HTMLDocumentParser.h 7.7 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194
  1. /*
  2. * Copyright (c) 2020, Andreas Kling <kling@serenityos.org>
  3. * All rights reserved.
  4. *
  5. * Redistribution and use in source and binary forms, with or without
  6. * modification, are permitted provided that the following conditions are met:
  7. *
  8. * 1. Redistributions of source code must retain the above copyright notice, this
  9. * list of conditions and the following disclaimer.
  10. *
  11. * 2. Redistributions in binary form must reproduce the above copyright notice,
  12. * this list of conditions and the following disclaimer in the documentation
  13. * and/or other materials provided with the distribution.
  14. *
  15. * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
  16. * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  17. * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  18. * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
  19. * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  20. * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
  21. * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  22. * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
  23. * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  24. * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  25. */
  26. #pragma once
  27. #include <AK/NonnullRefPtrVector.h>
  28. #include <LibWeb/DOM/Node.h>
  29. #include <LibWeb/HTML/Parser/HTMLTokenizer.h>
  30. #include <LibWeb/HTML/Parser/ListOfActiveFormattingElements.h>
  31. #include <LibWeb/HTML/Parser/StackOfOpenElements.h>
  32. namespace Web::HTML {
  33. #define ENUMERATE_INSERTION_MODES \
  34. __ENUMERATE_INSERTION_MODE(Initial) \
  35. __ENUMERATE_INSERTION_MODE(BeforeHTML) \
  36. __ENUMERATE_INSERTION_MODE(BeforeHead) \
  37. __ENUMERATE_INSERTION_MODE(InHead) \
  38. __ENUMERATE_INSERTION_MODE(InHeadNoscript) \
  39. __ENUMERATE_INSERTION_MODE(AfterHead) \
  40. __ENUMERATE_INSERTION_MODE(InBody) \
  41. __ENUMERATE_INSERTION_MODE(Text) \
  42. __ENUMERATE_INSERTION_MODE(InTable) \
  43. __ENUMERATE_INSERTION_MODE(InTableText) \
  44. __ENUMERATE_INSERTION_MODE(InCaption) \
  45. __ENUMERATE_INSERTION_MODE(InColumnGroup) \
  46. __ENUMERATE_INSERTION_MODE(InTableBody) \
  47. __ENUMERATE_INSERTION_MODE(InRow) \
  48. __ENUMERATE_INSERTION_MODE(InCell) \
  49. __ENUMERATE_INSERTION_MODE(InSelect) \
  50. __ENUMERATE_INSERTION_MODE(InSelectInTable) \
  51. __ENUMERATE_INSERTION_MODE(InTemplate) \
  52. __ENUMERATE_INSERTION_MODE(AfterBody) \
  53. __ENUMERATE_INSERTION_MODE(InFrameset) \
  54. __ENUMERATE_INSERTION_MODE(AfterFrameset) \
  55. __ENUMERATE_INSERTION_MODE(AfterAfterBody) \
  56. __ENUMERATE_INSERTION_MODE(AfterAfterFrameset)
  57. RefPtr<DOM::Document> parse_html_document(const StringView&, const URL&, const String& encoding);
  58. class HTMLDocumentParser {
  59. public:
  60. HTMLDocumentParser(const StringView& input, const String& encoding);
  61. HTMLDocumentParser(const StringView& input, const String& encoding, DOM::Document& existing_document);
  62. ~HTMLDocumentParser();
  63. void run(const URL&);
  64. DOM::Document& document();
  65. static NonnullRefPtrVector<DOM::Node> parse_html_fragment(DOM::Element& context_element, const StringView&);
  66. enum class InsertionMode {
  67. #define __ENUMERATE_INSERTION_MODE(mode) mode,
  68. ENUMERATE_INSERTION_MODES
  69. #undef __ENUMERATE_INSERTION_MODE
  70. };
  71. InsertionMode insertion_mode() const { return m_insertion_mode; }
  72. static bool is_special_tag(const FlyString& tag_name, const FlyString& namespace_);
  73. private:
  74. const char* insertion_mode_name() const;
  75. DOM::QuirksMode which_quirks_mode(const HTMLToken&) const;
  76. void handle_initial(HTMLToken&);
  77. void handle_before_html(HTMLToken&);
  78. void handle_before_head(HTMLToken&);
  79. void handle_in_head(HTMLToken&);
  80. void handle_in_head_noscript(HTMLToken&);
  81. void handle_after_head(HTMLToken&);
