html-to-markdown 2.9.2 → 2.11.1

data/sig/html_to_markdown.rbs

@@ -1,139 +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
+# 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

@@ -1,12 +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
+# 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/spec/cli_proxy_spec.rb

@@ -1,42 +1,42 @@
-# frozen_string_literal: true
-
-require 'spec_helper'
-require 'html_to_markdown/cli_proxy'
-require 'html_to_markdown/cli'
-require 'stringio'
-
-RSpec.describe HtmlToMarkdown::CLIProxy do
-  describe '.call' do
-    it 'executes the CLI binary' do
-      begin
-        binary = described_class.find_cli_binary
-      rescue HtmlToMarkdown::CLIProxy::MissingBinaryError
-        skip 'CLI binary not built'
-      end
-
-      expect(binary).to be_file
-
-      output = described_class.call(['--version'])
-      expect(output).to include(HtmlToMarkdown::VERSION)
-    end
-  end
-
-  describe HtmlToMarkdown::CLI do
-    it 'writes CLI output to stdout' do
-      begin
-        HtmlToMarkdown::CLIProxy.find_cli_binary
-      rescue HtmlToMarkdown::CLIProxy::MissingBinaryError
-        skip 'CLI binary not built'
-      end
-
-      stdout = StringIO.new
-      stderr = StringIO.new
-
-      exit_code = described_class.run(['--version'], stdout: stdout, stderr: stderr)
-
-      expect(exit_code).to eq(0)
-      expect(stdout.string).to include(HtmlToMarkdown::VERSION)
-      expect(stderr.string).to be_empty
-    end
-  end
-end
+# frozen_string_literal: true
+
+require 'spec_helper'
+require 'html_to_markdown/cli_proxy'
+require 'html_to_markdown/cli'
+require 'stringio'
+
+RSpec.describe HtmlToMarkdown::CLIProxy do
+  describe '.call' do
+    it 'executes the CLI binary' do
+      begin
+        binary = described_class.find_cli_binary
+      rescue HtmlToMarkdown::CLIProxy::MissingBinaryError
+        skip 'CLI binary not built'
+      end
+
+      expect(binary).to be_file
+
+      output = described_class.call(['--version'])
+      expect(output).to include(HtmlToMarkdown::VERSION)
+    end
+  end
+
+  describe HtmlToMarkdown::CLI do
+    it 'writes CLI output to stdout' do
+      begin
+        HtmlToMarkdown::CLIProxy.find_cli_binary
+      rescue HtmlToMarkdown::CLIProxy::MissingBinaryError
+        skip 'CLI binary not built'
+      end
+
+      stdout = StringIO.new
+      stderr = StringIO.new
+
+      exit_code = described_class.run(['--version'], stdout: stdout, stderr: stderr)
+
+      expect(exit_code).to eq(0)
+      expect(stdout.string).to include(HtmlToMarkdown::VERSION)
+      expect(stderr.string).to be_empty
+    end
+  end
+end

data/spec/convert_spec.rb

@@ -1,38 +1,77 @@
-# frozen_string_literal: true
-
-require 'spec_helper'
-
-RSpec.describe HtmlToMarkdown do
-  describe '.convert' do
-    it 'converts simple headings' do
-      expect(described_class.convert('<h1>Hello</h1>')).to eq("# Hello\n")
-    end
-
-    it 'accepts options hash' do
-      result = described_class.convert(
-        '<h1>Hello</h1>',
-        heading_style: :atx_closed,
-        default_title: true
-      )
-      expect(result).to include('Hello')
-    end
-  end
-
-  describe '.convert_with_inline_images' do
-    it 'returns inline images metadata' do
-      html = '<p><img src="data:image/png;base64,ZmFrZQ==" alt="fake"></p>'
-      extraction = described_class.convert_with_inline_images(html)
-      expect(extraction).to include(:markdown, :inline_images, :warnings)
-      expect(extraction[:inline_images].first[:description]).to eq('fake')
-    end
-  end
-
-  describe '.options' do
-    it 'returns a reusable options handle' do
-      handle = described_class.options(heading_style: :atx_closed)
-      expect(handle).to be_a(HtmlToMarkdown::Options)
-      result = described_class.convert_with_options('<h1>Hello</h1>', handle)
-      expect(result).to include('# Hello #')
-    end
-  end
-end
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe HtmlToMarkdown do
+  describe '.convert' do
+    it 'converts simple headings' do
+      expect(described_class.convert('<h1>Hello</h1>')).to eq("# Hello\n")
+    end
+
+    it 'accepts options hash' do
+      result = described_class.convert(
+        '<h1>Hello</h1>',
+        heading_style: :atx_closed,
+        default_title: true
+      )
+      expect(result).to include('Hello')
+    end
+  end
+
+  describe '.convert_with_inline_images' do
+    it 'returns inline images metadata' do
+      html = '<p><img src="data:image/png;base64,ZmFrZQ==" alt="fake"></p>'
+      extraction = described_class.convert_with_inline_images(html)
+      expect(extraction).to include(:markdown, :inline_images, :warnings)
+      expect(extraction[:inline_images].first[:description]).to eq('fake')
+    end
+  end
+
+  describe '.options' do
+    it 'returns a reusable options handle' do
+      handle = described_class.options(heading_style: :atx_closed)
+      expect(handle).to be_a(HtmlToMarkdown::Options)
+      result = described_class.convert_with_options('<h1>Hello</h1>', handle)
+      expect(result).to include('# Hello #')
+    end
+  end
+
+  describe 'panic handling' do
+    context 'when a Rust panic would occur' do
+      it 'catches panics in convert method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+
+        begin
+          result = described_class.convert(malformed_html)
+          expect(result).to be_a(String)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+
+      it 'catches panics in convert_with_options method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+        handle = described_class.options(heading_style: :atx)
+
+        begin
+          result = described_class.convert_with_options(malformed_html, handle)
+          expect(result).to be_a(String)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+
+      it 'catches panics in convert_with_inline_images method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+
+        begin
+          result = described_class.convert_with_inline_images(malformed_html)
+          expect(result).to be_a(Hash)
+          expect(result).to include(:markdown, :inline_images, :warnings)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -1,10 +1,10 @@
-# frozen_string_literal: true
-
-require 'bundler/setup'
-require 'html_to_markdown'
-
-RSpec.configure do |config|
-  config.expect_with :rspec do |c|
-    c.syntax = :expect
-  end
-end
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'html_to_markdown'
+
+RSpec.configure do |config|
+  config.expect_with :rspec do |c|
+    c.syntax = :expect
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 2.9.2
+  version: 2.11.1
 platform: ruby
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-11-28 00:00:00.000000000 Z
+date: 2025-12-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys