * Eat whitespaces and comments until the next token is found.
1916+yaml_parser_scan_to_next_token(yaml_parser_t *parser)
1918+ /* Until the next token is not found. */
1922+ /* Allow the BOM mark to start a line. */
1924+ if (!CACHE(parser, 1)) return 0;
1926+ if (parser->mark.column == 0 && IS_BOM(parser->buffer))
1932+ * Tabs are allowed:
1934+ * - in the flow context;
1935+ * - in the block context, but not at the beginning of the line or
1936+ * after '-', '?', or ':' (complex value).
1939+ if (!CACHE(parser, 1)) return 0;
1941+ while (CHECK(parser->buffer,' ') ||
1942+ ((parser->flow_level || !parser->simple_key_allowed) &&
1943+ CHECK(parser->buffer, '\t'))) {
1945+ if (!CACHE(parser, 1)) return 0;
1948+ /* Eat a comment until a line break. */
1950+ if (CHECK(parser->buffer, '#')) {
1951+ while (!IS_BREAKZ(parser->buffer)) {
1953+ if (!CACHE(parser, 1)) return 0;
1957+ /* If it is a line break, eat it. */
1959+ if (IS_BREAK(parser->buffer))
1961+ if (!CACHE(parser, 2)) return 0;
1964+ /* In the block context, a new line may start a simple key. */
1966+ if (!parser->flow_level) {
1967+ parser->simple_key_allowed = 1;
1972+ /* We have found a token. */
1982+ * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token.
1985+ * %YAML 1.1 # a comment \n
1986+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1987+ * %TAG !yaml! tag:yaml.org,2002: \n
1988+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1992+yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token)
1994+ yaml_mark_t start_mark, end_mark;
1995+ yaml_char_t *name = NULL;
1997+ yaml_char_t *handle = NULL, *prefix = NULL;
2001+ start_mark = parser->mark;
2005+ /* Scan the directive name. */
2007+ if (!yaml_parser_scan_directive_name(parser, start_mark, &name))
2010+ /* Is it a YAML directive? */
2012+ if (strcmp((char *)name, "YAML") == 0)
2014+ /* Scan the VERSION directive value. */
2016+ if (!yaml_parser_scan_version_directive_value(parser, start_mark,
2020+ end_mark = parser->mark;
2022+ /* Create a VERSION-DIRECTIVE token. */
2024+ VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor,
2025+ start_mark, end_mark);
2028+ /* Is it a TAG directive? */
2030+ else if (strcmp((char *)name, "TAG") == 0)
2032+ /* Scan the TAG directive value. */
2034+ if (!yaml_parser_scan_tag_directive_value(parser, start_mark,
2038+ end_mark = parser->mark;
2040+ /* Create a TAG-DIRECTIVE token. */
2042+ TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix,
2043+ start_mark, end_mark);
2046+ /* Unknown directive. */
2050+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2051+ start_mark, "found uknown directive name");
2055+ /* Eat the rest of the line including any comments. */
2057+ if (!CACHE(parser, 1)) goto error;
2059+ while (IS_BLANK(parser->buffer)) {
2061+ if (!CACHE(parser, 1)) goto error;
2064+ if (CHECK(parser->buffer, '#')) {
2065+ while (!IS_BREAKZ(parser->buffer)) {
2067+ if (!CACHE(parser, 1)) goto error;
2071+ /* Check if we are at the end of the line. */
2073+ if (!IS_BREAKZ(parser->buffer)) {
2074+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2075+ start_mark, "did not find expected comment or line break");
2079+ /* Eat a line break. */
2081+ if (IS_BREAK(parser->buffer)) {
2082+ if (!CACHE(parser, 2)) goto error;
2098+ * Scan the directive name.
2101+ * %YAML 1.1 # a comment \n
2103+ * %TAG !yaml! tag:yaml.org,2002: \n
2108+yaml_parser_scan_directive_name(yaml_parser_t *parser,
2109+ yaml_mark_t start_mark, yaml_char_t **name)
2111+ yaml_string_t string = NULL_STRING;
2113+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2115+ /* Consume the directive name. */
2117+ if (!CACHE(parser, 1)) goto error;
2119+ while (IS_ALPHA(parser->buffer))
2121+ if (!READ(parser, string)) goto error;
2122+ if (!CACHE(parser, 1)) goto error;
2125+ /* Check if the name is empty. */
2127+ if (string.start == string.pointer) {
2128+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2129+ start_mark, "could not find expected directive name");
2133+ /* Check for an blank character after the name. */
2135+ if (!IS_BLANKZ(parser->buffer)) {
2136+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2137+ start_mark, "found unexpected non-alphabetical character");
2141+ *name = string.start;
2146+ STRING_DEL(parser, string);
2151+ * Scan the value of VERSION-DIRECTIVE.
