Merged pure go port.
diff --git a/api.c b/api.c deleted file mode 100644 index 0c4732e..0000000 --- a/api.c +++ /dev/null
@@ -1,1392 +0,0 @@ - -#include "yaml_private.h" - -/* - * Get the library version. - */ - -YAML_DECLARE(const char *) -yaml_get_version_string(void) -{ - return YAML_VERSION_STRING; -} - -/* - * Get the library version numbers. - */ - -YAML_DECLARE(void) -yaml_get_version(int *major, int *minor, int *patch) -{ - *major = YAML_VERSION_MAJOR; - *minor = YAML_VERSION_MINOR; - *patch = YAML_VERSION_PATCH; -} - -/* - * Allocate a dynamic memory block. - */ - -YAML_DECLARE(void *) -yaml_malloc(size_t size) -{ - return malloc(size ? size : 1); -} - -/* - * Reallocate a dynamic memory block. - */ - -YAML_DECLARE(void *) -yaml_realloc(void *ptr, size_t size) -{ - return ptr ? realloc(ptr, size ? size : 1) : malloc(size ? size : 1); -} - -/* - * Free a dynamic memory block. - */ - -YAML_DECLARE(void) -yaml_free(void *ptr) -{ - if (ptr) free(ptr); -} - -/* - * Duplicate a string. - */ - -YAML_DECLARE(yaml_char_t *) -yaml_strdup(const yaml_char_t *str) -{ - if (!str) - return NULL; - - return (yaml_char_t *)strdup((char *)str); -} - -/* - * Extend a string. - */ - -YAML_DECLARE(int) -yaml_string_extend(yaml_char_t **start, - yaml_char_t **pointer, yaml_char_t **end) -{ - yaml_char_t *new_start = yaml_realloc(*start, (*end - *start)*2); - - if (!new_start) return 0; - - memset(new_start + (*end - *start), 0, *end - *start); - - *pointer = new_start + (*pointer - *start); - *end = new_start + (*end - *start)*2; - *start = new_start; - - return 1; -} - -/* - * Append a string B to a string A. - */ - -YAML_DECLARE(int) -yaml_string_join( - yaml_char_t **a_start, yaml_char_t **a_pointer, yaml_char_t **a_end, - yaml_char_t **b_start, yaml_char_t **b_pointer, yaml_char_t **b_end) -{ - if (*b_start == *b_pointer) - return 1; - - while (*a_end - *a_pointer <= *b_pointer - *b_start) { - if (!yaml_string_extend(a_start, a_pointer, a_end)) - return 0; - } - - memcpy(*a_pointer, *b_start, *b_pointer - *b_start); - *a_pointer += *b_pointer - *b_start; - - return 1; -} - -/* - * Extend a stack. - */ - -YAML_DECLARE(int) -yaml_stack_extend(void **start, void **top, void **end) -{ - void *new_start = yaml_realloc(*start, ((char *)*end - (char *)*start)*2); - - if (!new_start) return 0; - - *top = (char *)new_start + ((char *)*top - (char *)*start); - *end = (char *)new_start + ((char *)*end - (char *)*start)*2; - *start = new_start; - - return 1; -} - -/* - * Extend or move a queue. - */ - -YAML_DECLARE(int) -yaml_queue_extend(void **start, void **head, void **tail, void **end) -{ - /* Check if we need to resize the queue. */ - - if (*start == *head && *tail == *end) { - void *new_start = yaml_realloc(*start, - ((char *)*end - (char *)*start)*2); - - if (!new_start) return 0; - - *head = (char *)new_start + ((char *)*head - (char *)*start); - *tail = (char *)new_start + ((char *)*tail - (char *)*start); - *end = (char *)new_start + ((char *)*end - (char *)*start)*2; - *start = new_start; - } - - /* Check if we need to move the queue at the beginning of the buffer. */ - - if (*tail == *end) { - if (*head != *tail) { - memmove(*start, *head, (char *)*tail - (char *)*head); - } - *tail = (char *)*tail - (char *)*head + (char *)*start; - *head = *start; - } - - return 1; -} - - -/* - * Create a new parser object. - */ - -YAML_DECLARE(int) -yaml_parser_initialize(yaml_parser_t *parser) -{ - assert(parser); /* Non-NULL parser object expected. */ - - memset(parser, 0, sizeof(yaml_parser_t)); - if (!BUFFER_INIT(parser, parser->raw_buffer, INPUT_RAW_BUFFER_SIZE)) - goto error; - if (!BUFFER_INIT(parser, parser->buffer, INPUT_BUFFER_SIZE)) - goto error; - if (!QUEUE_INIT(parser, parser->tokens, INITIAL_QUEUE_SIZE)) - goto error; - if (!STACK_INIT(parser, parser->indents, INITIAL_STACK_SIZE)) - goto error; - if (!STACK_INIT(parser, parser->simple_keys, INITIAL_STACK_SIZE)) - goto error; - if (!STACK_INIT(parser, parser->states, INITIAL_STACK_SIZE)) - goto error; - if (!STACK_INIT(parser, parser->marks, INITIAL_STACK_SIZE)) - goto error; - if (!STACK_INIT(parser, parser->tag_directives, INITIAL_STACK_SIZE)) - goto error; - - return 1; - -error: - - BUFFER_DEL(parser, parser->raw_buffer); - BUFFER_DEL(parser, parser->buffer); - QUEUE_DEL(parser, parser->tokens); - STACK_DEL(parser, parser->indents); - STACK_DEL(parser, parser->simple_keys); - STACK_DEL(parser, parser->states); - STACK_DEL(parser, parser->marks); - STACK_DEL(parser, parser->tag_directives); - - return 0; -} - -/* - * Destroy a parser object. - */ - -YAML_DECLARE(void) -yaml_parser_delete(yaml_parser_t *parser) -{ - assert(parser); /* Non-NULL parser object expected. */ - - BUFFER_DEL(parser, parser->raw_buffer); - BUFFER_DEL(parser, parser->buffer); - while (!QUEUE_EMPTY(parser, parser->tokens)) { - yaml_token_delete(&DEQUEUE(parser, parser->tokens)); - } - QUEUE_DEL(parser, parser->tokens); - STACK_DEL(parser, parser->indents); - STACK_DEL(parser, parser->simple_keys); - STACK_DEL(parser, parser->states); - STACK_DEL(parser, parser->marks); - 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); - } - STACK_DEL(parser, parser->tag_directives); - - memset(parser, 0, sizeof(yaml_parser_t)); -} - -/* - * String read handler. - */ - -static int -yaml_string_read_handler(void *data, unsigned char *buffer, size_t size, - size_t *size_read) -{ - yaml_parser_t *parser = data; - - if (parser->input.string.current == parser->input.string.end) { - *size_read = 0; - return 1; - } - - if (size > (size_t)(parser->input.string.end - - parser->input.string.current)) { - size = parser->input.string.end - parser->input.string.current; - } - - memcpy(buffer, parser->input.string.current, size); - parser->input.string.current += size; - *size_read = size; - return 1; -} - -/* - * File read handler. - */ - -static int -yaml_file_read_handler(void *data, unsigned char *buffer, size_t size, - size_t *size_read) -{ - yaml_parser_t *parser = data; - - *size_read = fread(buffer, 1, size, parser->input.file); - return !ferror(parser->input.file); -} - -/* - * Set a string input. - */ - -YAML_DECLARE(void) -yaml_parser_set_input_string(yaml_parser_t *parser, - const unsigned char *input, size_t size) -{ - assert(parser); /* Non-NULL parser object expected. */ - assert(!parser->read_handler); /* You can set the source only once. */ - assert(input); /* Non-NULL input string expected. */ - - parser->read_handler = yaml_string_read_handler; - parser->read_handler_data = parser; - - parser->input.string.start = input; - parser->input.string.current = input; - parser->input.string.end = input+size; -} - -/* - * Set a file input. - */ - -YAML_DECLARE(void) -yaml_parser_set_input_file(yaml_parser_t *parser, FILE *file) -{ - assert(parser); /* Non-NULL parser object expected. */ - assert(!parser->read_handler); /* You can set the source only once. */ - assert(file); /* Non-NULL file object expected. */ - - parser->read_handler = yaml_file_read_handler; - parser->read_handler_data = parser; - - parser->input.file = file; -} - -/* - * Set a generic input. - */ - -YAML_DECLARE(void) -yaml_parser_set_input(yaml_parser_t *parser, - yaml_read_handler_t *handler, void *data) -{ - assert(parser); /* Non-NULL parser object expected. */ - assert(!parser->read_handler); /* You can set the source only once. */ - assert(handler); /* Non-NULL read handler expected. */ - - parser->read_handler = handler; - parser->read_handler_data = data; -} - -/* - * Set the source encoding. - */ - -YAML_DECLARE(void) -yaml_parser_set_encoding(yaml_parser_t *parser, yaml_encoding_t encoding) -{ - assert(parser); /* Non-NULL parser object expected. */ - assert(!parser->encoding); /* Encoding is already set or detected. */ - - parser->encoding = encoding; -} - -/* - * Create a new emitter object. - */ - -YAML_DECLARE(int) -yaml_emitter_initialize(yaml_emitter_t *emitter) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - memset(emitter, 0, sizeof(yaml_emitter_t)); - if (!BUFFER_INIT(emitter, emitter->buffer, OUTPUT_BUFFER_SIZE)) - goto error; - if (!BUFFER_INIT(emitter, emitter->raw_buffer, OUTPUT_RAW_BUFFER_SIZE)) - goto error; - if (!STACK_INIT(emitter, emitter->states, INITIAL_STACK_SIZE)) - goto error; - if (!QUEUE_INIT(emitter, emitter->events, INITIAL_QUEUE_SIZE)) - goto error; - if (!STACK_INIT(emitter, emitter->indents, INITIAL_STACK_SIZE)) - goto error; - if (!STACK_INIT(emitter, emitter->tag_directives, INITIAL_STACK_SIZE)) - goto error; - - return 1; - -error: - - BUFFER_DEL(emitter, emitter->buffer); - BUFFER_DEL(emitter, emitter->raw_buffer); - STACK_DEL(emitter, emitter->states); - QUEUE_DEL(emitter, emitter->events); - STACK_DEL(emitter, emitter->indents); - STACK_DEL(emitter, emitter->tag_directives); - - return 0; -} - -/* - * Destroy an emitter object. - */ - -YAML_DECLARE(void) -yaml_emitter_delete(yaml_emitter_t *emitter) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - BUFFER_DEL(emitter, emitter->buffer); - BUFFER_DEL(emitter, emitter->raw_buffer); - STACK_DEL(emitter, emitter->states); - while (!QUEUE_EMPTY(emitter, emitter->events)) { - yaml_event_delete(&DEQUEUE(emitter, emitter->events)); - } - QUEUE_DEL(emitter, emitter->events); - STACK_DEL(emitter, emitter->indents); - while (!STACK_EMPTY(empty, emitter->tag_directives)) { - yaml_tag_directive_t tag_directive = POP(emitter, emitter->tag_directives); - yaml_free(tag_directive.handle); - yaml_free(tag_directive.prefix); - } - STACK_DEL(emitter, emitter->tag_directives); - yaml_free(emitter->anchors); - - memset(emitter, 0, sizeof(yaml_emitter_t)); -} - -/* - * String write handler. - */ - -static int -yaml_string_write_handler(void *data, unsigned char *buffer, size_t size) -{ - yaml_emitter_t *emitter = data; - - if (emitter->output.string.size + *emitter->output.string.size_written - < size) { - memcpy(emitter->output.string.buffer - + *emitter->output.string.size_written, - buffer, - emitter->output.string.size - - *emitter->output.string.size_written); - *emitter->output.string.size_written = emitter->output.string.size; - return 0; - } - - memcpy(emitter->output.string.buffer - + *emitter->output.string.size_written, buffer, size); - *emitter->output.string.size_written += size; - return 1; -} - -/* - * File write handler. - */ - -static int -yaml_file_write_handler(void *data, unsigned char *buffer, size_t size) -{ - yaml_emitter_t *emitter = data; - - return (fwrite(buffer, 1, size, emitter->output.file) == size); -} -/* - * Set a string output. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output_string(yaml_emitter_t *emitter, - unsigned char *output, size_t size, size_t *size_written) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - assert(!emitter->write_handler); /* You can set the output only once. */ - assert(output); /* Non-NULL output string expected. */ - - emitter->write_handler = yaml_string_write_handler; - emitter->write_handler_data = emitter; - - emitter->output.string.buffer = output; - emitter->output.string.size = size; - emitter->output.string.size_written = size_written; - *size_written = 0; -} - -/* - * Set a file output. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output_file(yaml_emitter_t *emitter, FILE *file) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - assert(!emitter->write_handler); /* You can set the output only once. */ - assert(file); /* Non-NULL file object expected. */ - - emitter->write_handler = yaml_file_write_handler; - emitter->write_handler_data = emitter; - - emitter->output.file = file; -} - -/* - * Set a generic output handler. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output(yaml_emitter_t *emitter, - yaml_write_handler_t *handler, void *data) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - assert(!emitter->write_handler); /* You can set the output only once. */ - assert(handler); /* Non-NULL handler object expected. */ - - emitter->write_handler = handler; - emitter->write_handler_data = data; -} - -/* - * Set the output encoding. - */ - -YAML_DECLARE(void) -yaml_emitter_set_encoding(yaml_emitter_t *emitter, yaml_encoding_t encoding) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - assert(!emitter->encoding); /* You can set encoding only once. */ - - emitter->encoding = encoding; -} - -/* - * Set the canonical output style. - */ - -YAML_DECLARE(void) -yaml_emitter_set_canonical(yaml_emitter_t *emitter, int canonical) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - emitter->canonical = (canonical != 0); -} - -/* - * Set the indentation increment. - */ - -YAML_DECLARE(void) -yaml_emitter_set_indent(yaml_emitter_t *emitter, int indent) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - emitter->best_indent = (1 < indent && indent < 10) ? indent : 2; -} - -/* - * Set the preferred line width. - */ - -YAML_DECLARE(void) -yaml_emitter_set_width(yaml_emitter_t *emitter, int width) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - emitter->best_width = (width >= 0) ? width : -1; -} - -/* - * Set if unescaped non-ASCII characters are allowed. - */ - -YAML_DECLARE(void) -yaml_emitter_set_unicode(yaml_emitter_t *emitter, int unicode) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - emitter->unicode = (unicode != 0); -} - -/* - * Set the preferred line break character. - */ - -YAML_DECLARE(void) -yaml_emitter_set_break(yaml_emitter_t *emitter, yaml_break_t line_break) -{ - assert(emitter); /* Non-NULL emitter object expected. */ - - emitter->line_break = line_break; -} - -/* - * Destroy a token object. - */ - -YAML_DECLARE(void) -yaml_token_delete(yaml_token_t *token) -{ - assert(token); /* Non-NULL token object expected. */ - - switch (token->type) - { - case YAML_TAG_DIRECTIVE_TOKEN: - yaml_free(token->data.tag_directive.handle); - yaml_free(token->data.tag_directive.prefix); - break; - - case YAML_ALIAS_TOKEN: - yaml_free(token->data.alias.value); - break; - - case YAML_ANCHOR_TOKEN: - yaml_free(token->data.anchor.value); - break; - - case YAML_TAG_TOKEN: - yaml_free(token->data.tag.handle); - yaml_free(token->data.tag.suffix); - break; - - case YAML_SCALAR_TOKEN: - yaml_free(token->data.scalar.value); - break; - - default: - break; - } - - memset(token, 0, sizeof(yaml_token_t)); -} - -/* - * Check if a string is a valid UTF-8 sequence. - * - * Check 'reader.c' for more details on UTF-8 encoding. - */ - -static int -yaml_check_utf8(yaml_char_t *start, size_t length) -{ - yaml_char_t *end = start+length; - yaml_char_t *pointer = start; - - while (pointer < end) { - unsigned char octet; - unsigned int width; - unsigned int value; - size_t k; - - octet = pointer[0]; - width = (octet & 0x80) == 0x00 ? 1 : - (octet & 0xE0) == 0xC0 ? 2 : - (octet & 0xF0) == 0xE0 ? 3 : - (octet & 0xF8) == 0xF0 ? 4 : 0; - value = (octet & 0x80) == 0x00 ? octet & 0x7F : - (octet & 0xE0) == 0xC0 ? octet & 0x1F : - (octet & 0xF0) == 0xE0 ? octet & 0x0F : - (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; - if (!width) return 0; - if (pointer+width > end) return 0; - for (k = 1; k < width; k ++) { - octet = pointer[k]; - if ((octet & 0xC0) != 0x80) return 0; - value = (value << 6) + (octet & 0x3F); - } - if (!((width == 1) || - (width == 2 && value >= 0x80) || - (width == 3 && value >= 0x800) || - (width == 4 && value >= 0x10000))) return 0; - - pointer += width; - } - - return 1; -} - -/* - * Create STREAM-START. - */ - -YAML_DECLARE(int) -yaml_stream_start_event_initialize(yaml_event_t *event, - yaml_encoding_t encoding) -{ - yaml_mark_t mark = { 0, 0, 0 }; - - assert(event); /* Non-NULL event object is expected. */ - - STREAM_START_EVENT_INIT(*event, encoding, mark, mark); - - return 1; -} - -/* - * Create STREAM-END. - */ - -YAML_DECLARE(int) -yaml_stream_end_event_initialize(yaml_event_t *event) -{ - yaml_mark_t mark = { 0, 0, 0 }; - - assert(event); /* Non-NULL event object is expected. */ - - STREAM_END_EVENT_INIT(*event, mark, mark); - - return 1; -} - -/* - * Create DOCUMENT-START. - */ - -YAML_DECLARE(int) -yaml_document_start_event_initialize(yaml_event_t *event, - yaml_version_directive_t *version_directive, - yaml_tag_directive_t *tag_directives_start, - yaml_tag_directive_t *tag_directives_end, - int implicit) -{ - struct { - yaml_error_type_t error; - } context; - yaml_mark_t mark = { 0, 0, 0 }; - yaml_version_directive_t *version_directive_copy = NULL; - struct { - yaml_tag_directive_t *start; - yaml_tag_directive_t *end; - yaml_tag_directive_t *top; - } tag_directives_copy = { NULL, NULL, NULL }; - yaml_tag_directive_t value = { NULL, NULL }; - - assert(event); /* Non-NULL event object is expected. */ - assert((tag_directives_start && tag_directives_end) || - (tag_directives_start == tag_directives_end)); - /* Valid tag directives are expected. */ - - if (version_directive) { - version_directive_copy = yaml_malloc(sizeof(yaml_version_directive_t)); - if (!version_directive_copy) goto error; - version_directive_copy->major = version_directive->major; - version_directive_copy->minor = version_directive->minor; - } - - if (tag_directives_start != tag_directives_end) { - yaml_tag_directive_t *tag_directive; - if (!STACK_INIT(&context, tag_directives_copy, INITIAL_STACK_SIZE)) - goto error; - for (tag_directive = tag_directives_start; - tag_directive != tag_directives_end; tag_directive ++) { - assert(tag_directive->handle); - assert(tag_directive->prefix); - if (!yaml_check_utf8(tag_directive->handle, - strlen((char *)tag_directive->handle))) - goto error; - if (!yaml_check_utf8(tag_directive->prefix, - strlen((char *)tag_directive->prefix))) - goto error; - value.handle = yaml_strdup(tag_directive->handle); - value.prefix = yaml_strdup(tag_directive->prefix); - if (!value.handle || !value.prefix) goto error; - if (!PUSH(&context, tag_directives_copy, value)) - goto error; - value.handle = NULL; - value.prefix = NULL; - } - } - - DOCUMENT_START_EVENT_INIT(*event, version_directive_copy, - tag_directives_copy.start, tag_directives_copy.top, - implicit, mark, mark); - - return 1; - -error: - yaml_free(version_directive_copy); - while (!STACK_EMPTY(context, tag_directives_copy)) { - yaml_tag_directive_t value = POP(context, tag_directives_copy); - yaml_free(value.handle); - yaml_free(value.prefix); - } - STACK_DEL(context, tag_directives_copy); - yaml_free(value.handle); - yaml_free(value.prefix); - - return 0; -} - -/* - * Create DOCUMENT-END. - */ - -YAML_DECLARE(int) -yaml_document_end_event_initialize(yaml_event_t *event, int implicit) -{ - yaml_mark_t mark = { 0, 0, 0 }; - - assert(event); /* Non-NULL emitter object is expected. */ - - DOCUMENT_END_EVENT_INIT(*event, implicit, mark, mark); - - return 1; -} - -/* - * Create ALIAS. - */ - -YAML_DECLARE(int) -yaml_alias_event_initialize(yaml_event_t *event, yaml_char_t *anchor) -{ - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *anchor_copy = NULL; - - assert(event); /* Non-NULL event object is expected. */ - assert(anchor); /* Non-NULL anchor is expected. */ - - if (!yaml_check_utf8(anchor, strlen((char *)anchor))) return 0; - - anchor_copy = yaml_strdup(anchor); - if (!anchor_copy) - return 0; - - ALIAS_EVENT_INIT(*event, anchor_copy, mark, mark); - - return 1; -} - -/* - * Create SCALAR. - */ - -YAML_DECLARE(int) -yaml_scalar_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, - yaml_char_t *value, int length, - int plain_implicit, int quoted_implicit, - yaml_scalar_style_t style) -{ - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *anchor_copy = NULL; - yaml_char_t *tag_copy = NULL; - yaml_char_t *value_copy = NULL; - - assert(event); /* Non-NULL event object is expected. */ - assert(value); /* Non-NULL anchor is expected. */ - - if (anchor) { - if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; - anchor_copy = yaml_strdup(anchor); - if (!anchor_copy) goto error; - } - - if (tag) { - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - } - - if (length < 0) { - length = strlen((char *)value); - } - - if (!yaml_check_utf8(value, length)) goto error; - value_copy = yaml_malloc(length+1); - if (!value_copy) goto error; - memcpy(value_copy, value, length); - value_copy[length] = '\0'; - - SCALAR_EVENT_INIT(*event, anchor_copy, tag_copy, value_copy, length, - plain_implicit, quoted_implicit, style, mark, mark); - - return 1; - -error: - yaml_free(anchor_copy); - yaml_free(tag_copy); - yaml_free(value_copy); - - return 0; -} - -/* - * Create SEQUENCE-START. - */ - -YAML_DECLARE(int) -yaml_sequence_start_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, int implicit, - yaml_sequence_style_t style) -{ - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *anchor_copy = NULL; - yaml_char_t *tag_copy = NULL; - - assert(event); /* Non-NULL event object is expected. */ - - if (anchor) { - if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; - anchor_copy = yaml_strdup(anchor); - if (!anchor_copy) goto error; - } - - if (tag) { - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - } - - SEQUENCE_START_EVENT_INIT(*event, anchor_copy, tag_copy, - implicit, style, mark, mark); - - return 1; - -error: - yaml_free(anchor_copy); - yaml_free(tag_copy); - - return 0; -} - -/* - * Create SEQUENCE-END. - */ - -YAML_DECLARE(int) -yaml_sequence_end_event_initialize(yaml_event_t *event) -{ - yaml_mark_t mark = { 0, 0, 0 }; - - assert(event); /* Non-NULL event object is expected. */ - - SEQUENCE_END_EVENT_INIT(*event, mark, mark); - - return 1; -} - -/* - * Create MAPPING-START. - */ - -YAML_DECLARE(int) -yaml_mapping_start_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, int implicit, - yaml_mapping_style_t style) -{ - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *anchor_copy = NULL; - yaml_char_t *tag_copy = NULL; - - assert(event); /* Non-NULL event object is expected. */ - - if (anchor) { - if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; - anchor_copy = yaml_strdup(anchor); - if (!anchor_copy) goto error; - } - - if (tag) { - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - } - - MAPPING_START_EVENT_INIT(*event, anchor_copy, tag_copy, - implicit, style, mark, mark); - - return 1; - -error: - yaml_free(anchor_copy); - yaml_free(tag_copy); - - return 0; -} - -/* - * Create MAPPING-END. - */ - -YAML_DECLARE(int) -yaml_mapping_end_event_initialize(yaml_event_t *event) -{ - yaml_mark_t mark = { 0, 0, 0 }; - - assert(event); /* Non-NULL event object is expected. */ - - MAPPING_END_EVENT_INIT(*event, mark, mark); - - return 1; -} - -/* - * Destroy an event object. - */ - -YAML_DECLARE(void) -yaml_event_delete(yaml_event_t *event) -{ - yaml_tag_directive_t *tag_directive; - - assert(event); /* Non-NULL event object expected. */ - - switch (event->type) - { - case YAML_DOCUMENT_START_EVENT: - yaml_free(event->data.document_start.version_directive); - for (tag_directive = event->data.document_start.tag_directives.start; - tag_directive != event->data.document_start.tag_directives.end; - tag_directive++) { - yaml_free(tag_directive->handle); - yaml_free(tag_directive->prefix); - } - yaml_free(event->data.document_start.tag_directives.start); - break; - - case YAML_ALIAS_EVENT: - yaml_free(event->data.alias.anchor); - break; - - case YAML_SCALAR_EVENT: - yaml_free(event->data.scalar.anchor); - yaml_free(event->data.scalar.tag); - yaml_free(event->data.scalar.value); - break; - - case YAML_SEQUENCE_START_EVENT: - yaml_free(event->data.sequence_start.anchor); - yaml_free(event->data.sequence_start.tag); - break; - - case YAML_MAPPING_START_EVENT: - yaml_free(event->data.mapping_start.anchor); - yaml_free(event->data.mapping_start.tag); - break; - - default: - break; - } - - memset(event, 0, sizeof(yaml_event_t)); -} - -/* - * Create a document object. - */ - -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) -{ - struct { - yaml_error_type_t error; - } context; - struct { - yaml_node_t *start; - yaml_node_t *end; - yaml_node_t *top; - } nodes = { NULL, NULL, NULL }; - yaml_version_directive_t *version_directive_copy = NULL; - struct { - yaml_tag_directive_t *start; - yaml_tag_directive_t *end; - yaml_tag_directive_t *top; - } tag_directives_copy = { NULL, NULL, NULL }; - yaml_tag_directive_t value = { NULL, NULL }; - yaml_mark_t mark = { 0, 0, 0 }; - - assert(document); /* Non-NULL document object is expected. */ - assert((tag_directives_start && tag_directives_end) || - (tag_directives_start == tag_directives_end)); - /* Valid tag directives are expected. */ - - if (!STACK_INIT(&context, nodes, INITIAL_STACK_SIZE)) goto error; - - if (version_directive) { - version_directive_copy = yaml_malloc(sizeof(yaml_version_directive_t)); - if (!version_directive_copy) goto error; - version_directive_copy->major = version_directive->major; - version_directive_copy->minor = version_directive->minor; - } - - if (tag_directives_start != tag_directives_end) { - yaml_tag_directive_t *tag_directive; - if (!STACK_INIT(&context, tag_directives_copy, INITIAL_STACK_SIZE)) - goto error; - for (tag_directive = tag_directives_start; - tag_directive != tag_directives_end; tag_directive ++) { - assert(tag_directive->handle); - assert(tag_directive->prefix); - if (!yaml_check_utf8(tag_directive->handle, - strlen((char *)tag_directive->handle))) - goto error; - if (!yaml_check_utf8(tag_directive->prefix, - strlen((char *)tag_directive->prefix))) - goto error; - value.handle = yaml_strdup(tag_directive->handle); - value.prefix = yaml_strdup(tag_directive->prefix); - if (!value.handle || !value.prefix) goto error; - if (!PUSH(&context, tag_directives_copy, value)) - goto error; - value.handle = NULL; - value.prefix = NULL; - } - } - - DOCUMENT_INIT(*document, nodes.start, nodes.end, version_directive_copy, - tag_directives_copy.start, tag_directives_copy.top, - start_implicit, end_implicit, mark, mark); - - return 1; - -error: - STACK_DEL(&context, nodes); - yaml_free(version_directive_copy); - while (!STACK_EMPTY(&context, tag_directives_copy)) { - yaml_tag_directive_t value = POP(&context, tag_directives_copy); - yaml_free(value.handle); - yaml_free(value.prefix); - } - STACK_DEL(&context, tag_directives_copy); - yaml_free(value.handle); - yaml_free(value.prefix); - - return 0; -} - -/* - * Destroy a document object. - */ - -YAML_DECLARE(void) -yaml_document_delete(yaml_document_t *document) -{ - struct { - yaml_error_type_t error; - } context; - yaml_tag_directive_t *tag_directive; - - context.error = YAML_NO_ERROR; /* Eliminate a compliler warning. */ - - assert(document); /* Non-NULL document object is expected. */ - - while (!STACK_EMPTY(&context, document->nodes)) { - yaml_node_t node = POP(&context, document->nodes); - yaml_free(node.tag); - switch (node.type) { - case YAML_SCALAR_NODE: - yaml_free(node.data.scalar.value); - break; - case YAML_SEQUENCE_NODE: - STACK_DEL(&context, node.data.sequence.items); - break; - case YAML_MAPPING_NODE: - STACK_DEL(&context, node.data.mapping.pairs); - break; - default: - assert(0); /* Should not happen. */ - } - } - STACK_DEL(&context, document->nodes); - - yaml_free(document->version_directive); - for (tag_directive = document->tag_directives.start; - tag_directive != document->tag_directives.end; - tag_directive++) { - yaml_free(tag_directive->handle); - yaml_free(tag_directive->prefix); - } - yaml_free(document->tag_directives.start); - - memset(document, 0, sizeof(yaml_document_t)); -} - -/** - * Get a document node. - */ - -YAML_DECLARE(yaml_node_t *) -yaml_document_get_node(yaml_document_t *document, int index) -{ - assert(document); /* Non-NULL document object is expected. */ - - if (index > 0 && document->nodes.start + index <= document->nodes.top) { - return document->nodes.start + index - 1; - } - return NULL; -} - -/** - * Get the root object. - */ - -YAML_DECLARE(yaml_node_t *) -yaml_document_get_root_node(yaml_document_t *document) -{ - assert(document); /* Non-NULL document object is expected. */ - - if (document->nodes.top != document->nodes.start) { - return document->nodes.start; - } - return NULL; -} - -/* - * Add a scalar node to a document. - */ - -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) -{ - struct { - yaml_error_type_t error; - } context; - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *tag_copy = NULL; - yaml_char_t *value_copy = NULL; - yaml_node_t node; - - assert(document); /* Non-NULL document object is expected. */ - assert(value); /* Non-NULL value is expected. */ - - if (!tag) { - tag = (yaml_char_t *)YAML_DEFAULT_SCALAR_TAG; - } - - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - - if (length < 0) { - length = strlen((char *)value); - } - - if (!yaml_check_utf8(value, length)) goto error; - value_copy = yaml_malloc(length+1); - if (!value_copy) goto error; - memcpy(value_copy, value, length); - value_copy[length] = '\0'; - - SCALAR_NODE_INIT(node, tag_copy, value_copy, length, style, mark, mark); - if (!PUSH(&context, document->nodes, node)) goto error; - - return document->nodes.top - document->nodes.start; - -error: - yaml_free(tag_copy); - yaml_free(value_copy); - - return 0; -} - -/* - * Add a sequence node to a document. - */ - -YAML_DECLARE(int) -yaml_document_add_sequence(yaml_document_t *document, - yaml_char_t *tag, yaml_sequence_style_t style) -{ - struct { - yaml_error_type_t error; - } context; - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *tag_copy = NULL; - struct { - yaml_node_item_t *start; - yaml_node_item_t *end; - yaml_node_item_t *top; - } items = { NULL, NULL, NULL }; - yaml_node_t node; - - assert(document); /* Non-NULL document object is expected. */ - - if (!tag) { - tag = (yaml_char_t *)YAML_DEFAULT_SEQUENCE_TAG; - } - - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - - if (!STACK_INIT(&context, items, INITIAL_STACK_SIZE)) goto error; - - SEQUENCE_NODE_INIT(node, tag_copy, items.start, items.end, - style, mark, mark); - if (!PUSH(&context, document->nodes, node)) goto error; - - return document->nodes.top - document->nodes.start; - -error: - STACK_DEL(&context, items); - yaml_free(tag_copy); - - return 0; -} - -/* - * Add a mapping node to a document. - */ - -YAML_DECLARE(int) -yaml_document_add_mapping(yaml_document_t *document, - yaml_char_t *tag, yaml_mapping_style_t style) -{ - struct { - yaml_error_type_t error; - } context; - yaml_mark_t mark = { 0, 0, 0 }; - yaml_char_t *tag_copy = NULL; - struct { - yaml_node_pair_t *start; - yaml_node_pair_t *end; - yaml_node_pair_t *top; - } pairs = { NULL, NULL, NULL }; - yaml_node_t node; - - assert(document); /* Non-NULL document object is expected. */ - - if (!tag) { - tag = (yaml_char_t *)YAML_DEFAULT_MAPPING_TAG; - } - - if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; - tag_copy = yaml_strdup(tag); - if (!tag_copy) goto error; - - if (!STACK_INIT(&context, pairs, INITIAL_STACK_SIZE)) goto error; - - MAPPING_NODE_INIT(node, tag_copy, pairs.start, pairs.end, - style, mark, mark); - if (!PUSH(&context, document->nodes, node)) goto error; - - return document->nodes.top - document->nodes.start; - -error: - STACK_DEL(&context, pairs); - yaml_free(tag_copy); - - return 0; -} - -/* - * Append an item to a sequence node. - */ - -YAML_DECLARE(int) -yaml_document_append_sequence_item(yaml_document_t *document, - int sequence, int item) -{ - struct { - yaml_error_type_t error; - } context; - - assert(document); /* Non-NULL document is required. */ - assert(sequence > 0 - && document->nodes.start + sequence <= document->nodes.top); - /* Valid sequence id is required. */ - assert(document->nodes.start[sequence-1].type == YAML_SEQUENCE_NODE); - /* A sequence node is required. */ - assert(item > 0 && document->nodes.start + item <= document->nodes.top); - /* Valid item id is required. */ - - if (!PUSH(&context, - document->nodes.start[sequence-1].data.sequence.items, item)) - return 0; - - return 1; -} - -/* - * Append a pair of a key and a value to a mapping node. - */ - -YAML_DECLARE(int) -yaml_document_append_mapping_pair(yaml_document_t *document, - int mapping, int key, int value) -{ - struct { - yaml_error_type_t error; - } context; - - yaml_node_pair_t pair; - - assert(document); /* Non-NULL document is required. */ - assert(mapping > 0 - && document->nodes.start + mapping <= document->nodes.top); - /* Valid mapping id is required. */ - assert(document->nodes.start[mapping-1].type == YAML_MAPPING_NODE); - /* A mapping node is required. */ - assert(key > 0 && document->nodes.start + key <= document->nodes.top); - /* Valid key id is required. */ - assert(value > 0 && document->nodes.start + value <= document->nodes.top); - /* Valid value id is required. */ - - pair.key = key; - pair.value = value; - - if (!PUSH(&context, - document->nodes.start[mapping-1].data.mapping.pairs, pair)) - return 0; - - return 1; -} - -
diff --git a/apic.go b/apic.go new file mode 100644 index 0000000..ded1b99 --- /dev/null +++ b/apic.go
@@ -0,0 +1,742 @@ +package goyaml + +import ( + "io" + "os" +) + +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) { + copy(parser.tokens, parser.tokens[parser.tokens_head:]) + } + parser.tokens = parser.tokens[:len(parser.tokens)-parser.tokens_head] + parser.tokens_head = 0 + } + 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[parser.tokens_head+pos] = *token +} + +// Create a new parser object. +func yaml_parser_initialize(parser *yaml_parser_t) bool { + *parser = yaml_parser_t{ + raw_buffer: make([]byte, 0, input_raw_buffer_size), + buffer: make([]byte, 0, input_buffer_size), + } + return true +} + +// Destroy a parser object. +func yaml_parser_delete(parser *yaml_parser_t) { + *parser = yaml_parser_t{} +} + +// String read handler. +func yaml_string_read_handler(parser *yaml_parser_t, buffer []byte) (n int, err error) { + if parser.input_pos == len(parser.input) { + return 0, io.EOF + } + n = copy(buffer, parser.input[parser.input_pos:]) + parser.input_pos += n + return n, nil +} + +// File read handler. +func yaml_file_read_handler(parser *yaml_parser_t, buffer []byte) (n int, err error) { + return parser.input_file.Read(buffer) +} + +// Set a string input. +func yaml_parser_set_input_string(parser *yaml_parser_t, input []byte) { + if parser.read_handler != nil { + panic("must set the input source only once") + } + parser.read_handler = yaml_string_read_handler + parser.input = input + parser.input_pos = 0 +} + +// Set a file input. +func yaml_parser_set_input_file(parser *yaml_parser_t, file *os.File) { + if parser.read_handler != nil { + panic("must set the input source only once") + } + parser.read_handler = yaml_file_read_handler + parser.input_file = file +} + +// Set the source encoding. +func yaml_parser_set_encoding(parser *yaml_parser_t, encoding yaml_encoding_t) { + if parser.encoding != yaml_ANY_ENCODING { + panic("must set the encoding only once") + } + parser.encoding = encoding +} + +// Create a new emitter object. +func yaml_emitter_initialize(emitter *yaml_emitter_t) bool { + *emitter = yaml_emitter_t{ + buffer: make([]byte, output_buffer_size), + raw_buffer: make([]byte, 0, output_raw_buffer_size), + states: make([]yaml_emitter_state_t, 0, initial_stack_size), + events: make([]yaml_event_t, 0, initial_queue_size), + } + return true +} + +// Destroy an emitter object. +func yaml_emitter_delete(emitter *yaml_emitter_t) { + *emitter = yaml_emitter_t{} +} + +// String write handler. +func yaml_string_write_handler(emitter *yaml_emitter_t, buffer []byte) error { + *emitter.output_buffer = append(*emitter.output_buffer, buffer...) + return nil +} + +// File write handler. +func yaml_file_write_handler(emitter *yaml_emitter_t, buffer []byte) error { + _, err := emitter.output_file.Write(buffer) + return err +} + +// Set a string output. +func yaml_emitter_set_output_string(emitter *yaml_emitter_t, output_buffer *[]byte) { + if emitter.write_handler != nil { + panic("must set the output target only once") + } + emitter.write_handler = yaml_string_write_handler + emitter.output_buffer = output_buffer +} + +// Set a file output. +func yaml_emitter_set_output_file(emitter *yaml_emitter_t, file io.Writer) { + if emitter.write_handler != nil { + panic("must set the output target only once") + } + emitter.write_handler = yaml_file_write_handler + emitter.output_file = file +} + +// Set the output encoding. +func yaml_emitter_set_encoding(emitter *yaml_emitter_t, encoding yaml_encoding_t) { + if emitter.encoding != yaml_ANY_ENCODING { + panic("must set the output encoding only once") + } + emitter.encoding = encoding +} + +// Set the canonical output style. +func yaml_emitter_set_canonical(emitter *yaml_emitter_t, canonical bool) { + emitter.canonical = canonical +} + +//// Set the indentation increment. +func yaml_emitter_set_indent(emitter *yaml_emitter_t, indent int) { + if indent < 2 || indent > 9 { + indent = 2 + } + emitter.best_indent = indent +} + +// Set the preferred line width. +func yaml_emitter_set_width(emitter *yaml_emitter_t, width int) { + if width < 0 { + width = -1 + } + emitter.best_width = width +} + +// Set if unescaped non-ASCII characters are allowed. +func yaml_emitter_set_unicode(emitter *yaml_emitter_t, unicode bool) { + emitter.unicode = unicode +} + +// Set the preferred line break character. +func yaml_emitter_set_break(emitter *yaml_emitter_t, line_break yaml_break_t) { + emitter.line_break = line_break +} + +///* +// * Destroy a token object. +// */ +// +//YAML_DECLARE(void) +//yaml_token_delete(yaml_token_t *token) +//{ +// assert(token); // Non-NULL token object expected. +// +// switch (token.type) +// { +// case YAML_TAG_DIRECTIVE_TOKEN: +// yaml_free(token.data.tag_directive.handle); +// yaml_free(token.data.tag_directive.prefix); +// break; +// +// case YAML_ALIAS_TOKEN: +// yaml_free(token.data.alias.value); +// break; +// +// case YAML_ANCHOR_TOKEN: +// yaml_free(token.data.anchor.value); +// break; +// +// case YAML_TAG_TOKEN: +// yaml_free(token.data.tag.handle); +// yaml_free(token.data.tag.suffix); +// break; +// +// case YAML_SCALAR_TOKEN: +// yaml_free(token.data.scalar.value); +// break; +// +// default: +// break; +// } +// +// memset(token, 0, sizeof(yaml_token_t)); +//} +// +///* +// * Check if a string is a valid UTF-8 sequence. +// * +// * Check 'reader.c' for more details on UTF-8 encoding. +// */ +// +//static int +//yaml_check_utf8(yaml_char_t *start, size_t length) +//{ +// yaml_char_t *end = start+length; +// yaml_char_t *pointer = start; +// +// while (pointer < end) { +// unsigned char octet; +// unsigned int width; +// unsigned int value; +// size_t k; +// +// octet = pointer[0]; +// width = (octet & 0x80) == 0x00 ? 1 : +// (octet & 0xE0) == 0xC0 ? 2 : +// (octet & 0xF0) == 0xE0 ? 3 : +// (octet & 0xF8) == 0xF0 ? 4 : 0; +// value = (octet & 0x80) == 0x00 ? octet & 0x7F : +// (octet & 0xE0) == 0xC0 ? octet & 0x1F : +// (octet & 0xF0) == 0xE0 ? octet & 0x0F : +// (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; +// if (!width) return 0; +// if (pointer+width > end) return 0; +// for (k = 1; k < width; k ++) { +// octet = pointer[k]; +// if ((octet & 0xC0) != 0x80) return 0; +// value = (value << 6) + (octet & 0x3F); +// } +// if (!