html-to-markdown 3.4.0-aarch64-linux

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: '092b4d1ad3d0ea4ac57bfe807760729d6cd676066dd05fc5f7fd3ecfeb3cb1c7'
+  data.tar.gz: d488926fb2483f76d356eb12082bb0f426a21b7d8bde7a981297a14abc7542a7
+SHA512:
+  metadata.gz: 1d1cd3a0b1135303d143374ec4bac13cf69d6dc1448bf29c90431ee7de7cce0e228aa568604575c39b2fb1237a32a48f76aad79ec486739910a7bb907a1d640d
+  data.tar.gz: 0a58dbc37be917e28cbc14f2d97f6ed51db6191ebddf1229ab49fa78f5dcdf2623c67762dff40a99adc44fb0de339317ea10123312f50469e8a865d061998f31

data/Steepfile

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+target :lib do
+  signature 'sig'
+  check 'lib'
+end

data/lib/html_to_markdown/native.rb

@@ -0,0 +1,59 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:b54e7bb2ab55cc6c25c9cac0e62ec66c35fd2d1956ef9ba5e3dc9e7ba5e666a5
+# 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
+
+# Add accessor methods to Hash-based internally-tagged enum instances
+class Hash
+  # Support internally-tagged enum accessors like format.excel, format.email, etc.
+  # Also support direct field access like format.sheet_count
+  # rubocop:disable Metrics/CyclomaticComplexity
+  def method_missing(method_name, *args, &block)
+    # Try symbol key first (how Magnus converts JSON keys)
+    return self[method_name] if key?(method_name)
+
+    # Try string key
+    return self[method_name.to_s] if key?(method_name.to_s)
+
+    # Check if this hash has a 'format_type' field (indicating an internally-tagged enum)
+    format_type = self[:'format_type'] || self['format_type']
+    return super unless format_type
+
+    # If the method name matches the format_type (snake_case), extract and return the variant's wrapped data
+    # Internally-tagged enums store variant data in the '_0' field (from alef's struct variant conversion)
+    # This allows format.excel to return the ExcelMetadata hash with sheet_count, sheet_names, etc.
+    snake_case_method = method_name.to_s.downcase
+    if snake_case_method == format_type.to_s.downcase
+      return self[:'_0'] || self['_0'] || self
+    end
+
+    super
+  end
+  # rubocop:enable Metrics/CyclomaticComplexity
+
+  def respond_to_missing?(method_name, include_private = false)
+    return true if key?(method_name) || key?(method_name.to_s)
+
+    format_type = self[:'format_type'] || self['format_type']
+    return false unless format_type
+
+    snake_case_method = method_name.to_s.downcase
+    snake_case_method == format_type.to_s.downcase || super
+  end
+end

data/lib/html_to_markdown/version.rb

@@ -0,0 +1,10 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:9c58cf63849e82246f03b4fcc3996c264d47f2b2c27e0e8ba6b93eb4a84cb279
+# 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'
+end

data/lib/html_to_markdown.rb

@@ -0,0 +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_relative 'html_to_markdown/native'
+
+module HtmlToMarkdown
+  # Re-export all types and functions from native extension
+end

data/sig/html_to_markdown/cli.rbs

@@ -0,0 +1,24 @@
+module HtmlToMarkdown
+  module CLI
+    # Module method (module_function creates both module and instance methods)
+    #
+    # Run the CLI with the given arguments
+    #
+    # @param argv Command-line arguments (defaults to ARGV)
+    # @param stdout Output stream for standard output
+    # @param stderr Output stream for standard error
+    # @return Exit code (0 for success, non-zero for failure)
+    def self.run: (
+      ?Array[String] argv,
+      ?stdout: IO,
+      ?stderr: IO
+    ) -> Integer
+
+    # Instance method version (created by module_function)
+    def run: (
+      ?Array[String] argv,
+      ?stdout: IO,
+      ?stderr: IO
+    ) -> Integer
+  end
+end

