HTMLDocumentParser.h 5.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133
  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/StackOfOpenElements.h>
  31. #define ENUMERATE_INSERTION_MODES \
  32. __ENUMERATE_INSERTION_MODE(Initial) \
  33. __ENUMERATE_INSERTION_MODE(BeforeHTML) \
  34. __ENUMERATE_INSERTION_MODE(BeforeHead) \
  35. __ENUMERATE_INSERTION_MODE(InHead) \
  36. __ENUMERATE_INSERTION_MODE(InHeadNoscript) \
  37. __ENUMERATE_INSERTION_MODE(AfterHead) \
  38. __ENUMERATE_INSERTION_MODE(InBody) \
  39. __ENUMERATE_INSERTION_MODE(Text) \
  40. __ENUMERATE_INSERTION_MODE(InTable) \
  41. __ENUMERATE_INSERTION_MODE(InTableText) \
  42. __ENUMERATE_INSERTION_MODE(InCaption) \
  43. __ENUMERATE_INSERTION_MODE(InColumnGroup) \
  44. __ENUMERATE_INSERTION_MODE(InTableBody) \
  45. __ENUMERATE_INSERTION_MODE(InRow) \
  46. __ENUMERATE_INSERTION_MODE(InCell) \
  47. __ENUMERATE_INSERTION_MODE(InSelect) \
  48. __ENUMERATE_INSERTION_MODE(InSelectInTable) \
  49. __ENUMERATE_INSERTION_MODE(InTemplate) \
  50. __ENUMERATE_INSERTION_MODE(AfterBody) \
  51. __ENUMERATE_INSERTION_MODE(InFrameset) \
  52. __ENUMERATE_INSERTION_MODE(AfterFrameset) \
  53. __ENUMERATE_INSERTION_MODE(AfterAfterBody) \
  54. __ENUMERATE_INSERTION_MODE(AfterAfterFrameset)
  55. namespace Web {
  56. class HTMLDocumentParser {
  57. public:
  58. explicit HTMLDocumentParser(const StringView& input);
  59. ~HTMLDocumentParser();
  60. void run(const URL&);
  61. Document& document();
  62. enum class InsertionMode {
  63. #define __ENUMERATE_INSERTION_MODE(mode) mode,
  64. ENUMERATE_INSERTION_MODES
  65. #undef __ENUMERATE_INSERTION_MODE
  66. };
  67. InsertionMode insertion_mode() const { return m_insertion_mode; }
  68. private:
  69. const char* insertion_mode_name() const;
  70. void handle_initial(HTMLToken&);
  71. void handle_before_html(HTMLToken&);
  72. void handle_before_head(HTMLToken&);
  73. void handle_in_head(HTMLToken&);
  74. void handle_in_head_noscript(HTMLToken&);
  75. void handle_after_head(HTMLToken&);
  76. void handle_in_body(HTMLToken&);
  77. void handle_after_body(HTMLToken&);
  78. void handle_after_after_body(HTMLToken&);
  79. void handle_text(HTMLToken&);
  80. void handle_in_table(HTMLToken&);
  81. void generate_implied_end_tags(const FlyString& exception = {});
  82. bool stack_of_open_elements_has_element_with_tag_name_in_scope(const FlyString& tag_name);
  83. NonnullRefPtr<Element> create_element_for(HTMLToken&);
  84. RefPtr<Node> find_appropriate_place_for_inserting_node();
  85. RefPtr<Element> insert_html_element(HTMLToken&);
  86. Element& current_node();
  87. void insert_character(u32 data);
  88. void insert_comment(HTMLToken&);
  89. void reconstruct_the_active_formatting_elements();
  90. void close_a_p_element();
  91. void process_using_the_rules_for(InsertionMode, HTMLToken&);
  92. void parse_generic_raw_text_element(HTMLToken&);
  93. void increment_script_nesting_level();
  94. void decrement_script_nesting_level();
  95. size_t script_nesting_level() const { return m_script_nesting_level; }
  96. void reset_the_insertion_mode_appropriately();
  97. InsertionMode m_insertion_mode { InsertionMode::Initial };
  98. InsertionMode m_original_insertion_mode { InsertionMode::Initial };
  99. StackOfOpenElements m_stack_of_open_elements;
  100. NonnullRefPtrVector<Element> m_list_of_active_formatting_elements;
  101. HTMLTokenizer m_tokenizer;
  102. bool m_foster_parenting { false };
  103. bool m_frameset_ok { true };
  104. bool m_parsing_fragment { false };
  105. bool m_scripting_enabled { true };
  106. bool m_invoked_via_document_write { false };
  107. bool m_parser_pause_flag { false };
  108. size_t m_script_nesting_level { 0 };
  109. RefPtr<Document> m_document;
  110. RefPtr<HTMLHeadElement> m_head_element;
  111. RefPtr<HTMLFormElement> m_form_element;
  112. };
  113. }