All tests pass.
diff --git a/api_c.go b/api_c.go index 3212d0b..46a303d 100644 --- a/api_c.go +++ b/api_c.go
@@ -68,6 +68,7 @@ //} func yaml_insert_token(parser *yaml_parser_t, pos int, token *yaml_token_t) { + //fmt.Println("yaml_insert_token", "pos:", pos, "typ:", token.typ, "head:", parser.tokens_head, "len:", len(parser.tokens)) // Check if we can move the queue at the beginning of the buffer. if parser.tokens_head > 0 && len(parser.tokens) == cap(parser.tokens) { if parser.tokens_head != len(parser.tokens) { @@ -76,12 +77,12 @@ parser.tokens = parser.tokens[:len(parser.tokens)-parser.tokens_head] parser.tokens_head = 0 } - parser.tokens = append(parser.tokens, yaml_token_t{}) + parser.tokens = append(parser.tokens, *token) if pos < 0 { return } copy(parser.tokens[parser.tokens_head+pos+1:], parser.tokens[parser.tokens_head+pos:]) - parser.tokens[pos] = *token + parser.tokens[parser.tokens_head+pos] = *token } // Create a new parser object.
diff --git a/decode_test.go b/decode_test.go index 83532f4..b341848 100644 --- a/decode_test.go +++ b/decode_test.go
@@ -67,13 +67,28 @@ {"~: null key", map[interface{}]string{nil: "null key"}}, {"empty:", map[string]*bool{"empty": nil}}, - // Sequence + // Flow sequence {"seq: [A,B]", map[string]interface{}{"seq": []interface{}{"A", "B"}}}, - {"seq: [A,B,C]", map[string][]string{"seq": []string{"A", "B", "C"}}}, + {"seq: [A,B,C,]", map[string][]string{"seq": []string{"A", "B", "C"}}}, {"seq: [A,1,C]", map[string][]string{"seq": []string{"A", "1", "C"}}}, {"seq: [A,1,C]", map[string][]int{"seq": []int{1}}}, {"seq: [A,1,C]", map[string]interface{}{"seq": []interface{}{"A", 1, "C"}}}, + // Block sequence + {"seq:\n - A\n - B", map[string]interface{}{"seq": []interface{}{"A", "B"}}}, + {"seq:\n - A\n - B\n - C", map[string][]string{"seq": []string{"A", "B", "C"}}}, + {"seq:\n - A\n - 1\n - C", map[string][]string{"seq": []string{"A", "1", "C"}}}, + {"seq:\n - A\n - 1\n - C", map[string][]int{"seq": []int{1}}}, + {"seq:\n - A\n - 1\n - C", map[string]interface{}{"seq": []interface{}{"A", 1, "C"}}}, + + // Literal block scalar + {"scalar: | # Comment\n\n literal\n\n \ttext\n\n", + map[string]string{"scalar": "\nliteral\n\n\ttext\n"}}, + + // Folded block scalar + {"scalar: > # Comment\n\n folded\n line\n \n next\n line\n * one\n * two\n\n last\n line\n\n", + map[string]string{"scalar": "\nfolded line\nnext line\n * one\n * two\n\nlast line\n"}}, + // Map inside interface with no type hints. {"a: {b: c}", map[string]interface{}{"a": map[interface{}]interface{}{"b": "c"}}},
diff --git a/loader.c b/loader.c deleted file mode 100644 index 9d3d912..0000000 --- a/loader.c +++ /dev/null
@@ -1,432 +0,0 @@ - -#include "yaml_private.h" - -/* - * API functions. - */ - -YAML_DECLARE(int) -yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document); - -/* - * Error handling. - */ - -static int -yaml_parser_set_composer_error(yaml_parser_t *parser, - const char *problem, yaml_mark_t problem_mark); - -static int -yaml_parser_set_composer_error_context(yaml_parser_t *parser, - const char *context, yaml_mark_t context_mark, - const char *problem, yaml_mark_t problem_mark); - - -/* - * Alias handling. - */ - -static int -yaml_parser_register_anchor(yaml_parser_t *parser, - int index, yaml_char_t *anchor); - -/* - * Clean up functions. - */ - -static void -yaml_parser_delete_aliases(yaml_parser_t *parser); - -/* - * Composer functions. - */ - -static int -yaml_parser_load_document(yaml_parser_t *parser, yaml_event_t *first_event); - -static int -yaml_parser_load_node(yaml_parser_t *parser, yaml_event_t *first_event); - -static int -yaml_parser_load_alias(yaml_parser_t *parser, yaml_event_t *first_event); - -static int -yaml_parser_load_scalar(yaml_parser_t *parser, yaml_event_t *first_event); - -static int -yaml_parser_load_sequence(yaml_parser_t *parser, yaml_event_t *first_event); - -static int -yaml_parser_load_mapping(yaml_parser_t *parser, yaml_event_t *first_event); - -/* - * Load the next document of the stream. - */ - -YAML_DECLARE(int) -yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document) -{ - yaml_event_t event; - - assert(parser); /* Non-NULL parser object is expected. */ - assert(document); /* Non-NULL document object is expected. */ - - memset(document, 0, sizeof(yaml_document_t)); - if (!STACK_INIT(parser, document->nodes, INITIAL_STACK_SIZE)) - goto error; - - if (!parser->stream_start_produced) { - if (!yaml_parser_parse(parser, &event)) goto error; - assert(event.type == YAML_STREAM_START_EVENT); - /* STREAM-START is expected. */ - } - - if (parser->stream_end_produced) { - return 1; - } - - if (!yaml_parser_parse(parser, &event)) goto error; - if (event.type == YAML_STREAM_END_EVENT) { - return 1; - } - - if (!STACK_INIT(parser, parser->aliases, INITIAL_STACK_SIZE)) - goto error; - - parser->document = document; - - if (!yaml_parser_load_document(parser, &event)) goto error; - - yaml_parser_delete_aliases(parser); - parser->document = NULL; - - return 1; - -error: - - yaml_parser_delete_aliases(parser); - yaml_document_delete(document); - parser->document = NULL; - - return 0; -} - -/* - * Set composer error. - */ - -static int -yaml_parser_set_composer_error(yaml_parser_t *parser, - const char *problem, yaml_mark_t problem_mark) -{ - parser->error = YAML_COMPOSER_ERROR; - parser->problem = problem; - parser->problem_mark = problem_mark; - - return 0; -} - -/* - * Set composer error with context. - */ - -static int -yaml_parser_set_composer_error_context(yaml_parser_t *parser, - const char *context, yaml_mark_t context_mark, - const char *problem, yaml_mark_t problem_mark) -{ - parser->error = YAML_COMPOSER_ERROR; - parser->context = context; - parser->context_mark = context_mark; - parser->problem = problem; - parser->problem_mark = problem_mark; - - return 0; -} - -/* - * Delete the stack of aliases. - */ - -static void -yaml_parser_delete_aliases(yaml_parser_t *parser) -{ - while (!STACK_EMPTY(parser, parser->aliases)) { - yaml_free(POP(parser, parser->aliases).anchor); - } - STACK_DEL(parser, parser->aliases); -} - -/* - * Compose a document object. - */ - -static int -yaml_parser_load_document(yaml_parser_t *parser, yaml_event_t *first_event) -{ - yaml_event_t event; - - assert(first_event->type == YAML_DOCUMENT_START_EVENT); - /* DOCUMENT-START is expected. */ - - parser->document->version_directive - = first_event->data.document_start.version_directive; - parser->document->tag_directives.start - = first_event->data.document_start.tag_directives.start; - parser->document->tag_directives.end - = first_event->data.document_start.tag_directives.end; - parser->document->start_implicit - = first_event->data.document_start.implicit; - parser->document->start_mark = first_event->start_mark; - - if (!yaml_parser_parse(parser, &event)) return 0; - - if (!yaml_parser_load_node(parser, &event)) return 0; - - if (!yaml_parser_parse(parser, &event)) return 0; - assert(event.type == YAML_DOCUMENT_END_EVENT); - /* DOCUMENT-END is expected. */ - - parser->document->end_implicit = event.data.document_end.implicit; - parser->document->end_mark = event.end_mark; - - return 1; -} - -/* - * Compose a node. - */ - -static int -yaml_parser_load_node(yaml_parser_t *parser, yaml_event_t *first_event) -{ - switch (first_event->type) { - case YAML_ALIAS_EVENT: - return yaml_parser_load_alias(parser, first_event); - case YAML_SCALAR_EVENT: - return yaml_parser_load_scalar(parser, first_event); - case YAML_SEQUENCE_START_EVENT: - return yaml_parser_load_sequence(parser, first_event); - case YAML_MAPPING_START_EVENT: - return yaml_parser_load_mapping(parser, first_event); - default: - assert(0); /* Could not happen. */ - return 0; - } - - return 0; -} - -/* - * Add an anchor. - */ - -static int -yaml_parser_register_anchor(yaml_parser_t *parser, - int index, yaml_char_t *anchor) -{ - yaml_alias_data_t data; - yaml_alias_data_t *alias_data; - - if (!anchor) return 1; - - data.anchor = anchor; - data.index = index; - data.mark = parser->document->nodes.start[index-1].start_mark; - - for (alias_data = parser->aliases.start; - alias_data != parser->aliases.top; alias_data ++) { - if (strcmp((char *)alias_data->anchor, (char *)anchor) == 0) { - yaml_free(anchor); - return yaml_parser_set_composer_error_context(parser, - "found duplicate anchor; first occurence", - alias_data->mark, "second occurence", data.mark); - } - } - - if (!PUSH(parser, parser->aliases, data)) { - yaml_free(anchor); - return 0; - } - - return 1; -} - -/* - * Compose a node corresponding to an alias. - */ - -static int -yaml_parser_load_alias(yaml_parser_t *parser, yaml_event_t *first_event) -{ - yaml_char_t *anchor = first_event->data.alias.anchor; - yaml_alias_data_t *alias_data; - - for (alias_data = parser->aliases.start; - alias_data != parser->aliases.top; alias_data ++) { - if (strcmp((char *)alias_data->anchor, (char *)anchor) == 0) { - yaml_free(anchor); - return alias_data->index; - } - } - - yaml_free(anchor); - return yaml_parser_set_composer_error(parser, "found undefined alias", - first_event->start_mark); -} - -/* - * Compose a scalar node. - */ - -static int -yaml_parser_load_scalar(yaml_parser_t *parser, yaml_event_t *first_event) -{ - yaml_node_t node; - int index; - yaml_char_t *tag = first_event->data.scalar.tag; - - if (!tag || strcmp((char *)tag, "!") == 0) { - yaml_free(tag); - tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_SCALAR_TAG); - if (!tag) goto error; - } - - SCALAR_NODE_INIT(node, tag, first_event->data.scalar.value, - first_event->data.scalar.length, first_event->data.scalar.style, - first_event->start_mark, first_event->end_mark); - - if (!PUSH(parser, parser->document->nodes, node)) goto error; - - index = parser->document->nodes.top - parser->document->nodes.start; - - if (!yaml_parser_register_anchor(parser, index, - first_event->data.scalar.anchor)) return 0; - - return index; - -error: - yaml_free(tag); - yaml_free(first_event->data.scalar.anchor); - yaml_free(first_event->data.scalar.value); - return 0; -} - -/* - * Compose a sequence node. - */ - -static int -yaml_parser_load_sequence(yaml_parser_t *parser, yaml_event_t *first_event) -{ - yaml_event_t event; - yaml_node_t node; - struct { - yaml_node_item_t *start; - yaml_node_item_t *end; - yaml_node_item_t *top; - } items = { NULL, NULL, NULL }; - int index, item_index; - yaml_char_t *tag = first_event->data.sequence_start.tag; - - if (!tag || strcmp((char *)tag, "!") == 0) { - yaml_free(tag); - tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_SEQUENCE_TAG); - if (!tag) goto error; - } - - if (!STACK_INIT(parser, items, INITIAL_STACK_SIZE)) goto error; - - SEQUENCE_NODE_INIT(node, tag, items.start, items.end, - first_event->data.sequence_start.style, - first_event->start_mark, first_event->end_mark); - - if (!PUSH(parser, parser->document->nodes, node)) goto error; - - index = parser->document->nodes.top - parser->document->nodes.start; - - if (!yaml_parser_register_anchor(parser, index, - first_event->data.sequence_start.anchor)) return 0; - - if (!yaml_parser_parse(parser, &event)) return 0; - - while (event.type != YAML_SEQUENCE_END_EVENT) { - item_index = yaml_parser_load_node(parser, &event); - if (!item_index) return 0; - if (!PUSH(parser, - parser->document->nodes.start[index-1].data.sequence.items, - item_index)) return 0; - if (!yaml_parser_parse(parser, &event)) return 0; - } - - parser->document->nodes.start[index-1].end_mark = event.end_mark; - - return index; - -error: - yaml_free(tag); - yaml_free(first_event->data.sequence_start.anchor); - return 0; -} - -/* - * Compose a mapping node. - */ - -static int -yaml_parser_load_mapping(yaml_parser_t *parser, yaml_event_t *first_event) -{ - yaml_event_t event; - yaml_node_t node; - struct { - yaml_node_pair_t *start; - yaml_node_pair_t *end; - yaml_node_pair_t *top; - } pairs = { NULL, NULL, NULL }; - int index; - yaml_node_pair_t pair; - yaml_char_t *tag = first_event->data.mapping_start.tag; - - if (!tag || strcmp((char *)tag, "!") == 0) { - yaml_free(tag); - tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_MAPPING_TAG); - if (!tag) goto error; - } - - if (!STACK_INIT(parser, pairs, INITIAL_STACK_SIZE)) goto error; - - MAPPING_NODE_INIT(node, tag, pairs.start, pairs.end, - first_event->data.mapping_start.style, - first_event->start_mark, first_event->end_mark); - - if (!PUSH(parser, parser->document->nodes, node)) goto error; - - index = parser->document->nodes.top - parser->document->nodes.start; - - if (!yaml_parser_register_anchor(parser, index, - first_event->data.mapping_start.anchor)) return 0; - - if (!yaml_parser_parse(parser, &event)) return 0; - - while (event.type != YAML_MAPPING_END_EVENT) { - pair.key = yaml_parser_load_node(parser, &event); - if (!pair.key) return 0; - if (!yaml_parser_parse(parser, &event)) return 0; - pair.value = yaml_parser_load_node(parser, &event); - if (!pair.value) return 0; - if (!PUSH(parser, - parser->document->nodes.start[index-1].data.mapping.pairs, - pair)) return 0; - if (!yaml_parser_parse(parser, &event)) return 0; - } - - parser->document->nodes.start[index-1].end_mark = event.end_mark; - - return index; - -error: - yaml_free(tag); - yaml_free(first_event->data.mapping_start.anchor); - return 0; -} -
diff --git a/parser.c b/parser.c deleted file mode 100644 index eb2a2c7..0000000 --- a/parser.c +++ /dev/null
@@ -1,1374 +0,0 @@ - -/* - * The parser implements the following grammar: - * - * stream ::= STREAM-START implicit_document? explicit_document* STREAM-END - * implicit_document ::= block_node DOCUMENT-END* - * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* - * block_node_or_indentless_sequence ::= - * ALIAS - * | properties (block_content | indentless_block_sequence)? - * | block_content - * | indentless_block_sequence - * block_node ::= ALIAS - * | properties block_content? - * | block_content - * flow_node ::= ALIAS - * | properties flow_content? - * | flow_content - * properties ::= TAG ANCHOR? | ANCHOR TAG? - * block_content ::= block_collection | flow_collection | SCALAR - * flow_content ::= flow_collection | SCALAR - * block_collection ::= block_sequence | block_mapping - * flow_collection ::= flow_sequence | flow_mapping - * block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END - * indentless_sequence ::= (BLOCK-ENTRY block_node?)+ - * block_mapping ::= BLOCK-MAPPING_START - * ((KEY block_node_or_indentless_sequence?)? - * (VALUE block_node_or_indentless_sequence?)?)* - * BLOCK-END - * flow_sequence ::= FLOW-SEQUENCE-START - * (flow_sequence_entry FLOW-ENTRY)* - * flow_sequence_entry? - * FLOW-SEQUENCE-END - * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * flow_mapping ::= FLOW-MAPPING-START - * (flow_mapping_entry FLOW-ENTRY)* - * flow_mapping_entry? - * FLOW-MAPPING-END - * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - */ - -#include "yaml_private.h" - -/* - * Peek the next token in the token queue. - */ - -#define PEEK_TOKEN(parser) \ - ((parser->token_available || yaml_parser_fetch_more_tokens(parser)) ? \ - parser->tokens.head : NULL) - -/* - * Remove the next token from the queue (must be called after PEEK_TOKEN). - */ - -#define SKIP_TOKEN(parser) \ - (parser->token_available = 0, \ - parser->tokens_parsed ++, \ - parser->stream_end_produced = \ - (parser->tokens.head->type == YAML_STREAM_END_TOKEN), \ - parser->tokens.head ++) - -/* - * Public API declarations. - */ - -YAML_DECLARE(int) -yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event); - -/* - * Error handling. - */ - -static int -yaml_parser_set_parser_error(yaml_parser_t *parser, - const char *problem, yaml_mark_t problem_mark); - -static int -yaml_parser_set_parser_error_context(yaml_parser_t *parser, - const char *context, yaml_mark_t context_mark, - const char *problem, yaml_mark_t problem_mark); - -/* - * State functions. - */ - -static int -yaml_parser_state_machine(yaml_parser_t *parser, yaml_event_t *event); - -static int -yaml_parser_parse_stream_start(yaml_parser_t *parser, yaml_event_t *event); - -static int -yaml_parser_parse_document_start(yaml_parser_t *parser, yaml_event_t *event, - int implicit); - -static int -yaml_parser_parse_document_content(yaml_parser_t *parser, yaml_event_t *event); - -static int -yaml_parser_parse_document_end(yaml_parser_t *parser, yaml_event_t *event); - -static int -yaml_parser_parse_node(yaml_parser_t *parser, yaml_event_t *event, - int block, int indentless_sequence); - -static int -yaml_parser_parse_block_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event, int first); - -static int -yaml_parser_parse_indentless_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event); - -static int -yaml_parser_parse_block_mapping_key(yaml_parser_t *parser, - yaml_event_t *event, int first); - -static int -yaml_parser_parse_block_mapping_value(yaml_parser_t *parser, - yaml_event_t *event); - -static int -yaml_parser_parse_flow_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event, int first); - -static int -yaml_parser_parse_flow_sequence_entry_mapping_key(yaml_parser_t *parser, - yaml_event_t *event); - -static int -yaml_parser_parse_flow_sequence_entry_mapping_value(yaml_parser_t *parser, - yaml_event_t *event); - -static int -yaml_parser_parse_flow_sequence_entry_mapping_end(yaml_parser_t *parser, - yaml_event_t *event); - -static int -yaml_parser_parse_flow_mapping_key(yaml_parser_t *parser, - yaml_event_t *event, int first); - -static int -yaml_parser_parse_flow_mapping_value(yaml_parser_t *parser, - yaml_event_t *event, int empty); - -/* - * Utility functions. - */ - -static int -yaml_parser_process_empty_scalar(yaml_parser_t *parser, - yaml_event_t *event, yaml_mark_t mark); - -static int -yaml_parser_process_directives(yaml_parser_t *parser, - yaml_version_directive_t **version_directive_ref, - yaml_tag_directive_t **tag_directives_start_ref, - yaml_tag_directive_t **tag_directives_end_ref); - -static int -yaml_parser_append_tag_directive(yaml_parser_t *parser, - yaml_tag_directive_t value, int allow_duplicates, yaml_mark_t mark); - -/* - * Get the next event. - */ - -YAML_DECLARE(int) -yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event) -{ - assert(parser); /* Non-NULL parser object is expected. */ - assert(event); /* Non-NULL event object is expected. */ - - /* Erase the event object. */ - - memset(event, 0, sizeof(yaml_event_t)); - - /* No events after the end of the stream or error. */ - - if (parser->stream_end_produced || parser->error || - parser->state == YAML_PARSE_END_STATE) { - return 1; - } - - /* Generate the next event. */ - - return yaml_parser_state_machine(parser, event); -} - -/* - * Set parser error. - */ - -static int -yaml_parser_set_parser_error(yaml_parser_t *parser, - const char *problem, yaml_mark_t problem_mark) -{ - parser->error = YAML_PARSER_ERROR; - parser->problem = problem; - parser->problem_mark = problem_mark; - - return 0; -} - -static int -yaml_parser_set_parser_error_context(yaml_parser_t *parser, - const char *context, yaml_mark_t context_mark, - const char *problem, yaml_mark_t problem_mark) -{ - parser->error = YAML_PARSER_ERROR; - parser->context = context; - parser->context_mark = context_mark; - parser->problem = problem; - parser->problem_mark = problem_mark; - - return 0; -} - - -/* - * State dispatcher. - */ - -static int -yaml_parser_state_machine(yaml_parser_t *parser, yaml_event_t *event) -{ - switch (parser->state) - { - case YAML_PARSE_STREAM_START_STATE: - return yaml_parser_parse_stream_start(parser, event); - - case YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE: - return yaml_parser_parse_document_start(parser, event, 1); - - case YAML_PARSE_DOCUMENT_START_STATE: - return yaml_parser_parse_document_start(parser, event, 0); - - case YAML_PARSE_DOCUMENT_CONTENT_STATE: - return yaml_parser_parse_document_content(parser, event); - - case YAML_PARSE_DOCUMENT_END_STATE: - return yaml_parser_parse_document_end(parser, event); - - case YAML_PARSE_BLOCK_NODE_STATE: - return yaml_parser_parse_node(parser, event, 1, 0); - - case YAML_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE: - return yaml_parser_parse_node(parser, event, 1, 1); - - case YAML_PARSE_FLOW_NODE_STATE: - return yaml_parser_parse_node(parser, event, 0, 0); - - case YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE: - return yaml_parser_parse_block_sequence_entry(parser, event, 1); - - case YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE: - return yaml_parser_parse_block_sequence_entry(parser, event, 0); - - case YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE: - return yaml_parser_parse_indentless_sequence_entry(parser, event); - - case YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE: - return yaml_parser_parse_block_mapping_key(parser, event, 1); - - case YAML_PARSE_BLOCK_MAPPING_KEY_STATE: - return yaml_parser_parse_block_mapping_key(parser, event, 0); - - case YAML_PARSE_BLOCK_MAPPING_VALUE_STATE: - return yaml_parser_parse_block_mapping_value(parser, event); - - case YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE: - return yaml_parser_parse_flow_sequence_entry(parser, event, 1); - - case YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE: - return yaml_parser_parse_flow_sequence_entry(parser, event, 0); - - case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE: - return yaml_parser_parse_flow_sequence_entry_mapping_key(parser, event); - - case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE: - return yaml_parser_parse_flow_sequence_entry_mapping_value(parser, event); - - case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE: - return yaml_parser_parse_flow_sequence_entry_mapping_end(parser, event); - - case YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE: - return yaml_parser_parse_flow_mapping_key(parser, event, 1); - - case YAML_PARSE_FLOW_MAPPING_KEY_STATE: - return yaml_parser_parse_flow_mapping_key(parser, event, 0); - - case YAML_PARSE_FLOW_MAPPING_VALUE_STATE: - return yaml_parser_parse_flow_mapping_value(parser, event, 0); - - case YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE: - return yaml_parser_parse_flow_mapping_value(parser, event, 1); - - default: - assert(1); /* Invalid state. */ - } - - return 0; -} - -/* - * Parse the production: - * stream ::= STREAM-START implicit_document? explicit_document* STREAM-END - * ************ - */ - -static int -yaml_parser_parse_stream_start(yaml_parser_t *parser, yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type != YAML_STREAM_START_TOKEN) { - return yaml_parser_set_parser_error(parser, - "did not find expected <stream-start>", token->start_mark); - } - - parser->state = YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE; - STREAM_START_EVENT_INIT(*event, token->data.stream_start.encoding, - token->start_mark, token->start_mark); - SKIP_TOKEN(parser); - - return 1; -} - -/* - * Parse the productions: - * implicit_document ::= block_node DOCUMENT-END* - * * - * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* - * ************************* - */ - -static int -yaml_parser_parse_document_start(yaml_parser_t *parser, yaml_event_t *event, - int implicit) -{ - yaml_token_t *token; - yaml_version_directive_t *version_directive = NULL; - struct { - yaml_tag_directive_t *start; - yaml_tag_directive_t *end; - } tag_directives = { NULL, NULL }; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - /* Parse extra document end indicators. */ - - if (!implicit) - { - while (token->type == YAML_DOCUMENT_END_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - } - } - - /* Parse an implicit document. */ - - if (implicit && token->type != YAML_VERSION_DIRECTIVE_TOKEN && - token->type != YAML_TAG_DIRECTIVE_TOKEN && - token->type != YAML_DOCUMENT_START_TOKEN && - token->type != YAML_STREAM_END_TOKEN) - { - if (!yaml_parser_process_directives(parser, NULL, NULL, NULL)) - return 0; - if (!PUSH(parser, parser->states, YAML_PARSE_DOCUMENT_END_STATE)) - return 0; - parser->state = YAML_PARSE_BLOCK_NODE_STATE; - DOCUMENT_START_EVENT_INIT(*event, NULL, NULL, NULL, 1, - token->start_mark, token->start_mark); - return 1; - } - - /* Parse an explicit document. */ - - else if (token->type != YAML_STREAM_END_TOKEN) - { - yaml_mark_t start_mark, end_mark; - start_mark = token->start_mark; - if (!yaml_parser_process_directives(parser, &version_directive, - &tag_directives.start, &tag_directives.end)) - return 0; - token = PEEK_TOKEN(parser); - if (!token) goto error; - if (token->type != YAML_DOCUMENT_START_TOKEN) { - yaml_parser_set_parser_error(parser, - "did not find expected <document start>", token->start_mark); - goto error; - } - if (!PUSH(parser, parser->states, YAML_PARSE_DOCUMENT_END_STATE)) - goto error; - parser->state = YAML_PARSE_DOCUMENT_CONTENT_STATE; - end_mark = token->end_mark; - DOCUMENT_START_EVENT_INIT(*event, version_directive, - tag_directives.start, tag_directives.end, 0, - start_mark, end_mark); - SKIP_TOKEN(parser); - version_directive = NULL; - tag_directives.start = tag_directives.end = NULL; - return 1; - } - - /* Parse the stream end. */ - - else - { - parser->state = YAML_PARSE_END_STATE; - STREAM_END_EVENT_INIT(*event, token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; - } - -error: - yaml_free(version_directive); - while (tag_directives.start != tag_directives.end) { - yaml_free(tag_directives.end[-1].handle); - yaml_free(tag_directives.end[-1].prefix); - tag_directives.end --; - } - yaml_free(tag_directives.start); - return 0; -} - -/* - * Parse the productions: - * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* - * *********** - */ - -static int -yaml_parser_parse_document_content(yaml_parser_t *parser, yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_VERSION_DIRECTIVE_TOKEN || - token->type == YAML_TAG_DIRECTIVE_TOKEN || - token->type == YAML_DOCUMENT_START_TOKEN || - token->type == YAML_DOCUMENT_END_TOKEN || - token->type == YAML_STREAM_END_TOKEN) { - parser->state = POP(parser, parser->states); - return yaml_parser_process_empty_scalar(parser, event, - token->start_mark); - } - else { - return yaml_parser_parse_node(parser, event, 1, 0); - } -} - -/* - * Parse the productions: - * implicit_document ::= block_node DOCUMENT-END* - * ************* - * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* - * ************* - */ - -static int -yaml_parser_parse_document_end(yaml_parser_t *parser, yaml_event_t *event) -{ - yaml_token_t *token; - yaml_mark_t start_mark, end_mark; - int implicit = 1; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - start_mark = end_mark = token->start_mark; - - if (token->type == YAML_DOCUMENT_END_TOKEN) { - end_mark = token->end_mark; - SKIP_TOKEN(parser); - implicit = 0; - } - - while (!STACK_EMPTY(parser, parser->tag_directives)) { - yaml_tag_directive_t tag_directive = POP(parser, parser->tag_directives); - yaml_free(tag_directive.handle); - yaml_free(tag_directive.prefix); - } - - parser->state = YAML_PARSE_DOCUMENT_START_STATE; - DOCUMENT_END_EVENT_INIT(*event, implicit, start_mark, end_mark); - - return 1; -} - -/* - * Parse the productions: - * block_node_or_indentless_sequence ::= - * ALIAS - * ***** - * | properties (block_content | indentless_block_sequence)? - * ********** * - * | block_content | indentless_block_sequence - * * - * block_node ::= ALIAS - * ***** - * | properties block_content? - * ********** * - * | block_content - * * - * flow_node ::= ALIAS - * ***** - * | properties flow_content? - * ********** * - * | flow_content - * * - * properties ::= TAG ANCHOR? | ANCHOR TAG? - * ************************* - * block_content ::= block_collection | flow_collection | SCALAR - * ****** - * flow_content ::= flow_collection | SCALAR - * ****** - */ - -static int -yaml_parser_parse_node(yaml_parser_t *parser, yaml_event_t *event, - int block, int indentless_sequence) -{ - yaml_token_t *token; - yaml_char_t *anchor = NULL; - yaml_char_t *tag_handle = NULL; - yaml_char_t *tag_suffix = NULL; - yaml_char_t *tag = NULL; - yaml_mark_t start_mark, end_mark, tag_mark; - int implicit; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_ALIAS_TOKEN) - { - parser->state = POP(parser, parser->states); - ALIAS_EVENT_INIT(*event, token->data.alias.value, - token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; - } - - else - { - start_mark = end_mark = token->start_mark; - - if (token->type == YAML_ANCHOR_TOKEN) - { - anchor = token->data.anchor.value; - start_mark = token->start_mark; - end_mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) goto error; - if (token->type == YAML_TAG_TOKEN) - { - tag_handle = token->data.tag.handle; - tag_suffix = token->data.tag.suffix; - tag_mark = token->start_mark; - end_mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) goto error; - } - } - else if (token->type == YAML_TAG_TOKEN) - { - tag_handle = token->data.tag.handle; - tag_suffix = token->data.tag.suffix; - start_mark = tag_mark = token->start_mark; - end_mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) goto error; - if (token->type == YAML_ANCHOR_TOKEN) - { - anchor = token->data.anchor.value; - end_mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) goto error; - } - } - - if (tag_handle) { - if (!*tag_handle) { - tag = tag_suffix; - yaml_free(tag_handle); - tag_handle = tag_suffix = NULL; - } - else { - yaml_tag_directive_t *tag_directive; - for (tag_directive = parser->tag_directives.start; - tag_directive != parser->tag_directives.top; - tag_directive ++) { - if (strcmp((char *)tag_directive->handle, (char *)tag_handle) == 0) { - size_t prefix_len = strlen((char *)tag_directive->prefix); - size_t suffix_len = strlen((char *)tag_suffix); - tag = yaml_malloc(prefix_len+suffix_len+1); - if (!tag) { - parser->error = YAML_MEMORY_ERROR; - goto error; - } - memcpy(tag, tag_directive->prefix, prefix_len); - memcpy(tag+prefix_len, tag_suffix, suffix_len); - tag[prefix_len+suffix_len] = '\0'; - yaml_free(tag_handle); - yaml_free(tag_suffix); - tag_handle = tag_suffix = NULL; - break; - } - } - if (!tag) { - yaml_parser_set_parser_error_context(parser, - "while parsing a node", start_mark, - "found undefined tag handle", tag_mark); - goto error; - } - } - } - - implicit = (!tag || !*tag); - if (indentless_sequence && token->type == YAML_BLOCK_ENTRY_TOKEN) { - end_mark = token->end_mark; - parser->state = YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE; - SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, - YAML_BLOCK_SEQUENCE_STYLE, start_mark, end_mark); - return 1; - } - else { - if (token->type == YAML_SCALAR_TOKEN) { - int plain_implicit = 0; - int quoted_implicit = 0; - end_mark = token->end_mark; - if ((token->data.scalar.style == YAML_PLAIN_SCALAR_STYLE && !tag) - || (tag && strcmp((char *)tag, "!") == 0)) { - plain_implicit = 1; - } - else if (!tag) { - quoted_implicit = 1; - } - parser->state = POP(parser, parser->states); - SCALAR_EVENT_INIT(*event, anchor, tag, - token->data.scalar.value, token->data.scalar.length, - plain_implicit, quoted_implicit, - token->data.scalar.style, start_mark, end_mark); - SKIP_TOKEN(parser); - return 1; - } - else if (token->type == YAML_FLOW_SEQUENCE_START_TOKEN) { - end_mark = token->end_mark; - parser->state = YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE; - SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, - YAML_FLOW_SEQUENCE_STYLE, start_mark, end_mark); - return 1; - } - else if (token->type == YAML_FLOW_MAPPING_START_TOKEN) { - end_mark = token->end_mark; - parser->state = YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE; - MAPPING_START_EVENT_INIT(*event, anchor, tag, implicit, - YAML_FLOW_MAPPING_STYLE, start_mark, end_mark); - return 1; - } - else if (block && token->type == YAML_BLOCK_SEQUENCE_START_TOKEN) { - end_mark = token->end_mark; - parser->state = YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE; - SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, - YAML_BLOCK_SEQUENCE_STYLE, start_mark, end_mark); - return 1; - } - else if (block && token->type == YAML_BLOCK_MAPPING_START_TOKEN) { - end_mark = token->end_mark; - parser->state = YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE; - MAPPING_START_EVENT_INIT(*event, anchor, tag, implicit, - YAML_BLOCK_MAPPING_STYLE, start_mark, end_mark); - return 1; - } - else if (anchor || tag) { - yaml_char_t *value = yaml_malloc(1); - if (!value) { - parser->error = YAML_MEMORY_ERROR; - goto error; - } - value[0] = '\0'; - parser->state = POP(parser, parser->states); - SCALAR_EVENT_INIT(*event, anchor, tag, value, 0, - implicit, 0, YAML_PLAIN_SCALAR_STYLE, - start_mark, end_mark); - return 1; - } - else { - yaml_parser_set_parser_error_context(parser, - (block ? "while parsing a block node" - : "while parsing a flow node"), start_mark, - "did not find expected node content", token->start_mark); - goto error; - } - } - } - -error: - yaml_free(anchor); - yaml_free(tag_handle); - yaml_free(tag_suffix); - yaml_free(tag); - - return 0; -} - -/* - * Parse the productions: - * block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END - * ******************** *********** * ********* - */ - -static int -yaml_parser_parse_block_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event, int first) -{ - yaml_token_t *token; - - if (first) { - token = PEEK_TOKEN(parser); - if (!PUSH(parser, parser->marks, token->start_mark)) - return 0; - SKIP_TOKEN(parser); - } - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_BLOCK_ENTRY_TOKEN) - { - yaml_mark_t mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_BLOCK_ENTRY_TOKEN && - token->type != YAML_BLOCK_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 1, 0); - } - else { - parser->state = YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE; - return yaml_parser_process_empty_scalar(parser, event, mark); - } - } - - else if (token->type == YAML_BLOCK_END_TOKEN) - { - yaml_mark_t dummy_mark; /* Used to eliminate a compiler warning. */ - parser->state = POP(parser, parser->states); - dummy_mark = POP(parser, parser->marks); - SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; - } - - else - { - return yaml_parser_set_parser_error_context(parser, - "while parsing a block collection", POP(parser, parser->marks), - "did not find expected '-' indicator", token->start_mark); - } -} - -/* - * Parse the productions: - * indentless_sequence ::= (BLOCK-ENTRY block_node?)+ - * *********** * - */ - -static int -yaml_parser_parse_indentless_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_BLOCK_ENTRY_TOKEN) - { - yaml_mark_t mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_BLOCK_ENTRY_TOKEN && - token->type != YAML_KEY_TOKEN && - token->type != YAML_VALUE_TOKEN && - token->type != YAML_BLOCK_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 1, 0); - } - else { - parser->state = YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE; - return yaml_parser_process_empty_scalar(parser, event, mark); - } - } - - else - { - parser->state = POP(parser, parser->states); - SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->start_mark); - return 1; - } -} - -/* - * Parse the productions: - * block_mapping ::= BLOCK-MAPPING_START - * ******************* - * ((KEY block_node_or_indentless_sequence?)? - * *** * - * (VALUE block_node_or_indentless_sequence?)?)* - * - * BLOCK-END - * ********* - */ - -static int -yaml_parser_parse_block_mapping_key(yaml_parser_t *parser, - yaml_event_t *event, int first) -{ - yaml_token_t *token; - - if (first) { - token = PEEK_TOKEN(parser); - if (!PUSH(parser, parser->marks, token->start_mark)) - return 0; - SKIP_TOKEN(parser); - } - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_KEY_TOKEN) - { - yaml_mark_t mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_KEY_TOKEN && - token->type != YAML_VALUE_TOKEN && - token->type != YAML_BLOCK_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_BLOCK_MAPPING_VALUE_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 1, 1); - } - else { - parser->state = YAML_PARSE_BLOCK_MAPPING_VALUE_STATE; - return yaml_parser_process_empty_scalar(parser, event, mark); - } - } - - else if (token->type == YAML_BLOCK_END_TOKEN) - { - yaml_mark_t dummy_mark; /* Used to eliminate a compiler warning. */ - parser->state = POP(parser, parser->states); - dummy_mark = POP(parser, parser->marks); - MAPPING_END_EVENT_INIT(*event, token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; - } - - else - { - return yaml_parser_set_parser_error_context(parser, - "while parsing a block mapping", POP(parser, parser->marks), - "did not find expected key", token->start_mark); - } -} - -/* - * Parse the productions: - * block_mapping ::= BLOCK-MAPPING_START - * - * ((KEY block_node_or_indentless_sequence?)? - * - * (VALUE block_node_or_indentless_sequence?)?)