html-to-markdown 2.5.4 → 2.5.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0f6d03456f76e7f7b1157f052c51dc333e1bd68e72a6bb7664f4701f9a592ed2
-  data.tar.gz: e4a09afb52aba7580f9805b91981d96007f04c37fa7ba6059867d0e818e260e0
+  metadata.gz: da35a384f2b4f769a94313ea7611f281e2d85f1c01b8862f28ee721cd6fcdd22
+  data.tar.gz: e956bce4c519a62feb137aa6448b514a6099e75ee978d247846a31c35a466ce0
 SHA512:
-  metadata.gz: d37723f521d0765ff47578457ba24d6636fe5102af2672cc3f8485bef323770cdb8155512378db4025ea47aa4c31146291da960a69ccdacb93a461e4c8e64593
-  data.tar.gz: 31523b5389627bfb1476133f1daa39ae2273d32dfdd72dac0f7927cc45267e41def028ff07bec8a833c567d07d02babda7e8e4e53c7dc63f7490c8ad7dc00481
+  metadata.gz: b84f0b4305bd792948ee2924190143cd2ec0161d84ab0853b50039e214bbff19c6806718c12cb51a086e39557cb70e1650ef2baf4840419ced2e659e7575a28f
+  data.tar.gz: 636fc6ce5662a33ad62f2526a5b6105d755db0a57c6b99ed7c4c519ed0f6f44611be4e51932ccab868e30a6b89b87071678606f454e18d1f17b235546b7c91ee

data/.rubocop.yml

@@ -0,0 +1,29 @@
+plugins:
+  - rubocop-rspec
+
+AllCops:
+  NewCops: enable
+  TargetRubyVersion: 3.2
+  Exclude:
+    - "tmp/**/*"
+    - "vendor/**/*"
+
+Style/Documentation:
+  Enabled: false
+
+Metrics/BlockLength:
+  Exclude:
+    - "spec/**/*"
+    - "*.gemspec"
+
+Metrics/MethodLength:
+  Max: 15
+
+RSpec/MultipleExpectations:
+  Enabled: false
+
+RSpec/ExampleLength:
+  Enabled: false
+
+RSpec/SpecFilePathFormat:
+  Enabled: false

data/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "2.5.4"
+version = "2.5.5"
 edition = "2021"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 license = "MIT"
@@ -21,7 +21,7 @@ crate-type = ["cdylib", "rlib"]
 default = []
 
 [dependencies]
-html-to-markdown-rs = { version = "2.5.4", features = ["inline-images"] }
+html-to-markdown-rs = { version = "2.5.5", features = ["inline-images"] }
 magnus = { git = "https://github.com/matsadler/magnus", rev = "f6db11769efb517427bf7f121f9c32e18b059b38", features = ["rb-sys"] }
 
 [dev-dependencies]

data/Gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+ruby '>= 3.2'
+
+gemspec
+
+group :development, :test do
+  gem 'rake-compiler'
+  gem 'rb_sys' # provides build tooling when developing locally
+  gem 'rspec'
+  gem 'rubocop', require: false
+  gem 'rubocop-rspec', require: false
+end

data/Gemfile.lock

@@ -0,0 +1,80 @@
+PATH
+  remote: .
+  specs:
+    html-to-markdown (2.5.5)
+      rb_sys (>= 0.9, < 1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.3)
+    diff-lcs (1.6.2)
+    json (2.15.2)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    parallel (1.27.0)
+    parser (3.3.10.0)
+      ast (~> 2.4.1)
+      racc
+    prism (1.6.0)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    rake (13.3.0)
+    rake-compiler (1.3.0)
+      rake
+    rake-compiler-dock (1.9.1)
+    rb_sys (0.9.117)
+      rake-compiler-dock (= 1.9.1)
+    regexp_parser (2.11.3)
+    rspec (3.13.2)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.6)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.6)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.6)
+    rubocop (1.81.6)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.47.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.47.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    rubocop-rspec (3.7.0)
+      lint_roller (~> 1.1)
+      rubocop (~> 1.72, >= 1.72.1)
+    ruby-progressbar (1.13.0)
+    unicode-display_width (3.2.0)
+      unicode-emoji (~> 4.1)
+    unicode-emoji (4.1.0)
+
+PLATFORMS
+  arm64-darwin-24
+  ruby
+
+DEPENDENCIES
+  html-to-markdown!
+  rake-compiler
+  rb_sys
+  rspec
+  rubocop
+  rubocop-rspec
+
+RUBY VERSION
+   ruby 3.2.9p248
+
+BUNDLED WITH
+   2.5.12

data/README.md

@@ -156,7 +156,7 @@ You can also call the CLI binary directly for scripting:
 
 ```ruby
 HtmlToMarkdown::CLIProxy.call(['--version'])
-# => "html-to-markdown 2.5.4"
+# => "html-to-markdown 2.5.5"
 ```
 
