html-to-markdown 2.7.1 → 2.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 92b1acd7c60d7aa288f3a73ee5d5f67e0397719f61879edd0d8fa4d8e3b09601
-  data.tar.gz: 687dabe472299a6007d1cc0462acb8a5103b6a41d63c4987788c8d915bdfe8c1
+  metadata.gz: 00b01de61bb11f04e93d91e1b76d39eba48fc92f86eade0d4161e26cc057d145
+  data.tar.gz: fd4eb68b80988e643bcd5ff26a8090a2f5857d622583e9018d98ff5294c331bb
 SHA512:
-  metadata.gz: c98e25f2a37a2cedec0fa611e0460aaa6f26e7be19b3fba461f9a5a4fa6ebcc8bd76e0698489e1ba0c5e8a8a172596e67cdae9ba8dc0409c7466fb34329adb93
-  data.tar.gz: 8cea9bc49e6156ce2242c155959793bd778f8747aaa6f343a8eec8d14285d503b2ef659d3cc3304b955f614dbc8fe123c7e2b7a878d6ddc965ae0a4350fab443
+  metadata.gz: 25c7819d959377c33d53dc8c2e98a83901f9eed243861ab8f46920cca6461d669cd7aa0069b409f6d9926c5d1cf3c4902a2c03b046bc8ab149efc876f8d22903
+  data.tar.gz: e9af104c04a4ec024c39f7de01a57b4981a43163a9b0e0855e78c897f663a00c78ab0e4bcb0676188e8224407c20257b58a1d1371b005621167147cea905ebcf

data/Gemfile

@@ -9,7 +9,9 @@ gemspec
 group :development, :test do
   gem 'rake-compiler'
   gem 'rb_sys' # provides build tooling when developing locally
+  gem 'rbs', require: false
   gem 'rspec'
   gem 'rubocop', require: false
   gem 'rubocop-rspec', require: false
+  gem 'steep', require: false
 end

data/Gemfile.lock

@@ -1,17 +1,47 @@
 PATH
   remote: .
   specs:
-    html-to-markdown (2.7.1)
+    html-to-markdown (2.7.2)
       rb_sys (>= 0.9, < 1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    activesupport (8.1.1)
+      base64
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.3.1)
+      connection_pool (>= 2.2.5)
+      drb
+      i18n (>= 1.6, < 2)
+      json
+      logger (>= 1.4.2)
+      minitest (>= 5.1)
+      securerandom (>= 0.3)
+      tzinfo (~> 2.0, >= 2.0.5)
+      uri (>= 0.13.1)
     ast (2.4.3)
+    base64 (0.3.0)
+    bigdecimal (3.3.1)
+    concurrent-ruby (1.3.5)
+    connection_pool (2.5.4)
+    csv (3.3.5)
     diff-lcs (1.6.2)
+    drb (2.2.3)
+    ffi (1.17.2)
+    ffi (1.17.2-arm64-darwin)
+    fileutils (1.8.0)
+    i18n (1.14.7)
+      concurrent-ruby (~> 1.0)
     json (2.16.0)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
+    listen (3.9.0)
+      rb-fsevent (~> 0.10, >= 0.10.3)
+      rb-inotify (~> 0.9, >= 0.9.10)
+    logger (1.7.0)
+    minitest (5.26.1)
+    mutex_m (0.3.0)
     parallel (1.27.0)
     parser (3.3.10.0)
       ast (~> 2.4.1)
@@ -23,8 +53,13 @@ GEM
     rake-compiler (1.3.0)
       rake
     rake-compiler-dock (1.9.1)
+    rb-fsevent (0.11.2)
+    rb-inotify (0.11.1)
+      ffi (~> 1.0)
     rb_sys (0.9.117)
       rake-compiler-dock (= 1.9.1)
+    rbs (3.9.5)
+      logger
     regexp_parser (2.11.3)
     rspec (3.13.2)
       rspec-core (~> 3.13.0)
@@ -53,13 +88,37 @@ GEM
     rubocop-ast (1.48.0)
       parser (>= 3.3.7.2)
       prism (~> 1.4)
-    rubocop-rspec (3.7.0)
+    rubocop-rspec (3.8.0)
       lint_roller (~> 1.1)
-      rubocop (~> 1.72, >= 1.72.1)
+      rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
+    securerandom (0.4.1)
+    steep (1.10.0)
+      activesupport (>= 5.1)
+      concurrent-ruby (>= 1.1.10)
+      csv (>= 3.0.9)
+      fileutils (>= 1.1.0)
+      json (>= 2.1.0)
+      language_server-protocol (>= 3.17.0.4, < 4.0)
+      listen (~> 3.0)
+      logger (>= 1.3.0)
+      mutex_m (>= 0.3.0)
+      parser (>= 3.1)
+      rainbow (>= 2.2.2, < 4.0)
+      rbs (~> 3.9)
+      securerandom (>= 0.1)
+      strscan (>= 1.0.0)
+      terminal-table (>= 2, < 5)
+      uri (>= 0.12.0)
+    strscan (3.1.5)
+    terminal-table (4.0.0)
+      unicode-display_width (>= 1.1.1, < 4)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
     unicode-display_width (3.2.0)
       unicode-emoji (~> 4.1)
     unicode-emoji (4.1.0)
+    uri (1.1.1)
 
