HTMLParser.h 8.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220
  1. /*
  2. * Copyright (c) 2020-2022, Andreas Kling <kling@serenityos.org>
  3. *
  4. * SPDX-License-Identifier: BSD-2-Clause
  5. */
  6. #pragma once
  7. #include <LibGfx/Color.h>
  8. #include <LibJS/Heap/Cell.h>
  9. #include <LibWeb/DOM/Node.h>
  10. #include <LibWeb/HTML/Parser/HTMLTokenizer.h>
  11. #include <LibWeb/HTML/Parser/ListOfActiveFormattingElements.h>
  12. #include <LibWeb/HTML/Parser/StackOfOpenElements.h>
  13. namespace Web::HTML {
  14. #define ENUMERATE_INSERTION_MODES \
  15. __ENUMERATE_INSERTION_MODE(Initial) \
  16. __ENUMERATE_INSERTION_MODE(BeforeHTML) \
  17. __ENUMERATE_INSERTION_MODE(BeforeHead) \
  18. __ENUMERATE_INSERTION_MODE(InHead) \
  19. __ENUMERATE_INSERTION_MODE(InHeadNoscript) \
  20. __ENUMERATE_INSERTION_MODE(AfterHead) \
  21. __ENUMERATE_INSERTION_MODE(InBody) \
  22. __ENUMERATE_INSERTION_MODE(Text) \
  23. __ENUMERATE_INSERTION_MODE(InTable) \
  24. __ENUMERATE_INSERTION_MODE(InTableText) \
  25. __ENUMERATE_INSERTION_MODE(InCaption) \
  26. __ENUMERATE_INSERTION_MODE(InColumnGroup) \
  27. __ENUMERATE_INSERTION_MODE(InTableBody) \
  28. __ENUMERATE_INSERTION_MODE(InRow) \
  29. __ENUMERATE_INSERTION_MODE(InCell) \
  30. __ENUMERATE_INSERTION_MODE(InSelect) \
  31. __ENUMERATE_INSERTION_MODE(InSelectInTable) \
  32. __ENUMERATE_INSERTION_MODE(InTemplate) \
  33. __ENUMERATE_INSERTION_MODE(AfterBody) \
  34. __ENUMERATE_INSERTION_MODE(InFrameset) \
  35. __ENUMERATE_INSERTION_MODE(AfterFrameset) \
  36. __ENUMERATE_INSERTION_MODE(AfterAfterBody) \
  37. __ENUMERATE_INSERTION_MODE(AfterAfterFrameset)
  38. class HTMLParser final : public JS::Cell {
  39. JS_CELL(HTMLParser, JS::Cell);
  40. JS_DECLARE_ALLOCATOR(HTMLParser);
  41. friend class HTMLTokenizer;
  42. public:
  43. ~HTMLParser();
  44. static JS::NonnullGCPtr<HTMLParser> create_for_scripting(DOM::Document&);
  45. static JS::NonnullGCPtr<HTMLParser> create_with_uncertain_encoding(DOM::Document&, ByteBuffer const& input);
  46. static JS::NonnullGCPtr<HTMLParser> create(DOM::Document&, StringView input, StringView encoding);
  47. void run(HTMLTokenizer::StopAtInsertionPoint = HTMLTokenizer::StopAtInsertionPoint::No);
  48. void run(const URL::URL&, HTMLTokenizer::StopAtInsertionPoint = HTMLTokenizer::StopAtInsertionPoint::No);
  49. static void the_end(JS::NonnullGCPtr<DOM::Document>, JS::GCPtr<HTMLParser> = nullptr);
  50. DOM::Document& document();
  51. enum class AllowDeclarativeShadowRoots {
  52. No,
  53. Yes,
  54. };
  55. static Vector<JS::Handle<DOM::Node>> parse_html_fragment(DOM::Element& context_element, StringView, AllowDeclarativeShadowRoots = AllowDeclarativeShadowRoots::No);
  56. enum class SerializableShadowRoots {
  57. No,
  58. Yes,
  59. };
  60. static String serialize_html_fragment(DOM::Node const&, SerializableShadowRoots, Vector<JS::Handle<DOM::ShadowRoot>> const&, DOM::FragmentSerializationMode = DOM::FragmentSerializationMode::Inner);
  61. enum class InsertionMode {
  62. #define __ENUMERATE_INSERTION_MODE(mode) mode,
  63. ENUMERATE_INSERTION_MODES
  64. #undef __ENUMERATE_INSERTION_MODE
  65. };
  66. InsertionMode insertion_mode() const { return m_insertion_mode; }
  67. static bool is_special_tag(FlyString const& tag_name, Optional<FlyString> const& namespace_);
  68. HTMLTokenizer& tokenizer() { return m_tokenizer; }
  69. // https://html.spec.whatwg.org/multipage/parsing.html#abort-a-parser
  70. void abort();
  71. bool aborted() const { return m_aborted; }
  72. bool stopped() const { return m_stop_parsing; }
  73. size_t script_nesting_level() const { return m_script_nesting_level; }
  74. private:
  75. HTMLParser(DOM::Document&, StringView input, StringView encoding);
  76. HTMLParser(DOM::Document&);
  77. virtual void visit_edges(Cell::Visitor&) override;
  78. char const* insertion_mode_name() const;
  79. DOM::QuirksMode which_quirks_mode(HTMLToken const&) const;
  80. void handle_initial(HTMLToken&);
  81. void handle_before_html(HTMLToken&);
  82. void handle_before_head(HTMLToken&);
  83. void handle_in_head(HTMLToken&);
  84. void handle_in_head_noscript(HTMLToken&);
  85. void handle_after_head(HTMLToken&);
  86. void handle_in_body(HTMLToken&);
  87. void handle_after_body(HTMLToken&);
  88. void handle_after_after_body(HTMLToken&);
  89. void handle_text(HTMLToken&);
  90. void handle_in_table(HTMLToken&);