((width == 1) || +// (width == 2 && value >= 0x80) || +// (width == 3 && value >= 0x800) || +// (width == 4 && value >= 0x10000))) return 0; +// +// pointer += width; +// } +// +// return 1; +//} +// + +// Create STREAM-START. +func yaml_stream_start_event_initialize(event *yaml_event_t, encoding yaml_encoding_t) bool { + *event = yaml_event_t{ + typ: yaml_STREAM_START_EVENT, + encoding: encoding, + } + return true +} + +// Create STREAM-END. +func yaml_stream_end_event_initialize(event *yaml_event_t) bool { + *event = yaml_event_t{ + typ: yaml_STREAM_END_EVENT, + } + return true +} + +// Create DOCUMENT-START. +func yaml_document_start_event_initialize(event *yaml_event_t, version_directive *yaml_version_directive_t, + tag_directives []yaml_tag_directive_t, implicit bool) bool { + *event = yaml_event_t{ + typ: yaml_DOCUMENT_START_EVENT, + version_directive: version_directive, + tag_directives: tag_directives, + implicit: implicit, + } + return true +} + +// Create DOCUMENT-END. +func yaml_document_end_event_initialize(event *yaml_event_t, implicit bool) bool { + *event = yaml_event_t{ + typ: yaml_DOCUMENT_END_EVENT, + implicit: implicit, + } + return true +} + +///* +// * Create ALIAS. +// */ +// +//YAML_DECLARE(int) +//yaml_alias_event_initialize(event *yaml_event_t, anchor *yaml_char_t) +//{ +// mark yaml_mark_t = { 0, 0, 0 } +// anchor_copy *yaml_char_t = NULL +// +// assert(event) // Non-NULL event object is expected. +// assert(anchor) // Non-NULL anchor is expected. +// +// if (!yaml_check_utf8(anchor, strlen((char *)anchor))) return 0 +// +// anchor_copy = yaml_strdup(anchor) +// if (!anchor_copy) +// return 0 +// +// ALIAS_EVENT_INIT(*event, anchor_copy, mark, mark) +// +// return 1 +//} + +// Create SCALAR. +func yaml_scalar_event_initialize(event *yaml_event_t, anchor, tag, value []byte, plain_implicit, quoted_implicit bool, style yaml_scalar_style_t) bool { + *event = yaml_event_t{ + typ: yaml_SCALAR_EVENT, + anchor: anchor, + tag: tag, + value: value, + implicit: plain_implicit, + quoted_implicit: quoted_implicit, + style: yaml_style_t(style), + } + return true +} + +// Create SEQUENCE-START. +func yaml_sequence_start_event_initialize(event *yaml_event_t, anchor, tag []byte, implicit bool, style yaml_sequence_style_t) bool { + *event = yaml_event_t{ + typ: yaml_SEQUENCE_START_EVENT, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(style), + } + return true +} + +// Create SEQUENCE-END. +func yaml_sequence_end_event_initialize(event *yaml_event_t) bool { + *event = yaml_event_t{ + typ: yaml_SEQUENCE_END_EVENT, + } + return true +} + +// Create MAPPING-START. +func yaml_mapping_start_event_initialize(event *yaml_event_t, anchor, tag []byte, implicit bool, style yaml_mapping_style_t) bool { + *event = yaml_event_t{ + typ: yaml_MAPPING_START_EVENT, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(style), + } + return true +} + +// Create MAPPING-END. +func yaml_mapping_end_event_initialize(event *yaml_event_t) bool { + *event = yaml_event_t{ + typ: yaml_MAPPING_END_EVENT, + } + return true +} + +// Destroy an event object. +func yaml_event_delete(event *yaml_event_t) { + *event = yaml_event_t{} +} + +///* +// * Create a document object. +// */ +// +//YAML_DECLARE(int) +//yaml_document_initialize(document *yaml_document_t, +// version_directive *yaml_version_directive_t, +// tag_directives_start *yaml_tag_directive_t, +// tag_directives_end *yaml_tag_directive_t, +// start_implicit int, end_implicit int) +//{ +// struct { +// error yaml_error_type_t +// } context +// struct { +// start *yaml_node_t +// end *yaml_node_t +// top *yaml_node_t +// } nodes = { NULL, NULL, NULL } +// version_directive_copy *yaml_version_directive_t = NULL +// struct { +// start *yaml_tag_directive_t +// end *yaml_tag_directive_t +// top *yaml_tag_directive_t +// } tag_directives_copy = { NULL, NULL, NULL } +// value yaml_tag_directive_t = { NULL, NULL } +// mark yaml_mark_t = { 0, 0, 0 } +// +// assert(document) // Non-NULL document object is expected. +// assert((tag_directives_start && tag_directives_end) || +// (tag_directives_start == tag_directives_end)) +// // Valid tag directives are expected. +// +// if (!STACK_INIT(&context, nodes, INITIAL_STACK_SIZE)) goto error +// +// if (version_directive) { +// version_directive_copy = yaml_malloc(sizeof(yaml_version_directive_t)) +// if (!version_directive_copy) goto error +// version_directive_copy.major = version_directive.major +// version_directive_copy.minor = version_directive.minor +// } +// +// if (tag_directives_start != tag_directives_end) { +// tag_directive *yaml_tag_directive_t +// if (!STACK_INIT(&context, tag_directives_copy, INITIAL_STACK_SIZE)) +// goto error +// for (tag_directive = tag_directives_start +// tag_directive != tag_directives_end; tag_directive ++) { +// assert(tag_directive.handle) +// assert(tag_directive.prefix) +// if (!yaml_check_utf8(tag_directive.handle, +// strlen((char *)tag_directive.handle))) +// goto error +// if (!yaml_check_utf8(tag_directive.prefix, +// strlen((char *)tag_directive.prefix))) +// goto error +// value.handle = yaml_strdup(tag_directive.handle) +// value.prefix = yaml_strdup(tag_directive.prefix) +// if (!value.handle || !value.prefix) goto error +// if (!PUSH(&context, tag_directives_copy, value)) +// goto error +// value.handle = NULL +// value.prefix = NULL +// } +// } +// +// DOCUMENT_INIT(*document, nodes.start, nodes.end, version_directive_copy, +// tag_directives_copy.start, tag_directives_copy.top, +// start_implicit, end_implicit, mark, mark) +// +// return 1 +// +//error: +// STACK_DEL(&context, nodes) +// yaml_free(version_directive_copy) +// while (!STACK_EMPTY(&context, tag_directives_copy)) { +// value yaml_tag_directive_t = POP(&context, tag_directives_copy) +// yaml_free(value.handle) +// yaml_free(value.prefix) +// } +// STACK_DEL(&context, tag_directives_copy) +// yaml_free(value.handle) +// yaml_free(value.prefix) +// +// return 0 +//} +// +///* +// * Destroy a document object. +// */ +// +//YAML_DECLARE(void) +//yaml_document_delete(document *yaml_document_t) +//{ +// struct { +// error yaml_error_type_t +// } context +// tag_directive *yaml_tag_directive_t +// +// context.error = YAML_NO_ERROR // Eliminate a compliler warning. +// +// assert(document) // Non-NULL document object is expected. +// +// while (!STACK_EMPTY(&context, document.nodes)) { +// node yaml_node_t = POP(&context, document.nodes) +// yaml_free(node.tag) +// switch (node.type) { +// case YAML_SCALAR_NODE: +// yaml_free(node.data.scalar.value) +// break +// case YAML_SEQUENCE_NODE: +// STACK_DEL(&context, node.data.sequence.items) +// break +// case YAML_MAPPING_NODE: +// STACK_DEL(&context, node.data.mapping.pairs) +// break +// default: +// assert(0) // Should not happen. +// } +// } +// STACK_DEL(&context, document.nodes) +// +// yaml_free(document.version_directive) +// for (tag_directive = document.tag_directives.start +// tag_directive != document.tag_directives.end +// tag_directive++) { +// yaml_free(tag_directive.handle) +// yaml_free(tag_directive.prefix) +// } +// yaml_free(document.tag_directives.start) +// +// memset(document, 0, sizeof(yaml_document_t)) +//} +// +///** +// * Get a document node. +// */ +// +//YAML_DECLARE(yaml_node_t *) +//yaml_document_get_node(document *yaml_document_t, index int) +//{ +// assert(document) // Non-NULL document object is expected. +// +// if (index > 0 && document.nodes.start + index <= document.nodes.top) { +// return document.nodes.start + index - 1 +// } +// return NULL +//} +// +///** +// * Get the root object. +// */ +// +//YAML_DECLARE(yaml_node_t *) +//yaml_document_get_root_node(document *yaml_document_t) +//{ +// assert(document) // Non-NULL document object is expected. +// +// if (document.nodes.top != document.nodes.start) { +// return document.nodes.start +// } +// return NULL +//} +// +///* +// * Add a scalar node to a document. +// */ +// +//YAML_DECLARE(int) +//yaml_document_add_scalar(document *yaml_document_t, +// tag *yaml_char_t, value *yaml_char_t, length int, +// style yaml_scalar_style_t) +//{ +// struct { +// error yaml_error_type_t +// } context +// mark yaml_mark_t = { 0, 0, 0 } +// tag_copy *yaml_char_t = NULL +// value_copy *yaml_char_t = NULL +// node yaml_node_t +// +// assert(document) // Non-NULL document object is expected. +// assert(value) // Non-NULL value is expected. +// +// if (!tag) { +// tag = (yaml_char_t *)YAML_DEFAULT_SCALAR_TAG +// } +// +// if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error +// tag_copy = yaml_strdup(tag) +// if (!tag_copy) goto error +// +// if (length < 0) { +// length = strlen((char *)value) +// } +// +// if (!yaml_check_utf8(value, length)) goto error +// value_copy = yaml_malloc(length+1) +// if (!value_copy) goto error +// memcpy(value_copy, value, length) +// value_copy[length] = '\0' +// +// SCALAR_NODE_INIT(node, tag_copy, value_copy, length, style, mark, mark) +// if (!PUSH(&context, document.nodes, node)) goto error +// +// return document.nodes.top - document.nodes.start +// +//error: +// yaml_free(tag_copy) +// yaml_free(value_copy) +// +// return 0 +//} +// +///* +// * Add a sequence node to a document. +// */ +// +//YAML_DECLARE(int) +//yaml_document_add_sequence(document *yaml_document_t, +// tag *yaml_char_t, style yaml_sequence_style_t) +//{ +// struct { +// error yaml_error_type_t +// } context +// mark yaml_mark_t = { 0, 0, 0 } +// tag_copy *yaml_char_t = NULL +// struct { +// start *yaml_node_item_t +// end *yaml_node_item_t +// top *yaml_node_item_t +// } items = { NULL, NULL, NULL } +// node yaml_node_t +// +// assert(document) // Non-NULL document object is expected. +// +// if (!tag) { +// tag = (yaml_char_t *)YAML_DEFAULT_SEQUENCE_TAG +// } +// +// if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error +// tag_copy = yaml_strdup(tag) +// if (!tag_copy) goto error +// +// if (!STACK_INIT(&context, items, INITIAL_STACK_SIZE)) goto error +// +// SEQUENCE_NODE_INIT(node, tag_copy, items.start, items.end, +// style, mark, mark) +// if (!PUSH(&context, document.nodes, node)) goto error +// +// return document.nodes.top - document.nodes.start +// +//error: +// STACK_DEL(&context, items) +// yaml_free(tag_copy) +// +// return 0 +//} +// +///* +// * Add a mapping node to a document. +// */ +// +//YAML_DECLARE(int) +//yaml_document_add_mapping(document *yaml_document_t, +// tag *yaml_char_t, style yaml_mapping_style_t) +//{ +// struct { +// error yaml_error_type_t +// } context +// mark yaml_mark_t = { 0, 0, 0 } +// tag_copy *yaml_char_t = NULL +// struct { +// start *yaml_node_pair_t +// end *yaml_node_pair_t +// top *yaml_node_pair_t +// } pairs = { NULL, NULL, NULL } +// node yaml_node_t +// +// assert(document) // Non-NULL document object is expected. +// +// if (!tag) { +// tag = (yaml_char_t *)YAML_DEFAULT_MAPPING_TAG +// } +// +// if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error +// tag_copy = yaml_strdup(tag) +// if (!tag_copy) goto error +// +// if (!STACK_INIT(&context, pairs, INITIAL_STACK_SIZE)) goto error +// +// MAPPING_NODE_INIT(node, tag_copy, pairs.start, pairs.end, +// style, mark, mark) +// if (!PUSH(&context, document.nodes, node)) goto error +// +// return document.nodes.top - document.nodes.start +// +//error: +// STACK_DEL(&context, pairs) +// yaml_free(tag_copy) +// +// return 0 +//} +// +///* +// * Append an item to a sequence node. +// */ +// +//YAML_DECLARE(int) +//yaml_document_append_sequence_item(document *yaml_document_t, +// sequence int, item int) +//{ +// struct { +// error yaml_error_type_t +// } context +// +// assert(document) // Non-NULL document is required. +// assert(sequence > 0 +// && document.nodes.start + sequence <= document.nodes.top) +// // Valid sequence id is required. +// assert(document.nodes.start[sequence-1].type == YAML_SEQUENCE_NODE) +// // A sequence node is required. +// assert(item > 0 && document.nodes.start + item <= document.nodes.top) +// // Valid item id is required. +// +// if (!PUSH(&context, +// document.nodes.start[sequence-1].data.sequence.items, item)) +// return 0 +// +// return 1 +//} +// +///* +// * Append a pair of a key and a value to a mapping node. +// */ +// +//YAML_DECLARE(int) +//yaml_document_append_mapping_pair(document *yaml_document_t, +// mapping int, key int, value int) +//{ +// struct { +// error yaml_error_type_t +// } context +// +// pair yaml_node_pair_t +// +// assert(document) // Non-NULL document is required. +// assert(mapping > 0 +// && document.nodes.start + mapping <= document.nodes.top) +// // Valid mapping id is required. +// assert(document.nodes.start[mapping-1].type == YAML_MAPPING_NODE) +// // A mapping node is required. +// assert(key > 0 && document.nodes.start + key <= document.nodes.top) +// // Valid key id is required. +// assert(value > 0 && document.nodes.start + value <= document.nodes.top) +// // Valid value id is required. +// +// pair.key = key +// pair.value = value +// +// if (!PUSH(&context, +// document.nodes.start[mapping-1].data.mapping.pairs, pair)) +// return 0 +// +// return 1 +//} +// +//
diff --git a/config.h b/config.h deleted file mode 100644 index 6a3d605..0000000 --- a/config.h +++ /dev/null
@@ -1,4 +0,0 @@ -#define YAML_VERSION_STRING "0.1.3" -#define YAML_VERSION_MAJOR 0 -#define YAML_VERSION_MINOR 1 -#define YAML_VERSION_PATCH 3
diff --git a/decode.go b/decode.go index b03f36e..e7fb29b 100644 --- a/decode.go +++ b/decode.go
@@ -1,16 +1,8 @@ package goyaml -// #cgo LDFLAGS: -lm -lpthread -// #cgo windows CFLAGS: -DYAML_DECLARE_STATIC=1 -Dstrdup=_strdup -// #cgo CFLAGS: -I. -DHAVE_CONFIG_H=1 -// -// #include "helpers.h" -import "C" - import ( "reflect" "strconv" - "unsafe" ) const ( @@ -31,22 +23,18 @@ anchors map[string]*node } -func stry(s *C.yaml_char_t) string { - return C.GoString((*C.char)(unsafe.Pointer(s))) -} - // ---------------------------------------------------------------------------- // Parser, produces a node tree out of a libyaml event stream. type parser struct { - parser C.yaml_parser_t - event C.yaml_event_t + parser yaml_parser_t + event yaml_event_t doc *node } func newParser(b []byte) *parser { p := parser{} - if C.yaml_parser_initialize(&p.parser) == 0 { + if !yaml_parser_initialize(&p.parser) { panic("Failed to initialize YAML emitter") } @@ -54,35 +42,31 @@ b = []byte{'\n'} } - // How unsafe is this really? Will this break if the GC becomes compacting? - // Probably not, otherwise that would likely break &parse below as well. - input := (*C.uchar)(unsafe.Pointer(&b[0])) - C.yaml_parser_set_input_string(&p.parser, input, (C.size_t)(len(b))) + yaml_parser_set_input_string(&p.parser, b) p.skip() - if p.event._type != C.YAML_STREAM_START_EVENT { - panic("Expected stream start event, got " + - strconv.Itoa(int(p.event._type))) + if p.event.typ != yaml_STREAM_START_EVENT { + panic("Expected stream start event, got " + strconv.Itoa(int(p.event.typ))) } p.skip() return &p } func (p *parser) destroy() { - if p.event._type != C.YAML_NO_EVENT { - C.yaml_event_delete(&p.event) + if p.event.typ != yaml_NO_EVENT { + yaml_event_delete(&p.event) } - C.yaml_parser_delete(&p.parser) + yaml_parser_delete(&p.parser) } func (p *parser) skip() { - if p.event._type != C.YAML_NO_EVENT { - if p.event._type == C.YAML_STREAM_END_EVENT { + if p.event.typ != yaml_NO_EVENT { + if p.event.typ == yaml_STREAM_END_EVENT { panic("Attempted to go past the end of stream. Corrupted value?") } - C.yaml_event_delete(&p.event) + yaml_event_delete(&p.event) } - if C.yaml_parser_parse(&p.parser, &p.event) == 0 { + if !yaml_parser_parse(&p.parser, &p.event) { p.fail() } } @@ -91,54 +75,56 @@ var where string var line int if p.parser.problem_mark.line != 0 { - line = int(C.int(p.parser.problem_mark.line)) + line = p.parser.problem_mark.line } else if p.parser.context_mark.line != 0 { - line = int(C.int(p.parser.context_mark.line)) + line = p.parser.context_mark.line } if line != 0 { where = "line " + strconv.Itoa(line) + ": " } var msg string - if p.parser.problem != nil { - msg = C.GoString(p.parser.problem) + if len(p.parser.problem) > 0 { + msg = p.parser.problem } else { msg = "Unknown problem parsing YAML content" } panic(where + msg) } -func (p *parser) anchor(n *node, anchor *C.yaml_char_t) { +func (p *parser) anchor(n *node, anchor []byte) { if anchor != nil { - p.doc.anchors[stry(anchor)] = n + p.doc.anchors[string(anchor)] = n } } func (p *parser) parse() *node { - switch p.event._type { - case C.YAML_SCALAR_EVENT: + switch p.event.typ { + case yaml_SCALAR_EVENT: return p.scalar() - case C.YAML_ALIAS_EVENT: + case yaml_ALIAS_EVENT: return p.alias() - case C.YAML_MAPPING_START_EVENT: + case yaml_MAPPING_START_EVENT: return p.mapping() - case C.YAML_SEQUENCE_START_EVENT: + case yaml_SEQUENCE_START_EVENT: return p.sequence() - case C.YAML_DOCUMENT_START_EVENT: + case yaml_DOCUMENT_START_EVENT: return p.document() - case C.YAML_STREAM_END_EVENT: + case yaml_STREAM_END_EVENT: // Happens when attempting to decode an empty buffer. return nil default: panic("Attempted to parse unknown event: " + - strconv.Itoa(int(p.event._type))) + strconv.Itoa(int(p.event.typ))) } panic("Unreachable") } func (p *parser) node(kind int) *node { - return &node{kind: kind, - line: int(C.int(p.event.start_mark.line)), - column: int(C.int(p.event.start_mark.column))} + return &node{ + kind: kind, + line: p.event.start_mark.line, + column: p.event.start_mark.column, + } } func (p *parser) document() *node { @@ -147,38 +133,36 @@ p.doc = n p.skip() n.children = append(n.children, p.parse()) - if p.event._type != C.YAML_DOCUMENT_END_EVENT { + if p.event.typ != yaml_DOCUMENT_END_EVENT { panic("Expected end of document event but got " + - strconv.Itoa(int(p.event._type))) + strconv.Itoa(int(p.event.typ))) } p.skip() return n } func (p *parser) alias() *node { - alias := C.event_alias(&p.event) n := p.node(aliasNode) - n.value = stry(alias.anchor) + n.value = string(p.event.anchor) p.skip() return n } func (p *parser) scalar() *node { - scalar := C.event_scalar(&p.event) n := p.node(scalarNode) - n.value = stry(scalar.value) - n.tag = stry(scalar.tag) - n.implicit = (scalar.plain_implicit != 0) - p.anchor(n, scalar.anchor) + n.value = string(p.event.value) + n.tag = string(p.event.tag) + n.implicit = p.event.implicit + p.anchor(n, p.event.anchor) p.skip() return n } func (p *parser) sequence() *node { n := p.node(sequenceNode) - p.anchor(n, C.event_sequence_start(&p.event).anchor) + p.anchor(n, p.event.anchor) p.skip() - for p.event._type != C.YAML_SEQUENCE_END_EVENT { + for p.event.typ != yaml_SEQUENCE_END_EVENT { n.children = append(n.children, p.parse()) } p.skip() @@ -187,9 +171,9 @@ func (p *parser) mapping() *node { n := p.node(mappingNode) - p.anchor(n, C.event_mapping_start(&p.event).anchor) + p.anchor(n, p.event.anchor) p.skip() - for p.event._type != C.YAML_MAPPING_END_EVENT { + for p.event.typ != yaml_MAPPING_END_EVENT { n.children = append(n.children, p.parse(), p.parse()) } p.skip()
diff --git a/decode_test.go b/decode_test.go index 83532f4..89a9fdb 100644 --- a/decode_test.go +++ b/decode_test.go
@@ -13,125 +13,310 @@ data string value interface{} }{ - {"", &struct{}{}}, - {"{}", &struct{}{}}, - - {"v: hi", map[string]string{"v": "hi"}}, - {"v: hi", map[string]interface{}{"v": "hi"}}, - {"v: true", map[string]string{"v": "true"}}, - {"v: true", map[string]interface{}{"v": true}}, - {"v: 10", map[string]interface{}{"v": 10}}, - {"v: 0b10", map[string]interface{}{"v": 2}}, - {"v: 0xA", map[string]interface{}{"v": 10}}, - {"v: 4294967296", map[string]int64{"v": 4294967296}}, - {"v: 0.1", map[string]interface{}{"v": 0.1}}, - {"v: .1", map[string]interface{}{"v": 0.1}}, - {"v: .Inf", map[string]interface{}{"v": math.Inf(+1)}}, - {"v: -.Inf", map[string]interface{}{"v": math.Inf(-1)}}, - {"v: -10", map[string]interface{}{"v": -10}}, - {"v: -.1", map[string]interface{}{"v": -0.1}}, + { + "", + &struct{}{}, + }, { + "{}", &struct{}{}, + }, { + "v: hi", + map[string]string{"v": "hi"}, + }, { + "v: hi", map[string]interface{}{"v": "hi"}, + }, { + "v: true", + map[string]string{"v": "true"}, + }, { + "v: true", + map[string]interface{}{"v": true}, + }, { + "v: 10", + map[string]interface{}{"v": 10}, + }, { + "v: 0b10", + map[string]interface{}{"v": 2}, + }, { + "v: 0xA", + map[string]interface{}{"v": 10}, + }, { + "v: 4294967296", + map[string]int64{"v": 4294967296}, + }, { + "v: 0.1", + map[string]interface{}{"v": 0.1}, + }, { + "v: .1", + map[string]interface{}{"v": 0.1}, + }, { + "v: .Inf", + map[string]interface{}{"v": math.Inf(+1)}, + }, { + "v: -.Inf", + map[string]interface{}{"v": math.Inf(-1)}, + }, { + "v: -10", + map[string]interface{}{"v": -10}, + }, { + "v: -.1", + map[string]interface{}{"v": -0.1}, + }, // Simple values. - {"123", &unmarshalIntTest}, + { + "123", + &unmarshalIntTest, + }, // Floats from spec - {"canonical: 6.8523e+5", map[string]interface{}{"canonical": 6.8523e+5}}, - {"expo: 685.230_15e+03", map[string]interface{}{"expo": 685.23015e+03}}, - {"fixed: 685_230.15", map[string]interface{}{"fixed": 685230.15}}, + { + "canonical: 6.8523e+5", + map[string]interface{}{"canonical": 6.8523e+5}, + }, { + "expo: 685.230_15e+03", + map[string]interface{}{"expo": 685.23015e+03}, + }, { + "fixed: 685_230.15", + map[string]interface{}{"fixed": 685230.15}, + }, { + "neginf: -.inf", + map[string]interface{}{"neginf": math.Inf(-1)}, + }, { + "fixed: 685_230.15", + map[string]float64{"fixed": 685230.15}, + }, //{"sexa: 190:20:30.15", map[string]interface{}{"sexa": 0}}, // Unsupported - {"neginf: -.inf", map[string]interface{}{"neginf": math.Inf(-1)}}, //{"notanum: .NaN", map[string]interface{}{"notanum": math.NaN()}}, // Equality of NaN fails. - {"fixed: 685_230.15", map[string]float64{"fixed": 685230.15}}, // Bools from spec - {"canonical: y", map[string]interface{}{"canonical": true}}, - {"answer: NO", map[string]interface{}{"answer": false}}, - {"logical: True", map[string]interface{}{"logical": true}}, - {"option: on", map[string]interface{}{"option": true}}, - {"option: on", map[string]bool{"option": true}}, - + { + "canonical: y", + map[string]interface{}{"canonical": true}, + }, { + "answer: NO", + map[string]interface{}{"answer": false}, + }, { + "logical: True", + map[string]interface{}{"logical": true}, + }, { + "option: on", + map[string]interface{}{"option": true}, + }, { + "option: on", + map[string]bool{"option": true}, + }, // Ints from spec - {"canonical: 685230", map[string]interface{}{"canonical": 685230}}, - {"decimal: +685_230", map[string]interface{}{"decimal": 685230}}, - {"octal: 02472256", map[string]interface{}{"octal": 685230}}, - {"hexa: 0x_0A_74_AE", map[string]interface{}{"hexa": 685230}}, - {"bin: 0b1010_0111_0100_1010_1110", map[string]interface{}{"bin": 685230}}, - {"bin: -0b101010", map[string]interface{}{"bin": -42}}, + { + "canonical: 685230", + map[string]interface{}{"canonical": 685230}, + }, { + "decimal: +685_230", + map[string]interface{}{"decimal": 685230}, + }, { + "octal: 02472256", + map[string]interface{}{"octal": 685230}, + }, { + "hexa: 0x_0A_74_AE", + map[string]interface{}{"hexa": 685230}, + }, { + "bin: 0b1010_0111_0100_1010_1110", + map[string]interface{}{"bin": 685230}, + }, { + "bin: -0b101010", + map[string]interface{}{"bin": -42}, + }, { + "decimal: +685_230", + map[string]int{"decimal": 685230}, + }, + //{"sexa: 190:20:30", map[string]interface{}{"sexa": 0}}, // Unsupported - {"decimal: +685_230", map[string]int{"decimal": 685230}}, // Nulls from spec - {"empty:", map[string]interface{}{"empty": nil}}, - {"canonical: ~", map[string]interface{}{"canonical": nil}}, - {"english: null", map[string]interface{}{"english": nil}}, - {"~: null key", map[interface{}]string{nil: "null key"}}, - {"empty:", map[string]*bool{"empty": nil}}, + { + "empty:", + map[string]interface{}{"empty": nil}, + }, { + "canonical: ~", + map[string]interface{}{"canonical": nil}, + }, { + "english: null", + map[string]interface{}{"english": nil}, + }, { + "~: null key", + map[interface{}]string{nil: "null key"}, + }, { + "empty:", + map[string]*bool{"empty": nil}, + }, - // 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,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"}}}, + // 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,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"}}}, + { + "a: {b: c}", + map[string]interface{}{"a": map[interface{}]interface{}{"b": "c"}}, + }, // Structs and type conversions. - {"hello: world", &struct{ Hello string }{"world"}}, - {"a: {b: c}", &struct{ A struct{ B string } }{struct{ B string }{"c"}}}, - {"a: {b: c}", &struct{ A *struct{ B string } }{&struct{ B string }{"c"}}}, - {"a: {b: c}", &struct{ A map[string]string }{map[string]string{"b": "c"}}}, - {"a: {b: c}", &struct{ A *map[string]string }{&map[string]string{"b": "c"}}}, - {"a:", &struct{ A map[string]string }{}}, - {"a: 1", &struct{ A int }{1}}, - {"a: [1, 2]", &struct{ A []int }{[]int{1, 2}}}, - {"a: 1", &struct{ B int }{0}}, - {"a: 1", &struct { - B int "a" - }{1}}, - {"a: y", &struct{ A bool }{true}}, + { + "hello: world", + &struct{ Hello string }{"world"}, + }, { + "a: {b: c}", + &struct{ A struct{ B string } }{struct{ B string }{"c"}}, + }, { + "a: {b: c}", + &struct{ A *struct{ B string } }{&struct{ B string }{"c"}}, + }, { + "a: {b: c}", + &struct{ A map[string]string }{map[string]string{"b": "c"}}, + }, { + "a: {b: c}", + &struct{ A *map[string]string }{&map[string]string{"b": "c"}}, + }, { + "a:", + &struct{ A map[string]string }{}, + }, { + "a: 1", + &struct{ A int }{1}, + }, { + "a: [1, 2]", + &struct{ A []int }{[]int{1, 2}}, + }, { + "a: 1", + &struct{ B int }{0}, + }, { + "a: 1", + &struct { + B int "a" + }{1}, + }, { + "a: y", + &struct{ A bool }{true}, + }, // Some cross type conversions - {"v: 42", map[string]uint{"v": 42}}, - {"v: -42", map[string]uint{}}, - {"v: 4294967296", map[string]uint64{"v": 4294967296}}, - {"v: -4294967296", map[string]uint64{}}, + { + "v: 42", + map[string]uint{"v": 42}, + }, { + "v: -42", + map[string]uint{}, + }, { + "v: 4294967296", + map[string]uint64{"v": 4294967296}, + }, { + "v: -4294967296", + map[string]uint64{}, + }, // Overflow cases. - {"v: 4294967297", map[string]int32{}}, - {"v: 128", map[string]int8{}}, + { + "v: 4294967297", + map[string]int32{}, + }, { + "v: 128", + map[string]int8{}, + }, // Quoted values. - {"'1': '\"2\"'", map[interface{}]interface{}{"1": "\"2\""}}, + { + "'1': '\"2\"'", + map[interface{}]interface{}{"1": "\"2\""}, + }, { + "v:\n- A\n- 'B\n\n C'\n", + map[string][]string{"v": []string{"A", "B\nC"}}, + }, // Explicit tags. - {"v: !!float '1.1'", map[string]interface{}{"v": 1.1}}, - {"v: !!null ''", map[string]interface{}{"v": nil}}, - {"%TAG !y! tag:yaml.org,2002:\n---\nv: !y!int '1'", - map[string]interface{}{"v": 1}}, + { + "v: !!float '1.1'", + map[string]interface{}{"v": 1.1}, + }, { + "v: !!null ''", + map[string]interface{}{"v": nil}, + }, { + "%TAG !y! tag:yaml.org,2002:\n---\nv: !y!int '1'", + map[string]interface{}{"v": 1}, + }, // Anchors and aliases. - {"a: &x 1\nb: &y 2\nc: *x\nd: *y\n", &struct{ A, B, C, D int }{1, 2, 1, 2}}, - {"a: &a {c: 1}\nb: *a", + { + "a: &x 1\nb: &y 2\nc: *x\nd: *y\n", + &struct{ A, B, C, D int }{1, 2, 1, 2}, + }, { + "a: &a {c: 1}\nb: *a", &struct { A, B struct { C int } - }{struct{ C int }{1}, struct{ C int }{1}}}, - {"a: &a [1, 2]\nb: *a", &struct{ B []int }{[]int{1, 2}}}, + }{struct{ C int }{1}, struct{ C int }{1}}, + }, { + "a: &a [1, 2]\nb: *a", + &struct{ B []int }{[]int{1, 2}}, + }, // BUG #1133337 - {"foo: ''", map[string]*string{"foo": new(string)}}, - {"foo: null", map[string]string{}}, + { + "foo: ''", + map[string]*string{"foo": new(string)}, + }, { + "foo: null", + map[string]string{}, + }, // Ignored field - {"a: 1\nb: 2\n", + { + "a: 1\nb: 2\n", &struct { A int B int "-" - }{1, 0}}, + }{1, 0}, + }, } func (s *S) TestUnmarshal(c *C) { @@ -251,3 +436,32 @@ c.Assert(m["abc"].value, Equals, 1) c.Assert(m["ghi"].value, Equals, 3) } + +//var data []byte +//func init() { +// var err error +// data, err = ioutil.ReadFile("/tmp/file.yaml") +// if err != nil { +// panic(err) +// } +//} +// +//func (s *S) BenchmarkUnmarshal(c *C) { +// var err error +// for i := 0; i < c.N; i++ { +// var v map[string]interface{} +// err = goyaml.Unmarshal(data, &v) +// } +// if err != nil { +// panic(err) +// } +//} +// +//func (s *S) BenchmarkMarshal(c *C) { +// var v map[string]interface{} +// goyaml.Unmarshal(data, &v) +// c.ResetTimer() +// for i := 0; i < c.N; i++ { +// goyaml.Marshal(&v) +// } +//}
diff --git a/emitter.c b/emitter.c deleted file mode 100644 index c4b56a2..0000000 --- a/emitter.c +++ /dev/null
@@ -1,2329 +0,0 @@ - -#include "yaml_private.h" - -/* - * Flush the buffer if needed. - */ - -#define FLUSH(emitter) \ - ((emitter->buffer.pointer+5 < emitter->buffer.end) \ - || yaml_emitter_flush(emitter)) - -/* - * Put a character to the output buffer. - */ - -#define PUT(emitter,value) \ - (FLUSH(emitter) \ - && (*(emitter->buffer.pointer++) = (yaml_char_t)(value), \ - emitter->column ++, \ - 1)) - -/* - * Put a line break to the output buffer. - */ - -#define PUT_BREAK(emitter) \ - (FLUSH(emitter) \ - && ((emitter->line_break == YAML_CR_BREAK ? \ - (*(emitter->buffer.pointer++) = (yaml_char_t) '\r') : \ - emitter->line_break == YAML_LN_BREAK ? \ - (*(emitter->buffer.pointer++) = (yaml_char_t) '\n') : \ - emitter->line_break == YAML_CRLN_BREAK ? \ - (*(emitter->buffer.pointer++) = (yaml_char_t) '\r', \ - *(emitter->buffer.pointer++) = (yaml_char_t) '\n') : 0), \ - emitter->column = 0, \ - emitter->line ++, \ - 1)) - -/* - * Copy a character from a string into buffer. - */ - -#define WRITE(emitter,string) \ - (FLUSH(emitter) \ - && (COPY(emitter->buffer,string), \ - emitter->column ++, \ - 1)) - -/* - * Copy a line break character from a string into buffer. - */ - -#define WRITE_BREAK(emitter,string) \ - (FLUSH(emitter) \ - && (CHECK(string,'\n') ? \ - (PUT_BREAK(emitter), \ - string.pointer ++, \ - 1) : \ - (COPY(emitter->buffer,string), \ - emitter->column = 0, \ - emitter->line ++, \ - 1))) - -/* - * API functions. - */ - -YAML_DECLARE(int) -yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event); - -/* - * Utility functions. - */ - -static int -yaml_emitter_set_emitter_error(yaml_emitter_t *emitter, const char *problem); - -static int -yaml_emitter_need_more_events(yaml_emitter_t *emitter); - -static int -yaml_emitter_append_tag_directive(yaml_emitter_t *emitter, - yaml_tag_directive_t value, int allow_duplicates); - -static int -yaml_emitter_increase_indent(yaml_emitter_t *emitter, - int flow, int indentless); - -/* - * State functions. - */ - -static int -yaml_emitter_state_machine(yaml_emitter_t *emitter, yaml_event_t *event); - -static int -yaml_emitter_emit_stream_start(yaml_emitter_t *emitter, - yaml_event_t *event); - -static int -yaml_emitter_emit_document_start(yaml_emitter_t *emitter, - yaml_event_t *event, int first); - -static int -yaml_emitter_emit_document_content(yaml_emitter_t *emitter, - yaml_event_t *event); - -static int -yaml_emitter_emit_document_end(yaml_emitter_t *emitter, - yaml_event_t *event); - -static int -yaml_emitter_emit_flow_sequence_item(yaml_emitter_t *emitter, - yaml_event_t *event, int first); - -static int -yaml_emitter_emit_flow_mapping_key(yaml_emitter_t *emitter, - yaml_event_t *event, int first); - -static int -yaml_emitter_emit_flow_mapping_value(yaml_emitter_t *emitter, - yaml_event_t *event, int simple); - -static int -yaml_emitter_emit_block_sequence_item(yaml_emitter_t *emitter, - yaml_event_t *event, int first); - -static int -yaml_emitter_emit_block_mapping_key(yaml_emitter_t *emitter, - yaml_event_t *event, int first); - -static int -yaml_emitter_emit_block_mapping_value(yaml_emitter_t *emitter, - yaml_event_t *event, int simple); - -static int -yaml_emitter_emit_node(yaml_emitter_t *emitter, yaml_event_t *event, - int root, int sequence, int mapping, int simple_key); - -static int -yaml_emitter_emit_alias(yaml_emitter_t *emitter, yaml_event_t *event); - -static int -yaml_emitter_emit_scalar(yaml_emitter_t *emitter, yaml_event_t *event); - -static int -yaml_emitter_emit_sequence_start(yaml_emitter_t *emitter, yaml_event_t *event); - -static int -yaml_emitter_emit_mapping_start(yaml_emitter_t *emitter, yaml_event_t *event); - -/* - * Checkers. - */ - -static int -yaml_emitter_check_empty_document(yaml_emitter_t *emitter); - -static int -yaml_emitter_check_empty_sequence(yaml_emitter_t *emitter); - -static int -yaml_emitter_check_empty_mapping(yaml_emitter_t *emitter); - -static int -yaml_emitter_check_simple_key(yaml_emitter_t *emitter); - -static int -yaml_emitter_select_scalar_style(yaml_emitter_t *emitter, yaml_event_t *event); - -/* - * Processors. - */ - -static int -yaml_emitter_process_anchor(yaml_emitter_t *emitter); - -static int -yaml_emitter_process_tag(yaml_emitter_t *emitter); - -static int -yaml_emitter_process_scalar(yaml_emitter_t *emitter); - -/* - * Analyzers. - */ - -static int -yaml_emitter_analyze_version_directive(yaml_emitter_t *emitter, - yaml_version_directive_t version_directive); - -static int -yaml_emitter_analyze_tag_directive(yaml_emitter_t *emitter, - yaml_tag_directive_t tag_directive); - -static int -yaml_emitter_analyze_anchor(yaml_emitter_t *emitter, - yaml_char_t *anchor, int alias); - -static int -yaml_emitter_analyze_tag(yaml_emitter_t *emitter, - yaml_char_t *tag); - -static int -yaml_emitter_analyze_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length); - -static int -yaml_emitter_analyze_event(yaml_emitter_t *emitter, - yaml_event_t *event); - -/* - * Writers. - */ - -static int -yaml_emitter_write_bom(yaml_emitter_t *emitter); - -static int -yaml_emitter_write_indent(yaml_emitter_t *emitter); - -static int -yaml_emitter_write_indicator(yaml_emitter_t *emitter, - char *indicator, int need_whitespace, - int is_whitespace, int is_indention); - -static int -yaml_emitter_write_anchor(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length); - -static int -yaml_emitter_write_tag_handle(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length); - -static int -yaml_emitter_write_tag_content(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int need_whitespace); - -static int -yaml_emitter_write_plain_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks); - -static int -yaml_emitter_write_single_quoted_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks); - -static int -yaml_emitter_write_double_quoted_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks); - -static int -yaml_emitter_write_block_scalar_hints(yaml_emitter_t *emitter, - yaml_string_t string); - -static int -yaml_emitter_write_literal_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length); - -static int -yaml_emitter_write_folded_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length); - -/* - * Set an emitter error and return 0. - */ - -static int -yaml_emitter_set_emitter_error(yaml_emitter_t *emitter, const char *problem) -{ - emitter->error = YAML_EMITTER_ERROR; - emitter->problem = problem; - - return 0; -} - -/* - * Emit an event. - */ - -YAML_DECLARE(int) -yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event) -{ - if (!ENQUEUE(emitter, emitter->events, *event)) { - yaml_event_delete(event); - return 0; - } - - while (!yaml_emitter_need_more_events(emitter)) { - if (!yaml_emitter_analyze_event(emitter, emitter->events.head)) - return 0; - if (!yaml_emitter_state_machine(emitter, emitter->events.head)) - return 0; - yaml_event_delete(&DEQUEUE(emitter, emitter->events)); - } - - return 1; -} - -/* - * Check if we need to accumulate more events before emitting. - * - * We accumulate extra - * - 1 event for DOCUMENT-START - * - 2 events for SEQUENCE-START - * - 3 events for MAPPING-START - */ - -static int -yaml_emitter_need_more_events(yaml_emitter_t *emitter) -{ - int level = 0; - int accumulate = 0; - yaml_event_t *event; - - if (QUEUE_EMPTY(emitter, emitter->events)) - return 1; - - switch (emitter->events.head->type) { - case YAML_DOCUMENT_START_EVENT: - accumulate = 1; - break; - case YAML_SEQUENCE_START_EVENT: - accumulate = 2; - break; - case YAML_MAPPING_START_EVENT: - accumulate = 3; - break; - default: - return 0; - } - - if (emitter->events.tail - emitter->events.head > accumulate) - return 0; - - for (event = emitter->events.head; event != emitter->events.tail; event ++) { - switch (event->type) { - case YAML_STREAM_START_EVENT: - case YAML_DOCUMENT_START_EVENT: - case YAML_SEQUENCE_START_EVENT: - case YAML_MAPPING_START_EVENT: - level += 1; - break; - case YAML_STREAM_END_EVENT: - case YAML_DOCUMENT_END_EVENT: - case YAML_SEQUENCE_END_EVENT: - case YAML_MAPPING_END_EVENT: - level -= 1; - break; - default: - break; - } - if (!level) - return 0; - } - - return 1; -} - -/* - * Append a directive to the directives stack. - */ - -static int -yaml_emitter_append_tag_directive(yaml_emitter_t *emitter, - yaml_tag_directive_t value, int allow_duplicates) -{ - yaml_tag_directive_t *tag_directive; - yaml_tag_directive_t copy = { NULL, NULL }; - - for (tag_directive = emitter->tag_directives.start; - tag_directive != emitter->tag_directives.top; tag_directive ++) { - if (strcmp((char *)value.handle, (char *)tag_directive->handle) == 0) { - if (allow_duplicates) - return 1; - return yaml_emitter_set_emitter_error(emitter, - "duplicate %TAG directive"); - } - } - - copy.handle = yaml_strdup(value.handle); - copy.prefix = yaml_strdup(value.prefix); - if (!copy.handle || !copy.prefix) { - emitter->error = YAML_MEMORY_ERROR; - goto error; - } - - if (!PUSH(emitter, emitter->tag_directives, copy)) - goto error; - - return 1; - -error: - yaml_free(copy.handle); - yaml_free(copy.prefix); - return 0; -} - -/* - * Increase the indentation level. - */ - -static int -yaml_emitter_increase_indent(yaml_emitter_t *emitter, - int flow, int indentless) -{ - if (!PUSH(emitter, emitter->indents, emitter->indent)) - return 0; - - if (emitter->indent < 0) { - emitter->indent = flow ? emitter->best_indent : 0; - } - else if (!indentless) { - emitter->indent += emitter->best_indent; - } - - return 1; -} - -/* - * State dispatcher. - */ - -static int -yaml_emitter_state_machine(yaml_emitter_t *emitter, yaml_event_t *event) -{ - switch (emitter->state) - { - case YAML_EMIT_STREAM_START_STATE: - return yaml_emitter_emit_stream_start(emitter, event); - - case YAML_EMIT_FIRST_DOCUMENT_START_STATE: - return yaml_emitter_emit_document_start(emitter, event, 1); - - case YAML_EMIT_DOCUMENT_START_STATE: - return yaml_emitter_emit_document_start(emitter, event, 0); - - case YAML_EMIT_DOCUMENT_CONTENT_STATE: - return yaml_emitter_emit_document_content(emitter, event); - - case YAML_EMIT_DOCUMENT_END_STATE: - return yaml_emitter_emit_document_end(emitter, event); - - case YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE: - return yaml_emitter_emit_flow_sequence_item(emitter, event, 1); - - case YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE: - return yaml_emitter_emit_flow_sequence_item(emitter, event, 0); - - case YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE: - return yaml_emitter_emit_flow_mapping_key(emitter, event, 1); - - case YAML_EMIT_FLOW_MAPPING_KEY_STATE: - return yaml_emitter_emit_flow_mapping_key(emitter, event, 0); - - case YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE: - return yaml_emitter_emit_flow_mapping_value(emitter, event, 1); - - case YAML_EMIT_FLOW_MAPPING_VALUE_STATE: - return yaml_emitter_emit_flow_mapping_value(emitter, event, 0); - - case YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE: - return yaml_emitter_emit_block_sequence_item(emitter, event, 1); - - case YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE: - return yaml_emitter_emit_block_sequence_item(emitter, event, 0); - - case YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE: - return yaml_emitter_emit_block_mapping_key(emitter, event, 1); - - case YAML_EMIT_BLOCK_MAPPING_KEY_STATE: - return yaml_emitter_emit_block_mapping_key(emitter, event, 0); - - case YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE: - return yaml_emitter_emit_block_mapping_value(emitter, event, 1); - - case YAML_EMIT_BLOCK_MAPPING_VALUE_STATE: - return yaml_emitter_emit_block_mapping_value(emitter, event, 0); - - case YAML_EMIT_END_STATE: - return yaml_emitter_set_emitter_error(emitter, - "expected nothing after STREAM-END"); - - default: - assert(1); /* Invalid state. */ - } - - return 0; -} - -/* - * Expect STREAM-START. - */ - -static int -yaml_emitter_emit_stream_start(yaml_emitter_t *emitter, - yaml_event_t *event) -{ - if (event->type == YAML_STREAM_START_EVENT) - { - if (!emitter->encoding) { - emitter->encoding = event->data.stream_start.encoding; - } - - if (!emitter->encoding) { - emitter->encoding = YAML_UTF8_ENCODING; - } - - if (emitter->best_indent < 2 || emitter->best_indent > 9) { - emitter->best_indent = 2; - } - - if (emitter->best_width >= 0 - && emitter->best_width <= emitter->best_indent*2) { - emitter->best_width = 80; - } - - if (emitter->best_width < 0) { - emitter->best_width = INT_MAX; - } - - if (!emitter->line_break) { - emitter->line_break = YAML_LN_BREAK; - } - - emitter->indent = -1; - - emitter->line = 0; - emitter->column = 0; - emitter->whitespace = 1; - emitter->indention = 1; - - if (emitter->encoding != YAML_UTF8_ENCODING) { - if (!yaml_emitter_write_bom(emitter)) - return 0; - } - - emitter->state = YAML_EMIT_FIRST_DOCUMENT_START_STATE; - - return 1; - } - - return yaml_emitter_set_emitter_error(emitter, - "expected STREAM-START"); -} - -/* - * Expect DOCUMENT-START or STREAM-END. - */ - -static int -yaml_emitter_emit_document_start(yaml_emitter_t *emitter, - yaml_event_t *event, int first) -{ - if (event->type == YAML_DOCUMENT_START_EVENT) - { - 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 *tag_directive; - int implicit; - - if (event->data.document_start.version_directive) { - if (!yaml_emitter_analyze_version_directive(emitter, - *event->data.document_start.version_directive)) - return 0; - } - - for (tag_directive = event->data.document_start.tag_directives.start; - tag_directive != event->data.document_start.tag_directives.end; - tag_directive ++) { - if (!yaml_emitter_analyze_tag_directive(emitter, *tag_directive)) - return 0; - if (!yaml_emitter_append_tag_directive(emitter, *tag_directive, 0)) - return 0; - } - - for (tag_directive = default_tag_directives; - tag_directive->handle; tag_directive ++) { - if (!yaml_emitter_append_tag_directive(emitter, *tag_directive, 1)) - return 0; - } - - implicit = event->data.document_start.implicit; - if (!first || emitter->canonical) { - implicit = 0; - } - - if ((event->data.document_start.version_directive || - (event->data.document_start.tag_directives.start - != event->data.document_start.tag_directives.end)) && - emitter->open_ended) - { - if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - - if (event->data.document_start.version_directive) { - implicit = 0; - if (!yaml_emitter_write_indicator(emitter, "%YAML", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_indicator(emitter, "1.1", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - - if (event->data.document_start.tag_directives.start - != event->data.document_start.tag_directives.end) { - implicit = 0; - for (tag_directive = event->data.document_start.tag_directives.start; - tag_directive != event->data.document_start.tag_directives.end; - tag_directive ++) { - if (!yaml_emitter_write_indicator(emitter, "%TAG", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_tag_handle(emitter, tag_directive->handle, - strlen((char *)tag_directive->handle))) - return 0; - if (!yaml_emitter_write_tag_content(emitter, tag_directive->prefix, - strlen((char *)tag_directive->prefix), 1)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - } - - if (yaml_emitter_check_empty_document(emitter)) { - implicit = 0; - } - - if (!implicit) { - if (!yaml_emitter_write_indent(emitter)) - return 0; - if (!yaml_emitter_write_indicator(emitter, "---", 1, 0, 0)) - return 0; - if (emitter->canonical) { - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - } - - emitter->state = YAML_EMIT_DOCUMENT_CONTENT_STATE; - - return 1; - } - - else if (event->type == YAML_STREAM_END_EVENT) - { - if (emitter->open_ended) - { - if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - - if (!yaml_emitter_flush(emitter)) - return 0; - - emitter->state = YAML_EMIT_END_STATE; - - return 1; - } - - return yaml_emitter_set_emitter_error(emitter, - "expected DOCUMENT-START or STREAM-END"); -} - -/* - * Expect the root node. - */ - -static int -yaml_emitter_emit_document_content(yaml_emitter_t *emitter, - yaml_event_t *event) -{ - if (!PUSH(emitter, emitter->states, YAML_EMIT_DOCUMENT_END_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 1, 0, 0, 0); -} - -/* - * Expect DOCUMENT-END. - */ - -static int -yaml_emitter_emit_document_end(yaml_emitter_t *emitter, - yaml_event_t *event) -{ - if (event->type == YAML_DOCUMENT_END_EVENT) - { - if (!yaml_emitter_write_indent(emitter)) - return 0; - if (!event->data.document_end.implicit) { - if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - if (!yaml_emitter_flush(emitter)) - return 0; - - emitter->state = YAML_EMIT_DOCUMENT_START_STATE; - - while (!STACK_EMPTY(emitter, emitter->tag_directives)) { - yaml_tag_directive_t tag_directive = POP(emitter, - emitter->tag_directives); - yaml_free(tag_directive.handle); - yaml_free(tag_directive.prefix); - } - - return 1; - } - - return yaml_emitter_set_emitter_error(emitter, - "expected DOCUMENT-END"); -} - -/* - * - * Expect a flow item node. - */ - -static int -yaml_emitter_emit_flow_sequence_item(yaml_emitter_t *emitter, - yaml_event_t *event, int first) -{ - if (first) - { - if (!yaml_emitter_write_indicator(emitter, "[", 1, 1, 0)) - return 0; - if (!yaml_emitter_increase_indent(emitter, 1, 0)) - return 0; - emitter->flow_level ++; - } - - if (event->type == YAML_SEQUENCE_END_EVENT) - { - emitter->flow_level --; - emitter->indent = POP(emitter, emitter->indents); - if (emitter->canonical && !first) { - if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - if (!yaml_emitter_write_indicator(emitter, "]", 0, 0, 0)) - return 0; - emitter->state = POP(emitter, emitter->states); - - return 1; - } - - if (!first) { - if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) - return 0; - } - - if (emitter->canonical || emitter->column > emitter->best_width) { - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - if (!PUSH(emitter, emitter->states, YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 1, 0, 0); -} - -/* - * Expect a flow key node. - */ - -static int -yaml_emitter_emit_flow_mapping_key(yaml_emitter_t *emitter, - yaml_event_t *event, int first) -{ - if (first) - { - if (!yaml_emitter_write_indicator(emitter, "{", 1, 1, 0)) - return 0; - if (!yaml_emitter_increase_indent(emitter, 1, 0)) - return 0; - emitter->flow_level ++; - } - - if (event->type == YAML_MAPPING_END_EVENT) - { - emitter->flow_level --; - emitter->indent = POP(emitter, emitter->indents); - if (emitter->canonical && !first) { - if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) - return 0; - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - if (!yaml_emitter_write_indicator(emitter, "}", 0, 0, 0)) - return 0; - emitter->state = POP(emitter, emitter->states); - - return 1; - } - - if (!first) { - if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) - return 0; - } - if (emitter->canonical || emitter->column > emitter->best_width) { - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - - if (!emitter->canonical && yaml_emitter_check_simple_key(emitter)) - { - if (!PUSH(emitter, emitter->states, - YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 1); - } - else - { - if (!yaml_emitter_write_indicator(emitter, "?", 1, 0, 0)) - return 0; - if (!PUSH(emitter, emitter->states, - YAML_EMIT_FLOW_MAPPING_VALUE_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); - } -} - -/* - * Expect a flow value node. - */ - -static int -yaml_emitter_emit_flow_mapping_value(yaml_emitter_t *emitter, - yaml_event_t *event, int simple) -{ - if (simple) { - if (!yaml_emitter_write_indicator(emitter, ":", 0, 0, 0)) - return 0; - } - else { - if (emitter->canonical || emitter->column > emitter->best_width) { - if (!yaml_emitter_write_indent(emitter)) - return 0; - } - if (!yaml_emitter_write_indicator(emitter, ":", 1, 0, 0)) - return 0; - } - if (!PUSH(emitter, emitter->states, YAML_EMIT_FLOW_MAPPING_KEY_STATE)) - return 0; - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); -} - -/* - * Expect a block item node. - */ - -static int -yaml_emitter_emit_block_sequence_item(yaml_emitter_t *emitter, - yaml_event_t *event, int first) -{ - if (first) - { - if (!yaml_emitter_increase_indent(emitter, 0, - (emitter->mapping_context && !emitter->indention))) - return 0; - } - - if (event->type == YAML_SEQUENCE_END_EVENT) - { - emitter->indent = POP(emitter, emitter->indents); - emitter->state = POP(emitter, emitter->states); - - return 1; - } - - if (!yaml_emitter_write_indent(emitter)) - return 0; - if (!yaml_emitter_write_indicator(emitter, "-", 1, 0, 1)) - return 0; - if (!PUSH(emitter, emitter->states, - YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 1, 0, 0); -} - -/* - * Expect a block key node. - */ - -static int -yaml_emitter_emit_block_mapping_key(yaml_emitter_t *emitter, - yaml_event_t *event, int first) -{ - if (first) - { - if (!yaml_emitter_increase_indent(emitter, 0, 0)) - return 0; - } - - if (event->type == YAML_MAPPING_END_EVENT) - { - emitter->indent = POP(emitter, emitter->indents); - emitter->state = POP(emitter, emitter->states); - - return 1; - } - - if (!yaml_emitter_write_indent(emitter)) - return 0; - - if (yaml_emitter_check_simple_key(emitter)) - { - if (!PUSH(emitter, emitter->states, - YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 1); - } - else - { - if (!yaml_emitter_write_indicator(emitter, "?", 1, 0, 1)) - return 0; - if (!PUSH(emitter, emitter->states, - YAML_EMIT_BLOCK_MAPPING_VALUE_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); - } -} - -/* - * Expect a block value node. - */ - -static int -yaml_emitter_emit_block_mapping_value(yaml_emitter_t *emitter, - yaml_event_t *event, int simple) -{ - if (simple) { - if (!yaml_emitter_write_indicator(emitter, ":", 0, 0, 0)) - return 0; - } - else { - if (!yaml_emitter_write_indent(emitter)) - return 0; - if (!yaml_emitter_write_indicator(emitter, ":", 1, 0, 1)) - return 0; - } - if (!PUSH(emitter, emitter->states, - YAML_EMIT_BLOCK_MAPPING_KEY_STATE)) - return 0; - - return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); -} - -/* - * Expect a node. - */ - -static int -yaml_emitter_emit_node(yaml_emitter_t *emitter, yaml_event_t *event, - int root, int sequence, int mapping, int simple_key) -{ - emitter->root_context = root; - emitter->sequence_context = sequence; - emitter->mapping_context = mapping; - emitter->simple_key_context = simple_key; - - switch (event->type) - { - case YAML_ALIAS_EVENT: - return yaml_emitter_emit_alias(emitter, event); - - case YAML_SCALAR_EVENT: - return yaml_emitter_emit_scalar(emitter, event); - - case YAML_SEQUENCE_START_EVENT: - return yaml_emitter_emit_sequence_start(emitter, event); - - case YAML_MAPPING_START_EVENT: - return yaml_emitter_emit_mapping_start(emitter, event); - - default: - return yaml_emitter_set_emitter_error(emitter, - "expected SCALAR, SEQUENCE-START, MAPPING-START, or ALIAS"); - } - - return 0; -} - -/* - * Expect ALIAS. - */ - -static int -yaml_emitter_emit_alias(yaml_emitter_t *emitter, yaml_event_t *event) -{ - if (!yaml_emitter_process_anchor(emitter)) - return 0; - emitter->state = POP(emitter, emitter->states); - - return 1; -} - -/* - * Expect SCALAR. - */ - -static int -yaml_emitter_emit_scalar(yaml_emitter_t *emitter, yaml_event_t *event) -{ - if (!yaml_emitter_select_scalar_style(emitter, event)) - return 0; - if (!yaml_emitter_process_anchor(emitter)) - return 0; - if (!yaml_emitter_process_tag(emitter)) - return 0; - if (!yaml_emitter_increase_indent(emitter, 1, 0)) - return 0; - if (!yaml_emitter_process_scalar(emitter)) - return 0; - emitter->indent = POP(emitter, emitter->indents); - emitter->state = POP(emitter, emitter->states); - - return 1; -} - -/* - * Expect SEQUENCE-START. - */ - -static int -yaml_emitter_emit_sequence_start(yaml_emitter_t *emitter, yaml_event_t *event) -{ - if (!yaml_emitter_process_anchor(emitter)) - return 0; - if (!yaml_emitter_process_tag(emitter)) - return 0; - - if (emitter->flow_level || emitter->canonical - || event->data.sequence_start.style == YAML_FLOW_SEQUENCE_STYLE - || yaml_emitter_check_empty_sequence(emitter)) { - emitter->state = YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE; - } - else { - emitter->state = YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE; - } - - return 1; -} - -/* - * Expect MAPPING-START. - */ - -static int -yaml_emitter_emit_mapping_start(yaml_emitter_t *emitter, yaml_event_t *event) -{ - if (!yaml_emitter_process_anchor(emitter)) - return 0; - if (!yaml_emitter_process_tag(emitter)) - return 0; - - if (emitter->flow_level || emitter->canonical - || event->data.mapping_start.style == YAML_FLOW_MAPPING_STYLE - || yaml_emitter_check_empty_mapping(emitter)) { - emitter->state = YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE; - } - else { - emitter->state = YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE; - } - - return 1; -} - -/* - * Check if the document content is an empty scalar. - */ - -static int -yaml_emitter_check_empty_document(yaml_emitter_t *emitter) -{ - return 0; -} - -/* - * Check if the next events represent an empty sequence. - */ - -static int -yaml_emitter_check_empty_sequence(yaml_emitter_t *emitter) -{ - if (emitter->events.tail - emitter->events.head < 2) - return 0; - - return (emitter->events.head[0].type == YAML_SEQUENCE_START_EVENT - && emitter->events.head[1].type == YAML_SEQUENCE_END_EVENT); -} - -/* - * Check if the next events represent an empty mapping. - */ - -static int -yaml_emitter_check_empty_mapping(yaml_emitter_t *emitter) -{ - if (emitter->events.tail - emitter->events.head < 2) - return 0; - - return (emitter->events.head[0].type == YAML_MAPPING_START_EVENT - && emitter->events.head[1].type == YAML_MAPPING_END_EVENT); -} - -/* - * Check if the next node can be expressed as a simple key. - */ - -static int -yaml_emitter_check_simple_key(yaml_emitter_t *emitter) -{ - yaml_event_t *event = emitter->events.head; - size_t length = 0; - - switch (event->type) - { - case YAML_ALIAS_EVENT: - length += emitter->anchor_data.anchor_length; - break; - - case YAML_SCALAR_EVENT: - if (emitter->scalar_data.multiline) - return 0; - length += emitter->anchor_data.anchor_length - + emitter->tag_data.handle_length - + emitter->tag_data.suffix_length - + emitter->scalar_data.length; - break; - - case YAML_SEQUENCE_START_EVENT: - if (!yaml_emitter_check_empty_sequence(emitter)) - return 0; - length += emitter->anchor_data.anchor_length - + emitter->tag_data.handle_length - + emitter->tag_data.suffix_length; - break; - - case YAML_MAPPING_START_EVENT: - if (!yaml_emitter_check_empty_mapping(emitter)) - return 0; - length += emitter->anchor_data.anchor_length - + emitter->tag_data.handle_length - + emitter->tag_data.suffix_length; - break; - - default: - return 0; - } - - if (length > 128) - return 0; - - return 1; -} - -/* - * Determine an acceptable scalar style. - */ - -static int -yaml_emitter_select_scalar_style(yaml_emitter_t *emitter, yaml_event_t *event) -{ - yaml_scalar_style_t style = event->data.scalar.style; - int no_tag = (!emitter->tag_data.handle && !emitter->tag_data.suffix); - - if (no_tag && !event->data.scalar.plain_implicit - && !event->data.scalar.quoted_implicit) { - return yaml_emitter_set_emitter_error(emitter, - "neither tag nor implicit flags are specified"); - } - - if (style == YAML_ANY_SCALAR_STYLE) - style = YAML_PLAIN_SCALAR_STYLE; - - if (emitter->canonical) - style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; - - if (emitter->simple_key_context && emitter->scalar_data.multiline) - style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; - - if (style == YAML_PLAIN_SCALAR_STYLE) - { - if ((emitter->flow_level && !emitter->scalar_data.flow_plain_allowed) - || (!emitter->flow_level && !emitter->scalar_data.block_plain_allowed)) - style = YAML_SINGLE_QUOTED_SCALAR_STYLE; - if (!emitter->scalar_data.length - && (emitter->flow_level || emitter->simple_key_context)) - style = YAML_SINGLE_QUOTED_SCALAR_STYLE; - if (no_tag && !event->data.scalar.plain_implicit) - style = YAML_SINGLE_QUOTED_SCALAR_STYLE; - } - - if (style == YAML_SINGLE_QUOTED_SCALAR_STYLE) - { - if (!emitter->scalar_data.single_quoted_allowed) - style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; - } - - if (style == YAML_LITERAL_SCALAR_STYLE || style == YAML_FOLDED_SCALAR_STYLE) - { - if (!emitter->scalar_data.block_allowed - || emitter->flow_level || emitter->simple_key_context) - style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; - } - - if (no_tag && !event->data.scalar.quoted_implicit - && style != YAML_PLAIN_SCALAR_STYLE) - { - emitter->tag_data.handle = (yaml_char_t *)"!"; - emitter->tag_data.handle_length = 1; - } - - emitter->scalar_data.style = style; - - return 1; -} - -/* - * Write an achor. - */ - -static int -yaml_emitter_process_anchor(yaml_emitter_t *emitter) -{ - if (!emitter->anchor_data.anchor) - return 1; - - if (!yaml_emitter_write_indicator(emitter, - (emitter->anchor_data.alias ? "*" : "&"), 1, 0, 0)) - return 0; - - return yaml_emitter_write_anchor(emitter, - emitter->anchor_data.anchor, emitter->anchor_data.anchor_length); -} - -/* - * Write a tag. - */ - -static int -yaml_emitter_process_tag(yaml_emitter_t *emitter) -{ - if (!emitter->tag_data.handle && !emitter->tag_data.suffix) - return 1; - - if (emitter->tag_data.handle) - { - if (!yaml_emitter_write_tag_handle(emitter, emitter->tag_data.handle, - emitter->tag_data.handle_length)) - return 0; - if (emitter->tag_data.suffix) { - if (!yaml_emitter_write_tag_content(emitter, emitter->tag_data.suffix, - emitter->tag_data.suffix_length, 0)) - return 0; - } - } - else - { - if (!yaml_emitter_write_indicator(emitter, "!<", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_tag_content(emitter, emitter->tag_data.suffix, - emitter->tag_data.suffix_length, 0)) - return 0; - if (!yaml_emitter_write_indicator(emitter, ">", 0, 0, 0)) - return 0; - } - - return 1; -} - -/* - * Write a scalar. - */ - -static int -yaml_emitter_process_scalar(yaml_emitter_t *emitter) -{ - switch (emitter->scalar_data.style) - { - case YAML_PLAIN_SCALAR_STYLE: - return yaml_emitter_write_plain_scalar(emitter, - emitter->scalar_data.value, emitter->scalar_data.length, - !emitter->simple_key_context); - - case YAML_SINGLE_QUOTED_SCALAR_STYLE: - return yaml_emitter_write_single_quoted_scalar(emitter, - emitter->scalar_data.value, emitter->scalar_data.length, - !emitter->simple_key_context); - - case YAML_DOUBLE_QUOTED_SCALAR_STYLE: - return yaml_emitter_write_double_quoted_scalar(emitter, - emitter->scalar_data.value, emitter->scalar_data.length, - !emitter->simple_key_context); - - case YAML_LITERAL_SCALAR_STYLE: - return yaml_emitter_write_literal_scalar(emitter, - emitter->scalar_data.value, emitter->scalar_data.length); - - case YAML_FOLDED_SCALAR_STYLE: - return yaml_emitter_write_folded_scalar(emitter, - emitter->scalar_data.value, emitter->scalar_data.length); - - default: - assert(1); /* Impossible. */ - } - - return 0; -} - -/* - * Check if a %YAML directive is valid. - */ - -static int -yaml_emitter_analyze_version_directive(yaml_emitter_t *emitter, - yaml_version_directive_t version_directive) -{ - if (version_directive.major != 1 || version_directive.minor != 1) { - return yaml_emitter_set_emitter_error(emitter, - "incompatible %YAML directive"); - } - - return 1; -} - -/* - * Check if a %TAG directive is valid. - */ - -static int -yaml_emitter_analyze_tag_directive(yaml_emitter_t *emitter, - yaml_tag_directive_t tag_directive) -{ - yaml_string_t handle; - yaml_string_t prefix; - size_t handle_length; - size_t prefix_length; - - handle_length = strlen((char *)tag_directive.handle); - prefix_length = strlen((char *)tag_directive.prefix); - STRING_ASSIGN(handle, tag_directive.handle, handle_length); - STRING_ASSIGN(prefix, tag_directive.prefix, prefix_length); - - if (handle.start == handle.end) { - return yaml_emitter_set_emitter_error(emitter, - "tag handle must not be empty"); - } - - if (handle.start[0] != '!') { - return yaml_emitter_set_emitter_error(emitter, - "tag handle must start with '!'"); - } - - if (handle.end[-1] != '!') { - return yaml_emitter_set_emitter_error(emitter, - "tag handle must end with '!'"); - } - - handle.pointer ++; - - while (handle.pointer < handle.end-1) { - if (!IS_ALPHA(handle)) { - return yaml_emitter_set_emitter_error(emitter, - "tag handle must contain alphanumerical characters only"); - } - MOVE(handle); - } - - if (prefix.start == prefix.end) { - return yaml_emitter_set_emitter_error(emitter, - "tag prefix must not be empty"); - } - - return 1; -} - -/* - * Check if an anchor is valid. - */ - -static int -yaml_emitter_analyze_anchor(yaml_emitter_t *emitter, - yaml_char_t *anchor, int alias) -{ - size_t anchor_length; - yaml_string_t string; - - anchor_length = strlen((char *)anchor); - STRING_ASSIGN(string, anchor, anchor_length); - - if (string.start == string.end) { - return yaml_emitter_set_emitter_error(emitter, alias ? - "alias value must not be empty" : - "anchor value must not be empty"); - } - - while (string.pointer != string.end) { - if (!IS_ALPHA(string)) { - return yaml_emitter_set_emitter_error(emitter, alias ? - "alias value must contain alphanumerical characters only" : - "anchor value must contain alphanumerical characters only"); - } - MOVE(string); - } - - emitter->anchor_data.anchor = string.start; - emitter->anchor_data.anchor_length = string.end - string.start; - emitter->anchor_data.alias = alias; - - return 1; -} - -/* - * Check if a tag is valid. - */ - -static int -yaml_emitter_analyze_tag(yaml_emitter_t *emitter, - yaml_char_t *tag) -{ - size_t tag_length; - yaml_string_t string; - yaml_tag_directive_t *tag_directive; - - tag_length = strlen((char *)tag); - STRING_ASSIGN(string, tag, tag_length); - - if (string.start == string.end) { - return yaml_emitter_set_emitter_error(emitter, - "tag value must not be empty"); - } - - for (tag_directive = emitter->tag_directives.start; - tag_directive != emitter->tag_directives.top; tag_directive ++) { - size_t prefix_length = strlen((char *)tag_directive->prefix); - if (prefix_length < (size_t)(string.end - string.start) - && strncmp((char *)tag_directive->prefix, (char *)string.start, - prefix_length) == 0) - { - emitter->tag_data.handle = tag_directive->handle; - emitter->tag_data.handle_length = - strlen((char *)tag_directive->handle); - emitter->tag_data.suffix = string.start + prefix_length; - emitter->tag_data.suffix_length = - (string.end - string.start) - prefix_length; - return 1; - } - } - - emitter->tag_data.suffix = string.start; - emitter->tag_data.suffix_length = string.end - string.start; - - return 1; -} - -/* - * Check if a scalar is valid. - */ - -static int -yaml_emitter_analyze_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length) -{ - yaml_string_t string; - - int block_indicators = 0; - int flow_indicators = 0; - int line_breaks = 0; - int special_characters = 0; - - int leading_space = 0; - int leading_break = 0; - int trailing_space = 0; - int trailing_break = 0; - int break_space = 0; - int space_break = 0; - - int preceeded_by_whitespace = 0; - int followed_by_whitespace = 0; - int previous_space = 0; - int previous_break = 0; - - STRING_ASSIGN(string, value, length); - - emitter->scalar_data.value = value; - emitter->scalar_data.length = length; - - if (string.start == string.end) - { - emitter->scalar_data.multiline = 0; - emitter->scalar_data.flow_plain_allowed = 0; - emitter->scalar_data.block_plain_allowed = 1; - emitter->scalar_data.single_quoted_allowed = 1; - emitter->scalar_data.block_allowed = 0; - - return 1; - } - - if ((CHECK_AT(string, '-', 0) - && CHECK_AT(string, '-', 1) - && CHECK_AT(string, '-', 2)) - || (CHECK_AT(string, '.', 0) - && CHECK_AT(string, '.', 1) - && CHECK_AT(string, '.', 2))) { - block_indicators = 1; - flow_indicators = 1; - } - - preceeded_by_whitespace = 1; - followed_by_whitespace = IS_BLANKZ_AT(string, WIDTH(string)); - - while (string.pointer != string.end) - { - if (string.start == string.pointer) - { - if (CHECK(string, '#') || CHECK(string, ',') - || CHECK(string, '[') || CHECK(string, ']') - || CHECK(string, '{') || CHECK(string, '}') - || CHECK(string, '&') || CHECK(string, '*') - || CHECK(string, '!') || CHECK(string, '|') - || CHECK(string, '>') || CHECK(string, '\'') - || CHECK(string, '"') || CHECK(string, '%') - || CHECK(string, '@') || CHECK(string, '`')) { - flow_indicators = 1; - block_indicators = 1; - } - - if (CHECK(string, '?') || CHECK(string, ':')) { - flow_indicators = 1; - if (followed_by_whitespace) { - block_indicators = 1; - } - } - - if (CHECK(string, '-') && followed_by_whitespace) { - flow_indicators = 1; - block_indicators = 1; - } - } - else - { - if (CHECK(string, ',') || CHECK(string, '?') - || CHECK(string, '[') || CHECK(string, ']') - || CHECK(string, '{') || CHECK(string, '}')) { - flow_indicators = 1; - } - - if (CHECK(string, ':')) { - flow_indicators = 1; - if (followed_by_whitespace) { - block_indicators = 1; - } - } - - if (CHECK(string, '#') && preceeded_by_whitespace) { - flow_indicators = 1; - block_indicators = 1; - } - } - - if (!IS_PRINTABLE(string) - || (!IS_ASCII(string) && !emitter->unicode)) { - special_characters = 1; - } - - if (IS_BREAK(string)) { - line_breaks = 1; - } - - if (IS_SPACE(string)) - { - if (string.start == string.pointer) { - leading_space = 1; - } - if (string.pointer+WIDTH(string) == string.end) { - trailing_space = 1; - } - if (previous_break) { - break_space = 1; - } - previous_space = 1; - previous_break = 0; - } - else if (IS_BREAK(string)) - { - if (string.start == string.pointer) { - leading_break = 1; - } - if (string.pointer+WIDTH(string) == string.end) { - trailing_break = 1; - } - if (previous_space) { - space_break = 1; - } - previous_space = 0; - previous_break = 1; - } - else - { - previous_space = 0; - previous_break = 0; - } - - preceeded_by_whitespace = IS_BLANKZ(string); - MOVE(string); - if (string.pointer != string.end) { - followed_by_whitespace = IS_BLANKZ_AT(string, WIDTH(string)); - } - } - - emitter->scalar_data.multiline = line_breaks; - - emitter->scalar_data.flow_plain_allowed = 1; - emitter->scalar_data.block_plain_allowed = 1; - emitter->scalar_data.single_quoted_allowed = 1; - emitter->scalar_data.block_allowed = 1; - - if (leading_space || leading_break || trailing_space || trailing_break) { - emitter->scalar_data.flow_plain_allowed = 0; - emitter->scalar_data.block_plain_allowed = 0; - } - - if (trailing_space) { - emitter->scalar_data.block_allowed = 0; - } - - if (break_space) { - emitter->scalar_data.flow_plain_allowed = 0; - emitter->scalar_data.block_plain_allowed = 0; - emitter->scalar_data.single_quoted_allowed = 0; - } - - if (space_break || special_characters) { - emitter->scalar_data.flow_plain_allowed = 0; - emitter->scalar_data.block_plain_allowed = 0; - emitter->scalar_data.single_quoted_allowed = 0; - emitter->scalar_data.block_allowed = 0; - } - - if (line_breaks) { - emitter->scalar_data.flow_plain_allowed = 0; - emitter->scalar_data.block_plain_allowed = 0; - } - - if (flow_indicators) { - emitter->scalar_data.flow_plain_allowed = 0; - } - - if (block_indicators) { - emitter->scalar_data.block_plain_allowed = 0; - } - - return 1; -} - -/* - * Check if the event data is valid. - */ - -static int -yaml_emitter_analyze_event(yaml_emitter_t *emitter, - yaml_event_t *event) -{ - emitter->anchor_data.anchor = NULL; - emitter->anchor_data.anchor_length = 0; - emitter->tag_data.handle = NULL; - emitter->tag_data.handle_length = 0; - emitter->tag_data.suffix = NULL; - emitter->tag_data.suffix_length = 0; - emitter->scalar_data.value = NULL; - emitter->scalar_data.length = 0; - - switch (event->type) - { - case YAML_ALIAS_EVENT: - if (!yaml_emitter_analyze_anchor(emitter, - event->data.alias.anchor, 1)) - return 0; - return 1; - - case YAML_SCALAR_EVENT: - if (event->data.scalar.anchor) { - if (!yaml_emitter_analyze_anchor(emitter, - event->data.scalar.anchor, 0)) - return 0; - } - if (event->data.scalar.tag && (emitter->canonical || - (!event->data.scalar.plain_implicit - && !event->data.scalar.quoted_implicit))) { - if (!yaml_emitter_analyze_tag(emitter, event->data.scalar.tag)) - return 0; - } - if (!yaml_emitter_analyze_scalar(emitter, - event->data.scalar.value, event->data.scalar.length)) - return 0; - return 1; - - case YAML_SEQUENCE_START_EVENT: - if (event->data.sequence_start.anchor) { - if (!yaml_emitter_analyze_anchor(emitter, - event->data.sequence_start.anchor, 0)) - return 0; - } - if (event->data.sequence_start.tag && (emitter->canonical || - !event->data.sequence_start.implicit)) { - if (!yaml_emitter_analyze_tag(emitter, - event->data.sequence_start.tag)) - return 0; - } - return 1; - - case YAML_MAPPING_START_EVENT: - if (event->data.mapping_start.anchor) { - if (!yaml_emitter_analyze_anchor(emitter, - event->data.mapping_start.anchor, 0)) - return 0; - } - if (event->data.mapping_start.tag && (emitter->canonical || - !event->data.mapping_start.implicit)) { - if (!yaml_emitter_analyze_tag(emitter, - event->data.mapping_start.tag)) - return 0; - } - return 1; - - default: - return 1; - } -} - -/* - * Write the BOM character. - */ - -static int -yaml_emitter_write_bom(yaml_emitter_t *emitter) -{ - if (!FLUSH(emitter)) return 0; - - *(emitter->buffer.pointer++) = (yaml_char_t) '\xEF'; - *(emitter->buffer.pointer++) = (yaml_char_t) '\xBB'; - *(emitter->buffer.pointer++) = (yaml_char_t) '\xBF'; - - return 1; -} - -static int -yaml_emitter_write_indent(yaml_emitter_t *emitter) -{ - int indent = (emitter->indent >= 0) ? emitter->indent : 0; - - if (!emitter->indention || emitter->column > indent - || (emitter->column == indent && !emitter->whitespace)) { - if (!PUT_BREAK(emitter)) return 0; - } - - while (emitter->column < indent) { - if (!PUT(emitter, ' ')) return 0; - } - - emitter->whitespace = 1; - emitter->indention = 1; - - return 1; -} - -static int -yaml_emitter_write_indicator(yaml_emitter_t *emitter, - char *indicator, int need_whitespace, - int is_whitespace, int is_indention) -{ - size_t indicator_length; - yaml_string_t string; - - indicator_length = strlen(indicator); - STRING_ASSIGN(string, (yaml_char_t *)indicator, indicator_length); - - if (need_whitespace && !emitter->whitespace) { - if (!PUT(emitter, ' ')) return 0; - } - - while (string.pointer != string.end) { - if (!WRITE(emitter, string)) return 0; - } - - emitter->whitespace = is_whitespace; - emitter->indention = (emitter->indention && is_indention); - emitter->open_ended = 0; - - return 1; -} - -static int -yaml_emitter_write_anchor(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length) -{ - yaml_string_t string; - STRING_ASSIGN(string, value, length); - - while (string.pointer != string.end) { - if (!WRITE(emitter, string)) return 0; - } - - emitter->whitespace = 0; - emitter->indention = 0; - - return 1; -} - -static int -yaml_emitter_write_tag_handle(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length) -{ - yaml_string_t string; - STRING_ASSIGN(string, value, length); - - if (!emitter->whitespace) { - if (!PUT(emitter, ' ')) return 0; - } - - while (string.pointer != string.end) { - if (!WRITE(emitter, string)) return 0; - } - - emitter->whitespace = 0; - emitter->indention = 0; - - return 1; -} - -static int -yaml_emitter_write_tag_content(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, - int need_whitespace) -{ - yaml_string_t string; - STRING_ASSIGN(string, value, length); - - if (need_whitespace && !emitter->whitespace) { - if (!PUT(emitter, ' ')) return 0; - } - - while (string.pointer != string.end) { - if (IS_ALPHA(string) - || CHECK(string, ';') || CHECK(string, '/') - || CHECK(string, '?') || CHECK(string, ':') - || CHECK(string, '@') || CHECK(string, '&') - || CHECK(string, '=') || CHECK(string, '+') - || CHECK(string, '$') || CHECK(string, ',') - || CHECK(string, '_') || CHECK(string, '.') - || CHECK(string, '~') || CHECK(string, '*') - || CHECK(string, '\'') || CHECK(string, '(') - || CHECK(string, ')') || CHECK(string, '[') - || CHECK(string, ']')) { - if (!WRITE(emitter, string)) return 0; - } - else { - int width = WIDTH(string); - unsigned int value; - while (width --) { - value = *(string.pointer++); - if (!PUT(emitter, '%')) return 0; - if (!PUT(emitter, (value >> 4) - + ((value >> 4) < 10 ? '0' : 'A' - 10))) - return 0; - if (!PUT(emitter, (value & 0x0F) - + ((value & 0x0F) < 10 ? '0' : 'A' - 10))) - return 0; - } - } - } - - emitter->whitespace = 0; - emitter->indention = 0; - - return 1; -} - -static int -yaml_emitter_write_plain_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks) -{ - yaml_string_t string; - int spaces = 0; - int breaks = 0; - - STRING_ASSIGN(string, value, length); - - if (!emitter->whitespace) { - if (!PUT(emitter, ' ')) return 0; - } - - while (string.pointer != string.end) - { - if (IS_SPACE(string)) - { - if (allow_breaks && !spaces - && emitter->column > emitter->best_width - && !IS_SPACE_AT(string, 1)) { - if (!yaml_emitter_write_indent(emitter)) return 0; - MOVE(string); - } - else { - if (!WRITE(emitter, string)) return 0; - } - spaces = 1; - } - else if (IS_BREAK(string)) - { - if (!breaks && CHECK(string, '\n')) { - if (!PUT_BREAK(emitter)) return 0; - } - if (!WRITE_BREAK(emitter, string)) return 0; - emitter->indention = 1; - breaks = 1; - } - else - { - if (breaks) { - if (!yaml_emitter_write_indent(emitter)) return 0; - } - if (!WRITE(emitter, string)) return 0; - emitter->indention = 0; - spaces = 0; - breaks = 0; - } - } - - emitter->whitespace = 0; - emitter->indention = 0; - if (emitter->root_context) - { - emitter->open_ended = 1; - } - - return 1; -} - -static int -yaml_emitter_write_single_quoted_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks) -{ - yaml_string_t string; - int spaces = 0; - int breaks = 0; - - STRING_ASSIGN(string, value, length); - - if (!yaml_emitter_write_indicator(emitter, "'", 1, 0, 0)) - return 0; - - while (string.pointer != string.end) - { - if (IS_SPACE(string)) - { - if (allow_breaks && !spaces - && emitter->column > emitter->best_width - && string.pointer != string.start - && string.pointer != string.end - 1 - && !IS_SPACE_AT(string, 1)) { - if (!yaml_emitter_write_indent(emitter)) return 0; - MOVE(string); - } - else { - if (!WRITE(emitter, string)) return 0; - } - spaces = 1; - } - else if (IS_BREAK(string)) - { - if (!breaks && CHECK(string, '\n')) { - if (!PUT_BREAK(emitter)) return 0; - } - if (!WRITE_BREAK(emitter, string)) return 0; - emitter->indention = 1; - breaks = 1; - } - else - { - if (breaks) { - if (!yaml_emitter_write_indent(emitter)) return 0; - } - if (CHECK(string, '\'')) { - if (!PUT(emitter, '\'')) return 0; - } - if (!WRITE(emitter, string)) return 0; - emitter->indention = 0; - spaces = 0; - breaks = 0; - } - } - - if (!yaml_emitter_write_indicator(emitter, "'", 0, 0, 0)) - return 0; - - emitter->whitespace = 0; - emitter->indention = 0; - - return 1; -} - -static int -yaml_emitter_write_double_quoted_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length, int allow_breaks) -{ - yaml_string_t string; - int spaces = 0; - - STRING_ASSIGN(string, value, length); - - if (!yaml_emitter_write_indicator(emitter, "\"", 1, 0, 0)) - return 0; - - while (string.pointer != string.end) - { - if (!IS_PRINTABLE(string) || (!emitter->unicode && !IS_ASCII(string)) - || IS_BOM(string) || IS_BREAK(string) - || CHECK(string, '"') || CHECK(string, '\\')) - { - unsigned char octet; - unsigned int width; - unsigned int value; - int k; - - octet = string.pointer[0]; - width = (octet & 0x80) == 0x00 ? 1 : - (octet & 0xE0) == 0xC0 ? 2 : - (octet & 0xF0) == 0xE0 ? 3 : - (octet & 0xF8) == 0xF0 ? 4 : 0; - value = (octet & 0x80) == 0x00 ? octet & 0x7F : - (octet & 0xE0) == 0xC0 ? octet & 0x1F : - (octet & 0xF0) == 0xE0 ? octet & 0x0F : - (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; - for (k = 1; k < (int)width; k ++) { - octet = string.pointer[k]; - value = (value << 6) + (octet & 0x3F); - } - string.pointer += width; - - if (!PUT(emitter, '\\')) return 0; - - switch (value) - { - case 0x00: - if (!PUT(emitter, '0')) return 0; - break; - - case 0x07: - if (!PUT(emitter, 'a')) return 0; - break; - - case 0x08: - if (!PUT(emitter, 'b')) return 0; - break; - - case 0x09: - if (!PUT(emitter, 't')) return 0; - break; - - case 0x0A: - if (!PUT(emitter, 'n')) return 0; - break; - - case 0x0B: - if (!PUT(emitter, 'v')) return 0; - break; - - case 0x0C: - if (!PUT(emitter, 'f')) return 0; - break; - - case 0x0D: - if (!PUT(emitter, 'r')) return 0; - break; - - case 0x1B: - if (!PUT(emitter, 'e')) return 0; - break; - - case 0x22: - if (!PUT(emitter, '\"')) return 0; - break; - - case 0x5C: - if (!PUT(emitter, '\\')) return 0; - break; - - case 0x85: - if (!PUT(emitter, 'N')) return 0; - break; - - case 0xA0: - if (!PUT(emitter, '_')) return 0; - break; - - case 0x2028: - if (!PUT(emitter, 'L')) return 0; - break; - - case 0x2029: - if (!PUT(emitter, 'P')) return 0; - break; - - default: - if (value <= 0xFF) { - if (!PUT(emitter, 'x')) return 0; - width = 2; - } - else if (value <= 0xFFFF) { - if (!PUT(emitter, 'u')) return 0; - width = 4; - } - else { - if (!PUT(emitter, 'U')) return 0; - width = 8; - } - for (k = (width-1)*4; k >= 0; k -= 4) { - int digit = (value >> k) & 0x0F; - if (!PUT(emitter, digit + (digit < 10 ? '0' : 'A'-10))) - return 0; - } - } - spaces = 0; - } - else if (IS_SPACE(string)) - { - if (allow_breaks && !spaces - && emitter->column > emitter->best_width - && string.pointer != string.start - && string.pointer != string.end - 1) { - if (!yaml_emitter_write_indent(emitter)) return 0; - if (IS_SPACE_AT(string, 1)) { - if (!PUT(emitter, '\\')) return 0; - } - MOVE(string); - } - else { - if (!WRITE(emitter, string)) return 0; - } - spaces = 1; - } - else - { - if (!WRITE(emitter, string)) return 0; - spaces = 0; - } - } - - if (!yaml_emitter_write_indicator(emitter, "\"", 0, 0, 0)) - return 0; - - emitter->whitespace = 0; - emitter->indention = 0; - - return 1; -} - -static int -yaml_emitter_write_block_scalar_hints(yaml_emitter_t *emitter, - yaml_string_t string) -{ - char indent_hint[2]; - char *chomp_hint = NULL; - - if (IS_SPACE(string) || IS_BREAK(string)) - { - indent_hint[0] = '0' + (char)emitter->best_indent; - indent_hint[1] = '\0'; - if (!yaml_emitter_write_indicator(emitter, indent_hint, 0, 0, 0)) - return 0; - } - - emitter->open_ended = 0; - - string.pointer = string.end; - if (string.start == string.pointer) - { - chomp_hint = "-"; - } - else - { - do { - string.pointer --; - } while ((*string.pointer & 0xC0) == 0x80); - if (!IS_BREAK(string)) - { - chomp_hint = "-"; - } - else if (string.start == string.pointer) - { - chomp_hint = "+"; - emitter->open_ended = 1; - } - else - { - do { - string.pointer --; - } while ((*string.pointer & 0xC0) == 0x80); - if (IS_BREAK(string)) - { - chomp_hint = "+"; - emitter->open_ended = 1; - } - } - } - - if (chomp_hint) - { - if (!yaml_emitter_write_indicator(emitter, chomp_hint, 0, 0, 0)) - return 0; - } - - return 1; -} - -static int -yaml_emitter_write_literal_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length) -{ - yaml_string_t string; - int breaks = 1; - - STRING_ASSIGN(string, value, length); - - if (!yaml_emitter_write_indicator(emitter, "|", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_block_scalar_hints(emitter, string)) - return 0; - if (!PUT_BREAK(emitter)) return 0; - emitter->indention = 1; - emitter->whitespace = 1; - - while (string.pointer != string.end) - { - if (IS_BREAK(string)) - { - if (!WRITE_BREAK(emitter, string)) return 0; - emitter->indention = 1; - breaks = 1; - } - else - { - if (breaks) { - if (!yaml_emitter_write_indent(emitter)) return 0; - } - if (!WRITE(emitter, string)) return 0; - emitter->indention = 0; - breaks = 0; - } - } - - return 1; -} - -static int -yaml_emitter_write_folded_scalar(yaml_emitter_t *emitter, - yaml_char_t *value, size_t length) -{ - yaml_string_t string; - int breaks = 1; - int leading_spaces = 1; - - STRING_ASSIGN(string, value, length); - - if (!yaml_emitter_write_indicator(emitter, ">", 1, 0, 0)) - return 0; - if (!yaml_emitter_write_block_scalar_hints(emitter, string)) - return 0; - if (!PUT_BREAK(emitter)) return 0; - emitter->indention = 1; - emitter->whitespace = 1; - - while (string.pointer != string.end) - { - if (IS_BREAK(string)) - { - if (!breaks && !leading_spaces && CHECK(string, '\n')) { - int k = 0; - while (IS_BREAK_AT(string, k)) { - k += WIDTH_AT(string, k); - } - if (!IS_BLANKZ_AT(string, k)) { - if (!PUT_BREAK(emitter)) return 0; - } - } - if (!WRITE_BREAK(emitter, string)) return 0; - emitter->indention = 1; - breaks = 1; - } - else - { - if (breaks) { - if (!yaml_emitter_write_indent(emitter)) return 0; - leading_spaces = IS_BLANK(string); - } - if (!breaks && IS_SPACE(string) && !IS_SPACE_AT(string, 1) - && emitter->column > emitter->best_width) { - if (!yaml_emitter_write_indent(emitter)) return 0; - MOVE(string); - } - else { - if (!WRITE(emitter, string)) return 0; - } - emitter->indention = 0; - breaks = 0; - } - } - - return 1; -} -
diff --git a/emitterc.go b/emitterc.go new file mode 100644 index 0000000..ac63f28 --- /dev/null +++ b/emitterc.go
@@ -0,0 +1,1682 @@ +package goyaml + +import ( + "bytes" +) + +// Flush the buffer if needed. +func flush(emitter *yaml_emitter_t) bool { + if emitter.buffer_pos+5 >= len(emitter.buffer) { + return yaml_emitter_flush(emitter) + } + return true +} + +// Put a character to the output buffer. +func put(emitter *yaml_emitter_t, value byte) bool { + if emitter.buffer_pos+5 >= len(emitter.buffer) && !yaml_emitter_flush(emitter) { + return false + } + emitter.buffer[emitter.buffer_pos] = value + emitter.buffer_pos++ + emitter.column++ + return true +} + +// Put a line break to the output buffer. +func put_break(emitter *yaml_emitter_t) bool { + if emitter.buffer_pos+5 >= len(emitter.buffer) && !yaml_emitter_flush(emitter) { + return false + } + switch emitter.line_break { + case yaml_CR_BREAK: + emitter.buffer[emitter.buffer_pos] = '\r' + emitter.buffer_pos += 1 + case yaml_LN_BREAK: + emitter.buffer[emitter.buffer_pos] = '\n' + emitter.buffer_pos += 1 + case yaml_CRLN_BREAK: + emitter.buffer[emitter.buffer_pos+0] = '\r' + emitter.buffer[emitter.buffer_pos+1] = '\n' + emitter.buffer_pos += 2 + default: + panic("unknown line break setting") + } + emitter.column = 0 + emitter.line++ + return true +} + +// Copy a character from a string into buffer. +func write(emitter *yaml_emitter_t, s []byte, i *int) bool { + if emitter.buffer_pos+5 >= len(emitter.buffer) && !yaml_emitter_flush(emitter) { + return false + } + p := emitter.buffer_pos + w := width(s[*i]) + switch w { + case 4: + emitter.buffer[p+3] = s[*i+3] + fallthrough + case 3: + emitter.buffer[p+2] = s[*i+2] + fallthrough + case 2: + emitter.buffer[p+1] = s[*i+1] + fallthrough + case 1: + emitter.buffer[p+0] = s[*i+0] + default: + panic("unknown character width") + } + emitter.column++ + emitter.buffer_pos += w + *i += w + return true +} + +// Write a whole string into buffer. +func write_all(emitter *yaml_emitter_t, s []byte) bool { + for i := 0; i < len(s); { + if !write(emitter, s, &i) { + return false + } + } + return true +} + +// Copy a line break character from a string into buffer. +func write_break(emitter *yaml_emitter_t, s []byte, i *int) bool { + if s[*i] == '\n' { + if !put_break(emitter) { + return false + } + *i++ + } else { + if !write(emitter, s, i) { + return false + } + emitter.column = 0 + emitter.line++ + } + return true +} + +// Set an emitter error and return false. +func yaml_emitter_set_emitter_error(emitter *yaml_emitter_t, problem string) bool { + emitter.error = yaml_EMITTER_ERROR + emitter.problem = problem + return false +} + +// Emit an event. +func yaml_emitter_emit(emitter *yaml_emitter_t, event *yaml_event_t) bool { + emitter.events = append(emitter.events, *event) + for !yaml_emitter_need_more_events(emitter) { + event := &emitter.events[emitter.events_head] + if !yaml_emitter_analyze_event(emitter, event) { + return false + } + if !yaml_emitter_state_machine(emitter, event) { + return false + } + yaml_event_delete(event) + emitter.events_head++ + } + return true +} + +// Check if we need to accumulate more events before emitting. +// +// We accumulate extra +// - 1 event for DOCUMENT-START +// - 2 events for SEQUENCE-START +// - 3 events for MAPPING-START +// +func yaml_emitter_need_more_events(emitter *yaml_emitter_t) bool { + if emitter.events_head == len(emitter.events) { + return true + } + var accumulate int + switch emitter.events[emitter.events_head].typ { + case yaml_DOCUMENT_START_EVENT: + accumulate = 1 + break + case yaml_SEQUENCE_START_EVENT: + accumulate = 2 + break + case yaml_MAPPING_START_EVENT: + accumulate = 3 + break + default: + return false + } + if len(emitter.events)-emitter.events_head > accumulate { + return false + } + var level int + for i := emitter.events_head; i < len(emitter.events); i++ { + switch emitter.events[i].typ { + case yaml_STREAM_START_EVENT, yaml_DOCUMENT_START_EVENT, yaml_SEQUENCE_START_EVENT, yaml_MAPPING_START_EVENT: + level++ + case yaml_STREAM_END_EVENT, yaml_DOCUMENT_END_EVENT, yaml_SEQUENCE_END_EVENT, yaml_MAPPING_END_EVENT: + level-- + } + if level == 0 { + return false + } + } + return true +} + +// Append a directive to the directives stack. +func yaml_emitter_append_tag_directive(emitter *yaml_emitter_t, value *yaml_tag_directive_t, allow_duplicates bool) bool { + for i := 0; i < len(emitter.tag_directives); i++ { + if bytes.Equal(value.handle, emitter.tag_directives[i].handle) { + if allow_duplicates { + return true + } + return yaml_emitter_set_emitter_error(emitter, "duplicate %TAG directive") + } + } + + // [Go] Do we actually need to copy this given garbage collection + // and the lack of deallocating destructors? + tag_copy := yaml_tag_directive_t{ + handle: make([]byte, len(value.handle)), + prefix: make([]byte, len(value.prefix)), + } + copy(tag_copy.handle, value.handle) + copy(tag_copy.prefix, value.prefix) + emitter.tag_directives = append(emitter.tag_directives, tag_copy) + return true +} + +// Increase the indentation level. +func yaml_emitter_increase_indent(emitter *yaml_emitter_t, flow, indentless bool) bool { + emitter.indents = append(emitter.indents, emitter.indent) + if emitter.indent < 0 { + if flow { + emitter.indent = emitter.best_indent + } else { + emitter.indent = 0 + } + } else if !indentless { + emitter.indent += emitter.best_indent + } + return true +} + +// State dispatcher. +func yaml_emitter_state_machine(emitter *yaml_emitter_t, event *yaml_event_t) bool { + switch emitter.state { + default: + case yaml_EMIT_STREAM_START_STATE: + return yaml_emitter_emit_stream_start(emitter, event) + + case yaml_EMIT_FIRST_DOCUMENT_START_STATE: + return yaml_emitter_emit_document_start(emitter, event, true) + + case yaml_EMIT_DOCUMENT_START_STATE: + return yaml_emitter_emit_document_start(emitter, event, false) + + case yaml_EMIT_DOCUMENT_CONTENT_STATE: + return yaml_emitter_emit_document_content(emitter, event) + + case yaml_EMIT_DOCUMENT_END_STATE: + return yaml_emitter_emit_document_end(emitter, event) + + case yaml_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE: + return yaml_emitter_emit_flow_sequence_item(emitter, event, true) + + case yaml_EMIT_FLOW_SEQUENCE_ITEM_STATE: + return yaml_emitter_emit_flow_sequence_item(emitter, event, false) + + case yaml_EMIT_FLOW_MAPPING_FIRST_KEY_STATE: + return yaml_emitter_emit_flow_mapping_key(emitter, event, true) + + case yaml_EMIT_FLOW_MAPPING_KEY_STATE: + return yaml_emitter_emit_flow_mapping_key(emitter, event, false) + + case yaml_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE: + return yaml_emitter_emit_flow_mapping_value(emitter, event, true) + + case yaml_EMIT_FLOW_MAPPING_VALUE_STATE: + return yaml_emitter_emit_flow_mapping_value(emitter, event, false) + + case yaml_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE: + return yaml_emitter_emit_block_sequence_item(emitter, event, true) + + case yaml_EMIT_BLOCK_SEQUENCE_ITEM_STATE: + return yaml_emitter_emit_block_sequence_item(emitter, event, false) + + case yaml_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE: + return yaml_emitter_emit_block_mapping_key(emitter, event, true) + + case yaml_EMIT_BLOCK_MAPPING_KEY_STATE: + return yaml_emitter_emit_block_mapping_key(emitter, event, false) + + case yaml_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE: + return yaml_emitter_emit_block_mapping_value(emitter, event, true) + + case yaml_EMIT_BLOCK_MAPPING_VALUE_STATE: + return yaml_emitter_emit_block_mapping_value(emitter, event, false) + + case yaml_EMIT_END_STATE: + return yaml_emitter_set_emitter_error(emitter, "expected nothing after STREAM-END") + } + panic("invalid emitter state") +} + +// Expect STREAM-START. +func yaml_emitter_emit_stream_start(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if event.typ != yaml_STREAM_START_EVENT { + return yaml_emitter_set_emitter_error(emitter, "expected STREAM-START") + } + if emitter.encoding == yaml_ANY_ENCODING { + emitter.encoding = event.encoding + if emitter.encoding == yaml_ANY_ENCODING { + emitter.encoding = yaml_UTF8_ENCODING + } + } + if emitter.best_indent < 2 || emitter.best_indent > 9 { + emitter.best_indent = 2 + } + if emitter.best_width >= 0 && emitter.best_width <= emitter.best_indent*2 { + emitter.best_width = 80 + } + if emitter.best_width < 0 { + emitter.best_width = 1<<31 - 1 + } + if emitter.line_break == yaml_ANY_BREAK { + emitter.line_break = yaml_LN_BREAK + } + + emitter.indent = -1 + emitter.line = 0 + emitter.column = 0 + emitter.whitespace = true + emitter.indention = true + + if emitter.encoding != yaml_UTF8_ENCODING { + if !yaml_emitter_write_bom(emitter) { + return false + } + } + emitter.state = yaml_EMIT_FIRST_DOCUMENT_START_STATE + return true +} + +// Expect DOCUMENT-START or STREAM-END. +func yaml_emitter_emit_document_start(emitter *yaml_emitter_t, event *yaml_event_t, first bool) bool { + + if event.typ == yaml_DOCUMENT_START_EVENT { + + if event.version_directive != nil { + if !yaml_emitter_analyze_version_directive(emitter, event.version_directive) { + return false + } + } + + for i := 0; i < len(event.tag_directives); i++ { + tag_directive := &event.tag_directives[i] + if !yaml_emitter_analyze_tag_directive(emitter, tag_directive) { + return false + } + if !yaml_emitter_append_tag_directive(emitter, tag_directive, false) { + return false + } + } + + for i := 0; i < len(default_tag_directives); i++ { + tag_directive := &default_tag_directives[i] + if !yaml_emitter_append_tag_directive(emitter, tag_directive, true) { + return false + } + } + + implicit := event.implicit + if !first || emitter.canonical { + implicit = false + } + + if emitter.open_ended && (event.version_directive != nil || len(event.tag_directives) > 0) { + if !yaml_emitter_write_indicator(emitter, []byte("..."), true, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + + if event.version_directive != nil { + implicit = false + if !yaml_emitter_write_indicator(emitter, []byte("%YAML"), true, false, false) { + return false + } + if !yaml_emitter_write_indicator(emitter, []byte("1.1"), true, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + + if len(event.tag_directives) > 0 { + implicit = false + for i := 0; i < len(event.tag_directives); i++ { + tag_directive := &event.tag_directives[i] + if !yaml_emitter_write_indicator(emitter, []byte("%TAG"), true, false, false) { + return false + } + if !yaml_emitter_write_tag_handle(emitter, tag_directive.handle) { + return false + } + if !yaml_emitter_write_tag_content(emitter, tag_directive.prefix, true) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + } + + if yaml_emitter_check_empty_document(emitter) { + implicit = false + } + if !implicit { + if !yaml_emitter_write_indent(emitter) { + return false + } + if !yaml_emitter_write_indicator(emitter, []byte("---"), true, false, false) { + return false + } + if emitter.canonical { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + } + + emitter.state = yaml_EMIT_DOCUMENT_CONTENT_STATE + return true + } + + if event.typ == yaml_STREAM_END_EVENT { + if emitter.open_ended { + if !yaml_emitter_write_indicator(emitter, []byte("..."), true, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !yaml_emitter_flush(emitter) { + return false + } + emitter.state = yaml_EMIT_END_STATE + return true + } + + return yaml_emitter_set_emitter_error(emitter, "expected DOCUMENT-START or STREAM-END") +} + +// Expect the root node. +func yaml_emitter_emit_document_content(emitter *yaml_emitter_t, event *yaml_event_t) bool { + emitter.states = append(emitter.states, yaml_EMIT_DOCUMENT_END_STATE) + return yaml_emitter_emit_node(emitter, event, true, false, false, false) +} + +// Expect DOCUMENT-END. +func yaml_emitter_emit_document_end(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if event.typ != yaml_DOCUMENT_END_EVENT { + return yaml_emitter_set_emitter_error(emitter, "expected DOCUMENT-END") + } + if !yaml_emitter_write_indent(emitter) { + return false + } + if !event.implicit { + // [Go] Allocate the slice elsewhere. + if !yaml_emitter_write_indicator(emitter, []byte("..."), true, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !yaml_emitter_flush(emitter) { + return false + } + emitter.state = yaml_EMIT_DOCUMENT_START_STATE + emitter.tag_directives = emitter.tag_directives[:0] + return true +} + +// Expect a flow item node. +func yaml_emitter_emit_flow_sequence_item(emitter *yaml_emitter_t, event *yaml_event_t, first bool) bool { + if first { + if !yaml_emitter_write_indicator(emitter, []byte{'['}, true, true, false) { + return false + } + if !yaml_emitter_increase_indent(emitter, true, false) { + return false + } + emitter.flow_level++ + } + + if event.typ == yaml_SEQUENCE_END_EVENT { + emitter.flow_level-- + emitter.indent = emitter.indents[len(emitter.indents)-1] + emitter.indents = emitter.indents[:len(emitter.indents)-1] + if emitter.canonical && !first { + if !yaml_emitter_write_indicator(emitter, []byte{','}, false, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !yaml_emitter_write_indicator(emitter, []byte{']'}, false, false, false) { + return false + } + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + + return true + } + + if !first { + if !yaml_emitter_write_indicator(emitter, []byte{','}, false, false, false) { + return false + } + } + + if emitter.canonical || emitter.column > emitter.best_width { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + emitter.states = append(emitter.states, yaml_EMIT_FLOW_SEQUENCE_ITEM_STATE) + return yaml_emitter_emit_node(emitter, event, false, true, false, false) +} + +// Expect a flow key node. +func yaml_emitter_emit_flow_mapping_key(emitter *yaml_emitter_t, event *yaml_event_t, first bool) bool { + if first { + if !yaml_emitter_write_indicator(emitter, []byte{'{'}, true, true, false) { + return false + } + if !yaml_emitter_increase_indent(emitter, true, false) { + return false + } + emitter.flow_level++ + } + + if event.typ == yaml_MAPPING_END_EVENT { + emitter.flow_level-- + emitter.indent = emitter.indents[len(emitter.indents)-1] + emitter.indents = emitter.indents[:len(emitter.indents)-1] + if emitter.canonical && !first { + if !yaml_emitter_write_indicator(emitter, []byte{','}, false, false, false) { + return false + } + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !yaml_emitter_write_indicator(emitter, []byte{'}'}, false, false, false) { + return false + } + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + return true + } + + if !first { + if !yaml_emitter_write_indicator(emitter, []byte{','}, false, false, false) { + return false + } + } + if emitter.canonical || emitter.column > emitter.best_width { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + + if !emitter.canonical && yaml_emitter_check_simple_key(emitter) { + emitter.states = append(emitter.states, yaml_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, true) + } + if !yaml_emitter_write_indicator(emitter, []byte{'?'