 PLATFORMS
   arm64-darwin-24
@@ -69,9 +128,11 @@ DEPENDENCIES
   html-to-markdown!
   rake-compiler
   rb_sys
+  rbs
   rspec
   rubocop
   rubocop-rspec
+  steep
 
 RUBY VERSION
    ruby 3.2.9p248

data/Steepfile

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+# Steepfile for type checking html-to-markdown Ruby gem
+
+target :lib do
+  signature "sig"
+
+  check "lib"
+
+  # 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/ext/html-to-markdown-rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "2.7.1"
+version = "2.7.2"
 edition = "2024"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 license = "MIT"

data/lib/html_to_markdown/cli_proxy.rb

@@ -42,11 +42,11 @@ module HtmlToMarkdown
     end
 
     def root_path
-      @root_path ||= Pathname(__dir__).join('../..').expand_path
+      @root_path ||= Pathname(__dir__.to_s).join('../..').expand_path
     end
 
     def lib_path
-      @lib_path ||= Pathname(__dir__).join('..').expand_path
+      @lib_path ||= Pathname(__dir__.to_s).join('..').expand_path
     end
 
     def search_paths(binary_name)

data/lib/html_to_markdown/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HtmlToMarkdown
-  VERSION = '2.7.1'
+  VERSION = '2.7.2'
 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/html_to_markdown.rbs

