html-to-markdown 3.4.0.pre.rc.24-aarch64-linux → 3.4.0.pre.rc.30-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: eeb8b4589ba7a98ab2d206913e1d484305864c7ca1d5700f70dbc901ccfd6854
-  data.tar.gz: 1e0e434f693eee13aa4b3d8a5d367bf738d197712cdfd0a526b86e478551d0e7
+  metadata.gz: 0dc08795dc2bd8efce4fa93d0cd32f48820e5e62006a1ec30de1db83a0756aa6
+  data.tar.gz: f69ec46c76e87bedcf33032daff71050bc687c837b184ba434d24a2b8bf8a13c
 SHA512:
-  metadata.gz: d375116ad5a261bfa2ff3aa75244c7df761fae4c2b158b4425bf026636105ad1bc61c5f92d9d3cd593552a13c3280e5b24c98a44c98a80ec1cded15db959a792
-  data.tar.gz: cb0658eb7f815f8ae7e8bbe644396a9f2a7f019e75a1f4d988bc1b03b5cd46400aaec675274026934523eb442ac1678fc6fff9e8f89354dc2a42b47234b2842e
+  metadata.gz: d4c0ec31bc6b61106b1203c2b3d5aaef2900e9bf930ebc8c135258f9d85a70c73397e9a2cdfb087a182d235110f49603beb6c71d8b79c3d058f02f6e8b03a7e8
+  data.tar.gz: 90f3e6a64111b2dd63c8521205ab906ddf0c95d6c718910baf37a64826d52a6103c3efa81cb111e071624439f3451dd22f9d4466621855ea2615c027b4e07abb

data/Steepfile

@@ -1,32 +1,6 @@
 # frozen_string_literal: true
 
-# Steepfile for type checking html-to-markdown Ruby gem
-
 target :lib do
   signature 'sig'
-
   check 'lib'
-
-  configure_code_diagnostics do |hash|
-    hash[Steep::Diagnostic::Ruby::UnannotatedEmptyCollection] = :hint
-    hash[Steep::Diagnostic::Ruby::UnknownConstant] = :hint
-    hash[Steep::Diagnostic::Ruby::NoMethod] = :hint
-  end
-
-  # Configure libraries
-  library 'pathname'
-  library 'open3'
-
-  # Ignore vendor directory
-  ignore 'vendor'
-
-  # Ignore spec directory
-  ignore 'spec'
-
-  # Ignore bin directory
-  ignore 'bin'
-
-  # Ignore internal implementation modules (not public API)
-  ignore 'lib/html_to_markdown/cli.rb'
-  ignore 'lib/html_to_markdown/cli_proxy.rb'
 end

data/lib/html_to_markdown/native.rb

@@ -0,0 +1,21 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:990c47eb4d87f0600f1e6da62d32bf37c84cf430faf31d78f5df7425a93a0f0c
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
+# frozen_string_literal: true
+
+require 'json'
+require 'html_to_markdown_rb'
+
+module HtmlToMarkdown
+  # Re-export all public module functions from the native extension
+  HtmlToMarkdownRs.methods(false).each do |m|
+    define_singleton_method(m) { |*args, **kwargs, &blk| HtmlToMarkdownRs.public_send(m, *args, **kwargs, &blk) }
+  end
+
+  # Re-export all constants (classes, structs, etc.) from the native extension
+  HtmlToMarkdownRs.constants.each do |c|
+    const_set(c, HtmlToMarkdownRs.const_get(c)) unless const_defined?(c)
+  end
+end

data/lib/html_to_markdown/version.rb

@@ -1,5 +1,10 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:bf6359c7254886342acb441f675467dc2b2e926e46a52f7006642ddfd64583f8
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
 # frozen_string_literal: true
 
 module HtmlToMarkdown
-  VERSION = '3.4.0.pre.rc.24'
+  VERSION = '3.4.0.pre.rc.30'
 end

data/lib/html_to_markdown.rb

@@ -1,40 +1,13 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:b671355c68864d5f935b91f875ab29144d9543baad5a955cd926ab9881762a19
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
 # frozen_string_literal: true
 
 require_relative 'html_to_markdown/version'
-require 'html_to_markdown_rb'
-require 'json'
+require_relative 'html_to_markdown/native'
 
