@@ -0,0 +1,3580 @@
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, 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+ * 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;
1122+ simple_key.possible = 1;
1123+ simple_key.required = required;
1124+ simple_key.token_number =
1125+ parser->tokens_parsed + (parser->tokens.tail - parser->tokens.head);
1126+ simple_key.mark = parser->mark;
1128+ if (!yaml_parser_remove_simple_key(parser)) return 0;
1130+ *(parser->simple_keys.top-1) = simple_key;
1137+ * Remove a potential simple key at the current flow level.
1141+yaml_parser_remove_simple_key(yaml_parser_t *parser)
1143+ yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1145+ if (simple_key->possible)
1147+ /* If the key is required, it is an error. */
1149+ if (simple_key->required) {
1150+ return yaml_parser_set_scanner_error(parser,
1151+ "while scanning a simple key", simple_key->mark,
1152+ "could not find expected ':'");
1156+ /* Remove the key from the stack. */
1158+ simple_key->possible = 0;
1164+ * Increase the flow level and resize the simple key list if needed.
1168+yaml_parser_increase_flow_level(yaml_parser_t *parser)
1170+ yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } };
1172+ /* Reset the simple key on the next level. */
1174+ if (!PUSH(parser, parser->simple_keys, empty_simple_key))
1177+ /* Increase the flow level. */
1179+ if (parser->flow_level == INT_MAX) {
1180+ parser->error = YAML_MEMORY_ERROR;
1184+ parser->flow_level++;
1190+ * Decrease the flow level.
1194+yaml_parser_decrease_flow_level(yaml_parser_t *parser)
1196+ yaml_simple_key_t dummy_key; /* Used to eliminate a compiler warning. */
1198+ if (parser->flow_level) {
1199+ parser->flow_level --;
1200+ dummy_key = POP(parser, parser->simple_keys);
1207+ * Push the current indentation level to the stack and set the new level
1208+ * the current column is greater than the indentation level. In this case,
1209+ * append or insert the specified token into the token queue.
1214+yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column,
1215+ ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark)
1217+ yaml_token_t token;
1219+ /* In the flow context, do nothing. */
1221+ if (parser->flow_level)
1224+ if (parser->indent < column)
1227+ * Push the current indentation level to the stack and set the new
1228+ * indentation level.
1231+ if (!PUSH(parser, parser->indents, parser->indent))
1234+ if (column > INT_MAX) {
1235+ parser->error = YAML_MEMORY_ERROR;
1239+ parser->indent = column;
1241+ /* Create a token and insert it into the queue. */
1243+ TOKEN_INIT(token, type, mark, mark);
1245+ if (number == -1) {
1246+ if (!ENQUEUE(parser, parser->tokens, token))
1250+ if (!QUEUE_INSERT(parser,
1251+ parser->tokens, number - parser->tokens_parsed, token))
1260+ * Pop indentation levels from the indents stack until the current level
1261+ * becomes less or equal to the column. For each intendation level, append
1262+ * the BLOCK-END token.
1267+yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column)
1269+ yaml_token_t token;
1271+ /* In the flow context, do nothing. */
1273+ if (parser->flow_level)
1276+ /* Loop through the intendation levels in the stack. */
1278+ while (parser->indent > column)
1280+ /* Create a token and append it to the queue. */
1282+ TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark);
1284+ if (!ENQUEUE(parser, parser->tokens, token))
1287+ /* Pop the indentation level. */
1289+ parser->indent = POP(parser, parser->indents);
1296+ * Initialize the scanner and produce the STREAM-START token.
1300+yaml_parser_fetch_stream_start(yaml_parser_t *parser)
1302+ yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } };
1303+ yaml_token_t token;
1305+ /* Set the initial indentation. */
1307+ parser->indent = -1;
1309+ /* Initialize the simple key stack. */
1311+ if (!PUSH(parser, parser->simple_keys, simple_key))
1314+ /* A simple key is allowed at the beginning of the stream. */
1316+ parser->simple_key_allowed = 1;
1318+ /* We have started. */
1320+ parser->stream_start_produced = 1;
1322+ /* Create the STREAM-START token and append it to the queue. */
1324+ STREAM_START_TOKEN_INIT(token, parser->encoding,
1325+ parser->mark, parser->mark);
1327+ if (!ENQUEUE(parser, parser->tokens, token))
1334+ * Produce the STREAM-END token and shut down the scanner.
1338+yaml_parser_fetch_stream_end(yaml_parser_t *parser)
1340+ yaml_token_t token;
1342+ /* Force new line. */
1344+ if (parser->mark.column != 0) {
1345+ parser->mark.column = 0;
1346+ parser->mark.line ++;
1349+ /* Reset the indentation level. */
1351+ if (!yaml_parser_unroll_indent(parser, -1))
1354+ /* Reset simple keys. */
1356+ if (!yaml_parser_remove_simple_key(parser))
1359+ parser->simple_key_allowed = 0;
1361+ /* Create the STREAM-END token and append it to the queue. */
1363+ STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark);
1365+ if (!ENQUEUE(parser, parser->tokens, token))
1372+ * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token.
1376+yaml_parser_fetch_directive(yaml_parser_t *parser)
1378+ yaml_token_t token;
1380+ /* Reset the indentation level. */
1382+ if (!yaml_parser_unroll_indent(parser, -1))
1385+ /* Reset simple keys. */
1387+ if (!yaml_parser_remove_simple_key(parser))
1390+ parser->simple_key_allowed = 0;
1392+ /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */
1394+ if (!yaml_parser_scan_directive(parser, &token))
1397+ /* Append the token to the queue. */
1399+ if (!ENQUEUE(parser, parser->tokens, token)) {
1400+ yaml_token_delete(&token);
1408+ * Produce the DOCUMENT-START or DOCUMENT-END token.
1412+yaml_parser_fetch_document_indicator(yaml_parser_t *parser,
1413+ yaml_token_type_t type)
1415+ yaml_mark_t start_mark, end_mark;
1416+ yaml_token_t token;
1418+ /* Reset the indentation level. */
1420+ if (!yaml_parser_unroll_indent(parser, -1))
1423+ /* Reset simple keys. */
1425+ if (!yaml_parser_remove_simple_key(parser))
1428+ parser->simple_key_allowed = 0;
1430+ /* Consume the token. */
1432+ start_mark = parser->mark;
1438+ end_mark = parser->mark;
1440+ /* Create the DOCUMENT-START or DOCUMENT-END token. */
1442+ TOKEN_INIT(token, type, start_mark, end_mark);
1444+ /* Append the token to the queue. */
1446+ if (!ENQUEUE(parser, parser->tokens, token))
1453+ * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token.