}, true, false, false) { + return false + } + emitter.states = append(emitter.states, yaml_EMIT_FLOW_MAPPING_VALUE_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, false) +} + +// Expect a flow value node. +func yaml_emitter_emit_flow_mapping_value(emitter *yaml_emitter_t, event *yaml_event_t, simple bool) bool { + if simple { + if !yaml_emitter_write_indicator(emitter, []byte{':'}, false, false, false) { + return false + } + } else { + if emitter.canonical || emitter.column > emitter.best_width { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !yaml_emitter_write_indicator(emitter, []byte{':'}, true, false, false) { + return false + } + } + emitter.states = append(emitter.states, yaml_EMIT_FLOW_MAPPING_KEY_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, false) +} + +// Expect a block item node. +func yaml_emitter_emit_block_sequence_item(emitter *yaml_emitter_t, event *yaml_event_t, first bool) bool { + if first { + if !yaml_emitter_increase_indent(emitter, false, emitter.mapping_context && !emitter.indention) { + return false + } + } + if event.typ == yaml_SEQUENCE_END_EVENT { + emitter.indent = emitter.indents[len(emitter.indents)-1] + emitter.indents = emitter.indents[:len(emitter.indents)-1] + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + return true + } + if !yaml_emitter_write_indent(emitter) { + return false + } + if !yaml_emitter_write_indicator(emitter, []byte{'-'}, true, false, true) { + return false + } + emitter.states = append(emitter.states, yaml_EMIT_BLOCK_SEQUENCE_ITEM_STATE) + return yaml_emitter_emit_node(emitter, event, false, true, false, false) +} + +// Expect a block key node. +func yaml_emitter_emit_block_mapping_key(emitter *yaml_emitter_t, event *yaml_event_t, first bool) bool { + if first { + if !yaml_emitter_increase_indent(emitter, false, false) { + return false + } + } + if event.typ == yaml_MAPPING_END_EVENT { + emitter.indent = emitter.indents[len(emitter.indents)-1] + emitter.indents = emitter.indents[:len(emitter.indents)-1] + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + return true + } + if !yaml_emitter_write_indent(emitter) { + return false + } + if yaml_emitter_check_simple_key(emitter) { + emitter.states = append(emitter.states, yaml_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, true) + } + if !yaml_emitter_write_indicator(emitter, []byte{'?'}, true, false, true) { + return false + } + emitter.states = append(emitter.states, yaml_EMIT_BLOCK_MAPPING_VALUE_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, false) +} + +// Expect a block value node. +func yaml_emitter_emit_block_mapping_value(emitter *yaml_emitter_t, event *yaml_event_t, simple bool) bool { + if simple { + if !yaml_emitter_write_indicator(emitter, []byte{':'}, false, false, false) { + return false + } + } else { + if !yaml_emitter_write_indent(emitter) { + return false + } + if !yaml_emitter_write_indicator(emitter, []byte{':'}, true, false, true) { + return false + } + } + emitter.states = append(emitter.states, yaml_EMIT_BLOCK_MAPPING_KEY_STATE) + return yaml_emitter_emit_node(emitter, event, false, false, true, false) +} + +// Expect a node. +func yaml_emitter_emit_node(emitter *yaml_emitter_t, event *yaml_event_t, + root bool, sequence bool, mapping bool, simple_key bool) bool { + + emitter.root_context = root + emitter.sequence_context = sequence + emitter.mapping_context = mapping + emitter.simple_key_context = simple_key + + switch event.typ { + case yaml_ALIAS_EVENT: + return yaml_emitter_emit_alias(emitter, event) + case yaml_SCALAR_EVENT: + return yaml_emitter_emit_scalar(emitter, event) + case yaml_SEQUENCE_START_EVENT: + return yaml_emitter_emit_sequence_start(emitter, event) + case yaml_MAPPING_START_EVENT: + return yaml_emitter_emit_mapping_start(emitter, event) + default: + return yaml_emitter_set_emitter_error(emitter, + "expected SCALAR, SEQUENCE-START, MAPPING-START, or ALIAS") + } + return false +} + +// Expect ALIAS. +func yaml_emitter_emit_alias(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if !yaml_emitter_process_anchor(emitter) { + return false + } + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + return true +} + +// Expect SCALAR. +func yaml_emitter_emit_scalar(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if !yaml_emitter_select_scalar_style(emitter, event) { + return false + } + if !yaml_emitter_process_anchor(emitter) { + return false + } + if !yaml_emitter_process_tag(emitter) { + return false + } + if !yaml_emitter_increase_indent(emitter, true, false) { + return false + } + if !yaml_emitter_process_scalar(emitter) { + return false + } + emitter.indent = emitter.indents[len(emitter.indents)-1] + emitter.indents = emitter.indents[:len(emitter.indents)-1] + emitter.state = emitter.states[len(emitter.states)-1] + emitter.states = emitter.states[:len(emitter.states)-1] + return true +} + +// Expect SEQUENCE-START. +func yaml_emitter_emit_sequence_start(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if !yaml_emitter_process_anchor(emitter) { + return false + } + if !yaml_emitter_process_tag(emitter) { + return false + } + if emitter.flow_level > 0 || emitter.canonical || event.sequence_style() == yaml_FLOW_SEQUENCE_STYLE || + yaml_emitter_check_empty_sequence(emitter) { + emitter.state = yaml_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE + } else { + emitter.state = yaml_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE + } + return true +} + +// Expect MAPPING-START. +func yaml_emitter_emit_mapping_start(emitter *yaml_emitter_t, event *yaml_event_t) bool { + if !yaml_emitter_process_anchor(emitter) { + return false + } + if !yaml_emitter_process_tag(emitter) { + return false + } + if emitter.flow_level > 0 || emitter.canonical || event.mapping_style() == yaml_FLOW_MAPPING_STYLE || + yaml_emitter_check_empty_mapping(emitter) { + emitter.state = yaml_EMIT_FLOW_MAPPING_FIRST_KEY_STATE + } else { + emitter.state = yaml_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE + } + return true +} + +// Check if the document content is an empty scalar. +func yaml_emitter_check_empty_document(emitter *yaml_emitter_t) bool { + return false // [Go] Huh? +} + +// Check if the next events represent an empty sequence. +func yaml_emitter_check_empty_sequence(emitter *yaml_emitter_t) bool { + if len(emitter.events)-emitter.events_head < 2 { + return false + } + return emitter.events[emitter.events_head].typ == yaml_SEQUENCE_START_EVENT && + emitter.events[emitter.events_head+1].typ == yaml_SEQUENCE_END_EVENT +} + +// Check if the next events represent an empty mapping. +func yaml_emitter_check_empty_mapping(emitter *yaml_emitter_t) bool { + if len(emitter.events)-emitter.events_head < 2 { + return false + } + return emitter.events[emitter.events_head].typ == yaml_MAPPING_START_EVENT && + emitter.events[emitter.events_head+1].typ == yaml_MAPPING_END_EVENT +} + +// Check if the next node can be expressed as a simple key. +func yaml_emitter_check_simple_key(emitter *yaml_emitter_t) bool { + length := 0 + switch emitter.events[emitter.events_head].typ { + case yaml_ALIAS_EVENT: + length += len(emitter.anchor_data.anchor) + case yaml_SCALAR_EVENT: + if emitter.scalar_data.multiline { + return false + } + length += len(emitter.anchor_data.anchor) + + len(emitter.tag_data.handle) + + len(emitter.tag_data.suffix) + + len(emitter.scalar_data.value) + case yaml_SEQUENCE_START_EVENT: + if !yaml_emitter_check_empty_sequence(emitter) { + return false + } + length += len(emitter.anchor_data.anchor) + + len(emitter.tag_data.handle) + + len(emitter.tag_data.suffix) + case yaml_MAPPING_START_EVENT: + if !yaml_emitter_check_empty_mapping(emitter) { + return false + } + length += len(emitter.anchor_data.anchor) + + len(emitter.tag_data.handle) + + len(emitter.tag_data.suffix) + default: + return false + } + return length <= 128 +} + +// Determine an acceptable scalar style. +func yaml_emitter_select_scalar_style(emitter *yaml_emitter_t, event *yaml_event_t) bool { + + no_tag := len(emitter.tag_data.handle) == 0 && len(emitter.tag_data.suffix) == 0 + if no_tag && !event.implicit && !event.quoted_implicit { + return yaml_emitter_set_emitter_error(emitter, "neither tag nor implicit flags are specified") + } + + style := event.scalar_style() + if style == yaml_ANY_SCALAR_STYLE { + style = yaml_PLAIN_SCALAR_STYLE + } + if emitter.canonical { + style = yaml_DOUBLE_QUOTED_SCALAR_STYLE + } + if emitter.simple_key_context && emitter.scalar_data.multiline { + style = yaml_DOUBLE_QUOTED_SCALAR_STYLE + } + + if style == yaml_PLAIN_SCALAR_STYLE { + if emitter.flow_level > 0 && !emitter.scalar_data.flow_plain_allowed || + emitter.flow_level == 0 && !emitter.scalar_data.block_plain_allowed { + style = yaml_SINGLE_QUOTED_SCALAR_STYLE + } + if len(emitter.scalar_data.value) == 0 && (emitter.flow_level > 0 || emitter.simple_key_context) { + style = yaml_SINGLE_QUOTED_SCALAR_STYLE + } + if no_tag && !event.implicit { + style = yaml_SINGLE_QUOTED_SCALAR_STYLE + } + } + if style == yaml_SINGLE_QUOTED_SCALAR_STYLE { + if !emitter.scalar_data.single_quoted_allowed { + style = yaml_DOUBLE_QUOTED_SCALAR_STYLE + } + } + if style == yaml_LITERAL_SCALAR_STYLE || style == yaml_FOLDED_SCALAR_STYLE { + if !emitter.scalar_data.block_allowed || emitter.flow_level > 0 || emitter.simple_key_context { + style = yaml_DOUBLE_QUOTED_SCALAR_STYLE + } + } + + if no_tag && !event.quoted_implicit && style != yaml_PLAIN_SCALAR_STYLE { + emitter.tag_data.handle = []byte{'!'} + } + emitter.scalar_data.style = style + return true +} + +// Write an achor. +func yaml_emitter_process_anchor(emitter *yaml_emitter_t) bool { + if emitter.anchor_data.anchor == nil { + return true + } + c := []byte{'&'} + if emitter.anchor_data.alias { + c[0] = '*' + } + if !yaml_emitter_write_indicator(emitter, c, true, false, false) { + return false + } + return yaml_emitter_write_anchor(emitter, emitter.anchor_data.anchor) +} + +// Write a tag. +func yaml_emitter_process_tag(emitter *yaml_emitter_t) bool { + if len(emitter.tag_data.handle) == 0 && len(emitter.tag_data.suffix) == 0 { + return true + } + if len(emitter.tag_data.handle) > 0 { + if !yaml_emitter_write_tag_handle(emitter, emitter.tag_data.handle) { + return false + } + if len(emitter.tag_data.suffix) > 0 { + if !yaml_emitter_write_tag_content(emitter, emitter.tag_data.suffix, false) { + return false + } + } + } else { + // [Go] Allocate these slices elsewhere. + if !yaml_emitter_write_indicator(emitter, []byte("!<"), true, false, false) { + return false + } + if !yaml_emitter_write_tag_content(emitter, emitter.tag_data.suffix, false) { + return false + } + if !yaml_emitter_write_indicator(emitter, []byte{'>'}, false, false, false) { + return false + } + } + return true +} + +// Write a scalar. +func yaml_emitter_process_scalar(emitter *yaml_emitter_t) bool { + switch emitter.scalar_data.style { + case yaml_PLAIN_SCALAR_STYLE: + return yaml_emitter_write_plain_scalar(emitter, emitter.scalar_data.value, !emitter.simple_key_context) + + case yaml_SINGLE_QUOTED_SCALAR_STYLE: + return yaml_emitter_write_single_quoted_scalar(emitter, emitter.scalar_data.value, !emitter.simple_key_context) + + case yaml_DOUBLE_QUOTED_SCALAR_STYLE: + return yaml_emitter_write_double_quoted_scalar(emitter, emitter.scalar_data.value, !emitter.simple_key_context) + + case yaml_LITERAL_SCALAR_STYLE: + return yaml_emitter_write_literal_scalar(emitter, emitter.scalar_data.value) + + case yaml_FOLDED_SCALAR_STYLE: + return yaml_emitter_write_folded_scalar(emitter, emitter.scalar_data.value) + } + panic("unknown scalar style") +} + +// Check if a %YAML directive is valid. +func yaml_emitter_analyze_version_directive(emitter *yaml_emitter_t, version_directive *yaml_version_directive_t) bool { + if version_directive.major != 1 || version_directive.minor != 1 { + return yaml_emitter_set_emitter_error(emitter, "incompatible %YAML directive") + } + return true +} + +// Check if a %TAG directive is valid. +func yaml_emitter_analyze_tag_directive(emitter *yaml_emitter_t, tag_directive *yaml_tag_directive_t) bool { + handle := tag_directive.handle + prefix := tag_directive.prefix + if len(handle) == 0 { + return yaml_emitter_set_emitter_error(emitter, "tag handle must not be empty") + } + if handle[0] != '!' { + return yaml_emitter_set_emitter_error(emitter, "tag handle must start with '!'") + } + if handle[len(handle)-1] != '!' { + return yaml_emitter_set_emitter_error(emitter, "tag handle must end with '!'") + } + for i := 1; i < len(handle)-1; i += width(handle[i]) { + if !is_alpha(handle, i) { + return yaml_emitter_set_emitter_error(emitter, "tag handle must contain alphanumerical characters only") + } + } + if len(prefix) == 0 { + return yaml_emitter_set_emitter_error(emitter, "tag prefix must not be empty") + } + return true +} + +// Check if an anchor is valid. +func yaml_emitter_analyze_anchor(emitter *yaml_emitter_t, anchor []byte, alias bool) bool { + if len(anchor) == 0 { + problem := "anchor value must not be empty" + if alias { + problem = "alias value must not be empty" + } + return yaml_emitter_set_emitter_error(emitter, problem) + } + for i := 0; i < len(anchor); i += width(anchor[i]) { + if !is_alpha(anchor, i) { + problem := "anchor value must contain alphanumerical characters only" + if alias { + problem = "alias value must contain alphanumerical characters only" + } + return yaml_emitter_set_emitter_error(emitter, problem) + } + } + emitter.anchor_data.anchor = anchor + emitter.anchor_data.alias = alias + return true +} + +// Check if a tag is valid. +func yaml_emitter_analyze_tag(emitter *yaml_emitter_t, tag []byte) bool { + if len(tag) == 0 { + return yaml_emitter_set_emitter_error(emitter, "tag value must not be empty") + } + for i := 0; i < len(emitter.tag_directives); i++ { + tag_directive := &emitter.tag_directives[i] + if bytes.HasPrefix(tag, tag_directive.prefix) { + emitter.tag_data.handle = tag_directive.handle + emitter.tag_data.suffix = tag[len(tag_directive.prefix):] + } + return true + } + emitter.tag_data.suffix = tag + return true +} + +// Check if a scalar is valid. +func yaml_emitter_analyze_scalar(emitter *yaml_emitter_t, value []byte) bool { + var ( + block_indicators = false + flow_indicators = false + line_breaks = false + special_characters = false + + leading_space = false + leading_break = false + trailing_space = false + trailing_break = false + break_space = false + space_break = false + + preceeded_by_whitespace = false + followed_by_whitespace = false + previous_space = false + previous_break = false + ) + + emitter.scalar_data.value = value + + if len(value) == 0 { + emitter.scalar_data.multiline = false + emitter.scalar_data.flow_plain_allowed = false + emitter.scalar_data.block_plain_allowed = true + emitter.scalar_data.single_quoted_allowed = true + emitter.scalar_data.block_allowed = false + return true + } + + if (value[0] == '-' && value[1] == '-' && value[2] == '-') || (value[0] == '.' && value[1] == '.' && value[2] == '.') { + block_indicators = true + flow_indicators = true + } + + preceeded_by_whitespace = true + for i, w := 0, 0; i < len(value); i += w { + w = width(value[0]) + followed_by_whitespace = i+w >= len(value) || is_blank(value, i+w) + + if i == 0 { + switch value[i] { + case '#', ',', '[', ']', '{', '}', '&', '*', '!', '|', '>', '\'', '"', '%', '@', '`': + flow_indicators = true + block_indicators = true + case '?', ':': + flow_indicators = true + if followed_by_whitespace { + block_indicators = true + } + case '-': + if followed_by_whitespace { + flow_indicators = true + block_indicators = true + } + } + } else { + switch value[i] { + case ',', '?', '[', ']', '{', '}': + flow_indicators = true + case ':': + flow_indicators = true + if followed_by_whitespace { + block_indicators = true + } + case '#': + if preceeded_by_whitespace { + flow_indicators = true + block_indicators = true + } + } + } + + if !is_printable(value, i) || !is_ascii(value, i) && !emitter.unicode { + special_characters = true + } + if is_space(value, i) { + if i == 0 { + leading_space = true + } + if i+width(value[i]) == len(value) { + trailing_space = true + } + if previous_break { + break_space = true + } + previous_space = true + previous_break = false + } else if is_break(value, i) { + line_breaks = true + if i == 0 { + leading_break = true + } + if i+width(value[i]) == len(value) { + trailing_break = true + } + if previous_space { + space_break = true + } + previous_space = false + previous_break = true + } else { + previous_space = false + previous_break = false + } + + // [Go]: Why 'z'? Couldn't be the end of the string as that's the loop condition. + preceeded_by_whitespace = is_blankz(value, i) + } + + emitter.scalar_data.multiline = line_breaks + emitter.scalar_data.flow_plain_allowed = true + emitter.scalar_data.block_plain_allowed = true + emitter.scalar_data.single_quoted_allowed = true + emitter.scalar_data.block_allowed = true + + if leading_space || leading_break || trailing_space || trailing_break { + emitter.scalar_data.flow_plain_allowed = false + emitter.scalar_data.block_plain_allowed = false + } + if trailing_space { + emitter.scalar_data.block_allowed = false + } + if break_space { + emitter.scalar_data.flow_plain_allowed = false + emitter.scalar_data.block_plain_allowed = false + emitter.scalar_data.single_quoted_allowed = false + } + if space_break || special_characters { + emitter.scalar_data.flow_plain_allowed = false + emitter.scalar_data.block_plain_allowed = false + emitter.scalar_data.single_quoted_allowed = false + emitter.scalar_data.block_allowed = false + } + if line_breaks { + emitter.scalar_data.flow_plain_allowed = false + emitter.scalar_data.block_plain_allowed = false + } + if flow_indicators { + emitter.scalar_data.flow_plain_allowed = false + } + if block_indicators { + emitter.scalar_data.block_plain_allowed = false + } + return true +} + +// Check if the event data is valid. +func yaml_emitter_analyze_event(emitter *yaml_emitter_t, event *yaml_event_t) bool { + + emitter.anchor_data.anchor = nil + emitter.tag_data.handle = nil + emitter.tag_data.suffix = nil + emitter.scalar_data.value = nil + + switch event.typ { + case yaml_ALIAS_EVENT: + if !yaml_emitter_analyze_anchor(emitter, event.anchor, true) { + return false + } + + case yaml_SCALAR_EVENT: + if len(event.anchor) > 0 { + if !yaml_emitter_analyze_anchor(emitter, event.anchor, false) { + return false + } + } + if len(event.tag) > 0 && (emitter.canonical || (!event.implicit && !event.quoted_implicit)) { + if !yaml_emitter_analyze_tag(emitter, event.tag) { + return false + } + } + if !yaml_emitter_analyze_scalar(emitter, event.value) { + return false + } + + case yaml_SEQUENCE_START_EVENT: + if len(event.anchor) > 0 { + if !yaml_emitter_analyze_anchor(emitter, event.anchor, false) { + return false + } + } + if len(event.tag) > 0 && (emitter.canonical || !event.implicit) { + if !yaml_emitter_analyze_tag(emitter, event.tag) { + return false + } + } + + case yaml_MAPPING_START_EVENT: + if len(event.anchor) > 0 { + if !yaml_emitter_analyze_anchor(emitter, event.anchor, false) { + return false + } + } + if len(event.tag) > 0 && (emitter.canonical || !event.implicit) { + if !yaml_emitter_analyze_tag(emitter, event.tag) { + return false + } + } + } + return true +} + +// Write the BOM character. +func yaml_emitter_write_bom(emitter *yaml_emitter_t) bool { + if !flush(emitter) { + return false + } + pos := emitter.buffer_pos + emitter.buffer[pos+0] = '\xEF' + emitter.buffer[pos+1] = '\xBB' + emitter.buffer[pos+2] = '\xBF' + emitter.buffer_pos += 3 + return true +} + +func yaml_emitter_write_indent(emitter *yaml_emitter_t) bool { + indent := emitter.indent + if indent < 0 { + indent = 0 + } + if !emitter.indention || emitter.column > indent || (emitter.column == indent && !emitter.whitespace) { + if !put_break(emitter) { + return false + } + } + for emitter.column < indent { + if !put(emitter, ' ') { + return false + } + } + emitter.whitespace = true + emitter.indention = true + return true +} + +func yaml_emitter_write_indicator(emitter *yaml_emitter_t, indicator []byte, need_whitespace, is_whitespace, is_indention bool) bool { + if need_whitespace && !emitter.whitespace { + if !put(emitter, ' ') { + return false + } + } + if !write_all(emitter, indicator) { + return false + } + emitter.whitespace = is_whitespace + emitter.indention = (emitter.indention && is_indention) + emitter.open_ended = false + return true +} + +func yaml_emitter_write_anchor(emitter *yaml_emitter_t, value []byte) bool { + if !write_all(emitter, value) { + return false + } + emitter.whitespace = false + emitter.indention = false + return true +} + +func yaml_emitter_write_tag_handle(emitter *yaml_emitter_t, value []byte) bool { + if !emitter.whitespace { + if !put(emitter, ' ') { + return false + } + } + if !write_all(emitter, value) { + return false + } + emitter.whitespace = false + emitter.indention = false + return true +} + +func yaml_emitter_write_tag_content(emitter *yaml_emitter_t, value []byte, need_whitespace bool) bool { + if need_whitespace && !emitter.whitespace { + if !put(emitter, ' ') { + return false + } + } + for i := 0; i < len(value); { + var must_write bool + switch value[i] { + case ';', '/', '?', ':', '@', '&', '=', '+', '$', ',', '_', '.', '~', '*', '\'', '(', ')', '[', ']': + must_write = true + default: + must_write = is_alpha(value, i) + } + if must_write { + if !write(emitter, value, &i) { + return false + } + } else { + w := width(value[i]) + for k := 0; k < w; k++ { + octet := value[i] + i++ + + c := octet >> 4 + if c < 10 { + c += '0' + } else { + c += 'A' - 10 + } + if !put(emitter, c) { + return false + } + + c = octet & 0x0f + if c < 10 { + c += '0' + } else { + c += 'A' - 10 + } + if !put(emitter, c) { + return false + } + } + } + } + emitter.whitespace = false + emitter.indention = false + return true +} + +func yaml_emitter_write_plain_scalar(emitter *yaml_emitter_t, value []byte, allow_breaks bool) bool { + if !emitter.whitespace { + if !put(emitter, ' ') { + return false + } + } + + spaces := false + breaks := false + for i := 0; i < len(value); { + if is_space(value, i) { + if allow_breaks && !spaces && emitter.column > emitter.best_width && !is_space(value, i+1) { + if !yaml_emitter_write_indent(emitter) { + return false + } + i += width(value[i]) + } else { + if !write(emitter, value, &i) { + return false + } + } + spaces = true + } else if is_break(value, i) { + if !breaks && value[i] == '\n' { + if !put_break(emitter) { + return false + } + } + if !write_break(emitter, value, &i) { + return false + } + emitter.indention = true + breaks = true + } else { + if breaks { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !write(emitter, value, &i) { + return false + } + emitter.indention = false + spaces = false + breaks = false + } + } + + emitter.whitespace = false + emitter.indention = false + if emitter.root_context { + emitter.open_ended = true + } + + return true +} + +func yaml_emitter_write_single_quoted_scalar(emitter *yaml_emitter_t, value []byte, allow_breaks bool) bool { + + if !yaml_emitter_write_indicator(emitter, []byte{'\''}, true, false, false) { + return false + } + + spaces := false + breaks := false + for i := 0; i < len(value); { + if is_space(value, i) { + if allow_breaks && !spaces && emitter.column > emitter.best_width && i > 0 && i < len(value)-1 && !is_space(value, i+1) { + if !yaml_emitter_write_indent(emitter) { + return false + } + i += width(value[i]) + } else { + if !write(emitter, value, &i) { + return false + } + } + spaces = true + } else if is_break(value, i) { + if !breaks && value[i] == '\n' { + if !put_break(emitter) { + return false + } + } + if !write_break(emitter, value, &i) { + return false + } + emitter.indention = true + breaks = true + } else { + if breaks { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if value[i] == '\'' { + if !put(emitter, '\'') { + return false + } + } + if !write(emitter, value, &i) { + return false + } + emitter.indention = false + spaces = false + breaks = false + } + } + if !yaml_emitter_write_indicator(emitter, []byte{'\''}, false, false, false) { + return false + } + emitter.whitespace = false + emitter.indention = false + return true +} + +func yaml_emitter_write_double_quoted_scalar(emitter *yaml_emitter_t, value []byte, allow_breaks bool) bool { + spaces := false + if !yaml_emitter_write_indicator(emitter, []byte{'"'}, true, false, false) { + return false + } + + for i := 0; i < len(value); { + if !is_printable(value, i) || (!emitter.unicode && !is_ascii(value, i)) || + is_bom(value, i) || is_break(value, i) || + value[i] == '"' || value[i] == '\\' { + + octet := value[i] + + var w int + var v rune + switch { + case octet&0x80 == 0x00: + w, v = 1, rune(octet&0x7F) + case octet&0xE0 == 0xC0: + w, v = 2, rune(octet&0x1F) + case octet&0xF0 == 0xE0: + w, v = 3, rune(octet&0x0F) + case octet&0xF8 == 0xF0: + w, v = 4, rune(octet&0x07) + } + for k := 1; k < w; k++ { + octet = value[i+k] + v = (v << 6) + (rune(octet) & 0x3F) + } + i += w + + if !put(emitter, '\\') { + return false + } + + var ok bool + switch v { + case 0x00: + ok = put(emitter, '0') + case 0x07: + ok = put(emitter, 'a') + case 0x08: + ok = put(emitter, 'b') + case 0x09: + ok = put(emitter, 't') + case 0x0A: + ok = put(emitter, 'n') + case 0x0b: + ok = put(emitter, 'v') + case 0x0c: + ok = put(emitter, 'f') + case 0x0d: + ok = put(emitter, 'r') + case 0x1b: + ok = put(emitter, 'e') + case 0x22: + ok = put(emitter, '"') + case 0x5c: + ok = put(emitter, '\\') + case 0x85: + ok = put(emitter, 'N') + case 0xA0: + ok = put(emitter, '_') + case 0x2028: + ok = put(emitter, 'L') + case 0x2029: + ok = put(emitter, 'P') + default: + if v <= 0xFF { + ok = put(emitter, 'x') + w = 2 + } else if v <= 0xFFFF { + ok = put(emitter, 'u') + w = 4 + } else { + ok = put(emitter, 'U') + w = 8 + } + for k := (w - 1) * 4; ok && k >= 0; k -= 4 { + digit := byte((v >> uint(k)) & 0x0F) + if digit < 10 { + ok = put(emitter, digit+'0') + } else { + ok = put(emitter, digit+'A'-10) + } + } + } + if !ok { + return false + } + spaces = false + } else if is_space(value, i) { + if allow_breaks && !spaces && emitter.column > emitter.best_width && i > 0 && i < len(value)-1 { + if !yaml_emitter_write_indent(emitter) { + return false + } + if is_space(value, i+1) { + if !put(emitter, '\\') { + return false + } + } + i += width(value[i]) + } else if !write(emitter, value, &i) { + return false + } + spaces = true + } else { + if !write(emitter, value, &i) { + return false + } + spaces = false + } + } + if !yaml_emitter_write_indicator(emitter, []byte{'"'}, false, false, false) { + return false + } + emitter.whitespace = false + emitter.indention = false + return true +} + +func yaml_emitter_write_block_scalar_hints(emitter *yaml_emitter_t, value []byte) bool { + if is_space(value, 0) || is_break(value, 0) { + indent_hint := []byte{'0' + byte(emitter.best_indent)} + if !yaml_emitter_write_indicator(emitter, indent_hint, false, false, false) { + return false + } + } + + emitter.open_ended = false + + var chomp_hint [1]byte + if len(value) == 0 { + chomp_hint[0] = '-' + } else { + i := len(value) - 1 + for value[i]&0xC0 == 0x80 { + i-- + } + if !is_break(value, i) { + chomp_hint[0] = '-' + } else if i == 0 { + chomp_hint[0] = '+' + emitter.open_ended = true + } else { + i-- + for value[i]&0xC0 == 0x80 { + i-- + } + if is_break(value, i) { + chomp_hint[0] = '+' + emitter.open_ended = true + } + } + } + if chomp_hint[0] != 0 { + if !yaml_emitter_write_indicator(emitter, chomp_hint[:], false, false, false) { + return false + } + } + return true +} + +func yaml_emitter_write_literal_scalar(emitter *yaml_emitter_t, value []byte) bool { + if !yaml_emitter_write_indicator(emitter, []byte{'|'}, true, false, false) { + return false + } + if !yaml_emitter_write_block_scalar_hints(emitter, value) { + return false + } + if !put_break(emitter) { + return false + } + emitter.indention = true + emitter.whitespace = true + breaks := true + for i := 0; i < len(value); { + if is_break(value, i) { + if !write_break(emitter, value, &i) { + return false + } + emitter.indention = true + breaks = true + } else { + if breaks { + if !yaml_emitter_write_indent(emitter) { + return false + } + } + if !write(emitter, value, &i) { + return false + } + emitter.indention = false + breaks = false + } + } + + return true +} + +func yaml_emitter_write_folded_scalar(emitter *yaml_emitter_t, value []byte) bool { + if !yaml_emitter_write_indicator(emitter, []byte{'>'}, true, false, false) { + return false + } + if !yaml_emitter_write_block_scalar_hints(emitter, value) { + return false + } + + if !put_break(emitter) { + return false + } + emitter.indention = true + emitter.whitespace = true + + breaks := true + leading_spaces := true + for i := 0; i < len(value); { + if is_break(value, i) { + if !breaks && !leading_spaces && value[i] == '\n' { + k := 0 + for is_break(value, k) { + k += width(value[k]) + } + if !is_blankz(value, k) { + if !put_break(emitter) { + return false + } + } + } + if !write_break(emitter, value, &i) { + return false + } + emitter.indention = true + breaks = true + } else { + if breaks { + if !yaml_emitter_write_indent(emitter) { + return false + } + leading_spaces = is_blank(value, i) + } + if !breaks && is_space(value, i) && !is_space(value, i+1) && emitter.column > emitter.best_width { + if !yaml_emitter_write_indent(emitter) { + return false + } + i += width(value[i]) + } else { + if !write(emitter, value, &i) { + return false + } + } + emitter.indention = false + breaks = false + } + } + return true +}
diff --git a/encode.go b/encode.go index c7fcdb2..ad7853c 100644 --- a/encode.go +++ b/encode.go
@@ -1,84 +1,56 @@ package goyaml -// #include "helpers.h" -import "C" - import ( "reflect" "sort" "strconv" - "unsafe" ) type encoder struct { - emitter C.yaml_emitter_t - event C.yaml_event_t + emitter yaml_emitter_t + event yaml_event_t out []byte - tmp []byte - tmph *reflect.SliceHeader flow bool } -//export outputHandler -func outputHandler(data unsafe.Pointer, buffer *C.uchar, size C.size_t) C.int { - e := (*encoder)(data) - e.tmph.Data = uintptr(unsafe.Pointer(buffer)) - e.tmph.Len = int(size) - e.tmph.Cap = int(size) - e.out = append(e.out, e.tmp...) - return 1 -} - func newEncoder() (e *encoder) { e = &encoder{} - e.tmph = (*reflect.SliceHeader)(unsafe.Pointer(&e.tmp)) - if C.yaml_emitter_initialize(&e.emitter) == 0 { - panic("Failed to initialize YAML emitter") - } - C.set_output_handler(&e.emitter) - C.yaml_stream_start_event_initialize(&e.event, C.YAML_UTF8_ENCODING) + e.must(yaml_emitter_initialize(&e.emitter)) + yaml_emitter_set_output_string(&e.emitter, &e.out) + e.must(yaml_stream_start_event_initialize(&e.event, yaml_UTF8_ENCODING)) e.emit() - C.yaml_document_start_event_initialize(&e.event, nil, nil, nil, 1) + e.must(yaml_document_start_event_initialize(&e.event, nil, nil, true)) e.emit() return e } func (e *encoder) finish() { - C.yaml_document_end_event_initialize(&e.event, 1) + e.must(yaml_document_end_event_initialize(&e.event, true)) e.emit() - e.emitter.open_ended = 0 - C.yaml_stream_end_event_initialize(&e.event) + e.emitter.open_ended = false + e.must(yaml_stream_end_event_initialize(&e.event)) e.emit() } func (e *encoder) destroy() { - C.yaml_emitter_delete(&e.emitter) + yaml_emitter_delete(&e.emitter) } func (e *encoder) emit() { // This will internally delete the e.event value. - if C.yaml_emitter_emit(&e.emitter, &e.event) == 0 && - e.event._type != C.YAML_DOCUMENT_END_EVENT && - e.event._type != C.YAML_STREAM_END_EVENT { - if e.emitter.error == C.YAML_EMITTER_ERROR { - // XXX TESTME - panic("YAML emitter error: " + C.GoString(e.emitter.problem)) - } else { - // XXX TESTME - panic("Unknown YAML emitter error") - } + if !yaml_emitter_emit(&e.emitter, &e.event) && e.event.typ != yaml_DOCUMENT_END_EVENT && e.event.typ != yaml_STREAM_END_EVENT { + e.must(false) } } -func (e *encoder) fail(msg string) { - if msg == "" { - if e.emitter.problem != nil { - msg = C.GoString(e.emitter.problem) - } else { +func (e *encoder) must(ok bool) { + if !ok { + msg := e.emitter.problem + if msg == "" { msg = "Unknown problem generating YAML content" } + panic(msg) } - panic(msg) } func (e *encoder) marshal(tag string, in reflect.Value) { @@ -155,62 +127,43 @@ } func (e *encoder) mappingv(tag string, f func()) { - var ctag *C.yaml_char_t - var free func() - cimplicit := C.int(1) - if tag != "" { - ctag, free = ystr(tag) - defer free() - cimplicit = 0 - } - cstyle := C.yaml_mapping_style_t(C.YAML_BLOCK_MAPPING_STYLE) + implicit := tag == "" + style := yaml_BLOCK_MAPPING_STYLE if e.flow { e.flow = false - cstyle = C.YAML_FLOW_MAPPING_STYLE + style = yaml_FLOW_MAPPING_STYLE } - C.yaml_mapping_start_event_initialize(&e.event, nil, ctag, cimplicit, - cstyle) + e.must(yaml_mapping_start_event_initialize(&e.event, nil, []byte(tag), implicit, style)) e.emit() f() - C.yaml_mapping_end_event_initialize(&e.event) + e.must(yaml_mapping_end_event_initialize(&e.event)) e.emit() } func (e *encoder) slicev(tag string, in reflect.Value) { - var ctag *C.yaml_char_t - var free func() - var cimplicit C.int - if tag != "" { - ctag, free = ystr(tag) - defer free() - cimplicit = 0 - } else { - cimplicit = 1 - } - - cstyle := C.yaml_sequence_style_t(C.YAML_BLOCK_SEQUENCE_STYLE) + implicit := tag == "" + style := yaml_BLOCK_SEQUENCE_STYLE if e.flow { e.flow = false - cstyle = C.YAML_FLOW_SEQUENCE_STYLE + style = yaml_FLOW_SEQUENCE_STYLE } - C.yaml_sequence_start_event_initialize(&e.event, nil, ctag, cimplicit, - cstyle) + e.must(yaml_sequence_start_event_initialize(&e.event, nil, []byte(tag), implicit, style)) e.emit() n := in.Len() for i := 0; i < n; i++ { e.marshal("", in.Index(i)) } - C.yaml_sequence_end_event_initialize(&e.event) + e.must(yaml_sequence_end_event_initialize(&e.event)) e.emit() } func (e *encoder) stringv(tag string, in reflect.Value) { - var style C.yaml_scalar_style_t + var style yaml_scalar_style_t s := in.String() if rtag, _ := resolve("", s); rtag != "!!str" { - style = C.YAML_DOUBLE_QUOTED_SCALAR_STYLE + style = yaml_DOUBLE_QUOTED_SCALAR_STYLE } else { - style = C.YAML_PLAIN_SCALAR_STYLE + style = yaml_PLAIN_SCALAR_STYLE } e.emitScalar(s, "", tag, style) } @@ -222,17 +175,17 @@ } else { s = "false" } - e.emitScalar(s, "", tag, C.YAML_PLAIN_SCALAR_STYLE) + e.emitScalar(s, "", tag, yaml_PLAIN_SCALAR_STYLE) } func (e *encoder) intv(tag string, in reflect.Value) { s := strconv.FormatInt(in.Int(), 10) - e.emitScalar(s, "", tag, C.YAML_PLAIN_SCALAR_STYLE) + e.emitScalar(s, "", tag, yaml_PLAIN_SCALAR_STYLE) } func (e *encoder) uintv(tag string, in reflect.Value) { s := strconv.FormatUint(in.Uint(), 10) - e.emitScalar(s, "", tag, C.YAML_PLAIN_SCALAR_STYLE) + e.emitScalar(s, "", tag, yaml_PLAIN_SCALAR_STYLE) } func (e *encoder) floatv(tag string, in reflect.Value) { @@ -246,42 +199,18 @@ case "NaN": s = ".nan" } - e.emitScalar(s, "", tag, C.YAML_PLAIN_SCALAR_STYLE) + e.emitScalar(s, "", tag, yaml_PLAIN_SCALAR_STYLE) } func (e *encoder) nilv() { - e.emitScalar("null", "", "", C.YAML_PLAIN_SCALAR_STYLE) + e.emitScalar("null", "", "", yaml_PLAIN_SCALAR_STYLE) } -func (e *encoder) emitScalar(value, anchor, tag string, style C.yaml_scalar_style_t) { - var canchor, ctag, cvalue *C.yaml_char_t - var cimplicit C.int - var free func() - if anchor != "" { - canchor, free = ystr(anchor) - defer free() +func (e *encoder) emitScalar(value, anchor, tag string, style yaml_scalar_style_t) { + implicit := tag == "" + if !implicit { + style = yaml_PLAIN_SCALAR_STYLE } - if tag != "" { - ctag, free = ystr(tag) - defer free() - cimplicit = 0 - style = C.YAML_PLAIN_SCALAR_STYLE - } else { - cimplicit = 1 - } - cvalue, free = ystr(value) - defer free() - size := C.int(len(value)) - if C.yaml_scalar_event_initialize(&e.event, canchor, ctag, cvalue, size, - cimplicit, cimplicit, style) == 0 { - e.fail("") - } + e.must(yaml_scalar_event_initialize(&e.event, []byte(anchor), []byte(tag), []byte(value), implicit, implicit, style)) e.emit() } - -func ystr(s string) (ys *C.yaml_char_t, free func()) { - up := unsafe.Pointer(C.CString(s)) - ys = (*C.yaml_char_t)(up) - free = func() { C.free(up) } - return ys, free -}
diff --git a/encode_test.go b/encode_test.go index 1d63c02..0d34d88 100644 --- a/encode_test.go +++ b/encode_test.go
@@ -12,105 +12,194 @@ var marshalIntTest = 123 var marshalTests = []struct { - data string value interface{} + data string }{ - {"{}\n", &struct{}{}}, - {"v: hi\n", map[string]string{"v": "hi"}}, - {"v: hi\n", map[string]interface{}{"v": "hi"}}, - {"v: \"true\"\n", map[string]string{"v": "true"}}, - {"v: \"false\"\n", map[string]string{"v": "false"}}, - {"v: true\n", map[string]interface{}{"v": true}}, - {"v: false\n", map[string]interface{}{"v": false}}, - {"v: 10\n", map[string]interface{}{"v": 10}}, - {"v: -10\n", map[string]interface{}{"v": -10}}, - {"v: 42\n", map[string]uint{"v": 42}}, - {"v: 4294967296\n", map[string]interface{}{"v": int64(4294967296)}}, - {"v: 4294967296\n", map[string]int64{"v": int64(4294967296)}}, - {"v: 4294967296\n", map[string]uint64{"v": 4294967296}}, - {"v: \"10\"\n", map[string]interface{}{"v": "10"}}, - {"v: 0.1\n", map[string]interface{}{"v": 0.1}}, - {"v: 0.1\n", map[string]interface{}{"v": float64(0.1)}}, - {"v: -0.1\n", map[string]interface{}{"v": -0.1}}, - {"v: .inf\n", map[string]interface{}{"v": math.Inf(+1)}}, - {"v: -.inf\n", map[string]interface{}{"v": math.Inf(-1)}}, - {"v: .nan\n", map[string]interface{}{"v": math.NaN()}}, - {"v: null\n", map[string]interface{}{"v": nil}}, - {"v: \"\"\n", map[string]interface{}{"v": ""}}, - {"v:\n- A\n- B\n", map[string][]string{"v": []string{"A", "B"}}}, - {"v:\n- A\n- 1\n", map[string][]interface{}{"v": []interface{}{"A", 1}}}, - {"a:\n b: c\n", - map[string]interface{}{"a": map[interface{}]interface{}{"b": "c"}}}, + { + &struct{}{}, + "{}\n", + }, { + map[string]string{"v": "hi"}, + "v: hi\n", + }, { + map[string]interface{}{"v": "hi"}, + "v: hi\n", + }, { + map[string]string{"v": "true"}, + "v: \"true\"\n", + }, { + map[string]string{"v": "false"}, + "v: \"false\"\n", + }, { + map[string]interface{}{"v": true}, + "v: true\n", + }, { + map[string]interface{}{"v": false}, + "v: false\n", + }, { + map[string]interface{}{"v": 10}, + "v: 10\n", + }, { + map[string]interface{}{"v": -10}, + "v: -10\n", + }, { + map[string]uint{"v": 42}, + "v: 42\n", + }, { + map[string]interface{}{"v": int64(4294967296)}, + "v: 4294967296\n", + }, { + map[string]int64{"v": int64(4294967296)}, + "v: 4294967296\n", + }, { + map[string]uint64{"v": 4294967296}, + "v: 4294967296\n", + }, { + map[string]interface{}{"v": "10"}, + "v: \"10\"\n", + }, { + map[string]interface{}{"v": 0.1}, + "v: 0.1\n", + }, { + map[string]interface{}{"v": float64(0.1)}, + "v: 0.1\n", + }, { + map[string]interface{}{"v": -0.1}, + "v: -0.1\n", + }, { + map[string]interface{}{"v": math.Inf(+1)}, + "v: .inf\n", + }, { + map[string]interface{}{"v": math.Inf(-1)}, + "v: -.inf\n", + }, { + map[string]interface{}{"v": math.NaN()}, + "v: .nan\n", + }, { + map[string]interface{}{"v": nil}, + "v: null\n", + }, { + map[string]interface{}{"v": ""}, + "v: \"\"\n", + }, { + map[string][]string{"v": []string{"A", "B"}}, + "v:\n- A\n- B\n", + }, { + map[string][]string{"v": []string{"A", "B\nC"}}, + "v:\n- A\n- 'B\n\n C'\n", + }, { + map[string][]interface{}{"v": []interface{}{"A", 1, map[string][]int{"B": []int{2, 3}}}}, + "v:\n- A\n- 1\n- B:\n - 2\n - 3\n", + }, { + map[string]interface{}{"a": map[interface{}]interface{}{"b": "c"}}, + "a:\n b: c\n", + }, // Simple values. - {"123\n", &marshalIntTest}, + { + &marshalIntTest, + "123\n", + }, // Structures - {"hello: world\n", &struct{ Hello string }{"world"}}, - {"a:\n b: c\n", &struct { - A struct { - B string - } - }{struct{ B string }{"c"}}}, - {"a:\n b: c\n", &struct { - A *struct { - B string - } - }{&struct{ B string }{"c"}}}, - {"a: null\n", &struct { - A *struct { - B string - } - }{}}, - {"a: 1\n", &struct{ A int }{1}}, - {"a:\n- 1\n- 2\n", &struct{ A []int }{[]int{1, 2}}}, - {"a: 1\n", &struct { - B int "a" - }{1}}, - {"a: true\n", &struct{ A bool }{true}}, - - // Conditional flag - {"a: 1\n", &struct { - A int "a,omitempty" - B int "b,omitempty" - }{1, 0}}, - {"{}\n", &struct { - A int "a,omitempty" - B int "b,omitempty" - }{0, 0}}, - {"{}\n", &struct { - A *struct{ X int } "a,omitempty" - B int "b,omitempty" - }{nil, 0}}, - - // Flow flag - {"a: [1, 2]\n", &struct { - A []int "a,flow" - }{[]int{1, 2}}}, - {"a: {b: c}\n", - &struct { - A map[string]string "a,flow" - }{map[string]string{"b": "c"}}}, - {"a: {b: c}\n", + { + &struct{ Hello string }{"world"}, + "hello: world\n", + }, { &struct { A struct { B string + } + }{struct{ B string }{"c"}}, + "a:\n b: c\n", + }, { + &struct { + A *struct { + B string + } + }{&struct{ B string }{"c"}}, + "a:\n b: c\n", + }, { + &struct { + A *struct { + B string + } + }{}, + "a: null\n", + }, { + &struct{ A int }{1}, + "a: 1\n", + }, { + &struct{ A []int }{[]int{1, 2}}, + "a:\n- 1\n- 2\n", + }, { + &struct { + B int "a" + }{1}, + "a: 1\n", + }, { + &struct{ A bool }{true}, + "a: true\n", + }, + + // Conditional flag + { + &struct { + A int "a,omitempty" + B int "b,omitempty" + }{1, 0}, + "a: 1\n", + }, { + &struct { + A int "a,omitempty" + B int "b,omitempty" + }{0, 0}, + "{}\n", + }, { + &struct { + A *struct{ X int } "a,omitempty" + B int "b,omitempty" + }{nil, 0}, + "{}\n", + }, + + // Flow flag + { + &struct { + A []int "a,flow" + }{[]int{1, 2}}, + "a: [1, 2]\n", + }, { + &struct { + A map[string]string "a,flow" + }{map[string]string{"b": "c", "d": "e"}}, + "a: {b: c, d: e}\n", + }, { + &struct { + A struct { + B, D string } "a,flow" - }{struct{ B string }{"c"}}}, + }{struct{ B, D string }{"c", "e"}}, + "a: {b: c, d: e}\n", + }, // Unexported field - {"a: 1\n", + { &struct { u int A int - }{0, 1}}, + }{0, 1}, + "a: 1\n", + }, // Ignored field - {"a: 1\n", + { &struct { A int B int "-" - }{1, 2}}, + }{1, 2}, + "a: 1\n", + }, } func (s *S) TestMarshal(c *C) {
diff --git a/helpers.c b/helpers.c deleted file mode 100644 index 733b618..0000000 --- a/helpers.c +++ /dev/null
@@ -1,18 +0,0 @@ -#include "_cgo_export.h" -#include "helpers.h" - -#define DEFINE_YUNION_FUNC(name) \ - __typeof__(((yaml_event_t *)0)->data.name) * \ - event_##name(yaml_event_t *event) { \ - return &event->data.name; \ - } - -DEFINE_YUNION_FUNC(scalar) -DEFINE_YUNION_FUNC(alias) -DEFINE_YUNION_FUNC(mapping_start) -DEFINE_YUNION_FUNC(sequence_start) - -void set_output_handler(yaml_emitter_t *e) -{ - yaml_emitter_set_output(e, (yaml_write_handler_t*)outputHandler, (void *)e); -}
diff --git a/helpers.h b/helpers.h deleted file mode 100644 index e4d8639..0000000 --- a/helpers.h +++ /dev/null
@@ -1,20 +0,0 @@ -#ifndef helpers_h -#define helpers_h - -#define CGO_LDFLAGS "-lm -lpthread" -#define CGO_CFLAGS "-I. -DHAVE_CONFIG_H=1" - -#include <yaml.h> - -#define DECLARE_YUNION_FUNC(name) \ - __typeof__(((yaml_event_t *)0)->data.name) *\ - event_##name(yaml_event_t *event); - -DECLARE_YUNION_FUNC(scalar) -DECLARE_YUNION_FUNC(alias) -DECLARE_YUNION_FUNC(mapping_start) -DECLARE_YUNION_FUNC(sequence_start) - -void set_output_handler(yaml_emitter_t *e); - -#endif
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/parserc.go b/parserc.go new file mode 100644 index 0000000..0fdfa4e --- /dev/null +++ b/parserc.go