-# High-performance HTML to Markdown conversion.
-#
-# @example Simple conversion
-#   HtmlToMarkdown.convert('<h1>Hello</h1>') # => "# Hello\n\n"
-#
-# @example With options
-#   HtmlToMarkdown.convert('<h1>Hello</h1>', heading_style: 'atx')
 module HtmlToMarkdown
-  # Convert HTML to Markdown.
-  #
-  # @param html [String] The HTML content to convert.
-  # @param options [Hash] Optional conversion options.
-  #   Supported keys (all optional):
-  #   - :heading_style       - 'atx', 'atx_closed', 'setext', 'underlined'
-  #   - :code_block_style    - 'backticks', 'tildes', 'indented'
-  #   - :escape_asterisks    - Boolean
-  #   - :escape_underscores  - Boolean
-  #   - :escape_misc         - Boolean
-  #   - :escape_ascii        - Boolean
-  #   - :strip_newlines      - Boolean
-  #   - :keep_inline_images_in - Array of tag names
-  #   - :strip_tags          - Array of tag names to strip
-  #   - :preserve_tags       - Array of tag names to preserve verbatim
-  #   (and more, matching ConversionOptions fields)
-  # @return [String] The converted Markdown content.
-  def self.convert(html, options = {}, visitor = nil)
-    # The Rust FFI expects options as a JSON string; serialise the hash here
-    # rather than constructing a ConversionOptions object, which the generated
-    # FFI layer cannot coerce back to String (see issue #334).
-    opts_json = options.nil? || options.empty? ? nil : options.to_json
-    result = HtmlToMarkdownRs.convert(html, opts_json, visitor)
-    result.content || ''
-  end
+  # Re-export all types and functions from native extension
 end

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:f0d66ccd989cb158aa2206dc4fc0596d3e4060cbb323372db1418e22598b6c21
+# alef:hash:da88db156d77eefe37cfd0ca53ea75c07abbc5d3ebb7ad977060f871af4c9ff3
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # Issues & docs: https://github.com/kreuzberg-dev/alef
@@ -17,7 +17,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::DocumentMetadata;
     # let doc = DocumentMetadata {
     #     title: Some("My Article".to_string()),
     #     description: Some("A great article about Rust".to_string()),
@@ -28,17 +27,17 @@ module HtmlToMarkdown
     # assert_eq!(doc.title, Some("My Article".to_string()));
     # ```
 
-    attr_accessor title: String
-    attr_accessor description: String
-    attr_accessor keywords: Array[String]
-    attr_accessor author: String
-    attr_accessor canonical_url: String
-    attr_accessor base_href: String
-    attr_accessor language: String
-    attr_accessor text_direction: TextDirection
-    attr_accessor open_graph: Hash[String, String]
-    attr_accessor twitter_card: Hash[String, String]
-    attr_accessor meta_tags: Hash[String, String]
+    attr_accessor title: String?
+    attr_accessor description: String?
+    attr_accessor keywords: Array[String]?
+    attr_accessor author: String?
+    attr_accessor canonical_url: String?
+    attr_accessor base_href: String?
+    attr_accessor language: String?
+    attr_accessor text_direction: TextDirection?
+    attr_accessor open_graph: Hash[String, String]?
+    attr_accessor twitter_card: Hash[String, String]?
+    attr_accessor meta_tags: Hash[String, String]?
 
     def initialize: (?title: String, ?description: String, keywords: Array[String], ?author: String, ?canonical_url: String, ?base_href: String, ?language: String, ?text_direction: TextDirection, open_graph: Hash[String, String], twitter_card: Hash[String, String], meta_tags: Hash[String, String]) -> void
   end
@@ -52,7 +51,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::HeaderMetadata;
     # let header = HeaderMetadata {
     #     level: 1,
     #     text: "Main Title".to_string(),
@@ -83,7 +81,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::{LinkMetadata, LinkType};
     # let link = LinkMetadata {
     #     href: "https://example.com".to_string(),
     #     text: "Example".to_string(),
@@ -117,7 +114,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::{ImageMetadata, ImageType};
     # let img = ImageMetadata {
     #     src: "https://example.com/image.jpg".to_string(),
     #     alt: Some("An example image".to_string()),
@@ -149,7 +145,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::{StructuredData, StructuredDataType};
     # let schema = StructuredData {
     #     data_type: StructuredDataType::JsonLd,
     #     raw_json: r#"{"@context":"https://schema.org","@type":"Article"}"#.to_string(),
@@ -175,7 +170,6 @@ module HtmlToMarkdown
     # # Examples
     #
     # ```
-    # # use html_to_markdown_rs::metadata::HtmlMetadata;
     # let metadata = HtmlMetadata {
     #     document: Default::default(),
     #     headers: Vec::new(),
@@ -187,11 +181,11 @@ module HtmlToMarkdown
     # assert!(metadata.headers.is_empty());
     # ```
 
