html-to-markdown 3.2.3 → 3.4.0.pre.rc.13

data/Gemfile.lock

@@ -1,173 +0,0 @@
-PATH
-  remote: .
-  specs:
-    html-to-markdown (3.2.3)
-      rb_sys (>= 0.9, < 1.0)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    ast (2.4.3)
-    concurrent-ruby (1.3.6)
-    csv (3.3.5)
-    diff-lcs (1.6.2)
-    ffi (1.17.4-arm64-darwin)
-    ffi (1.17.4-x86_64-linux-gnu)
-    fileutils (1.8.0)
-    json (2.19.3)
-    language_server-protocol (3.17.0.5)
-    lint_roller (1.1.0)
-    listen (3.10.0)
-      logger
-      rb-fsevent (~> 0.10, >= 0.10.3)
-      rb-inotify (~> 0.9, >= 0.9.10)
-    logger (1.7.0)
-    parallel (2.0.1)
-    parser (3.3.11.1)
-      ast (~> 2.4.1)
-      racc
-    prism (1.9.0)
-    racc (1.8.1)
-    rainbow (3.1.1)
-    rake (13.4.2)
-    rake-compiler (1.3.1)
-      rake
-    rake-compiler-dock (1.11.0)
-    rb-fsevent (0.11.2)
-    rb-inotify (0.11.1)
-      ffi (~> 1.0)
-    rb_sys (0.9.126)
-      json (>= 2)
-      rake-compiler-dock (= 1.11.0)
-    rbs (4.0.2)
-      logger
-      prism (>= 1.6.0)
-      tsort
-    regexp_parser (2.12.0)
-    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 (3.13.8)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-support (3.13.7)
-    rubocop (1.86.1)
-      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 (>= 1.49.0, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.49.1)
-      parser (>= 3.3.7.2)
-      prism (~> 1.7)
-    rubocop-performance (1.26.1)
-      lint_roller (~> 1.1)
-      rubocop (>= 1.75.0, < 2.0)
-      rubocop-ast (>= 1.47.1, < 2.0)
-    rubocop-rspec (3.9.0)
-      lint_roller (~> 1.1)
-      rubocop (~> 1.81)
-    ruby-progressbar (1.13.0)
-    securerandom (0.4.1)
-    steep (2.0.0)
-      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)
-      parser (>= 3.2)
-      prism (>= 0.25.0)
-      rainbow (>= 2.2.2, < 4.0)
-      rbs (~> 4.0)
-      securerandom (>= 0.1)
-      strscan (>= 1.0.0)
-      terminal-table (>= 2, < 5)
-      uri (>= 0.12.0)
-    strscan (3.1.8)
-    terminal-table (4.0.0)
-      unicode-display_width (>= 1.1.1, < 4)
-    tsort (0.2.0)
-    unicode-display_width (3.2.0)
-      unicode-emoji (~> 4.1)
-    unicode-emoji (4.2.0)
-    uri (1.1.1)
-
-PLATFORMS
-  arm64-darwin
-  x86_64-linux
-
-DEPENDENCIES
-  html-to-markdown!
-  rake-compiler
-  rb_sys
-  rbs
-  rspec
-  rubocop
-  rubocop-performance
-  rubocop-rspec
-  steep
-
-CHECKSUMS
-  ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
-  concurrent-ruby (1.3.6) sha256=6b56837e1e7e5292f9864f34b69c5a2cbc75c0cf5338f1ce9903d10fa762d5ab
-  csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
-  diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
-  ffi (1.17.4-arm64-darwin) sha256=19071aaf1419251b0a46852abf960e77330a3b334d13a4ab51d58b31a937001b
-  ffi (1.17.4-x86_64-linux-gnu) sha256=9d3db14c2eae074b382fa9c083fe95aec6e0a1451da249eab096c34002bc752d
-  fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
-  html-to-markdown (3.2.3)
-  json (2.19.3) sha256=289b0bb53052a1fa8c34ab33cc750b659ba14a5c45f3fcf4b18762dc67c78646
-  language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
-  lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
-  listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
-  logger (1.7.0) sha256=196edec7cc44b66cfb40f9755ce11b392f21f7967696af15d274dde7edff0203
-  parallel (2.0.1) sha256=337782d3e39f4121e67563bf91dd8ece67f48923d90698614773a0ec9a5b2c7d
-  parser (3.3.11.1) sha256=d17ace7aabe3e72c3cc94043714be27cc6f852f104d81aa284c2281aecc65d54
-  prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
-  racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
-  rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
-  rake (13.4.2) sha256=cb825b2bd5f1f8e91ca37bddb4b9aaf345551b4731da62949be002fa89283701
-  rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
-  rake-compiler-dock (1.11.0) sha256=eab51f2cd533eb35cea6b624a75281f047123e70a64c58b607471bb49428f8c2
