HTMLDocumentParser.h 6.2 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163
  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/Parser/HTMLTokenizer.h>
  30. #include <LibWeb/Parser/ListOfActiveFormattingElements.h>
  31. #include <LibWeb/Parser/StackOfOpenElements.h>
  32. #define ENUMERATE_INSERTION_MODES \
  33. __ENUMERATE_INSERTION_MODE(Initial) \
  34. __ENUMERATE_INSERTION_MODE(BeforeHTML) \
  35. __ENUMERATE_INSERTION_MODE(BeforeHead) \
  36. __ENUMERATE_INSERTION_MODE(InHead) \
  37. __ENUMERATE_INSERTION_MODE(InHeadNoscript) \
  38. __ENUMERATE_INSERTION_MODE(AfterHead) \
  39. __ENUMERATE_INSERTION_MODE(InBody) \
  40. __ENUMERATE_INSERTION_MODE(Text) \
  41. __ENUMERATE_INSERTION_MODE(InTable) \
  42. __ENUMERATE_INSERTION_MODE(InTableText) \
  43. __ENUMERATE_INSERTION_MODE(InCaption) \
  44. __ENUMERATE_INSERTION_MODE(InColumnGroup) \
  45. __ENUMERATE_INSERTION_MODE(InTableBody) \
  46. __ENUMERATE_INSERTION_MODE(InRow) \
  47. __ENUMERATE_INSERTION_MODE(InCell) \
  48. __ENUMERATE_INSERTION_MODE(InSelect) \
  49. __ENUMERATE_INSERTION_MODE(InSelectInTable) \
  50. __ENUMERATE_INSERTION_MODE(InTemplate) \
  51. __ENUMERATE_INSERTION_MODE(AfterBody) \
  52. __ENUMERATE_INSERTION_MODE(InFrameset) \
  53. __ENUMERATE_INSERTION_MODE(AfterFrameset) \
  54. __ENUMERATE_INSERTION_MODE(AfterAfterBody) \
  55. __ENUMERATE_INSERTION_MODE(AfterAfterFrameset)
  56. namespace Web {
  57. class HTMLDocumentParser {
  58. public:
  59. HTMLDocumentParser(const StringView& input, const String& encoding);
  60. ~HTMLDocumentParser();
  61. void run(const URL&);
  62. Document& document();
  63. enum class InsertionMode {
  64. #define __ENUMERATE_INSERTION_MODE(mode) mode,
  65. ENUMERATE_INSERTION_MODES
  66. #undef __ENUMERATE_INSERTION_MODE
  67. };
  68. InsertionMode insertion_mode() const { return m_insertion_mode; }
  69. static bool is_special_tag(const FlyString& tag_name);
  70. private:
  71. const char* insertion_mode_name() const;
  72. void handle_initial(HTMLToken&);
  73. void handle_before_html(HTMLToken&);
  74. void handle_before_head(HTMLToken&);
  75. void handle_in_head(HTMLToken&);
  76. void handle_in_head_noscript(HTMLToken&);
  77. void handle_after_head(HTMLToken&);
  78. void handle_in_body(HTMLToken&);
  79. void handle_after_body(HTMLToken&);
  80. void handle_after_after_body(HTMLToken&);
  81. void handle_text(HTMLToken&);
  82. void handle_in_table(HTMLToken&);
  83. void handle_in_table_body(HTMLToken&);
  84. void handle_in_row(HTMLToken&);
  85. void handle_in_cell(HTMLToken&);
  86. void handle_in_table_text(HTMLToken&);
  87. void handle_in_select_in_table(HTMLToken&);
  88. void handle_in_select(HTMLToken&);
  89. void stop_parsing() { m_stop_parsing = true; }
  90. void generate_implied_end_tags(const FlyString& exception = {});
  91. bool stack_of_open_elements_has_element_with_tag_name_in_scope(const FlyString& tag_name);
  92. NonnullRefPtr<Element> create_element_for(HTMLToken&);
  93. RefPtr<Node> find_appropriate_place_for_inserting_node();
  94. Text* find_character_insertion_node();
  95. void flush_character_insertions();
  96. RefPtr<Element> insert_html_element(HTMLToken&);
  97. Element& current_node();
  98. Element& node_before_current_node();
  99. void insert_character(u32 data);
  100. void insert_comment(HTMLToken&);
  101. void reconstruct_the_active_formatting_elements();
  102. void close_a_p_element();
  103. void process_using_the_rules_for(InsertionMode, HTMLToken&);
  104. void parse_generic_raw_text_element(HTMLToken&);
  105. void increment_script_nesting_level();
  106. void decrement_script_nesting_level();
  107. size_t script_nesting_level() const { return m_script_nesting_level; }
  108. void reset_the_insertion_mode_appropriately();
  109. enum AdoptionAgencyAlgorithmOutcome {
  110. DoNothing,
  111. RunAnyOtherEndTagSteps,
  112. };
  113. AdoptionAgencyAlgorithmOutcome run_the_adoption_agency_algorithm(HTMLToken&);
  114. void clear_the_stack_back_to_a_table_context();
  115. void clear_the_stack_back_to_a_table_body_context();
  116. void clear_the_stack_back_to_a_table_row_context();
  117. void close_the_cell();
  118. InsertionMode m_insertion_mode { InsertionMode::Initial };
  119. InsertionMode m_original_insertion_mode { InsertionMode::Initial };
  120. StackOfOpenElements m_stack_of_open_elements;
  121. ListOfActiveFormattingElements m_list_of_active_formatting_elements;
  122. HTMLTokenizer m_tokenizer;
  123. bool m_foster_parenting { false };
  124. bool m_frameset_ok { true };
  125. bool m_parsing_fragment { false };
  126. bool m_scripting_enabled { true };
  127. bool m_invoked_via_document_write { false };
  128. bool m_aborted { false };
  129. bool m_parser_pause_flag { false };
  130. bool m_stop_parsing { false };
  131. size_t m_script_nesting_level { 0 };
  132. RefPtr<Document> m_document;
  133. RefPtr<HTMLHeadElement> m_head_element;
  134. RefPtr<HTMLFormElement> m_form_element;
  135. Vector<HTMLToken> m_pending_table_character_tokens;
  136. RefPtr<Text> m_character_insertion_node;
  137. StringBuilder m_character_insertion_builder;
  138. };
  139. }