1457+yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser,
1458+ yaml_token_type_t type)
1460+ yaml_mark_t start_mark, end_mark;
1461+ yaml_token_t token;
1463+ /* The indicators '[' and '{' may start a simple key. */
1465+ if (!yaml_parser_save_simple_key(parser))
1468+ /* Increase the flow level. */
1470+ if (!yaml_parser_increase_flow_level(parser))
1473+ /* A simple key may follow the indicators '[' and '{'. */
1475+ parser->simple_key_allowed = 1;
1477+ /* Consume the token. */
1479+ start_mark = parser->mark;
1481+ end_mark = parser->mark;
1483+ /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */
1485+ TOKEN_INIT(token, type, start_mark, end_mark);
1487+ /* Append the token to the queue. */
1489+ if (!ENQUEUE(parser, parser->tokens, token))
1496+ * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token.
1500+yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser,
1501+ yaml_token_type_t type)
1503+ yaml_mark_t start_mark, end_mark;
1504+ yaml_token_t token;
1506+ /* Reset any potential simple key on the current flow level. */
1508+ if (!yaml_parser_remove_simple_key(parser))
1511+ /* Decrease the flow level. */
1513+ if (!yaml_parser_decrease_flow_level(parser))
1516+ /* No simple keys after the indicators ']' and '}'. */
1518+ parser->simple_key_allowed = 0;
1520+ /* Consume the token. */
1522+ start_mark = parser->mark;
1524+ end_mark = parser->mark;
1526+ /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */
1528+ TOKEN_INIT(token, type, start_mark, end_mark);
1530+ /* Append the token to the queue. */
1532+ if (!ENQUEUE(parser, parser->tokens, token))
1539+ * Produce the FLOW-ENTRY token.
1543+yaml_parser_fetch_flow_entry(yaml_parser_t *parser)
1545+ yaml_mark_t start_mark, end_mark;
1546+ yaml_token_t token;
1548+ /* Reset any potential simple keys on the current flow level. */
1550+ if (!yaml_parser_remove_simple_key(parser))
1553+ /* Simple keys are allowed after ','. */
1555+ parser->simple_key_allowed = 1;
1557+ /* Consume the token. */
1559+ start_mark = parser->mark;
1561+ end_mark = parser->mark;
1563+ /* Create the FLOW-ENTRY token and append it to the queue. */
1565+ TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark);
1567+ if (!ENQUEUE(parser, parser->tokens, token))
1574+ * Produce the BLOCK-ENTRY token.
1578+yaml_parser_fetch_block_entry(yaml_parser_t *parser)
1580+ yaml_mark_t start_mark, end_mark;
1581+ yaml_token_t token;
1583+ /* Check if the scanner is in the block context. */
1585+ if (!parser->flow_level)
1587+ /* Check if we are allowed to start a new entry. */
1589+ if (!parser->simple_key_allowed) {
1590+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1591+ "block sequence entries are not allowed in this context");
1594+ /* Add the BLOCK-SEQUENCE-START token if needed. */
1596+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1597+ YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark))
1603+ * It is an error for the '-' indicator to occur in the flow context,
1604+ * but we let the Parser detect and report about it because the Parser
1605+ * is able to point to the context.
1609+ /* Reset any potential simple keys on the current flow level. */
1611+ if (!yaml_parser_remove_simple_key(parser))
1614+ /* Simple keys are allowed after '-'. */
1616+ parser->simple_key_allowed = 1;
1618+ /* Consume the token. */
1620+ start_mark = parser->mark;
1622+ end_mark = parser->mark;
1624+ /* Create the BLOCK-ENTRY token and append it to the queue. */
1626+ TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark);
1628+ if (!ENQUEUE(parser, parser->tokens, token))
1635+ * Produce the KEY token.
1639+yaml_parser_fetch_key(yaml_parser_t *parser)
1641+ yaml_mark_t start_mark, end_mark;
1642+ yaml_token_t token;
1644+ /* In the block context, additional checks are required. */
1646+ if (!parser->flow_level)
1648+ /* Check if we are allowed to start a new key (not nessesary simple). */
1650+ if (!parser->simple_key_allowed) {
1651+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1652+ "mapping keys are not allowed in this context");
1655+ /* Add the BLOCK-MAPPING-START token if needed. */
1657+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1658+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1662+ /* Reset any potential simple keys on the current flow level. */
1664+ if (!yaml_parser_remove_simple_key(parser))
1667+ /* Simple keys are allowed after '?' in the block context. */
1669+ parser->simple_key_allowed = (!parser->flow_level);
1671+ /* Consume the token. */
1673+ start_mark = parser->mark;
1675+ end_mark = parser->mark;
1677+ /* Create the KEY token and append it to the queue. */
1679+ TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark);
1681+ if (!ENQUEUE(parser, parser->tokens, token))
1688+ * Produce the VALUE token.