@@ -0,0 +1,1096 @@ +package goyaml + +import ( + "bytes" +) + +// 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?)? + +// Peek the next token in the token queue. +func peek_token(parser *yaml_parser_t) *yaml_token_t { + if parser.token_available || yaml_parser_fetch_more_tokens(parser) { + return &parser.tokens[parser.tokens_head] + } + return nil +} + +// Remove the next token from the queue (must be called after peek_token). +func skip_token(parser *yaml_parser_t) { + parser.token_available = false + parser.tokens_parsed++ + parser.stream_end_produced = parser.tokens[parser.tokens_head].typ == yaml_STREAM_END_TOKEN + parser.tokens_head++ +} + +// Get the next event. +func yaml_parser_parse(parser *yaml_parser_t, event *yaml_event_t) bool { + // Erase the event object. + *event = yaml_event_t{} + + // No events after the end of the stream or error. + if parser.stream_end_produced || parser.error != yaml_NO_ERROR || parser.state == yaml_PARSE_END_STATE { + return true + } + + // Generate the next event. + return yaml_parser_state_machine(parser, event) +} + +// Set parser error. +func yaml_parser_set_parser_error(parser *yaml_parser_t, problem string, problem_mark yaml_mark_t) bool { + parser.error = yaml_PARSER_ERROR + parser.problem = problem + parser.problem_mark = problem_mark + return false +} + +func yaml_parser_set_parser_error_context(parser *yaml_parser_t, context string, context_mark yaml_mark_t, problem string, problem_mark yaml_mark_t) bool { + parser.error = yaml_PARSER_ERROR + parser.context = context + parser.context_mark = context_mark + parser.problem = problem + parser.problem_mark = problem_mark + return false +} + +// 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) + + case yaml_PARSE_IMPLICIT_DOCUMENT_START_STATE: + return yaml_parser_parse_document_start(parser, event, true) + + case yaml_PARSE_DOCUMENT_START_STATE: + return yaml_parser_parse_document_start(parser, event, false) + + 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, true, false) + + case yaml_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE: + return yaml_parser_parse_node(parser, event, true, true) + + case yaml_PARSE_FLOW_NODE_STATE: + return yaml_parser_parse_node(parser, event, false, false) + + case yaml_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE: + return yaml_parser_parse_block_sequence_entry(parser, event, true) + + case yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE: + return yaml_parser_parse_block_sequence_entry(parser, event, false) + + 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, true) + + case yaml_PARSE_BLOCK_MAPPING_KEY_STATE: + return yaml_parser_parse_block_mapping_key(parser, event, false) + + 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, true) + + case yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE: + return yaml_parser_parse_flow_sequence_entry(parser, event, false) + + 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, true) + + case yaml_PARSE_FLOW_MAPPING_KEY_STATE: + return yaml_parser_parse_flow_mapping_key(parser, event, false) + + case yaml_PARSE_FLOW_MAPPING_VALUE_STATE: + return yaml_parser_parse_flow_mapping_value(parser, event, false) + + case yaml_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE: + return yaml_parser_parse_flow_mapping_value(parser, event, true) + + default: + panic("invalid parser state") + } + return false +} + +// Parse the production: +// stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +// ************ +func yaml_parser_parse_stream_start(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + if token.typ != 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 + *event = yaml_event_t{ + typ: yaml_STREAM_START_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + encoding: token.encoding, + } + skip_token(parser) + return true +} + +// Parse the productions: +// implicit_document ::= block_node DOCUMENT-END* +// * +// 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 + } + + // Parse extra document end indicators. + if !implicit { + for token.typ == yaml_DOCUMENT_END_TOKEN { + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } + } + + if implicit && token.typ != yaml_VERSION_DIRECTIVE_TOKEN && + 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 + } + parser.states = append(parser.states, yaml_PARSE_DOCUMENT_END_STATE) + parser.state = yaml_PARSE_BLOCK_NODE_STATE + + *event = yaml_event_t{ + typ: yaml_DOCUMENT_START_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + + } else if token.typ != yaml_STREAM_END_TOKEN { + // Parse an explicit document. + var version_directive *yaml_version_directive_t + var tag_directives []yaml_tag_directive_t + start_mark := token.start_mark + if !yaml_parser_process_directives(parser, &version_directive, &tag_directives) { + return false + } + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_DOCUMENT_START_TOKEN { + yaml_parser_set_parser_error(parser, + "did not find expected <document start>", token.start_mark) + return false + } + parser.states = append(parser.states, yaml_PARSE_DOCUMENT_END_STATE) + parser.state = yaml_PARSE_DOCUMENT_CONTENT_STATE + end_mark := token.end_mark + + *event = yaml_event_t{ + typ: yaml_DOCUMENT_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + version_directive: version_directive, + tag_directives: tag_directives, + implicit: false, + } + skip_token(parser) + + } else { + // Parse the stream end. + parser.state = yaml_PARSE_END_STATE + *event = yaml_event_t{ + typ: yaml_STREAM_END_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + skip_token(parser) + } + + return true +} + +// Parse the productions: +// explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +// *********** +// +func yaml_parser_parse_document_content(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + if token.typ == yaml_VERSION_DIRECTIVE_TOKEN || + token.typ == yaml_TAG_DIRECTIVE_TOKEN || + token.typ == yaml_DOCUMENT_START_TOKEN || + token.typ == yaml_DOCUMENT_END_TOKEN || + token.typ == yaml_STREAM_END_TOKEN { + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + return yaml_parser_process_empty_scalar(parser, event, + token.start_mark) + } + return yaml_parser_parse_node(parser, event, true, false) +} + +// Parse the productions: +// implicit_document ::= block_node DOCUMENT-END* +// ************* +// explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +// +func yaml_parser_parse_document_end(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + + start_mark := token.start_mark + end_mark := token.start_mark + + implicit := true + if token.typ == yaml_DOCUMENT_END_TOKEN { + end_mark = token.end_mark + skip_token(parser) + implicit = false + } + + parser.tag_directives = parser.tag_directives[:0] + + parser.state = yaml_PARSE_DOCUMENT_START_STATE + *event = yaml_event_t{ + typ: yaml_DOCUMENT_END_EVENT, + start_mark: start_mark, + end_mark: end_mark, + implicit: implicit, + } + return true +} + +// 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 +// ****** +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] + *event = yaml_event_t{ + typ: yaml_ALIAS_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + anchor: token.value, + } + skip_token(parser) + return true + } + + start_mark := token.start_mark + end_mark := token.start_mark + + var tag_token bool + var tag_handle, tag_suffix, anchor []byte + var tag_mark yaml_mark_t + if token.typ == yaml_ANCHOR_TOKEN { + anchor = token.value + start_mark = token.start_mark + end_mark = token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ == yaml_TAG_TOKEN { + tag_token = true + tag_handle = token.value + tag_suffix = token.suffix + tag_mark = token.start_mark + end_mark = token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } + } else if token.typ == yaml_TAG_TOKEN { + tag_token = true + tag_handle = token.value + tag_suffix = token.suffix + start_mark = token.start_mark + tag_mark = token.start_mark + end_mark = token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ == yaml_ANCHOR_TOKEN { + anchor = token.value + end_mark = token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } + } + + var tag []byte + if tag_token { + if len(tag_handle) == 0 { + tag = tag_suffix + tag_suffix = nil + } 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(tag, tag_suffix...) + break + } + } + if len(tag) == 0 { + yaml_parser_set_parser_error_context(parser, + "while parsing a node", start_mark, + "found undefined tag handle", tag_mark) + return false + } + } + } + + implicit := len(tag) == 0 + if indentless_sequence && token.typ == yaml_BLOCK_ENTRY_TOKEN { + end_mark = token.end_mark + parser.state = yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE + *event = yaml_event_t{ + typ: yaml_SEQUENCE_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(yaml_BLOCK_SEQUENCE_STYLE), + } + return true + } + if token.typ == yaml_SCALAR_TOKEN { + var plain_implicit, quoted_implicit bool + end_mark = token.end_mark + if (len(tag) == 0 && token.style == yaml_PLAIN_SCALAR_STYLE) || (len(tag) == 1 && tag[0] == '!') { + plain_implicit = true + } else if len(tag) == 0 { + quoted_implicit = true + } + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + + *event = yaml_event_t{ + typ: yaml_SCALAR_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + value: token.value, + implicit: plain_implicit, + quoted_implicit: quoted_implicit, + style: yaml_style_t(token.style), + } + skip_token(parser) + return true + } + if token.typ == yaml_FLOW_SEQUENCE_START_TOKEN { + // [Go] Some of the events below can be merged as they differ only on style. + end_mark = token.end_mark + parser.state = yaml_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE + *event = yaml_event_t{ + typ: yaml_SEQUENCE_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(yaml_FLOW_SEQUENCE_STYLE), + } + return true + } + if token.typ == yaml_FLOW_MAPPING_START_TOKEN { + end_mark = token.end_mark + parser.state = yaml_PARSE_FLOW_MAPPING_FIRST_KEY_STATE + *event = yaml_event_t{ + typ: yaml_MAPPING_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(yaml_FLOW_MAPPING_STYLE), + } + return true + } + if block && token.typ == yaml_BLOCK_SEQUENCE_START_TOKEN { + end_mark = token.end_mark + parser.state = yaml_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE + *event = yaml_event_t{ + typ: yaml_SEQUENCE_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(yaml_BLOCK_SEQUENCE_STYLE), + } + return true + } + if block && token.typ == yaml_BLOCK_MAPPING_START_TOKEN { + end_mark = token.end_mark + parser.state = yaml_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE + *event = yaml_event_t{ + typ: yaml_MAPPING_START_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + style: yaml_style_t(yaml_BLOCK_MAPPING_STYLE), + } + return true + } + if len(anchor) > 0 || len(tag) > 0 { + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + + *event = yaml_event_t{ + typ: yaml_SCALAR_EVENT, + start_mark: start_mark, + end_mark: end_mark, + anchor: anchor, + tag: tag, + implicit: implicit, + quoted_implicit: false, + style: yaml_style_t(yaml_PLAIN_SCALAR_STYLE), + } + return true + } + + context := "while parsing a flow node" + if block { + context = "while parsing a block node" + } + yaml_parser_set_parser_error_context(parser, context, start_mark, + "did not find expected node content", token.start_mark) + return false +} + +// Parse the productions: +// block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +// ******************** *********** * ********* +// +func yaml_parser_parse_block_sequence_entry(parser *yaml_parser_t, event *yaml_event_t, first bool) bool { + if first { + token := peek_token(parser) + parser.marks = append(parser.marks, token.start_mark) + skip_token(parser) + } + + token := peek_token(parser) + if token == nil { + return false + } + + if token.typ == yaml_BLOCK_ENTRY_TOKEN { + mark := token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_BLOCK_ENTRY_TOKEN && token.typ != yaml_BLOCK_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE) + return yaml_parser_parse_node(parser, event, true, false) + } else { + parser.state = yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE + return yaml_parser_process_empty_scalar(parser, event, mark) + } + } + if token.typ == yaml_BLOCK_END_TOKEN { + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + + *event = yaml_event_t{ + typ: yaml_SEQUENCE_END_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + + skip_token(parser) + return true + } + + context_mark := parser.marks[len(parser.marks)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + return yaml_parser_set_parser_error_context(parser, + "while parsing a block collection", context_mark, + "did not find expected '-' indicator", token.start_mark) +} + +// Parse the productions: +// indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +// *********** * +func yaml_parser_parse_indentless_sequence_entry(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + + if token.typ == yaml_BLOCK_ENTRY_TOKEN { + mark := token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_BLOCK_ENTRY_TOKEN && + token.typ != yaml_KEY_TOKEN && + token.typ != yaml_VALUE_TOKEN && + token.typ != yaml_BLOCK_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE) + return yaml_parser_parse_node(parser, event, true, false) + } + parser.state = yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE + return yaml_parser_process_empty_scalar(parser, event, mark) + } + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + + *event = yaml_event_t{ + typ: yaml_SEQUENCE_END_EVENT, + start_mark: token.start_mark, + end_mark: token.start_mark, // [Go] Shouldn't this be token.end_mark? + } + return true +} + +// Parse the productions: +// block_mapping ::= BLOCK-MAPPING_START +// ******************* +// ((KEY block_node_or_indentless_sequence?)? +// *** * +// (VALUE block_node_or_indentless_sequence?)?)* +// +// BLOCK-END +// ********* +// +func yaml_parser_parse_block_mapping_key(parser *yaml_parser_t, event *yaml_event_t, first bool) bool { + if first { + token := peek_token(parser) + parser.marks = append(parser.marks, token.start_mark) + skip_token(parser) + } + + token := peek_token(parser) + if token == nil { + return false + } + + if token.typ == yaml_KEY_TOKEN { + mark := token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_KEY_TOKEN && + token.typ != yaml_VALUE_TOKEN && + token.typ != yaml_BLOCK_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_BLOCK_MAPPING_VALUE_STATE) + return yaml_parser_parse_node(parser, event, true, true) + } else { + parser.state = yaml_PARSE_BLOCK_MAPPING_VALUE_STATE + return yaml_parser_process_empty_scalar(parser, event, mark) + } + } else if token.typ == yaml_BLOCK_END_TOKEN { + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + *event = yaml_event_t{ + typ: yaml_MAPPING_END_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + skip_token(parser) + return true + } + + context_mark := parser.marks[len(parser.marks)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + return yaml_parser_set_parser_error_context(parser, + "while parsing a block mapping", context_mark, + "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 +// +// +func yaml_parser_parse_block_mapping_value(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + if token.typ == yaml_VALUE_TOKEN { + mark := token.end_mark + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_KEY_TOKEN && + token.typ != yaml_VALUE_TOKEN && + token.typ != yaml_BLOCK_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_BLOCK_MAPPING_KEY_STATE) + return yaml_parser_parse_node(parser, event, true, true) + } + parser.state = yaml_PARSE_BLOCK_MAPPING_KEY_STATE + return yaml_parser_process_empty_scalar(parser, event, mark) + } + 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?)? +// * +// +func yaml_parser_parse_flow_sequence_entry(parser *yaml_parser_t, event *yaml_event_t, first bool) bool { + if first { + token := peek_token(parser) + parser.marks = append(parser.marks, token.start_mark) + skip_token(parser) + } + token := peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_FLOW_SEQUENCE_END_TOKEN { + if !first { + if token.typ == yaml_FLOW_ENTRY_TOKEN { + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } else { + context_mark := parser.marks[len(parser.marks)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + return yaml_parser_set_parser_error_context(parser, + "while parsing a flow sequence", context_mark, + "did not find expected ',' or ']'", token.start_mark) + } + } + + if token.typ == yaml_KEY_TOKEN { + parser.state = yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE + *event = yaml_event_t{ + typ: yaml_MAPPING_START_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + implicit: true, + style: yaml_style_t(yaml_FLOW_MAPPING_STYLE), + } + skip_token(parser) + return true + } else if token.typ != yaml_FLOW_SEQUENCE_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } + } + + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + + *event = yaml_event_t{ + typ: yaml_SEQUENCE_END_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + + skip_token(parser) + return true +} + +// +// Parse the productions: +// flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +// *** * +// +func yaml_parser_parse_flow_sequence_entry_mapping_key(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_VALUE_TOKEN && + token.typ != yaml_FLOW_ENTRY_TOKEN && + token.typ != yaml_FLOW_SEQUENCE_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } + 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?)? +// ***** * +// +func yaml_parser_parse_flow_sequence_entry_mapping_value(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + if token.typ == yaml_VALUE_TOKEN { + skip_token(parser) + token := peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_FLOW_ENTRY_TOKEN && token.typ != yaml_FLOW_SEQUENCE_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } + } + 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?)? +// * +// +func yaml_parser_parse_flow_sequence_entry_mapping_end(parser *yaml_parser_t, event *yaml_event_t) bool { + token := peek_token(parser) + if token == nil { + return false + } + parser.state = yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE + *event = yaml_event_t{ + typ: yaml_MAPPING_END_EVENT, + start_mark: token.start_mark, + end_mark: token.start_mark, // [Go] Shouldn't this be end_mark? + } + return true +} + +// 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?)? +// * *** * +// +func yaml_parser_parse_flow_mapping_key(parser *yaml_parser_t, event *yaml_event_t, first bool) bool { + if first { + token := peek_token(parser) + parser.marks = append(parser.marks, token.start_mark) + skip_token(parser) + } + + token := peek_token(parser) + if token == nil { + return false + } + + if token.typ != yaml_FLOW_MAPPING_END_TOKEN { + if !first { + if token.typ == yaml_FLOW_ENTRY_TOKEN { + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } else { + context_mark := parser.marks[len(parser.marks)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + return yaml_parser_set_parser_error_context(parser, + "while parsing a flow mapping", context_mark, + "did not find expected ',' or '}'", token.start_mark) + } + } + + if token.typ == yaml_KEY_TOKEN { + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_VALUE_TOKEN && + token.typ != yaml_FLOW_ENTRY_TOKEN && + token.typ != yaml_FLOW_MAPPING_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_MAPPING_VALUE_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } else { + parser.state = yaml_PARSE_FLOW_MAPPING_VALUE_STATE + return yaml_parser_process_empty_scalar(parser, event, token.start_mark) + } + } else if token.typ != yaml_FLOW_MAPPING_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } + } + + parser.state = parser.states[len(parser.states)-1] + parser.states = parser.states[:len(parser.states)-1] + parser.marks = parser.marks[:len(parser.marks)-1] + *event = yaml_event_t{ + typ: yaml_MAPPING_END_EVENT, + start_mark: token.start_mark, + end_mark: token.end_mark, + } + skip_token(parser) + return true +} + +// Parse the productions: +// flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +// * ***** * +// +func yaml_parser_parse_flow_mapping_value(parser *yaml_parser_t, event *yaml_event_t, empty bool) bool { + token := peek_token(parser) + if token == nil { + return false + } + if empty { + parser.state = yaml_PARSE_FLOW_MAPPING_KEY_STATE + return yaml_parser_process_empty_scalar(parser, event, token.start_mark) + } + if token.typ == yaml_VALUE_TOKEN { + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + if token.typ != yaml_FLOW_ENTRY_TOKEN && token.typ != yaml_FLOW_MAPPING_END_TOKEN { + parser.states = append(parser.states, yaml_PARSE_FLOW_MAPPING_KEY_STATE) + return yaml_parser_parse_node(parser, event, false, false) + } + } + parser.state = yaml_PARSE_FLOW_MAPPING_KEY_STATE + return yaml_parser_process_empty_scalar(parser, event, token.start_mark) +} + +// Generate an empty scalar event. +func yaml_parser_process_empty_scalar(parser *yaml_parser_t, event *yaml_event_t, mark yaml_mark_t) bool { + *event = yaml_event_t{ + typ: yaml_SCALAR_EVENT, + start_mark: mark, + end_mark: mark, + value: nil, // Empty + implicit: true, + style: yaml_style_t(yaml_PLAIN_SCALAR_STYLE), + } + return true +} + +var default_tag_directives = []yaml_tag_directive_t{ + {[]byte("!"), []byte("!")}, + {[]byte("!!"), []byte("tag:yaml.org,2002:")}, +} + +// Parse directives. +func yaml_parser_process_directives(parser *yaml_parser_t, + version_directive_ref **yaml_version_directive_t, + tag_directives_ref *[]yaml_tag_directive_t) bool { + + var version_directive *yaml_version_directive_t + var tag_directives []yaml_tag_directive_t + + token := peek_token(parser) + if token == nil { + return false + } + + for token.typ == yaml_VERSION_DIRECTIVE_TOKEN || token.typ == yaml_TAG_DIRECTIVE_TOKEN { + if token.typ == yaml_VERSION_DIRECTIVE_TOKEN { + if version_directive != nil { + yaml_parser_set_parser_error(parser, + "found duplicate %YAML directive", token.start_mark) + return false + } + if token.major != 1 || token.minor != 1 { + yaml_parser_set_parser_error(parser, + "found incompatible YAML document", token.start_mark) + return false + } + version_directive = &yaml_version_directive_t{ + major: token.major, + minor: token.minor, + } + } else if token.typ == yaml_TAG_DIRECTIVE_TOKEN { + value := yaml_tag_directive_t{ + handle: token.value, + prefix: token.prefix, + } + if !yaml_parser_append_tag_directive(parser, value, false, token.start_mark) { + return false + } + tag_directives = append(tag_directives, value) + } + + skip_token(parser) + token = peek_token(parser) + if token == nil { + return false + } + } + + for i := range default_tag_directives { + if !yaml_parser_append_tag_directive(parser, default_tag_directives[i], true, token.start_mark) { + return false + } + } + + if version_directive_ref != nil { + *version_directive_ref = version_directive + } + if tag_directives_ref != nil { + *tag_directives_ref = tag_directives + } + return true +} + +// Append a tag directive to the directives stack. +func yaml_parser_append_tag_directive(parser *yaml_parser_t, value yaml_tag_directive_t, allow_duplicates bool, mark yaml_mark_t) bool { + for i := range parser.tag_directives { + if bytes.Equal(value.handle, parser.tag_directives[i].handle) { + if allow_duplicates { + return true + } + return yaml_parser_set_parser_error(parser, "found duplicate %TAG directive", mark) + } + } + + // [Go] I suspect the copy is unnecessary. This was likely done + // because there was no way to track ownership of the data. + value_copy := yaml_tag_directive_t{ + handle: make([]byte, len(value.handle)), + prefix: make([]byte, len(value.prefix)), + } + copy(value_copy.handle, value.handle) + copy(value_copy.prefix, value.prefix) + parser.tag_directives = append(parser.tag_directives, value_copy) + return true +}
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/readerc.go b/readerc.go new file mode 100644 index 0000000..c732935 --- /dev/null +++ b/readerc.go
@@ -0,0 +1,391 @@ +package goyaml + +import ( + "io" +) + +// Set the reader error and return 0. +func yaml_parser_set_reader_error(parser *yaml_parser_t, problem string, offset int, value int) bool { + parser.error = yaml_READER_ERROR + parser.problem = problem + parser.problem_offset = offset + parser.problem_value = value + return false +} + +// Byte order marks. +const ( + bom_UTF8 = "\xef\xbb\xbf" + bom_UTF16LE = "\xff\xfe" + 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. +func yaml_parser_determine_encoding(parser *yaml_parser_t) bool { + // Ensure that we had enough bytes in the raw buffer. + for !parser.eof && len(parser.raw_buffer)-parser.raw_buffer_pos < 3 { + if !yaml_parser_update_raw_buffer(parser) { + return false + } + } + + // Determine the encoding. + buf := parser.raw_buffer + pos := parser.raw_buffer_pos + avail := len(buf) - pos + if avail >= 2 && buf[pos] == bom_UTF16LE[0] && buf[pos+1] == bom_UTF16LE[1] { + parser.encoding = yaml_UTF16LE_ENCODING + parser.raw_buffer_pos += 2 + parser.offset += 2 + } else if avail >= 2 && buf[pos] == bom_UTF16BE[0] && buf[pos+1] == bom_UTF16BE[1] { + parser.encoding = yaml_UTF16BE_ENCODING + parser.raw_buffer_pos += 2 + parser.offset += 2 + } else if avail >= 3 && buf[pos] == bom_UTF8[0] && buf[pos+1] == bom_UTF8[1] && buf[pos+2] == bom_UTF8[2] { + parser.encoding = yaml_UTF8_ENCODING + parser.raw_buffer_pos += 3 + parser.offset += 3 + } else { + parser.encoding = yaml_UTF8_ENCODING + } + return true +} + +// Update the raw buffer. +func yaml_parser_update_raw_buffer(parser *yaml_parser_t) bool { + size_read := 0 + + // Return if the raw buffer is full. + if parser.raw_buffer_pos == 0 && len(parser.raw_buffer) == cap(parser.raw_buffer) { + return true + } + + // Return on EOF. + if parser.eof { + return true + } + + // Move the remaining bytes in the raw buffer to the beginning. + if parser.raw_buffer_pos > 0 && parser.raw_buffer_pos < len(parser.raw_buffer) { + copy(parser.raw_buffer, parser.raw_buffer[parser.raw_buffer_pos:]) + } + parser.raw_buffer = parser.raw_buffer[:len(parser.raw_buffer)-parser.raw_buffer_pos] + parser.raw_buffer_pos = 0 + + // Call the read handler to fill the buffer. + size_read, err := parser.read_handler(parser, parser.raw_buffer[len(parser.raw_buffer):cap(parser.raw_buffer)]) + parser.raw_buffer = parser.raw_buffer[:len(parser.raw_buffer)+size_read] + if err == io.EOF { + parser.eof = true + } else if err != nil { + return yaml_parser_set_reader_error(parser, "input error: "+err.Error(), parser.offset, -1) + } + return true +} + +// Ensure that the buffer contains at least `length` characters. +// Return true on success, false on failure. +// +// The length is supposed to be significantly less that the buffer size. +func yaml_parser_update_buffer(parser *yaml_parser_t, length int) bool { + if parser.read_handler == nil { + panic("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_pos == len(parser.raw_buffer) { + return true + } + + // Return if the buffer contains enough characters. + if parser.unread >= length { + return true + } + + // Determine the input encoding if it is not known yet. + if parser.encoding == yaml_ANY_ENCODING { + if !yaml_parser_determine_encoding(parser) { + return false + } + } + + // Move the unread characters to the beginning of the buffer. + buffer_len := len(parser.buffer) + if parser.buffer_pos > 0 && parser.buffer_pos < buffer_len { + copy(parser.buffer, parser.buffer[parser.buffer_pos:]) + buffer_len -= parser.buffer_pos + parser.buffer_pos = 0 + } else if parser.buffer_pos == buffer_len { + buffer_len = 0 + parser.buffer_pos = 0 + } + + // Open the whole buffer for writing, and cut it before returning. + parser.buffer = parser.buffer[:cap(parser.buffer)] + + // Fill the buffer until it has enough characters. + first := true + for parser.unread < length { + + // Fill the raw buffer if necessary. + if !first || parser.raw_buffer_pos == len(parser.raw_buffer) { + if !yaml_parser_update_raw_buffer(parser) { + parser.buffer = parser.buffer[:buffer_len] + return false + } + } + first = false + + // Decode the raw buffer. + inner: + for parser.raw_buffer_pos != len(parser.raw_buffer) { + var value rune + var width int + + raw_unread := len(parser.raw_buffer) - parser.raw_buffer_pos + + // 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[parser.raw_buffer_pos] + switch { + case octet&0x80 == 0x00: + width = 1 + case octet&0xE0 == 0xC0: + width = 2 + case octet&0xF0 == 0xE0: + width = 3 + case octet&0xF8 == 0xF0: + width = 4 + default: + // The leading octet is invalid. + return yaml_parser_set_reader_error(parser, + "invalid leading UTF-8 octet", + parser.offset, int(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) + } + break inner + } + + // Decode the leading octet. + switch { + case octet&0x80 == 0x00: + value = rune(octet & 0x7F) + case octet&0xE0 == 0xC0: + value = rune(octet & 0x1F) + case octet&0xF0 == 0xE0: + value = rune(octet & 0x0F) + case octet&0xF8 == 0xF0: + value = rune(octet & 0x07) + default: + value = 0 + } + + // Check and decode the trailing octets. + for k := 1; k < width; k++ { + octet = parser.raw_buffer[parser.raw_buffer_pos+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, int(octet)) + } + + // Decode the octet. + value = (value << 6) + rune(octet&0x3F) + } + + // Check the length of the sequence against the value. + switch { + case width == 1: + case width == 2 && value >= 0x80: + case width == 3 && value >= 0x800: + case width == 4 && value >= 0x10000: + default: + 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, int(value)) + } + + case yaml_UTF16LE_ENCODING, yaml_UTF16BE_ENCODING: + var low, high int + if parser.encoding == yaml_UTF16LE_ENCODING { + low, high = 0, 1 + } else { + high, low = 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) + } + break inner + } + + // Get the character. + value = rune(parser.raw_buffer[parser.raw_buffer_pos+low]) + + (rune(parser.raw_buffer[parser.raw_buffer_pos+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, int(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) + } + break inner + } + + // Get the next character. + value2 := rune(parser.raw_buffer[parser.raw_buffer_pos+low+2]) + + (rune(parser.raw_buffer[parser.raw_buffer_pos+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, int(value2)) + } + + // Generate the value of the surrogate pair. + value = 0x10000 + ((value & 0x3FF) << 10) + (value2 & 0x3FF) + } else { + width = 2 + } + + default: + panic("impossible") + } + + // 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) + switch { + case value == 0x09: + case value == 0x0A: + case value == 0x0D: + case value >= 0x20 && value <= 0x7E: + case value == 0x85: + case value >= 0xA0 && value <= 0xD7FF: + case value >= 0xE000 && value <= 0xFFFD: + case value >= 0x10000 && value <= 0x10FFFF: + default: + return yaml_parser_set_reader_error(parser, + "control characters are not allowed", + parser.offset, int(value)) + } + + // Move the raw pointers. + parser.raw_buffer_pos += width + parser.offset += width + + // Finally put the character into the buffer. + if value <= 0x7F { + // 0000 0000-0000 007F . 0xxxxxxx + parser.buffer[buffer_len+0] = byte(value) + } else if value <= 0x7FF { + // 0000 0080-0000 07FF . 110xxxxx 10xxxxxx + parser.buffer[buffer_len+0] = byte(0xC0 + (value >> 6)) + parser.buffer[buffer_len+1] = byte(0x80 + (value & 0x3F)) + } else if value <= 0xFFFF { + // 0000 0800-0000 FFFF . 1110xxxx 10xxxxxx 10xxxxxx + parser.buffer[buffer_len+0] = byte(0xE0 + (value >> 12)) + parser.buffer[buffer_len+1] = byte(0x80 + ((value >> 6) & 0x3F)) + parser.buffer[buffer_len+2] = byte(0x80 + (value & 0x3F)) + } else { + // 0001 0000-0010 FFFF . 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx + parser.buffer[buffer_len+0] = byte(0xF0 + (value >> 18)) + parser.buffer[buffer_len+1] = byte(0x80 + ((value >> 12) & 0x3F)) + parser.buffer[buffer_len+2] = byte(0x80 + ((value >> 6) & 0x3F)) + parser.buffer[buffer_len+3] = byte(0x80 + (value & 0x3F)) + } + buffer_len += width + + parser.unread++ + } + + // On EOF, put NUL into the buffer and return. + if parser.eof { + parser.buffer[buffer_len] = 0 + buffer_len++ + parser.unread++ + break + } + } + parser.buffer = parser.buffer[:buffer_len] + return true +}
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/scannerc.go b/scannerc.go new file mode 100644 index 0000000..daad349 --- /dev/null +++ b/scannerc.go
@@ -0,0 +1,2710 @@ +package goyaml + +import ( + "bytes" + "fmt" +) + +// 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 +// + +// Ensure that the buffer contains the required number of characters. +// Return true on success, false on failure (reader error or memory error). +func cache(parser *yaml_parser_t, length int) bool { + // [Go] This was inlined: !cache(A, B) -> unread < B && !update(A, B) + return parser.unread >= length || yaml_parser_update_buffer(parser, length) +} + +// Advance the buffer pointer. +func skip(parser *yaml_parser_t) { + parser.mark.index++ + parser.mark.column++ + parser.unread-- + parser.buffer_pos += width(parser.buffer[parser.buffer_pos]) +} + +func skip_line(parser *yaml_parser_t) { + if is_crlf(parser.buffer, parser.buffer_pos) { + parser.mark.index += 2 + parser.mark.column = 0 + parser.mark.line++ + parser.unread -= 2 + parser.buffer_pos += 2 + } else if is_break(parser.buffer, parser.buffer_pos) { + parser.mark.index++ + parser.mark.column = 0 + parser.mark.line++ + parser.unread-- + parser.buffer_pos += width(parser.buffer[parser.buffer_pos]) + } +} + +// Copy a character to a string buffer and advance pointers. +func read(parser *yaml_parser_t, s []byte) []byte { + w := width(parser.buffer[parser.buffer_pos]) + if w == 0 { + panic("invalid character sequence") + } + if len(s) == 0 { + s = make([]byte, 0, 32) + } + if w == 1 && len(s)+w <= cap(s) { + s = s[:len(s)+1] + s[len(s)-1] = parser.buffer[parser.buffer_pos] + parser.buffer_pos++ + } else { + s = append(s, parser.buffer[parser.buffer_pos:parser.buffer_pos+w]...) + parser.buffer_pos += w + } + parser.mark.index++ + parser.mark.column++ + parser.unread-- + return s +} + +// Copy a line break character to a string buffer and advance pointers. +func read_line(parser *yaml_parser_t, s []byte) []byte { + buf := parser.buffer + pos := parser.buffer_pos + switch { + case buf[pos] == '\r' && buf[pos+1] == '\n': + // CR LF . LF + s = append(s, '\n') + parser.buffer_pos += 2 + parser.mark.index++ + parser.unread-- + case buf[pos] == '\r' || buf[pos] == '\n': + // CR|LF . LF + s = append(s, '\n') + parser.buffer_pos += 1 + case buf[pos] == '\xC2' && buf[pos+1] == '\x85': + // NEL . LF + s = append(s, '\n') + parser.buffer_pos += 2 + case buf[pos] == '\xE2' && buf[pos+1] == '\x80' && (buf[pos+2] == '\xA8' || buf[pos+2] == '\xA9'): + // LS|PS . LS|PS + s = append(s, buf[parser.buffer_pos:pos+3]...) + parser.buffer_pos += 3 + default: + return s + } + parser.mark.index++ + parser.mark.column = 0 + parser.mark.line++ + parser.unread-- + return s +} + +// Get the next token. +func yaml_parser_scan(parser *yaml_parser_t, token *yaml_token_t) bool { + // Erase the token object. + *token = yaml_token_t{} // [Go] Is this necessary? + + // No tokens after STREAM-END or error. + if parser.stream_end_produced || parser.error != yaml_NO_ERROR { + return true + } + + // Ensure that the tokens queue contains enough tokens. + if !parser.token_available { + if !yaml_parser_fetch_more_tokens(parser) { + return false + } + } + + // Fetch the next token from the queue. + *token = parser.tokens[parser.tokens_head] + parser.tokens_head++ + parser.tokens_parsed++ + parser.token_available = false + + if token.typ == yaml_STREAM_END_TOKEN { + parser.stream_end_produced = true + } + return true +} + +// Set the scanner error and return false. +func yaml_parser_set_scanner_error(parser *yaml_parser_t, context string, context_mark yaml_mark_t, problem string) bool { + parser.error = yaml_SCANNER_ERROR + parser.context = context + parser.context_mark = context_mark + parser.problem = problem + parser.problem_mark = parser.mark + return false +} + +func yaml_parser_set_scanner_tag_error(parser *yaml_parser_t, directive bool, context_mark yaml_mark_t, problem string) bool { + context := "while parsing a tag" + if directive { + context = "while parsing a %TAG directive" + } + 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 { + // While we need more tokens to fetch, do it. + for { + // Check if we really need to fetch more tokens. + need_more_tokens := false + + if parser.tokens_head == len(parser.tokens) { + // Queue is empty. + need_more_tokens = true + } else { + // Check if any potential simple key may occupy the head position. + if !yaml_parser_stale_simple_keys(parser) { + return false + } + + 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 + } + } + } + + // We are finished. + if !need_more_tokens { + break + } + // Fetch the next token. + if !yaml_parser_fetch_next_token(parser) { + return false + } + } + + parser.token_available = true + return true +} + +// The dispatcher for token fetchers. +func yaml_parser_fetch_next_token(parser *yaml_parser_t) bool { + // Ensure that the buffer is initialized. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + // 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 false + } + + // Remove obsolete potential simple keys. + if !yaml_parser_stale_simple_keys(parser) { + return false + } + + // Check the indentation level against the current column. + if !yaml_parser_unroll_indent(parser, parser.mark.column) { + return false + } + + // Ensure that the buffer contains at least 4 characters. 4 is the length + // of the longest indicators ('--- ' and '... '). + if parser.unread < 4 && !yaml_parser_update_buffer(parser, 4) { + return false + } + + // Is it the end of the stream? + if is_z(parser.buffer, parser.buffer_pos) { + return yaml_parser_fetch_stream_end(parser) + } + + // Is it a directive? + if parser.mark.column == 0 && parser.buffer[parser.buffer_pos] == '%' { + return yaml_parser_fetch_directive(parser) + } + + buf := parser.buffer + pos := parser.buffer_pos + + // Is it the document start indicator? + if parser.mark.column == 0 && buf[pos] == '-' && buf[pos+1] == '-' && buf[pos+2] == '-' && is_blankz(buf, pos+3) { + return yaml_parser_fetch_document_indicator(parser, yaml_DOCUMENT_START_TOKEN) + } + + // Is it the document end indicator? + if parser.mark.column == 0 && buf[pos] == '.' && buf[pos+1] == '.' && buf[pos+2] == '.' && is_blankz(buf, pos+3) { + return yaml_parser_fetch_document_indicator(parser, yaml_DOCUMENT_END_TOKEN) + } + + // Is it the flow sequence start indicator? + if buf[pos] == '[' { + return yaml_parser_fetch_flow_collection_start(parser, yaml_FLOW_SEQUENCE_START_TOKEN) + } + + // Is it the flow mapping start indicator? + if parser.buffer[parser.buffer_pos] == '{' { + return yaml_parser_fetch_flow_collection_start(parser, yaml_FLOW_MAPPING_START_TOKEN) + } + + // Is it the flow sequence end indicator? + if parser.buffer[parser.buffer_pos] == ']' { + return yaml_parser_fetch_flow_collection_end(parser, + yaml_FLOW_SEQUENCE_END_TOKEN) + } + + // Is it the flow mapping end indicator? + if parser.buffer[parser.buffer_pos] == '}' { + return yaml_parser_fetch_flow_collection_end(parser, + yaml_FLOW_MAPPING_END_TOKEN) + } + + // Is it the flow entry indicator? + if parser.buffer[parser.buffer_pos] == ',' { + return yaml_parser_fetch_flow_entry(parser) + } + + // Is it the block entry indicator? + if parser.buffer[parser.buffer_pos] == '-' && is_blankz(parser.buffer, parser.buffer_pos+1) { + return yaml_parser_fetch_block_entry(parser) + } + + // Is it the key indicator? + if parser.buffer[parser.buffer_pos] == '?' && (parser.flow_level > 0 || is_blankz(parser.buffer, parser.buffer_pos+1)) { + return yaml_parser_fetch_key(parser) + } + + // Is it the value indicator? + if parser.buffer[parser.buffer_pos] == ':' && (parser.flow_level > 0 || is_blankz(parser.buffer, parser.buffer_pos+1)) { + return yaml_parser_fetch_value(parser) + } + + // Is it an alias? + if parser.buffer[parser.buffer_pos] == '*' { + return yaml_parser_fetch_anchor(parser, yaml_ALIAS_TOKEN) + } + + // Is it an anchor? + if parser.buffer[parser.buffer_pos] == '&' { + return yaml_parser_fetch_anchor(parser, yaml_ANCHOR_TOKEN) + } + + // Is it a tag? + if parser.buffer[parser.buffer_pos] == '!' { + return yaml_parser_fetch_tag(parser) + } + + // Is it a literal scalar? + if parser.buffer[parser.buffer_pos] == '|' && parser.flow_level == 0 { + return yaml_parser_fetch_block_scalar(parser, true) + } + + // Is it a folded scalar? + if parser.buffer[parser.buffer_pos] == '>' && parser.flow_level == 0 { + return yaml_parser_fetch_block_scalar(parser, false) + } + + // Is it a single-quoted scalar? + if parser.buffer[parser.buffer_pos] == '\'' { + return yaml_parser_fetch_flow_scalar(parser, true) + } + + // Is it a double-quoted scalar? + if parser.buffer[parser.buffer_pos] == '"' { + return yaml_parser_fetch_flow_scalar(parser, false) + } + + // 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. + // [Go] Make this logic more reasonable. + //switch parser.buffer[parser.buffer_pos] { + //case '-', '?', ':', ',', '?', '-', ',', ':', ']', '[', '}', '{', '&', '#', '!', '*', '>', '|', '"', '\'', '@', '%', '-', '`': + //} + if !(is_blankz(parser.buffer, parser.buffer_pos) || parser.buffer[parser.buffer_pos] == '-' || + parser.buffer[parser.buffer_pos] == '?' || parser.buffer[parser.buffer_pos] == ':' || + parser.buffer[parser.buffer_pos] == ',' || parser.buffer[parser.buffer_pos] == '[' || + parser.buffer[parser.buffer_pos] == ']' || parser.buffer[parser.buffer_pos] == '{' || + parser.buffer[parser.buffer_pos] == '}' || parser.buffer[parser.buffer_pos] == '#' || + parser.buffer[parser.buffer_pos] == '&' || parser.buffer[parser.buffer_pos] == '*' || + parser.buffer[parser.buffer_pos] == '!' || parser.buffer[parser.buffer_pos] == '|' || + parser.buffer[parser.buffer_pos] == '>' || parser.buffer[parser.buffer_pos] == '\'' || + parser.buffer[parser.buffer_pos] == '"' || parser.buffer[parser.buffer_pos] == '%' || + parser.buffer[parser.buffer_pos] == '@' || parser.buffer[parser.buffer_pos] == '`') || + (parser.buffer[parser.buffer_pos] == '-' && !is_blank(parser.buffer, parser.buffer_pos+1)) || + (parser.flow_level == 0 && + (parser.buffer[parser.buffer_pos] == '?' || parser.buffer[parser.buffer_pos] == ':') && + !is_blankz(parser.buffer, parser.buffer_pos+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. +func yaml_parser_stale_simple_keys(parser *yaml_parser_t) bool { + // Check for a potential simple key for each flow level. + for i := range parser.simple_keys { + simple_key := &parser.simple_keys[i] + + // 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 = false + } + } + return true +} + +// Check if a simple key may start at the current position and add it if +// needed. +func yaml_parser_save_simple_key(parser *yaml_parser_t) bool { + // 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. + + required := parser.flow_level == 0 && parser.indent == 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. + if required && !parser.simple_key_allowed { + panic("should not happen") + } + + // + // If the current position may start a simple key, save it. + // + if parser.simple_key_allowed { + simple_key := yaml_simple_key_t{ + possible: true, + required: required, + token_number: parser.tokens_parsed + (len(parser.tokens) - parser.tokens_head), + } + simple_key.mark = parser.mark + + if !yaml_parser_remove_simple_key(parser) { + return false + } + parser.simple_keys[len(parser.simple_keys)-1] = simple_key + } + return true +} + +// Remove a potential simple key at the current flow level. +func yaml_parser_remove_simple_key(parser *yaml_parser_t) bool { + i := len(parser.simple_keys) - 1 + if parser.simple_keys[i].possible { + // If the key is required, it is an error. + if parser.simple_keys[i].required { + return yaml_parser_set_scanner_error(parser, + "while scanning a simple key", parser.simple_keys[i].mark, + "could not find expected ':'") + } + } + // Remove the key from the stack. + parser.simple_keys[i].possible = false + return true +} + +// Increase the flow level and resize the simple key list if needed. +func yaml_parser_increase_flow_level(parser *yaml_parser_t) bool { + // Reset the simple key on the next level. + parser.simple_keys = append(parser.simple_keys, yaml_simple_key_t{}) + + // Increase the flow level. + parser.flow_level++ + return true +} + +// Decrease the flow level. +func yaml_parser_decrease_flow_level(parser *yaml_parser_t) bool { + if parser.flow_level > 0 { + parser.flow_level-- + parser.simple_keys = parser.simple_keys[:len(parser.simple_keys)-1] + } + return true +} + +// 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. +func yaml_parser_roll_indent(parser *yaml_parser_t, column, number int, typ yaml_token_type_t, mark yaml_mark_t) bool { + // In the flow context, do nothing. + if parser.flow_level > 0 { + return true + } + + if parser.indent < column { + // Push the current indentation level to the stack and set the new + // indentation level. + parser.indents = append(parser.indents, parser.indent) + parser.indent = column + + // Create a token and insert it into the queue. + token := yaml_token_t{ + typ: typ, + start_mark: mark, + end_mark: mark, + } + if number > -1 { + number -= parser.tokens_parsed + } + yaml_insert_token(parser, number, &token) + } + return true +} + +// 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. +func yaml_parser_unroll_indent(parser *yaml_parser_t, column int) bool { + // In the flow context, do nothing. + if parser.flow_level > 0 { + return true + } + + // Loop through the intendation levels in the stack. + for parser.indent > column { + // Create a token and append it to the queue. + token := yaml_token_t{ + typ: yaml_BLOCK_END_TOKEN, + start_mark: parser.mark, + end_mark: parser.mark, + } + yaml_insert_token(parser, -1, &token) + + // Pop the indentation level. + parser.indent = parser.indents[len(parser.indents)-1] + parser.indents = parser.indents[:len(parser.indents)-1] + } + return true +} + +// 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 + + // Initialize the simple key stack. + parser.simple_keys = append(parser.simple_keys, yaml_simple_key_t{}) + + // A simple key is allowed at the beginning of the stream. + parser.simple_key_allowed = true + + // We have started. + parser.stream_start_produced = true + + // Create the STREAM-START token and append it to the queue. + token := yaml_token_t{ + typ: yaml_STREAM_START_TOKEN, + start_mark: parser.mark, + end_mark: parser.mark, + encoding: parser.encoding, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// 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 + parser.mark.line++ + } + + // Reset the indentation level. + if !yaml_parser_unroll_indent(parser, -1) { + return false + } + + // Reset simple keys. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + parser.simple_key_allowed = false + + // Create the STREAM-END token and append it to the queue. + token := yaml_token_t{ + typ: yaml_STREAM_END_TOKEN, + start_mark: parser.mark, + end_mark: parser.mark, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token. +func yaml_parser_fetch_directive(parser *yaml_parser_t) bool { + // Reset the indentation level. + if !yaml_parser_unroll_indent(parser, -1) { + return false + } + + // Reset simple keys. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + parser.simple_key_allowed = false + + // Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. + token := yaml_token_t{} + if !yaml_parser_scan_directive(parser, &token) { + return false + } + // Append the token to the queue. + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the DOCUMENT-START or DOCUMENT-END token. +func yaml_parser_fetch_document_indicator(parser *yaml_parser_t, typ yaml_token_type_t) bool { + // Reset the indentation level. + if !yaml_parser_unroll_indent(parser, -1) { + return false + } + + // Reset simple keys. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + parser.simple_key_allowed = false + + // 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 := yaml_token_t{ + typ: typ, + start_mark: start_mark, + end_mark: end_mark, + } + // Append the token to the queue. + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token. +func yaml_parser_fetch_flow_collection_start(parser *yaml_parser_t, typ yaml_token_type_t) bool { + // The indicators '[' and '{' may start a simple key. + if !yaml_parser_save_simple_key(parser) { + return false + } + + // Increase the flow level. + if !yaml_parser_increase_flow_level(parser) { + return false + } + + // A simple key may follow the indicators '[' and '{'. + parser.simple_key_allowed = true + + // Consume the token. + start_mark := parser.mark + skip(parser) + end_mark := parser.mark + + // Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. + token := yaml_token_t{ + typ: typ, + start_mark: start_mark, + end_mark: end_mark, + } + // Append the token to the queue. + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token. +func yaml_parser_fetch_flow_collection_end(parser *yaml_parser_t, typ yaml_token_type_t) bool { + // Reset any potential simple key on the current flow level. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + // Decrease the flow level. + if !yaml_parser_decrease_flow_level(parser) { + return false + } + + // No simple keys after the indicators ']' and '}'. + parser.simple_key_allowed = false + + // Consume the token. + + start_mark := parser.mark + skip(parser) + end_mark := parser.mark + + // Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. + token := yaml_token_t{ + typ: typ, + start_mark: start_mark, + end_mark: end_mark, + } + // Append the token to the queue. + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the FLOW-ENTRY token. +func yaml_parser_fetch_flow_entry(parser *yaml_parser_t) bool { + // Reset any potential simple keys on the current flow level. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + // Simple keys are allowed after ','. + parser.simple_key_allowed = true + + // 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 := yaml_token_t{ + typ: yaml_FLOW_ENTRY_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the BLOCK-ENTRY token. +func yaml_parser_fetch_block_entry(parser *yaml_parser_t) bool { + // Check if the scanner is in the block context. + if parser.flow_level == 0 { + // Check if we are allowed to start a new entry. + if !parser.simple_key_allowed { + return yaml_parser_set_scanner_error(parser, "", 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 false + } + } 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 false + } + + // Simple keys are allowed after '-'. + parser.simple_key_allowed = true + + // 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 := yaml_token_t{ + typ: yaml_BLOCK_ENTRY_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the KEY token. +func yaml_parser_fetch_key(parser *yaml_parser_t) bool { + + // In the block context, additional checks are required. + if parser.flow_level == 0 { + // 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, "", 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 false + } + } + + // Reset any potential simple keys on the current flow level. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + // Simple keys are allowed after '?' in the block context. + parser.simple_key_allowed = parser.flow_level == 0 + + // Consume the token. + start_mark := parser.mark + skip(parser) + end_mark := parser.mark + + // Create the KEY token and append it to the queue. + token := yaml_token_t{ + typ: yaml_KEY_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the VALUE token. +func yaml_parser_fetch_value(parser *yaml_parser_t) bool { + + simple_key := &parser.simple_keys[len(parser.simple_keys)-1] + + // Have we found a simple key? + if simple_key.possible { + // Create the KEY token and insert it into the queue. + token := yaml_token_t{ + typ: yaml_KEY_TOKEN, + start_mark: simple_key.mark, + end_mark: simple_key.mark, + } + yaml_insert_token(parser, simple_key.token_number-parser.tokens_parsed, &token) + + // 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 false + } + + // Remove the simple key. + simple_key.possible = false + + // A simple key cannot follow another simple key. + parser.simple_key_allowed = false + + } else { + // The ':' indicator follows a complex key. + + // In the block context, extra checks are required. + if parser.flow_level == 0 { + + // Check if we are allowed to start a complex value. + if !parser.simple_key_allowed { + return yaml_parser_set_scanner_error(parser, "", 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 false + } + } + + // Simple keys after ':' are allowed in the block context. + parser.simple_key_allowed = parser.flow_level == 0 + } + + // Consume the token. + start_mark := parser.mark + skip(parser) + end_mark := parser.mark + + // Create the VALUE token and append it to the queue. + token := yaml_token_t{ + typ: yaml_VALUE_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the ALIAS or ANCHOR token. +func yaml_parser_fetch_anchor(parser *yaml_parser_t, typ yaml_token_type_t) bool { + // An anchor or an alias could be a simple key. + if !yaml_parser_save_simple_key(parser) { + return false + } + + // A simple key cannot follow an anchor or an alias. + parser.simple_key_allowed = false + + // Create the ALIAS or ANCHOR token and append it to the queue. + var token yaml_token_t + if !yaml_parser_scan_anchor(parser, &token, typ) { + return false + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the TAG token. +func yaml_parser_fetch_tag(parser *yaml_parser_t) bool { + // A tag could be a simple key. + if !yaml_parser_save_simple_key(parser) { + return false + } + + // A simple key cannot follow a tag. + parser.simple_key_allowed = false + + // Create the TAG token and append it to the queue. + var token yaml_token_t + if !yaml_parser_scan_tag(parser, &token) { + return false + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens. +func yaml_parser_fetch_block_scalar(parser *yaml_parser_t, literal bool) bool { + // Remove any potential simple keys. + if !yaml_parser_remove_simple_key(parser) { + return false + } + + // A simple key may follow a block scalar. + parser.simple_key_allowed = true + + // Create the SCALAR token and append it to the queue. + var token yaml_token_t + if !yaml_parser_scan_block_scalar(parser, &token, literal) { + return false + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens. +func yaml_parser_fetch_flow_scalar(parser *yaml_parser_t, single bool) bool { + // A plain scalar could be a simple key. + if !yaml_parser_save_simple_key(parser) { + return false + } + + // A simple key cannot follow a flow scalar. + parser.simple_key_allowed = false + + // Create the SCALAR token and append it to the queue. + var token yaml_token_t + if !yaml_parser_scan_flow_scalar(parser, &token, single) { + return false + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Produce the SCALAR(...,plain) token. +func yaml_parser_fetch_plain_scalar(parser *yaml_parser_t) bool { + // A plain scalar could be a simple key. + if !yaml_parser_save_simple_key(parser) { + return false + } + + // A simple key cannot follow a flow scalar. + parser.simple_key_allowed = false + + // Create the SCALAR token and append it to the queue. + var token yaml_token_t + if !yaml_parser_scan_plain_scalar(parser, &token) { + return false + } + yaml_insert_token(parser, -1, &token) + return true +} + +// Eat whitespaces and comments until the next token is found. +func yaml_parser_scan_to_next_token(parser *yaml_parser_t) bool { + + // Until the next token is not found. + for { + // Allow the BOM mark to start a line. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if parser.mark.column == 0 && is_bom(parser.buffer, parser.buffer_pos) { + 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 parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for parser.buffer[parser.buffer_pos] == ' ' || ((parser.flow_level > 0 || !parser.simple_key_allowed) && parser.buffer[parser.buffer_pos] == '\t') { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Eat a comment until a line break. + if parser.buffer[parser.buffer_pos] == '#' { + for !is_breakz(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + } + + // If it is a line break, eat it. + if is_break(parser.buffer, parser.buffer_pos) { + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + skip_line(parser) + + // In the block context, a new line may start a simple key. + if parser.flow_level == 0 { + parser.simple_key_allowed = true + } + } else { + break // We have found a token. + } + } + + return true +} + +// Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token. +// +// Scope: +// %YAML 1.1 # a comment \n +// ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +// %TAG !yaml! tag:yaml.org,2002: \n +// ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +// +func yaml_parser_scan_directive(parser *yaml_parser_t, token *yaml_token_t) bool { + // Eat '%'. + start_mark := parser.mark + skip(parser) + + // Scan the directive name. + var name []byte + if !yaml_parser_scan_directive_name(parser, start_mark, &name) { + return false + } + + // Is it a YAML directive? + if bytes.Equal(name, []byte("YAML")) { + // Scan the VERSION directive value. + var major, minor int8 + if !yaml_parser_scan_version_directive_value(parser, start_mark, &major, &minor) { + return false + } + end_mark := parser.mark + + // Create a VERSION-DIRECTIVE token. + *token = yaml_token_t{ + typ: yaml_VERSION_DIRECTIVE_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + major: major, + minor: minor, + } + + // Is it a TAG directive? + } else if bytes.Equal(name, []byte("TAG")) { + // Scan the TAG directive value. + var handle, prefix []byte + if !yaml_parser_scan_tag_directive_value(parser, start_mark, &handle, &prefix) { + return false + } + end_mark := parser.mark + + // Create a TAG-DIRECTIVE token. + *token = yaml_token_t{ + typ: yaml_TAG_DIRECTIVE_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + value: handle, + prefix: prefix, + } + + // Unknown directive. + } else { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "found uknown directive name") + return false + } + + // Eat the rest of the line including any comments. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for is_blank(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + if parser.buffer[parser.buffer_pos] == '#' { + for !is_breakz(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + } + + // Check if we are at the end of the line. + if !is_breakz(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "did not find expected comment or line break") + return false + } + + // Eat a line break. + if is_break(parser.buffer, parser.buffer_pos) { + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + skip_line(parser) + } + + return true +} + +// Scan the directive name. +// +// Scope: +// %YAML 1.1 # a comment \n +// ^^^^ +// %TAG !yaml! tag:yaml.org,2002: \n +// ^^^ +// +func yaml_parser_scan_directive_name(parser *yaml_parser_t, start_mark yaml_mark_t, name *[]byte) bool { + // Consume the directive name. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + var s []byte + for is_alpha(parser.buffer, parser.buffer_pos) { + s = read(parser, s) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Check if the name is empty. + if len(s) == 0 { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "could not find expected directive name") + return false + } + + // Check for an blank character after the name. + if !is_blankz(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "found unexpected non-alphabetical character") + return false + } + *name = s + return true +} + +// Scan the value of VERSION-DIRECTIVE. +// +// Scope: +// %YAML 1.1 # a comment \n +// ^^^^^^ +func yaml_parser_scan_version_directive_value(parser *yaml_parser_t, start_mark yaml_mark_t, major, minor *int8) bool { + // Eat whitespaces. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + for is_blank(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Consume the major version number. + if !yaml_parser_scan_version_directive_number(parser, start_mark, major) { + return false + } + + // Eat '.'. + if parser.buffer[parser.buffer_pos] != '.' { + 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 false + } + return true +} + +const max_number_length = 2 + +// Scan the version number of VERSION-DIRECTIVE. +// +// Scope: +// %YAML 1.1 # a comment \n +// ^ +// %YAML 1.1 # a comment \n +// ^ +func yaml_parser_scan_version_directive_number(parser *yaml_parser_t, start_mark yaml_mark_t, number *int8) bool { + + // Repeat while the next character is digit. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + var value, length int8 + for is_digit(parser.buffer, parser.buffer_pos) { + // Check if the number is too long. + length++ + 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 + int8(as_digit(parser.buffer, parser.buffer_pos)) + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Check if the number was present. + if length == 0 { + return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", + start_mark, "did not find expected version number") + } + *number = value + return true +} + +// Scan the value of a TAG-DIRECTIVE token. +// +// Scope: +// %TAG !yaml! tag:yaml.org,2002: \n +// ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +// +func yaml_parser_scan_tag_directive_value(parser *yaml_parser_t, start_mark yaml_mark_t, handle, prefix *[]byte) bool { + var handle_value, prefix_value []byte + + // Eat whitespaces. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for is_blank(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Scan a handle. + if !yaml_parser_scan_tag_handle(parser, true, start_mark, &handle_value) { + return false + } + + // Expect a whitespace. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if !is_blank(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", + start_mark, "did not find expected whitespace") + return false + } + + // Eat whitespaces. + for is_blank(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Scan a prefix. + if !yaml_parser_scan_tag_uri(parser, true, nil, start_mark, &prefix_value) { + return false + } + + // Expect a whitespace or line break. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if !is_blankz(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", + start_mark, "did not find expected whitespace or line break") + return false + } + + *handle = handle_value + *prefix = prefix_value + return true +} + +func yaml_parser_scan_anchor(parser *yaml_parser_t, token *yaml_token_t, typ yaml_token_type_t) bool { + var s []byte + + // Eat the indicator character. + start_mark := parser.mark + skip(parser) + + // Consume the value. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for is_alpha(parser.buffer, parser.buffer_pos) { + s = read(parser, s) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + 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 len(s) == 0 || + !(is_blankz(parser.buffer, parser.buffer_pos) || parser.buffer[parser.buffer_pos] == '?' || + parser.buffer[parser.buffer_pos] == ':' || parser.buffer[parser.buffer_pos] == ',' || + parser.buffer[parser.buffer_pos] == ']' || parser.buffer[parser.buffer_pos] == '}' || + parser.buffer[parser.buffer_pos] == '%' || parser.buffer[parser.buffer_pos] == '@' || + parser.buffer[parser.buffer_pos] == '`') { + context := "while scanning an alias" + if typ == yaml_ANCHOR_TOKEN { + context = "while scanning an anchor" + } + yaml_parser_set_scanner_error(parser, context, start_mark, + "did not find expected alphabetic or numeric character") + return false + } + + // Create a token. + *token = yaml_token_t{ + typ: typ, + start_mark: start_mark, + end_mark: end_mark, + value: s, + } + + return true +} + +/* + * Scan a TAG token. + */ + +func yaml_parser_scan_tag(parser *yaml_parser_t, token *yaml_token_t) bool { + var handle, suffix []byte + + start_mark := parser.mark + + // Check if the tag is in the canonical form. + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + + if parser.buffer[parser.buffer_pos+1] == '<' { + // Keep the handle as '' + + // Eat '!<' + skip(parser) + skip(parser) + + // Consume the tag value. + if !yaml_parser_scan_tag_uri(parser, false, nil, start_mark, &suffix) { + return false + } + + // Check for '>' and eat it. + if parser.buffer[parser.buffer_pos] != '>' { + yaml_parser_set_scanner_error(parser, "while scanning a tag", + start_mark, "did not find the expected '>'") + return false + } + + 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, false, start_mark, &handle) { + return false + } + + // Check if it is, indeed, handle. + if handle[0] == '!' && len(handle) > 1 && handle[len(handle)-1] == '!' { + // Scan the suffix now. + if !yaml_parser_scan_tag_uri(parser, false, nil, start_mark, &suffix) { + return false + } + } else { + // It wasn't a handle after all. Scan the rest of the tag. + if !yaml_parser_scan_tag_uri(parser, false, handle, start_mark, &suffix) { + return false + } + + // Set the handle to '!'. + handle = []byte{'!'} + + // A special case: the '!' tag. Set the handle to '' and the + // suffix to '!'. + if len(suffix) == 0 { + handle, suffix = suffix, handle + } + } + } + + // Check the character which ends the tag. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if !is_blankz(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a tag", + start_mark, "did not find expected whitespace or line break") + return false + } + + end_mark := parser.mark + + // Create a token. + *token = yaml_token_t{ + typ: yaml_TAG_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + value: handle, + suffix: suffix, + } + return true +} + +// Scan a tag handle. +func yaml_parser_scan_tag_handle(parser *yaml_parser_t, directive bool, start_mark yaml_mark_t, handle *[]byte) bool { + // Check the initial '!' character. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if parser.buffer[parser.buffer_pos] != '!' { + yaml_parser_set_scanner_tag_error(parser, directive, + start_mark, "did not find expected '!'") + return false + } + + var s []byte + + // Copy the '!' character. + s = read(parser, s) + + // Copy all subsequent alphabetical and numerical characters. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + for is_alpha(parser.buffer, parser.buffer_pos) { + s = read(parser, s) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Check if the trailing character is '!' and copy it. + if parser.buffer[parser.buffer_pos] == '!' { + s = read(parser, s) + } 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 && !(s[0] == '!' && s[1] == 0) { + yaml_parser_set_scanner_tag_error(parser, directive, + start_mark, "did not find expected '!'") + return false + } + } + + *handle = s + return true +} + +// Scan a tag. +func yaml_parser_scan_tag_uri(parser *yaml_parser_t, directive bool, head []byte, start_mark yaml_mark_t, uri *[]byte) bool { + //size_t length = head ? strlen((char *)head) : 0 + var s []byte + + // Copy the head if needed. + // + // Note that we don't copy the leading '!' character. + if len(head) > 1 { + s = append(s, head[1:]...) + } + + // Scan the tag. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + // The set of characters that may appear in URI is as follows: + // + // '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&', + // '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']', + // '%'. + // [Go] Convert this into more reasonable logic. + for is_alpha(parser.buffer, parser.buffer_pos) || parser.buffer[parser.buffer_pos] == ';' || + parser.buffer[parser.buffer_pos] == '/' || parser.buffer[parser.buffer_pos] == '?' || + parser.buffer[parser.buffer_pos] == ':' || parser.buffer[parser.buffer_pos] == '@' || + parser.buffer[parser.buffer_pos] == '&' || parser.buffer[parser.buffer_pos] == '=' || + parser.buffer[parser.buffer_pos] == '+' || parser.buffer[parser.buffer_pos] == '$' || + parser.buffer[parser.buffer_pos] == ',' || parser.buffer[parser.buffer_pos] == '.' || + parser.buffer[parser.buffer_pos] == '!' || parser.buffer[parser.buffer_pos] == '~' || + parser.buffer[parser.buffer_pos] == '*' || parser.buffer[parser.buffer_pos] == '\'' || + parser.buffer[parser.buffer_pos] == '(' || parser.buffer[parser.buffer_pos] == ')' || + parser.buffer[parser.buffer_pos] == '[' || parser.buffer[parser.buffer_pos] == ']' || + parser.buffer[parser.buffer_pos] == '%' { + // Check if it is a URI-escape sequence. + if parser.buffer[parser.buffer_pos] == '%' { + if !yaml_parser_scan_uri_escapes(parser, directive, start_mark, &s) { + return false + } + } else { + s = read(parser, s) + } + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Check if the tag is non-empty. + if len(s) == 0 { + yaml_parser_set_scanner_tag_error(parser, directive, + start_mark, "did not find expected tag URI") + return false + } + *uri = s + return true +} + +// Decode an URI-escape sequence corresponding to a single UTF-8 character. +func yaml_parser_scan_uri_escapes(parser *yaml_parser_t, directive bool, start_mark yaml_mark_t, s *[]byte) bool { + + // Decode the required number of characters. + w := 1024 + for w > 0 { + // Check for a URI-escaped octet. + if parser.unread < 3 && !yaml_parser_update_buffer(parser, 3) { + return false + } + + if !(parser.buffer[parser.buffer_pos] == '%' && + is_hex(parser.buffer, parser.buffer_pos+1) && + is_hex(parser.buffer, parser.buffer_pos+2)) { + return yaml_parser_set_scanner_tag_error(parser, directive, + start_mark, "did not find URI escaped octet") + } + + // Get the octet. + octet := byte((as_hex(parser.buffer, parser.buffer_pos+1) << 4) + as_hex(parser.buffer, parser.buffer_pos+2)) + + // If it is the leading octet, determine the length of the UTF-8 sequence. + if w == 1024 { + w = width(octet) + if w == 0 { + return yaml_parser_set_scanner_tag_error(parser, directive, + 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_tag_error(parser, directive, + start_mark, "found an incorrect trailing UTF-8 octet") + } + } + + // Copy the octet and move the pointers. + *s = append(*s, octet) + skip(parser) + skip(parser) + skip(parser) + w-- + } + return true +} + +// Scan a block scalar. +func yaml_parser_scan_block_scalar(parser *yaml_parser_t, token *yaml_token_t, literal bool) bool { + // Eat the indicator '|' or '>'. + start_mark := parser.mark + skip(parser) + + // Scan the additional block scalar indicators. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + // Check for a chomping indicator. + var chomping, increment int + if parser.buffer[parser.buffer_pos] == '+' || parser.buffer[parser.buffer_pos] == '-' { + // Set the chomping method and eat the indicator. + if parser.buffer[parser.buffer_pos] == '+' { + chomping = +1 + } else { + chomping = -1 + } + skip(parser) + + // Check for an indentation indicator. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if is_digit(parser.buffer, parser.buffer_pos) { + // Check that the intendation is greater than 0. + if parser.buffer[parser.buffer_pos] == '0' { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "found an intendation indicator equal to 0") + return false + } + + // Get the intendation level and eat the indicator. + increment = as_digit(parser.buffer, parser.buffer_pos) + skip(parser) + } + + } else if is_digit(parser.buffer, parser.buffer_pos) { + // Do the same as above, but in the opposite order. + + if parser.buffer[parser.buffer_pos] == '0' { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "found an intendation indicator equal to 0") + return false + } + increment = as_digit(parser.buffer, parser.buffer_pos) + skip(parser) + + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + if parser.buffer[parser.buffer_pos] == '+' || parser.buffer[parser.buffer_pos] == '-' { + if parser.buffer[parser.buffer_pos] == '+' { + chomping = +1 + } else { + chomping = -1 + } + skip(parser) + } + } + + // Eat whitespaces and comments to the end of the line. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + for is_blank(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + if parser.buffer[parser.buffer_pos] == '#' { + for !is_breakz(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + } + + // Check if we are at the end of the line. + if !is_breakz(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "did not find expected comment or line break") + return false + } + + // Eat a line break. + if is_break(parser.buffer, parser.buffer_pos) { + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + skip_line(parser) + } + + end_mark := parser.mark + + // Set the intendation level if it was specified. + var indent int + if increment > 0 { + if parser.indent >= 0 { + indent = parser.indent + increment + } else { + indent = increment + } + } + + // Scan the leading line breaks and determine the indentation level if needed. + var s, leading_break, trailing_breaks []byte + if !yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks, start_mark, &end_mark) { + return false + } + + // Scan the block scalar content. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + var leading_blank, trailing_blank bool + for parser.mark.column == indent && !is_z(parser.buffer, parser.buffer_pos) { + // We are at the beginning of a non-empty line. + + // Is it a trailing whitespace? + 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 && 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, ' ') + } + } else { + s = append(s, leading_break...) + } + leading_break = leading_break[:0] + + // Append the remaining line breaks. + s = append(s, trailing_breaks...) + trailing_breaks = trailing_breaks[:0] + + // Is it a leading whitespace? + leading_blank = is_blank(parser.buffer, parser.buffer_pos) + + // Consume the current line. + for !is_breakz(parser.buffer, parser.buffer_pos) { + s = read(parser, s) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Consume the line break. + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + + leading_break = read_line(parser, leading_break) + + // Eat the following intendation spaces and line breaks. + if !yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks, start_mark, &end_mark) { + return false + } + } + + // Chomp the tail. + if chomping != -1 { + s = append(s, leading_break...) + } + if chomping == 1 { + s = append(s, trailing_breaks...) + } + + // Create a token. + *token = yaml_token_t{ + typ: yaml_SCALAR_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + value: s, + style: yaml_LITERAL_SCALAR_STYLE, + } + if !literal { + token.style = yaml_FOLDED_SCALAR_STYLE + } + return true +} + +// Scan intendation spaces and line breaks for a block scalar. Determine the +// intendation level if needed. +func yaml_parser_scan_block_scalar_breaks(parser *yaml_parser_t, indent *int, breaks *[]byte, start_mark yaml_mark_t, end_mark *yaml_mark_t) bool { + *end_mark = parser.mark + + // Eat the intendation spaces and line breaks. + max_indent := 0 + for { + // Eat the intendation spaces. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + for (*indent == 0 || parser.mark.column < *indent) && is_space(parser.buffer, parser.buffer_pos) { + skip(parser) + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + if parser.mark.column > max_indent { + max_indent = parser.mark.column + } + + // Check for a tab character messing the intendation. + if (*indent == 0 || parser.mark.column < *indent) && is_tab(parser.buffer, parser.buffer_pos) { + 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, parser.buffer_pos) { + break + } + + // Consume the line break. + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + // [Go] Should really be returning breaks instead. + *breaks = read_line(parser, *breaks) + *end_mark = parser.mark + } + + // Determine the indentation level if needed. + if *indent == 0 { + *indent = max_indent + if *indent < parser.indent+1 { + *indent = parser.indent + 1 + } + if *indent < 1 { + *indent = 1 + } + } + return true +} + +// Scan a quoted scalar. +func yaml_parser_scan_flow_scalar(parser *yaml_parser_t, token *yaml_token_t, single bool) bool { + // Eat the left quote. + start_mark := parser.mark + skip(parser) + + // Consume the content of the quoted scalar. + var s, leading_break, trailing_breaks, whitespaces []byte + for { + // Check that there are no document indicators at the beginning of the line. + if parser.unread < 4 && !yaml_parser_update_buffer(parser, 4) { + return false + } + + if parser.mark.column == 0 && + ((parser.buffer[parser.buffer_pos+0] == '-' && + parser.buffer[parser.buffer_pos+1] == '-' && + parser.buffer[parser.buffer_pos+2] == '-') || + (parser.buffer[parser.buffer_pos+0] == '.' && + parser.buffer[parser.buffer_pos+1] == '.' && + parser.buffer[parser.buffer_pos+2] == '.')) && + is_blankz(parser.buffer, parser.buffer_pos+3) { + yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", + start_mark, "found unexpected document indicator") + return false + } + + // Check for EOF. + if is_z(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", + start_mark, "found unexpected end of stream") + return false + } + + // Consume non-blank characters. + leading_blanks := false + for !is_blankz(parser.buffer, parser.buffer_pos) { + if single && parser.buffer[parser.buffer_pos] == '\'' && parser.buffer[parser.buffer_pos+1] == '\'' { + // Is is an escaped single quote. + s = append(s, '\'') + skip(parser) + skip(parser) + + } else if single && parser.buffer[parser.buffer_pos] == '\'' { + // It is a right single quote. + break + } else if !single && parser.buffer[parser.buffer_pos] == '"' { + // It is a right double quote. + break + + } else if !single && parser.buffer[parser.buffer_pos] == '\\' && is_break(parser.buffer, parser.buffer_pos+1) { + // It is an escaped line break. + if parser.unread < 3 && !yaml_parser_update_buffer(parser, 3) { + return false + } + skip(parser) + skip_line(parser) + leading_blanks = true + break + + } else if !single && parser.buffer[parser.buffer_pos] == '\\' { + // It is an escape sequence. + code_length := 0 + + // Check the escape character. + switch parser.buffer[parser.buffer_pos+1] { + case '0': + s = append(s, 0) + case 'a': + s = append(s, '\x07') + case 'b': + s = append(s, '\x08') + case 't', '\t': + s = append(s, '\x09') + case 'n': + s = append(s, '\x0A') + case 'v': + s = append(s, '\x0B') + case 'f': + s = append(s, '\x0C') + case 'r': + s = append(s, '\x0D') + case 'e': + s = append(s, '\x1B') + case ' ': + s = append(s, '\x20') + case '"': + s = append(s, '"') + case '\'': + s = append(s, '\'') + case '\\': + s = append(s, '\\') + case 'N': // NEL (#x85) + s = append(s, '\xC2') + s = append(s, '\x85') + case '_': // #xA0 + s = append(s, '\xC2') + s = append(s, '\xA0') + case 'L': // LS (#x2028) + s = append(s, '\xE2') + s = append(s, '\x80') + s = append(s, '\xA8') + case 'P': // PS (#x2029) + s = append(s, '\xE2') + s = append(s, '\x80') + s = append(s, '\xA9') + case 'x': + code_length = 2 + case 'u': + code_length = 4 + case 'U': + code_length = 8 + default: + yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", + start_mark, "found unknown escape character") + return false + } + + skip(parser) + skip(parser) + + // Consume an arbitrary escape code. + if code_length > 0 { + var value int + + // Scan the character value. + if parser.unread < code_length && !yaml_parser_update_buffer(parser, code_length) { + return false + } + for k := 0; k < code_length; k++ { + if !is_hex(parser.buffer, parser.buffer_pos+k) { + yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", + start_mark, "did not find expected hexdecimal number") + return false + } + value = (value << 4) + as_hex(parser.buffer, parser.buffer_pos+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") + return false + } + if value <= 0x7F { + s = append(s, byte(value)) + } else if value <= 0x7FF { + s = append(s, byte(0xC0+(value>>6))) + s = append(s, byte(0x80+(value&0x3F))) + } else if value <= 0xFFFF { + s = append(s, byte(0xE0+(value>>12))) + s = append(s, byte(0x80+((value>>6)&0x3F))) + s = append(s, byte(0x80+(value&0x3F))) + } else { + s = append(s, byte(0xF0+(value>>18))) + s = append(s, byte(0x80+((value>>12)&0x3F))) + s = append(s, byte(0x80+((value>>6)&0x3F))) + s = append(s, byte(0x80+(value&0x3F))) + } + + // Advance the pointer. + for k := 0; k < code_length; k++ { + skip(parser) + } + } + } else { + // It is a non-escaped non-blank character. + s = read(parser, s) + } + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + } + + // Check if we are at the end of the scalar. + if single { + if parser.buffer[parser.buffer_pos] == '\'' { + break + } + } else { + if parser.buffer[parser.buffer_pos] == '"' { + break + } + } + + // Consume blank characters. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for is_blank(parser.buffer, parser.buffer_pos) || is_break(parser.buffer, parser.buffer_pos) { + if is_blank(parser.buffer, parser.buffer_pos) { + // Consume a space or a tab character. + if !leading_blanks { + whitespaces = read(parser, whitespaces) + } else { + skip(parser) + } + } else { + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + + // Check if it is a first line break. + if !leading_blanks { + whitespaces = whitespaces[:0] + leading_break = read_line(parser, leading_break) + leading_blanks = true + } else { + trailing_breaks = read_line(parser, trailing_breaks) + } + } + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Join the whitespaces or fold line breaks. + if leading_blanks { + // Do we need to fold line breaks? + if leading_break[0] == '\n' { + if len(trailing_breaks) == 0 { + s = append(s, ' ') + } else { + s = append(s, trailing_breaks...) + } + } else { + s = append(s, leading_break...) + s = append(s, trailing_breaks...) + } + trailing_breaks = trailing_breaks[:0] + leading_break = leading_break[:0] + } else { + s = append(s, whitespaces...) + whitespaces = whitespaces[:0] + } + } + + // Eat the right quote. + skip(parser) + end_mark := parser.mark + + // Create a token. + *token = yaml_token_t{ + typ: yaml_SCALAR_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + value: s, + style: yaml_SINGLE_QUOTED_SCALAR_STYLE, + } + if !single { + token.style = yaml_DOUBLE_QUOTED_SCALAR_STYLE + } + return true +} + +// 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 + + start_mark := parser.mark + end_mark := parser.mark + + // Consume the content of the plain scalar. + for { + // Check for a document indicator. + if parser.unread < 4 && !yaml_parser_update_buffer(parser, 4) { + return false + } + if parser.mark.column == 0 && + ((parser.buffer[parser.buffer_pos+0] == '-' && + parser.buffer[parser.buffer_pos+1] == '-' && + parser.buffer[parser.buffer_pos+2] == '-') || + (parser.buffer[parser.buffer_pos+0] == '.' && + parser.buffer[parser.buffer_pos+1] == '.' && + parser.buffer[parser.buffer_pos+2] == '.')) && + is_blankz(parser.buffer, parser.buffer_pos+3) { + break + } + + // Check for a comment. + if parser.buffer[parser.buffer_pos] == '#' { + break + } + + // Consume non-blank characters. + for !is_blankz(parser.buffer, parser.buffer_pos) { + + // Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". + if parser.flow_level > 0 && + parser.buffer[parser.buffer_pos] == ':' && + !is_blankz(parser.buffer, parser.buffer_pos+1) { + yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", + start_mark, "found unexpected ':'") + return false + } + + // Check for indicators that may end a plain scalar. + if (parser.buffer[parser.buffer_pos] == ':' && is_blankz(parser.buffer, parser.buffer_pos+1)) || + (parser.flow_level > 0 && + (parser.buffer[parser.buffer_pos] == ',' || parser.buffer[parser.buffer_pos] == ':' || + parser.buffer[parser.buffer_pos] == '?' || parser.buffer[parser.buffer_pos] == '[' || + parser.buffer[parser.buffer_pos] == ']' || parser.buffer[parser.buffer_pos] == '{' || + parser.buffer[parser.buffer_pos] == '}')) { + break + } + + // Check if we need to join whitespaces and breaks. + if leading_blanks || len(whitespaces) > 0 { + if leading_blanks { + // Do we need to fold line breaks? + if leading_break[0] == '\n' { + if len(trailing_breaks) == 0 { + s = append(s, ' ') + } else { + s = append(s, trailing_breaks...) + } + } else { + s = append(s, leading_break...) + s = append(s, trailing_breaks...) + } + trailing_breaks = trailing_breaks[:0] + leading_break = leading_break[:0] + leading_blanks = false + } else { + s = append(s, whitespaces...) + whitespaces = whitespaces[:0] + } + } + + // Copy the character. + s = read(parser, s) + + end_mark = parser.mark + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + } + + // Is it the end? + if !(is_blank(parser.buffer, parser.buffer_pos) || is_break(parser.buffer, parser.buffer_pos)) { + break + } + + // Consume blank characters. + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + + for is_blank(parser.buffer, parser.buffer_pos) || is_break(parser.buffer, parser.buffer_pos) { + if is_blank(parser.buffer, parser.buffer_pos) { + + // Check for tab character that abuse intendation. + if leading_blanks && parser.mark.column < indent && is_tab(parser.buffer, parser.buffer_pos) { + yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", + start_mark, "found a tab character that violate intendation") + return false + } + + // Consume a space or a tab character. + if !leading_blanks { + whitespaces = read(parser, whitespaces) + } else { + skip(parser) + } + } else { + if parser.unread < 2 && !yaml_parser_update_buffer(parser, 2) { + return false + } + + // Check if it is a first line break. + if !leading_blanks { + whitespaces = whitespaces[:0] + leading_break = read_line(parser, leading_break) + leading_blanks = true + } else { + trailing_breaks = read_line(parser, trailing_breaks) + } + } + if parser.unread < 1 && !yaml_parser_update_buffer(parser, 1) { + return false + } + } + + // Check intendation level. + if parser.flow_level == 0 && parser.mark.column < indent { + break + } + } + + // Create a token. + *token = yaml_token_t{ + typ: yaml_SCALAR_TOKEN, + start_mark: start_mark, + end_mark: end_mark, + value: s, + style: yaml_PLAIN_SCALAR_STYLE, + } + + // Note that we change the 'simple_key_allowed' flag. + if leading_blanks { + parser.simple_key_allowed = true + } + return true +}
diff --git a/writer.c b/writer.c deleted file mode 100644 index b90019f..0000000 --- a/writer.c +++ /dev/null
@@ -1,141 +0,0 @@ - -#include "yaml_private.h" - -/* - * Declarations. - */ - -static int -yaml_emitter_set_writer_error(yaml_emitter_t *emitter, const char *problem); - -YAML_DECLARE(int) -yaml_emitter_flush(yaml_emitter_t *emitter); - -/* - * Set the writer error and return 0. - */ - -static int -yaml_emitter_set_writer_error(yaml_emitter_t *emitter, const char *problem) -{ - emitter->error = YAML_WRITER_ERROR; - emitter->problem = problem; - - return 0; -} - -/* - * Flush the output buffer. - */ - -YAML_DECLARE(int) -yaml_emitter_flush(yaml_emitter_t *emitter) -{ - int low, high; - - assert(emitter); /* Non-NULL emitter object is expected. */ - assert(emitter->write_handler); /* Write handler must be set. */ - assert(emitter->encoding); /* Output encoding must be set. */ - - emitter->buffer.last = emitter->buffer.pointer; - emitter->buffer.pointer = emitter->buffer.start; - - /* Check if the buffer is empty. */ - - if (emitter->buffer.start == emitter->buffer.last) { - return 1; - } - - /* If the output encoding is UTF-8, we don't need to recode the buffer. */ - - if (emitter->encoding == YAML_UTF8_ENCODING) - { - if (emitter->write_handler(emitter->write_handler_data, - emitter->buffer.start, - emitter->buffer.last - emitter->buffer.start)) { - emitter->buffer.last = emitter->buffer.start; - emitter->buffer.pointer = emitter->buffer.start; - return 1; - } - else { - return yaml_emitter_set_writer_error(emitter, "write error"); - } - } - - /* Recode the buffer into the raw buffer. */ - - low = (emitter->encoding == YAML_UTF16LE_ENCODING ? 0 : 1); - high = (emitter->encoding == YAML_UTF16LE_ENCODING ? 1 : 0); - - while (emitter->buffer.pointer != emitter->buffer.last) - { - unsigned char octet; - unsigned int width; - unsigned int value; - size_t k; - - /* - * See the "reader.c" code for more details on UTF-8 encoding. Note - * that we assume that the buffer contains a valid UTF-8 sequence. - */ - - /* Read the next UTF-8 character. */ - - octet = emitter->buffer.pointer[0]; - - width = (octet & 0x80) == 0x00 ? 1 : - (octet & 0xE0) == 0xC0 ? 2 : - (octet & 0xF0) == 0xE0 ? 3 : - (octet & 0xF8) == 0xF0 ? 4 : 0; - - value = (octet & 0x80) == 0x00 ? octet & 0x7F : - (octet & 0xE0) == 0xC0 ? octet & 0x1F : - (octet & 0xF0) == 0xE0 ? octet & 0x0F : - (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; - - for (k = 1; k < width; k ++) { - octet = emitter->buffer.pointer[k]; - value = (value << 6) + (octet & 0x3F); - } - - emitter->buffer.pointer += width; - - /* Write the character. */ - - if (value < 0x10000) - { - emitter->raw_buffer.last[high] = value >> 8; - emitter->raw_buffer.last[low] = value & 0xFF; - - emitter->raw_buffer.last += 2; - } - else - { - /* Write the character using a surrogate pair (check "reader.c"). */ - - value -= 0x10000; - emitter->raw_buffer.last[high] = 0xD8 + (value >> 18); - emitter->raw_buffer.last[low] = (value >> 10) & 0xFF; - emitter->raw_buffer.last[high+2] = 0xDC + ((value >> 8) & 0xFF); - emitter->raw_buffer.last[low+2] = value & 0xFF; - - emitter->raw_buffer.last += 4; - } - } - - /* Write the raw buffer. */ - - if (emitter->write_handler(emitter->write_handler_data, - emitter->raw_buffer.start, - emitter->raw_buffer.last - emitter->raw_buffer.start)) { - emitter->buffer.last = emitter->buffer.start; - emitter->buffer.pointer = emitter->buffer.start; - emitter->raw_buffer.last = emitter->raw_buffer.start; - emitter->raw_buffer.pointer = emitter->raw_buffer.start; - return 1; - } - else { - return yaml_emitter_set_writer_error(emitter, "write error"); - } -} -
diff --git a/writerc.go b/writerc.go new file mode 100644 index 0000000..4809bfb --- /dev/null +++ b/writerc.go