 Rebuild the CLI locally if you see `CLI binary not built` during tests:

data/Rakefile

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rb_sys/extensiontask'
+require 'rspec/core/rake_task'
+
+GEMSPEC = Gem::Specification.load(File.expand_path('html-to-markdown-rb.gemspec', __dir__))
+
+RbSys::ExtensionTask.new('html-to-markdown-rb', GEMSPEC) do |ext|
+  ext.lib_dir = 'lib'
+  ext.cross_compile = true
+  ext.cross_platform = %w[
+    x86_64-linux
+    x86_64-darwin
+    arm64-darwin
+    x64-mingw32
+  ]
+end
+
+RSpec::Core::RakeTask.new(:spec)
+
+task spec: :compile
+task default: :spec

data/extconf.rb

@@ -5,7 +5,7 @@ require 'rb_sys/mkmf'
 require 'rbconfig'
 
 if RbConfig::CONFIG['host_os'] =~ /mswin|mingw/
-  devkit = ENV['RI_DEVKIT']
+  devkit = ENV.fetch('RI_DEVKIT', nil)
   prefix = ENV['MSYSTEM_PREFIX'] || '/ucrt64'
 
   if devkit

data/html-to-markdown-rb.gemspec

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+require_relative 'lib/html_to_markdown/version'
+
+readme_path = File.expand_path('README.md', __dir__)
+readme_body = File.read(readme_path, encoding: 'UTF-8')
+
+Gem::Specification.new do |spec|
+  spec.name          = 'html-to-markdown'
+  spec.version       = HtmlToMarkdown::VERSION
+  spec.authors       = ["Na'aman Hirschfeld"]
+  spec.email         = ['nhirschfeld@gmail.com']
+
+  spec.summary       = 'Blazing-fast HTML to Markdown conversion for Ruby, powered by Rust.'
+  spec.description   = readme_body
+  spec.homepage      = 'https://github.com/Goldziher/html-to-markdown'
+  spec.license       = 'MIT'
+
+  spec.required_ruby_version = Gem::Requirement.new('>= 3.2')
+
+  spec.bindir = 'exe'
+  spec.executables = ['html-to-markdown']
+  spec.require_paths = ['lib']
+
+  spec.files = `git ls-files -z`.split("\x0")
+  spec.extra_rdoc_files = ['README.md']
+
+  spec.extensions = ['extconf.rb']
+
+  spec.add_dependency 'rb_sys', '>= 0.9', '< 1.0'
+  spec.metadata['rubygems_mfa_required'] = 'true'
+  spec.metadata['homepage_uri'] = 'https://github.com/Goldziher/html-to-markdown'
+  spec.metadata['source_code_uri'] = 'https://github.com/Goldziher/html-to-markdown'
+  spec.metadata['bug_tracker_uri'] = 'https://github.com/Goldziher/html-to-markdown/issues'
+  spec.metadata['changelog_uri'] = 'https://github.com/Goldziher/html-to-markdown/releases'
+  spec.metadata['documentation_uri'] = 'https://github.com/Goldziher/html-to-markdown/blob/main/README.md'
+end