-    attr_accessor document: DocumentMetadata
-    attr_accessor headers: Array[HeaderMetadata]
-    attr_accessor links: Array[LinkMetadata]
-    attr_accessor images: Array[ImageMetadata]
-    attr_accessor structured_data: Array[StructuredData]
+    attr_accessor document: DocumentMetadata?
+    attr_accessor headers: Array[HeaderMetadata]?
+    attr_accessor links: Array[LinkMetadata]?
+    attr_accessor images: Array[ImageMetadata]?
+    attr_accessor structured_data: Array[StructuredData]?
 
     def initialize: (document: DocumentMetadata, headers: Array[HeaderMetadata], links: Array[LinkMetadata], images: Array[ImageMetadata], structured_data: Array[StructuredData]) -> void
   end
@@ -213,48 +207,49 @@ module HtmlToMarkdown
     #     .build();
     # ```
 
-    attr_accessor heading_style: HeadingStyle
-    attr_accessor list_indent_type: ListIndentType
-    attr_accessor list_indent_width: Integer
-    attr_accessor bullets: String
-    attr_accessor strong_em_symbol: String
-    attr_accessor escape_asterisks: bool
-    attr_accessor escape_underscores: bool
-    attr_accessor escape_misc: bool
-    attr_accessor escape_ascii: bool
-    attr_accessor code_language: String
-    attr_accessor autolinks: bool
-    attr_accessor default_title: bool
-    attr_accessor br_in_tables: bool
-    attr_accessor highlight_style: HighlightStyle
-    attr_accessor extract_metadata: bool
-    attr_accessor whitespace_mode: WhitespaceMode
-    attr_accessor strip_newlines: bool
-    attr_accessor wrap: bool
-    attr_accessor wrap_width: Integer
-    attr_accessor convert_as_inline: bool
-    attr_accessor sub_symbol: String
-    attr_accessor sup_symbol: String
-    attr_accessor newline_style: NewlineStyle
-    attr_accessor code_block_style: CodeBlockStyle
-    attr_accessor keep_inline_images_in: Array[String]
-    attr_accessor preprocessing: PreprocessingOptions
-    attr_accessor encoding: String
-    attr_accessor debug: bool
-    attr_accessor strip_tags: Array[String]
-    attr_accessor preserve_tags: Array[String]
-    attr_accessor skip_images: bool
-    attr_accessor link_style: LinkStyle
-    attr_accessor output_format: OutputFormat
-    attr_accessor include_document_structure: bool
-    attr_accessor extract_images: bool
-    attr_accessor max_image_size: Integer
-    attr_accessor capture_svg: bool
-    attr_accessor infer_dimensions: bool
-    attr_accessor max_depth: Integer
-    attr_accessor exclude_selectors: Array[String]
-
-    def initialize: (heading_style: HeadingStyle, list_indent_type: ListIndentType, list_indent_width: Integer, bullets: String, strong_em_symbol: String, escape_asterisks: bool, escape_underscores: bool, escape_misc: bool, escape_ascii: bool, code_language: String, autolinks: bool, default_title: bool, br_in_tables: bool, highlight_style: HighlightStyle, extract_metadata: bool, whitespace_mode: WhitespaceMode, strip_newlines: bool, wrap: bool, wrap_width: Integer, convert_as_inline: bool, sub_symbol: String, sup_symbol: String, newline_style: NewlineStyle, code_block_style: CodeBlockStyle, keep_inline_images_in: Array[String], preprocessing: PreprocessingOptions, encoding: String, debug: bool, strip_tags: Array[String], preserve_tags: Array[String], skip_images: bool, link_style: LinkStyle, output_format: OutputFormat, include_document_structure: bool, extract_images: bool, max_image_size: Integer, capture_svg: bool, infer_dimensions: bool, ?max_depth: Integer, exclude_selectors: Array[String]) -> void
+    attr_accessor heading_style: HeadingStyle?
+    attr_accessor list_indent_type: ListIndentType?
+    attr_accessor list_indent_width: Integer?
+    attr_accessor bullets: String?
+    attr_accessor strong_em_symbol: String?
+    attr_accessor escape_asterisks: bool?
+    attr_accessor escape_underscores: bool?
+    attr_accessor escape_misc: bool?
+    attr_accessor escape_ascii: bool?
+    attr_accessor code_language: String?
+    attr_accessor autolinks: bool?
+    attr_accessor default_title: bool?
+    attr_accessor br_in_tables: bool?
+    attr_accessor highlight_style: HighlightStyle?
+    attr_accessor extract_metadata: bool?
+    attr_accessor whitespace_mode: WhitespaceMode?
+    attr_accessor strip_newlines: bool?
+    attr_accessor wrap: bool?
+    attr_accessor wrap_width: Integer?
+    attr_accessor convert_as_inline: bool?
+    attr_accessor sub_symbol: String?
+    attr_accessor sup_symbol: String?
+    attr_accessor newline_style: NewlineStyle?
+    attr_accessor code_block_style: CodeBlockStyle?
+    attr_accessor keep_inline_images_in: Array[String]?
+    attr_accessor preprocessing: PreprocessingOptions?
+    attr_accessor encoding: String?
+    attr_accessor debug: bool?
+    attr_accessor strip_tags: Array[String]?
+    attr_accessor preserve_tags: Array[String]?
+    attr_accessor skip_images: bool?
+    attr_accessor link_style: LinkStyle?
+    attr_accessor output_format: OutputFormat?
+    attr_accessor include_document_structure: bool?
+    attr_accessor extract_images: bool?
+    attr_accessor max_image_size: Integer?
+    attr_accessor capture_svg: bool?
+    attr_accessor infer_dimensions: bool?
+    attr_accessor max_depth: Integer?
+    attr_accessor exclude_selectors: Array[String]?
+    attr_accessor visitor: VisitorHandle?
+
+    def initialize: (heading_style: HeadingStyle, list_indent_type: ListIndentType, list_indent_width: Integer, bullets: String, strong_em_symbol: String, escape_asterisks: bool, escape_underscores: bool, escape_misc: bool, escape_ascii: bool, code_language: String, autolinks: bool, default_title: bool, br_in_tables: bool, highlight_style: HighlightStyle, extract_metadata: bool, whitespace_mode: WhitespaceMode, strip_newlines: bool, wrap: bool, wrap_width: Integer, convert_as_inline: bool, sub_symbol: String, sup_symbol: String, newline_style: NewlineStyle, code_block_style: CodeBlockStyle, keep_inline_images_in: Array[String], preprocessing: PreprocessingOptions, encoding: String, debug: bool, strip_tags: Array[String], preserve_tags: Array[String], skip_images: bool, link_style: LinkStyle, output_format: OutputFormat, include_document_structure: bool, extract_images: bool, max_image_size: Integer, capture_svg: bool, infer_dimensions: bool, ?max_depth: Integer, exclude_selectors: Array[String], ?visitor: VisitorHandle) -> void
     def apply_update: (ConversionOptionsUpdate update) -> void
     def self.default: () -> ConversionOptions
     def self.builder: () -> ConversionOptionsBuilder
@@ -271,6 +266,7 @@ module HtmlToMarkdown
     def preserve_tags: (Array[String] tags) -> ConversionOptionsBuilder
     def keep_inline_images_in: (Array[String] tags) -> ConversionOptionsBuilder
     def exclude_selectors: (Array[String] selectors) -> ConversionOptionsBuilder
+    def visitor: (?VisitorHandle visitor) -> ConversionOptionsBuilder
     def preprocessing: (PreprocessingOptions preprocessing) -> ConversionOptionsBuilder
     def build: () -> ConversionOptions
   end
@@ -281,57 +277,58 @@ module HtmlToMarkdown
     # Uses `Option<T>` fields for selective updates. Bindings use this to construct
     # options from language-native types. Prefer [`ConversionOptionsBuilder`] for Rust code.
 