* - * ***** * - * BLOCK-END - * - */ - -static int -yaml_parser_parse_block_mapping_value(yaml_parser_t *parser, - yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_VALUE_TOKEN) - { - yaml_mark_t mark = token->end_mark; - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_KEY_TOKEN && - token->type != YAML_VALUE_TOKEN && - token->type != YAML_BLOCK_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_BLOCK_MAPPING_KEY_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 1, 1); - } - else { - parser->state = YAML_PARSE_BLOCK_MAPPING_KEY_STATE; - return yaml_parser_process_empty_scalar(parser, event, mark); - } - } - - else - { - parser->state = YAML_PARSE_BLOCK_MAPPING_KEY_STATE; - return yaml_parser_process_empty_scalar(parser, event, token->start_mark); - } -} - -/* - * Parse the productions: - * flow_sequence ::= FLOW-SEQUENCE-START - * ******************* - * (flow_sequence_entry FLOW-ENTRY)* - * * ********** - * flow_sequence_entry? - * * - * FLOW-SEQUENCE-END - * ***************** - * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * * - */ - -static int -yaml_parser_parse_flow_sequence_entry(yaml_parser_t *parser, - yaml_event_t *event, int first) -{ - yaml_token_t *token; - yaml_mark_t dummy_mark; /* Used to eliminate a compiler warning. */ - - if (first) { - token = PEEK_TOKEN(parser); - if (!PUSH(parser, parser->marks, token->start_mark)) - return 0; - SKIP_TOKEN(parser); - } - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type != YAML_FLOW_SEQUENCE_END_TOKEN) - { - if (!first) { - if (token->type == YAML_FLOW_ENTRY_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - } - else { - return yaml_parser_set_parser_error_context(parser, - "while parsing a flow sequence", POP(parser, parser->marks), - "did not find expected ',' or ']'", token->start_mark); - } - } - - if (token->type == YAML_KEY_TOKEN) { - parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE; - MAPPING_START_EVENT_INIT(*event, NULL, NULL, - 1, YAML_FLOW_MAPPING_STYLE, - token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; - } - - else if (token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - } - - parser->state = POP(parser, parser->states); - dummy_mark = POP(parser, parser->marks); - SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; -} - -/* - * Parse the productions: - * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * *** * - */ - -static int -yaml_parser_parse_flow_sequence_entry_mapping_key(yaml_parser_t *parser, - yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type != YAML_VALUE_TOKEN && token->type != YAML_FLOW_ENTRY_TOKEN - && token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - else { - yaml_mark_t mark = token->end_mark; - SKIP_TOKEN(parser); - parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE; - return yaml_parser_process_empty_scalar(parser, event, mark); - } -} - -/* - * Parse the productions: - * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * ***** * - */ - -static int -yaml_parser_parse_flow_sequence_entry_mapping_value(yaml_parser_t *parser, - yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type == YAML_VALUE_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_FLOW_ENTRY_TOKEN - && token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - } - parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE; - return yaml_parser_process_empty_scalar(parser, event, token->start_mark); -} - -/* - * Parse the productions: - * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * * - */ - -static int -yaml_parser_parse_flow_sequence_entry_mapping_end(yaml_parser_t *parser, - yaml_event_t *event) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE; - - MAPPING_END_EVENT_INIT(*event, token->start_mark, token->start_mark); - return 1; -} - -/* - * Parse the productions: - * flow_mapping ::= FLOW-MAPPING-START - * ****************** - * (flow_mapping_entry FLOW-ENTRY)* - * * ********** - * flow_mapping_entry? - * ****************** - * FLOW-MAPPING-END - * **************** - * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * * *** * - */ - -static int -yaml_parser_parse_flow_mapping_key(yaml_parser_t *parser, - yaml_event_t *event, int first) -{ - yaml_token_t *token; - yaml_mark_t dummy_mark; /* Used to eliminate a compiler warning. */ - - if (first) { - token = PEEK_TOKEN(parser); - if (!PUSH(parser, parser->marks, token->start_mark)) - return 0; - SKIP_TOKEN(parser); - } - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (token->type != YAML_FLOW_MAPPING_END_TOKEN) - { - if (!first) { - if (token->type == YAML_FLOW_ENTRY_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - } - else { - return yaml_parser_set_parser_error_context(parser, - "while parsing a flow mapping", POP(parser, parser->marks), - "did not find expected ',' or '}'", token->start_mark); - } - } - - if (token->type == YAML_KEY_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_VALUE_TOKEN - && token->type != YAML_FLOW_ENTRY_TOKEN - && token->type != YAML_FLOW_MAPPING_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_MAPPING_VALUE_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - else { - parser->state = YAML_PARSE_FLOW_MAPPING_VALUE_STATE; - return yaml_parser_process_empty_scalar(parser, event, - token->start_mark); - } - } - else if (token->type != YAML_FLOW_MAPPING_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - } - - parser->state = POP(parser, parser->states); - dummy_mark = POP(parser, parser->marks); - MAPPING_END_EVENT_INIT(*event, token->start_mark, token->end_mark); - SKIP_TOKEN(parser); - return 1; -} - -/* - * Parse the productions: - * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? - * * ***** * - */ - -static int -yaml_parser_parse_flow_mapping_value(yaml_parser_t *parser, - yaml_event_t *event, int empty) -{ - yaml_token_t *token; - - token = PEEK_TOKEN(parser); - if (!token) return 0; - - if (empty) { - parser->state = YAML_PARSE_FLOW_MAPPING_KEY_STATE; - return yaml_parser_process_empty_scalar(parser, event, - token->start_mark); - } - - if (token->type == YAML_VALUE_TOKEN) { - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) return 0; - if (token->type != YAML_FLOW_ENTRY_TOKEN - && token->type != YAML_FLOW_MAPPING_END_TOKEN) { - if (!PUSH(parser, parser->states, - YAML_PARSE_FLOW_MAPPING_KEY_STATE)) - return 0; - return yaml_parser_parse_node(parser, event, 0, 0); - } - } - - parser->state = YAML_PARSE_FLOW_MAPPING_KEY_STATE; - return yaml_parser_process_empty_scalar(parser, event, token->start_mark); -} - -/* - * Generate an empty scalar event. - */ - -static int -yaml_parser_process_empty_scalar(yaml_parser_t *parser, yaml_event_t *event, - yaml_mark_t mark) -{ - yaml_char_t *value; - - value = yaml_malloc(1); - if (!value) { - parser->error = YAML_MEMORY_ERROR; - return 0; - } - value[0] = '\0'; - - SCALAR_EVENT_INIT(*event, NULL, NULL, value, 0, - 1, 0, YAML_PLAIN_SCALAR_STYLE, mark, mark); - - return 1; -} - -/* - * Parse directives. - */ - -static int -yaml_parser_process_directives(yaml_parser_t *parser, - yaml_version_directive_t **version_directive_ref, - yaml_tag_directive_t **tag_directives_start_ref, - yaml_tag_directive_t **tag_directives_end_ref) -{ - yaml_tag_directive_t default_tag_directives[] = { - {(yaml_char_t *)"!", (yaml_char_t *)"!"}, - {(yaml_char_t *)"!!", (yaml_char_t *)"tag:yaml.org,2002:"}, - {NULL, NULL} - }; - yaml_tag_directive_t *default_tag_directive; - yaml_version_directive_t *version_directive = NULL; - struct { - yaml_tag_directive_t *start; - yaml_tag_directive_t *end; - yaml_tag_directive_t *top; - } tag_directives = { NULL, NULL, NULL }; - yaml_token_t *token; - - if (!STACK_INIT(parser, tag_directives, INITIAL_STACK_SIZE)) - goto error; - - token = PEEK_TOKEN(parser); - if (!token) goto error; - - while (token->type == YAML_VERSION_DIRECTIVE_TOKEN || - token->type == YAML_TAG_DIRECTIVE_TOKEN) - { - if (token->type == YAML_VERSION_DIRECTIVE_TOKEN) { - if (version_directive) { - yaml_parser_set_parser_error(parser, - "found duplicate %YAML directive", token->start_mark); - goto error; - } - if (token->data.version_directive.major != 1 - || token->data.version_directive.minor != 1) { - yaml_parser_set_parser_error(parser, - "found incompatible YAML document", token->start_mark); - goto error; - } - version_directive = yaml_malloc(sizeof(yaml_version_directive_t)); - if (!version_directive) { - parser->error = YAML_MEMORY_ERROR; - goto error; - } - version_directive->major = token->data.version_directive.major; - version_directive->minor = token->data.version_directive.minor; - } - - else if (token->type == YAML_TAG_DIRECTIVE_TOKEN) { - yaml_tag_directive_t value; - value.handle = token->data.tag_directive.handle; - value.prefix = token->data.tag_directive.prefix; - - if (!yaml_parser_append_tag_directive(parser, value, 0, - token->start_mark)) - goto error; - if (!PUSH(parser, tag_directives, value)) - goto error; - } - - SKIP_TOKEN(parser); - token = PEEK_TOKEN(parser); - if (!token) goto error; - } - - for (default_tag_directive = default_tag_directives; - default_tag_directive->handle; default_tag_directive++) { - if (!yaml_parser_append_tag_directive(parser, *default_tag_directive, 1, - token->start_mark)) - goto error; - } - - if (version_directive_ref) { - *version_directive_ref = version_directive; - } - if (tag_directives_start_ref) { - if (STACK_EMPTY(parser, tag_directives)) { - *tag_directives_start_ref = *tag_directives_end_ref = NULL; - STACK_DEL(parser, tag_directives); - } - else { - *tag_directives_start_ref = tag_directives.start; - *tag_directives_end_ref = tag_directives.top; - } - } - else { - STACK_DEL(parser, tag_directives); - } - - return 1; - -error: - yaml_free(version_directive); - while (!STACK_EMPTY(parser, tag_directives)) { - yaml_tag_directive_t tag_directive = POP(parser, tag_directives); - yaml_free(tag_directive.handle); - yaml_free(tag_directive.prefix); - } - STACK_DEL(parser, tag_directives); - return 0; -} - -/* - * Append a tag directive to the directives stack. - */ - -static int -yaml_parser_append_tag_directive(yaml_parser_t *parser, - yaml_tag_directive_t value, int allow_duplicates, yaml_mark_t mark) -{ - yaml_tag_directive_t *tag_directive; - yaml_tag_directive_t copy = { NULL, NULL }; - - for (tag_directive = parser->tag_directives.start; - tag_directive != parser->tag_directives.top; tag_directive ++) { - if (strcmp((char *)value.handle, (char *)tag_directive->handle) == 0) { - if (allow_duplicates) - return 1; - return yaml_parser_set_parser_error(parser, - "found duplicate %TAG directive", mark); - } - } - - copy.handle = yaml_strdup(value.handle); - copy.prefix = yaml_strdup(value.prefix); - if (!copy.handle || !copy.prefix) { - parser->error = YAML_MEMORY_ERROR; - goto error; - } - - if (!PUSH(parser, parser->tag_directives, copy)) - goto error; - - return 1; - -error: - yaml_free(copy.handle); - yaml_free(copy.prefix); - return 0; -} -
diff --git a/parser_c.go b/parser_c.go index c965594..da0c19f 100644 --- a/parser_c.go +++ b/parser_c.go
@@ -91,6 +91,8 @@ // State dispatcher. func yaml_parser_state_machine(parser *yaml_parser_t, event *yaml_event_t) bool { + //trace("yaml_parser_state_machine", "state:", parser.state.String()) + switch parser.state { case yaml_PARSE_STREAM_START_STATE: return yaml_parser_parse_stream_start(parser, event) @@ -195,6 +197,7 @@ // explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* // ************************* func yaml_parser_parse_document_start(parser *yaml_parser_t, event *yaml_event_t, implicit bool) bool { + token := peek_token(parser) if token == nil { return false @@ -212,10 +215,10 @@ } if implicit && token.typ != yaml_VERSION_DIRECTIVE_TOKEN && - // Parse an implicit document. token.typ != yaml_TAG_DIRECTIVE_TOKEN && token.typ != yaml_DOCUMENT_START_TOKEN && token.typ != yaml_STREAM_END_TOKEN { + // Parse an implicit document. if !yaml_parser_process_directives(parser, nil, nil) { return false } @@ -356,10 +359,13 @@ // flow_content ::= flow_collection | SCALAR // ****** func yaml_parser_parse_node(parser *yaml_parser_t, event *yaml_event_t, block, indentless_sequence bool) bool { + //defer trace("yaml_parser_parse_node", "block:", block, "indentless_sequence:", indentless_sequence)() + token := peek_token(parser) if token == nil { return false } + if token.typ == yaml_ALIAS_TOKEN { parser.state = parser.states[len(parser.states)-1] parser.states = parser.states[:len(parser.states)-1] @@ -431,7 +437,7 @@ } else { for i := range parser.tag_directives { if bytes.Equal(parser.tag_directives[i].handle, tag_handle) { - tag := append([]byte(nil), parser.tag_directives[i].prefix...) + tag = append([]byte(nil), parser.tag_directives[i].prefix...) tag = append(tag, tag_suffix...) break }
diff --git a/reader.c b/reader.c deleted file mode 100644 index 829e32d..0000000 --- a/reader.c +++ /dev/null
@@ -1,465 +0,0 @@ - -#include "yaml_private.h" - -/* - * Declarations. - */ - -static int -yaml_parser_set_reader_error(yaml_parser_t *parser, const char *problem, - size_t offset, int value); - -static int -yaml_parser_update_raw_buffer(yaml_parser_t *parser); - -static int -yaml_parser_determine_encoding(yaml_parser_t *parser); - -YAML_DECLARE(int) -yaml_parser_update_buffer(yaml_parser_t *parser, size_t length); - -/* - * Set the reader error and return 0. - */ - -static int -yaml_parser_set_reader_error(yaml_parser_t *parser, const char *problem, - size_t offset, int value) -{ - parser->error = YAML_READER_ERROR; - parser->problem = problem; - parser->problem_offset = offset; - parser->problem_value = value; - - return 0; -} - -/* - * Byte order marks. - */ - -#define BOM_UTF8 "\xef\xbb\xbf" -#define BOM_UTF16LE "\xff\xfe" -#define BOM_UTF16BE "\xfe\xff" - -/* - * Determine the input stream encoding by checking the BOM symbol. If no BOM is - * found, the UTF-8 encoding is assumed. Return 1 on success, 0 on failure. - */ - -static int -yaml_parser_determine_encoding(yaml_parser_t *parser) -{ - /* Ensure that we had enough bytes in the raw buffer. */ - - while (!parser->eof - && parser->raw_buffer.last - parser->raw_buffer.pointer < 3) { - if (!yaml_parser_update_raw_buffer(parser)) { - return 0; - } - } - - /* Determine the encoding. */ - - if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 2 - && !memcmp(parser->raw_buffer.pointer, BOM_UTF16LE, 2)) { - parser->encoding = YAML_UTF16LE_ENCODING; - parser->raw_buffer.pointer += 2; - parser->offset += 2; - } - else if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 2 - && !memcmp(parser->raw_buffer.pointer, BOM_UTF16BE, 2)) { - parser->encoding = YAML_UTF16BE_ENCODING; - parser->raw_buffer.pointer += 2; - parser->offset += 2; - } - else if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 3 - && !memcmp(parser->raw_buffer.pointer, BOM_UTF8, 3)) { - parser->encoding = YAML_UTF8_ENCODING; - parser->raw_buffer.pointer += 3; - parser->offset += 3; - } - else { - parser->encoding = YAML_UTF8_ENCODING; - } - - return 1; -} - -/* - * Update the raw buffer. - */ - -static int -yaml_parser_update_raw_buffer(yaml_parser_t *parser) -{ - size_t size_read = 0; - - /* Return if the raw buffer is full. */ - - if (parser->raw_buffer.start == parser->raw_buffer.pointer - && parser->raw_buffer.last == parser->raw_buffer.end) - return 1; - - /* Return on EOF. */ - - if (parser->eof) return 1; - - /* Move the remaining bytes in the raw buffer to the beginning. */ - - if (parser->raw_buffer.start < parser->raw_buffer.pointer - && parser->raw_buffer.pointer < parser->raw_buffer.last) { - memmove(parser->raw_buffer.start, parser->raw_buffer.pointer, - parser->raw_buffer.last - parser->raw_buffer.pointer); - } - parser->raw_buffer.last -= - parser->raw_buffer.pointer - parser->raw_buffer.start; - parser->raw_buffer.pointer = parser->raw_buffer.start; - - /* Call the read handler to fill the buffer. */ - - if (!parser->read_handler(parser->read_handler_data, parser->raw_buffer.last, - parser->raw_buffer.end - parser->raw_buffer.last, &size_read)) { - return yaml_parser_set_reader_error(parser, "input error", - parser->offset, -1); - } - parser->raw_buffer.last += size_read; - if (!size_read) { - parser->eof = 1; - } - - return 1; -} - -/* - * Ensure that the buffer contains at least `length` characters. - * Return 1 on success, 0 on failure. - * - * The length is supposed to be significantly less that the buffer size. - */ - -YAML_DECLARE(int) -yaml_parser_update_buffer(yaml_parser_t *parser, size_t length) -{ - int first = 1; - - assert(parser->read_handler); /* Read handler must be set. */ - - /* If the EOF flag is set and the raw buffer is empty, do nothing. */ - - if (parser->eof && parser->raw_buffer.pointer == parser->raw_buffer.last) - return 1; - - /* Return if the buffer contains enough characters. */ - - if (parser->unread >= length) - return 1; - - /* Determine the input encoding if it is not known yet. */ - - if (!parser->encoding) { - if (!yaml_parser_determine_encoding(parser)) - return 0; - } - - /* Move the unread characters to the beginning of the buffer. */ - - if (parser->buffer.start < parser->buffer.pointer - && parser->buffer.pointer < parser->buffer.last) { - size_t size = parser->buffer.last - parser->buffer.pointer; - memmove(parser->buffer.start, parser->buffer.pointer, size); - parser->buffer.pointer = parser->buffer.start; - parser->buffer.last = parser->buffer.start + size; - } - else if (parser->buffer.pointer == parser->buffer.last) { - parser->buffer.pointer = parser->buffer.start; - parser->buffer.last = parser->buffer.start; - } - - /* Fill the buffer until it has enough characters. */ - - while (parser->unread < length) - { - /* Fill the raw buffer if necessary. */ - - if (!first || parser->raw_buffer.pointer == parser->raw_buffer.last) { - if (!yaml_parser_update_raw_buffer(parser)) return 0; - } - first = 0; - - /* Decode the raw buffer. */ - - while (parser->raw_buffer.pointer != parser->raw_buffer.last) - { - unsigned int value = 0, value2 = 0; - int incomplete = 0; - unsigned char octet; - unsigned int width = 0; - int low, high; - size_t k; - size_t raw_unread = parser->raw_buffer.last - parser->raw_buffer.pointer; - - /* Decode the next character. */ - - switch (parser->encoding) - { - case YAML_UTF8_ENCODING: - - /* - * Decode a UTF-8 character. Check RFC 3629 - * (http://www.ietf.org/rfc/rfc3629.txt) for more details. - * - * The following table (taken from the RFC) is used for - * decoding. - * - * Char. number range | UTF-8 octet sequence - * (hexadecimal) | (binary) - * --------------------+------------------------------------ - * 0000 0000-0000 007F | 0xxxxxxx - * 0000 0080-0000 07FF | 110xxxxx 10xxxxxx - * 0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx - * 0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx - * - * Additionally, the characters in the range 0xD800-0xDFFF - * are prohibited as they are reserved for use with UTF-16 - * surrogate pairs. - */ - - /* Determine the length of the UTF-8 sequence. */ - - octet = parser->raw_buffer.pointer[0]; - width = (octet & 0x80) == 0x00 ? 1 : - (octet & 0xE0) == 0xC0 ? 2 : - (octet & 0xF0) == 0xE0 ? 3 : - (octet & 0xF8) == 0xF0 ? 4 : 0; - - /* Check if the leading octet is valid. */ - - if (!width) - return yaml_parser_set_reader_error(parser, - "invalid leading UTF-8 octet", - parser->offset, octet); - - /* Check if the raw buffer contains an incomplete character. */ - - if (width > raw_unread) { - if (parser->eof) { - return yaml_parser_set_reader_error(parser, - "incomplete UTF-8 octet sequence", - parser->offset, -1); - } - incomplete = 1; - break; - } - - /* Decode the leading octet. */ - - value = (octet & 0x80) == 0x00 ? octet & 0x7F : - (octet & 0xE0) == 0xC0 ? octet & 0x1F : - (octet & 0xF0) == 0xE0 ? octet & 0x0F : - (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; - - /* Check and decode the trailing octets. */ - - for (k = 1; k < width; k ++) - { - octet = parser->raw_buffer.pointer[k]; - - /* Check if the octet is valid. */ - - if ((octet & 0xC0) != 0x80) - return yaml_parser_set_reader_error(parser, - "invalid trailing UTF-8 octet", - parser->offset+k, octet); - - /* Decode the octet. */ - - value = (value << 6) + (octet & 0x3F); - } - - /* Check the length of the sequence against the value. */ - - if (!((width == 1) || - (width == 2 && value >= 0x80) || - (width == 3 && value >= 0x800) || - (width == 4 && value >= 0x10000))) - return yaml_parser_set_reader_error(parser, - "invalid length of a UTF-8 sequence", - parser->offset, -1); - - /* Check the range of the value. */ - - if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) - return yaml_parser_set_reader_error(parser, - "invalid Unicode character", - parser->offset, value); - - break; - - case YAML_UTF16LE_ENCODING: - case YAML_UTF16BE_ENCODING: - - low = (parser->encoding == YAML_UTF16LE_ENCODING ? 0 : 1); - high = (parser->encoding == YAML_UTF16LE_ENCODING ? 