  91. void handle_in_table_body(HTMLToken&);
  92. void handle_in_row(HTMLToken&);
  93. void handle_in_cell(HTMLToken&);
  94. void handle_in_table_text(HTMLToken&);
  95. void handle_in_select_in_table(HTMLToken&);
  96. void handle_in_select(HTMLToken&);
  97. void handle_in_caption(HTMLToken&);
  98. void handle_in_column_group(HTMLToken&);
  99. void handle_in_template(HTMLToken&);
  100. void handle_in_frameset(HTMLToken&);
  101. void handle_after_frameset(HTMLToken&);
  102. void handle_after_after_frameset(HTMLToken&);
  103. void stop_parsing() { m_stop_parsing = true; }
  104. void generate_implied_end_tags(FlyString const& exception = {});
  105. void generate_all_implied_end_tags_thoroughly();
  106. JS::NonnullGCPtr<DOM::Element> create_element_for(HTMLToken const&, Optional<FlyString> const& namespace_, DOM::Node& intended_parent);
  107. struct AdjustedInsertionLocation {
  108. JS::GCPtr<DOM::Node> parent;
  109. JS::GCPtr<DOM::Node> insert_before_sibling;
  110. };
  111. AdjustedInsertionLocation find_appropriate_place_for_inserting_node(JS::GCPtr<DOM::Element> override_target = nullptr);
  112. void insert_an_element_at_the_adjusted_insertion_location(JS::NonnullGCPtr<DOM::Element>);
  113. DOM::Text* find_character_insertion_node();
  114. void flush_character_insertions();
  115. enum class OnlyAddToElementStack {
  116. No,
  117. Yes,
  118. };
  119. JS::NonnullGCPtr<DOM::Element> insert_foreign_element(HTMLToken const&, Optional<FlyString> const& namespace_, OnlyAddToElementStack);
  120. JS::NonnullGCPtr<DOM::Element> insert_html_element(HTMLToken const&);
  121. DOM::Element& current_node();
  122. DOM::Element& adjusted_current_node();
  123. DOM::Element& node_before_current_node();
  124. void insert_character(u32 data);
  125. void insert_comment(HTMLToken&);
  126. void reconstruct_the_active_formatting_elements();
  127. void close_a_p_element();
  128. void process_using_the_rules_for(InsertionMode, HTMLToken&);
  129. void process_using_the_rules_for_foreign_content(HTMLToken&);
  130. void parse_generic_raw_text_element(HTMLToken&);
  131. void increment_script_nesting_level();
  132. void decrement_script_nesting_level();
  133. void reset_the_insertion_mode_appropriately();
  134. void adjust_mathml_attributes(HTMLToken&);
  135. void adjust_svg_tag_names(HTMLToken&);
  136. void adjust_svg_attributes(HTMLToken&);
  137. static void adjust_foreign_attributes(HTMLToken&);
  138. enum AdoptionAgencyAlgorithmOutcome {
  139. DoNothing,
  140. RunAnyOtherEndTagSteps,
  141. };
  142. AdoptionAgencyAlgorithmOutcome run_the_adoption_agency_algorithm(HTMLToken&);
  143. void clear_the_stack_back_to_a_table_context();
  144. void clear_the_stack_back_to_a_table_body_context();
  145. void clear_the_stack_back_to_a_table_row_context();
  146. void close_the_cell();
  147. InsertionMode m_insertion_mode { InsertionMode::Initial };
  148. InsertionMode m_original_insertion_mode { InsertionMode::Initial };
  149. StackOfOpenElements m_stack_of_open_elements;
  150. Vector<InsertionMode> m_stack_of_template_insertion_modes;
  151. ListOfActiveFormattingElements m_list_of_active_formatting_elements;
  152. HTMLTokenizer m_tokenizer;
  153. bool m_foster_parenting { false };
  154. bool m_frameset_ok { true };
  155. bool m_parsing_fragment { false };
  156. // https://html.spec.whatwg.org/multipage/parsing.html#scripting-flag
  157. // The scripting flag is set to "enabled" if scripting was enabled for the Document with which the parser is associated when the parser was created, and "disabled" otherwise.
  158. bool m_scripting_enabled { true };
  159. bool m_invoked_via_document_write { false };
  160. bool m_aborted { false };
  161. bool m_parser_pause_flag { false };
  162. bool m_stop_parsing { false };
  163. size_t m_script_nesting_level { 0 };
  164. JS::Realm& realm();
  165. JS::GCPtr<DOM::Document> m_document;
  166. JS::GCPtr<HTMLHeadElement> m_head_element;
  167. JS::GCPtr<HTMLFormElement> m_form_element;
  168. JS::GCPtr<DOM::Element> m_context_element;
  169. Vector<HTMLToken> m_pending_table_character_tokens;
  170. JS::GCPtr<DOM::Text> m_character_insertion_node;
  171. StringBuilder m_character_insertion_builder;
  172. };
  173. RefPtr<CSS::StyleValue> parse_dimension_value(StringView);
  174. RefPtr<CSS::StyleValue> parse_nonzero_dimension_value(StringView);
  175. Optional<Color> parse_legacy_color_value(StringView);
  176. }