-    attr_accessor heading_style: HeadingStyle
-    attr_accessor list_indent_type: ListIndentType
-    attr_accessor list_indent_width: Integer
-    attr_accessor bullets: String
-    attr_accessor strong_em_symbol: String
-    attr_accessor escape_asterisks: bool
-    attr_accessor escape_underscores: bool
-    attr_accessor escape_misc: bool
-    attr_accessor escape_ascii: bool
-    attr_accessor code_language: String
-    attr_accessor autolinks: bool
-    attr_accessor default_title: bool
-    attr_accessor br_in_tables: bool
-    attr_accessor highlight_style: HighlightStyle
-    attr_accessor extract_metadata: bool
-    attr_accessor whitespace_mode: WhitespaceMode
-    attr_accessor strip_newlines: bool
-    attr_accessor wrap: bool
-    attr_accessor wrap_width: Integer
-    attr_accessor convert_as_inline: bool
-    attr_accessor sub_symbol: String
-    attr_accessor sup_symbol: String
-    attr_accessor newline_style: NewlineStyle
-    attr_accessor code_block_style: CodeBlockStyle
-    attr_accessor keep_inline_images_in: Array[String]
-    attr_accessor preprocessing: PreprocessingOptionsUpdate
-    attr_accessor encoding: String
-    attr_accessor debug: bool
-    attr_accessor strip_tags: Array[String]
-    attr_accessor preserve_tags: Array[String]
-    attr_accessor skip_images: bool
-    attr_accessor link_style: LinkStyle
-    attr_accessor output_format: OutputFormat
-    attr_accessor include_document_structure: bool
-    attr_accessor extract_images: bool
-    attr_accessor max_image_size: Integer
-    attr_accessor capture_svg: bool
-    attr_accessor infer_dimensions: bool
+    attr_accessor heading_style: HeadingStyle?
+    attr_accessor list_indent_type: ListIndentType?
+    attr_accessor list_indent_width: Integer?
+    attr_accessor bullets: String?
+    attr_accessor strong_em_symbol: String?
+    attr_accessor escape_asterisks: bool?
+    attr_accessor escape_underscores: bool?
+    attr_accessor escape_misc: bool?
+    attr_accessor escape_ascii: bool?
+    attr_accessor code_language: String?
+    attr_accessor autolinks: bool?
+    attr_accessor default_title: bool?
+    attr_accessor br_in_tables: bool?
+    attr_accessor highlight_style: HighlightStyle?
+    attr_accessor extract_metadata: bool?
+    attr_accessor whitespace_mode: WhitespaceMode?
+    attr_accessor strip_newlines: bool?
+    attr_accessor wrap: bool?
+    attr_accessor wrap_width: Integer?
+    attr_accessor convert_as_inline: bool?
+    attr_accessor sub_symbol: String?
+    attr_accessor sup_symbol: String?
+    attr_accessor newline_style: NewlineStyle?
+    attr_accessor code_block_style: CodeBlockStyle?
+    attr_accessor keep_inline_images_in: Array[String]?
+    attr_accessor preprocessing: PreprocessingOptionsUpdate?
+    attr_accessor encoding: String?
+    attr_accessor debug: bool?
+    attr_accessor strip_tags: Array[String]?
+    attr_accessor preserve_tags: Array[String]?
+    attr_accessor skip_images: bool?
+    attr_accessor link_style: LinkStyle?
+    attr_accessor output_format: OutputFormat?
+    attr_accessor include_document_structure: bool?
+    attr_accessor extract_images: bool?
+    attr_accessor max_image_size: Integer?
+    attr_accessor capture_svg: bool?
+    attr_accessor infer_dimensions: bool?
     attr_accessor max_depth: Integer?
-    attr_accessor exclude_selectors: Array[String]
+    attr_accessor exclude_selectors: Array[String]?
+    attr_accessor visitor: VisitorHandle?
 
-    def initialize: (?heading_style: HeadingStyle, ?list_indent_type: ListIndentType, ?list_indent_width: Integer, ?bullets: String, ?strong_em_symbol: String, ?escape_asterisks: bool, ?escape_underscores: bool, ?escape_misc: bool, ?escape_ascii: bool, ?code_language: String, ?autolinks: bool, ?default_title: bool, ?br_in_tables: bool, ?highlight_style: HighlightStyle, ?extract_metadata: bool, ?whitespace_mode: WhitespaceMode, ?strip_newlines: bool, ?wrap: bool, ?wrap_width: Integer, ?convert_as_inline: bool, ?sub_symbol: String, ?sup_symbol: String, ?newline_style: NewlineStyle, ?code_block_style: CodeBlockStyle, ?keep_inline_images_in: Array[String], ?preprocessing: PreprocessingOptionsUpdate, ?encoding: String, ?debug: bool, ?strip_tags: Array[String], ?preserve_tags: Array[String], ?skip_images: bool, ?link_style: LinkStyle, ?output_format: OutputFormat, ?include_document_structure: bool, ?extract_images: bool, ?max_image_size: Integer, ?capture_svg: bool, ?infer_dimensions: bool, ?max_depth: Integer?, ?exclude_selectors: Array[String]) -> void
+    def initialize: (?heading_style: HeadingStyle, ?list_indent_type: ListIndentType, ?list_indent_width: Integer, ?bullets: String, ?strong_em_symbol: String, ?escape_asterisks: bool, ?escape_underscores: bool, ?escape_misc: bool, ?escape_ascii: bool, ?code_language: String, ?autolinks: bool, ?default_title: bool, ?br_in_tables: bool, ?highlight_style: HighlightStyle, ?extract_metadata: bool, ?whitespace_mode: WhitespaceMode, ?strip_newlines: bool, ?wrap: bool, ?wrap_width: Integer, ?convert_as_inline: bool, ?sub_symbol: String, ?sup_symbol: String, ?newline_style: NewlineStyle, ?code_block_style: CodeBlockStyle, ?keep_inline_images_in: Array[String], ?preprocessing: PreprocessingOptionsUpdate, ?encoding: String, ?debug: bool, ?strip_tags: Array[String], ?preserve_tags: Array[String], ?skip_images: bool, ?link_style: LinkStyle, ?output_format: OutputFormat, ?include_document_structure: bool, ?extract_images: bool, ?max_image_size: Integer, ?capture_svg: bool, ?infer_dimensions: bool, ?max_depth: Integer?, ?exclude_selectors: Array[String], ?visitor: VisitorHandle) -> void
   end
 
   class PreprocessingOptions
     # HTML preprocessing options for document cleanup before conversion.
 
-    attr_accessor enabled: bool
-    attr_accessor preset: PreprocessingPreset
-    attr_accessor remove_navigation: bool
-    attr_accessor remove_forms: bool
+    attr_accessor enabled: bool?
+    attr_accessor preset: PreprocessingPreset?
+    attr_accessor remove_navigation: bool?
+    attr_accessor remove_forms: bool?
 
     def initialize: (enabled: bool, preset: PreprocessingPreset, remove_navigation: bool, remove_forms: bool) -> void
     def apply_update: (PreprocessingOptionsUpdate update) -> void
@@ -347,10 +344,10 @@ module HtmlToMarkdown
     # Only specified fields (Some values) will override existing options; None values leave the
     # corresponding fields unchanged when applied via [`PreprocessingOptions::apply_update`].
 
-    attr_accessor enabled: bool
-    attr_accessor preset: PreprocessingPreset
-    attr_accessor remove_navigation: bool
-    attr_accessor remove_forms: bool
+    attr_accessor enabled: bool?
+    attr_accessor preset: PreprocessingPreset?
+    attr_accessor remove_navigation: bool?
+    attr_accessor remove_forms: bool?
 
     def initialize: (?enabled: bool, ?preset: PreprocessingPreset, ?remove_navigation: bool, ?remove_forms: bool) -> void
   end
@@ -407,12 +404,12 @@ module HtmlToMarkdown
     # assert!(result.warnings.is_empty());
     # ```
 
-    attr_accessor content: String
-    attr_accessor document: DocumentStructure
-    attr_accessor metadata: HtmlMetadata
-    attr_accessor tables: Array[TableData]
-    attr_accessor images: Array[String]
-    attr_accessor warnings: Array[ProcessingWarning]
+    attr_accessor content: String?
+    attr_accessor document: DocumentStructure?
+    attr_accessor metadata: HtmlMetadata?
+    attr_accessor tables: Array[TableData]?
+    attr_accessor images: Array[String]?
+    attr_accessor warnings: Array[ProcessingWarning]?
 
     def initialize: (?content: String, ?document: DocumentStructure, metadata: HtmlMetadata, tables: Array[TableData], images: Array[String], warnings: Array[ProcessingWarning]) -> void
   end
@@ -420,9 +417,9 @@ module HtmlToMarkdown
   class TableGrid
     # A structured table grid with cell-level data including spans.
 
-    attr_accessor rows: Integer
-    attr_accessor cols: Integer
-    attr_accessor cells: Array[GridCell]
+    attr_accessor rows: Integer?
+    attr_accessor cols: Integer?
+    attr_accessor cells: Array[GridCell]?
 
     def initialize: (rows: Integer, cols: Integer, cells: Array[GridCell]) -> void
   end
@@ -458,6 +455,13 @@ module HtmlToMarkdown
     def initialize: (message: String, kind: WarningKind) -> void
   end
 
+  class VisitorHandle
+    # Type alias for a visitor handle (Rc-wrapped `RefCell` for interior mutability).
+    #
+    # This allows visitors to be passed around and shared while still being mutable.
+
+  end
+
   class NodeContext
     # Context information passed to all visitor methods.
     #
@@ -479,112 +483,77 @@ module HtmlToMarkdown
     # Text directionality of document content.
     #
     # Corresponds to the HTML `dir` attribute and `bdi` element directionality.
-
-    LeftToRight: Integer
-    RightToLeft: Integer
-    Auto: Integer
+    type instance = :left_to_right | :right_to_left | :auto
   end
 
   class LinkType
     # Link classification based on href value and document context.
     #
     # Used to categorize links during extraction for filtering and analysis.
-
-    Anchor: Integer
-    Internal: Integer
-    External: Integer
-    Email: Integer
-    Phone: Integer
-    Other: Integer
+    type instance = :anchor | :internal | :external | :email | :phone | :other
   end
 