2154+ * %YAML 1.1 # a comment \n
2159+yaml_parser_scan_version_directive_value(yaml_parser_t *parser,
2160+ yaml_mark_t start_mark, int *major, int *minor)
2162+ /* Eat whitespaces. */
2164+ if (!CACHE(parser, 1)) return 0;
2166+ while (IS_BLANK(parser->buffer)) {
2168+ if (!CACHE(parser, 1)) return 0;
2171+ /* Consume the major version number. */
2173+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, major))
2178+ if (!CHECK(parser->buffer, '.')) {
2179+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2180+ start_mark, "did not find expected digit or '.' character");
2185+ /* Consume the minor version number. */
2187+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor))
2193+#define MAX_NUMBER_LENGTH 9
2196+ * Scan the version number of VERSION-DIRECTIVE.
2199+ * %YAML 1.1 # a comment \n
2201+ * %YAML 1.1 # a comment \n
2206+yaml_parser_scan_version_directive_number(yaml_parser_t *parser,
2207+ yaml_mark_t start_mark, int *number)
2212+ /* Repeat while the next character is digit. */
2214+ if (!CACHE(parser, 1)) return 0;
2216+ while (IS_DIGIT(parser->buffer))
2218+ /* Check if the number is too long. */
2220+ if (++length > MAX_NUMBER_LENGTH) {
2221+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2222+ start_mark, "found extremely long version number");
2225+ value = value*10 + AS_DIGIT(parser->buffer);
2229+ if (!CACHE(parser, 1)) return 0;
2232+ /* Check if the number was present. */
2235+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2236+ start_mark, "did not find expected version number");
2245+ * Scan the value of a TAG-DIRECTIVE token.
2248+ * %TAG !yaml! tag:yaml.org,2002: \n
2249+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2253+yaml_parser_scan_tag_directive_value(yaml_parser_t *parser,
2254+ yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix)
2256+ yaml_char_t *handle_value = NULL;
2257+ yaml_char_t *prefix_value = NULL;
2259+ /* Eat whitespaces. */
2261+ if (!CACHE(parser, 1)) goto error;
2263+ while (IS_BLANK(parser->buffer)) {
2265+ if (!CACHE(parser, 1)) goto error;
2268+ /* Scan a handle. */
2270+ if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value))
2273+ /* Expect a whitespace. */
2275+ if (!CACHE(parser, 1)) goto error;
2277+ if (!IS_BLANK(parser->buffer)) {
2278+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2279+ start_mark, "did not find expected whitespace");
2283+ /* Eat whitespaces. */
2285+ while (IS_BLANK(parser->buffer)) {
2287+ if (!CACHE(parser, 1)) goto error;
2290+ /* Scan a prefix. */
2292+ if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value))
2295+ /* Expect a whitespace or line break. */
2297+ if (!CACHE(parser, 1)) goto error;
2299+ if (!IS_BLANKZ(parser->buffer)) {
2300+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2301+ start_mark, "did not find expected whitespace or line break");
2305+ *handle = handle_value;
2306+ *prefix = prefix_value;
2311+ yaml_free(handle_value);
2312+ yaml_free(prefix_value);
2317+yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token,
2318+ yaml_token_type_t type)
2321+ yaml_mark_t start_mark, end_mark;
2322+ yaml_string_t string = NULL_STRING;
2324+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2326+ /* Eat the indicator character. */
2328+ start_mark = parser->mark;
2332+ /* Consume the value. */
2334+ if (!CACHE(parser, 1)) goto error;
2336+ while (IS_ALPHA(parser->buffer)) {
2337+ if (!READ(parser, string)) goto error;
2338+ if (!CACHE(parser, 1)) goto error;
2342+ end_mark = parser->mark;
2345+ * Check if length of the anchor is greater than 0 and it is followed by
2346+ * a whitespace character or one of the indicators:
2348+ * '?', ':', ',', ']', '}', '%', '@', '`'.
2351+ if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?')
2352+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',')
2353+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}')
2354+ || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@')
2355+ || CHECK(parser->buffer, '`'))) {
2356+ yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ?