@@ -0,0 +1,89 @@ +package goyaml + +// Set the writer error and return false. +func yaml_emitter_set_writer_error(emitter *yaml_emitter_t, problem string) bool { + emitter.error = yaml_WRITER_ERROR + emitter.problem = problem + return false +} + +// Flush the output buffer. +func yaml_emitter_flush(emitter *yaml_emitter_t) bool { + if emitter.write_handler == nil { + panic("write handler not set") + } + + // Check if the buffer is empty. + if emitter.buffer_pos == 0 { + return true + } + + // If the output encoding is UTF-8, we don't need to recode the buffer. + if emitter.encoding == yaml_UTF8_ENCODING { + if err := emitter.write_handler(emitter, emitter.buffer[:emitter.buffer_pos]); err != nil { + return yaml_emitter_set_writer_error(emitter, "write error: "+err.Error()) + } + emitter.buffer_pos = 0 + return true + } + + // Recode the buffer into the raw buffer. + var low, high int + if emitter.encoding == yaml_UTF16LE_ENCODING { + low, high = 0, 1 + } else { + high, low = 1, 0 + } + + pos := 0 + for pos < emitter.buffer_pos { + // See the "reader.c" code for more details on UTF-8 encoding. Note + // that we assume that the buffer contains a valid UTF-8 sequence. + + // Read the next UTF-8 character. + octet := emitter.buffer[pos] + + var w int + var value rune + switch { + case octet&0x80 == 0x00: + w, value = 1, rune(octet&0x7F) + case octet&0xE0 == 0xC0: + w, value = 2, rune(octet&0x1F) + case octet&0xF0 == 0xE0: + w, value = 3, rune(octet&0x0F) + case octet&0xF8 == 0xF0: + w, value = 4, rune(octet&0x07) + } + for k := 1; k < w; k++ { + octet = emitter.buffer[pos+k] + value = (value << 6) + (rune(octet) & 0x3F) + } + pos += w + + // Write the character. + if value < 0x10000 { + var b [2]byte + b[high] = byte(value >> 8) + b[low] = byte(value & 0xFF) + emitter.raw_buffer = append(emitter.raw_buffer, b[0], b[1]) + } else { + // Write the character using a surrogate pair (check "reader.c"). + var b [4]byte + value -= 0x10000 + b[high] = byte(0xD8 + (value >> 18)) + b[low] = byte((value >> 10) & 0xFF) + b[high+2] = byte(0xDC + ((value >> 8) & 0xFF)) + b[low+2] = byte(value & 0xFF) + emitter.raw_buffer = append(emitter.raw_buffer, b[0], b[1], b[2], b[3]) + } + } + + // Write the raw buffer. + if err := emitter.write_handler(emitter, emitter.raw_buffer); err != nil { + return yaml_emitter_set_writer_error(emitter, "write error: "+err.Error()) + } + emitter.buffer_pos = 0 + emitter.raw_buffer = emitter.raw_buffer[:0] + return true +}
diff --git a/yaml.h b/yaml.h deleted file mode 100644 index 400cae1..0000000 --- a/yaml.h +++ /dev/null
@@ -1,1971 +0,0 @@ -/** - * @file yaml.h - * @brief Public interface for libyaml. - * - * Include the header file with the code: - * @code - * #include <yaml.h> - * @endcode - */ - -#ifndef YAML_H -#define YAML_H - -#ifdef __cplusplus -extern "C" { -#endif - -#include <stdlib.h> -#include <stdio.h> -#include <string.h> - -/** - * @defgroup export Export Definitions - * @{ - */ - -/** The public API declaration. */ - -#ifdef WIN32 -# if defined(YAML_DECLARE_STATIC) -# define YAML_DECLARE(type) type -# elif defined(YAML_DECLARE_EXPORT) -# define YAML_DECLARE(type) __declspec(dllexport) type -# else -# define YAML_DECLARE(type) __declspec(dllimport) type -# endif -#else -# define YAML_DECLARE(type) type -#endif - -/** @} */ - -/** - * @defgroup version Version Information - * @{ - */ - -/** - * Get the library version as a string. - * - * @returns The function returns the pointer to a static string of the form - * @c "X.Y.Z", where @c X is the major version number, @c Y is a minor version - * number, and @c Z is the patch version number. - */ - -YAML_DECLARE(const char *) -yaml_get_version_string(void); - -/** - * Get the library version numbers. - * - * @param[out] major Major version number. - * @param[out] minor Minor version number. - * @param[out] patch Patch version number. - */ - -YAML_DECLARE(void) -yaml_get_version(int *major, int *minor, int *patch); - -/** @} */ - -/** - * @defgroup basic Basic Types - * @{ - */ - -/** The character type (UTF-8 octet). */ -typedef unsigned char yaml_char_t; - -/** The version directive data. */ -typedef struct yaml_version_directive_s { - /** The major version number. */ - int major; - /** The minor version number. */ - int minor; -} yaml_version_directive_t; - -/** The tag directive data. */ -typedef struct yaml_tag_directive_s { - /** The tag handle. */ - yaml_char_t *handle; - /** The tag prefix. */ - yaml_char_t *prefix; -} yaml_tag_directive_t; - -/** The stream encoding. */ -typedef enum yaml_encoding_e { - /** Let the parser choose the encoding. */ - YAML_ANY_ENCODING, - /** The default UTF-8 encoding. */ - YAML_UTF8_ENCODING, - /** The UTF-16-LE encoding with BOM. */ - YAML_UTF16LE_ENCODING, - /** The UTF-16-BE encoding with BOM. */ - YAML_UTF16BE_ENCODING -} yaml_encoding_t; - -/** Line break types. */ - -typedef enum yaml_break_e { - /** Let the parser choose the break type. */ - YAML_ANY_BREAK, - /** Use CR for line breaks (Mac style). */ - YAML_CR_BREAK, - /** Use LN for line breaks (Unix style). */ - YAML_LN_BREAK, - /** Use CR LN for line breaks (DOS style). */ - YAML_CRLN_BREAK -} yaml_break_t; - -/** Many bad things could happen with the parser and emitter. */ -typedef enum yaml_error_type_e { - /** No error is produced. */ - YAML_NO_ERROR, - - /** Cannot allocate or reallocate a block of memory. */ - YAML_MEMORY_ERROR, - - /** Cannot read or decode the input stream. */ - YAML_READER_ERROR, - /** Cannot scan the input stream. */ - YAML_SCANNER_ERROR, - /** Cannot parse the input stream. */ - YAML_PARSER_ERROR, - /** Cannot compose a YAML document. */ - YAML_COMPOSER_ERROR, - - /** Cannot write to the output stream. */ - YAML_WRITER_ERROR, - /** Cannot emit a YAML stream. */ - YAML_EMITTER_ERROR -} yaml_error_type_t; - -/** The pointer position. */ -typedef struct yaml_mark_s { - /** The position index. */ - size_t index; - - /** The position line. */ - size_t line; - - /** The position column. */ - size_t column; -} yaml_mark_t; - -/** @} */ - -/** - * @defgroup styles Node Styles - * @{ - */ - -/** Scalar styles. */ -typedef enum yaml_scalar_style_e { - /** Let the emitter choose the style. */ - YAML_ANY_SCALAR_STYLE, - - /** The plain scalar style. */ - YAML_PLAIN_SCALAR_STYLE, - - /** The single-quoted scalar style. */ - YAML_SINGLE_QUOTED_SCALAR_STYLE, - /** The double-quoted scalar style. */ - YAML_DOUBLE_QUOTED_SCALAR_STYLE, - - /** The literal scalar style. */ - YAML_LITERAL_SCALAR_STYLE, - /** The folded scalar style. */ - YAML_FOLDED_SCALAR_STYLE -} yaml_scalar_style_t; - -/** Sequence styles. */ -typedef enum yaml_sequence_style_e { - /** Let the emitter choose the style. */ - YAML_ANY_SEQUENCE_STYLE, - - /** The block sequence style. */ - YAML_BLOCK_SEQUENCE_STYLE, - /** The flow sequence style. */ - YAML_FLOW_SEQUENCE_STYLE -} yaml_sequence_style_t; - -/** Mapping styles. */ -typedef enum yaml_mapping_style_e { - /** Let the emitter choose the style. */ - YAML_ANY_MAPPING_STYLE, - - /** The block mapping style. */ - YAML_BLOCK_MAPPING_STYLE, - /** The flow mapping style. */ - YAML_FLOW_MAPPING_STYLE -/* YAML_FLOW_SET_MAPPING_STYLE */ -} yaml_mapping_style_t; - -/** @} */ - -/** - * @defgroup tokens Tokens - * @{ - */ - -/** Token types. */ -typedef enum yaml_token_type_e { - /** An empty token. */ - YAML_NO_TOKEN, - - /** A STREAM-START token. */ - YAML_STREAM_START_TOKEN, - /** A STREAM-END token. */ - YAML_STREAM_END_TOKEN, - - /** A VERSION-DIRECTIVE token. */ - YAML_VERSION_DIRECTIVE_TOKEN, - /** A TAG-DIRECTIVE token. */ - YAML_TAG_DIRECTIVE_TOKEN, - /** A DOCUMENT-START token. */ - YAML_DOCUMENT_START_TOKEN, - /** A DOCUMENT-END token. */ - YAML_DOCUMENT_END_TOKEN, - - /** A BLOCK-SEQUENCE-START token. */ - YAML_BLOCK_SEQUENCE_START_TOKEN, - /** A BLOCK-SEQUENCE-END token. */ - YAML_BLOCK_MAPPING_START_TOKEN, - /** A BLOCK-END token. */ - YAML_BLOCK_END_TOKEN, - - /** A FLOW-SEQUENCE-START token. */ - YAML_FLOW_SEQUENCE_START_TOKEN, - /** A FLOW-SEQUENCE-END token. */ - YAML_FLOW_SEQUENCE_END_TOKEN, - /** A FLOW-MAPPING-START token. */ - YAML_FLOW_MAPPING_START_TOKEN, - /** A FLOW-MAPPING-END token. */ - YAML_FLOW_MAPPING_END_TOKEN, - - /** A BLOCK-ENTRY token. */ - YAML_BLOCK_ENTRY_TOKEN, - /** A FLOW-ENTRY token. */ - YAML_FLOW_ENTRY_TOKEN, - /** A KEY token. */ - YAML_KEY_TOKEN, - /** A VALUE token. */ - YAML_VALUE_TOKEN, - - /** An ALIAS token. */ - YAML_ALIAS_TOKEN, - /** An ANCHOR token. */ - YAML_ANCHOR_TOKEN, - /** A TAG token. */ - YAML_TAG_TOKEN, - /** A SCALAR token. */ - YAML_SCALAR_TOKEN -} yaml_token_type_t; - -/** The token structure. */ -typedef struct yaml_token_s { - - /** The token type. */ - yaml_token_type_t type; - - /** The token data. */ - union { - - /** The stream start (for @c YAML_STREAM_START_TOKEN). */ - struct { - /** The stream encoding. */ - yaml_encoding_t encoding; - } stream_start; - - /** The alias (for @c YAML_ALIAS_TOKEN). */ - struct { - /** The alias value. */ - yaml_char_t *value; - } alias; - - /** The anchor (for @c YAML_ANCHOR_TOKEN). */ - struct { - /** The anchor value. */ - yaml_char_t *value; - } anchor; - - /** The tag (for @c YAML_TAG_TOKEN). */ - struct { - /** The tag handle. */ - yaml_char_t *handle; - /** The tag suffix. */ - yaml_char_t *suffix; - } tag; - - /** The scalar value (for @c YAML_SCALAR_TOKEN). */ - struct { - /** The scalar value. */ - yaml_char_t *value; - /** The length of the scalar value. */ - size_t length; - /** The scalar style. */ - yaml_scalar_style_t style; - } scalar; - - /** The version directive (for @c YAML_VERSION_DIRECTIVE_TOKEN). */ - struct { - /** The major version number. */ - int major; - /** The minor version number. */ - int minor; - } version_directive; - - /** The tag directive (for @c YAML_TAG_DIRECTIVE_TOKEN). */ - struct { - /** The tag handle. */ - yaml_char_t *handle; - /** The tag prefix. */ - yaml_char_t *prefix; - } tag_directive; - - } data; - - /** The beginning of the token. */ - yaml_mark_t start_mark; - /** The end of the token. */ - yaml_mark_t end_mark; - -} yaml_token_t; - -/** - * Free any memory allocated for a token object. - * - * @param[in,out] token A token object. - */ - -YAML_DECLARE(void) -yaml_token_delete(yaml_token_t *token); - -/** @} */ - -/** - * @defgroup events Events - * @{ - */ - -/** Event types. */ -typedef enum yaml_event_type_e { - /** An empty event. */ - YAML_NO_EVENT, - - /** A STREAM-START event. */ - YAML_STREAM_START_EVENT, - /** A STREAM-END event. */ - YAML_STREAM_END_EVENT, - - /** A DOCUMENT-START event. */ - YAML_DOCUMENT_START_EVENT, - /** A DOCUMENT-END event. */ - YAML_DOCUMENT_END_EVENT, - - /** An ALIAS event. */ - YAML_ALIAS_EVENT, - /** A SCALAR event. */ - YAML_SCALAR_EVENT, - - /** A SEQUENCE-START event. */ - YAML_SEQUENCE_START_EVENT, - /** A SEQUENCE-END event. */ - YAML_SEQUENCE_END_EVENT, - - /** A MAPPING-START event. */ - YAML_MAPPING_START_EVENT, - /** A MAPPING-END event. */ - YAML_MAPPING_END_EVENT -} yaml_event_type_t; - -/** The event structure. */ -typedef struct yaml_event_s { - - /** The event type. */ - yaml_event_type_t type; - - /** The event data. */ - union { - - /** The stream parameters (for @c YAML_STREAM_START_EVENT). */ - struct { - /** The document encoding. */ - yaml_encoding_t encoding; - } stream_start; - - /** The document parameters (for @c YAML_DOCUMENT_START_EVENT). */ - struct { - /** The version directive. */ - yaml_version_directive_t *version_directive; - - /** The list of tag directives. */ - struct { - /** The beginning of the tag directives list. */ - yaml_tag_directive_t *start; - /** The end of the tag directives list. */ - yaml_tag_directive_t *end; - } tag_directives; - - /** Is the document indicator implicit? */ - int implicit; - } document_start; - - /** The document end parameters (for @c YAML_DOCUMENT_END_EVENT). */ - struct { - /** Is the document end indicator implicit? */ - int implicit; - } document_end; - - /** The alias parameters (for @c YAML_ALIAS_EVENT). */ - struct { - /** The anchor. */ - yaml_char_t *anchor; - } alias; - - /** The scalar parameters (for @c YAML_SCALAR_EVENT). */ - struct { - /** The anchor. */ - yaml_char_t *anchor; - /** The tag. */ - yaml_char_t *tag; - /** The scalar value. */ - yaml_char_t *value; - /** The length of the scalar value. */ - size_t length; - /** Is the tag optional for the plain style? */ - int plain_implicit; - /** Is the tag optional for any non-plain style? */ - int quoted_implicit; - /** The scalar style. */ - yaml_scalar_style_t style; - } scalar; - - /** The sequence parameters (for @c YAML_SEQUENCE_START_EVENT). */ - struct { - /** The anchor. */ - yaml_char_t *anchor; - /** The tag. */ - yaml_char_t *tag; - /** Is the tag optional? */ - int implicit; - /** The sequence style. */ - yaml_sequence_style_t style; - } sequence_start; - - /** The mapping parameters (for @c YAML_MAPPING_START_EVENT). */ - struct { - /** The anchor. */ - yaml_char_t *anchor; - /** The tag. */ - yaml_char_t *tag; - /** Is the tag optional? */ - int implicit; - /** The mapping style. */ - yaml_mapping_style_t style; - } mapping_start; - - } data; - - /** The beginning of the event. */ - yaml_mark_t start_mark; - /** The end of the event. */ - yaml_mark_t end_mark; - -} yaml_event_t; - -/** - * Create the STREAM-START event. - * - * @param[out] event An empty event object. - * @param[in] encoding The stream encoding. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_stream_start_event_initialize(yaml_event_t *event, - yaml_encoding_t encoding); - -/** - * Create the STREAM-END event. - * - * @param[out] event An empty event object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_stream_end_event_initialize(yaml_event_t *event); - -/** - * Create the DOCUMENT-START event. - * - * The @a implicit argument is considered as a stylistic parameter and may be - * ignored by the emitter. - * - * @param[out] event An empty event 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] implicit If the document start indicator is - * implicit. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_document_start_event_initialize(yaml_event_t *event, - yaml_version_directive_t *version_directive, - yaml_tag_directive_t *tag_directives_start, - yaml_tag_directive_t *tag_directives_end, - int implicit); - -/** - * Create the DOCUMENT-END event. - * - * The @a implicit argument is considered as a stylistic parameter and may be - * ignored by the emitter. - * - * @param[out] event An empty event object. - * @param[in] implicit If the document end indicator is implicit. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_document_end_event_initialize(yaml_event_t *event, int implicit); - -/** - * Create an ALIAS event. - * - * @param[out] event An empty event object. - * @param[in] anchor The anchor value. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_alias_event_initialize(yaml_event_t *event, yaml_char_t *anchor); - -/** - * Create a SCALAR event. - * - * The @a style argument may be ignored by the emitter. - * - * Either the @a tag attribute or one of the @a plain_implicit and - * @a quoted_implicit flags must be set. - * - * @param[out] event An empty event object. - * @param[in] anchor The scalar anchor or @c NULL. - * @param[in] tag The scalar tag or @c NULL. - * @param[in] value The scalar value. - * @param[in] length The length of the scalar value. - * @param[in] plain_implicit If the tag may be omitted for the plain - * style. - * @param[in] quoted_implicit If the tag may be omitted for any - * non-plain style. - * @param[in] style The scalar style. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_scalar_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, - yaml_char_t *value, int length, - int plain_implicit, int quoted_implicit, - yaml_scalar_style_t style); - -/** - * Create a SEQUENCE-START event. - * - * The @a style argument may be ignored by the emitter. - * - * Either the @a tag attribute or the @a implicit flag must be set. - * - * @param[out] event An empty event object. - * @param[in] anchor The sequence anchor or @c NULL. - * @param[in] tag The sequence tag or @c NULL. - * @param[in] implicit If the tag may be omitted. - * @param[in] style The sequence style. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_sequence_start_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, int implicit, - yaml_sequence_style_t style); - -/** - * Create a SEQUENCE-END event. - * - * @param[out] event An empty event object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_sequence_end_event_initialize(yaml_event_t *event); - -/** - * Create a MAPPING-START event. - * - * The @a style argument may be ignored by the emitter. - * - * Either the @a tag attribute or the @a implicit flag must be set. - * - * @param[out] event An empty event object. - * @param[in] anchor The mapping anchor or @c NULL. - * @param[in] tag The mapping tag or @c NULL. - * @param[in] implicit If the tag may be omitted. - * @param[in] style The mapping style. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_mapping_start_event_initialize(yaml_event_t *event, - yaml_char_t *anchor, yaml_char_t *tag, int implicit, - yaml_mapping_style_t style); - -/** - * Create a MAPPING-END event. - * - * @param[out] event An empty event object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_mapping_end_event_initialize(yaml_event_t *event); - -/** - * Free any memory allocated for an event object. - * - * @param[in,out] event An event object. - */ - -YAML_DECLARE(void) -yaml_event_delete(yaml_event_t *event); - -/** @} */ - -/** - * @defgroup nodes Nodes - * @{ - */ - -/** The tag @c !!null with the only possible value: @c null. */ -#define YAML_NULL_TAG "tag:yaml.org,2002:null" -/** The tag @c !!bool with the values: @c true and @c falce. */ -#define YAML_BOOL_TAG "tag:yaml.org,2002:bool" -/** The tag @c !!str for string values. */ -#define YAML_STR_TAG "tag:yaml.org,2002:str" -/** The tag @c !!int for integer values. */ -#define YAML_INT_TAG "tag:yaml.org,2002:int" -/** The tag @c !!float for float values. */ -#define YAML_FLOAT_TAG "tag:yaml.org,2002:float" -/** The tag @c !!timestamp for date and time values. */ -#define YAML_TIMESTAMP_TAG "tag:yaml.org,2002:timestamp" - -/** The tag @c !!seq is used to denote sequences. */ -#define YAML_SEQ_TAG "tag:yaml.org,2002:seq" -/** The tag @c !!map is used to denote mapping. */ -#define YAML_MAP_TAG "tag:yaml.org,2002:map" - -/** The default scalar tag is @c !!str. */ -#define YAML_DEFAULT_SCALAR_TAG YAML_STR_TAG -/** The default sequence tag is @c !!seq. */ -#define YAML_DEFAULT_SEQUENCE_TAG YAML_SEQ_TAG -/** The default mapping tag is @c !!map. */ -#define YAML_DEFAULT_MAPPING_TAG YAML_MAP_TAG - -/** Node types. */ -typedef enum yaml_node_type_e { - /** An empty node. */ - YAML_NO_NODE, - - /** A scalar node. */ - YAML_SCALAR_NODE, - /** A sequence node. */ - YAML_SEQUENCE_NODE, - /** A mapping node. */ - YAML_MAPPING_NODE -} yaml_node_type_t; - -/** The forward definition of a document node structure. */ -typedef struct yaml_node_s yaml_node_t; - -/** An element of a sequence node. */ -typedef int yaml_node_item_t; - -/** An element of a mapping node. */ -typedef struct yaml_node_pair_s { - /** The key of the element. */ - int key; - /** The value of the element. */ - int value; -} yaml_node_pair_t; - -/** The node structure. */ -struct yaml_node_s { - - /** The node type. */ - yaml_node_type_t type; - - /** The node tag. */ - yaml_char_t *tag; - - /** The node data. */ - union { - - /** The scalar parameters (for @c YAML_SCALAR_NODE). */ - struct { - /** The scalar value. */ - yaml_char_t *value; - /** The length of the scalar value. */ - size_t length; - /** The scalar style. */ - yaml_scalar_style_t style; - } scalar; - - /** The sequence parameters (for @c YAML_SEQUENCE_NODE). */ - struct { - /** The stack of sequence items. */ - struct { - /** The beginning of the stack. */ - yaml_node_item_t *start; - /** The end of the stack. */ - yaml_node_item_t *end; - /** The top of the stack. */ - yaml_node_item_t *top; - } items; - /** The sequence style. */ - yaml_sequence_style_t style; - } sequence; - - /** The mapping parameters (for @c YAML_MAPPING_NODE). */ - struct { - /** The stack of mapping pairs (key, value). */ - struct { - /** The beginning of the stack. */ - yaml_node_pair_t *start; - /** The end of the stack. */ - yaml_node_pair_t *end; - /** The top of the stack. */ - yaml_node_pair_t *top; - } pairs; - /** The mapping style. */ - yaml_mapping_style_t style; - } mapping; - - } data; - - /** The beginning of the node. */ - yaml_mark_t start_mark; - /** The end of the node. */ - yaml_mark_t end_mark; - -}; - -/** The document structure. */ -typedef struct yaml_document_s { - - /** The document nodes. */ - struct { - /** The beginning of the stack. */ - yaml_node_t *start; - /** The end of the stack. */ - yaml_node_t *end; - /** The top of the stack. */ - yaml_node_t *top; - } nodes; - - /** The version directive. */ - yaml_version_directive_t *version_directive; - - /** The list of tag directives. */ - struct { - /** The beginning of the tag directives list. */ - yaml_tag_directive_t *start; - /** The end of the tag directives list. */ - yaml_tag_directive_t *end; - } tag_directives; - - /** Is the document start indicator implicit? */ - int start_implicit; - /** Is the document end indicator implicit? */ - int end_implicit; - - /** The beginning of the document. */ - yaml_mark_t start_mark; - /** The end of the document. */ - yaml_mark_t end_mark; - -} yaml_document_t; - -/** - * 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); - -/** @} */ - -/** - * @defgroup parser Parser Definitions - * @{ - */ - -/** - * The prototype of a read handler. - * - * The read handler is called when the parser needs to read more bytes from the - * source. The handler should write not more than @a size bytes to the @a - * buffer. The number of written bytes should be set to the @a length variable. - * - * @param[in,out] data A pointer to an application data specified by - * yaml_parser_set_input(). - * @param[out] buffer The buffer to write the data from the source. - * @param[in] size The size of the buffer. - * @param[out] size_read The actual number of bytes read from the source. - * - * @returns On success, the handler should return @c 1. If the handler failed, - * the returned value should be @c 0. On EOF, the handler should set the - * @a size_read to @c 0 and return @c 1. - */ - -typedef int yaml_read_handler_t(void *data, unsigned char *buffer, size_t size, - size_t *size_read); - -/** - * This structure holds information about a potential simple key. - */ - -typedef struct yaml_simple_key_s { - /** Is a simple key possible? */ - int possible; - - /** Is a simple key required? */ - int required; - - /** The number of the token. */ - size_t token_number; - - /** The position mark. */ - yaml_mark_t mark; -} yaml_simple_key_t; - -/** - * The states of the parser. - */ -typedef enum yaml_parser_state_e { - /** Expect STREAM-START. */ - YAML_PARSE_STREAM_START_STATE, - /** Expect the beginning of an implicit document. */ - YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE, - /** Expect DOCUMENT-START. */ - YAML_PARSE_DOCUMENT_START_STATE, - /** Expect the content of a document. */ - YAML_PARSE_DOCUMENT_CONTENT_STATE, - /** Expect DOCUMENT-END. */ - YAML_PARSE_DOCUMENT_END_STATE, - /** Expect a block node. */ - YAML_PARSE_BLOCK_NODE_STATE, - /** Expect a block node or indentless sequence. */ - YAML_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE, - /** Expect a flow node. */ - YAML_PARSE_FLOW_NODE_STATE, - /** Expect the first entry of a block sequence. */ - YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE, - /** Expect an entry of a block sequence. */ - YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE, - /** Expect an entry of an indentless sequence. */ - YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE, - /** Expect the first key of a block mapping. */ - YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE, - /** Expect a block mapping key. */ - YAML_PARSE_BLOCK_MAPPING_KEY_STATE, - /** Expect a block mapping value. */ - YAML_PARSE_BLOCK_MAPPING_VALUE_STATE, - /** Expect the first entry of a flow sequence. */ - YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE, - /** Expect an entry of a flow sequence. */ - YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE, - /** Expect a key of an ordered mapping. */ - YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE, - /** Expect a value of an ordered mapping. */ - YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE, - /** Expect the and of an ordered mapping entry. */ - YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE, - /** Expect the first key of a flow mapping. */ - YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE, - /** Expect a key of a flow mapping. */ - YAML_PARSE_FLOW_MAPPING_KEY_STATE, - /** Expect a value of a flow mapping. */ - YAML_PARSE_FLOW_MAPPING_VALUE_STATE, - /** Expect an empty value of a flow mapping. */ - YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE, - /** Expect nothing. */ - YAML_PARSE_END_STATE -} yaml_parser_state_t; - -/** - * This structure holds aliases data. - */ - -typedef struct yaml_alias_data_s { - /** The anchor. */ - yaml_char_t *anchor; - /** The node id. */ - int index; - /** The anchor mark. */ - yaml_mark_t mark; -} yaml_alias_data_t; - -/** - * The parser structure. - * - * All members are internal. Manage the structure using the @c yaml_parser_ - * family of functions. - */ - -typedef struct yaml_parser_s { - - /** - * @name Error handling - * @{ - */ - - /** Error type. */ - yaml_error_type_t error; - /** Error description. */ - const char *problem; - /** The byte about which the problem occured. */ - size_t problem_offset; - /** The problematic value (@c -1 is none). */ - int problem_value; - /** The problem position. */ - yaml_mark_t problem_mark; - /** The error context. */ - const char *context; - /** The context position. */ - yaml_mark_t context_mark; - - /** - * @} - */ - - /** - * @name Reader stuff - * @{ - */ - - /** Read handler. */ - yaml_read_handler_t *read_handler; - - /** A pointer for passing to the read handler. */ - void *read_handler_data; - - /** Standard (string or file) input data. */ - union { - /** String input data. */ - struct { - /** The string start pointer. */ - const unsigned char *start; - /** The string end pointer. */ - const unsigned char *end; - /** The string current position. */ - const unsigned char *current; - } string; - - /** File input data. */ - FILE *file; - } input; - - /** EOF flag */ - int eof; - - /** The working buffer. */ - struct { - /** The beginning of the buffer. */ - yaml_char_t *start; - /** The end of the buffer. */ - yaml_char_t *end; - /** The current position of the buffer. */ - yaml_char_t *pointer; - /** The last filled position of the buffer. */ - yaml_char_t *last; - } buffer; - - /* The number of unread characters in the buffer. */ - size_t unread; - - /** The raw buffer. */ - struct { - /** The beginning of the buffer. */ - unsigned char *start; - /** The end of the buffer. */ - unsigned char *end; - /** The current position of the buffer. */ - unsigned char *pointer; - /** The last filled position of the buffer. */ - unsigned char *last; - } raw_buffer; - - /** The input encoding. */ - yaml_encoding_t encoding; - - /** The offset of the current position (in bytes). */ - size_t offset; - - /** The mark of the current position. */ - yaml_mark_t mark; - - /** - * @} - */ - - /** - * @name Scanner stuff - * @{ - */ - - /** Have we started to scan the input stream? */ - int stream_start_produced; - - /** Have we reached the end of the input stream? */ - int stream_end_produced; - - /** The number of unclosed '[' and '{' indicators. */ - int flow_level; - - /** The tokens queue. */ - struct { - /** The beginning of the tokens queue. */ - yaml_token_t *start; - /** The end of the tokens queue. */ - yaml_token_t *end; - /** The head of the tokens queue. */ - yaml_token_t *head; - /** The tail of the tokens queue. */ - yaml_token_t *tail; - } tokens; - - /** The number of tokens fetched from the queue. */ - size_t tokens_parsed; - - /* Does the tokens queue contain a token ready for dequeueing. */ - int token_available; - - /** The indentation levels stack. */ - struct { - /** The beginning of the stack. */ - int *start; - /** The end of the stack. */ - int *end; - /** The top of the stack. */ - int *top; - } indents; - - /** The current indentation level. */ - int indent; - - /** May a simple key occur at the current position? */ - int simple_key_allowed; - - /** The stack of simple keys. */ - struct { - /** The beginning of the stack. */ - yaml_simple_key_t *start; - /** The end of the stack. */ - yaml_simple_key_t *end; - /** The top of the stack. */ - yaml_simple_key_t *top; - } simple_keys; - - /** - * @} - */ - - /** - * @name Parser stuff - * @{ - */ - - /** The parser states stack. */ - struct { - /** The beginning of the stack. */ - yaml_parser_state_t *start; - /** The end of the stack. */ - yaml_parser_state_t *end; - /** The top of the stack. */ - yaml_parser_state_t *top; - } states; - - /** The current parser state. */ - yaml_parser_state_t state; - - /** The stack of marks. */ - struct { - /** The beginning of the stack. */ - yaml_mark_t *start; - /** The end of the stack. */ - yaml_mark_t *end; - /** The top of the stack. */ - yaml_mark_t *top; - } marks; - - /** The list of TAG directives. */ - struct { - /** The beginning of the list. */ - yaml_tag_directive_t *start; - /** The end of the list. */ - yaml_tag_directive_t *end; - /** The top of the list. */ - yaml_tag_directive_t *top; - } tag_directives; - - /** - * @} - */ - - /** - * @name Dumper stuff - * @{ - */ - - /** The alias data. */ - struct { - /** The beginning of the list. */ - yaml_alias_data_t *start; - /** The end of the list. */ - yaml_alias_data_t *end; - /** The top of the list. */ - yaml_alias_data_t *top; - } aliases; - - /** The currently parsed document. */ - yaml_document_t *document; - - /** - * @} - */ - -} yaml_parser_t; - -/** - * 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, - const unsigned char *input, size_t 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 - * @c YAML_STREAM_START_TOKEN while the ending token has the type - * @c 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 - * @c YAML_STREAM_START_EVENT while the ending event has the type - * @c 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 - * @{ - */ - -/** - * The prototype of a write handler. - * - * The write handler is called when the emitter needs to flush the accumulated - * characters to the output. The handler should write @a size bytes of the - * @a buffer to the output. - * - * @param[in,out] data A pointer to an application data specified by - * yaml_emitter_set_output(). - * @param[in] buffer The buffer with bytes to be written. - * @param[in] size The size of the buffer. - * - * @returns On success, the handler should return @c 1. If the handler failed, - * the returned value should be @c 0. - */ - -typedef int yaml_write_handler_t(void *data, unsigned char *buffer, size_t size); - -/** The emitter states. */ -typedef enum yaml_emitter_state_e { - /** Expect STREAM-START. */ - YAML_EMIT_STREAM_START_STATE, - /** Expect the first DOCUMENT-START or STREAM-END. */ - YAML_EMIT_FIRST_DOCUMENT_START_STATE, - /** Expect DOCUMENT-START or STREAM-END. */ - YAML_EMIT_DOCUMENT_START_STATE, - /** Expect the content of a document. */ - YAML_EMIT_DOCUMENT_CONTENT_STATE, - /** Expect DOCUMENT-END. */ - YAML_EMIT_DOCUMENT_END_STATE, - /** Expect the first item of a flow sequence. */ - YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE, - /** Expect an item of a flow sequence. */ - YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE, - /** Expect the first key of a flow mapping. */ - YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE, - /** Expect a key of a flow mapping. */ - YAML_EMIT_FLOW_MAPPING_KEY_STATE, - /** Expect a value for a simple key of a flow mapping. */ - YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE, - /** Expect a value of a flow mapping. */ - YAML_EMIT_FLOW_MAPPING_VALUE_STATE, - /** Expect the first item of a block sequence. */ - YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE, - /** Expect an item of a block sequence. */ - YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE, - /** Expect the first key of a block mapping. */ - YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE, - /** Expect the key of a block mapping. */ - YAML_EMIT_BLOCK_MAPPING_KEY_STATE, - /** Expect a value for a simple key of a block mapping. */ - YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE, - /** Expect a value of a block mapping. */ - YAML_EMIT_BLOCK_MAPPING_VALUE_STATE, - /** Expect nothing. */ - YAML_EMIT_END_STATE -} yaml_emitter_state_t; - -/** - * The emitter structure. - * - * All members are internal. Manage the structure using the @c yaml_emitter_ - * family of functions. - */ - -typedef struct yaml_emitter_s { - - /** - * @name Error handling - * @{ - */ - - /** Error type. */ - yaml_error_type_t error; - /** Error description. */ - const char *problem; - - /** - * @} - */ - - /** - * @name Writer stuff - * @{ - */ - - /** Write handler. */ - yaml_write_handler_t *write_handler; - - /** A pointer for passing to the white handler. */ - void *write_handler_data; - - /** Standard (string or file) output data. */ - union { - /** String output data. */ - struct { - /** The buffer pointer. */ - unsigned char *buffer; - /** The buffer size. */ - size_t size; - /** The number of written bytes. */ - size_t *size_written; - } string; - - /** File output data. */ - FILE *file; - } output; - - /** The working buffer. */ - struct { - /** The beginning of the buffer. */ - yaml_char_t *start; - /** The end of the buffer. */ - yaml_char_t *end; - /** The current position of the buffer. */ - yaml_char_t *pointer; - /** The last filled position of the buffer. */ - yaml_char_t *last; - } buffer; - - /** The raw buffer. */ - struct { - /** The beginning of the buffer. */ - unsigned char *start; - /** The end of the buffer. */ - unsigned char *end; - /** The current position of the buffer. */ - unsigned char *pointer; - /** The last filled position of the buffer. */ - unsigned char *last; - } raw_buffer; - - /** The stream encoding. */ - yaml_encoding_t encoding; - - /** - * @} - */ - - /** - * @name Emitter stuff - * @{ - */ - - /** If the output is in the canonical style? */ - int canonical; - /** The number of indentation spaces. */ - int best_indent; - /** The preferred width of the output lines. */ - int best_width; - /** Allow unescaped non-ASCII characters? */ - int unicode; - /** The preferred line break. */ - yaml_break_t line_break; - - /** The stack of states. */ - struct { - /** The beginning of the stack. */ - yaml_emitter_state_t *start; - /** The end of the stack. */ - yaml_emitter_state_t *end; - /** The top of the stack. */ - yaml_emitter_state_t *top; - } states; - - /** The current emitter state. */ - yaml_emitter_state_t state; - - /** The event queue. */ - struct { - /** The beginning of the event queue. */ - yaml_event_t *start; - /** The end of the event queue. */ - yaml_event_t *end; - /** The head of the event queue. */ - yaml_event_t *head; - /** The tail of the event queue. */ - yaml_event_t *tail; - } events; - - /** The stack of indentation levels. */ - struct { - /** The beginning of the stack. */ - int *start; - /** The end of the stack. */ - int *end; - /** The top of the stack. */ - int *top; - } indents; - - /** The list of tag directives. */ - struct { - /** The beginning of the list. */ - yaml_tag_directive_t *start; - /** The end of the list. */ - yaml_tag_directive_t *end; - /** The top of the list. */ - yaml_tag_directive_t *top; - } tag_directives; - - /** The current indentation level. */ - int indent; - - /** The current flow level. */ - int flow_level; - - /** Is it the document root context? */ - int root_context; - /** Is it a sequence context? */ - int sequence_context; - /** Is it a mapping context? */ - int mapping_context; - /** Is it a simple mapping key context? */ - int simple_key_context; - - /** The current line. */ - int line; - /** The current column. */ - int column; - /** If the last character was a whitespace? */ - int whitespace; - /** If the last character was an indentation character (' ', '-', '?', ':')? */ - int indention; - /** If an explicit document end is required? */ - int open_ended; - - /** Anchor analysis. */ - struct { - /** The anchor value. */ - yaml_char_t *anchor; - /** The anchor length. */ - size_t anchor_length; - /** Is it an alias? */ - int alias; - } anchor_data; - - /** Tag analysis. */ - struct { - /** The tag handle. */ - yaml_char_t *handle; - /** The tag handle length. */ - size_t handle_length; - /** The tag suffix. */ - yaml_char_t *suffix; - /** The tag suffix length. */ - size_t suffix_length; - } tag_data; - - /** Scalar analysis. */ - struct { - /** The scalar value. */ - yaml_char_t *value; - /** The scalar length. */ - size_t length; - /** Does the scalar contain line breaks? */ - int multiline; - /** Can the scalar be expessed in the flow plain style? */ - int flow_plain_allowed; - /** Can the scalar be expressed in the block plain style? */ - int block_plain_allowed; - /** Can the scalar be expressed in the single quoted style? */ - int single_quoted_allowed; - /** Can the scalar be expressed in the literal or folded styles? */ - int block_allowed; - /** The output style. */ - yaml_scalar_style_t style; - } scalar_data; - - /** - * @} - */ - - /** - * @name Dumper stuff - * @{ - */ - - /** If the stream was already opened? */ - int opened; - /** If the stream was already closed? */ - int closed; - - /** The information associated with the document nodes. */ - struct { - /** The number of references. */ - int references; - /** The anchor id. */ - int anchor; - /** If the node has been emitted? */ - int serialized; - } *anchors; - - /** The last assigned anchor id. */ - int last_anchor_id; - - /** The currently emitted document. */ - yaml_document_t *document; - - /** - * @} - */ - -} yaml_emitter_t; - -/** - * Initialize an emitter. - * - * This function creates a new emitter object. An application is responsible - * for destroying the object using the yaml_emitter_delete() function. - * - * @param[out] emitter An empty parser object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_initialize(yaml_emitter_t *emitter); - -/** - * Destroy an emitter. - * - * @param[in,out] emitter An emitter object. - */ - -YAML_DECLARE(void) -yaml_emitter_delete(yaml_emitter_t *emitter); - -/** - * Set a string output. - * - * The emitter will write the output characters to the @a output buffer of the - * size @a size. The emitter will set @a size_written to the number of written - * bytes. If the buffer is smaller than required, the emitter produces the - * YAML_WRITE_ERROR error. - * - * @param[in,out] emitter An emitter object. - * @param[in] output An output buffer. - * @param[in] size The buffer size. - * @param[in] size_written The pointer to save the number of written - * bytes. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output_string(yaml_emitter_t *emitter, - unsigned char *output, size_t size, size_t *size_written); - -/** - * Set a file output. - * - * @a file should be a file object open for writing. The application is - * responsible for closing the @a file. - * - * @param[in,out] emitter An emitter object. - * @param[in] file An open file. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output_file(yaml_emitter_t *emitter, FILE *file); - -/** - * Set a generic output handler. - * - * @param[in,out] emitter An emitter object. - * @param[in] handler A write handler. - * @param[in] data Any application data for passing to the write - * handler. - */ - -YAML_DECLARE(void) -yaml_emitter_set_output(yaml_emitter_t *emitter, - yaml_write_handler_t *handler, void *data); - -/** - * Set the output encoding. - * - * @param[in,out] emitter An emitter object. - * @param[in] encoding The output encoding. - */ - -YAML_DECLARE(void) -yaml_emitter_set_encoding(yaml_emitter_t *emitter, yaml_encoding_t encoding); - -/** - * Set if the output should be in the "canonical" format as in the YAML - * specification. - * - * @param[in,out] emitter An emitter object. - * @param[in] canonical If the output is canonical. - */ - -YAML_DECLARE(void) -yaml_emitter_set_canonical(yaml_emitter_t *emitter, int canonical); - -/** - * Set the intendation increment. - * - * @param[in,out] emitter An emitter object. - * @param[in] indent The indentation increment (1 < . < 10). - */ - -YAML_DECLARE(void) -yaml_emitter_set_indent(yaml_emitter_t *emitter, int indent); - -/** - * Set the preferred line width. @c -1 means unlimited. - * - * @param[in,out] emitter An emitter object. - * @param[in] width The preferred line width. - */ - -YAML_DECLARE(void) -yaml_emitter_set_width(yaml_emitter_t *emitter, int width); - -/** - * Set if unescaped non-ASCII characters are allowed. - * - * @param[in,out] emitter An emitter object. - * @param[in] unicode If unescaped Unicode characters are allowed. - */ - -YAML_DECLARE(void) -yaml_emitter_set_unicode(yaml_emitter_t *emitter, int unicode); - -/** - * Set the preferred line break. - * - * @param[in,out] emitter An emitter object. - * @param[in] line_break The preferred line break. - */ - -YAML_DECLARE(void) -yaml_emitter_set_break(yaml_emitter_t *emitter, yaml_break_t line_break); - -/** - * Emit an event. - * - * The event object may be generated using the yaml_parser_parse() function. - * The emitter takes the responsibility for the event object and destroys its - * content after it is emitted. The event object is destroyed even if the - * function fails. - * - * @param[in,out] emitter An emitter object. - * @param[in,out] event An event object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event); - -/** - * Start a YAML stream. - * - * This function should be used before yaml_emitter_dump() is called. - * - * @param[in,out] emitter An emitter object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_open(yaml_emitter_t *emitter); - -/** - * Finish a YAML stream. - * - * This function should be used after yaml_emitter_dump() is called. - * - * @param[in,out] emitter An emitter object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_close(yaml_emitter_t *emitter); - -/** - * Emit a YAML document. - * - * The documen object may be generated using the yaml_parser_load() function - * or the yaml_document_initialize() function. The emitter takes the - * responsibility for the document object and destoys its content after - * it is emitted. The document object is destroyedeven if the function fails. - * - * @param[in,out] emitter An emitter object. - * @param[in,out] document A document object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_dump(yaml_emitter_t *emitter, yaml_document_t *document); - -/** - * Flush the accumulated characters to the output. - * - * @param[in,out] emitter An emitter object. - * - * @returns @c 1 if the function succeeded, @c 0 on error. - */ - -YAML_DECLARE(int) -yaml_emitter_flush(yaml_emitter_t *emitter); - -/** @} */ - -#ifdef __cplusplus -} -#endif - -#endif /* #ifndef YAML_H */ -
diff --git a/yaml_private.h b/yaml_private.h deleted file mode 100644 index ed5ea66..0000000 --- a/yaml_private.h +++ /dev/null