1692+yaml_parser_fetch_value(yaml_parser_t *parser)
1694+ yaml_mark_t start_mark, end_mark;
1695+ yaml_token_t token;
1696+ yaml_simple_key_t *simple_key = parser->simple_keys.top-1;
1698+ /* Have we found a simple key? */
1700+ if (simple_key->possible)
1703+ /* Create the KEY token and insert it into the queue. */
1705+ TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark);
1707+ if (!QUEUE_INSERT(parser, parser->tokens,
1708+ simple_key->token_number - parser->tokens_parsed, token))
1711+ /* In the block context, we may need to add the BLOCK-MAPPING-START token. */
1713+ if (!yaml_parser_roll_indent(parser, simple_key->mark.column,
1714+ simple_key->token_number,
1715+ YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark))
1718+ /* Remove the simple key. */
1720+ simple_key->possible = 0;
1722+ /* A simple key cannot follow another simple key. */
1724+ parser->simple_key_allowed = 0;
1728+ /* The ':' indicator follows a complex key. */
1730+ /* In the block context, extra checks are required. */
1732+ if (!parser->flow_level)
1734+ /* Check if we are allowed to start a complex value. */
1736+ if (!parser->simple_key_allowed) {
1737+ return yaml_parser_set_scanner_error(parser, NULL, parser->mark,
1738+ "mapping values are not allowed in this context");
1741+ /* Add the BLOCK-MAPPING-START token if needed. */
1743+ if (!yaml_parser_roll_indent(parser, parser->mark.column, -1,
1744+ YAML_BLOCK_MAPPING_START_TOKEN, parser->mark))
1748+ /* Simple keys after ':' are allowed in the block context. */
1750+ parser->simple_key_allowed = (!parser->flow_level);
1753+ /* Consume the token. */
1755+ start_mark = parser->mark;
1757+ end_mark = parser->mark;
1759+ /* Create the VALUE token and append it to the queue. */
1761+ TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark);
1763+ if (!ENQUEUE(parser, parser->tokens, token))
1770+ * Produce the ALIAS or ANCHOR token.
1774+yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type)
1776+ yaml_token_t token;
1778+ /* An anchor or an alias could be a simple key. */
1780+ if (!yaml_parser_save_simple_key(parser))
1783+ /* A simple key cannot follow an anchor or an alias. */
1785+ parser->simple_key_allowed = 0;
1787+ /* Create the ALIAS or ANCHOR token and append it to the queue. */
1789+ if (!yaml_parser_scan_anchor(parser, &token, type))
1792+ if (!ENQUEUE(parser, parser->tokens, token)) {
1793+ yaml_token_delete(&token);
1800+ * Produce the TAG token.
1804+yaml_parser_fetch_tag(yaml_parser_t *parser)
1806+ yaml_token_t token;
1808+ /* A tag could be a simple key. */
1810+ if (!yaml_parser_save_simple_key(parser))
1813+ /* A simple key cannot follow a tag. */
1815+ parser->simple_key_allowed = 0;
1817+ /* Create the TAG token and append it to the queue. */
1819+ if (!yaml_parser_scan_tag(parser, &token))
1822+ if (!ENQUEUE(parser, parser->tokens, token)) {
1823+ yaml_token_delete(&token);
1831+ * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens.
1835+yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal)
1837+ yaml_token_t token;
1839+ /* Remove any potential simple keys. */
1841+ if (!yaml_parser_remove_simple_key(parser))
1844+ /* A simple key may follow a block scalar. */
1846+ parser->simple_key_allowed = 1;
1848+ /* Create the SCALAR token and append it to the queue. */
1850+ if (!yaml_parser_scan_block_scalar(parser, &token, literal))
1853+ if (!ENQUEUE(parser, parser->tokens, token)) {
1854+ yaml_token_delete(&token);
1862+ * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens.
1866+yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single)
1868+ yaml_token_t token;
1870+ /* A plain scalar could be a simple key. */
1872+ if (!yaml_parser_save_simple_key(parser))
1875+ /* A simple key cannot follow a flow scalar. */
1877+ parser->simple_key_allowed = 0;
1879+ /* Create the SCALAR token and append it to the queue. */
1881+ if (!yaml_parser_scan_flow_scalar(parser, &token, single))
1884+ if (!ENQUEUE(parser, parser->tokens, token)) {
1885+ yaml_token_delete(&token);
1893+ * Produce the SCALAR(...,plain) token.
1897+yaml_parser_fetch_plain_scalar(yaml_parser_t *parser)
1899+ yaml_token_t token;
1901+ /* A plain scalar could be a simple key. */
1903+ if (!yaml_parser_save_simple_key(parser))
1906+ /* A simple key cannot follow a flow scalar. */
1908+ parser->simple_key_allowed = 0;
1910+ /* Create the SCALAR token and append it to the queue. */
1912+ if (!yaml_parser_scan_plain_scalar(parser, &token))
1915+ if (!ENQUEUE(parser, parser->tokens, token)) {
1916+ yaml_token_delete(&token);
1924+ * Eat whitespaces and comments until the next token is found.
1928+yaml_parser_scan_to_next_token(yaml_parser_t *parser)
1930+ /* Until the next token is not found. */
1934+ /* Allow the BOM mark to start a line. */
1936+ if (!CACHE(parser, 1)) return 0;
1938+ if (parser->mark.column == 0 && IS_BOM(parser->buffer))
1944+ * Tabs are allowed:
1946+ * - in the flow context;
1947+ * - in the block context, but not at the beginning of the line or
1948+ * after '-', '?', or ':' (complex value).
1951+ if (!CACHE(parser, 1)) return 0;
1953+ while (CHECK(parser->buffer,' ') ||
1954+ ((parser->flow_level || !parser->simple_key_allowed) &&
1955+ CHECK(parser->buffer, '\t'))) {
1957+ if (!CACHE(parser, 1)) return 0;
1960+ /* Eat a comment until a line break. */
1962+ if (CHECK(parser->buffer, '#')) {
1963+ while (!IS_BREAKZ(parser->buffer)) {
1965+ if (!CACHE(parser, 1)) return 0;
1969+ /* If it is a line break, eat it. */
1971+ if (IS_BREAK(parser->buffer))
1973+ if (!CACHE(parser, 2)) return 0;
1976+ /* In the block context, a new line may start a simple key. */
1978+ if (!parser->flow_level) {
1979+ parser->simple_key_allowed = 1;
1984+ /* We have found a token. */
1994+ * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token.