1 : 0); - - /* - * The UTF-16 encoding is not as simple as one might - * naively think. Check RFC 2781 - * (http://www.ietf.org/rfc/rfc2781.txt). - * - * Normally, two subsequent bytes describe a Unicode - * character. However a special technique (called a - * surrogate pair) is used for specifying character - * values larger than 0xFFFF. - * - * A surrogate pair consists of two pseudo-characters: - * high surrogate area (0xD800-0xDBFF) - * low surrogate area (0xDC00-0xDFFF) - * - * The following formulas are used for decoding - * and encoding characters using surrogate pairs: - * - * U = U' + 0x10000 (0x01 00 00 <= U <= 0x10 FF FF) - * U' = yyyyyyyyyyxxxxxxxxxx (0 <= U' <= 0x0F FF FF) - * W1 = 110110yyyyyyyyyy - * W2 = 110111xxxxxxxxxx - * - * where U is the character value, W1 is the high surrogate - * area, W2 is the low surrogate area. - */ - - /* Check for incomplete UTF-16 character. */ - - if (raw_unread < 2) { - if (parser->eof) { - return yaml_parser_set_reader_error(parser, - "incomplete UTF-16 character", - parser->offset, -1); - } - incomplete = 1; - break; - } - - /* Get the character. */ - - value = parser->raw_buffer.pointer[low] - + (parser->raw_buffer.pointer[high] << 8); - - /* Check for unexpected low surrogate area. */ - - if ((value & 0xFC00) == 0xDC00) - return yaml_parser_set_reader_error(parser, - "unexpected low surrogate area", - parser->offset, value); - - /* Check for a high surrogate area. */ - - if ((value & 0xFC00) == 0xD800) { - - width = 4; - - /* Check for incomplete surrogate pair. */ - - if (raw_unread < 4) { - if (parser->eof) { - return yaml_parser_set_reader_error(parser, - "incomplete UTF-16 surrogate pair", - parser->offset, -1); - } - incomplete = 1; - break; - } - - /* Get the next character. */ - - value2 = parser->raw_buffer.pointer[low+2] - + (parser->raw_buffer.pointer[high+2] << 8); - - /* Check for a low surrogate area. */ - - if ((value2 & 0xFC00) != 0xDC00) - return yaml_parser_set_reader_error(parser, - "expected low surrogate area", - parser->offset+2, value2); - - /* Generate the value of the surrogate pair. */ - - value = 0x10000 + ((value & 0x3FF) << 10) + (value2 & 0x3FF); - } - - else { - width = 2; - } - - break; - - default: - assert(1); /* Impossible. */ - } - - /* Check if the raw buffer contains enough bytes to form a character. */ - - if (incomplete) break; - - /* - * Check if the character is in the allowed range: - * #x9 | #xA | #xD | [#x20-#x7E] (8 bit) - * | #x85 | [#xA0-#xD7FF] | [#xE000-#xFFFD] (16 bit) - * | [#x10000-#x10FFFF] (32 bit) - */ - - if (! (value == 0x09 || value == 0x0A || value == 0x0D - || (value >= 0x20 && value <= 0x7E) - || (value == 0x85) || (value >= 0xA0 && value <= 0xD7FF) - || (value >= 0xE000 && value <= 0xFFFD) - || (value >= 0x10000 && value <= 0x10FFFF))) - return yaml_parser_set_reader_error(parser, - "control characters are not allowed", - parser->offset, value); - - /* Move the raw pointers. */ - - parser->raw_buffer.pointer += width; - parser->offset += width; - - /* Finally put the character into the buffer. */ - - /* 0000 0000-0000 007F -> 0xxxxxxx */ - if (value <= 0x7F) { - *(parser->buffer.last++) = value; - } - /* 0000 0080-0000 07FF -> 110xxxxx 10xxxxxx */ - else if (value <= 0x7FF) { - *(parser->buffer.last++) = 0xC0 + (value >> 6); - *(parser->buffer.last++) = 0x80 + (value & 0x3F); - } - /* 0000 0800-0000 FFFF -> 1110xxxx 10xxxxxx 10xxxxxx */ - else if (value <= 0xFFFF) { - *(parser->buffer.last++) = 0xE0 + (value >> 12); - *(parser->buffer.last++) = 0x80 + ((value >> 6) & 0x3F); - *(parser->buffer.last++) = 0x80 + (value & 0x3F); - } - /* 0001 0000-0010 FFFF -> 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ - else { - *(parser->buffer.last++) = 0xF0 + (value >> 18); - *(parser->buffer.last++) = 0x80 + ((value >> 12) & 0x3F); - *(parser->buffer.last++) = 0x80 + ((value >> 6) & 0x3F); - *(parser->buffer.last++) = 0x80 + (value & 0x3F); - } - - parser->unread ++; - } - - /* On EOF, put NUL into the buffer and return. */ - - if (parser->eof) { - *(parser->buffer.last++) = '\0'; - parser->unread ++; - return 1; - } - - } - - return 1; -} -
diff --git a/scanner.c b/scanner.c deleted file mode 100644 index a2e8619..0000000 --- a/scanner.c +++ /dev/null
@@ -1,3570 +0,0 @@ - -/* - * Introduction - * ************ - * - * The following notes assume that you are familiar with the YAML specification - * (http://yaml.org/spec/cvs/current.html). We mostly follow it, although in - * some cases we are less restrictive that it requires. - * - * The process of transforming a YAML stream into a sequence of events is - * divided on two steps: Scanning and Parsing. - * - * The Scanner transforms the input stream into a sequence of tokens, while the - * parser transform the sequence of tokens produced by the Scanner into a - * sequence of parsing events. - * - * The Scanner is rather clever and complicated. The Parser, on the contrary, - * is a straightforward implementation of a recursive-descendant parser (or, - * LL(1) parser, as it is usually called). - * - * Actually there are two issues of Scanning that might be called "clever", the - * rest is quite straightforward. The issues are "block collection start" and - * "simple keys". Both issues are explained below in details. - * - * Here the Scanning step is explained and implemented. We start with the list - * of all the tokens produced by the Scanner together with short descriptions. - * - * Now, tokens: - * - * STREAM-START(encoding) # The stream start. - * STREAM-END # The stream end. - * VERSION-DIRECTIVE(major,minor) # The '%YAML' directive. - * TAG-DIRECTIVE(handle,prefix) # The '%TAG' directive. - * DOCUMENT-START # '---' - * DOCUMENT-END # '...' - * BLOCK-SEQUENCE-START # Indentation increase denoting a block - * BLOCK-MAPPING-START # sequence or a block mapping. - * BLOCK-END # Indentation decrease. - * FLOW-SEQUENCE-START # '[' - * FLOW-SEQUENCE-END # ']' - * BLOCK-SEQUENCE-START # '{' - * BLOCK-SEQUENCE-END # '}' - * BLOCK-ENTRY # '-' - * FLOW-ENTRY # ',' - * KEY # '?' or nothing (simple keys). - * VALUE # ':' - * ALIAS(anchor) # '*anchor' - * ANCHOR(anchor) # '&anchor' - * TAG(handle,suffix) # '!handle!suffix' - * SCALAR(value,style) # A scalar. - * - * The following two tokens are "virtual" tokens denoting the beginning and the - * end of the stream: - * - * STREAM-START(encoding) - * STREAM-END - * - * We pass the information about the input stream encoding with the - * STREAM-START token. - * - * The next two tokens are responsible for tags: - * - * VERSION-DIRECTIVE(major,minor) - * TAG-DIRECTIVE(handle,prefix) - * - * Example: - * - * %YAML 1.1 - * %TAG ! !foo - * %TAG !yaml! tag:yaml.org,2002: - * --- - * - * The correspoding sequence of tokens: - * - * STREAM-START(utf-8) - * VERSION-DIRECTIVE(1,1) - * TAG-DIRECTIVE("!","!foo") - * TAG-DIRECTIVE("!yaml","tag:yaml.org,2002:") - * DOCUMENT-START - * STREAM-END - * - * Note that the VERSION-DIRECTIVE and TAG-DIRECTIVE tokens occupy a whole - * line. - * - * The document start and end indicators are represented by: - * - * DOCUMENT-START - * DOCUMENT-END - * - * Note that if a YAML stream contains an implicit document (without '---' - * and '...' indicators), no DOCUMENT-START and DOCUMENT-END tokens will be - * produced. - * - * In the following examples, we present whole documents together with the - * produced tokens. - * - * 1. An implicit document: - * - * 'a scalar' - * - * Tokens: - * - * STREAM-START(utf-8) - * SCALAR("a scalar",single-quoted) - * STREAM-END - * - * 2. An explicit document: - * - * --- - * 'a scalar' - * ... - * - * Tokens: - * - * STREAM-START(utf-8) - * DOCUMENT-START - * SCALAR("a scalar",single-quoted) - * DOCUMENT-END - * STREAM-END - * - * 3. Several documents in a stream: - * - * 'a scalar' - * --- - * 'another scalar' - * --- - * 'yet another scalar' - * - * Tokens: - * - * STREAM-START(utf-8) - * SCALAR("a scalar",single-quoted) - * DOCUMENT-START - * SCALAR("another scalar",single-quoted) - * DOCUMENT-START - * SCALAR("yet another scalar",single-quoted) - * STREAM-END - * - * We have already introduced the SCALAR token above. The following tokens are - * used to describe aliases, anchors, tag, and scalars: - * - * ALIAS(anchor) - * ANCHOR(anchor) - * TAG(handle,suffix) - * SCALAR(value,style) - * - * The following series of examples illustrate the usage of these tokens: - * - * 1. A recursive sequence: - * - * &A [ *A ] - * - * Tokens: - * - * STREAM-START(utf-8) - * ANCHOR("A") - * FLOW-SEQUENCE-START - * ALIAS("A") - * FLOW-SEQUENCE-END - * STREAM-END - * - * 2. A tagged scalar: - * - * !!float "3.14" # A good approximation. - * - * Tokens: - * - * STREAM-START(utf-8) - * TAG("!!","float") - * SCALAR("3.14",double-quoted) - * STREAM-END - * - * 3. Various scalar styles: - * - * --- # Implicit empty plain scalars do not produce tokens. - * --- a plain scalar - * --- 'a single-quoted scalar' - * --- "a double-quoted scalar" - * --- |- - * a literal scalar - * --- >- - * a folded - * scalar - * - * Tokens: - * - * STREAM-START(utf-8) - * DOCUMENT-START - * DOCUMENT-START - * SCALAR("a plain scalar",plain) - * DOCUMENT-START - * SCALAR("a single-quoted scalar",single-quoted) - * DOCUMENT-START - * SCALAR("a double-quoted scalar",double-quoted) - * DOCUMENT-START - * SCALAR("a literal scalar",literal) - * DOCUMENT-START - * SCALAR("a folded scalar",folded) - * STREAM-END - * - * Now it's time to review collection-related tokens. We will start with - * flow collections: - * - * FLOW-SEQUENCE-START - * FLOW-SEQUENCE-END - * FLOW-MAPPING-START - * FLOW-MAPPING-END - * FLOW-ENTRY - * KEY - * VALUE - * - * The tokens FLOW-SEQUENCE-START, FLOW-SEQUENCE-END, FLOW-MAPPING-START, and - * FLOW-MAPPING-END represent the indicators '[', ']', '{', and '}' - * correspondingly. FLOW-ENTRY represent the ',' indicator. Finally the - * indicators '?' and ':', which are used for denoting mapping keys and values, - * are represented by the KEY and VALUE tokens. - * - * The following examples show flow collections: - * - * 1. A flow sequence: - * - * [item 1, item 2, item 3] - * - * Tokens: - * - * STREAM-START(utf-8) - * FLOW-SEQUENCE-START - * SCALAR("item 1",plain) - * FLOW-ENTRY - * SCALAR("item 2",plain) - * FLOW-ENTRY - * SCALAR("item 3",plain) - * FLOW-SEQUENCE-END - * STREAM-END - * - * 2. A flow mapping: - * - * { - * a simple key: a value, # Note that the KEY token is produced. - * ? a complex key: another value, - * } - * - * Tokens: - * - * STREAM-START(utf-8) - * FLOW-MAPPING-START - * KEY - * SCALAR("a simple key",plain) - * VALUE - * SCALAR("a value",plain) - * FLOW-ENTRY - * KEY - * SCALAR("a complex key",plain) - * VALUE - * SCALAR("another value",plain) - * FLOW-ENTRY - * FLOW-MAPPING-END - * STREAM-END - * - * A simple key is a key which is not denoted by the '?' indicator. Note that - * the Scanner still produce the KEY token whenever it encounters a simple key. - * - * For scanning block collections, the following tokens are used (note that we - * repeat KEY and VALUE here): - * - * BLOCK-SEQUENCE-START - * BLOCK-MAPPING-START - * BLOCK-END - * BLOCK-ENTRY - * KEY - * VALUE - * - * The tokens BLOCK-SEQUENCE-START and BLOCK-MAPPING-START denote indentation - * increase that precedes a block collection (cf. the INDENT token in Python). - * The token BLOCK-END denote indentation decrease that ends a block collection - * (cf. the DEDENT token in Python). However YAML has some syntax pecularities - * that makes detections of these tokens more complex. - * - * The tokens BLOCK-ENTRY, KEY, and VALUE are used to represent the indicators - * '-', '?', and ':' correspondingly. - * - * The following examples show how the tokens BLOCK-SEQUENCE-START, - * BLOCK-MAPPING-START, and BLOCK-END are emitted by the Scanner: - * - * 1. Block sequences: - * - * - item 1 - * - item 2 - * - - * - item 3.1 - * - item 3.2 - * - - * key 1: value 1 - * key 2: value 2 - * - * Tokens: - * - * STREAM-START(utf-8) - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * SCALAR("item 1",plain) - * BLOCK-ENTRY - * SCALAR("item 2",plain) - * BLOCK-ENTRY - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * SCALAR("item 3.1",plain) - * BLOCK-ENTRY - * SCALAR("item 3.2",plain) - * BLOCK-END - * BLOCK-ENTRY - * BLOCK-MAPPING-START - * KEY - * SCALAR("key 1",plain) - * VALUE - * SCALAR("value 1",plain) - * KEY - * SCALAR("key 2",plain) - * VALUE - * SCALAR("value 2",plain) - * BLOCK-END - * BLOCK-END - * STREAM-END - * - * 2. Block mappings: - * - * a simple key: a value # The KEY token is produced here. - * ? a complex key - * : another value - * a mapping: - * key 1: value 1 - * key 2: value 2 - * a sequence: - * - item 1 - * - item 2 - * - * Tokens: - * - * STREAM-START(utf-8) - * BLOCK-MAPPING-START - * KEY - * SCALAR("a simple key",plain) - * VALUE - * SCALAR("a value",plain) - * KEY - * SCALAR("a complex key",plain) - * VALUE - * SCALAR("another value",plain) - * KEY - * SCALAR("a mapping",plain) - * BLOCK-MAPPING-START - * KEY - * SCALAR("key 1",plain) - * VALUE - * SCALAR("value 1",plain) - * KEY - * SCALAR("key 2",plain) - * VALUE - * SCALAR("value 2",plain) - * BLOCK-END - * KEY - * SCALAR("a sequence",plain) - * VALUE - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * SCALAR("item 1",plain) - * BLOCK-ENTRY - * SCALAR("item 2",plain) - * BLOCK-END - * BLOCK-END - * STREAM-END - * - * YAML does not always require to start a new block collection from a new - * line. If the current line contains only '-', '?', and ':' indicators, a new - * block collection may start at the current line. The following examples - * illustrate this case: - * - * 1. Collections in a sequence: - * - * - - item 1 - * - item 2 - * - key 1: value 1 - * key 2: value 2 - * - ? complex key - * : complex value - * - * Tokens: - * - * STREAM-START(utf-8) - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * SCALAR("item 1",plain) - * BLOCK-ENTRY - * SCALAR("item 2",plain) - * BLOCK-END - * BLOCK-ENTRY - * BLOCK-MAPPING-START - * KEY - * SCALAR("key 1",plain) - * VALUE - * SCALAR("value 1",plain) - * KEY - * SCALAR("key 2",plain) - * VALUE - * SCALAR("value 2",plain) - * BLOCK-END - * BLOCK-ENTRY - * BLOCK-MAPPING-START - * KEY - * SCALAR("complex key") - * VALUE - * SCALAR("complex value") - * BLOCK-END - * BLOCK-END - * STREAM-END - * - * 2. Collections in a mapping: - * - * ? a sequence - * : - item 1 - * - item 2 - * ? a mapping - * : key 1: value 1 - * key 2: value 2 - * - * Tokens: - * - * STREAM-START(utf-8) - * BLOCK-MAPPING-START - * KEY - * SCALAR("a sequence",plain) - * VALUE - * BLOCK-SEQUENCE-START - * BLOCK-ENTRY - * SCALAR("item 1",plain) - * BLOCK-ENTRY - * SCALAR("item 2",plain) - * BLOCK-END - * KEY - * SCALAR("a mapping",plain) - * VALUE - * BLOCK-MAPPING-START - * KEY - * SCALAR("key 1",plain) - * VALUE - * SCALAR("value 1",plain) - * KEY - * SCALAR("key 2",plain) - * VALUE - * SCALAR("value 2",plain) - * BLOCK-END - * BLOCK-END - * STREAM-END - * - * YAML also permits non-indented sequences if they are included into a block - * mapping. In this case, the token BLOCK-SEQUENCE-START is not produced: - * - * key: - * - item 1 # BLOCK-SEQUENCE-START is NOT produced here. - * - item 2 - * - * Tokens: - * - * STREAM-START(utf-8) - * BLOCK-MAPPING-START - * KEY - * SCALAR("key",plain) - * VALUE - * BLOCK-ENTRY - * SCALAR("item 1",plain) - * BLOCK-ENTRY - * SCALAR("item 2",plain) - * BLOCK-END - */ - -#include "yaml_private.h" - -/* - * Ensure that the buffer contains the required number of characters. - * Return 1 on success, 0 on failure (reader error or memory error). - */ - -#define CACHE(parser,length) \ - (parser->unread >= (length) \ - ? 1 \ - : yaml_parser_update_buffer(parser, (length))) - -/* - * Advance the buffer pointer. - */ - -#define SKIP(parser) \ - (parser->mark.index ++, \ - parser->mark.column ++, \ - parser->unread --, \ - parser->buffer.pointer += WIDTH(parser->buffer)) - -#define SKIP_LINE(parser) \ - (IS_CRLF(parser->buffer) ? \ - (parser->mark.index += 2, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread -= 2, \ - parser->buffer.pointer += 2) : \ - IS_BREAK(parser->buffer) ? \ - (parser->mark.index ++, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread --, \ - parser->buffer.pointer += WIDTH(parser->buffer)) : 0) - -/* - * Copy a character to a string buffer and advance pointers. - */ - -#define READ(parser,string) \ - (STRING_EXTEND(parser,string) ? \ - (COPY(string,parser->buffer), \ - parser->mark.index ++, \ - parser->mark.column ++, \ - parser->unread --, \ - 1) : 0) - -/* - * Copy a line break character to a string buffer and advance pointers. - */ - -#define READ_LINE(parser,string) \ - (STRING_EXTEND(parser,string) ? \ - (((CHECK_AT(parser->buffer,'\r',0) \ - && CHECK_AT(parser->buffer,'\n',1)) ? /* CR LF -> LF */ \ - (*((string).pointer++) = (yaml_char_t) '\n', \ - parser->buffer.pointer += 2, \ - parser->mark.index += 2, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread -= 2) : \ - (CHECK_AT(parser->buffer,'\r',0) \ - || CHECK_AT(parser->buffer,'\n',0)) ? /* CR|LF -> LF */ \ - (*((string).pointer++) = (yaml_char_t) '\n', \ - parser->buffer.pointer ++, \ - parser->mark.index ++, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread --) : \ - (CHECK_AT(parser->buffer,'\xC2',0) \ - && CHECK_AT(parser->buffer,'\x85',1)) ? /* NEL -> LF */ \ - (*((string).pointer++) = (yaml_char_t) '\n', \ - parser->buffer.pointer += 2, \ - parser->mark.index ++, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread --) : \ - (CHECK_AT(parser->buffer,'\xE2',0) && \ - CHECK_AT(parser->buffer,'\x80',1) && \ - (CHECK_AT(parser->buffer,'\xA8',2) || \ - CHECK_AT(parser->buffer,'\xA9',2))) ? /* LS|PS -> LS|PS */ \ - (*((string).pointer++) = *(parser->buffer.pointer++), \ - *((string).pointer++) = *(parser->buffer.pointer++), \ - *((string).pointer++) = *(parser->buffer.pointer++), \ - parser->mark.index ++, \ - parser->mark.column = 0, \ - parser->mark.line ++, \ - parser->unread --) : 0), \ - 1) : 0) - -/* - * Public API declarations. - */ - -YAML_DECLARE(int) -yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token); - -/* - * Error handling. - */ - -static int -yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, - yaml_mark_t context_mark, const char *problem); - -/* - * High-level token API. - */ - -YAML_DECLARE(int) -yaml_parser_fetch_more_tokens(yaml_parser_t *parser); - -static int -yaml_parser_fetch_next_token(yaml_parser_t *parser); - -/* - * Potential simple keys. - */ - -static int -yaml_parser_stale_simple_keys(yaml_parser_t *parser); - -static int -yaml_parser_save_simple_key(yaml_parser_t *parser); - -static int -yaml_parser_remove_simple_key(yaml_parser_t *parser); - -static int -yaml_parser_increase_flow_level(yaml_parser_t *parser); - -static int -yaml_parser_decrease_flow_level(yaml_parser_t *parser); - -/* - * Indentation treatment. - */ - -static int -yaml_parser_roll_indent(yaml_parser_t *parser, int column, - int number, yaml_token_type_t type, yaml_mark_t mark); - -static int -yaml_parser_unroll_indent(yaml_parser_t *parser, int column); - -/* - * Token fetchers. - */ - -static int -yaml_parser_fetch_stream_start(yaml_parser_t *parser); - -static int -yaml_parser_fetch_stream_end(yaml_parser_t *parser); - -static int -yaml_parser_fetch_directive(yaml_parser_t *parser); - -static int -yaml_parser_fetch_document_indicator(yaml_parser_t *parser, - yaml_token_type_t type); - -static int -yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, - yaml_token_type_t type); - -static int -yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, - yaml_token_type_t type); - -static int -yaml_parser_fetch_flow_entry(yaml_parser_t *parser); - -static int -yaml_parser_fetch_block_entry(yaml_parser_t *parser); - -static int -yaml_parser_fetch_key(yaml_parser_t *parser); - -static int -yaml_parser_fetch_value(yaml_parser_t *parser); - -static int -yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type); - -static int -yaml_parser_fetch_tag(yaml_parser_t *parser); - -static int -yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal); - -static int -yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single); - -static int -yaml_parser_fetch_plain_scalar(yaml_parser_t *parser); - -/* - * Token scanners. - */ - -static int -yaml_parser_scan_to_next_token(yaml_parser_t *parser); - -static int -yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token); - -static int -yaml_parser_scan_directive_name(yaml_parser_t *parser, - yaml_mark_t start_mark, yaml_char_t **name); - -static int -yaml_parser_scan_version_directive_value(yaml_parser_t *parser, - yaml_mark_t