   class ImageType
     # Image source classification for proper handling and processing.
     #
     # Determines whether an image is embedded (data URI), inline SVG, external, or relative.
-
-    DataUri: Integer
-    InlineSvg: Integer
-    External: Integer
-    Relative: Integer
+    type instance = :data_uri | :inline_svg | :external | :relative
   end
 
   class StructuredDataType
     # Structured data format type.
     #
     # Identifies the schema/format used for structured data markup.
-
-    JsonLd: Integer
-    Microdata: Integer
-    RDFa: Integer
+    type instance = :json_ld | :microdata | :r_d_fa
   end
 
   class PreprocessingPreset
     # HTML preprocessing aggressiveness level.
     #
     # Controls the extent of cleanup performed before conversion. Higher levels remove more elements.
-
-    Minimal: Integer
-    Standard: Integer
-    Aggressive: Integer
+    type instance = :minimal | :standard | :aggressive
   end
 
   class HeadingStyle
     # Heading style options for Markdown output.
     #
     # Controls how headings (h1-h6) are rendered in the output Markdown.
-
-    Underlined: Integer
-    Atx: Integer
-    AtxClosed: Integer
+    type instance = :underlined | :atx | :atx_closed
   end
 
   class ListIndentType
     # List indentation character type.
     #
     # Controls whether list items are indented with spaces or tabs.
-
-    Spaces: Integer
-    Tabs: Integer
+    type instance = :spaces | :tabs
   end
 
   class WhitespaceMode
     # Whitespace handling strategy during conversion.
     #
     # Determines how sequences of whitespace characters (spaces, tabs, newlines) are processed.
-
-    Normalized: Integer
-    Strict: Integer
+    type instance = :normalized | :strict
   end
 
   class NewlineStyle
     # Line break syntax in Markdown output.
     #
     # Controls how soft line breaks (from `<br>` or line breaks in source) are rendered.
-
-    Spaces: Integer
-    Backslash: Integer
+    type instance = :spaces | :backslash
   end
 
   class CodeBlockStyle
     # Code block fence style in Markdown output.
     #
     # Determines how code blocks (`<pre><code>`) are rendered in Markdown.
-
-    Indented: Integer
-    Backticks: Integer
-    Tildes: Integer
+    type instance = :indented | :backticks | :tildes
   end
 
   class HighlightStyle
     # Highlight rendering style for `<mark>` elements.
     #
     # Controls how highlighted text is rendered in Markdown output.
-
-    DoubleEqual: Integer
-    Html: Integer
-    Bold: Integer
-    None: Integer
+    type instance = :double_equal | :html | :bold | :none
   end
 
   class LinkStyle
@@ -592,66 +561,31 @@ module HtmlToMarkdown
     #
     # Controls whether links and images use inline `[text](url)` syntax or
     # reference-style `[text][1]` syntax with definitions collected at the end.
-
-    Inline: Integer
-    Reference: Integer
+    type instance = :inline | :reference
   end
 
   class OutputFormat
     # Output format for conversion.
     #
     # Specifies the target markup language format for the conversion output.
-
-    Markdown: Integer
-    Djot: Integer
-    Plain: Integer
+    type instance = :markdown | :djot | :plain
   end
 
   class NodeContent
     # The semantic content type of a document node.
     #
     # Uses internally tagged representation (`"node_type": "heading"`) for JSON serialization.
-
-    Heading: Integer
-    Paragraph: Integer
-    List: Integer
-    ListItem: Integer
-    Table: Integer
-    Image: Integer
-    Code: Integer
-    Quote: Integer
-    DefinitionList: Integer
-    DefinitionItem: Integer
-    RawBlock: Integer
-    MetadataBlock: Integer
-    Group: Integer
   end
 
   class AnnotationKind
     # The type of an inline text annotation.
     #
     # Uses internally tagged representation (`"annotation_type": "bold"`) for JSON serialization.
-
-    Bold: Integer
-    Italic: Integer
-    Underline: Integer
-    Strikethrough: Integer
-    Code: Integer
-    Subscript: Integer
-    Superscript: Integer
-    Highlight: Integer
-    Link: Integer
   end
 
   class WarningKind
     # Categories of processing warnings.
-
-    ImageExtractionFailed: Integer
-    EncodingFallback: Integer
-    TruncatedInput: Integer
-    MalformedHtml: Integer
-    SanitizationApplied: Integer
-    DepthLimitExceeded: Integer
+    type instance = :image_extraction_failed | :encoding_fallback | :truncated_input | :malformed_html | :sanitization_applied | :depth_limit_exceeded
   end
 