1997+ * %YAML 1.1 # a comment \n
1998+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1999+ * %TAG !yaml! tag:yaml.org,2002: \n
2000+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2004+yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token)
2006+ yaml_mark_t start_mark, end_mark;
2007+ yaml_char_t *name = NULL;
2009+ yaml_char_t *handle = NULL, *prefix = NULL;
2013+ start_mark = parser->mark;
2017+ /* Scan the directive name. */
2019+ if (!yaml_parser_scan_directive_name(parser, start_mark, &name))
2022+ /* Is it a YAML directive? */
2024+ if (strcmp((char *)name, "YAML") == 0)
2026+ /* Scan the VERSION directive value. */
2028+ if (!yaml_parser_scan_version_directive_value(parser, start_mark,
2032+ end_mark = parser->mark;
2034+ /* Create a VERSION-DIRECTIVE token. */
2036+ VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor,
2037+ start_mark, end_mark);
2040+ /* Is it a TAG directive? */
2042+ else if (strcmp((char *)name, "TAG") == 0)
2044+ /* Scan the TAG directive value. */
2046+ if (!yaml_parser_scan_tag_directive_value(parser, start_mark,
2050+ end_mark = parser->mark;
2052+ /* Create a TAG-DIRECTIVE token. */
2054+ TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix,
2055+ start_mark, end_mark);
2058+ /* Unknown directive. */
2062+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2063+ start_mark, "found uknown directive name");
2067+ /* Eat the rest of the line including any comments. */
2069+ if (!CACHE(parser, 1)) goto error;
2071+ while (IS_BLANK(parser->buffer)) {
2073+ if (!CACHE(parser, 1)) goto error;
2076+ if (CHECK(parser->buffer, '#')) {
2077+ while (!IS_BREAKZ(parser->buffer)) {
2079+ if (!CACHE(parser, 1)) goto error;
2083+ /* Check if we are at the end of the line. */
2085+ if (!IS_BREAKZ(parser->buffer)) {
2086+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2087+ start_mark, "did not find expected comment or line break");
2091+ /* Eat a line break. */
2093+ if (IS_BREAK(parser->buffer)) {
2094+ if (!CACHE(parser, 2)) goto error;
2110+ * Scan the directive name.
2113+ * %YAML 1.1 # a comment \n
2115+ * %TAG !yaml! tag:yaml.org,2002: \n
2120+yaml_parser_scan_directive_name(yaml_parser_t *parser,
2121+ yaml_mark_t start_mark, yaml_char_t **name)
2123+ yaml_string_t string = NULL_STRING;
2125+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2127+ /* Consume the directive name. */
2129+ if (!CACHE(parser, 1)) goto error;
2131+ while (IS_ALPHA(parser->buffer))
2133+ if (!READ(parser, string)) goto error;
2134+ if (!CACHE(parser, 1)) goto error;
2137+ /* Check if the name is empty. */
2139+ if (string.start == string.pointer) {
2140+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2141+ start_mark, "could not find expected directive name");
2145+ /* Check for an blank character after the name. */
2147+ if (!IS_BLANKZ(parser->buffer)) {
2148+ yaml_parser_set_scanner_error(parser, "while scanning a directive",
2149+ start_mark, "found unexpected non-alphabetical character");
2153+ *name = string.start;
2158+ STRING_DEL(parser, string);
2163+ * Scan the value of VERSION-DIRECTIVE.
2166+ * %YAML 1.1 # a comment \n
2171+yaml_parser_scan_version_directive_value(yaml_parser_t *parser,
2172+ yaml_mark_t start_mark, int *major, int *minor)
2174+ /* Eat whitespaces. */
2176+ if (!CACHE(parser, 1)) return 0;
2178+ while (IS_BLANK(parser->buffer)) {
2180+ if (!CACHE(parser, 1)) return 0;
2183+ /* Consume the major version number. */
2185+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, major))
2190+ if (!CHECK(parser->buffer, '.')) {
2191+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2192+ start_mark, "did not find expected digit or '.' character");
2197+ /* Consume the minor version number. */
2199+ if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor))
2205+#define MAX_NUMBER_LENGTH 9
2208+ * Scan the version number of VERSION-DIRECTIVE.
2211+ * %YAML 1.1 # a comment \n
2213+ * %YAML 1.1 # a comment \n
2218+yaml_parser_scan_version_directive_number(yaml_parser_t *parser,
2219+ yaml_mark_t start_mark, int *number)
2224+ /* Repeat while the next character is digit. */
2226+ if (!CACHE(parser, 1)) return 0;
2228+ while (IS_DIGIT(parser->buffer))
2230+ /* Check if the number is too long. */
2232+ if (++length > MAX_NUMBER_LENGTH) {
2233+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2234+ start_mark, "found extremely long version number");
2237+ value = value*10 + AS_DIGIT(parser->buffer);
2241+ if (!CACHE(parser, 1)) return 0;
2244+ /* Check if the number was present. */
2247+ return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive",
2248+ start_mark, "did not find expected version number");
2257+ * Scan the value of a TAG-DIRECTIVE token.
2260+ * %TAG !yaml! tag:yaml.org,2002: \n
2261+ * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2265+yaml_parser_scan_tag_directive_value(yaml_parser_t *parser,
2266+ yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix)
2268+ yaml_char_t *handle_value = NULL;
2269+ yaml_char_t *prefix_value = NULL;
2271+ /* Eat whitespaces. */
2273+ if (!CACHE(parser, 1)) goto error;
2275+ while (IS_BLANK(parser->buffer)) {
2277+ if (!CACHE(parser, 1)) goto error;
2280+ /* Scan a handle. */
2282+ if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value))
2285+ /* Expect a whitespace. */
2287+ if (!CACHE(parser, 1)) goto error;
2289+ if (!IS_BLANK(parser->buffer)) {
2290+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2291+ start_mark, "did not find expected whitespace");
2295+ /* Eat whitespaces. */
2297+ while (IS_BLANK(parser->buffer)) {
2299+ if (!CACHE(parser, 1)) goto error;
2302+ /* Scan a prefix. */
2304+ if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value))
2307+ /* Expect a whitespace or line break. */
2309+ if (!CACHE(parser, 1)) goto error;
2311+ if (!IS_BLANKZ(parser->buffer)) {
2312+ yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive",
2313+ start_mark, "did not find expected whitespace or line break");
2317+ *handle = handle_value;
2318+ *prefix = prefix_value;
2323+ yaml_free(handle_value);
2324+ yaml_free(prefix_value);
2329+yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token,
2330+ yaml_token_type_t type)
2333+ yaml_mark_t start_mark, end_mark;
2334+ yaml_string_t string = NULL_STRING;
2336+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2338+ /* Eat the indicator character. */
2340+ start_mark = parser->mark;
2344+ /* Consume the value. */
2346+ if (!CACHE(parser, 1)) goto error;
2348+ while (IS_ALPHA(parser->buffer)) {
2349+ if (!READ(parser, string)) goto error;
2350+ if (!CACHE(parser, 1)) goto error;
2354+ end_mark = parser->mark;
2357+ * Check if length of the anchor is greater than 0 and it is followed by
2358+ * a whitespace character or one of the indicators:
2360+ * '?', ':', ',', ']', '}', '%', '@', '`'.