start_mark, int *major, int *minor); - -static int -yaml_parser_scan_version_directive_number(yaml_parser_t *parser, - yaml_mark_t start_mark, int *number); - -static int -yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, - yaml_mark_t mark, yaml_char_t **handle, yaml_char_t **prefix); - -static int -yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, - yaml_token_type_t type); - -static int -yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token); - -static int -yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, - yaml_mark_t start_mark, yaml_char_t **handle); - -static int -yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, - yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri); - -static int -yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, - yaml_mark_t start_mark, yaml_string_t *string); - -static int -yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, - int literal); - -static int -yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, - int *indent, yaml_string_t *breaks, - yaml_mark_t start_mark, yaml_mark_t *end_mark); - -static int -yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, - int single); - -static int -yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token); - -/* - * Get the next token. - */ - -YAML_DECLARE(int) -yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token) -{ - assert(parser); /* Non-NULL parser object is expected. */ - assert(token); /* Non-NULL token object is expected. */ - - /* Erase the token object. */ - - memset(token, 0, sizeof(yaml_token_t)); - - /* No tokens after STREAM-END or error. */ - - if (parser->stream_end_produced || parser->error) { - return 1; - } - - /* Ensure that the tokens queue contains enough tokens. */ - - if (!parser->token_available) { - if (!yaml_parser_fetch_more_tokens(parser)) - return 0; - } - - /* Fetch the next token from the queue. */ - - *token = DEQUEUE(parser, parser->tokens); - parser->token_available = 0; - parser->tokens_parsed ++; - - if (token->type == YAML_STREAM_END_TOKEN) { - parser->stream_end_produced = 1; - } - - return 1; -} - -/* - * Set the scanner error and return 0. - */ - -static int -yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, - yaml_mark_t context_mark, const char *problem) -{ - parser->error = YAML_SCANNER_ERROR; - parser->context = context; - parser->context_mark = context_mark; - parser->problem = problem; - parser->problem_mark = parser->mark; - - return 0; -} - -/* - * Ensure that the tokens queue contains at least one token which can be - * returned to the Parser. - */ - -YAML_DECLARE(int) -yaml_parser_fetch_more_tokens(yaml_parser_t *parser) -{ - int need_more_tokens; - - /* While we need more tokens to fetch, do it. */ - - while (1) - { - /* - * Check if we really need to fetch more tokens. - */ - - need_more_tokens = 0; - - if (parser->tokens.head == parser->tokens.tail) - { - /* Queue is empty. */ - - need_more_tokens = 1; - } - else - { - yaml_simple_key_t *simple_key; - - /* Check if any potential simple key may occupy the head position. */ - - if (!yaml_parser_stale_simple_keys(parser)) - return 0; - - for (simple_key = parser->simple_keys.start; - simple_key != parser->simple_keys.top; simple_key++) { - if (simple_key->possible - && simple_key->token_number == parser->tokens_parsed) { - need_more_tokens = 1; - break; - } - } - } - - /* We are finished. */ - - if (!need_more_tokens) - break; - - /* Fetch the next token. */ - - if (!yaml_parser_fetch_next_token(parser)) - return 0; - } - - parser->token_available = 1; - - return 1; -} - -/* - * The dispatcher for token fetchers. - */ - -static int -yaml_parser_fetch_next_token(yaml_parser_t *parser) -{ - /* Ensure that the buffer is initialized. */ - - if (!CACHE(parser, 1)) - return 0; - - /* Check if we just started scanning. Fetch STREAM-START then. */ - - if (!parser->stream_start_produced) - return yaml_parser_fetch_stream_start(parser); - - /* Eat whitespaces and comments until we reach the next token. */ - - if (!yaml_parser_scan_to_next_token(parser)) - return 0; - - /* Remove obsolete potential simple keys. */ - - if (!yaml_parser_stale_simple_keys(parser)) - return 0; - - /* Check the indentation level against the current column. */ - - if (!yaml_parser_unroll_indent(parser, parser->mark.column)) - return 0; - - /* - * Ensure that the buffer contains at least 4 characters. 4 is the length - * of the longest indicators ('--- ' and '... '). - */ - - if (!CACHE(parser, 4)) - return 0; - - /* Is it the end of the stream? */ - - if (IS_Z(parser->buffer)) - return yaml_parser_fetch_stream_end(parser); - - /* Is it a directive? */ - - if (parser->mark.column == 0 && CHECK(parser->buffer, '%')) - return yaml_parser_fetch_directive(parser); - - /* Is it the document start indicator? */ - - if (parser->mark.column == 0 - && CHECK_AT(parser->buffer, '-', 0) - && CHECK_AT(parser->buffer, '-', 1) - && CHECK_AT(parser->buffer, '-', 2) - && IS_BLANKZ_AT(parser->buffer, 3)) - return yaml_parser_fetch_document_indicator(parser, - YAML_DOCUMENT_START_TOKEN); - - /* Is it the document end indicator? */ - - if (parser->mark.column == 0 - && CHECK_AT(parser->buffer, '.', 0) - && CHECK_AT(parser->buffer, '.', 1) - && CHECK_AT(parser->buffer, '.', 2) - && IS_BLANKZ_AT(parser->buffer, 3)) - return yaml_parser_fetch_document_indicator(parser, - YAML_DOCUMENT_END_TOKEN); - - /* Is it the flow sequence start indicator? */ - - if (CHECK(parser->buffer, '[')) - return yaml_parser_fetch_flow_collection_start(parser, - YAML_FLOW_SEQUENCE_START_TOKEN); - - /* Is it the flow mapping start indicator? */ - - if (CHECK(parser->buffer, '{')) - return yaml_parser_fetch_flow_collection_start(parser, - YAML_FLOW_MAPPING_START_TOKEN); - - /* Is it the flow sequence end indicator? */ - - if (CHECK(parser->buffer, ']')) - return yaml_parser_fetch_flow_collection_end(parser, - YAML_FLOW_SEQUENCE_END_TOKEN); - - /* Is it the flow mapping end indicator? */ - - if (CHECK(parser->buffer, '}')) - return yaml_parser_fetch_flow_collection_end(parser, - YAML_FLOW_MAPPING_END_TOKEN); - - /* Is it the flow entry indicator? */ - - if (CHECK(parser->buffer, ',')) - return yaml_parser_fetch_flow_entry(parser); - - /* Is it the block entry indicator? */ - - if (CHECK(parser->buffer, '-') && IS_BLANKZ_AT(parser->buffer, 1)) - return yaml_parser_fetch_block_entry(parser); - - /* Is it the key indicator? */ - - if (CHECK(parser->buffer, '?') - && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) - return yaml_parser_fetch_key(parser); - - /* Is it the value indicator? */ - - if (CHECK(parser->buffer, ':') - && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) - return yaml_parser_fetch_value(parser); - - /* Is it an alias? */ - - if (CHECK(parser->buffer, '*')) - return yaml_parser_fetch_anchor(parser, YAML_ALIAS_TOKEN); - - /* Is it an anchor? */ - - if (CHECK(parser->buffer, '&')) - return yaml_parser_fetch_anchor(parser, YAML_ANCHOR_TOKEN); - - /* Is it a tag? */ - - if (CHECK(parser->buffer, '!')) - return yaml_parser_fetch_tag(parser); - - /* Is it a literal scalar? */ - - if (CHECK(parser->buffer, '|') && !parser->flow_level) - return yaml_parser_fetch_block_scalar(parser, 1); - - /* Is it a folded scalar? */ - - if (CHECK(parser->buffer, '>') && !parser->flow_level) - return yaml_parser_fetch_block_scalar(parser, 0); - - /* Is it a single-quoted scalar? */ - - if (CHECK(parser->buffer, '\'')) - return yaml_parser_fetch_flow_scalar(parser, 1); - - /* Is it a double-quoted scalar? */ - - if (CHECK(parser->buffer, '"')) - return yaml_parser_fetch_flow_scalar(parser, 0); - - /* - * Is it a plain scalar? - * - * A plain scalar may start with any non-blank characters except - * - * '-', '?', ':', ',', '[', ']', '{', '}', - * '#', '&', '*', '!', '|', '>', '\'', '\"', - * '%', '@', '`'. - * - * In the block context (and, for the '-' indicator, in the flow context - * too), it may also start with the characters - * - * '-', '?', ':' - * - * if it is followed by a non-space character. - * - * The last rule is more restrictive than the specification requires. - */ - - if (!(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '-') - || CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':') - || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '[') - || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') - || CHECK(parser->buffer, '}') || CHECK(parser->buffer, '#') - || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '*') - || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '|') - || CHECK(parser->buffer, '>') || CHECK(parser->buffer, '\'') - || CHECK(parser->buffer, '"') || CHECK(parser->buffer, '%') - || CHECK(parser->buffer, '@') || CHECK(parser->buffer, '`')) || - (CHECK(parser->buffer, '-') && !IS_BLANK_AT(parser->buffer, 1)) || - (!parser->flow_level && - (CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':')) - && !IS_BLANKZ_AT(parser->buffer, 1))) - return yaml_parser_fetch_plain_scalar(parser); - - /* - * If we don't determine the token type so far, it is an error. - */ - - return yaml_parser_set_scanner_error(parser, - "while scanning for the next token", parser->mark, - "found character that cannot start any token"); -} - -/* - * Check the list of potential simple keys and remove the positions that - * cannot contain simple keys anymore. - */ - -static int -yaml_parser_stale_simple_keys(yaml_parser_t *parser) -{ - yaml_simple_key_t *simple_key; - - /* Check for a potential simple key for each flow level. */ - - for (simple_key = parser->simple_keys.start; - simple_key != parser->simple_keys.top; simple_key ++) - { - /* - * The specification requires that a simple key - * - * - is limited to a single line, - * - is shorter than 1024 characters. - */ - - if (simple_key->possible - && (simple_key->mark.line < parser->mark.line - || simple_key->mark.index+1024 < parser->mark.index)) { - - /* Check if the potential simple key to be removed is required. */ - - if (simple_key->required) { - return yaml_parser_set_scanner_error(parser, - "while scanning a simple key", simple_key->mark, - "could not find expected ':'"); - } - - simple_key->possible = 0; - } - } - - return 1; -} - -/* - * Check if a simple key may start at the current position and add it if - * needed. - */ - -static int -yaml_parser_save_simple_key(yaml_parser_t *parser) -{ - /* - * A simple key is required at the current position if the scanner is in - * the block context and the current column coincides with the indentation - * level. - */ - - int required = (!parser->flow_level - && parser->indent == (int)parser->mark.column); - - /* - * A simple key is required only when it is the first token in the current - * line. Therefore it is always allowed. But we add a check anyway. - */ - - assert(parser->simple_key_allowed || !required); /* Impossible. */ - - /* - * If the current position may start a simple key, save it. - */ - - if (parser->simple_key_allowed) - { - yaml_simple_key_t simple_key; - simple_key.possible = 1; - simple_key.required = required; - simple_key.token_number = - parser->tokens_parsed + (parser->tokens.tail - parser->tokens.head); - simple_key.mark = parser->mark; - - if (!yaml_parser_remove_simple_key(parser)) return 0; - - *(parser->simple_keys.top-1) = simple_key; - } - - return 1; -} - -/* - * Remove a potential simple key at the current flow level. - */ - -static int -yaml_parser_remove_simple_key(yaml_parser_t *parser) -{ - yaml_simple_key_t *simple_key = parser->simple_keys.top-1; - - if (simple_key->possible) - { - /* If the key is required, it is an error. */ - - if (simple_key->required) { - return yaml_parser_set_scanner_error(parser, - "while scanning a simple key", simple_key->mark, - "could not find expected ':'"); - } - } - - /* Remove the key from the stack. */ - - simple_key->possible = 0; - - return 1; -} - -/* - * Increase the flow level and resize the simple key list if needed. - */ - -static int -yaml_parser_increase_flow_level(yaml_parser_t *parser) -{ - yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } }; - - /* Reset the simple key on the next level. */ - - if (!PUSH(parser, parser->simple_keys, empty_simple_key)) - return 0; - - /* Increase the flow level. */ - - parser->flow_level++; - - return 1; -} - -/* - * Decrease the flow level. - */ - -static int -yaml_parser_decrease_flow_level(yaml_parser_t *parser) -{ - yaml_simple_key_t dummy_key; /* Used to eliminate a compiler warning. */ - - if (parser->flow_level) { - parser->flow_level --; - dummy_key = POP(parser, parser->simple_keys); - } - - return 1; -} - -/* - * Push the current indentation level to the stack and set the new level - * the current column is greater than the indentation level. In this case, - * append or insert the specified token into the token queue. - * - */ - -static int -yaml_parser_roll_indent(yaml_parser_t *parser, int column, - int number, yaml_token_type_t type, yaml_mark_t mark) -{ - yaml_token_t token; - - /* In the flow context, do nothing. */ - - if (parser->flow_level) - return 1; - - if (parser->indent < column) - { - /* - * Push the current indentation level to the stack and set the new - * indentation level. - */ - - if (!PUSH(parser, parser->indents, parser->indent)) - return 0; - - parser->indent = column; - - /* Create a token and insert it into the queue. */ - - TOKEN_INIT(token, type, mark, mark); - - if (number == -1) { - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - } - else { - if (!QUEUE_INSERT(parser, - parser->tokens, number - parser->tokens_parsed, token)) - return 0; - } - } - - return 1; -} - -/* - * Pop indentation levels from the indents stack until the current level - * becomes less or equal to the column. For each intendation level, append - * the BLOCK-END token. - */ - - -static int -yaml_parser_unroll_indent(yaml_parser_t *parser, int column) -{ - yaml_token_t token; - - /* In the flow context, do nothing. */ - - if (parser->flow_level) - return 1; - - /* Loop through the intendation levels in the stack. */ - - while (parser->indent > column) - { - /* Create a token and append it to the queue. */ - - TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - /* Pop the indentation level. */ - - parser->indent = POP(parser, parser->indents); - } - - return 1; -} - -/* - * Initialize the scanner and produce the STREAM-START token. - */ - -static int -yaml_parser_fetch_stream_start(yaml_parser_t *parser) -{ - yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } }; - yaml_token_t token; - - /* Set the initial indentation. */ - - parser->indent = -1; - - /* Initialize the simple key stack. */ - - if (!PUSH(parser, parser->simple_keys, simple_key)) - return 0; - - /* A simple key is allowed at the beginning of the stream. */ - - parser->simple_key_allowed = 1; - - /* We have started. */ - - parser->stream_start_produced = 1; - - /* Create the STREAM-START token and append it to the queue. */ - - STREAM_START_TOKEN_INIT(token, parser->encoding, - parser->mark, parser->mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the STREAM-END token and shut down the scanner. - */ - -static int -yaml_parser_fetch_stream_end(yaml_parser_t *parser) -{ - yaml_token_t token; - - /* Force new line. */ - - if (parser->mark.column != 0) { - parser->mark.column = 0; - parser->mark.line ++; - } - - /* Reset the indentation level. */ - - if (!yaml_parser_unroll_indent(parser, -1)) - return 0; - - /* Reset simple keys. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - parser->simple_key_allowed = 0; - - /* Create the STREAM-END token and append it to the queue. */ - - STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token. - */ - -static int -yaml_parser_fetch_directive(yaml_parser_t *parser) -{ - yaml_token_t token; - - /* Reset the indentation level. */ - - if (!yaml_parser_unroll_indent(parser, -1)) - return 0; - - /* Reset simple keys. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - parser->simple_key_allowed = 0; - - /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */ - - if (!yaml_parser_scan_directive(parser, &token)) - return 0; - - /* Append the token to the queue. */ - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - - return 1; -} - -/* - * Produce the DOCUMENT-START or DOCUMENT-END token. - */ - -static int -yaml_parser_fetch_document_indicator(yaml_parser_t *parser, - yaml_token_type_t type) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* Reset the indentation level. */ - - if (!yaml_parser_unroll_indent(parser, -1)) - return 0; - - /* Reset simple keys. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - parser->simple_key_allowed = 0; - - /* Consume the token. */ - - start_mark = parser->mark; - - SKIP(parser); - SKIP(parser); - SKIP(parser); - - end_mark = parser->mark; - - /* Create the DOCUMENT-START or DOCUMENT-END token. */ - - TOKEN_INIT(token, type, start_mark, end_mark); - - /* Append the token to the queue. */ - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token. - */ - -static int -yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, - yaml_token_type_t type) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* The indicators '[' and '{' may start a simple key. */ - - if (!yaml_parser_save_simple_key(parser)) - return 0; - - /* Increase the flow level. */ - - if (!yaml_parser_increase_flow_level(parser)) - return 0; - - /* A simple key may follow the indicators '[' and '{'. */ - - parser->simple_key_allowed = 1; - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */ - - TOKEN_INIT(token, type, start_mark, end_mark); - - /* Append the token to the queue. */ - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token. - */ - -static int -yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, - yaml_token_type_t type) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* Reset any potential simple key on the current flow level. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - /* Decrease the flow level. */ - - if (!yaml_parser_decrease_flow_level(parser)) - return 0; - - /* No simple keys after the indicators ']' and '}'. */ - - parser->simple_key_allowed = 0; - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */ - - TOKEN_INIT(token, type, start_mark, end_mark); - - /* Append the token to the queue. */ - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the FLOW-ENTRY token. - */ - -static int -yaml_parser_fetch_flow_entry(yaml_parser_t *parser) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* Reset any potential simple keys on the current flow level. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - /* Simple keys are allowed after ','. */ - - parser->simple_key_allowed = 1; - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the FLOW-ENTRY token and append it to the queue. */ - - TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the BLOCK-ENTRY token. - */ - -static int -yaml_parser_fetch_block_entry(yaml_parser_t *parser) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* Check if the scanner is in the block context. */ - - if (!parser->flow_level) - { - /* Check if we are allowed to start a new entry. */ - - if (!parser->simple_key_allowed) { - return yaml_parser_set_scanner_error(parser, NULL, parser->mark, - "block sequence entries are not allowed in this context"); - } - - /* Add the BLOCK-SEQUENCE-START token if needed. */ - - if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, - YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark)) - return 0; - } - else - { - /* - * It is an error for the '-' indicator to occur in the flow context, - * but we let the Parser detect and report about it because the Parser - * is able to point to the context. - */ - } - - /* Reset any potential simple keys on the current flow level. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - /* Simple keys are allowed after '-'. */ - - parser->simple_key_allowed = 1; - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the BLOCK-ENTRY token and append it to the queue. */ - - TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the KEY token. - */ - -static int -yaml_parser_fetch_key(yaml_parser_t *parser) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - - /* In the block context, additional checks are required. */ - - if (!parser->flow_level) - { - /* Check if we are allowed to start a new key (not nessesary simple). */ - - if (!parser->simple_key_allowed) { - return yaml_parser_set_scanner_error(parser, NULL, parser->mark, - "mapping keys are not allowed in this context"); - } - - /* Add the BLOCK-MAPPING-START token if needed. */ - - if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, - YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) - return 0; - } - - /* Reset any potential simple keys on the current flow level. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - /* Simple keys are allowed after '?' in the block context. */ - - parser->simple_key_allowed = (!parser->flow_level); - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the KEY token and append it to the queue. */ - - TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the VALUE token. - */ - -static int -yaml_parser_fetch_value(yaml_parser_t *parser) -{ - yaml_mark_t start_mark, end_mark; - yaml_token_t token; - yaml_simple_key_t *simple_key = parser->simple_keys.top-1; - - /* Have we found a simple key? */ - - if (simple_key->possible) - { - - /* Create the KEY token and insert it into the queue. */ - - TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark); - - if (!QUEUE_INSERT(parser, parser->tokens, - simple_key->token_number - parser->tokens_parsed, token)) - return 0; - - /* In the block context, we may need to add the BLOCK-MAPPING-START token. */ - - if (!yaml_parser_roll_indent(parser, simple_key->mark.column, - simple_key->token_number, - YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark)) - return 0; - - /* Remove the simple key. */ - - simple_key->possible = 0; - - /* A simple key cannot follow another simple key. */ - - parser->simple_key_allowed = 0; - } - else - { - /* The ':' indicator follows a complex key. */ - - /* In the block context, extra checks are required. */ - - if (!parser->flow_level) - { - /* Check if we are allowed to start a complex value. */ - - if (!parser->simple_key_allowed) { - return yaml_parser_set_scanner_error(parser, NULL, parser->mark, - "mapping values are not allowed in this context"); - } - - /* Add the BLOCK-MAPPING-START token if needed. */ - - if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, - YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) - return 0; - } - - /* Simple keys after ':' are allowed in the block context. */ - - parser->simple_key_allowed = (!parser->flow_level); - } - - /* Consume the token. */ - - start_mark = parser->mark; - SKIP(parser); - end_mark = parser->mark; - - /* Create the VALUE token and append it to the queue. */ - - TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark); - - if (!ENQUEUE(parser, parser->tokens, token)) - return 0; - - return 1; -} - -/* - * Produce the ALIAS or ANCHOR token. - */ - -static int -yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type) -{ - yaml_token_t token; - - /* An anchor or an alias could be a simple key. */ - - if (!yaml_parser_save_simple_key(parser)) - return 0; - - /* A simple key cannot follow an anchor or an alias. */ - - parser->simple_key_allowed = 0; - - /* Create the ALIAS or ANCHOR token and append it to the queue. */ - - if (!yaml_parser_scan_anchor(parser, &token, type)) - return 0; - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - return 1; -} - -/* - * Produce the TAG token. - */ - -static int -yaml_parser_fetch_tag(yaml_parser_t *parser) -{ - yaml_token_t token; - - /* A tag could be a simple key. */ - - if (!yaml_parser_save_simple_key(parser)) - return 0; - - /* A simple key cannot follow a tag. */ - - parser->simple_key_allowed = 0; - - /* Create the TAG token and append it to the queue. */ - - if (!yaml_parser_scan_tag(parser, &token)) - return 0; - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - - return 1; -} - -/* - * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens. - */ - -static int -yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal) -{ - yaml_token_t token; - - /* Remove any potential simple keys. */ - - if (!yaml_parser_remove_simple_key(parser)) - return 0; - - /* A simple key may follow a block scalar. */ - - parser->simple_key_allowed = 1; - - /* Create the SCALAR token and append it to the queue. */ - - if (!yaml_parser_scan_block_scalar(parser, &token, literal)) - return 0; - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - - return 1; -} - -/* - * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens. - */ - -static int -yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single) -{ - yaml_token_t token; - - /* A plain scalar could be a simple key. */ - - if (!yaml_parser_save_simple_key(parser)) - return 0; - - /* A simple key cannot follow a flow scalar. */ - - parser->simple_key_allowed = 0; - - /* Create the SCALAR token and append it to the queue. */ - - if (!yaml_parser_scan_flow_scalar(parser, &token, single)) - return 0; - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - - return 1; -} - -/* - * Produce the SCALAR(...,plain) token. - */ - -static int -yaml_parser_fetch_plain_scalar(yaml_parser_t *parser) -{ - yaml_token_t token; - - /* A plain scalar could be a simple key. */ - - if (!yaml_parser_save_simple_key(parser)) - return 0; - - /* A simple key cannot follow a flow scalar. */ - - parser->simple_key_allowed = 0; - - /* Create the SCALAR token and append it to the queue. */ - - if (!yaml_parser_scan_plain_scalar(parser, &token)) - return 0; - - if (!ENQUEUE(parser, parser->tokens, token)) { - yaml_token_delete(&token); - return 0; - } - - return 1; -} - -/* - * Eat whitespaces and comments until the next token is found. - */ - -static int -yaml_parser_scan_to_next_token(yaml_parser_t *parser) -{ - /* Until the next token is not found. */ - - while (1) - { - /* Allow the BOM mark to start a line. */ - - if (!CACHE(parser, 1)) return 0; - - if (parser->mark.column == 0 && IS_BOM(parser->buffer)) - SKIP(parser); - - /* - * Eat whitespaces. - * - * Tabs are allowed: - * - * - in the flow context; - * - in the block context, but not at the beginning of the line or - * after '-', '?', or ':' (complex value). - */ - - if (!CACHE(parser, 1)) return 0; - - while (CHECK(parser->buffer,' ') || - ((parser->flow_level || !parser->simple_key_allowed) && - CHECK(parser->buffer, '\t'))) { - SKIP(parser); - if (!CACHE(parser, 1)) return 0; - } - - /* Eat a comment until a line break. */ - - if (CHECK(parser->buffer, '#')) { - while (!IS_BREAKZ(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) return 0; - } - } - - /* If it is a line break, eat it. */ - - if (IS_BREAK(parser->buffer)) - { - if (!CACHE(parser, 2)) return 0; - SKIP_LINE(parser); - - /* In the block context, a new line may start a simple key. */ - - if (!parser->flow_level) { - parser->simple_key_allowed = 1; - } - } - else - { - /* We have found a token. */ - - break; - } - } - - return 1; -} - -/* - * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token. - * - * Scope: - * %YAML 1.1 # a comment \n - * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - * %TAG !yaml! tag:yaml.org,2002: \n - * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - */ - -int -yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token) -{ - yaml_mark_t start_mark, end_mark; - yaml_char_t *name = NULL; - int major, minor; - yaml_char_t *handle = NULL, *prefix = NULL; - - /* Eat '%'. */ - - start_mark = parser->mark; - - SKIP(parser); - - /* Scan the directive name. */ - - if (!yaml_parser_scan_directive_name(parser, start_mark, &name)) - goto error; - - /* Is it a YAML directive? */ - - if (strcmp((char *)name, "YAML") == 0) - { - /* Scan the VERSION directive value. */ - - if (!yaml_parser_scan_version_directive_value(parser, start_mark, - &major, &minor)) - goto error; - - end_mark = parser->mark; - - /* Create a VERSION-DIRECTIVE token. */ - - VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor, - start_mark, end_mark); - } - - /* Is it a TAG directive? */ - - else if (strcmp((char *)name, "TAG") == 0) - { - /* Scan the TAG directive value. */ - - if (!yaml_parser_scan_tag_directive_value(parser, start_mark, - &handle, &prefix)) - goto error; - - end_mark = parser->mark; - - /* Create a TAG-DIRECTIVE token. */ - - TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix, - start_mark, end_mark); - } - - /* Unknown directive. */ - - else - { - yaml_parser_set_scanner_error(parser, "while scanning a directive", - start_mark, "found uknown directive name"); - goto error; - } - - /* Eat the rest of the line including any comments. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_BLANK(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - - if (CHECK(parser->buffer, '#')) { - while (!IS_BREAKZ(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - } - - /* Check if we are at the end of the line. */ - - if (!IS_BREAKZ(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a directive", - start_mark, "did not find expected comment or line break"); - goto error; - } - - /* Eat a line break. */ - - if (IS_BREAK(parser->buffer)) { - if (!CACHE(parser, 2)) goto error; - SKIP_LINE(parser); - } - - yaml_free(name); - - return 1; - -error: - yaml_free(prefix); - yaml_free(handle); - yaml_free(name); - return 0; -} - -/* - * Scan the directive name. - * - * Scope: - * %YAML 1.1 # a comment \n - * ^^^^ - * %TAG !yaml! tag:yaml.org,2002: \n - * ^^^ - */ - -static int -yaml_parser_scan_directive_name(yaml_parser_t *parser, - yaml_mark_t start_mark, yaml_char_t **name) -{ - yaml_string_t string = NULL_STRING; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - - /* Consume the directive name. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_ALPHA(parser->buffer)) - { - if (!READ(parser, string)) goto error; - if (!CACHE(parser, 1)) goto error; - } - - /* Check if the name is empty. */ - - if (string.start == string.pointer) { - yaml_parser_set_scanner_error(parser, "while scanning a directive", - start_mark, "could not find expected directive name"); - goto error; - } - - /* Check for an blank character after the name. */ - - if (!IS_BLANKZ(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a directive", - start_mark, "found unexpected non-alphabetical character"); - goto error; - } - - *name = string.start; - - return 1; - -error: - STRING_DEL(parser, string); - return 0; -} - -/* - * Scan the value of VERSION-DIRECTIVE. - * - * Scope: - * %YAML 1.1 # a comment \n - * ^^^^^^ - */ - -static int -yaml_parser_scan_version_directive_value(yaml_parser_t *parser, - yaml_mark_t start_mark, int *major, int *minor) -{ - /* Eat whitespaces. */ - - if (!CACHE(parser, 1)) return 0; - - while (IS_BLANK(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) return 0; - } - - /* Consume the major version number. */ - - if (!yaml_parser_scan_version_directive_number(parser, start_mark, major)) - return 0; - - /* Eat '.'. */ - - if (!CHECK(parser->buffer, '.')) { - return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", - start_mark, "did not find expected digit or '.' character"); - } - - SKIP(parser); - - /* Consume the minor version number. */ - - if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor)) - return 0; - - return 1; -} - -#define MAX_NUMBER_LENGTH 9 - -/* - * Scan the version number of VERSION-DIRECTIVE. - * - * Scope: - * %YAML 1.1 # a comment \n - * ^ - * %YAML 1.1 # a comment \n - * ^ - */ - -static int -yaml_parser_scan_version_directive_number(yaml_parser_t *parser, - yaml_mark_t start_mark, int *number) -{ - int value = 0; - size_t length = 0; - - /* Repeat while the next character is digit. */ - - if (!CACHE(parser, 1)) return 0; - - while (IS_DIGIT(parser->buffer)) - { - /* Check if the number is too long. */ - - if (++length > MAX_NUMBER_LENGTH) { - return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", - start_mark, "found extremely long version number"); - } - - value = value*10 + AS_DIGIT(parser->buffer); - - SKIP(parser); - - if (!CACHE(parser, 1)) return 0; - } - - /* Check if the number was present. */ - - if (!length) { - return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", - start_mark, "did not find expected version number"); - } - - *number = value; - - return 1; -} - -/* - * Scan the value of a TAG-DIRECTIVE token. - * - * Scope: - * %TAG !yaml! tag:yaml.org,2002: \n - * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - */ - -static int -yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, - yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix) -{ - yaml_char_t *handle_value = NULL; - yaml_char_t *prefix_value = NULL; - - /* Eat whitespaces. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_BLANK(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - - /* Scan a handle. */ - - if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value)) - goto error; - - /* Expect a whitespace. */ - - if (!CACHE(parser, 1)) goto error; - - if (!IS_BLANK(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", - start_mark, "did not find expected whitespace"); - goto error; - } - - /* Eat whitespaces. */ - - while (IS_BLANK(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - - /* Scan a prefix. */ - - if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value)) - goto error; - - /* Expect a whitespace or line break. */ - - if (!CACHE(parser, 1)) goto error; - - if (!IS_BLANKZ(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", - start_mark, "did not find expected whitespace or line break"); - goto error; - } - - *handle = handle_value; - *prefix = prefix_value; - - return 1; - -error: - yaml_free(handle_value); - yaml_free(prefix_value); - return 0; -} - -static int -yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, - yaml_token_type_t type) -{ - int length = 0; - yaml_mark_t start_mark, end_mark; - yaml_string_t string = NULL_STRING; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - - /* Eat the indicator character. */ - - start_mark = parser->mark; - - SKIP(parser); - - /* Consume the value. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_ALPHA(parser->buffer)) { - if (!READ(parser, string)) goto error; - if (!CACHE(parser, 1)) goto error; - length ++; - } - - end_mark = parser->mark; - - /* - * Check if length of the anchor is greater than 0 and it is followed by - * a whitespace character or one of the indicators: - * - * '?', ':', ',', ']', '}', '%', '@', '`'. - */ - - if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?') - || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',') - || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}') - || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@') - || CHECK(parser->buffer, '`'))) { - yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ? - "while scanning an anchor" : "while scanning an alias", start_mark, - "did not find expected alphabetic or numeric character"); - goto error; - } - - /* Create a token. */ - - if (type == YAML_ANCHOR_TOKEN) { - ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark); - } - else { - ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark); - } - - return 1; - -error: - STRING_DEL(parser, string); - return 0; -} - -/* - * Scan a TAG token. - */ - -static int -yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token) -{ - yaml_char_t *handle = NULL; - yaml_char_t *suffix = NULL; - yaml_mark_t start_mark, end_mark; - - start_mark = parser->mark; - - /* Check if the tag is in the canonical form. */ - - if (!CACHE(parser, 2)) goto error; - - if (CHECK_AT(parser->buffer, '<', 1)) - { - /* Set the handle to '' */ - - handle = yaml_malloc(1); - if (!handle) goto error; - handle[0] = '\0'; - - /* Eat '!<' */ - - SKIP(parser); - SKIP(parser); - - /* Consume the tag value. */ - - if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) - goto error; - - /* Check for '>' and eat it. */ - - if (!CHECK(parser->buffer, '>')) { - yaml_parser_set_scanner_error(parser, "while scanning a tag", - start_mark, "did not find the expected '>'"); - goto error; - } - - SKIP(parser); - } - else - { - /* The tag has either the '!suffix' or the '!handle!suffix' form. */ - - /* First, try to scan a handle. */ - - if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle)) - goto error; - - /* Check if it is, indeed, handle. */ - - if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!') - { - /* Scan the suffix now. */ - - if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) - goto error; - } - else - { - /* It wasn't a handle after all. Scan the rest of the tag. */ - - if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix)) - goto error; - - /* Set the handle to '!'. */ - - yaml_free(handle); - handle = yaml_malloc(2); - if (!handle) goto error; - handle[0] = '!'; - handle[1] = '\0'; - - /* - * A special case: the '!' tag. Set the handle to '' and the - * suffix to '!'. - */ - - if (suffix[0] == '\0') { - yaml_char_t *tmp = handle; - handle = suffix; - suffix = tmp; - } - } - } - - /* Check the character which ends the tag. */ - - if (!CACHE(parser, 1)) goto error; - - if (!IS_BLANKZ(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a tag", - start_mark, "did not find expected whitespace or line break"); - goto error; - } - - end_mark = parser->mark; - - /* Create a token. */ - - TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark); - - return 1; - -error: - yaml_free(handle); - yaml_free(suffix); - return 0; -} - -/* - * Scan a tag handle. - */ - -static int -yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, - yaml_mark_t start_mark, yaml_char_t **handle) -{ - yaml_string_t string = NULL_STRING; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - - /* Check the initial '!' character. */ - - if (!CACHE(parser, 1)) goto error; - - if (!CHECK(parser->buffer, '!')) { - yaml_parser_set_scanner_error(parser, directive ? - "while scanning a tag directive" : "while scanning a tag", - start_mark, "did not find expected '!'"); - goto error; - } - - /* Copy the '!' character. */ - - if (!READ(parser, string)) goto error; - - /* Copy all subsequent alphabetical and numerical characters. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_ALPHA(parser->buffer)) - { - if (!READ(parser, string)) goto error; - if (!CACHE(parser, 1)) goto error; - } - - /* Check if the trailing character is '!' and copy it. */ - - if (CHECK(parser->buffer, '!')) - { - if (!READ(parser, string)) goto error; - } - else - { - /* - * It's either the '!' tag or not really a tag handle. If it's a %TAG - * directive, it's an error. If it's a tag token, it must be a part of - * URI. - */ - - if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) { - yaml_parser_set_scanner_error(parser, "while parsing a tag directive", - start_mark, "did not find expected '!'"); - goto error; - } - } - - *handle = string.start; - - return 1; - -error: - STRING_DEL(parser, string); - return 0; -} - -/* - * Scan a tag. - */ - -static int -yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, - yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri) -{ - size_t length = head ? strlen((char *)head) : 0; - yaml_string_t string = NULL_STRING; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - - /* Resize the string to include the head. */ - - while (string.end - string.start <= (int)length) { - if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) { - parser->error = YAML_MEMORY_ERROR; - goto error; - } - } - - /* - * Copy the head if needed. - * - * Note that we don't copy the leading '!' character. - */ - - if (length > 1) { - memcpy(string.start, head+1, length-1); - string.pointer += length-1; - } - - /* Scan the tag. */ - - if (!CACHE(parser, 1)) goto error; - - /* - * The set of characters that may appear in URI is as follows: - * - * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&', - * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']', - * '%'. - */ - - while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';') - || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?') - || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@') - || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=') - || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$') - || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.') - || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~') - || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'') - || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')') - || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']') - || CHECK(parser->buffer, '%')) - { - /* Check if it is a URI-escape sequence. */ - - if (CHECK(parser->buffer, '%')) { - if (!yaml_parser_scan_uri_escapes(parser, - directive, start_mark, &string)) goto error; - } - else { - if (!READ(parser, string)) goto error; - } - - length ++; - if (!CACHE(parser, 1)) goto error; - } - - /* Check if the tag is non-empty. */ - - if (!length) { - if (!STRING_EXTEND(parser, string)) - goto error; - - yaml_parser_set_scanner_error(parser, directive ? - "while parsing a %TAG directive" : "while parsing a tag", - start_mark, "did not find expected tag URI"); - goto error; - } - - *uri = string.start; - - return 1; - -error: - STRING_DEL(parser, string); - return 0; -} - -/* - * Decode an URI-escape sequence corresponding to a single UTF-8 character. - */ - -static int -yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, - yaml_mark_t start_mark, yaml_string_t *string) -{ - int width = 0; - - /* Decode the required number of characters. */ - - do { - - unsigned char octet = 0; - - /* Check for a URI-escaped octet. */ - - if (!CACHE(parser, 3)) return 0; - - if (!(CHECK(parser->buffer, '%') - && IS_HEX_AT(parser->buffer, 1) - && IS_HEX_AT(parser->buffer, 2))) { - return yaml_parser_set_scanner_error(parser, directive ? - "while parsing a %TAG directive" : "while parsing a tag", - start_mark, "did not find URI escaped octet"); - } - - /* Get the octet. */ - - octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2); - - /* If it is the leading octet, determine the length of the UTF-8 sequence. */ - - if (!width) - { - width = (octet & 0x80) == 0x00 ? 1 : - (octet & 0xE0) == 0xC0 ? 2 : - (octet & 0xF0) == 0xE0 ? 3 : - (octet & 0xF8) == 0xF0 ? 4 : 0; - if (!width) { - return yaml_parser_set_scanner_error(parser, directive ? - "while parsing a %TAG directive" : "while parsing a tag", - start_mark, "found an incorrect leading UTF-8 octet"); - } - } - else - { - /* Check if the trailing octet is correct. */ - - if ((octet & 0xC0) != 0x80) { - return yaml_parser_set_scanner_error(parser, directive ? - "while parsing a %TAG directive" : "while parsing a tag", - start_mark, "found an incorrect trailing UTF-8 octet"); - } - } - - /* Copy the octet and move the pointers. */ - - *(string->pointer++) = octet; - SKIP(parser); - SKIP(parser); - SKIP(parser); - - } while (--width); - - return 1; -} - -/* - * Scan a block scalar. - */ - -static int -yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, - int literal) -{ - yaml_mark_t start_mark; - yaml_mark_t end_mark; - yaml_string_t string = NULL_STRING; - yaml_string_t leading_break = NULL_STRING; - yaml_string_t trailing_breaks = NULL_STRING; - int chomping = 0; - int increment = 0; - int indent = 0; - int leading_blank = 0; - int trailing_blank = 0; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; - - /* Eat the indicator '|' or '>'. */ - - start_mark = parser->mark; - - SKIP(parser); - - /* Scan the additional block scalar indicators. */ - - if (!CACHE(parser, 1)) goto error; - - /* Check for a chomping indicator. */ - - if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) - { - /* Set the chomping method and eat the indicator. */ - - chomping = CHECK(parser->buffer, '+') ? +1 : -1; - - SKIP(parser); - - /* Check for an indentation indicator. */ - - if (!CACHE(parser, 1)) goto error; - - if (IS_DIGIT(parser->buffer)) - { - /* Check that the intendation is greater than 0. */ - - if (CHECK(parser->buffer, '0')) { - yaml_parser_set_scanner_error(parser, "while scanning a block scalar", - start_mark, "found an intendation indicator equal to 0"); - goto error; - } - - /* Get the intendation level and eat the indicator. */ - - increment = AS_DIGIT(parser->buffer); - - SKIP(parser); - } - } - - /* Do the same as above, but in the opposite order. */ - - else if (IS_DIGIT(parser->buffer)) - { - if (CHECK(parser->buffer, '0')) { - yaml_parser_set_scanner_error(parser, "while scanning a block scalar", - start_mark, "found an intendation indicator equal to 0"); - goto error; - } - - increment = AS_DIGIT(parser->buffer); - - SKIP(parser); - - if (!CACHE(parser, 1)) goto error; - - if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) { - chomping = CHECK(parser->buffer, '+') ? +1 : -1; - - SKIP(parser); - } - } - - /* Eat whitespaces and comments to the end of the line. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_BLANK(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - - if (CHECK(parser->buffer, '#')) { - while (!IS_BREAKZ(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) goto error; - } - } - - /* Check if we are at the end of the line. */ - - if (!IS_BREAKZ(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a block scalar", - start_mark, "did not find expected comment or line break"); - goto error; - } - - /* Eat a line break. */ - - if (IS_BREAK(parser->buffer)) { - if (!CACHE(parser, 2)) goto error; - SKIP_LINE(parser); - } - - end_mark = parser->mark; - - /* Set the intendation level if it was specified. */ - - if (increment) { - indent = parser->indent >= 0 ? parser->indent+increment : increment; - } - - /* Scan the leading line breaks and determine the indentation level if needed. */ - - if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks, - start_mark, &end_mark)) goto error; - - /* Scan the block scalar content. */ - - if (!CACHE(parser, 1)) goto error; - - while ((int)parser->mark.column == indent && !IS_Z(parser->buffer)) - { - /* - * We are at the beginning of a non-empty line. - */ - - /* Is it a trailing whitespace? */ - - trailing_blank = IS_BLANK(parser->buffer); - - /* Check if we need to fold the leading line break. */ - - if (!literal && (*leading_break.start == '\n') - && !leading_blank && !trailing_blank) - { - /* Do we need to join the lines by space? */ - - if (*trailing_breaks.start == '\0') { - if (!STRING_EXTEND(parser, string)) goto error; - *(string.pointer ++) = ' '; - } - - CLEAR(parser, leading_break); - } - else { - if (!JOIN(parser, string, leading_break)) goto error; - CLEAR(parser, leading_break); - } - - /* Append the remaining line breaks. */ - - if (!JOIN(parser, string, trailing_breaks)) goto error; - CLEAR(parser, trailing_breaks); - - /* Is it a leading whitespace? */ - - leading_blank = IS_BLANK(parser->buffer); - - /* Consume the current line. */ - - while (!IS_BREAKZ(parser->buffer)) { - if (!READ(parser, string)) goto error; - if (!CACHE(parser, 1)) goto error; - } - - /* Consume the line break. */ - - if (!CACHE(parser, 2)) goto error; - - if (!READ_LINE(parser, leading_break)) goto error; - - /* Eat the following intendation spaces and line breaks. */ - - if (!yaml_parser_scan_block_scalar_breaks(parser, - &indent, &trailing_breaks, start_mark, &end_mark)) goto error; - } - - /* Chomp the tail. */ - - if (chomping != -1) { - if (!JOIN(parser, string, leading_break)) goto error; - } - if (chomping == 1) { - if (!JOIN(parser, string, trailing_breaks)) goto error; - } - - /* Create a token. */ - - SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, - literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE, - start_mark, end_mark); - - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - - return 1; - -error: - STRING_DEL(parser, string); - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - - return 0; -} - -/* - * Scan intendation spaces and line breaks for a block scalar. Determine the - * intendation level if needed. - */ - -static int -yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, - int *indent, yaml_string_t *breaks, - yaml_mark_t start_mark, yaml_mark_t *end_mark) -{ - int max_indent = 0; - - *end_mark = parser->mark; - - /* Eat the intendation spaces and line breaks. */ - - while (1) - { - /* Eat the intendation spaces. */ - - if (!CACHE(parser, 1)) return 0; - - while ((!*indent || (int)parser->mark.column < *indent) - && IS_SPACE(parser->buffer)) { - SKIP(parser); - if (!CACHE(parser, 1)) return 0; - } - - if ((int)parser->mark.column > max_indent) - max_indent = (int)parser->mark.column; - - /* Check for a tab character messing the intendation. */ - - if ((!*indent || (int)parser->mark.column < *indent) - && IS_TAB(parser->buffer)) { - return yaml_parser_set_scanner_error(parser, "while scanning a block scalar", - start_mark, "found a tab character where an intendation space is expected"); - } - - /* Have we found a non-empty line? */ - - if (!IS_BREAK(parser->buffer)) break; - - /* Consume the line break. */ - - if (!CACHE(parser, 2)) return 0; - if (!READ_LINE(parser, *breaks)) return 0; - *end_mark = parser->mark; - } - - /* Determine the indentation level if needed. */ - - if (!*indent) { - *indent = max_indent; - if (*indent < parser->indent + 1) - *indent = parser->indent + 1; - if (*indent < 1) - *indent = 1; - } - - return 1; -} - -/* - * Scan a quoted scalar. - */ - -static int -yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, - int single) -{ - yaml_mark_t start_mark; - yaml_mark_t end_mark; - yaml_string_t string = NULL_STRING; - yaml_string_t leading_break = NULL_STRING; - yaml_string_t trailing_breaks = NULL_STRING; - yaml_string_t whitespaces = NULL_STRING; - int leading_blanks; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; - - /* Eat the left quote. */ - - start_mark = parser->mark; - - SKIP(parser); - - /* Consume the content of the quoted scalar. */ - - while (1) - { - /* Check that there are no document indicators at the beginning of the line. */ - - if (!CACHE(parser, 4)) goto error; - - if (parser->mark.column == 0 && - ((CHECK_AT(parser->buffer, '-', 0) && - CHECK_AT(parser->buffer, '-', 1) && - CHECK_AT(parser->buffer, '-', 2)) || - (CHECK_AT(parser->buffer, '.', 0) && - CHECK_AT(parser->buffer, '.', 1) && - CHECK_AT(parser->buffer, '.', 2))) && - IS_BLANKZ_AT(parser->buffer, 3)) - { - yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", - start_mark, "found unexpected document indicator"); - goto error; - } - - /* Check for EOF. */ - - if (IS_Z(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", - start_mark, "found unexpected end of stream"); - goto error; - } - - /* Consume non-blank characters. */ - - if (!CACHE(parser, 2)) goto error; - - leading_blanks = 0; - - while (!IS_BLANKZ(parser->buffer)) - { - /* Check for an escaped single quote. */ - - if (single && CHECK_AT(parser->buffer, '\'', 0) - && CHECK_AT(parser->buffer, '\'', 1)) - { - if (!STRING_EXTEND(parser, string)) goto error; - *(string.pointer++) = '\''; - SKIP(parser); - SKIP(parser); - } - - /* Check for the right quote. */ - - else if (CHECK(parser->buffer, single ? '\'' : '"')) - { - break; - } - - /* Check for an escaped line break. */ - - else if (!single && CHECK(parser->buffer, '\\') - && IS_BREAK_AT(parser->buffer, 1)) - { - if (!CACHE(parser, 3)) goto error; - SKIP(parser); - SKIP_LINE(parser); - leading_blanks = 1; - break; - } - - /* Check for an escape sequence. */ - - else if (!single && CHECK(parser->buffer, '\\')) - { - size_t code_length = 0; - - if (!STRING_EXTEND(parser, string)) goto error; - - /* Check the escape character. */ - - switch (parser->buffer.pointer[1]) - { - case '0': - *(string.pointer++) = '\0'; - break; - - case 'a': - *(string.pointer++) = '\x07'; - break; - - case 'b': - *(string.pointer++) = '\x08'; - break; - - case 't': - case '\t': - *(string.pointer++) = '\x09'; - break; - - case 'n': - *(string.pointer++) = '\x0A'; - break; - - case 'v': - *(string.pointer++) = '\x0B'; - break; - - case 'f': - *(string.pointer++) = '\x0C'; - break; - - case 'r': - *(string.pointer++) = '\x0D'; - break; - - case 'e': - *(string.pointer++) = '\x1B'; - break; - - case ' ': - *(string.pointer++) = '\x20'; - break; - - case '"': - *(string.pointer++) = '"'; - break; - - case '\'': - *(string.pointer++) = '\''; - break; - - case '\\': - *(string.pointer++) = '\\'; - break; - - case 'N': /* NEL (#x85) */ - *(string.pointer++) = '\xC2'; - *(string.pointer++) = '\x85'; - break; - - case '_': /* #xA0 */ - *(string.pointer++) = '\xC2'; - *(string.pointer++) = '\xA0'; - break; - - case 'L': /* LS (#x2028) */ - *(string.pointer++) = '\xE2'; - *(string.pointer++) = '\x80'; - *(string.pointer++) = '\xA8'; - break; - - case 'P': /* PS (#x2029) */ - *(string.pointer++) = '\xE2'; - *(string.pointer++) = '\x80'; - *(string.pointer++) = '\xA9'; - break; - - case 'x': - code_length = 2; - break; - - case 'u': - code_length = 4; - break; - - case 'U': - code_length = 8; - break; - - default: - yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", - start_mark, "found unknown escape character"); - goto error; - } - - SKIP(parser); - SKIP(parser); - - /* Consume an arbitrary escape code. */ - - if (code_length) - { - unsigned int value = 0; - size_t k; - - /* Scan the character value. */ - - if (!CACHE(parser, code_length)) goto error; - - for (k = 0; k < code_length; k ++) { - if (!IS_HEX_AT(parser->buffer, k)) { - yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", - start_mark, "did not find expected hexdecimal number"); - goto error; - } - value = (value << 4) + AS_HEX_AT(parser->buffer, k); - } - - /* Check the value and write the character. */ - - if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) { - yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", - start_mark, "found invalid Unicode character escape code"); - goto error; - } - - if (value <= 0x7F) { - *(string.pointer++) = value; - } - else if (value <= 0x7FF) { - *(string.pointer++) = 0xC0 + (value >> 6); - *(string.pointer++) = 0x80 + (value & 0x3F); - } - else if (value <= 0xFFFF) { - *(string.pointer++) = 0xE0 + (value >> 12); - *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); - *(string.pointer++) = 0x80 + (value & 0x3F); - } - else { - *(string.pointer++) = 0xF0 + (value >> 18); - *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F); - *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); - *(string.pointer++) = 0x80 + (value & 0x3F); - } - - /* Advance the pointer. */ - - for (k = 0; k < code_length; k ++) { - SKIP(parser); - } - } - } - - else - { - /* It is a non-escaped non-blank character. */ - - if (!READ(parser, string)) goto error; - } - - if (!CACHE(parser, 2)) goto error; - } - - /* Check if we are at the end of the scalar. */ - - if (CHECK(parser->buffer, single ? '\'' : '"')) - break; - - /* Consume blank characters. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) - { - if (IS_BLANK(parser->buffer)) - { - /* Consume a space or a tab character. */ - - if (!leading_blanks) { - if (!READ(parser, whitespaces)) goto error; - } - else { - SKIP(parser); - } - } - else - { - if (!CACHE(parser, 2)) goto error; - - /* Check if it is a first line break. */ - - if (!leading_blanks) - { - CLEAR(parser, whitespaces); - if (!READ_LINE(parser, leading_break)) goto error; - leading_blanks = 1; - } - else - { - if (!READ_LINE(parser, trailing_breaks)) goto error; - } - } - if (!CACHE(parser, 1)) goto error; - } - - /* Join the whitespaces or fold line breaks. */ - - if (leading_blanks) - { - /* Do we need to fold line breaks? */ - - if (leading_break.start[0] == '\n') { - if (trailing_breaks.start[0] == '\0') { - if (!STRING_EXTEND(parser, string)) goto error; - *(string.pointer++) = ' '; - } - else { - if (!JOIN(parser, string, trailing_breaks)) goto error; - CLEAR(parser, trailing_breaks); - } - CLEAR(parser, leading_break); - } - else { - if (!JOIN(parser, string, leading_break)) goto error; - if (!JOIN(parser, string, trailing_breaks)) goto error; - CLEAR(parser, leading_break); - CLEAR(parser, trailing_breaks); - } - } - else - { - if (!JOIN(parser, string, whitespaces)) goto error; - CLEAR(parser, whitespaces); - } - } - - /* Eat the right quote. */ - - SKIP(parser); - - end_mark = parser->mark; - - /* Create a token. */ - - SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, - single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE, - start_mark, end_mark); - - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - STRING_DEL(parser, whitespaces); - - return 1; - -error: - STRING_DEL(parser, string); - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - STRING_DEL(parser, whitespaces); - - return 0; -} - -/* - * Scan a plain scalar. - */ - -static int -yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token) -{ - yaml_mark_t start_mark; - yaml_mark_t end_mark; - yaml_string_t string = NULL_STRING; - yaml_string_t leading_break = NULL_STRING; - yaml_string_t trailing_breaks = NULL_STRING; - yaml_string_t whitespaces = NULL_STRING; - int leading_blanks = 0; - int indent = parser->indent+1; - - if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; - if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; - - start_mark = end_mark = parser->mark; - - /* Consume the content of the plain scalar. */ - - while (1) - { - /* Check for a document indicator. */ - - if (!CACHE(parser, 4)) goto error; - - if (parser->mark.column == 0 && - ((CHECK_AT(parser->buffer, '-', 0) && - CHECK_AT(parser->buffer, '-', 1) && - CHECK_AT(parser->buffer, '-', 2)) || - (CHECK_AT(parser->buffer, '.', 0) && - CHECK_AT(parser->buffer, '.', 1) && - CHECK_AT(parser->buffer, '.', 2))) && - IS_BLANKZ_AT(parser->buffer, 3)) break; - - /* Check for a comment. */ - - if (CHECK(parser->buffer, '#')) - break; - - /* Consume non-blank characters. */ - - while (!IS_BLANKZ(parser->buffer)) - { - /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */ - - if (parser->flow_level - && CHECK(parser->buffer, ':') - && !IS_BLANKZ_AT(parser->buffer, 1)) { - yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", - start_mark, "found unexpected ':'"); - goto error; - } - - /* Check for indicators that may end a plain scalar. */ - - if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1)) - || (parser->flow_level && - (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':') - || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[') - || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') - || CHECK(parser->buffer, '}')))) - break; - - /* Check if we need to join whitespaces and breaks. */ - - if (leading_blanks || whitespaces.start != whitespaces.pointer) - { - if (leading_blanks) - { - /* Do we need to fold line breaks? */ - - if (leading_break.start[0] == '\n') { - if (trailing_breaks.start[0] == '\0') { - if (!STRING_EXTEND(parser, string)) goto error; - *(string.pointer++) = ' '; - } - else { - if (!JOIN(parser, string, trailing_breaks)) goto error; - CLEAR(parser, trailing_breaks); - } - CLEAR(parser, leading_break); - } - else { - if (!JOIN(parser, string, leading_break)) goto error; - if (!JOIN(parser, string, trailing_breaks)) goto error; - CLEAR(parser, leading_break); - CLEAR(parser, trailing_breaks); - } - - leading_blanks = 0; - } - else - { - if (!JOIN(parser, string, whitespaces)) goto error; - CLEAR(parser, whitespaces); - } - } - - /* Copy the character. */ - - if (!READ(parser, string)) goto error; - - end_mark = parser->mark; - - if (!CACHE(parser, 2)) goto error; - } - - /* Is it the end? */ - - if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))) - break; - - /* Consume blank characters. */ - - if (!CACHE(parser, 1)) goto error; - - while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) - { - if (IS_BLANK(parser->buffer)) - { - /* Check for tab character that abuse intendation. */ - - if (leading_blanks && (int)parser->mark.column < indent - && IS_TAB(parser->buffer)) { - yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", - start_mark, "found a tab character that violate intendation"); - goto error; - } - - /* Consume a space or a tab character. */ - - if (!leading_blanks) { - if (!READ(parser, whitespaces)) goto error; - } - else { - SKIP(parser); - } - } - else - { - if (!CACHE(parser, 2)) goto error; - - /* Check if it is a first line break. */ - - if (!leading_blanks) - { - CLEAR(parser, whitespaces); - if (!READ_LINE(parser, leading_break)) goto error; - leading_blanks = 1; - } - else - { - if (!READ_LINE(parser, trailing_breaks)) goto error; - } - } - if (!CACHE(parser, 1)) goto error; - } - - /* Check intendation level. */ - - if (!parser->flow_level && (int)parser->mark.column < indent) - break; - } - - /* Create a token. */ - - SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, - YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark); - - /* Note that we change the 'simple_key_allowed' flag. */ - - if (leading_blanks) { - parser->simple_key_allowed = 1; - } - - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - STRING_DEL(parser, whitespaces); - - return 1; - -error: - STRING_DEL(parser, string); - STRING_DEL(parser, leading_break); - STRING_DEL(parser, trailing_breaks); - STRING_DEL(parser, whitespaces); - - return 0; -} -