2357+ "while scanning an anchor" : "while scanning an alias", start_mark,
2358+ "did not find expected alphabetic or numeric character");
2362+ /* Create a token. */
2364+ if (type == YAML_ANCHOR_TOKEN) {
2365+ ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2368+ ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2374+ STRING_DEL(parser, string);
2379+ * Scan a TAG token.
2383+yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token)
2385+ yaml_char_t *handle = NULL;
2386+ yaml_char_t *suffix = NULL;
2387+ yaml_mark_t start_mark, end_mark;
2389+ start_mark = parser->mark;
2391+ /* Check if the tag is in the canonical form. */
2393+ if (!CACHE(parser, 2)) goto error;
2395+ if (CHECK_AT(parser->buffer, '<', 1))
2397+ /* Set the handle to '' */
2399+ handle = yaml_malloc(1);
2400+ if (!handle) goto error;
2408+ /* Consume the tag value. */
2410+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2413+ /* Check for '>' and eat it. */
2415+ if (!CHECK(parser->buffer, '>')) {
2416+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2417+ start_mark, "did not find the expected '>'");
2425+ /* The tag has either the '!suffix' or the '!handle!suffix' form. */
2427+ /* First, try to scan a handle. */
2429+ if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle))
2432+ /* Check if it is, indeed, handle. */
2434+ if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!')
2436+ /* Scan the suffix now. */
2438+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2443+ /* It wasn't a handle after all. Scan the rest of the tag. */
2445+ if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix))
2448+ /* Set the handle to '!'. */
2451+ handle = yaml_malloc(2);
2452+ if (!handle) goto error;
2457+ * A special case: the '!' tag. Set the handle to '' and the
2461+ if (suffix[0] == '\0') {
2462+ yaml_char_t *tmp = handle;
2469+ /* Check the character which ends the tag. */
2471+ if (!CACHE(parser, 1)) goto error;
2473+ if (!IS_BLANKZ(parser->buffer)) {
2474+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2475+ start_mark, "did not find expected whitespace or line break");
2479+ end_mark = parser->mark;
2481+ /* Create a token. */
2483+ TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark);
2494+ * Scan a tag handle.
2498+yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive,
2499+ yaml_mark_t start_mark, yaml_char_t **handle)
2501+ yaml_string_t string = NULL_STRING;
2503+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2505+ /* Check the initial '!' character. */
2507+ if (!CACHE(parser, 1)) goto error;
2509+ if (!CHECK(parser->buffer, '!')) {
2510+ yaml_parser_set_scanner_error(parser, directive ?
2511+ "while scanning a tag directive" : "while scanning a tag",
2512+ start_mark, "did not find expected '!'");
2516+ /* Copy the '!' character. */
2518+ if (!READ(parser, string)) goto error;
2520+ /* Copy all subsequent alphabetical and numerical characters. */
2522+ if (!CACHE(parser, 1)) goto error;
2524+ while (IS_ALPHA(parser->buffer))
2526+ if (!READ(parser, string)) goto error;
2527+ if (!CACHE(parser, 1)) goto error;
2530+ /* Check if the trailing character is '!' and copy it. */
2532+ if (CHECK(parser->buffer, '!'))
2534+ if (!READ(parser, string)) goto error;
2539+ * It's either the '!' tag or not really a tag handle. If it's a %TAG
2540+ * directive, it's an error. If it's a tag token, it must be a part of
2544+ if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) {
2545+ yaml_parser_set_scanner_error(parser, "while parsing a tag directive",
2546+ start_mark, "did not find expected '!'");
2551+ *handle = string.start;
2556+ STRING_DEL(parser, string);
2565+yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive,
2566+ yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri)
2568+ size_t length = head ? strlen((char *)head) : 0;
2569+ yaml_string_t string = NULL_STRING;
2571+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2573+ /* Resize the string to include the head. */
2575+ while (string.end - string.start <= (int)length) {
2576+ if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) {
2577+ parser->error = YAML_MEMORY_ERROR;
2583+ * Copy the head if needed.
2585+ * Note that we don't copy the leading '!' character.
2589+ memcpy(string.start, head+1, length-1);
2590+ string.pointer += length-1;
2593+ /* Scan the tag. */
2595+ if (!CACHE(parser, 1)) goto error;
2598+ * The set of characters that may appear in URI is as follows:
2600+ * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&',
2601+ * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']',
2605+ while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';')
2606+ || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?')
2607+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@')
2608+ || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=')
2609+ || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$')
2610+ || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.')