data/sig/html_to_markdown/cli_proxy.rbs

@@ -0,0 +1,48 @@
+module HtmlToMarkdown
+  module CLIProxy
+    # Base error class
+    class Error < StandardError
+    end
+
+    # Error when CLI binary is not found
+    class MissingBinaryError < Error
+    end
+
+    # Error when CLI execution fails
+    class CLIExecutionError < Error
+      attr_reader stderr: String
+      attr_reader status: Integer?
+
+      def initialize: (String message, stderr: String, status: Integer?) -> void
+    end
+
+    # Module methods (module_function creates both module and instance methods)
+
+    # Execute CLI with given arguments
+    def self.call: (Array[String] argv) -> String
+
+    # Find the CLI binary in search paths
+    def self.find_cli_binary: () -> Pathname
+
+    # Get root path of the gem
+    def self.root_path: () -> Pathname
+
+    # Get lib path of the gem
+    def self.lib_path: () -> Pathname
+
+    # Get search paths for CLI binary
+    def self.search_paths: (String binary_name) -> Array[Pathname]
+
+    # Get error message for missing binary
+    def self.missing_binary_message: () -> String
+
+    # Instance method versions (created by module_function)
+
+    def call: (Array[String] argv) -> String
+    def find_cli_binary: () -> Pathname
+    def root_path: () -> Pathname
+    def lib_path: () -> Pathname
+    def search_paths: (String binary_name) -> Array[Pathname]
+    def missing_binary_message: () -> String
+  end
+end

data/sig/open3.rbs

@@ -0,0 +1,12 @@
+# Type signature for Open3 standard library
+module Open3
+  # Execute command and capture stdout, stderr, and status
+  #
+  # @param cmd Command to execute
+  # @param args Command arguments
+  # @return Array containing stdout (String), stderr (String), and status (Process::Status)
+  def self.capture3: (
+    String cmd,
+    *String args
+  ) -> [String, String, Process::Status]
+end

data/sig/types.rbs

@@ -0,0 +1,609 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:da88db156d77eefe37cfd0ca53ea75c07abbc5d3ebb7ad977060f871af4c9ff3
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
+
+module HtmlToMarkdown
+
+  VERSION: String
+
+  class DocumentMetadata
+    # Document-level metadata extracted from `<head>` and top-level elements.
+    #
+    # Contains all metadata typically used by search engines, social media platforms,
+    # and browsers for document indexing and presentation.
+    #
+    # # Examples
+    #
+    # ```
+    # let doc = DocumentMetadata {
+    #     title: Some("My Article".to_string()),
+    #     description: Some("A great article about Rust".to_string()),
+    #     keywords: vec!["rust".to_string(), "programming".to_string()],
+    #     ..Default::default()
+    # };
+    #
+    # 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]?
+
+    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
+
+  class HeaderMetadata
+    # Header element metadata with hierarchy tracking.
+    #
+    # Captures heading elements (h1-h6) with their text content, identifiers,
+    # and position in the document structure.
+    #
+    # # Examples
+    #
+    # ```
+    # let header = HeaderMetadata {
+    #     level: 1,
+    #     text: "Main Title".to_string(),
+    #     id: Some("main-title".to_string()),
+    #     depth: 0,
+    #     html_offset: 145,
+    # };
+    #
+    # assert_eq!(header.level, 1);
+    # assert!(header.is_valid());
+    # ```
+
+    attr_reader level: Integer
+    attr_reader text: String
+    attr_reader id: String
+    attr_reader depth: Integer
+    attr_reader html_offset: Integer
+
+    def initialize: (level: Integer, text: String, ?id: String, depth: Integer, html_offset: Integer) -> void
+    def is_valid: () -> bool
+  end
+
+  class LinkMetadata
+    # Hyperlink metadata with categorization and attributes.
+    #
+    # Represents `<a>` elements with parsed href values, text content, and link type classification.
+    #
+    # # Examples
+    #
+    # ```
+    # let link = LinkMetadata {
+    #     href: "https://example.com".to_string(),
+    #     text: "Example".to_string(),
+    #     title: Some("Visit Example".to_string()),
+    #     link_type: LinkType::External,
+    #     rel: vec!["nofollow".to_string()],
+    #     attributes: Default::default(),
+    # };
+    #
+    # assert_eq!(link.link_type, LinkType::External);
+    # assert_eq!(link.text, "Example");
+    # ```
+
+    attr_reader href: String
+    attr_reader text: String
+    attr_reader title: String
+    attr_reader link_type: LinkType
+    attr_reader rel: Array[String]
+    attr_reader attributes: Hash[String, String]
+
+    def initialize: (href: String, text: String, ?title: String, link_type: LinkType, rel: Array[String], attributes: Hash[String, String]) -> void
+    def self.classify_link: (String href) -> LinkType
+  end
+
+  class ImageMetadata
+    # Image metadata with source and dimensions.
+    #
+    # Captures `<img>` elements and inline `<svg>` elements with metadata
+    # for image analysis and optimization.
+    #
+    # # Examples
+    #
+    # ```
+    # let img = ImageMetadata {
+    #     src: "https://example.com/image.jpg".to_string(),
+    #     alt: Some("An example image".to_string()),
+    #     title: Some("Example".to_string()),
+    #     dimensions: Some((800, 600)),
+    #     image_type: ImageType::External,
+    #     attributes: Default::default(),
+    # };
+    #
+    # assert_eq!(img.image_type, ImageType::External);
+    # ```
+
+    attr_reader src: String
+    attr_reader alt: String
+    attr_reader title: String
+    attr_reader dimensions: Array[Integer]
+    attr_reader image_type: ImageType
+    attr_reader attributes: Hash[String, String]
+
+    def initialize: (src: String, ?alt: String, ?title: String, ?dimensions: Array[Integer], image_type: ImageType, attributes: Hash[String, String]) -> void
+  end
+
+  class StructuredData
+    # Structured data block (JSON-LD, Microdata, or RDFa).
+    #
+    # Represents machine-readable structured data found in the document.
+    # JSON-LD blocks are collected as raw JSON strings for flexibility.
+    #
+    # # Examples
+    #
+    # ```
+    # let schema = StructuredData {
+    #     data_type: StructuredDataType::JsonLd,
+    #     raw_json: r#"{"@context":"https://schema.org","@type":"Article"}"#.to_string(),
+    #     schema_type: Some("Article".to_string()),
+    # };
+    #
+    # assert_eq!(schema.data_type, StructuredDataType::JsonLd);
+    # ```
+
+    attr_reader data_type: StructuredDataType
+    attr_reader raw_json: String
+    attr_reader schema_type: String
+
+    def initialize: (data_type: StructuredDataType, raw_json: String, ?schema_type: String) -> void
+  end
+
+  class HtmlMetadata
+    # Comprehensive metadata extraction result from HTML document.
+    #
+    # Contains all extracted metadata types in a single structure,
+    # suitable for serialization and transmission across language boundaries.
+    #
+    # # Examples
+    #
+    # ```
+    # let metadata = HtmlMetadata {
+    #     document: Default::default(),
+    #     headers: Vec::new(),
+    #     links: Vec::new(),
+    #     images: Vec::new(),
+    #     structured_data: Vec::new(),
+    # };
+    #
+    # 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]?
+
+    def initialize: (document: DocumentMetadata, headers: Array[HeaderMetadata], links: Array[LinkMetadata], images: Array[ImageMetadata], structured_data: Array[StructuredData]) -> void
+  end
+
+  class ConversionOptions
+    # Main conversion options for HTML to Markdown conversion.
+    #
+    # Use [`ConversionOptions::builder()`] to construct, or [`Default::default()`] for defaults.
+    #
+    # # Example
+    #
+    # ```text
+    # use html_to_markdown_rs::ConversionOptions;
+    #
+    # let options = ConversionOptions::builder()
+    #     .heading_style(HeadingStyle::Atx)
+    #     .wrap(true)
+    #     .wrap_width(100)
+    #     .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]?
+    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
+    def self.from_update: (ConversionOptionsUpdate update) -> ConversionOptions
+    def self.from: (ConversionOptionsUpdate update) -> ConversionOptions
+  end
+
+  class ConversionOptionsBuilder
+    # Builder for [`ConversionOptions`].
+    #
+    # All fields start with default values. Call `.build()` to produce the final options.
+
+    def strip_tags: (Array[String] tags) -> ConversionOptionsBuilder
+    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
+
+  class ConversionOptionsUpdate
+    # Partial update for `ConversionOptions`.
+    #
+    # 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 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: 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?
+
+    def initialize: (enabled: bool, preset: PreprocessingPreset, remove_navigation: bool, remove_forms: bool) -> void
+    def apply_update: (PreprocessingOptionsUpdate update) -> void
+    def self.default: () -> PreprocessingOptions
+    def self.from_update: (PreprocessingOptionsUpdate update) -> PreprocessingOptions
+    def self.from: (PreprocessingOptionsUpdate update) -> PreprocessingOptions
+  end
+
+  class PreprocessingOptionsUpdate
+    # Partial update for `PreprocessingOptions`.
+    #
+    # This struct uses `Option<T>` to represent optional fields that can be selectively updated.
+    # 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?
+
+    def initialize: (?enabled: bool, ?preset: PreprocessingPreset, ?remove_navigation: bool, ?remove_forms: bool) -> void
+  end
+
+  class DocumentStructure
+    # A structured document tree representing the semantic content of an HTML document.
+    #
+    # Uses a flat node array with index-based parent/child references for efficient traversal.
+
+    attr_reader nodes: Array[DocumentNode]
+    attr_reader source_format: String
+
+    def initialize: (nodes: Array[DocumentNode], ?source_format: String) -> void
+  end
+
+  class DocumentNode
+    # A single node in the document tree.
+
+    attr_reader id: String
+    attr_reader content: NodeContent
+    attr_reader parent: Integer
+    attr_reader children: Array[Integer]
+    attr_reader annotations: Array[TextAnnotation]
+    attr_reader attributes: Hash[String, String]
+
+    def initialize: (id: String, content: NodeContent, ?parent: Integer, children: Array[Integer], annotations: Array[TextAnnotation], ?attributes: Hash[String, String]) -> void
+  end
+
+  class TextAnnotation
+    # An inline text annotation with byte-range offsets.
+    #
+    # Annotations describe formatting (bold, italic, etc.) and links within a node's text content.
+
+    attr_reader start: Integer
+    attr_reader end: Integer
+    attr_reader kind: AnnotationKind
+
+    def initialize: (start: Integer, end: Integer, kind: AnnotationKind) -> void
+  end
+
+  class ConversionResult
+    # The primary result of HTML conversion and extraction.
+    #
+    # Contains the converted text output, optional structured document tree,
+    # metadata, extracted tables, images, and processing warnings.
+    #
+    # # Example
+    #
+    # ```text
+    # use html_to_markdown_rs::{convert, ConversionOptions};
+    #
+    # let result = convert("<h1>Hello</h1><p>World</p>", None)?;
+    # assert!(result.content.is_some());
+    # 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]?
+
+    def initialize: (?content: String, ?document: DocumentStructure, metadata: HtmlMetadata, tables: Array[TableData], images: Array[String], warnings: Array[ProcessingWarning]) -> void
+  end
+
+  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]?
+
+    def initialize: (rows: Integer, cols: Integer, cells: Array[GridCell]) -> void
+  end
+
+  class GridCell
+    # A single cell in a table grid.
+
+    attr_reader content: String
+    attr_reader row: Integer
+    attr_reader col: Integer
+    attr_reader row_span: Integer
+    attr_reader col_span: Integer
+    attr_reader is_header: bool
+
+    def initialize: (content: String, row: Integer, col: Integer, row_span: Integer, col_span: Integer, is_header: bool) -> void
+  end
+
+  class TableData
+    # A top-level extracted table with both structured data and markdown representation.
+
+    attr_reader grid: TableGrid
+    attr_reader markdown: String
+
+    def initialize: (grid: TableGrid, markdown: String) -> void
+  end
+
+  class ProcessingWarning
+    # A non-fatal warning generated during HTML processing.
+
+    attr_reader message: String
+    attr_reader kind: WarningKind
+
+    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.
+    #
+    # Provides comprehensive metadata about the current node being visited,
+    # including its type, attributes, position in the DOM tree, and parent context.
+
+    attr_reader node_type: NodeType
+    attr_reader tag_name: String
+    attr_reader attributes: Hash[String, String]
+    attr_reader depth: Integer
+    attr_reader index_in_parent: Integer
+    attr_reader parent_tag: String
+    attr_reader is_inline: bool
+
+    def initialize: (node_type: NodeType, tag_name: String, attributes: Hash[String, String], depth: Integer, index_in_parent: Integer, ?parent_tag: String, is_inline: bool) -> void
+  end
+
+  class TextDirection
+    # Text directionality of document content.
+    #
+    # Corresponds to the HTML `dir` attribute and `bdi` element directionality.
+    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.
+    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.
+    type instance = :data_uri | :inline_svg | :external | :relative
+  end
+
+  class StructuredDataType
+    # Structured data format type.
+    #
+    # Identifies the schema/format used for structured data markup.
+    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.
+    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.
+    type instance = :underlined | :atx | :atx_closed
+  end
+
+  class ListIndentType
+    # List indentation character type.
+    #
+    # Controls whether list items are indented with spaces or tabs.
+    type instance = :spaces | :tabs
+  end
+
+  class WhitespaceMode
+    # Whitespace handling strategy during conversion.
+    #
+    # Determines how sequences of whitespace characters (spaces, tabs, newlines) are processed.
+    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.
+    type instance = :spaces | :backslash
+  end
+
+  class CodeBlockStyle
+    # Code block fence style in Markdown output.
+    #
+    # Determines how code blocks (`<pre><code>`) are rendered in Markdown.
+    type instance = :indented | :backticks | :tildes
+  end
+
+  class HighlightStyle
+    # Highlight rendering style for `<mark>` elements.
+    #
+    # Controls how highlighted text is rendered in Markdown output.
+    type instance = :double_equal | :html | :bold | :none
+  end
+
+  class LinkStyle
+    # Link rendering style in Markdown output.
+    #
+    # Controls whether links and images use inline `[text](url)` syntax or
+    # reference-style `[text][1]` syntax with definitions collected at the end.
+    type instance = :inline | :reference
+  end
+
+  class OutputFormat
+    # Output format for conversion.
+    #
+    # Specifies the target markup language format for the conversion output.
+    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.
+  end
+
+  class AnnotationKind
+    # The type of an inline text annotation.
+    #
+    # Uses internally tagged representation (`"annotation_type": "bold"`) for JSON serialization.
+  end
+
+  class WarningKind
+    # Categories of processing warnings.
+    type instance = :image_extraction_failed | :encoding_fallback | :truncated_input | :malformed_html | :sanitization_applied | :depth_limit_exceeded
+  end
+
+  class NodeType
+    # Node type enumeration covering all HTML element types.
+    #
+    # This enum categorizes all HTML elements that the converter recognizes,
+    # providing a coarse-grained classification for visitor dispatch.
+    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
+    # Result of a visitor callback.
+    #
+    # Allows visitors to control the conversion flow by either proceeding
+    # with default behavior, providing custom output, skipping elements,
+    # preserving HTML, or signaling errors.
+  end
+
+  def self.convert: (String html, ?ConversionOptions options) -> ConversionResult
+
+end

metadata

@@ -0,0 +1,54 @@
+--- !ruby/object:Gem::Specification
+name: html-to-markdown
+version: !ruby/object:Gem::Version
+  version: 3.4.0
+platform: aarch64-linux
+authors:
+- Kreuzberg Team
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2026-05-09 00:00:00.000000000 Z
+dependencies: []
+description: High-performance HTML to Markdown converter
+email:
+executables: []
+extensions: []
+extra_rdoc_files: []
+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
+- sig/html_to_markdown/cli_proxy.rbs
+- sig/open3.rbs
+- sig/types.rbs
+homepage: https://github.com/kreuzberg-dev/html-to-markdown
+licenses:
+- MIT
+metadata:
+  keywords: html,markdown,converter
+  rubygems_mfa_required: 'true'
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.2.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.22
+signing_key:
+specification_version: 4
+summary: High-performance HTML to Markdown converter
+test_files: []