-  rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
-  rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
-  rb_sys (0.9.126) sha256=ba958e0b8b4b89eeae0b3d24b64c809eb2c37e0ab0773a49e9b1c2e22c95aef8
-  rbs (4.0.2) sha256=af75671e66cd03434cc546622741ebf83f6197ec4328375805306330bf78ef25
-  regexp_parser (2.12.0) sha256=35a916a1d63190ab5c9009457136ae5f3c0c7512d60291d0d1378ba18ce08ebb
-  rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
-  rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
-  rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
-  rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
-  rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
-  rubocop (1.86.1) sha256=44415f3f01d01a21e01132248d2fd0867572475b566ca188a0a42133a08d4531
-  rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
-  rubocop-performance (1.26.1) sha256=cd19b936ff196df85829d264b522fd4f98b6c89ad271fa52744a8c11b8f71834
-  rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
-  ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
-  securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
-  steep (2.0.0) sha256=6eb0ecc09637bbb54f0a5f2cf63daea6d3208ccace64b4f1107d976333605c30
-  strscan (3.1.8) sha256=aae2db611a225559f21ffbb71765c9a4e60fd262534a9ea84f4f11c7f32f679e
-  terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2
-  tsort (0.2.0) sha256=9650a793f6859a43b6641671278f79cfead60ac714148aabe4e3f0060480089f
-  unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
-  unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
-  uri (1.1.1) sha256=379fa58d27ffb1387eaada68c749d1426738bd0f654d812fcc07e7568f5c57c6
-
-RUBY VERSION
-  ruby 3.4.8
-
-BUNDLED WITH
-  4.0.3

data/README.md

@@ -1,331 +0,0 @@
-# html-to-markdown
-
-<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
-  <!-- Language Bindings -->
-  <a href="https://crates.io/crates/html-to-markdown-rs">
-    <img src="https://img.shields.io/crates/v/html-to-markdown-rs?label=Rust&color=007ec6" alt="Rust">
-  </a>
-  <a href="https://pypi.org/project/html-to-markdown/">
-    <img src="https://img.shields.io/pypi/v/html-to-markdown?label=Python&color=007ec6" alt="Python">
-  </a>
-  <a href="https://www.npmjs.com/package/@kreuzberg/html-to-markdown-node">
-    <img src="https://img.shields.io/npm/v/@kreuzberg/html-to-markdown-node?label=Node.js&color=007ec6" alt="Node.js">
-  </a>
-  <a href="https://www.npmjs.com/package/@kreuzberg/html-to-markdown-wasm">
-    <img src="https://img.shields.io/npm/v/@kreuzberg/html-to-markdown-wasm?label=WASM&color=007ec6" alt="WASM">
-  </a>
-  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/html-to-markdown">
-    <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/html-to-markdown?label=Java&color=007ec6" alt="Java">
-  </a>
-  <a href="https://pkg.go.dev/github.com/kreuzberg-dev/html-to-markdown/packages/go/v3/htmltomarkdown">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/html-to-markdown?label=Go&color=007ec6&filter=v3.2.0" alt="Go">
-  </a>
-  <a href="https://www.nuget.org/packages/KreuzbergDev.HtmlToMarkdown/">
-    <img src="https://img.shields.io/nuget/v/KreuzbergDev.HtmlToMarkdown?label=C%23&color=007ec6" alt="C#">
-  </a>
-  <a href="https://packagist.org/packages/kreuzberg-dev/html-to-markdown">
-    <img src="https://img.shields.io/packagist/v/kreuzberg-dev/html-to-markdown?label=PHP&color=007ec6" alt="PHP">
-  </a>
-  <a href="https://rubygems.org/gems/html-to-markdown">
-    <img src="https://img.shields.io/gem/v/html-to-markdown?label=Ruby&color=007ec6" alt="Ruby">
-  </a>
-  <a href="https://hex.pm/packages/html_to_markdown">
-    <img src="https://img.shields.io/hexpm/v/html_to_markdown?label=Elixir&color=007ec6" alt="Elixir">
-  </a>
-  <a href="https://kreuzberg-dev.r-universe.dev/htmltomarkdown">
-    <img src="https://img.shields.io/cran/v/htmltomarkdown?label=R&color=007ec6" alt="R">
-  </a>
-  <a href="https://github.com/kreuzberg-dev/html-to-markdown/releases">