2611+ || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~')
2612+ || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'')
2613+ || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')')
2614+ || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']')
2615+ || CHECK(parser->buffer, '%'))
2617+ /* Check if it is a URI-escape sequence. */
2619+ if (CHECK(parser->buffer, '%')) {
2620+ if (!yaml_parser_scan_uri_escapes(parser,
2621+ directive, start_mark, &string)) goto error;
2624+ if (!READ(parser, string)) goto error;
2628+ if (!CACHE(parser, 1)) goto error;
2631+ /* Check if the tag is non-empty. */
2634+ if (!STRING_EXTEND(parser, string))
2637+ yaml_parser_set_scanner_error(parser, directive ?
2638+ "while parsing a %TAG directive" : "while parsing a tag",
2639+ start_mark, "did not find expected tag URI");
2643+ *uri = string.start;
2648+ STRING_DEL(parser, string);
2653+ * Decode an URI-escape sequence corresponding to a single UTF-8 character.
2657+yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive,
2658+ yaml_mark_t start_mark, yaml_string_t *string)
2662+ /* Decode the required number of characters. */
2666+ unsigned char octet = 0;
2668+ /* Check for a URI-escaped octet. */
2670+ if (!CACHE(parser, 3)) return 0;
2672+ if (!(CHECK(parser->buffer, '%')
2673+ && IS_HEX_AT(parser->buffer, 1)
2674+ && IS_HEX_AT(parser->buffer, 2))) {
2675+ return yaml_parser_set_scanner_error(parser, directive ?
2676+ "while parsing a %TAG directive" : "while parsing a tag",
2677+ start_mark, "did not find URI escaped octet");
2680+ /* Get the octet. */
2682+ octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2);
2684+ /* If it is the leading octet, determine the length of the UTF-8 sequence. */
2688+ width = (octet & 0x80) == 0x00 ? 1 :
2689+ (octet & 0xE0) == 0xC0 ? 2 :
2690+ (octet & 0xF0) == 0xE0 ? 3 :
2691+ (octet & 0xF8) == 0xF0 ? 4 : 0;
2693+ return yaml_parser_set_scanner_error(parser, directive ?
2694+ "while parsing a %TAG directive" : "while parsing a tag",
2695+ start_mark, "found an incorrect leading UTF-8 octet");
2700+ /* Check if the trailing octet is correct. */
2702+ if ((octet & 0xC0) != 0x80) {
2703+ return yaml_parser_set_scanner_error(parser, directive ?
2704+ "while parsing a %TAG directive" : "while parsing a tag",
2705+ start_mark, "found an incorrect trailing UTF-8 octet");
2709+ /* Copy the octet and move the pointers. */
2711+ *(string->pointer++) = octet;
2722+ * Scan a block scalar.
2726+yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token,
2729+ yaml_mark_t start_mark;
2730+ yaml_mark_t end_mark;
2731+ yaml_string_t string = NULL_STRING;
2732+ yaml_string_t leading_break = NULL_STRING;
2733+ yaml_string_t trailing_breaks = NULL_STRING;
2737+ int leading_blank = 0;
2738+ int trailing_blank = 0;
2740+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2741+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
2742+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
2744+ /* Eat the indicator '|' or '>'. */
2746+ start_mark = parser->mark;
2750+ /* Scan the additional block scalar indicators. */
2752+ if (!CACHE(parser, 1)) goto error;
2754+ /* Check for a chomping indicator. */
2756+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-'))
2758+ /* Set the chomping method and eat the indicator. */
2760+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2764+ /* Check for an indentation indicator. */
2766+ if (!CACHE(parser, 1)) goto error;
2768+ if (IS_DIGIT(parser->buffer))
2770+ /* Check that the intendation is greater than 0. */
2772+ if (CHECK(parser->buffer, '0')) {
2773+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2774+ start_mark, "found an intendation indicator equal to 0");
2778+ /* Get the intendation level and eat the indicator. */
2780+ increment = AS_DIGIT(parser->buffer);
2786+ /* Do the same as above, but in the opposite order. */
2788+ else if (IS_DIGIT(parser->buffer))
2790+ if (CHECK(parser->buffer, '0')) {
2791+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2792+ start_mark, "found an intendation indicator equal to 0");
2796+ increment = AS_DIGIT(parser->buffer);
2800+ if (!CACHE(parser, 1)) goto error;
2802+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) {
2803+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2809+ /* Eat whitespaces and comments to the end of the line. */
2811+ if (!CACHE(parser, 1)) goto error;