@@ -1,640 +0,0 @@ - -#if HAVE_CONFIG_H -#include <config.h> -#endif - -#include <yaml.h> - -#include <assert.h> -#include <limits.h> - -/* - * Memory management. - */ - -YAML_DECLARE(void *) -yaml_malloc(size_t size); - -YAML_DECLARE(void *) -yaml_realloc(void *ptr, size_t size); - -YAML_DECLARE(void) -yaml_free(void *ptr); - -YAML_DECLARE(yaml_char_t *) -yaml_strdup(const yaml_char_t *); - -/* - * Reader: Ensure that the buffer contains at least `length` characters. - */ - -YAML_DECLARE(int) -yaml_parser_update_buffer(yaml_parser_t *parser, size_t length); - -/* - * Scanner: Ensure that the token stack contains at least one token ready. - */ - -YAML_DECLARE(int) -yaml_parser_fetch_more_tokens(yaml_parser_t *parser); - -/* - * The size of the input raw buffer. - */ - -#define INPUT_RAW_BUFFER_SIZE 16384 - -/* - * The size of the input buffer. - * - * It should be possible to decode the whole raw buffer. - */ - -#define INPUT_BUFFER_SIZE (INPUT_RAW_BUFFER_SIZE*3) - -/* - * The size of the output buffer. - */ - -#define OUTPUT_BUFFER_SIZE 16384 - -/* - * The size of the output raw buffer. - * - * It should be possible to encode the whole output buffer. - */ - -#define OUTPUT_RAW_BUFFER_SIZE (OUTPUT_BUFFER_SIZE*2+2) - -/* - * The size of other stacks and queues. - */ - -#define INITIAL_STACK_SIZE 16 -#define INITIAL_QUEUE_SIZE 16 -#define INITIAL_STRING_SIZE 16 - -/* - * Buffer management. - */ - -#define BUFFER_INIT(context,buffer,size) \ - (((buffer).start = yaml_malloc(size)) ? \ - ((buffer).last = (buffer).pointer = (buffer).start, \ - (buffer).end = (buffer).start+(size), \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define BUFFER_DEL(context,buffer) \ - (yaml_free((buffer).start), \ - (buffer).start = (buffer).pointer = (buffer).end = 0) - -/* - * String management. - */ - -typedef struct { - yaml_char_t *start; - yaml_char_t *end; - yaml_char_t *pointer; -} yaml_string_t; - -YAML_DECLARE(int) -yaml_string_extend(yaml_char_t **start, - yaml_char_t **pointer, yaml_char_t **end); - -YAML_DECLARE(int) -yaml_string_join( - yaml_char_t **a_start, yaml_char_t **a_pointer, yaml_char_t **a_end, - yaml_char_t **b_start, yaml_char_t **b_pointer, yaml_char_t **b_end); - -#define NULL_STRING { NULL, NULL, NULL } - -#define STRING(string,length) { (string), (string)+(length), (string) } - -#define STRING_ASSIGN(value,string,length) \ - ((value).start = (string), \ - (value).end = (string)+(length), \ - (value).pointer = (string)) - -#define STRING_INIT(context,string,size) \ - (((string).start = yaml_malloc(size)) ? \ - ((string).pointer = (string).start, \ - (string).end = (string).start+(size), \ - memset((string).start, 0, (size)), \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define STRING_DEL(context,string) \ - (yaml_free((string).start), \ - (string).start = (string).pointer = (string).end = 0) - -#define STRING_EXTEND(context,string) \ - (((string).pointer+5 < (string).end) \ - || yaml_string_extend(&(string).start, \ - &(string).pointer, &(string).end)) - -#define CLEAR(context,string) \ - ((string).pointer = (string).start, \ - memset((string).start, 0, (string).end-(string).start)) - -#define JOIN(context,string_a,string_b) \ - ((yaml_string_join(&(string_a).start, &(string_a).pointer, \ - &(string_a).end, &(string_b).start, \ - &(string_b).pointer, &(string_b).end)) ? \ - ((string_b).pointer = (string_b).start, \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -/* - * String check operations. - */ - -/* - * Check the octet at the specified position. - */ - -#define CHECK_AT(string,octet,offset) \ - ((string).pointer[offset] == (yaml_char_t)(octet)) - -/* - * Check the current octet in the buffer. - */ - -#define CHECK(string,octet) CHECK_AT((string),(octet),0) - -/* - * Check if the character at the specified position is an alphabetical - * character, a digit, '_', or '-'. - */ - -#define IS_ALPHA_AT(string,offset) \ - (((string).pointer[offset] >= (yaml_char_t) '0' && \ - (string).pointer[offset] <= (yaml_char_t) '9') || \ - ((string).pointer[offset] >= (yaml_char_t) 'A' && \ - (string).pointer[offset] <= (yaml_char_t) 'Z') || \ - ((string).pointer[offset] >= (yaml_char_t) 'a' && \ - (string).pointer[offset] <= (yaml_char_t) 'z') || \ - (string).pointer[offset] == '_' || \ - (string).pointer[offset] == '-') - -#define IS_ALPHA(string) IS_ALPHA_AT((string),0) - -/* - * Check if the character at the specified position is a digit. - */ - -#define IS_DIGIT_AT(string,offset) \ - (((string).pointer[offset] >= (yaml_char_t) '0' && \ - (string).pointer[offset] <= (yaml_char_t) '9')) - -#define IS_DIGIT(string) IS_DIGIT_AT((string),0) - -/* - * Get the value of a digit. - */ - -#define AS_DIGIT_AT(string,offset) \ - ((string).pointer[offset] - (yaml_char_t) '0') - -#define AS_DIGIT(string) AS_DIGIT_AT((string),0) - -/* - * Check if the character at the specified position is a hex-digit. - */ - -#define IS_HEX_AT(string,offset) \ - (((string).pointer[offset] >= (yaml_char_t) '0' && \ - (string).pointer[offset] <= (yaml_char_t) '9') || \ - ((string).pointer[offset] >= (yaml_char_t) 'A' && \ - (string).pointer[offset] <= (yaml_char_t) 'F') || \ - ((string).pointer[offset] >= (yaml_char_t) 'a' && \ - (string).pointer[offset] <= (yaml_char_t) 'f')) - -#define IS_HEX(string) IS_HEX_AT((string),0) - -/* - * Get the value of a hex-digit. - */ - -#define AS_HEX_AT(string,offset) \ - (((string).pointer[offset] >= (yaml_char_t) 'A' && \ - (string).pointer[offset] <= (yaml_char_t) 'F') ? \ - ((string).pointer[offset] - (yaml_char_t) 'A' + 10) : \ - ((string).pointer[offset] >= (yaml_char_t) 'a' && \ - (string).pointer[offset] <= (yaml_char_t) 'f') ? \ - ((string).pointer[offset] - (yaml_char_t) 'a' + 10) : \ - ((string).pointer[offset] - (yaml_char_t) '0')) - -#define AS_HEX(string) AS_HEX_AT((string),0) - -/* - * Check if the character is ASCII. - */ - -#define IS_ASCII_AT(string,offset) \ - ((string).pointer[offset] <= (yaml_char_t) '\x7F') - -#define IS_ASCII(string) IS_ASCII_AT((string),0) - -/* - * Check if the character can be printed unescaped. - */ - -#define IS_PRINTABLE_AT(string,offset) \ - (((string).pointer[offset] == 0x0A) /* . == #x0A */ \ - || ((string).pointer[offset] >= 0x20 /* #x20 <= . <= #x7E */ \ - && (string).pointer[offset] <= 0x7E) \ - || ((string).pointer[offset] == 0xC2 /* #0xA0 <= . <= #xD7FF */ \ - && (string).pointer[offset+1] >= 0xA0) \ - || ((string).pointer[offset] > 0xC2 \ - && (string).pointer[offset] < 0xED) \ - || ((string).pointer[offset] == 0xED \ - && (string).pointer[offset+1] < 0xA0) \ - || ((string).pointer[offset] == 0xEE) \ - || ((string).pointer[offset] == 0xEF /* #xE000 <= . <= #xFFFD */ \ - && !((string).pointer[offset+1] == 0xBB /* && . != #xFEFF */ \ - && (string).pointer[offset+2] == 0xBF) \ - && !((string).pointer[offset+1] == 0xBF \ - && ((string).pointer[offset+2] == 0xBE \ - || (string).pointer[offset+2] == 0xBF)))) - -#define IS_PRINTABLE(string) IS_PRINTABLE_AT((string),0) - -/* - * Check if the character at the specified position is NUL. - */ - -#define IS_Z_AT(string,offset) CHECK_AT((string),'\0',(offset)) - -#define IS_Z(string) IS_Z_AT((string),0) - -/* - * Check if the character at the specified position is BOM. - */ - -#define IS_BOM_AT(string,offset) \ - (CHECK_AT((string),'\xEF',(offset)) \ - && CHECK_AT((string),'\xBB',(offset)+1) \ - && CHECK_AT((string),'\xBF',(offset)+2)) /* BOM (#xFEFF) */ - -#define IS_BOM(string) IS_BOM_AT(string,0) - -/* - * Check if the character at the specified position is space. - */ - -#define IS_SPACE_AT(string,offset) CHECK_AT((string),' ',(offset)) - -#define IS_SPACE(string) IS_SPACE_AT((string),0) - -/* - * Check if the character at the specified position is tab. - */ - -#define IS_TAB_AT(string,offset) CHECK_AT((string),'\t',(offset)) - -#define IS_TAB(string) IS_TAB_AT((string),0) - -/* - * Check if the character at the specified position is blank (space or tab). - */ - -#define IS_BLANK_AT(string,offset) \ - (IS_SPACE_AT((string),(offset)) || IS_TAB_AT((string),(offset))) - -#define IS_BLANK(string) IS_BLANK_AT((string),0) - -/* - * Check if the character at the specified position is a line break. - */ - -#define IS_BREAK_AT(string,offset) \ - (CHECK_AT((string),'\r',(offset)) /* CR (#xD)*/ \ - || CHECK_AT((string),'\n',(offset)) /* LF (#xA) */ \ - || (CHECK_AT((string),'\xC2',(offset)) \ - && CHECK_AT((string),'\x85',(offset)+1)) /* NEL (#x85) */ \ - || (CHECK_AT((string),'\xE2',(offset)) \ - && CHECK_AT((string),'\x80',(offset)+1) \ - && CHECK_AT((string),'\xA8',(offset)+2)) /* LS (#x2028) */ \ - || (CHECK_AT((string),'\xE2',(offset)) \ - && CHECK_AT((string),'\x80',(offset)+1) \ - && CHECK_AT((string),'\xA9',(offset)+2))) /* PS (#x2029) */ - -#define IS_BREAK(string) IS_BREAK_AT((string),0) - -#define IS_CRLF_AT(string,offset) \ - (CHECK_AT((string),'\r',(offset)) && CHECK_AT((string),'\n',(offset)+1)) - -#define IS_CRLF(string) IS_CRLF_AT((string),0) - -/* - * Check if the character is a line break or NUL. - */ - -#define IS_BREAKZ_AT(string,offset) \ - (IS_BREAK_AT((string),(offset)) || IS_Z_AT((string),(offset))) - -#define IS_BREAKZ(string) IS_BREAKZ_AT((string),0) - -/* - * Check if the character is a line break, space, or NUL. - */ - -#define IS_SPACEZ_AT(string,offset) \ - (IS_SPACE_AT((string),(offset)) || IS_BREAKZ_AT((string),(offset))) - -#define IS_SPACEZ(string) IS_SPACEZ_AT((string),0) - -/* - * Check if the character is a line break, space, tab, or NUL. - */ - -#define IS_BLANKZ_AT(string,offset) \ - (IS_BLANK_AT((string),(offset)) || IS_BREAKZ_AT((string),(offset))) - -#define IS_BLANKZ(string) IS_BLANKZ_AT((string),0) - -/* - * Determine the width of the character. - */ - -#define WIDTH_AT(string,offset) \ - (((string).pointer[offset] & 0x80) == 0x00 ? 1 : \ - ((string).pointer[offset] & 0xE0) == 0xC0 ? 2 : \ - ((string).pointer[offset] & 0xF0) == 0xE0 ? 3 : \ - ((string).pointer[offset] & 0xF8) == 0xF0 ? 4 : 0) - -#define WIDTH(string) WIDTH_AT((string),0) - -/* - * Move the string pointer to the next character. - */ - -#define MOVE(string) ((string).pointer += WIDTH((string))) - -/* - * Copy a character and move the pointers of both strings. - */ - -#define COPY(string_a,string_b) \ - ((*(string_b).pointer & 0x80) == 0x00 ? \ - (*((string_a).pointer++) = *((string_b).pointer++)) : \ - (*(string_b).pointer & 0xE0) == 0xC0 ? \ - (*((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++)) : \ - (*(string_b).pointer & 0xF0) == 0xE0 ? \ - (*((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++)) : \ - (*(string_b).pointer & 0xF8) == 0xF0 ? \ - (*((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++), \ - *((string_a).pointer++) = *((string_b).pointer++)) : 0) - -/* - * Stack and queue management. - */ - -YAML_DECLARE(int) -yaml_stack_extend(void **start, void **top, void **end); - -YAML_DECLARE(int) -yaml_queue_extend(void **start, void **head, void **tail, void **end); - -#define STACK_INIT(context,stack,size) \ - (((stack).start = yaml_malloc((size)*sizeof(*(stack).start))) ? \ - ((stack).top = (stack).start, \ - (stack).end = (stack).start+(size), \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define STACK_DEL(context,stack) \ - (yaml_free((stack).start), \ - (stack).start = (stack).top = (stack).end = 0) - -#define STACK_EMPTY(context,stack) \ - ((stack).start == (stack).top) - -#define PUSH(context,stack,value) \ - (((stack).top != (stack).end \ - || yaml_stack_extend((void **)&(stack).start, \ - (void **)&(stack).top, (void **)&(stack).end)) ? \ - (*((stack).top++) = value, \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define POP(context,stack) \ - (*(--(stack).top)) - -#define QUEUE_INIT(context,queue,size) \ - (((queue).start = yaml_malloc((size)*sizeof(*(queue).start))) ? \ - ((queue).head = (queue).tail = (queue).start, \ - (queue).end = (queue).start+(size), \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define QUEUE_DEL(context,queue) \ - (yaml_free((queue).start), \ - (queue).start = (queue).head = (queue).tail = (queue).end = 0) - -#define QUEUE_EMPTY(context,queue) \ - ((queue).head == (queue).tail) - -#define ENQUEUE(context,queue,value) \ - (((queue).tail != (queue).end \ - || yaml_queue_extend((void **)&(queue).start, (void **)&(queue).head, \ - (void **)&(queue).tail, (void **)&(queue).end)) ? \ - (*((queue).tail++) = value, \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -#define DEQUEUE(context,queue) \ - (*((queue).head++)) - -#define QUEUE_INSERT(context,queue,index,value) \ - (((queue).tail != (queue).end \ - || yaml_queue_extend((void **)&(queue).start, (void **)&(queue).head, \ - (void **)&(queue).tail, (void **)&(queue).end)) ? \ - (memmove((queue).head+(index)+1,(queue).head+(index), \ - ((queue).tail-(queue).head-(index))*sizeof(*(queue).start)), \ - *((queue).head+(index)) = value, \ - (queue).tail++, \ - 1) : \ - ((context)->error = YAML_MEMORY_ERROR, \ - 0)) - -/* - * Token initializers. - */ - -#define TOKEN_INIT(token,token_type,token_start_mark,token_end_mark) \ - (memset(&(token), 0, sizeof(yaml_token_t)), \ - (token).type = (token_type), \ - (token).start_mark = (token_start_mark), \ - (token).end_mark = (token_end_mark)) - -#define STREAM_START_TOKEN_INIT(token,token_encoding,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_STREAM_START_TOKEN,(start_mark),(end_mark)), \ - (token).data.stream_start.encoding = (token_encoding)) - -#define STREAM_END_TOKEN_INIT(token,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_STREAM_END_TOKEN,(start_mark),(end_mark))) - -#define ALIAS_TOKEN_INIT(token,token_value,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_ALIAS_TOKEN,(start_mark),(end_mark)), \ - (token).data.alias.value = (token_value)) - -#define ANCHOR_TOKEN_INIT(token,token_value,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_ANCHOR_TOKEN,(start_mark),(end_mark)), \ - (token).data.anchor.value = (token_value)) - -#define TAG_TOKEN_INIT(token,token_handle,token_suffix,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_TAG_TOKEN,(start_mark),(end_mark)), \ - (token).data.tag.handle = (token_handle), \ - (token).data.tag.suffix = (token_suffix)) - -#define SCALAR_TOKEN_INIT(token,token_value,token_length,token_style,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_SCALAR_TOKEN,(start_mark),(end_mark)), \ - (token).data.scalar.value = (token_value), \ - (token).data.scalar.length = (token_length), \ - (token).data.scalar.style = (token_style)) - -#define VERSION_DIRECTIVE_TOKEN_INIT(token,token_major,token_minor,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_VERSION_DIRECTIVE_TOKEN,(start_mark),(end_mark)), \ - (token).data.version_directive.major = (token_major), \ - (token).data.version_directive.minor = (token_minor)) - -#define TAG_DIRECTIVE_TOKEN_INIT(token,token_handle,token_prefix,start_mark,end_mark) \ - (TOKEN_INIT((token),YAML_TAG_DIRECTIVE_TOKEN,(start_mark),(end_mark)), \ - (token).data.tag_directive.handle = (token_handle), \ - (token).data.tag_directive.prefix = (token_prefix)) - -/* - * Event initializers. - */ - -#define EVENT_INIT(event,event_type,event_start_mark,event_end_mark) \ - (memset(&(event), 0, sizeof(yaml_event_t)), \ - (event).type = (event_type), \ - (event).start_mark = (event_start_mark), \ - (event).end_mark = (event_end_mark)) - -#define STREAM_START_EVENT_INIT(event,event_encoding,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_STREAM_START_EVENT,(start_mark),(end_mark)), \ - (event).data.stream_start.encoding = (event_encoding)) - -#define STREAM_END_EVENT_INIT(event,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_STREAM_END_EVENT,(start_mark),(end_mark))) - -#define DOCUMENT_START_EVENT_INIT(event,event_version_directive, \ - event_tag_directives_start,event_tag_directives_end,event_implicit,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_DOCUMENT_START_EVENT,(start_mark),(end_mark)), \ - (event).data.document_start.version_directive = (event_version_directive), \ - (event).data.document_start.tag_directives.start = (event_tag_directives_start), \ - (event).data.document_start.tag_directives.end = (event_tag_directives_end), \ - (event).data.document_start.implicit = (event_implicit)) - -#define DOCUMENT_END_EVENT_INIT(event,event_implicit,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_DOCUMENT_END_EVENT,(start_mark),(end_mark)), \ - (event).data.document_end.implicit = (event_implicit)) - -#define ALIAS_EVENT_INIT(event,event_anchor,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_ALIAS_EVENT,(start_mark),(end_mark)), \ - (event).data.alias.anchor = (event_anchor)) - -#define SCALAR_EVENT_INIT(event,event_anchor,event_tag,event_value,event_length, \ - event_plain_implicit, event_quoted_implicit,event_style,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_SCALAR_EVENT,(start_mark),(end_mark)), \ - (event).data.scalar.anchor = (event_anchor), \ - (event).data.scalar.tag = (event_tag), \ - (event).data.scalar.value = (event_value), \ - (event).data.scalar.length = (event_length), \ - (event).data.scalar.plain_implicit = (event_plain_implicit), \ - (event).data.scalar.quoted_implicit = (event_quoted_implicit), \ - (event).data.scalar.style = (event_style)) - -#define SEQUENCE_START_EVENT_INIT(event,event_anchor,event_tag, \ - event_implicit,event_style,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_SEQUENCE_START_EVENT,(start_mark),(end_mark)), \ - (event).data.sequence_start.anchor = (event_anchor), \ - (event).data.sequence_start.tag = (event_tag), \ - (event).data.sequence_start.implicit = (event_implicit), \ - (event).data.sequence_start.style = (event_style)) - -#define SEQUENCE_END_EVENT_INIT(event,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_SEQUENCE_END_EVENT,(start_mark),(end_mark))) - -#define MAPPING_START_EVENT_INIT(event,event_anchor,event_tag, \ - event_implicit,event_style,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_MAPPING_START_EVENT,(start_mark),(end_mark)), \ - (event).data.mapping_start.anchor = (event_anchor), \ - (event).data.mapping_start.tag = (event_tag), \ - (event).data.mapping_start.implicit = (event_implicit), \ - (event).data.mapping_start.style = (event_style)) - -#define MAPPING_END_EVENT_INIT(event,start_mark,end_mark) \ - (EVENT_INIT((event),YAML_MAPPING_END_EVENT,(start_mark),(end_mark))) - -/* - * Document initializer. - */ - -#define DOCUMENT_INIT(document,document_nodes_start,document_nodes_end, \ - document_version_directive,document_tag_directives_start, \ - document_tag_directives_end,document_start_implicit, \ - document_end_implicit,document_start_mark,document_end_mark) \ - (memset(&(document), 0, sizeof(yaml_document_t)), \ - (document).nodes.start = (document_nodes_start), \ - (document).nodes.end = (document_nodes_end), \ - (document).nodes.top = (document_nodes_start), \ - (document).version_directive = (document_version_directive), \ - (document).tag_directives.start = (document_tag_directives_start), \ - (document).tag_directives.end = (document_tag_directives_end), \ - (document).start_implicit = (document_start_implicit), \ - (document).end_implicit = (document_end_implicit), \ - (document).start_mark = (document_start_mark), \ - (document).end_mark = (document_end_mark)) - -/* - * Node initializers. - */ - -#define NODE_INIT(node,node_type,node_tag,node_start_mark,node_end_mark) \ - (memset(&(node), 0, sizeof(yaml_node_t)), \ - (node).type = (node_type), \ - (node).tag = (node_tag), \ - (node).start_mark = (node_start_mark), \ - (node).end_mark = (node_end_mark)) - -#define SCALAR_NODE_INIT(node,node_tag,node_value,node_length, \ - node_style,start_mark,end_mark) \ - (NODE_INIT((node),YAML_SCALAR_NODE,(node_tag),(start_mark),(end_mark)), \ - (node).data.scalar.value = (node_value), \ - (node).data.scalar.length = (node_length), \ - (node).data.scalar.style = (node_style)) - -#define SEQUENCE_NODE_INIT(node,node_tag,node_items_start,node_items_end, \ - node_style,start_mark,end_mark) \ - (NODE_INIT((node),YAML_SEQUENCE_NODE,(node_tag),(start_mark),(end_mark)), \ - (node).data.sequence.items.start = (node_items_start), \ - (node).data.sequence.items.end = (node_items_end), \ - (node).data.sequence.items.top = (node_items_start), \ - (node).data.sequence.style = (node_style)) - -#define MAPPING_NODE_INIT(node,node_tag,node_pairs_start,node_pairs_end, \ - node_style,start_mark,end_mark) \ - (NODE_INIT((node),YAML_MAPPING_NODE,(node_tag),(start_mark),(end_mark)), \ - (node).data.mapping.pairs.start = (node_pairs_start), \ - (node).data.mapping.pairs.end = (node_pairs_end), \ - (node).data.mapping.pairs.top = (node_pairs_start), \ - (node).data.mapping.style = (node_style)) -
diff --git a/yamlh.go b/yamlh.go new file mode 100644 index 0000000..7733b86 --- /dev/null +++ b/yamlh.go
@@ -0,0 +1,712 @@ +package goyaml + +import ( + "io" +) + +// The version directive data. +type yaml_version_directive_t struct { + major int8 // The major version number. + minor int8 // The minor version number. +} + +// The tag directive data. +type yaml_tag_directive_t struct { + handle []byte // The tag handle. + prefix []byte // The tag prefix. +} + +type yaml_encoding_t int + +// The stream encoding. +const ( + // Let the parser choose the encoding. + yaml_ANY_ENCODING yaml_encoding_t = iota + + yaml_UTF8_ENCODING // The default UTF-8 encoding. + yaml_UTF16LE_ENCODING // The UTF-16-LE encoding with BOM. + yaml_UTF16BE_ENCODING // The UTF-16-BE encoding with BOM. +) + +type yaml_break_t int + +// Line break types. +const ( + // Let the parser choose the break type. + yaml_ANY_BREAK yaml_break_t = iota + + yaml_CR_BREAK // Use CR for line breaks (Mac style). + yaml_LN_BREAK // Use LN for line breaks (Unix style). + yaml_CRLN_BREAK // Use CR LN for line breaks (DOS style). +) + +type yaml_error_type_t int + +// Many bad things could happen with the parser and emitter. +const ( + // No error is produced. + yaml_NO_ERROR yaml_error_type_t = iota + + yaml_MEMORY_ERROR // Cannot allocate or reallocate a block of memory. + yaml_READER_ERROR // Cannot read or decode the input stream. + yaml_SCANNER_ERROR // Cannot scan the input stream. + yaml_PARSER_ERROR // Cannot parse the input stream. + yaml_COMPOSER_ERROR // Cannot compose a YAML document. + yaml_WRITER_ERROR // Cannot write to the output stream. + yaml_EMITTER_ERROR // Cannot emit a YAML stream. +) + +// The pointer position. +type yaml_mark_t struct { + index int // The position index. + line int // The position line. + column int // The position column. +} + +// Node Styles + +type yaml_style_t int8 + +type yaml_scalar_style_t yaml_style_t + +// Scalar styles. +const ( + // Let the emitter choose the style. + yaml_ANY_SCALAR_STYLE yaml_scalar_style_t = iota + + yaml_PLAIN_SCALAR_STYLE // The plain scalar style. + yaml_SINGLE_QUOTED_SCALAR_STYLE // The single-quoted scalar style. + yaml_DOUBLE_QUOTED_SCALAR_STYLE // The double-quoted scalar style. + yaml_LITERAL_SCALAR_STYLE // The literal scalar style. + yaml_FOLDED_SCALAR_STYLE // The folded scalar style. +) + +type yaml_sequence_style_t yaml_style_t + +// Sequence styles. +const ( + // Let the emitter choose the style. + yaml_ANY_SEQUENCE_STYLE yaml_sequence_style_t = iota + + yaml_BLOCK_SEQUENCE_STYLE // The block sequence style. + yaml_FLOW_SEQUENCE_STYLE // The flow sequence style. +) + +type yaml_mapping_style_t yaml_style_t + +// Mapping styles. +const ( + // Let the emitter choose the style. + YAML_ANY_MAPPING_STYLE yaml_mapping_style_t = iota + + yaml_BLOCK_MAPPING_STYLE // The block mapping style. + yaml_FLOW_MAPPING_STYLE // The flow mapping style. +) + +// Tokens + +type yaml_token_type_t int + +// Token types. +const ( + // An empty token. + yaml_NO_TOKEN yaml_token_type_t = iota + + yaml_STREAM_START_TOKEN // A STREAM-START token. + yaml_STREAM_END_TOKEN // A STREAM-END token. + + yaml_VERSION_DIRECTIVE_TOKEN // A VERSION-DIRECTIVE token. + yaml_TAG_DIRECTIVE_TOKEN // A TAG-DIRECTIVE token. + yaml_DOCUMENT_START_TOKEN // A DOCUMENT-START token. + yaml_DOCUMENT_END_TOKEN // A DOCUMENT-END token. + + yaml_BLOCK_SEQUENCE_START_TOKEN // A BLOCK-SEQUENCE-START token. + yaml_BLOCK_MAPPING_START_TOKEN // A BLOCK-SEQUENCE-END token. + yaml_BLOCK_END_TOKEN // A BLOCK-END token. + + yaml_FLOW_SEQUENCE_START_TOKEN // A FLOW-SEQUENCE-START token. + yaml_FLOW_SEQUENCE_END_TOKEN // A FLOW-SEQUENCE-END token. + yaml_FLOW_MAPPING_START_TOKEN // A FLOW-MAPPING-START token. + yaml_FLOW_MAPPING_END_TOKEN // A FLOW-MAPPING-END token. + + yaml_BLOCK_ENTRY_TOKEN // A BLOCK-ENTRY token. + yaml_FLOW_ENTRY_TOKEN // A FLOW-ENTRY token. + yaml_KEY_TOKEN // A KEY token. + yaml_VALUE_TOKEN // A VALUE token. + + yaml_ALIAS_TOKEN // An ALIAS token. + yaml_ANCHOR_TOKEN // An ANCHOR token. + yaml_TAG_TOKEN // A TAG token. + 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 { + // The token type. + typ yaml_token_type_t + + // The start/end of the token. + start_mark, end_mark yaml_mark_t + + // The stream encoding (for yaml_STREAM_START_TOKEN). + encoding yaml_encoding_t + + // The alias/anchor/scalar value or tag/tag directive handle + // (for yaml_ALIAS_TOKEN, yaml_ANCHOR_TOKEN, yaml_SCALAR_TOKEN, yaml_TAG_TOKEN, yaml_TAG_DIRECTIVE_TOKEN). + value []byte + + // The tag suffix (for yaml_TAG_TOKEN). + suffix []byte + + // The tag directive prefix (for yaml_TAG_DIRECTIVE_TOKEN). + prefix []byte + + // The scalar style (for yaml_SCALAR_TOKEN). + style yaml_scalar_style_t + + // The version directive major/minor (for yaml_VERSION_DIRECTIVE_TOKEN). + major, minor int8 +} + +// Events + +type yaml_event_type_t int8 + +// Event types. +const ( + // An empty event. + yaml_NO_EVENT yaml_event_type_t = iota + + yaml_STREAM_START_EVENT // A STREAM-START event. + yaml_STREAM_END_EVENT // A STREAM-END event. + yaml_DOCUMENT_START_EVENT // A DOCUMENT-START event. + yaml_DOCUMENT_END_EVENT // A DOCUMENT-END event. + yaml_ALIAS_EVENT // An ALIAS event. + yaml_SCALAR_EVENT // A SCALAR event. + yaml_SEQUENCE_START_EVENT // A SEQUENCE-START event. + yaml_SEQUENCE_END_EVENT // A SEQUENCE-END event. + yaml_MAPPING_START_EVENT // A MAPPING-START event. + yaml_MAPPING_END_EVENT // A MAPPING-END event. +) + +// The event structure. +type yaml_event_t struct { + + // The event type. + typ yaml_event_type_t + + // The start and end of the event. + start_mark, end_mark yaml_mark_t + + // The document encoding (for yaml_STREAM_START_EVENT). + encoding yaml_encoding_t + + // The version directive (for yaml_DOCUMENT_START_EVENT). + version_directive *yaml_version_directive_t + + // The list of tag directives (for yaml_DOCUMENT_START_EVENT). + tag_directives []yaml_tag_directive_t + + // The anchor (for yaml_SCALAR_EVENT, yaml_SEQUENCE_START_EVENT, yaml_MAPPING_START_EVENT, yaml_ALIAS_EVENT). + anchor []byte + + // The tag (for yaml_SCALAR_EVENT, yaml_SEQUENCE_START_EVENT, yaml_MAPPING_START_EVENT). + tag []byte + + // The scalar value (for yaml_SCALAR_EVENT). + value []byte + + // Is the document start/end indicator implicit, or the tag optional? + // (for yaml_DOCUMENT_START_EVENT, yaml_DOCUMENT_END_EVENT, yaml_SEQUENCE_START_EVENT, yaml_MAPPING_START_EVENT, yaml_SCALAR_EVENT). + implicit bool + + // Is the tag optional for any non-plain style? (for yaml_SCALAR_EVENT). + quoted_implicit bool + + // The style (for yaml_SCALAR_EVENT, yaml_SEQUENCE_START_EVENT, yaml_MAPPING_START_EVENT). + style yaml_style_t +} + +func (e *yaml_event_t) scalar_style() yaml_scalar_style_t { return yaml_scalar_style_t(e.style) } +func (e *yaml_event_t) sequence_style() yaml_sequence_style_t { return yaml_sequence_style_t(e.style) } +func (e *yaml_event_t) mapping_style() yaml_mapping_style_t { return yaml_mapping_style_t(e.style) } + +// Nodes + +const ( + yaml_NULL_TAG = "tag:yaml.org,2002:null" // The tag !!null with the only possible value: null. + yaml_BOOL_TAG = "tag:yaml.org,2002:bool" // The tag !!bool with the values: true and false. + yaml_STR_TAG = "tag:yaml.org,2002:str" // The tag !!str for string values. + yaml_INT_TAG = "tag:yaml.org,2002:int" // The tag !!int for integer values. + yaml_FLOAT_TAG = "tag:yaml.org,2002:float" // The tag !!float for float values. + yaml_TIMESTAMP_TAG = "tag:yaml.org,2002:timestamp" // The tag !!timestamp for date and time values. + + yaml_SEQ_TAG = "tag:yaml.org,2002:seq" // The tag !!seq is used to denote sequences. + yaml_MAP_TAG = "tag:yaml.org,2002:map" // The tag !!map is used to denote mapping. + + yaml_DEFAULT_SCALAR_TAG = yaml_STR_TAG // The default scalar tag is !!str. + yaml_DEFAULT_SEQUENCE_TAG = yaml_SEQ_TAG // The default sequence tag is !!seq. + yaml_DEFAULT_MAPPING_TAG = yaml_MAP_TAG // The default mapping tag is !!map. +) + +type yaml_node_type_t int + +// Node types. +const ( + // An empty node. + yaml_NO_NODE yaml_node_type_t = iota + + yaml_SCALAR_NODE // A scalar node. + yaml_SEQUENCE_NODE // A sequence node. + yaml_MAPPING_NODE // A mapping node. +) + +// An element of a sequence node. +type yaml_node_item_t int + +// An element of a mapping node. +type yaml_node_pair_t struct { + key int // The key of the element. + value int // The value of the element. +} + +// The node structure. +type yaml_node_t struct { + typ yaml_node_type_t // The node type. + tag []byte // The node tag. + + // The node data. + + // The scalar parameters (for yaml_SCALAR_NODE). + scalar struct { + value []byte // The scalar value. + length int // The length of the scalar value. + style yaml_scalar_style_t // The scalar style. + } + + // The sequence parameters (for YAML_SEQUENCE_NODE). + sequence struct { + items_data []yaml_node_item_t // The stack of sequence items. + style yaml_sequence_style_t // The sequence style. + } + + // The mapping parameters (for yaml_MAPPING_NODE). + mapping struct { + pairs_data []yaml_node_pair_t // The stack of mapping pairs (key, value). + pairs_start *yaml_node_pair_t // The beginning of the stack. + pairs_end *yaml_node_pair_t // The end of the stack. + pairs_top *yaml_node_pair_t // The top of the stack. + style yaml_mapping_style_t // The mapping style. + } + + start_mark yaml_mark_t // The beginning of the node. + end_mark yaml_mark_t // The end of the node. + +} + +// The document structure. +type yaml_document_t struct { + + // The document nodes. + nodes []yaml_node_t + + // The version directive. + version_directive *yaml_version_directive_t + + // The list of tag directives. + tag_directives_data []yaml_tag_directive_t + tag_directives_start int // The beginning of the tag directives list. + tag_directives_end int // The end of the tag directives list. + + start_implicit int // Is the document start indicator implicit? + end_implicit int // Is the document end indicator implicit? + + // The start/end of the document. + start_mark, end_mark yaml_mark_t +} + +// The prototype of a read handler. +// +// The read handler is called when the parser needs to read more bytes from the +// source. The handler should write not more than size bytes to the buffer. +// The number of written bytes should be set to the size_read variable. +// +// [in,out] data A pointer to an application data specified by +// yaml_parser_set_input(). +// [out] buffer The buffer to write the data from the source. +// [in] size The size of the buffer. +// [out] size_read The actual number of bytes read from the source. +// +// On success, the handler should return 1. If the handler failed, +// the returned value should be 0. On EOF, the handler should set the +// size_read to 0 and return 1. +type yaml_read_handler_t func(parser *yaml_parser_t, buffer []byte) (n int, err error) + +// This structure holds information about a potential simple key. +type yaml_simple_key_t struct { + possible bool // Is a simple key possible? + required bool // Is a simple key required? + token_number int // The number of the token. + mark yaml_mark_t // The position mark. +} + +// The states of the parser. +type yaml_parser_state_t int + +const ( + yaml_PARSE_STREAM_START_STATE yaml_parser_state_t = iota + + yaml_PARSE_IMPLICIT_DOCUMENT_START_STATE // Expect the beginning of an implicit document. + yaml_PARSE_DOCUMENT_START_STATE // Expect DOCUMENT-START. + yaml_PARSE_DOCUMENT_CONTENT_STATE // Expect the content of a document. + yaml_PARSE_DOCUMENT_END_STATE // Expect DOCUMENT-END. + yaml_PARSE_BLOCK_NODE_STATE // Expect a block node. + yaml_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE // Expect a block node or indentless sequence. + yaml_PARSE_FLOW_NODE_STATE // Expect a flow node. + yaml_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE // Expect the first entry of a block sequence. + yaml_PARSE_BLOCK_SEQUENCE_ENTRY_STATE // Expect an entry of a block sequence. + yaml_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE // Expect an entry of an indentless sequence. + yaml_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE // Expect the first key of a block mapping. + yaml_PARSE_BLOCK_MAPPING_KEY_STATE // Expect a block mapping key. + yaml_PARSE_BLOCK_MAPPING_VALUE_STATE // Expect a block mapping value. + yaml_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE // Expect the first entry of a flow sequence. + yaml_PARSE_FLOW_SEQUENCE_ENTRY_STATE // Expect an entry of a flow sequence. + yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE // Expect a key of an ordered mapping. + yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE // Expect a value of an ordered mapping. + yaml_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE // Expect the and of an ordered mapping entry. + yaml_PARSE_FLOW_MAPPING_FIRST_KEY_STATE // Expect the first key of a flow mapping. + yaml_PARSE_FLOW_MAPPING_KEY_STATE // Expect a key of a flow mapping. + yaml_PARSE_FLOW_MAPPING_VALUE_STATE // Expect a value of a flow mapping. + yaml_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE // Expect an empty value of a flow mapping. + 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. + index int // The node id. + mark yaml_mark_t // The anchor mark. +} + +// The parser structure. +// +// All members are internal. Manage the structure using the +// yaml_parser_ family of functions. +type yaml_parser_t struct { + + // Error handling + + error yaml_error_type_t // Error type. + + problem string // Error description. + + // The byte about which the problem occured. + problem_offset int + problem_value int + problem_mark yaml_mark_t + + // The error context. + context string + context_mark yaml_mark_t + + // Reader stuff + + read_handler yaml_read_handler_t // Read handler. + + input_file io.Reader // File input data. + input []byte // String input data. + input_pos int + + eof bool // EOF flag + + buffer []byte // The working buffer. + buffer_pos int // The current position of the buffer. + + unread int // The number of unread characters in the buffer. + + raw_buffer []byte // The raw buffer. + raw_buffer_pos int // The current position of the buffer. + + encoding yaml_encoding_t // The input encoding. + + offset int // The offset of the current position (in bytes). + mark yaml_mark_t // The mark of the current position. + + // Scanner stuff + + stream_start_produced bool // Have we started to scan the input stream? + stream_end_produced bool // Have we reached the end of the input stream? + + flow_level int // The number of unclosed '[' and '{' indicators. + + tokens []yaml_token_t // The tokens queue. + tokens_head int // The head of the tokens queue. + tokens_parsed int // The number of tokens fetched from the queue. + token_available bool // Does the tokens queue contain a token ready for dequeueing. + + indent int // The current indentation level. + indents []int // The indentation levels stack. + + simple_key_allowed bool // May a simple key occur at the current position? + simple_keys []yaml_simple_key_t // The stack of simple keys. + + // Parser stuff + + state yaml_parser_state_t // The current parser state. + states []yaml_parser_state_t // The parser states stack. + marks []yaml_mark_t // The stack of marks. + tag_directives []yaml_tag_directive_t // The list of TAG directives. + + // Dumper stuff + + aliases []yaml_alias_data_t // The alias data. + + document *yaml_document_t // The currently parsed document. +} + +// Emitter Definitions + +// The prototype of a write handler. +// +// The write handler is called when the emitter needs to flush the accumulated +// characters to the output. The handler should write @a size bytes of the +// @a buffer to the output. +// +// @param[in,out] data A pointer to an application data specified by +// yaml_emitter_set_output(). +// @param[in] buffer The buffer with bytes to be written. +// @param[in] size The size of the buffer. +// +// @returns On success, the handler should return @c 1. If the handler failed, +// the returned value should be @c 0. +// +type yaml_write_handler_t func(emitter *yaml_emitter_t, buffer []byte) error + +type yaml_emitter_state_t int + +// The emitter states. +const ( + // Expect STREAM-START. + yaml_EMIT_STREAM_START_STATE yaml_emitter_state_t = iota + + yaml_EMIT_FIRST_DOCUMENT_START_STATE // Expect the first DOCUMENT-START or STREAM-END. + yaml_EMIT_DOCUMENT_START_STATE // Expect DOCUMENT-START or STREAM-END. + yaml_EMIT_DOCUMENT_CONTENT_STATE // Expect the content of a document. + yaml_EMIT_DOCUMENT_END_STATE // Expect DOCUMENT-END. + yaml_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE // Expect the first item of a flow sequence. + yaml_EMIT_FLOW_SEQUENCE_ITEM_STATE // Expect an item of a flow sequence. + yaml_EMIT_FLOW_MAPPING_FIRST_KEY_STATE // Expect the first key of a flow mapping. + yaml_EMIT_FLOW_MAPPING_KEY_STATE // Expect a key of a flow mapping. + yaml_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE // Expect a value for a simple key of a flow mapping. + yaml_EMIT_FLOW_MAPPING_VALUE_STATE // Expect a value of a flow mapping. + yaml_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE // Expect the first item of a block sequence. + yaml_EMIT_BLOCK_SEQUENCE_ITEM_STATE // Expect an item of a block sequence. + yaml_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE // Expect the first key of a block mapping. + yaml_EMIT_BLOCK_MAPPING_KEY_STATE // Expect the key of a block mapping. + yaml_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE // Expect a value for a simple key of a block mapping. + yaml_EMIT_BLOCK_MAPPING_VALUE_STATE // Expect a value of a block mapping. + yaml_EMIT_END_STATE // Expect nothing. +) + +// The emitter structure. +// +// All members are internal. Manage the structure using the @c yaml_emitter_ +// family of functions. +type yaml_emitter_t struct { + + // Error handling + + error yaml_error_type_t // Error type. + problem string // Error description. + + // Writer stuff + + write_handler yaml_write_handler_t // Write handler. + + output_buffer *[]byte // String output data. + output_file io.Writer // File output data. + + buffer []byte // The working buffer. + buffer_pos int // The current position of the buffer. + + raw_buffer []byte // The raw buffer. + raw_buffer_pos int // The current position of the buffer. + + encoding yaml_encoding_t // The stream encoding. + + // Emitter stuff + + canonical bool // If the output is in the canonical style? + best_indent int // The number of indentation spaces. + best_width int // The preferred width of the output lines. + unicode bool // Allow unescaped non-ASCII characters? + line_break yaml_break_t // The preferred line break. + + state yaml_emitter_state_t // The current emitter state. + states []yaml_emitter_state_t // The stack of states. + + events []yaml_event_t // The event queue. + events_head int // The head of the event queue. + + indents []int // The stack of indentation levels. + + tag_directives []yaml_tag_directive_t // The list of tag directives. + + indent int // The current indentation level. + + flow_level int // The current flow level. + + root_context bool // Is it the document root context? + sequence_context bool // Is it a sequence context? + mapping_context bool // Is it a mapping context? + simple_key_context bool // Is it a simple mapping key context? + + line int // The current line. + column int // The current column. + whitespace bool // If the last character was a whitespace? + indention bool // If the last character was an indentation character (' ', '-', '?', ':')? + open_ended bool // If an explicit document end is required? + + // Anchor analysis. + anchor_data struct { + anchor []byte // The anchor value. + alias bool // Is it an alias? + } + + // Tag analysis. + tag_data struct { + handle []byte // The tag handle. + suffix []byte // The tag suffix. + } + + // Scalar analysis. + scalar_data struct { + value []byte // The scalar value. + multiline bool // Does the scalar contain line breaks? + flow_plain_allowed bool // Can the scalar be expessed in the flow plain style? + block_plain_allowed bool // Can the scalar be expressed in the block plain style? + single_quoted_allowed bool // Can the scalar be expressed in the single quoted style? + block_allowed bool // Can the scalar be expressed in the literal or folded styles? + style yaml_scalar_style_t // The output style. + } + + // Dumper stuff + + opened bool // If the stream was already opened? + closed bool // If the stream was already closed? + + // The information associated with the document nodes. + anchors *struct { + references int // The number of references. + anchor int // The anchor id. + serialized bool // If the node has been emitted? + } + + last_anchor_id int // The last assigned anchor id. + + document *yaml_document_t // The currently emitted document. +}
diff --git a/yamlprivateh.go b/yamlprivateh.go new file mode 100644 index 0000000..fd8414b --- /dev/null +++ b/yamlprivateh.go
@@ -0,0 +1,173 @@ +package goyaml + +const ( + // The size of the input raw buffer. + input_raw_buffer_size = 512 + + // The size of the input buffer. + // It should be possible to decode the whole raw buffer. + input_buffer_size = input_raw_buffer_size * 3 + + // The size of the output buffer. + output_buffer_size = 128 + + // The size of the output raw buffer. + // It should be possible to encode the whole output buffer. + output_raw_buffer_size = (output_buffer_size*2 + 2) + + // The size of other stacks and queues. + initial_stack_size = 16 + initial_queue_size = 16 + initial_string_size = 16 +) + +// Check if the character at the specified position is an alphabetical +// character, a digit, '_', or '-'. +func is_alpha(b []byte, i int) bool { + return b[i] >= '0' && b[i] <= '9' || b[i] >= 'A' && b[i] <= 'Z' || b[i] >= 'a' && b[i] <= 'z' || b[i] == '_' || b[i] == '-' +} + +// Check if the character at the specified position is a digit. +func is_digit(b []byte, i int) bool { + return b[i] >= '0' && b[i] <= '9' +} + +// Get the value of a digit. +func as_digit(b []byte, i int) int { + return int(b[i]) - '0' +} + +// Check if the character at the specified position is a hex-digit. +func is_hex(b []byte, i int) bool { + return b[i] >= '0' && b[i] <= '9' || b[i] >= 'A' && b[i] <= 'F' || b[i] >= 'a' && b[i] <= 'f' +} + +// Get the value of a hex-digit. +func as_hex(b []byte, i int) int { + bi := b[i] + if bi >= 'A' && bi <= 'F' { + return int(bi) - 'A' + 10 + } + if bi >= 'a' && bi <= 'f' { + return int(bi) - 'a' + 10 + } + return int(bi) - '0' +} + +// Check if the character is ASCII. +func is_ascii(b []byte, i int) bool { + return b[i] <= 0x7F +} + +// Check if the character at the start of the buffer can be printed unescaped. +func is_printable(b []byte, i int) bool { + return ((b[i] == 0x0A) || // . == #x0A + (b[i] >= 0x20 && b[i] <= 0x7E) || // #x20 <= . <= #x7E + (b[i] == 0xC2 && b[i+1] >= 0xA0) || // #0xA0 <= . <= #xD7FF + (b[i] > 0xC2 && b[i] < 0xED) || + (b[i] == 0xED && b[i+1] < 0xA0) || + (b[i] == 0xEE) || + (b[i] == 0xEF && // #xE000 <= . <= #xFFFD + !(b[i+1] == 0xBB && b[i+2] == 0xBF) && // && . != #xFEFF + !(b[i+1] == 0xBF && (b[i+2] == 0xBE || b[i+2] == 0xBF)))) +} + +// Check if the character at the specified position is NUL. +func is_z(b []byte, i int) bool { + return b[i] == 0x00 +} + +// Check if the beginning of the buffer is a BOM. +func is_bom(b []byte, i int) bool { + return b[0] == 0xEF && b[1] == 0xBB && b[2] == 0xBF +} + +// Check if the character at the specified position is space. +func is_space(b []byte, i int) bool { + return b[i] == ' ' +} + +// Check if the character at the specified position is tab. +func is_tab(b []byte, i int) bool { + return b[i] == '\t' +} + +// Check if the character at the specified position is blank (space or tab). +func is_blank(b []byte, i int) bool { + //return is_space(b, i) || is_tab(b, i) + return b[i] == ' ' || b[i] == '\t' +} + +// Check if the character at the specified position is a line break. +func is_break(b []byte, i int) bool { + return (b[i] == '\r' || // CR (#xD) + b[i] == '\n' || // LF (#xA) + b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9) // PS (#x2029) +} + +func is_crlf(b []byte, i int) bool { + return b[i] == '\r' && b[i+1] == '\n' +} + +// Check if the character is a line break or NUL. +func is_breakz(b []byte, i int) bool { + //return is_break(b, i) || is_z(b, i) + return (// is_break: + b[i] == '\r' || // CR (#xD) + b[i] == '\n' || // LF (#xA) + b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029) + // is_z: + b[i] == 0) +} + +// Check if the character is a line break, space, or NUL. +func is_spacez(b []byte, i int) bool { + //return is_space(b, i) || is_breakz(b, i) + return (// is_space: + b[i] == ' ' || + // is_breakz: + b[i] == '\r' || // CR (#xD) + b[i] == '\n' || // LF (#xA) + b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029) + b[i] == 0) +} + +// Check if the character is a line break, space, tab, or NUL. +func is_blankz(b []byte, i int) bool { + //return is_blank(b, i) || is_breakz(b, i) + return (// is_blank: + b[i] == ' ' || b[i] == '\t' || + // is_breakz: + b[i] == '\r' || // CR (#xD) + b[i] == '\n' || // LF (#xA) + b[i] == 0xC2 && b[i+1] == 0x85 || // NEL (#x85) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA8 || // LS (#x2028) + b[i] == 0xE2 && b[i+1] == 0x80 && b[i+2] == 0xA9 || // PS (#x2029) + b[i] == 0) +} + +// Determine the width of the character. +func width(b byte) int { + // Don't replace these by a switch without first + // confirming that it is being inlined. + if b&0x80 == 0x00 { + return 1 + } + if b&0xE0 == 0xC0 { + return 2 + } + if b&0xF0 == 0xE0 { + return 3 + } + if b&0xF8 == 0xF0 { + return 4 + } + return 0 + +}