data/lib/html_to_markdown/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HtmlToMarkdown
-  VERSION = '2.5.4'
+  VERSION = '2.5.5'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 2.5.4
+  version: 2.5.5
 platform: ruby
 authors:
 - Na'aman Hirschfeld
@@ -30,21 +30,97 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '1.0'
-description: |-
-  html-to-markdown wraps our ultra-fast Rust converter with a Ruby-native API via Magnus and rb-sys.
-  Enjoy identical output to the Python, Node, and WASM bindings, a bundled CLI proxy, and seamless cross-platform installs.
+description: "# html-to-markdown-rb\n\nBlazing-fast HTML → Markdown conversion for
+  Ruby, powered by the same Rust engine used by our Python, Node.js, and WebAssembly
+  packages. Ship identical Markdown across every runtime while enjoying native extension
+  performance.\n\n[![Crates.io](https://img.shields.io/crates/v/html-to-markdown-rs.svg)](https://crates.io/crates/html-to-markdown-rs)\n[![npm
+  version](https://badge.fury.io/js/html-to-markdown-node.svg)](https://www.npmjs.com/package/html-to-markdown-node)\n[![PyPI
+  version](https://badge.fury.io/py/html-to-markdown.svg)](https://pypi.org/project/html-to-markdown/)\n[![Gem
+  Version](https://badge.fury.io/rb/html-to-markdown.svg)](https://rubygems.org/gems/html-to-markdown)\n[![License:
+  MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE)\n\n##
+  Features\n\n- ⚡ **Rust-fast**: Ruby bindings around a highly optimised Rust core
+  (60‑80× faster than BeautifulSoup-based converters).\n- \U0001F501 **Identical output**:
+  Shares logic with the Python wheels, npm bindings, WASM package, and CLI — consistent
+  Markdown everywhere.\n- ⚙️ **Rich configuration**: Control heading styles, list
+  indentation, whitespace handling, HTML preprocessing, and more.\n- \U0001F5BC️ **Inline
+  image extraction**: Pull out embedded images (PNG/JPEG/SVG/data URIs) alongside
+  Markdown.\n- \U0001F9F0 **Bundled CLI proxy**: Call the Rust CLI straight from Ruby
+  or shell scripts.\n- \U0001F6E0️ **First-class Rails support**: Works with `Gem.win_platform?`
+  builds, supports Trusted Publishing, and compiles on install if no native gem matches.\n\n##
+  Installation\n\n```bash\nbundle add html-to-markdown\n# or\ngem install html-to-markdown\n```\n\nAdd
+  the gem to your project and Bundler will compile the native Rust extension on first
+  install.\n\n### Requirements\n\n- Ruby **3.2+** (Magnus relies on the fiber scheduler
+  APIs added in 3.2)\n- Rust toolchain **1.85+** with Cargo available on your `$PATH`\n-
+  Ruby development headers (`ruby-dev`, `ruby-devel`, or the platform equivalent)\n\n**Windows**:
+  install [RubyInstaller with MSYS2](https://rubyinstaller.org/) (UCRT64). Run once:\n\n```powershell\nridk
+  exec pacman -S --needed --noconfirm base-devel mingw-w64-ucrt-x86_64-toolchain\n```\n\nThis
+  provides the standard headers (including `strings.h`) required for the bindgen step.\n\n##
+  Performance Snapshot\n\nApple M4 • Real Wikipedia documents • `HtmlToMarkdown.convert`
+  (Ruby)\n\n| Document            | Size  | Latency | Throughput | Docs/sec |\n| -------------------
+  | ----- | ------- | ---------- | -------- |\n| Lists (Timeline)    | 129KB | 0.69ms
+  \ | 187 MB/s   | 1,450    |\n| Tables (Countries)  | 360KB | 2.19ms  | 164 MB/s
+  \  | 456      |\n| Mixed (Python wiki) | 656KB | 4.88ms  | 134 MB/s   | 205      |\n\n>
+  Same core, same benchmarks: the Ruby extension stays within single-digit % of the
+  Rust CLI and mirrors the Python/Node numbers.\n\n## Quick Start\n\n```ruby\nrequire
+  'html_to_markdown'\n\nhtml = <<~HTML\n  <h1>Welcome</h1>\n  <p>This is <strong>Rust-fast</strong>
+  conversion!</p>\n  <ul>\n    <li>Native extension</li>\n    <li>Identical output
+  across languages</li>\n  </ul>\nHTML\n\nmarkdown = HtmlToMarkdown.convert(html)\nputs