2813+ while (IS_BLANK(parser->buffer)) {
2815+ if (!CACHE(parser, 1)) goto error;
2818+ if (CHECK(parser->buffer, '#')) {
2819+ while (!IS_BREAKZ(parser->buffer)) {
2821+ if (!CACHE(parser, 1)) goto error;
2825+ /* Check if we are at the end of the line. */
2827+ if (!IS_BREAKZ(parser->buffer)) {
2828+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2829+ start_mark, "did not find expected comment or line break");
2833+ /* Eat a line break. */
2835+ if (IS_BREAK(parser->buffer)) {
2836+ if (!CACHE(parser, 2)) goto error;
2840+ end_mark = parser->mark;
2842+ /* Set the intendation level if it was specified. */
2845+ indent = parser->indent >= 0 ? parser->indent+increment : increment;
2848+ /* Scan the leading line breaks and determine the indentation level if needed. */
2850+ if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks,
2851+ start_mark, &end_mark)) goto error;
2853+ /* Scan the block scalar content. */
2855+ if (!CACHE(parser, 1)) goto error;
2857+ while ((int)parser->mark.column == indent && !IS_Z(parser->buffer))
2860+ * We are at the beginning of a non-empty line.
2863+ /* Is it a trailing whitespace? */
2865+ trailing_blank = IS_BLANK(parser->buffer);
2867+ /* Check if we need to fold the leading line break. */
2869+ if (!literal && (*leading_break.start == '\n')
2870+ && !leading_blank && !trailing_blank)
2872+ /* Do we need to join the lines by space? */
2874+ if (*trailing_breaks.start == '\0') {
2875+ if (!STRING_EXTEND(parser, string)) goto error;
2876+ *(string.pointer ++) = ' ';
2879+ CLEAR(parser, leading_break);
2882+ if (!JOIN(parser, string, leading_break)) goto error;
2883+ CLEAR(parser, leading_break);
2886+ /* Append the remaining line breaks. */
2888+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2889+ CLEAR(parser, trailing_breaks);
2891+ /* Is it a leading whitespace? */
2893+ leading_blank = IS_BLANK(parser->buffer);
2895+ /* Consume the current line. */
2897+ while (!IS_BREAKZ(parser->buffer)) {
2898+ if (!READ(parser, string)) goto error;
2899+ if (!CACHE(parser, 1)) goto error;
2902+ /* Consume the line break. */
2904+ if (!CACHE(parser, 2)) goto error;
2906+ if (!READ_LINE(parser, leading_break)) goto error;
2908+ /* Eat the following intendation spaces and line breaks. */
2910+ if (!yaml_parser_scan_block_scalar_breaks(parser,
2911+ &indent, &trailing_breaks, start_mark, &end_mark)) goto error;
2914+ /* Chomp the tail. */
2916+ if (chomping != -1) {
2917+ if (!JOIN(parser, string, leading_break)) goto error;
2919+ if (chomping == 1) {
2920+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2923+ /* Create a token. */
2925+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
2926+ literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE,
2927+ start_mark, end_mark);
2929+ STRING_DEL(parser, leading_break);
2930+ STRING_DEL(parser, trailing_breaks);
2935+ STRING_DEL(parser, string);
2936+ STRING_DEL(parser, leading_break);
2937+ STRING_DEL(parser, trailing_breaks);
2943+ * Scan intendation spaces and line breaks for a block scalar. Determine the
2944+ * intendation level if needed.
2948+yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser,
2949+ int *indent, yaml_string_t *breaks,
2950+ yaml_mark_t start_mark, yaml_mark_t *end_mark)
2952+ int max_indent = 0;
2954+ *end_mark = parser->mark;
2956+ /* Eat the intendation spaces and line breaks. */
2960+ /* Eat the intendation spaces. */
2962+ if (!CACHE(parser, 1)) return 0;
2964+ while ((!*indent || (int)parser->mark.column < *indent)
2965+ && IS_SPACE(parser->buffer)) {
2967+ if (!CACHE(parser, 1)) return 0;
2970+ if ((int)parser->mark.column > max_indent)
2971+ max_indent = (int)parser->mark.column;
2973+ /* Check for a tab character messing the intendation. */
2975+ if ((!*indent || (int)parser->mark.column < *indent)
2976+ && IS_TAB(parser->buffer)) {
2977+ return yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2978+ start_mark, "found a tab character where an intendation space is expected");
2981+ /* Have we found a non-empty line? */
2983+ if (!IS_BREAK(parser->buffer)) break;
2985+ /* Consume the line break. */
2987+ if (!CACHE(parser, 2)) return 0;
2988+ if (!READ_LINE(parser, *breaks)) return 0;
2989+ *end_mark = parser->mark;
2992+ /* Determine the indentation level if needed. */
2995+ *indent = max_indent;
2996+ if (*indent < parser->indent + 1)
2997+ *indent = parser->indent + 1;
3006+ * Scan a quoted scalar.