2363+ if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?')
2364+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',')
2365+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}')
2366+ || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@')
2367+ || CHECK(parser->buffer, '`'))) {
2368+ yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ?
2369+ "while scanning an anchor" : "while scanning an alias", start_mark,
2370+ "did not find expected alphabetic or numeric character");
2374+ /* Create a token. */
2376+ if (type == YAML_ANCHOR_TOKEN) {
2377+ ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2380+ ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark);
2386+ STRING_DEL(parser, string);
2391+ * Scan a TAG token.
2395+yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token)
2397+ yaml_char_t *handle = NULL;
2398+ yaml_char_t *suffix = NULL;
2399+ yaml_mark_t start_mark, end_mark;
2401+ start_mark = parser->mark;
2403+ /* Check if the tag is in the canonical form. */
2405+ if (!CACHE(parser, 2)) goto error;
2407+ if (CHECK_AT(parser->buffer, '<', 1))
2409+ /* Set the handle to '' */
2411+ handle = yaml_malloc(1);
2412+ if (!handle) goto error;
2420+ /* Consume the tag value. */
2422+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2425+ /* Check for '>' and eat it. */
2427+ if (!CHECK(parser->buffer, '>')) {
2428+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2429+ start_mark, "did not find the expected '>'");
2437+ /* The tag has either the '!suffix' or the '!handle!suffix' form. */
2439+ /* First, try to scan a handle. */
2441+ if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle))
2444+ /* Check if it is, indeed, handle. */
2446+ if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!')
2448+ /* Scan the suffix now. */
2450+ if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix))
2455+ /* It wasn't a handle after all. Scan the rest of the tag. */
2457+ if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix))
2460+ /* Set the handle to '!'. */
2463+ handle = yaml_malloc(2);
2464+ if (!handle) goto error;
2469+ * A special case: the '!' tag. Set the handle to '' and the
2473+ if (suffix[0] == '\0') {
2474+ yaml_char_t *tmp = handle;
2481+ /* Check the character which ends the tag. */
2483+ if (!CACHE(parser, 1)) goto error;
2485+ if (!IS_BLANKZ(parser->buffer)) {
2486+ yaml_parser_set_scanner_error(parser, "while scanning a tag",
2487+ start_mark, "did not find expected whitespace or line break");
2491+ end_mark = parser->mark;
2493+ /* Create a token. */
2495+ TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark);
2506+ * Scan a tag handle.
2510+yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive,
2511+ yaml_mark_t start_mark, yaml_char_t **handle)
2513+ yaml_string_t string = NULL_STRING;
2515+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2517+ /* Check the initial '!' character. */
2519+ if (!CACHE(parser, 1)) goto error;
2521+ if (!CHECK(parser->buffer, '!')) {
2522+ yaml_parser_set_scanner_error(parser, directive ?
2523+ "while scanning a tag directive" : "while scanning a tag",
2524+ start_mark, "did not find expected '!'");
2528+ /* Copy the '!' character. */
2530+ if (!READ(parser, string)) goto error;
2532+ /* Copy all subsequent alphabetical and numerical characters. */
2534+ if (!CACHE(parser, 1)) goto error;
2536+ while (IS_ALPHA(parser->buffer))
2538+ if (!READ(parser, string)) goto error;
2539+ if (!CACHE(parser, 1)) goto error;
2542+ /* Check if the trailing character is '!' and copy it. */
2544+ if (CHECK(parser->buffer, '!'))
2546+ if (!READ(parser, string)) goto error;
2551+ * It's either the '!' tag or not really a tag handle. If it's a %TAG
2552+ * directive, it's an error. If it's a tag token, it must be a part of
2556+ if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) {
2557+ yaml_parser_set_scanner_error(parser, "while parsing a tag directive",
2558+ start_mark, "did not find expected '!'");
2563+ *handle = string.start;
2568+ STRING_DEL(parser, string);
2577+yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive,
2578+ yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri)
2580+ size_t length = head ? strlen((char *)head) : 0;
2581+ yaml_string_t string = NULL_STRING;
2583+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2585+ /* Resize the string to include the head. */
2587+ while ((size_t)(string.end - string.start) <= length) {
2588+ if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) {
2589+ parser->error = YAML_MEMORY_ERROR;
2595+ * Copy the head if needed.
2597+ * Note that we don't copy the leading '!' character.
2601+ memcpy(string.start, head+1, length-1);
2602+ string.pointer += length-1;
2605+ /* Scan the tag. */
2607+ if (!CACHE(parser, 1)) goto error;
2610+ * The set of characters that may appear in URI is as follows:
2612+ * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&',
2613+ * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']',
2617+ while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';')
2618+ || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?')
2619+ || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@')
2620+ || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=')
2621+ || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$')
2622+ || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.')
2623+ || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~')
2624+ || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'')
2625+ || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')')
2626+ || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']')
2627+ || CHECK(parser->buffer, '%'))
2629+ /* Check if it is a URI-escape sequence. */
2631+ if (CHECK(parser->buffer, '%')) {
2632+ if (!yaml_parser_scan_uri_escapes(parser,
2633+ directive, start_mark, &string)) goto error;
2636+ if (!READ(parser, string)) goto error;
2640+ if (!CACHE(parser, 1)) goto error;
2643+ /* Check if the tag is non-empty. */
2646+ if (!STRING_EXTEND(parser, string))
2649+ yaml_parser_set_scanner_error(parser, directive ?
2650+ "while parsing a %TAG directive" : "while parsing a tag",
2651+ start_mark, "did not find expected tag URI");
2655+ *uri = string.start;
2660+ STRING_DEL(parser, string);
2665+ * Decode an URI-escape sequence corresponding to a single UTF-8 character.
2669+yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive,
2670+ yaml_mark_t start_mark, yaml_string_t *string)
2674+ /* Decode the required number of characters. */
2678+ unsigned char octet = 0;
2680+ /* Check for a URI-escaped octet. */
2682+ if (!CACHE(parser, 3)) return 0;
2684+ if (!(CHECK(parser->buffer, '%')
2685+ && IS_HEX_AT(parser->buffer, 1)
2686+ && IS_HEX_AT(parser->buffer, 2))) {
2687+ return yaml_parser_set_scanner_error(parser, directive ?
2688+ "while parsing a %TAG directive" : "while parsing a tag",
2689+ start_mark, "did not find URI escaped octet");
2692+ /* Get the octet. */
2694+ octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2);
2696+ /* If it is the leading octet, determine the length of the UTF-8 sequence. */
2700+ width = (octet & 0x80) == 0x00 ? 1 :
2701+ (octet & 0xE0) == 0xC0 ? 2 :
2702+ (octet & 0xF0) == 0xE0 ? 3 :
2703+ (octet & 0xF8) == 0xF0 ? 4 : 0;
2705+ return yaml_parser_set_scanner_error(parser, directive ?
2706+ "while parsing a %TAG directive" : "while parsing a tag",
2707+ start_mark, "found an incorrect leading UTF-8 octet");
2712+ /* Check if the trailing octet is correct. */
2714+ if ((octet & 0xC0) != 0x80) {
2715+ return yaml_parser_set_scanner_error(parser, directive ?
2716+ "while parsing a %TAG directive" : "while parsing a tag",
2717+ start_mark, "found an incorrect trailing UTF-8 octet");
2721+ /* Copy the octet and move the pointers. */
2723+ *(string->pointer++) = octet;
2734+ * Scan a block scalar.
2738+yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token,
2741+ yaml_mark_t start_mark;
2742+ yaml_mark_t end_mark;
2743+ yaml_string_t string = NULL_STRING;
2744+ yaml_string_t leading_break = NULL_STRING;
2745+ yaml_string_t trailing_breaks = NULL_STRING;
2749+ int leading_blank = 0;
2750+ int trailing_blank = 0;
2752+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
2753+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
2754+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
2756+ /* Eat the indicator '|' or '>'. */
2758+ start_mark = parser->mark;
2762+ /* Scan the additional block scalar indicators. */
2764+ if (!CACHE(parser, 1)) goto error;
2766+ /* Check for a chomping indicator. */
2768+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-'))
2770+ /* Set the chomping method and eat the indicator. */
2772+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2776+ /* Check for an indentation indicator. */
2778+ if (!CACHE(parser, 1)) goto error;
2780+ if (IS_DIGIT(parser->buffer))
2782+ /* Check that the intendation is greater than 0. */
2784+ if (CHECK(parser->buffer, '0')) {
2785+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2786+ start_mark, "found an intendation indicator equal to 0");
2790+ /* Get the intendation level and eat the indicator. */
2792+ increment = AS_DIGIT(parser->buffer);
2798+ /* Do the same as above, but in the opposite order. */
2800+ else if (IS_DIGIT(parser->buffer))
2802+ if (CHECK(parser->buffer, '0')) {
2803+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2804+ start_mark, "found an intendation indicator equal to 0");
2808+ increment = AS_DIGIT(parser->buffer);
2812+ if (!CACHE(parser, 1)) goto error;
2814+ if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) {
2815+ chomping = CHECK(parser->buffer, '+') ? +1 : -1;
2821+ /* Eat whitespaces and comments to the end of the line. */
2823+ if (!CACHE(parser, 1)) goto error;
2825+ while (IS_BLANK(parser->buffer)) {
2827+ if (!CACHE(parser, 1)) goto error;
2830+ if (CHECK(parser->buffer, '#')) {
2831+ while (!IS_BREAKZ(parser->buffer)) {
2833+ if (!CACHE(parser, 1)) goto error;
2837+ /* Check if we are at the end of the line. */
2839+ if (!IS_BREAKZ(parser->buffer)) {
2840+ yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2841+ start_mark, "did not find expected comment or line break");
2845+ /* Eat a line break. */
2847+ if (IS_BREAK(parser->buffer)) {
2848+ if (!CACHE(parser, 2)) goto error;
2852+ end_mark = parser->mark;
2854+ /* Set the intendation level if it was specified. */
2857+ indent = parser->indent >= 0 ? parser->indent+increment : increment;
2860+ /* Scan the leading line breaks and determine the indentation level if needed. */
2862+ if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks,
2863+ start_mark, &end_mark)) goto error;
2865+ /* Scan the block scalar content. */
2867+ if (!CACHE(parser, 1)) goto error;
2869+ while ((int)parser->mark.column == indent && !IS_Z(parser->buffer))
2872+ * We are at the beginning of a non-empty line.
2875+ /* Is it a trailing whitespace? */
2877+ trailing_blank = IS_BLANK(parser->buffer);
2879+ /* Check if we need to fold the leading line break. */
2881+ if (!literal && (*leading_break.start == '\n')
2882+ && !leading_blank && !trailing_blank)
2884+ /* Do we need to join the lines by space? */
2886+ if (*trailing_breaks.start == '\0') {
2887+ if (!STRING_EXTEND(parser, string)) goto error;
2888+ *(string.pointer ++) = ' ';
2891+ CLEAR(parser, leading_break);
2894+ if (!JOIN(parser, string, leading_break)) goto error;
2895+ CLEAR(parser, leading_break);
2898+ /* Append the remaining line breaks. */
2900+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2901+ CLEAR(parser, trailing_breaks);
2903+ /* Is it a leading whitespace? */
2905+ leading_blank = IS_BLANK(parser->buffer);
2907+ /* Consume the current line. */
2909+ while (!IS_BREAKZ(parser->buffer)) {
2910+ if (!READ(parser, string)) goto error;
2911+ if (!CACHE(parser, 1)) goto error;
2914+ /* Consume the line break. */
2916+ if (!CACHE(parser, 2)) goto error;
2918+ if (!READ_LINE(parser, leading_break)) goto error;
2920+ /* Eat the following intendation spaces and line breaks. */
2922+ if (!yaml_parser_scan_block_scalar_breaks(parser,
2923+ &indent, &trailing_breaks, start_mark, &end_mark)) goto error;
2926+ /* Chomp the tail. */
2928+ if (chomping != -1) {
2929+ if (!JOIN(parser, string, leading_break)) goto error;
2931+ if (chomping == 1) {
2932+ if (!JOIN(parser, string, trailing_breaks)) goto error;
2935+ /* Create a token. */
2937+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
2938+ literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE,
2939+ start_mark, end_mark);
2941+ STRING_DEL(parser, leading_break);
2942+ STRING_DEL(parser, trailing_breaks);
2947+ STRING_DEL(parser, string);
2948+ STRING_DEL(parser, leading_break);
2949+ STRING_DEL(parser, trailing_breaks);
2955+ * Scan intendation spaces and line breaks for a block scalar. Determine the
2956+ * intendation level if needed.
