RubyGems - html-to-markdown - Versions diffs - 3.4.1-aarch64-linux → 3.5.0-aarch64-linux - Mend

html-to-markdown 3.4.1-aarch64-linux → 3.5.0-aarch64-linux

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (13) hide show

checksums.yaml +4 -4
data/Steepfile +10 -2
data/ext/html_to_markdown_rb/Cargo.toml +1 -1
data/ext/html_to_markdown_rb/extconf.rb +5 -5
data/ext/html_to_markdown_rb/native/Cargo.lock +10 -10
data/ext/html_to_markdown_rb/native/Cargo.toml +2 -11
data/ext/html_to_markdown_rb/src/lib.rs +184 -122
data/lib/html_to_markdown/native.rb +1204 -36
data/lib/html_to_markdown/version.rb +2 -2
data/lib/html_to_markdown.rb +3 -3
data/lib/html_to_markdown_rb.so +0 -0
data/sig/types.rbs +12 -273
metadata +16 -2

data/lib/html_to_markdown/version.rb CHANGED Viewed

@@ -1,10 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:ee219b60565c49b67427d4a5c825fcafe3db1061d9c81a06de306dd72495b28b
+# alef:hash:13800159bcd376ddaa37a79cd1dbda8cbefca3a8450e10e9a6510a9576cad1f4
 # 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 = '3.4.1'
+  VERSION = "3.5.0"
 end

data/lib/html_to_markdown.rb CHANGED Viewed

@@ -1,12 +1,12 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:8697ef2add7937bd1fef3fb3a54b34edd14a9764276d0e9f4a53aab7ce9499e0
+# alef:hash:47eeb6be7adffaa90e4383392c292f7b374ce905d84da6b6997e9798053a05a0
 # 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'
+require_relative "html_to_markdown/version"
+require_relative "html_to_markdown/native"
 module HtmlToMarkdown
   # Re-export all types and functions from native extension

data/lib/html_to_markdown_rb.so CHANGED Viewed

Binary file

data/sig/types.rbs CHANGED Viewed

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:7e5aa912785759cbcad9e2b4750726cbd2e1d7d0717eb2078ffde17d2dd6344f
+# alef:hash:86b0e721bec1828e9c4c971cf6a562e12a69f76d8e0f89e96dc5c1b80f4dd75e
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # Issues & docs: https://github.com/kreuzberg-dev/alef
@@ -8,25 +8,9 @@ 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()));
-    # ```
+  type json_value = Hash[String, untyped] | Array[untyped] | String | Integer | Float | bool | nil
+  class DocumentMetadata
     attr_accessor title: String?
     attr_accessor description: String?
     attr_accessor keywords: Array[String]?
@@ -39,30 +23,10 @@ module HtmlToMarkdown
     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
+    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
@@ -74,26 +38,6 @@ module HtmlToMarkdown
   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
@@ -102,30 +46,9 @@ module HtmlToMarkdown
     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
@@ -137,23 +60,6 @@ module HtmlToMarkdown
   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
@@ -162,51 +68,16 @@ module HtmlToMarkdown
   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
+    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?
@@ -220,6 +91,7 @@ module HtmlToMarkdown
     attr_accessor autolinks: bool?
     attr_accessor default_title: bool?
     attr_accessor br_in_tables: bool?
+    attr_accessor compact_tables: bool?
     attr_accessor highlight_style: HighlightStyle?
     attr_accessor extract_metadata: bool?
     attr_accessor whitespace_mode: WhitespaceMode?
@@ -249,34 +121,11 @@ module HtmlToMarkdown
     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 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, ?compact_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 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?
@@ -290,6 +139,7 @@ module HtmlToMarkdown
     attr_accessor autolinks: bool?
     attr_accessor default_title: bool?
     attr_accessor br_in_tables: bool?
+    attr_accessor compact_tables: bool?
     attr_accessor highlight_style: HighlightStyle?
     attr_accessor extract_metadata: bool?
     attr_accessor whitespace_mode: WhitespaceMode?
@@ -319,31 +169,20 @@ module HtmlToMarkdown
     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
+    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, ?compact_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 initialize: (?enabled: bool, ?preset: PreprocessingPreset, ?remove_navigation: bool, ?remove_forms: bool) -> 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?
@@ -353,10 +192,6 @@ module HtmlToMarkdown
   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
@@ -364,8 +199,6 @@ module HtmlToMarkdown
   end
   class DocumentNode
-    # A single node in the document tree.
     attr_reader id: String
     attr_reader content: NodeContent
     attr_reader parent: Integer
@@ -377,10 +210,6 @@ module HtmlToMarkdown
   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
@@ -389,21 +218,6 @@ module HtmlToMarkdown
   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?
@@ -411,22 +225,18 @@ module HtmlToMarkdown
     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
+    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
+    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
@@ -438,8 +248,6 @@ module HtmlToMarkdown
   end
   class TableData
-    # A top-level extracted table with both structured data and markdown representation.
     attr_reader grid: TableGrid
     attr_reader markdown: String
@@ -447,8 +255,6 @@ module HtmlToMarkdown
   end
   class ProcessingWarning
-    # A non-fatal warning generated during HTML processing.
     attr_reader message: String
     attr_reader kind: WarningKind
@@ -456,20 +262,9 @@ module HtmlToMarkdown
   end
   class VisitorHandle
-    # Type alias for a visitor handle (`Arc`-wrapped `Mutex` for thread-safe shared mutation).
-    #
-    # `Send + Sync` so that types embedding a `VisitorHandle` (e.g. `ConversionOptions`)
-    # can be shared across threads — required by callers that stash configs inside
-    # axum/rmcp/tokio Send-bound contexts.
   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]
@@ -482,128 +277,72 @@ module HtmlToMarkdown
   end
   class TextDirection
-    # Text directionality of document content.
-    #
-    # Corresponds to the HTML `dir` attribute and `bdi` element directionality.
     type value = :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 value = :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 value = :data_uri | :inline_svg | :external | :relative
   end
   class StructuredDataType
-    # Structured data format type.
-    #
-    # Identifies the schema/format used for structured data markup.
     type value = :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 value = :minimal | :standard | :aggressive
   end
   class HeadingStyle
-    # Heading style options for Markdown output.
-    #
-    # Controls how headings (h1-h6) are rendered in the output Markdown.
     type value = :underlined | :atx | :atx_closed
   end
   class ListIndentType
-    # List indentation character type.
-    #
-    # Controls whether list items are indented with spaces or tabs.
     type value = :spaces | :tabs
   end
   class WhitespaceMode
-    # Whitespace handling strategy during conversion.
-    #
-    # Determines how sequences of whitespace characters (spaces, tabs, newlines) are processed.
     type value = :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 value = :spaces | :backslash
   end
   class CodeBlockStyle
-    # Code block fence style in Markdown output.
-    #
-    # Determines how code blocks (`<pre><code>`) are rendered in Markdown.
     type value = :indented | :backticks | :tildes
   end
   class HighlightStyle
-    # Highlight rendering style for `<mark>` elements.
-    #
-    # Controls how highlighted text is rendered in Markdown output.
     type value = :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 value = :inline | :reference
   end
   class OutputFormat
-    # Output format for conversion.
-    #
-    # Specifies the target markup language format for the conversion output.
     type value = :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 value = :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 value = :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

metadata CHANGED Viewed

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 3.4.1
+  version: 3.5.0
 platform: aarch64-linux
 authors:
 - Kreuzberg Team
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-05-14 00:00:00.000000000 Z
+date: 2026-05-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: sorbet-runtime
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
 description: High-performance HTML to Markdown converter
 email:
 executables: []