  82. void handle_in_body(HTMLToken&);
  83. void handle_after_body(HTMLToken&);
  84. void handle_after_after_body(HTMLToken&);
  85. void handle_text(HTMLToken&);
  86. void handle_in_table(HTMLToken&);
  87. void handle_in_table_body(HTMLToken&);
  88. void handle_in_row(HTMLToken&);
  89. void handle_in_cell(HTMLToken&);
  90. void handle_in_table_text(HTMLToken&);
  91. void handle_in_select_in_table(HTMLToken&);
  92. void handle_in_select(HTMLToken&);
  93. void handle_in_caption(HTMLToken&);
  94. void handle_in_column_group(HTMLToken&);
  95. void handle_in_template(HTMLToken&);
  96. void handle_in_frameset(HTMLToken&);
  97. void handle_after_frameset(HTMLToken&);
  98. void handle_after_after_frameset(HTMLToken&);
  99. void stop_parsing() { m_stop_parsing = true; }
  100. void generate_implied_end_tags(const FlyString& exception = {});
  101. void generate_all_implied_end_tags_thoroughly();
  102. bool stack_of_open_elements_has_element_with_tag_name_in_scope(const FlyString& tag_name);
  103. NonnullRefPtr<DOM::Element> create_element_for(const HTMLToken&, const FlyString& namespace_);
  104. struct AdjustedInsertionLocation {
  105. RefPtr<DOM::Node> parent;
  106. RefPtr<DOM::Node> insert_before_sibling;
  107. };
  108. AdjustedInsertionLocation find_appropriate_place_for_inserting_node();
  109. DOM::Text* find_character_insertion_node();
  110. void flush_character_insertions();
  111. RefPtr<DOM::Element> insert_foreign_element(const HTMLToken&, const FlyString&);
  112. RefPtr<DOM::Element> insert_html_element(const HTMLToken&);
  113. DOM::Element& current_node();
  114. DOM::Element& adjusted_current_node();
  115. DOM::Element& node_before_current_node();
  116. void insert_character(u32 data);
  117. void insert_comment(HTMLToken&);
  118. void reconstruct_the_active_formatting_elements();
  119. void close_a_p_element();
  120. void process_using_the_rules_for(InsertionMode, HTMLToken&);
  121. void process_using_the_rules_for_foreign_content(HTMLToken&);
  122. void parse_generic_raw_text_element(HTMLToken&);
  123. void increment_script_nesting_level();
  124. void decrement_script_nesting_level();
  125. size_t script_nesting_level() const { return m_script_nesting_level; }
  126. void reset_the_insertion_mode_appropriately();
  127. void adjust_mathml_attributes(HTMLToken&);
  128. void adjust_svg_tag_names(HTMLToken&);
  129. void adjust_svg_attributes(HTMLToken&);
  130. void adjust_foreign_attributes(HTMLToken&);
  131. enum AdoptionAgencyAlgorithmOutcome {
  132. DoNothing,
  133. RunAnyOtherEndTagSteps,
  134. };
  135. AdoptionAgencyAlgorithmOutcome run_the_adoption_agency_algorithm(HTMLToken&);
  136. void clear_the_stack_back_to_a_table_context();
  137. void clear_the_stack_back_to_a_table_body_context();
  138. void clear_the_stack_back_to_a_table_row_context();
  139. void close_the_cell();
  140. InsertionMode m_insertion_mode { InsertionMode::Initial };
  141. InsertionMode m_original_insertion_mode { InsertionMode::Initial };
  142. StackOfOpenElements m_stack_of_open_elements;
  143. Vector<InsertionMode> m_stack_of_template_insertion_modes;
  144. ListOfActiveFormattingElements m_list_of_active_formatting_elements;
  145. HTMLTokenizer m_tokenizer;
  146. bool m_foster_parenting { false };
  147. bool m_frameset_ok { true };
  148. bool m_parsing_fragment { false };
  149. bool m_scripting_enabled { true };
  150. bool m_invoked_via_document_write { false };
  151. bool m_aborted { false };
  152. bool m_parser_pause_flag { false };
  153. bool m_stop_parsing { false };
  154. size_t m_script_nesting_level { 0 };
  155. RefPtr<DOM::Document> m_document;
  156. RefPtr<HTMLHeadElement> m_head_element;
  157. RefPtr<HTMLFormElement> m_form_element;
  158. RefPtr<DOM::Element> m_context_element;
  159. Vector<HTMLToken> m_pending_table_character_tokens;
  160. RefPtr<DOM::Text> m_character_insertion_node;
  161. StringBuilder m_character_insertion_builder;
  162. };
  163. }