2960+yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser,
2961+ int *indent, yaml_string_t *breaks,
2962+ yaml_mark_t start_mark, yaml_mark_t *end_mark)
2964+ int max_indent = 0;
2966+ *end_mark = parser->mark;
2968+ /* Eat the intendation spaces and line breaks. */
2972+ /* Eat the intendation spaces. */
2974+ if (!CACHE(parser, 1)) return 0;
2976+ while ((!*indent || (int)parser->mark.column < *indent)
2977+ && IS_SPACE(parser->buffer)) {
2979+ if (!CACHE(parser, 1)) return 0;
2982+ if ((int)parser->mark.column > max_indent)
2983+ max_indent = (int)parser->mark.column;
2985+ /* Check for a tab character messing the intendation. */
2987+ if ((!*indent || (int)parser->mark.column < *indent)
2988+ && IS_TAB(parser->buffer)) {
2989+ return yaml_parser_set_scanner_error(parser, "while scanning a block scalar",
2990+ start_mark, "found a tab character where an intendation space is expected");
2993+ /* Have we found a non-empty line? */
2995+ if (!IS_BREAK(parser->buffer)) break;
2997+ /* Consume the line break. */
2999+ if (!CACHE(parser, 2)) return 0;
3000+ if (!READ_LINE(parser, *breaks)) return 0;
3001+ *end_mark = parser->mark;
3004+ /* Determine the indentation level if needed. */
3007+ *indent = max_indent;
3008+ if (*indent < parser->indent + 1)
3009+ *indent = parser->indent + 1;
3018+ * Scan a quoted scalar.
3022+yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token,
3025+ yaml_mark_t start_mark;
3026+ yaml_mark_t end_mark;
3027+ yaml_string_t string = NULL_STRING;
3028+ yaml_string_t leading_break = NULL_STRING;
3029+ yaml_string_t trailing_breaks = NULL_STRING;
3030+ yaml_string_t whitespaces = NULL_STRING;
3031+ int leading_blanks;
3033+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3034+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3035+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3036+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3038+ /* Eat the left quote. */
3040+ start_mark = parser->mark;
3044+ /* Consume the content of the quoted scalar. */
3048+ /* Check that there are no document indicators at the beginning of the line. */
3050+ if (!CACHE(parser, 4)) goto error;
3052+ if (parser->mark.column == 0 &&
3053+ ((CHECK_AT(parser->buffer, '-', 0) &&
3054+ CHECK_AT(parser->buffer, '-', 1) &&
3055+ CHECK_AT(parser->buffer, '-', 2)) ||
3056+ (CHECK_AT(parser->buffer, '.', 0) &&
3057+ CHECK_AT(parser->buffer, '.', 1) &&
3058+ CHECK_AT(parser->buffer, '.', 2))) &&
3059+ IS_BLANKZ_AT(parser->buffer, 3))
3061+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3062+ start_mark, "found unexpected document indicator");
3066+ /* Check for EOF. */
3068+ if (IS_Z(parser->buffer)) {
3069+ yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar",
3070+ start_mark, "found unexpected end of stream");
3074+ /* Consume non-blank characters. */
3076+ if (!CACHE(parser, 2)) goto error;
3078+ leading_blanks = 0;
3080+ while (!IS_BLANKZ(parser->buffer))
3082+ /* Check for an escaped single quote. */
3084+ if (single && CHECK_AT(parser->buffer, '\'', 0)
3085+ && CHECK_AT(parser->buffer, '\'', 1))
3087+ if (!STRING_EXTEND(parser, string)) goto error;
3088+ *(string.pointer++) = '\'';
3093+ /* Check for the right quote. */
3095+ else if (CHECK(parser->buffer, single ? '\'' : '"'))
3100+ /* Check for an escaped line break. */
3102+ else if (!single && CHECK(parser->buffer, '\\')
3103+ && IS_BREAK_AT(parser->buffer, 1))
3105+ if (!CACHE(parser, 3)) goto error;
3108+ leading_blanks = 1;
3112+ /* Check for an escape sequence. */
3114+ else if (!single && CHECK(parser->buffer, '\\'))
3116+ size_t code_length = 0;
3118+ if (!STRING_EXTEND(parser, string)) goto error;
3120+ /* Check the escape character. */
3122+ switch (parser->buffer.pointer[1])
3125+ *(string.pointer++) = '\0';
3129+ *(string.pointer++) = '\x07';
3133+ *(string.pointer++) = '\x08';
3138+ *(string.pointer++) = '\x09';
3142+ *(string.pointer++) = '\x0A';
3146+ *(string.pointer++) = '\x0B';
3150+ *(string.pointer++) = '\x0C';
3154+ *(string.pointer++) = '\x0D';
3158+ *(string.pointer++) = '\x1B';
3162+ *(string.pointer++) = '\x20';
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+ if (CHECK(parser->buffer, single ? '\'' : '"'))
3290+ /* Consume blank characters. */
3292+ if (!CACHE(parser, 1)) goto error;
3294+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3296+ if (IS_BLANK(parser->buffer))
3298+ /* Consume a space or a tab character. */
3300+ if (!leading_blanks) {
3301+ if (!READ(parser, whitespaces)) goto error;
3309+ if (!CACHE(parser, 2)) goto error;
3311+ /* Check if it is a first line break. */
3313+ if (!leading_blanks)
3315+ CLEAR(parser, whitespaces);
3316+ if (!READ_LINE(parser, leading_break)) goto error;
3317+ leading_blanks = 1;
3321+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3324+ if (!CACHE(parser, 1)) goto error;
3327+ /* Join the whitespaces or fold line breaks. */
3329+ if (leading_blanks)
3331+ /* Do we need to fold line breaks? */
3333+ if (leading_break.start[0] == '\n') {
3334+ if (trailing_breaks.start[0] == '\0') {
3335+ if (!STRING_EXTEND(parser, string)) goto error;
3336+ *(string.pointer++) = ' ';
3339+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3340+ CLEAR(parser, trailing_breaks);
3342+ CLEAR(parser, leading_break);
3345+ if (!JOIN(parser, string, leading_break)) goto error;
3346+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3347+ CLEAR(parser, leading_break);
3348+ CLEAR(parser, trailing_breaks);
3353+ if (!JOIN(parser, string, whitespaces)) goto error;
3354+ CLEAR(parser, whitespaces);
3358+ /* Eat the right quote. */
3362+ end_mark = parser->mark;
3364+ /* Create a token. */
3366+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3367+ single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE,
3368+ start_mark, end_mark);
3370+ STRING_DEL(parser, leading_break);
3371+ STRING_DEL(parser, trailing_breaks);
3372+ STRING_DEL(parser, whitespaces);
3377+ STRING_DEL(parser, string);
3378+ STRING_DEL(parser, leading_break);
3379+ STRING_DEL(parser, trailing_breaks);
3380+ STRING_DEL(parser, whitespaces);
3386+ * Scan a plain scalar.