+  markdown\n# # Welcome\n#\n# This is **Rust-fast** conversion!\n#\n# - Native extension\n#
+  - Identical output across languages\n```\n\n## API\n\n### Conversion Options\n\nPass
+  a Ruby hash (string or symbol keys) to tweak rendering. Every option maps one-for-one
+  with the Rust/Python/Node APIs.\n\n```ruby\nrequire 'html_to_markdown'\n\nmarkdown
+  = HtmlToMarkdown.convert(\n  '<pre><code class=\"language-ruby\">puts \"hi\"</code></pre>',\n
+  \ heading_style: :atx,\n  code_block_style: :fenced,\n  bullets: '*+-',\n  list_indent_type:
+  :spaces,\n  list_indent_width: 2,\n  whitespace_mode: :normalized,\n  highlight_style:
+  :double_equal\n)\n\nputs markdown\n```\n\n### HTML Preprocessing\n\nClean up scraped
+  HTML (navigation, forms, malformed markup) before conversion:\n\n```ruby\nrequire
+  'html_to_markdown'\n\nmarkdown = HtmlToMarkdown.convert(\n  html,\n  preprocessing:
+  {\n    enabled: true,\n    preset: :aggressive, # :minimal, :standard, :aggressive\n
+  \   remove_navigation: true,\n    remove_forms: true\n  }\n)\n```\n\n### Inline
+  Images\n\nExtract inline binary data (data URIs, SVG) together with the converted
+  Markdown.\n\n```ruby\nrequire 'html_to_markdown'\n\nresult = HtmlToMarkdown.convert_with_inline_images(\n
+  \ '<img src=\"data:image/png;base64,iVBORw0...\" alt=\"Pixel\">',\n  image_config:
+  {\n    max_decoded_size_bytes: 1 * 1024 * 1024,\n    infer_dimensions: true,\n    filename_prefix:
+  'img_',\n    capture_svg: true\n  }\n)\n\nputs result.markdown\nresult.inline_images.each
+  do |img|\n  puts \"#{img.filename} -> #{img.format} (#{img.data.bytesize} bytes)\"\nend\n```\n\n##
+  CLI\n\nThe gem bundles a small proxy for the Rust CLI binary. Use it when you need
+  parity with the standalone `html-to-markdown` executable.\n\n```ruby\nrequire 'html_to_markdown/cli'\n\nHtmlToMarkdown::CLI.run(%w[--heading-style
+  atx input.html], stdout: $stdout)\n# => writes converted Markdown to STDOUT\n```\n\nYou
+  can also call the CLI binary directly for scripting:\n\n```ruby\nHtmlToMarkdown::CLIProxy.call(['--version'])\n#
+  => \"html-to-markdown 2.5.5\"\n```\n\nRebuild the CLI locally if you see `CLI binary
+  not built` during tests:\n\n```bash\nbundle exec rake compile          # builds
+  the extension\nbundle exec ruby scripts/prepare_ruby_gem.rb  # copies the CLI into
+  lib/bin/\n```\n\n## Error Handling\n\nConversion errors raise `HtmlToMarkdown::Error`
+  (wrapping the Rust error context). CLI invocations use specialised subclasses:\n\n-
+  `HtmlToMarkdown::CLIProxy::MissingBinaryError`\n- `HtmlToMarkdown::CLIProxy::CLIExecutionError`\n\nRescue
+  them to provide clearer feedback in your application.\n\n## Consistent Across Languages\n\nThe
+  Ruby gem shares the exact Rust core with:\n\n- [Python wheels](https://pypi.org/project/html-to-markdown/)\n-
+  [Node.js / Bun bindings](https://www.npmjs.com/package/html-to-markdown-node)\n-
+  [WebAssembly package](https://www.npmjs.com/package/html-to-markdown-wasm)\n- The
+  Rust crate and CLI\n\nUse whichever runtime fits your stack while keeping formatting
+  behaviour identical.\n\n## Development\n\n```bash\nbundle exec rake compile   #
+  build the native extension\nbundle exec rspec          # run test suite\n```\n\nThe
+  extension uses [Magnus](https://github.com/matsadler/magnus) plus `rb-sys` for bindgen.
+  When editing the Rust code under `src/`, rerun `rake compile`.\n\n## License\n\nMIT
+  © Na'aman Hirschfeld\n"
 email:
 - nhirschfeld@gmail.com
 executables:
 - html-to-markdown
 extensions:
 - extconf.rb
-extra_rdoc_files: []
+extra_rdoc_files:
+- README.md
 files:
+- ".rubocop.yml"
 - Cargo.toml
+- Gemfile
+- Gemfile.lock
 - README.md
+- Rakefile
 - exe/html-to-markdown
 - extconf.rb
+- html-to-markdown-rb.gemspec
 - lib/html_to_markdown.rb
 - lib/html_to_markdown/cli.rb
 - lib/html_to_markdown/cli_proxy.rb