dymokomi/luce-browser-html
Source of release 0.5.1
0.5.1 / src / html_syntax / html_tokenizer_3.lucb
#==============================================================================================
#
# html_tokenizer_3 - HTMLTokenizer states: DOCTYPE public and system identifiers
#
# DESCRIPTION:
# Port of Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp (lines 706-1136): the states
# AfterDOCTYPEPublicKeyword to BogusDOCTYPE of next_token, one function each (see
# html_tokenizer_1 for how the macros map to TokenizerStep).
#
#==============================================================================================
# mark: Keywords ================================================================================
# 13.2.5.57 After DOCTYPE public keyword state, https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-keyword-state
func html_tokenizer_after_doctype_public_keyword_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return tokenizer_switch_to(this, .before_doctype_public_identifier)
if on(current_input_character, '"'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).missing_public_identifier = false
return tokenizer_switch_to(this, .doctype_public_identifier_double_quoted)
if on(current_input_character, '\''):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).missing_public_identifier = false
return tokenizer_switch_to(this, .doctype_public_identifier_single_quoted)
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# 13.2.5.63 After DOCTYPE system keyword state, https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-keyword-state
func html_tokenizer_after_doctype_system_keyword_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return tokenizer_switch_to(this, .before_doctype_system_identifier)
if on(current_input_character, '"'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = ak.string_new()
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_double_quoted)
if on(current_input_character, '\''):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = ak.string_new()
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_single_quoted)
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# mark: Before the identifiers ==================================================================
# 13.2.5.58 Before DOCTYPE public identifier state, https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-public-identifier-state
func html_tokenizer_before_doctype_public_identifier_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return TokenizerStep.consume_next
if on(current_input_character, '"'):
html_token_ensure_doctype_data(&this.m_current_token).missing_public_identifier = false
return tokenizer_switch_to(this, .doctype_public_identifier_double_quoted)
if on(current_input_character, '\''):
html_token_ensure_doctype_data(&this.m_current_token).missing_public_identifier = false
return tokenizer_switch_to(this, .doctype_public_identifier_single_quoted)
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# 13.2.5.64 Before DOCTYPE system identifier state, https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-system-identifier-state
func html_tokenizer_before_doctype_system_identifier_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return TokenizerStep.consume_next
if on(current_input_character, '"'):
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_double_quoted)
if on(current_input_character, '\''):
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_single_quoted)
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# mark: Quoted identifiers ======================================================================
# 13.2.5.59 DOCTYPE public identifier (double-quoted) state, https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(double-quoted)-state
func html_tokenizer_doctype_public_identifier_double_quoted_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on(current_input_character, '"'):
html_token_ensure_doctype_data(&this.m_current_token).public_identifier = html_tokenizer_consume_current_builder(this)
return tokenizer_switch_to(this, .after_doctype_public_identifier)
if on(current_input_character, 0):
log_parse_error()
ak.string_builder_append_code_point(&this.m_current_builder, 0xFFFD)
return TokenizerStep.consume_next
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).public_identifier = html_tokenizer_consume_current_builder(this)
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
ak.string_builder_append_code_point(&this.m_current_builder, input_value(current_input_character))
return TokenizerStep.consume_next
# 13.2.5.60 DOCTYPE public identifier (single-quoted) state, https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(single-quoted)-state
func html_tokenizer_doctype_public_identifier_single_quoted_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on(current_input_character, '\''):
html_token_ensure_doctype_data(&this.m_current_token).public_identifier = html_tokenizer_consume_current_builder(this)
return tokenizer_switch_to(this, .after_doctype_public_identifier)
if on(current_input_character, 0):
log_parse_error()
ak.string_builder_append_code_point(&this.m_current_builder, 0xFFFD)
return TokenizerStep.consume_next
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).public_identifier = html_tokenizer_consume_current_builder(this)
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
ak.string_builder_append_code_point(&this.m_current_builder, input_value(current_input_character))
return TokenizerStep.consume_next
# 13.2.5.65 DOCTYPE system identifier (double-quoted) state, https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(double-quoted)-state
func html_tokenizer_doctype_system_identifier_double_quoted_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on(current_input_character, '"'):
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = html_tokenizer_consume_current_builder(this)
return tokenizer_switch_to(this, .after_doctype_system_identifier)
if on(current_input_character, 0):
log_parse_error()
ak.string_builder_append_code_point(&this.m_current_builder, 0xFFFD)
return TokenizerStep.consume_next
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = html_tokenizer_consume_current_builder(this)
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
ak.string_builder_append_code_point(&this.m_current_builder, input_value(current_input_character))
return TokenizerStep.consume_next
# 13.2.5.66 DOCTYPE system identifier (single-quoted) state, https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(single-quoted)-state
func html_tokenizer_doctype_system_identifier_single_quoted_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on(current_input_character, '\''):
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = html_tokenizer_consume_current_builder(this)
return tokenizer_switch_to(this, .after_doctype_system_identifier)
if on(current_input_character, 0):
log_parse_error()
ak.string_builder_append_code_point(&this.m_current_builder, 0xFFFD)
return TokenizerStep.consume_next
if on(current_input_character, '>'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).system_identifier = html_tokenizer_consume_current_builder(this)
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
ak.string_builder_append_code_point(&this.m_current_builder, input_value(current_input_character))
return TokenizerStep.consume_next
# mark: After the identifiers ===================================================================
# 13.2.5.61 After DOCTYPE public identifier state, https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-identifier-state
func html_tokenizer_after_doctype_public_identifier_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return tokenizer_switch_to(this, .between_doctype_public_and_system_identifiers)
if on(current_input_character, '>'):
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on(current_input_character, '"'):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_double_quoted)
if on(current_input_character, '\''):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_single_quoted)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# 13.2.5.62 Between DOCTYPE public and system identifiers state, https://html.spec.whatwg.org/multipage/parsing.html#between-doctype-public-and-system-identifiers-state
func html_tokenizer_between_doctype_public_and_system_identifiers_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return TokenizerStep.consume_next
if on(current_input_character, '>'):
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on(current_input_character, '"'):
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_double_quoted)
if on(current_input_character, '\''):
html_token_ensure_doctype_data(&this.m_current_token).missing_system_identifier = false
return tokenizer_switch_to(this, .doctype_system_identifier_single_quoted)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
return tokenizer_reconsume_in(this, .bogus_doctype)
# 13.2.5.67 After DOCTYPE system identifier state, https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-identifier-state
func html_tokenizer_after_doctype_system_identifier_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on_whitespace(current_input_character):
return TokenizerStep.consume_next
if on(current_input_character, '>'):
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on_eof(current_input_character):
log_parse_error()
html_token_ensure_doctype_data(&this.m_current_token).force_quirks = true
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
log_parse_error()
return tokenizer_reconsume_in(this, .bogus_doctype)
# 13.2.5.68 Bogus DOCTYPE state, https://html.spec.whatwg.org/multipage/parsing.html#bogus-doctype-state
func html_tokenizer_bogus_doctype_state(this: HtmlTokenizer*, current_input_character: u32?, stop_at_insertion_point: HtmlTokenizerStopAtInsertionPoint) -> TokenizerStep:
if on(current_input_character, '>'):
return tokenizer_switch_to_and_emit_current_token(this, .data)
if on(current_input_character, 0):
log_parse_error()
return TokenizerStep.consume_next
if on_eof(current_input_character):
ak.queue_enqueue(&this.m_queued_tokens, html_tokenizer_move_current_token(this))
return tokenizer_emit_eof(this)
return TokenizerStep.consume_next