   class NodeType
@@ -659,95 +593,7 @@ module HtmlToMarkdown
     #
     # This enum categorizes all HTML elements that the converter recognizes,
     # providing a coarse-grained classification for visitor dispatch.
-
-    Text: Integer
-    Element: Integer
-    Heading: Integer
-    Paragraph: Integer
-    Div: Integer
-    Blockquote: Integer
-    Pre: Integer
-    Hr: Integer
-    List: Integer
-    ListItem: Integer
-    DefinitionList: Integer
-    DefinitionTerm: Integer
-    DefinitionDescription: Integer
-    Table: Integer
-    TableRow: Integer
-    TableCell: Integer
-    TableHeader: Integer
-    TableBody: Integer
-    TableHead: Integer
-    TableFoot: Integer
-    Link: Integer
-    Image: Integer
-    Strong: Integer
-    Em: Integer
-    Code: Integer
-    Strikethrough: Integer
-    Underline: Integer
-    Subscript: Integer
-    Superscript: Integer
-    Mark: Integer
-    Small: Integer
-    Br: Integer
-    Span: Integer
-    Article: Integer
-    Section: Integer
-    Nav: Integer
-    Aside: Integer
-    Header: Integer
-    Footer: Integer
-    Main: Integer
-    Figure: Integer
-    Figcaption: Integer
-    Time: Integer
-    Details: Integer
-    Summary: Integer
-    Form: Integer
-    Input: Integer
-    Select: Integer
-    Option: Integer
-    Button: Integer
-    Textarea: Integer
-    Label: Integer
-    Fieldset: Integer
-    Legend: Integer
-    Audio: Integer
-    Video: Integer
-    Picture: Integer
-    Source: Integer
-    Iframe: Integer
-    Svg: Integer
-    Canvas: Integer
-    Ruby: Integer
-    Rt: Integer
-    Rp: Integer
-    Abbr: Integer
-    Kbd: Integer
-    Samp: Integer
-    Var: Integer
-    Cite: Integer
-    Q: Integer
-    Del: Integer
-    Ins: Integer
-    Data: Integer
-    Meter: Integer
-    Progress: Integer
-    Output: Integer
-    Template: Integer
-    Slot: Integer
-    Html: Integer
-    Head: Integer
-    Body: Integer
-    Title: Integer
-    Meta: Integer
-    LinkTag: Integer
-    Style: Integer
-    Script: Integer
-    Base: Integer
-    Custom: Integer
+    type instance = :text | :element | :heading | :paragraph | :div | :blockquote | :pre | :hr | :list | :list_item | :definition_list | :definition_term | :definition_description | :table | :table_row | :table_cell | :table_header | :table_body | :table_head | :table_foot | :link | :image | :strong | :em | :code | :strikethrough | :underline | :subscript | :superscript | :mark | :small | :br | :span | :article | :section | :nav | :aside | :header | :footer | :main | :figure | :figcaption | :time | :details | :summary | :form | :input | :select | :option | :button | :textarea | :label | :fieldset | :legend | :audio | :video | :picture | :source | :iframe | :svg | :canvas | :ruby | :rt | :rp | :abbr | :kbd | :samp | :var | :cite | :q | :del | :ins | :data | :meter | :progress | :output | :template | :slot | :html | :head | :body | :title | :meta | :link_tag | :style | :script | :base | :custom
   end
 
   class VisitResult
@@ -756,14 +602,8 @@ module HtmlToMarkdown
     # Allows visitors to control the conversion flow by either proceeding
     # with default behavior, providing custom output, skipping elements,
     # preserving HTML, or signaling errors.
-
-    Continue: Integer
-    Custom: Integer
-    Skip: Integer
-    PreserveHtml: Integer
-    Error: Integer
   end
 
-  def self.convert: (String html, ?ConversionOptions options, ?String visitor) -> ConversionResult
+  def self.convert: (String html, ?ConversionOptions options) -> ConversionResult
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 3.4.0.pre.rc.24
+  version: 3.4.0.pre.rc.30
 platform: aarch64-linux
 authors:
 - Kreuzberg Team
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-05-01 00:00:00.000000000 Z
+date: 2026-05-07 00:00:00.000000000 Z
 dependencies: []
 description: High-performance HTML to Markdown converter
 email:
@@ -19,6 +19,7 @@ files:
 - Steepfile
 - lib/bin/html-to-markdown
 - lib/html_to_markdown.rb
+- lib/html_to_markdown/native.rb
 - lib/html_to_markdown/version.rb
 - lib/html_to_markdown_rb.so
 - sig/html_to_markdown/cli.rbs