3390+yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token)
3392+ yaml_mark_t start_mark;
3393+ yaml_mark_t end_mark;
3394+ yaml_string_t string = NULL_STRING;
3395+ yaml_string_t leading_break = NULL_STRING;
3396+ yaml_string_t trailing_breaks = NULL_STRING;
3397+ yaml_string_t whitespaces = NULL_STRING;
3398+ int leading_blanks = 0;
3399+ int indent = parser->indent+1;
3401+ if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error;
3402+ if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error;
3403+ if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error;
3404+ if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error;
3406+ start_mark = end_mark = parser->mark;
3408+ /* Consume the content of the plain scalar. */
3412+ /* Check for a document indicator. */
3414+ if (!CACHE(parser, 4)) goto error;
3416+ if (parser->mark.column == 0 &&
3417+ ((CHECK_AT(parser->buffer, '-', 0) &&
3418+ CHECK_AT(parser->buffer, '-', 1) &&
3419+ CHECK_AT(parser->buffer, '-', 2)) ||
3420+ (CHECK_AT(parser->buffer, '.', 0) &&
3421+ CHECK_AT(parser->buffer, '.', 1) &&
3422+ CHECK_AT(parser->buffer, '.', 2))) &&
3423+ IS_BLANKZ_AT(parser->buffer, 3)) break;
3425+ /* Check for a comment. */
3427+ if (CHECK(parser->buffer, '#'))
3430+ /* Consume non-blank characters. */
3432+ while (!IS_BLANKZ(parser->buffer))
3434+ /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */
3436+ if (parser->flow_level
3437+ && CHECK(parser->buffer, ':')
3438+ && !IS_BLANKZ_AT(parser->buffer, 1)) {
3439+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3440+ start_mark, "found unexpected ':'");
3444+ /* Check for indicators that may end a plain scalar. */
3446+ if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1))
3447+ || (parser->flow_level &&
3448+ (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':')
3449+ || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[')
3450+ || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{')
3451+ || CHECK(parser->buffer, '}'))))
3454+ /* Check if we need to join whitespaces and breaks. */
3456+ if (leading_blanks || whitespaces.start != whitespaces.pointer)
3458+ if (leading_blanks)
3460+ /* Do we need to fold line breaks? */
3462+ if (leading_break.start[0] == '\n') {
3463+ if (trailing_breaks.start[0] == '\0') {
3464+ if (!STRING_EXTEND(parser, string)) goto error;
3465+ *(string.pointer++) = ' ';
3468+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3469+ CLEAR(parser, trailing_breaks);
3471+ CLEAR(parser, leading_break);
3474+ if (!JOIN(parser, string, leading_break)) goto error;
3475+ if (!JOIN(parser, string, trailing_breaks)) goto error;
3476+ CLEAR(parser, leading_break);
3477+ CLEAR(parser, trailing_breaks);
3480+ leading_blanks = 0;
3484+ if (!JOIN(parser, string, whitespaces)) goto error;
3485+ CLEAR(parser, whitespaces);
3489+ /* Copy the character. */
3491+ if (!READ(parser, string)) goto error;
3493+ end_mark = parser->mark;
3495+ if (!CACHE(parser, 2)) goto error;
3498+ /* Is it the end? */
3500+ if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)))
3503+ /* Consume blank characters. */
3505+ if (!CACHE(parser, 1)) goto error;
3507+ while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))
3509+ if (IS_BLANK(parser->buffer))
3511+ /* Check for tab character that abuse intendation. */
3513+ if (leading_blanks && (int)parser->mark.column < indent
3514+ && IS_TAB(parser->buffer)) {
3515+ yaml_parser_set_scanner_error(parser, "while scanning a plain scalar",
3516+ start_mark, "found a tab character that violate intendation");
3520+ /* Consume a space or a tab character. */
3522+ if (!leading_blanks) {
3523+ if (!READ(parser, whitespaces)) goto error;
3531+ if (!CACHE(parser, 2)) goto error;
3533+ /* Check if it is a first line break. */
3535+ if (!leading_blanks)
3537+ CLEAR(parser, whitespaces);
3538+ if (!READ_LINE(parser, leading_break)) goto error;
3539+ leading_blanks = 1;
3543+ if (!READ_LINE(parser, trailing_breaks)) goto error;
3546+ if (!CACHE(parser, 1)) goto error;
3549+ /* Check intendation level. */
3551+ if (!parser->flow_level && (int)parser->mark.column < indent)
3555+ /* Create a token. */
3557+ SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start,
3558+ YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark);
3560+ /* Note that we change the 'simple_key_allowed' flag. */
3562+ if (leading_blanks) {
3563+ parser->simple_key_allowed = 1;
3566+ STRING_DEL(parser, leading_break);
3567+ STRING_DEL(parser, trailing_breaks);
3568+ STRING_DEL(parser, whitespaces);
3573+ STRING_DEL(parser, string);
3574+ STRING_DEL(parser, leading_break);
3575+ STRING_DEL(parser, trailing_breaks);
3576+ STRING_DEL(parser, whitespaces);