-    <img src="https://img.shields.io/badge/C-FFI-007ec6" alt="C">
-  </a>
-
-  <!-- Project Info -->
-  <a href="https://docs.html-to-markdown.kreuzberg.dev">
-    <img src="https://img.shields.io/badge/Docs-kreuzberg.dev-007ec6" alt="Documentation">
-  </a>
-  <a href="https://github.com/kreuzberg-dev/html-to-markdown/blob/main/LICENSE">
-    <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License">
-  </a>
-</div>
-
-<img width="1128" height="191" alt="html-to-markdown" src="https://github.com/user-attachments/assets/419fc06c-8313-4324-b159-4b4d3cfce5c0" />
-
-<div align="center" style="margin-top: 20px;">
-  <a href="https://discord.gg/pXxagNK2zN">
-      <img height="22" src="https://img.shields.io/badge/Discord-Join%20our%20community-7289da?logo=discord&logoColor=white" alt="Discord">
-  </a>
-</div>
-
-Blazing-fast HTML to Markdown conversion for Ruby, powered by the same Rust engine used by our Python, Node.js, WebAssembly, and PHP packages.
-Ship identical Markdown across every runtime while enjoying native extension performance with Magnus bindings.
-
-
-## Installation
-
-```bash
-gem install html-to-markdown
-```
-
-
-
-Requires Ruby 3.2+ with Magnus native extension bindings. Published for Linux, macOS.
-
-
-
-
-
-
-## Performance Snapshot
-
-**Apple M4** · `convert()` · Real Wikipedia documents
-
-| Document | Size | Latency | Throughput |
-|----------|------|---------|------------|
-| Lists (Timeline) | 129KB | 0.71ms | 182 MB/s |
-| Tables (Countries) | 360KB | 2.15ms | 167 MB/s |
-| Mixed (Python wiki) | 656KB | 4.89ms | 134 MB/s |
-
-
-
-
-## Quick Start
-
-Basic conversion:
-
-```ruby
-require 'html_to_markdown'
-
-html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
-result = HtmlToMarkdown.convert(html)
-markdown = result[:content]
-```
-
-
-With conversion options:
-
-```ruby
-require 'html_to_markdown'
-
-html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
-result = HtmlToMarkdown.convert(html, heading_style: :atx, code_block_style: :fenced)
-markdown = result[:content]
-```
-
-
-## API Reference
-
-### Core Function
-
-
-**`convert(html, options: nil, visitor: nil) -> ConversionResult`**
-
-Converts HTML to Markdown. Returns a `ConversionResult` hash with all results in a single call.
-
-```ruby
-require 'html_to_markdown'
-
-result = HtmlToMarkdown.convert(html)
-markdown = result[:content]       # Converted Markdown string
-metadata = result[:metadata]      # Metadata (when extract_metadata: true)
-tables   = result[:tables]        # Structured table data (when extract_tables: true)
-document = result[:document]      # Document-level info
-images   = result[:images]        # Extracted images
-warnings = result[:warnings]      # Any conversion warnings
-```
-
-
-
-### Options
-
-**`ConversionOptions`** – Key configuration fields:
-
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
-- `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
-- `wrap`: Enable text wrapping — default: `false`
-- `wrap_width`: Wrap at column — default: `80`
-- `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
-- `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
-
-## Djot Output Format
-
-The library supports converting HTML to [Djot](https://djot.net/), a lightweight markup language similar to Markdown but with a different syntax for some elements. Set `output_format` to `"djot"` to use this format.
-
-### Syntax Differences
-
-| Element | Markdown | Djot |
-|---------|----------|------|
-| Strong | `**text**` | `*text*` |
-| Emphasis | `*text*` | `_text_` |
-| Strikethrough | `~~text~~` | `{-text-}` |
-| Inserted/Added | N/A | `{+text+}` |
-| Highlighted | N/A | `{=text=}` |
-| Subscript | N/A | `~text~` |
-| Superscript | N/A | `^text^` |
-
-### Example Usage
-
-
-
-```ruby
-require 'html_to_markdown'
-
-html = "<p>This is <strong>bold</strong> and <em>italic</em> text.</p>"
-
-# Default Markdown output
-markdown = HtmlToMarkdown.convert(html)
-# Result: "This is **bold** and *italic* text."