3010+yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token,
3013+ yaml_mark_t start_mark;
3014+ yaml_mark_t end_mark;
3015+ yaml_string_t string = NULL_STRING;
3016+ yaml_string_t leading_break = NULL_STRING;
3017+ yaml_string_t trailing_breaks = NULL_STRING;
3018+ yaml_string_t whitespaces = NULL_STRING;
3019+ int leading_blanks;
3021+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3022+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3023+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3024+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3026+ /* Eat the left quote. */
3028+ start_mark = parser->mark;
3032+ /* Consume the content of the quoted scalar. */
3036+ /* Check that there are no document indicators at the beginning of the line. */
3038+ if (!CACHE(parser, 4)) goto error;
3040+ if (parser->mark.column == 0 &&
3041+ ((CHECK_AT(parser->buffer, '-', 0) &&
3042+ CHECK_AT(parser->buffer, '-', 1) &&
3043+ CHECK_AT(parser->buffer, '-', 2)) ||
3044+ (CHECK_AT(parser->buffer, '.', 0) &&
3045+ CHECK_AT(parser->buffer, '.', 1) &&
3046+ CHECK_AT(parser->buffer, '.', 2))) &&
3047+ IS_BLANKZ_AT(parser->buffer, 3))
3049+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3050+ start_mark, "found unexpected document indicator");
3054+ /* Check for EOF. */
3056+ if (IS_Z(parser->buffer)) {
3057+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3058+ start_mark, "found unexpected end of stream");
3062+ /* Consume non-blank characters. */
3064+ if (!CACHE(parser, 2)) goto error;
3066+ leading_blanks = 0;
3068+ while (!IS_BLANKZ(parser->buffer))
3070+ /* Check for an escaped single quote. */
3072+ if (single && CHECK_AT(parser->buffer, '\'', 0)
3073+ && CHECK_AT(parser->buffer, '\'', 1))
3075+ if (!STRING_EXTEND(parser, string)) goto error;
3076+ *(string.pointer++) = '\'';
3081+ /* Check for the right quote. */
3083+ else if (CHECK(parser->buffer, single ? '\'' : '"'))
3088+ /* Check for an escaped line break. */
3090+ else if (!single && CHECK(parser->buffer, '\\')
3091+ && IS_BREAK_AT(parser->buffer, 1))
3093+ if (!CACHE(parser, 3)) goto error;
3096+ leading_blanks = 1;
3100+ /* Check for an escape sequence. */
3102+ else if (!single && CHECK(parser->buffer, '\\'))
3104+ size_t code_length = 0;
3106+ if (!STRING_EXTEND(parser, string)) goto error;
3108+ /* Check the escape character. */
3110+ switch (parser->buffer.pointer[1])
3113+ *(string.pointer++) = '\0';
3117+ *(string.pointer++) = '\x07';
3121+ *(string.pointer++) = '\x08';
3126+ *(string.pointer++) = '\x09';
3130+ *(string.pointer++) = '\x0A';
3134+ *(string.pointer++) = '\x0B';
3138+ *(string.pointer++) = '\x0C';
3142+ *(string.pointer++) = '\x0D';
3146+ *(string.pointer++) = '\x1B';
3150+ *(string.pointer++) = '\x20';
3154+ *(string.pointer++) = '"';
3158+ *(string.pointer++) = '\'';
3162+ *(string.pointer++) = '\\';
3165+ case 'N': /* NEL (#x85) */
3166+ *(string.pointer++) = '\xC2';
3167+ *(string.pointer++) = '\x85';
3170+ case '_': /* #xA0 */
3171+ *(string.pointer++) = '\xC2';
3172+ *(string.pointer++) = '\xA0';
3175+ case 'L': /* LS (#x2028) */
3176+ *(string.pointer++) = '\xE2';
3177+ *(string.pointer++) = '\x80';
3178+ *(string.pointer++) = '\xA8';
3181+ case 'P': /* PS (#x2029) */
3182+ *(string.pointer++) = '\xE2';
3183+ *(string.pointer++) = '\x80';
3184+ *(string.pointer++) = '\xA9';
3200+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3201+ start_mark, "found unknown escape character");
3208+ /* Consume an arbitrary escape code. */