diff --git a/scanner_c.go b/scanner_c.go index e926272..9eeeffe 100644 --- a/scanner_c.go +++ b/scanner_c.go
@@ -2,6 +2,7 @@ import ( "bytes" + "fmt" ) // Introduction @@ -533,7 +534,7 @@ parser.buffer_pos += 2 parser.mark.index++ parser.unread-- - case buf[pos] == '\r' || buf[pos+1] == '\n': + case buf[pos] == '\r' || buf[pos] == '\n': // CR|LF . LF *s = append(*s, '\n') parser.buffer_pos += 1 @@ -546,7 +547,7 @@ *s = append(*s, buf[parser.buffer_pos:pos+3]...) parser.buffer_pos += 3 default: - return false + return true } parser.mark.index++ parser.mark.column = 0 @@ -602,6 +603,13 @@ return yaml_parser_set_scanner_error(parser, context, context_mark, "did not find URI escaped octet") } +func trace(args ...interface{}) func() { + pargs := append([]interface{}{"+++"}, args...) + fmt.Println(pargs...) + pargs = append([]interface{}{"---"}, args...) + return func() { fmt.Println(pargs...) } +} + // Ensure that the tokens queue contains at least one token which can be // returned to the Parser. func yaml_parser_fetch_more_tokens(parser *yaml_parser_t) bool { @@ -619,7 +627,8 @@ return false } - for _, simple_key := range parser.simple_keys { + for i := range parser.simple_keys { + simple_key := &parser.simple_keys[i] if simple_key.possible && simple_key.token_number == parser.tokens_parsed { need_more_tokens = true break @@ -643,7 +652,6 @@ // The dispatcher for token fetchers. func yaml_parser_fetch_next_token(parser *yaml_parser_t) bool { - // Ensure that the buffer is initialized. if !cache(parser, 1) { return false @@ -819,7 +827,8 @@ // cannot contain simple keys anymore. func yaml_parser_stale_simple_keys(parser *yaml_parser_t) bool { // Check for a potential simple key for each flow level. - for _, simple_key := range parser.simple_keys { + for i := range parser.simple_keys { + simple_key := &parser.simple_keys[i] // The specification requires that a simple key // @@ -965,6 +974,7 @@ // Initialize the scanner and produce the STREAM-START token. func yaml_parser_fetch_stream_start(parser *yaml_parser_t) bool { + // Set the initial indentation. parser.indent = -1 @@ -990,6 +1000,7 @@ // Produce the STREAM-END token and shut down the scanner. func yaml_parser_fetch_stream_end(parser *yaml_parser_t) bool { + // Force new line. if parser.mark.column != 0 { parser.mark.column = 0 @@ -2177,7 +2188,7 @@ trailing_blank = is_blank(parser.buffer, parser.buffer_pos) // Check if we need to fold the leading line break. - if !literal && !leading_blank && !trailing_blank && leading_break[0] == '\n' { + if !literal && !leading_blank && !trailing_blank && len(leading_break) > 0 && leading_break[0] == '\n' { // Do we need to join the lines by space? if len(trailing_breaks) == 0 { s = append(s, ' ') @@ -2255,7 +2266,7 @@ if !cache(parser, 1) { return false } - for *indent == 0 || parser.mark.column < *indent && is_space(parser.buffer, parser.buffer_pos) { + for (*indent == 0 || parser.mark.column < *indent) && is_space(parser.buffer, parser.buffer_pos) { skip(parser) if !cache(parser, 1) { return false @@ -2569,6 +2580,7 @@ // Scan a plain scalar. func yaml_parser_scan_plain_scalar(parser *yaml_parser_t, token *yaml_token_t) bool { + var s, leading_break, trailing_breaks, whitespaces []byte var leading_blanks bool var indent = parser.indent + 1
diff --git a/yaml_h.go b/yaml_h.go index ad23067..0c1df00 100644 --- a/yaml_h.go +++ b/yaml_h.go
@@ -138,6 +138,56 @@ yaml_SCALAR_TOKEN // A SCALAR token. ) +func (tt yaml_token_type_t) String() string { + switch tt { + case yaml_NO_TOKEN: + return "yaml_NO_TOKEN" + case yaml_STREAM_START_TOKEN: + return "yaml_STREAM_START_TOKEN" + case yaml_STREAM_END_TOKEN: + return "yaml_STREAM_END_TOKEN" + case yaml_VERSION_DIRECTIVE_TOKEN: + return "yaml_VERSION_DIRECTIVE_TOKEN" + case yaml_TAG_DIRECTIVE_TOKEN: + return "yaml_TAG_DIRECTIVE_TOKEN" + case yaml_DOCUMENT_START_TOKEN: + return "yaml_DOCUMENT_START_TOKEN" + case yaml_DOCUMENT_END_TOKEN: + return "yaml_DOCUMENT_END_TOKEN" + case yaml_BLOCK_SEQUENCE_START_TOKEN: + return "yaml_BLOCK_SEQUENCE_START_TOKEN" + case yaml_BLOCK_MAPPING_START_TOKEN: + return "yaml_BLOCK_MAPPING_START_TOKEN" + case yaml_BLOCK_END_TOKEN: + return "yaml_BLOCK_END_TOKEN" + case yaml_FLOW_SEQUENCE_START_TOKEN: + return "yaml_FLOW_SEQUENCE_START_TOKEN" + case yaml_FLOW_SEQUENCE_END_TOKEN: + return "yaml_FLOW_SEQUENCE_END_TOKEN" + case yaml_FLOW_MAPPING_START_TOKEN: + return "yaml_FLOW_MAPPING_START_TOKEN" + case yaml_FLOW_MAPPING_END_TOKEN: + return "yaml_FLOW_MAPPING_END_TOKEN" + case yaml_BLOCK_ENTRY_TOKEN: + return "yaml_BLOCK_ENTRY_TOKEN" + case yaml_FLOW_ENTRY_TOKEN: + return "yaml_FLOW_ENTRY_TOKEN" + case yaml_KEY_TOKEN: + return "yaml_KEY_TOKEN" + case yaml_VALUE_TOKEN: + return "yaml_VALUE_TOKEN" + case yaml_ALIAS_TOKEN: + return "yaml_ALIAS_TOKEN" + case yaml_ANCHOR_TOKEN: + return "yaml_ANCHOR_TOKEN" + case yaml_TAG_TOKEN: + return "yaml_TAG_TOKEN" + case yaml_SCALAR_TOKEN: + return "yaml_SCALAR_TOKEN" + } + return "<unknown token>" +} + // The token structure. type yaml_token_t struct { @@ -553,157 +603,6 @@ } -///** -// * Create a YAML document. -// * -// * @param[out] document An empty document object. -// * @param[in] version_directive The %YAML directive value or -// * @c NULL. -// * @param[in] tag_directives_start The beginning of the %TAG -// * directives list. -// * @param[in] tag_directives_end The end of the %TAG directives -// * list. -// * @param[in] start_implicit If the document start indicator is -// * implicit. -// * @param[in] end_implicit If the document end indicator is -// * implicit. -// * -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_initialize(yaml_document_t *document, -// yaml_version_directive_t *version_directive, -// yaml_tag_directive_t *tag_directives_start, -// yaml_tag_directive_t *tag_directives_end, -// int start_implicit, int end_implicit); -// -///** -// * Delete a YAML document and all its nodes. -// * -// * @param[in,out] document A document object. -// */ -// -//YAML_DECLARE(void) -//yaml_document_delete(yaml_document_t *document); -// -///** -// * Get a node of a YAML document. -// * -// * The pointer returned by this function is valid until any of the functions -// * modifying the documents are called. -// * -// * @param[in] document A document object. -// * @param[in] index The node id. -// * -// * @returns the node objct or @c NULL if @c node_id is out of range. -// */ -// -//YAML_DECLARE(yaml_node_t *) -//yaml_document_get_node(yaml_document_t *document, int index); -// -///** -// * Get the root of a YAML document node. -// * -// * The root object is the first object added to the document. -// * -// * The pointer returned by this function is valid until any of the functions -// * modifying the documents are called. -// * -// * An empty document produced by the parser signifies the end of a YAML -// * stream. -// * -// * @param[in] document A document object. -// * -// * @returns the node object or @c NULL if the document is empty. -// */ -// -//YAML_DECLARE(yaml_node_t *) -//yaml_document_get_root_node(yaml_document_t *document); -// -///** -// * Create a SCALAR node and attach it to the document. -// * -// * The @a style argument may be ignored by the emitter. -// * -// * @param[in,out] document A document object. -// * @param[in] tag The scalar tag. -// * @param[in] value The scalar value. -// * @param[in] length The length of the scalar value. -// * @param[in] style The scalar style. -// * -// * @returns the node id or @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_add_scalar(yaml_document_t *document, -// yaml_char_t *tag, yaml_char_t *value, int length, -// yaml_scalar_style_t style); -// -///** -// * Create a SEQUENCE node and attach it to the document. -// * -// * The @a style argument may be ignored by the emitter. -// * -// * @param[in,out] document A document object. -// * @param[in] tag The sequence tag. -// * @param[in] style The sequence style. -// * -// * @returns the node id or @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_add_sequence(yaml_document_t *document, -// yaml_char_t *tag, yaml_sequence_style_t style); -// -///** -// * Create a MAPPING node and attach it to the document. -// * -// * The @a style argument may be ignored by the emitter. -// * -// * @param[in,out] document A document object. -// * @param[in] tag The sequence tag. -// * @param[in] style The sequence style. -// * -// * @returns the node id or @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_add_mapping(yaml_document_t *document, -// yaml_char_t *tag, yaml_mapping_style_t style); -// -///** -// * Add an item to a SEQUENCE node. -// * -// * @param[in,out] document A document object. -// * @param[in] sequence The sequence node id. -// * @param[in] item The item node id. -//* -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_append_sequence_item(yaml_document_t *document, -// int sequence, int item); -// -///** -// * Add a pair of a key and a value to a MAPPING node. -// * -// * @param[in,out] document A document object. -// * @param[in] mapping The mapping node id. -// * @param[in] key The key node id. -// * @param[in] value The value node id. -//* -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_document_append_mapping_pair(yaml_document_t *document, -// int mapping, int key, int value); -// - -// Parser Definitions - // The prototype of a read handler. // // The read handler is called when the parser needs to read more bytes from the @@ -760,6 +659,60 @@ yaml_PARSE_END_STATE // Expect nothing. ) +func (ps yaml_parser_state_t) String() string { + switch ps { + case yaml_PARSE_STREAM_START_STATE: + return "yaml_PARSE_STREAM_START_STATE" + case yaml_PARSE_IMPLICIT_DOCUMENT_START_STATE: + return "yaml_PARSE_IMPLICIT_DOCUMENT_START_STATE" + case yaml_PARSE_DOCUMENT_START_STATE: + return "yaml_PARSE_DOCUMENT_START_STATE" + case yaml_PARSE_DOCUMENT_CONTENT_STATE: + return "yaml_PARSE_DOCUMENT_CONTENT_STATE" + case yaml_PARSE_DOCUMENT_END_STATE: + return "yaml_PARSE_DOCUMENT_END_STATE" + case yaml_PARSE_BLOCK_NODE_STATE: + return "yaml_PARSE_BLOCK_NODE_STATE" + case yaml_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE: + return "yaml_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE" + case yaml_PARSE_FLOW_NODE_STATE: + return "yaml_PARSE_FLOW_NODE_STATE" + case yaml_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE: + return "yaml_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE" + case yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE: + return "yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE" + case yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE: + return "yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE" + case yaml_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE: + return "yaml_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE" + case yaml_PARSE_BLOCK_MAPPING_KEY_STATE: + return "yaml_PARSE_BLOCK_MAPPING_KEY_STATE" + case yaml_PARSE_BLOCK_MAPPING_VALUE_STATE: + return "yaml_PARSE_BLOCK_MAPPING_VALUE_STATE" + case yaml_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE: + return "yaml_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE" + case yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE: + return "yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE" + case yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE: + return "yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE" + case yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE: + return "yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE" + case yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE: + return "yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE" + case yaml_PARSE_FLOW_MAPPING_FIRST_KEY_STATE: + return "yaml_PARSE_FLOW_MAPPING_FIRST_KEY_STATE" + case yaml_PARSE_FLOW_MAPPING_KEY_STATE: + return "yaml_PARSE_FLOW_MAPPING_KEY_STATE" + case yaml_PARSE_FLOW_MAPPING_VALUE_STATE: + return "yaml_PARSE_FLOW_MAPPING_VALUE_STATE" + case yaml_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE: + return "yaml_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE" + case yaml_PARSE_END_STATE: + return "yaml_PARSE_END_STATE" + } + return "<unknown parser state>" +} + // This structure holds aliases data. type yaml_alias_data_t struct { anchor []byte // The anchor. @@ -843,157 +796,6 @@ document *yaml_document_t // The currently parsed document. } -// -///** -// * Initialize a parser. -// * -// * This function creates a new parser object. An application is responsible -// * for destroying the object using the yaml_parser_delete() function. -// * -// * @param[out] parser An empty parser object. -// * -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_parser_initialize(yaml_parser_t *parser); -// -///** -// * Destroy a parser. -// * -// * @param[in,out] parser A parser object. -// */ -// -//YAML_DECLARE(void) -//yaml_parser_delete(yaml_parser_t *parser); -// -///** -// * Set a string input. -// * -// * Note that the @a input pointer must be valid while the @a parser object -// * exists. The application is responsible for destroing @a input after -// * destroying the @a parser. -// * -// * @param[in,out] parser A parser object. -// * @param[in] input A source data. -// * @param[in] size The length of the source data in bytes. -// */ -// -//YAML_DECLARE(void) -//yaml_parser_set_input_string(yaml_parser_t *parser, -// unsigned char *input, int size); -// -///** -// * Set a file input. -// * -// * @a file should be a file object open for reading. The application is -// * responsible for closing the @a file. -// * -// * @param[in,out] parser A parser object. -// * @param[in] file An open file. -// */ -// -//YAML_DECLARE(void) -//yaml_parser_set_input_file(yaml_parser_t *parser, FILE *file); -// -///** -// * Set a generic input handler. -// * -// * @param[in,out] parser A parser object. -// * @param[in] handler A read handler. -// * @param[in] data Any application data for passing to the read -// * handler. -// */ -// -//YAML_DECLARE(void) -//yaml_parser_set_input(yaml_parser_t *parser, -// yaml_read_handler_t *handler, void *data); -// -///** -// * Set the source encoding. -// * -// * @param[in,out] parser A parser object. -// * @param[in] encoding The source encoding. -// */ -// -//YAML_DECLARE(void) -//yaml_parser_set_encoding(yaml_parser_t *parser, yaml_encoding_t encoding); -// -///** -// * Scan the input stream and produce the next token. -// * -// * Call the function subsequently to produce a sequence of tokens corresponding -// * to the input stream. The initial token has the type -// * yaml_STREAM_START_TOKEN while the ending token has the type -// * yaml_STREAM_END_TOKEN. -// * -// * An application is responsible for freeing any buffers associated with the -// * produced token object using the @c yaml_token_delete function. -// * -// * An application must not alternate the calls of yaml_parser_scan() with the -// * calls of yaml_parser_parse() or yaml_parser_load(). Doing this will break -// * the parser. -// * -// * @param[in,out] parser A parser object. -// * @param[out] token An empty token object. -// * -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token); -// -///** -// * Parse the input stream and produce the next parsing event. -// * -// * Call the function subsequently to produce a sequence of events corresponding -// * to the input stream. The initial event has the type -// * yaml_STREAM_START_EVENT while the ending event has the type -// * yaml_STREAM_END_EVENT. -// * -// * An application is responsible for freeing any buffers associated with the -// * produced event object using the yaml_event_delete() function. -// * -// * An application must not alternate the calls of yaml_parser_parse() with the -// * calls of yaml_parser_scan() or yaml_parser_load(). Doing this will break the -// * parser. -// * -// * @param[in,out] parser A parser object. -// * @param[out] event An empty event object. -// * -// * @returns @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event); -// -///** -// * Parse the input stream and produce the next YAML document. -// * -// * Call this function subsequently to produce a sequence of documents -// * constituting the input stream. -// * -// * If the produced document has no root node, it means that the document -// * end has been reached. -// * -// * An application is responsible for freeing any data associated with the -// * produced document object using the yaml_document_delete() function. -// * -// * An application must not alternate the calls of yaml_parser_load() with the -// * calls of yaml_parser_scan() or yaml_parser_parse(). Doing this will break -// * the parser. -// * -// * @param[in,out] parser A parser object. -// * @param[out] document An empty document object. -// * -// * @return @c 1 if the function succeeded, @c 0 on error. -// */ -// -//YAML_DECLARE(int) -//yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document); -// -//// @} -// ///** // * @defgroup emitter Emitter Definitions // * @{