@@ -0,0 +1,139 @@
+# Type definitions for HtmlToMarkdown Ruby gem
+module HtmlToMarkdown
+  VERSION: String
+
+  # Opaque handle for reusable conversion options
+  class Options
+  end
+
+  type heading_style = :underlined | :atx | :atx_closed
+  type list_indent_type = :spaces | :tabs
+  type highlight_style = :double_equal | :html | :bold | :none
+  type whitespace_mode = :normalized | :strict
+  type newline_style = :spaces | :backslash
+  type code_block_style = :indented | :backticks | :tildes
+  type preprocessing_preset = :minimal | :standard | :aggressive
+
+  type preprocessing_options = {
+    enabled: bool,
+    preset: preprocessing_preset,
+    remove_navigation: bool,
+    remove_forms: bool
+  }
+
+  type conversion_options = {
+    heading_style: heading_style,
+    list_indent_type: list_indent_type,
+    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,
+    hocr_spatial_tables: bool,
+    highlight_style: highlight_style,
+    extract_metadata: bool,
+    whitespace_mode: whitespace_mode,
+    strip_newlines: bool,
+    wrap: bool,
+    wrap_width: Integer,
+    convert_as_inline: bool,
+    sub_symbol: String,
+    sup_symbol: String,
+    newline_style: newline_style,
+    code_block_style: code_block_style,
+    keep_inline_images_in: Array[String],
+    preprocessing: preprocessing_options,
+    encoding: String,
+    debug: bool,
+    strip_tags: Array[String],
+    preserve_tags: Array[String]
+  }
+
+  type inline_image_config = {
+    max_decoded_size_bytes: Integer,
+    filename_prefix: String?,
+    capture_svg: bool,
+    infer_dimensions: bool
+  }
+
+  type inline_image_format = "png" | "jpeg" | "gif" | "bmp" | "webp" | "svg" | String
+
+  type inline_image_source = "img_data_uri" | "svg_element"
+
+  type inline_image = {
+    data: String,
+    format: inline_image_format,
+    filename: String?,
+    description: String?,
+    dimensions: [Integer, Integer]?,
+    source: inline_image_source,
+    attributes: Hash[String, String]
+  }
+
+  type inline_image_warning = {
+    index: Integer,
+    message: String
+  }
+
+  type html_extraction = {
+    markdown: String,
+    inline_images: Array[inline_image],
+    warnings: Array[inline_image_warning]
+  }
+
+  # Native methods (implemented in Rust via Magnus/rb-sys)
+  # These are aliased from the Rust extension and available as both module and instance methods
+  private
+
+  def self.native_convert: (String html, conversion_options? options) -> String
+  def self.native_options: (conversion_options? options_hash) -> Options
+  def self.native_convert_with_options: (String html, Options options_handle) -> String
+  def self.native_convert_with_inline_images: (
+    String html,
+    conversion_options? options,
+    inline_image_config? image_config
+  ) -> html_extraction
+
+  def native_convert: (String html, conversion_options? options) -> String
+  def native_options: (conversion_options? options_hash) -> Options
+  def native_convert_with_options: (String html, Options options_handle) -> String
+  def native_convert_with_inline_images: (
+    String html,
+    conversion_options? options,
+    inline_image_config? image_config
+  ) -> html_extraction
+
+  public
+
+  # Convert HTML to Markdown with optional configuration
+  def self.convert: (String html, ?conversion_options? options) -> String
+
+  # Create a reusable options handle for performance
+  def self.options: (?conversion_options? options_hash) -> Options
+
+  # Convert HTML using a pre-built options handle
+  def self.convert_with_options: (String html, Options options_handle) -> String
+
+  # Convert HTML with inline image extraction
+  def self.convert_with_inline_images: (
+    String html,
+    ?conversion_options? options,
+    ?inline_image_config? image_config
+  ) -> html_extraction
+
+  # Instance method versions (created by module_function)
+  def convert: (String html, ?conversion_options? options) -> String
+  def options: (?conversion_options? options_hash) -> Options
+  def convert_with_options: (String html, Options options_handle) -> String
+  def convert_with_inline_images: (
+    String html,
+    ?conversion_options? options,
+    ?inline_image_config? image_config
+  ) -> html_extraction
+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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 2.7.1
+  version: 2.7.2
 platform: ruby
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-11-12 00:00:00.000000000 Z
+date: 2025-11-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -47,6 +47,7 @@ files:
 - Gemfile.lock
 - README.md
 - Rakefile
+- Steepfile
 - bin/benchmark.rb
 - exe/html-to-markdown
 - ext/html-to-markdown-rb/extconf.rb
@@ -59,6 +60,10 @@ files:
 - lib/html_to_markdown/cli.rb
 - lib/html_to_markdown/cli_proxy.rb
 - lib/html_to_markdown/version.rb
+- sig/html_to_markdown.rbs
+- sig/html_to_markdown/cli.rbs
+- sig/html_to_markdown/cli_proxy.rbs
+- sig/open3.rbs
 - spec/cli_proxy_spec.rb
 - spec/convert_spec.rb
 - spec/spec_helper.rb