3212+ unsigned int value = 0;
3215+ /* Scan the character value. */
3217+ if (!CACHE(parser, code_length)) goto error;
3219+ for (k = 0; k < code_length; k ++) {
3220+ if (!IS_HEX_AT(parser->buffer, k)) {
3221+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3222+ start_mark, "did not find expected hexdecimal number");
3225+ value = (value << 4) + AS_HEX_AT(parser->buffer, k);
3228+ /* Check the value and write the character. */
3230+ if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) {
3231+ yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar",
3232+ start_mark, "found invalid Unicode character escape code");
3236+ if (value <= 0x7F) {
3237+ *(string.pointer++) = value;
3239+ else if (value <= 0x7FF) {
3240+ *(string.pointer++) = 0xC0 + (value >> 6);
3241+ *(string.pointer++) = 0x80 + (value & 0x3F);
3243+ else if (value <= 0xFFFF) {
3244+ *(string.pointer++) = 0xE0 + (value >> 12);
3245+ *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3246+ *(string.pointer++) = 0x80 + (value & 0x3F);
3249+ *(string.pointer++) = 0xF0 + (value >> 18);
3250+ *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F);
3251+ *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F);
3252+ *(string.pointer++) = 0x80 + (value & 0x3F);
3255+ /* Advance the pointer. */
3257+ for (k = 0; k < code_length; k ++) {
3265+ /* It is a non-escaped non-blank character. */
3267+ if (!READ(parser, string)) goto error;
3270+ if (!CACHE(parser, 2)) goto error;
3273+ /* Check if we are at the end of the scalar. */
3275+ if (CHECK(parser->buffer, single ? '\'' : '"'))
3278+ /* Consume blank characters. */
3280+ if (!CACHE(parser, 1)) goto error;
3282+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3284+ if (IS_BLANK(parser->buffer))
3286+ /* Consume a space or a tab character. */
3288+ if (!leading_blanks) {
3289+ if (!READ(parser, whitespaces)) goto error;
3297+ if (!CACHE(parser, 2)) goto error;
3299+ /* Check if it is a first line break. */
3301+ if (!leading_blanks)
3303+ CLEAR(parser, whitespaces);
3304+ if (!READ_LINE(parser, leading_break)) goto error;
3305+ leading_blanks = 1;
3309+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3312+ if (!CACHE(parser, 1)) goto error;
3315+ /* Join the whitespaces or fold line breaks. */
3317+ if (leading_blanks)
3319+ /* Do we need to fold line breaks? */
3321+ if (leading_break.start[0] == '\n') {
3322+ if (trailing_breaks.start[0] == '\0') {
3323+ if (!STRING_EXTEND(parser, string)) goto error;
3324+ *(string.pointer++) = ' ';
3327+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3328+ CLEAR(parser, trailing_breaks);
3330+ CLEAR(parser, leading_break);
3333+ if (!JOIN(parser, string, leading_break)) goto error;
3334+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3335+ CLEAR(parser, leading_break);
3336+ CLEAR(parser, trailing_breaks);
3341+ if (!JOIN(parser, string, whitespaces)) goto error;
3342+ CLEAR(parser, whitespaces);
3346+ /* Eat the right quote. */
3350+ end_mark = parser->mark;
3352+ /* Create a token. */
3354+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3355+ single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE,
3356+ start_mark, end_mark);
3358+ STRING_DEL(parser, leading_break);
3359+ STRING_DEL(parser, trailing_breaks);
3360+ STRING_DEL(parser, whitespaces);
3365+ STRING_DEL(parser, string);
3366+ STRING_DEL(parser, leading_break);
3367+ STRING_DEL(parser, trailing_breaks);
3368+ STRING_DEL(parser, whitespaces);
3374+ * Scan a plain scalar.
3378+yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token)
3380+ yaml_mark_t start_mark;
3381+ yaml_mark_t end_mark;
3382+ yaml_string_t string = NULL_STRING;
3383+ yaml_string_t leading_break = NULL_STRING;
3384+ yaml_string_t trailing_breaks = NULL_STRING;
3385+ yaml_string_t whitespaces = NULL_STRING;
3386+ int leading_blanks = 0;
3387+ int indent = parser->indent+1;
3389+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3390+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3391+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3392+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3394+ start_mark = end_mark = parser->mark;
3396+ /* Consume the content of the plain scalar. */
3400+ /* Check for a document indicator. */
3402+ if (!CACHE(parser, 4)) goto error;
3404+ if (parser->mark.column == 0 &&
3405+ ((CHECK_AT(parser->buffer, '-', 0) &&
3406+ CHECK_AT(parser->buffer, '-', 1) &&
3407+ CHECK_AT(parser->buffer, '-', 2)) ||
3408+ (CHECK_AT(parser->buffer, '.', 0) &&
3409+ CHECK_AT(parser->buffer, '.', 1) &&
3410+ CHECK_AT(parser->buffer, '.', 2))) &&
3411+ IS_BLANKZ_AT(parser->buffer, 3)) break;
3413+ /* Check for a comment. */
3415+ if (CHECK(parser->buffer, '#'))
3418+ /* Consume non-blank characters. */
3420+ while (!IS_BLANKZ(parser->buffer))
3422+ /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */
3424+ if (parser->flow_level
3425+ && CHECK(parser->buffer, ':')
3426+ && !IS_BLANKZ_AT(parser->buffer, 1)) {
3427+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3428+ start_mark, "found unexpected ':'");
3432+ /* Check for indicators that may end a plain scalar. */
3434+ if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1))
3435+ || (parser->flow_level &&
3436+ (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':')
3437+ || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[')
3438+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{')
3439+ || CHECK(parser->buffer, '}'))))
3442+ /* Check if we need to join whitespaces and breaks. */
3444+ if (leading_blanks || whitespaces.start != whitespaces.pointer)
3446+ if (leading_blanks)
3448+ /* Do we need to fold line breaks? */
3450+ if (leading_break.start[0] == '\n') {
3451+ if (trailing_breaks.start[0] == '\0') {
3452+ if (!STRING_EXTEND(parser, string)) goto error;
3453+ *(string.pointer++) = ' ';
3456+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3457+ CLEAR(parser, trailing_breaks);
3459+ CLEAR(parser, leading_break);
3462+ if (!JOIN(parser, string, leading_break)) goto error;
3463+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3464+ CLEAR(parser, leading_break);
3465+ CLEAR(parser, trailing_breaks);
3468+ leading_blanks = 0;
3472+ if (!JOIN(parser, string, whitespaces)) goto error;
3473+ CLEAR(parser, whitespaces);
3477+ /* Copy the character. */
3479+ if (!READ(parser, string)) goto error;
3481+ end_mark = parser->mark;
3483+ if (!CACHE(parser, 2)) goto error;
3486+ /* Is it the end? */
3488+ if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)))
3491+ /* Consume blank characters. */
3493+ if (!CACHE(parser, 1)) goto error;
3495+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3497+ if (IS_BLANK(parser->buffer))
3499+ /* Check for tab character that abuse intendation. */
3501+ if (leading_blanks && (int)parser->mark.column < indent
3502+ && IS_TAB(parser->buffer)) {
3503+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3504+ start_mark, "found a tab character that violate intendation");
3508+ /* Consume a space or a tab character. */
3510+ if (!leading_blanks) {
3511+ if (!READ(parser, whitespaces)) goto error;
3519+ if (!CACHE(parser, 2)) goto error;
3521+ /* Check if it is a first line break. */
3523+ if (!leading_blanks)
3525+ CLEAR(parser, whitespaces);
3526+ if (!READ_LINE(parser, leading_break)) goto error;
3527+ leading_blanks = 1;
3531+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3534+ if (!CACHE(parser, 1)) goto error;
3537+ /* Check intendation level. */
3539+ if (!parser->flow_level && (int)parser->mark.column < indent)
3543+ /* Create a token. */
3545+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3546+ YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark);
3548+ /* Note that we change the 'simple_key_allowed' flag. */
3550+ if (leading_blanks) {
3551+ parser->simple_key_allowed = 1;
3554+ STRING_DEL(parser, leading_break);
3555+ STRING_DEL(parser, trailing_breaks);
3556+ STRING_DEL(parser, whitespaces);
3561+ STRING_DEL(parser, string);
3562+ STRING_DEL(parser, leading_break);
3563+ STRING_DEL(parser, trailing_breaks);
3564+ STRING_DEL(parser, whitespaces);