-
-# Djot output
-djot = HtmlToMarkdown.convert(html, output_format: 'djot')
-# Result: "This is *bold* and _italic_ text."
-```
-
-
-
-Djot's extended syntax allows you to express more semantic meaning in lightweight text, making it useful for documents that require strikethrough, insertion tracking, or mathematical notation.
-
-## Plain Text Output
-
-Set `output_format` to `"plain"` to strip all markup and return only visible text. This bypasses the Markdown conversion pipeline entirely for maximum speed.
-
-
-
-```ruby
-require 'html_to_markdown'
-
-html = "<h1>Title</h1><p>This is <strong>bold</strong> and <em>italic</em> text.</p>"
-
-plain = HtmlToMarkdown.convert(html, output_format: 'plain')
-# Result: "Title\n\nThis is bold and italic text."
-```
-
-
-
-Plain text mode is useful for search indexing, text extraction, and feeding content to LLMs.
-
-
-
-## Metadata Extraction
-
-The metadata extraction feature enables comprehensive document analysis during conversion. Extract document properties, headers, links, images, and structured data in a single pass — all via the standard `convert()` function.
-
-**Use Cases:**
-
-- **SEO analysis** – Extract title, description, Open Graph tags, Twitter cards
-- **Table of contents generation** – Build structured outlines from heading hierarchy
-- **Content migration** – Document all external links and resources
-- **Accessibility audits** – Check for images without alt text, empty links, invalid heading hierarchy
-- **Link validation** – Classify and validate anchor, internal, external, email, and phone links
-
-**Zero Overhead When Disabled:** Metadata extraction adds negligible overhead and happens during the HTML parsing pass. Pass `extract_metadata: true` in `ConversionOptions` to enable it; the result is available at `result.metadata`.
-
-### Example: Quick Start
-
-
-
-```ruby
-require 'html_to_markdown'
-
-html = '<h1>Article</h1><img src="test.jpg" alt="test">'
-result = HtmlToMarkdown.convert(html, extract_metadata: true)
-
-puts result[:content]                             # Converted Markdown
-puts result[:metadata][:document][:title]         # Document title
-puts result[:metadata][:headers]                  # All h1-h6 elements
-puts result[:metadata][:links]                    # All hyperlinks
-puts result[:metadata][:images]                   # All images with alt text
-puts result[:metadata][:structured_data]          # JSON-LD, Microdata, RDFa
-```
-
-
-
-
-
-
-## Visitor Pattern
-
-The visitor pattern enables custom HTML→Markdown conversion logic by providing callbacks for specific HTML elements during traversal. Pass a visitor as the third argument to `convert()`.
-
-**Use Cases:**
-
-- **Custom Markdown dialects** – Convert to Obsidian, Notion, or other flavors
-- **Content filtering** – Remove tracking pixels, ads, or unwanted elements
-- **URL rewriting** – Rewrite CDN URLs, add query parameters, validate links
-- **Accessibility validation** – Check alt text, heading hierarchy, link text
-- **Analytics** – Track element usage, link destinations, image sources
-
-**Supported Visitor Methods:** 40+ callbacks for text, inline elements, links, images, headings, lists, blocks, and tables.
-
-### Example: Quick Start
-
-
-
-```ruby
-require 'html_to_markdown'
-
-class MyVisitor
-  def visit_link(ctx, href, text, title = nil)
-    # Rewrite CDN URLs
-    if href.start_with?('https://old-cdn.com')
-      href = href.sub('https://old-cdn.com', 'https://new-cdn.com')
-    end
-    { type: :custom, output: "[#{text}](#{href})" }
-  end
-
-  def visit_image(ctx, src, alt = nil, title = nil)
-    # Skip tracking pixels
-    src.include?('tracking') ? { type: :skip } : { type: :continue }
-  end
-end
-
-html = '<a href="https://old-cdn.com/file.pdf">Download</a>'
-result = HtmlToMarkdown.convert(html, visitor: MyVisitor.new)
-markdown = result[:content]
-```
-
-
-
-
-## Examples
-
-
-## Links
-
-- **GitHub:** [github.com/kreuzberg-dev/html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown)
-
-- **RubyGems:** [rubygems.org/gems/html-to-markdown](https://rubygems.org/gems/html-to-markdown)
-
-- **Kreuzberg Ecosystem:** [kreuzberg.dev](https://kreuzberg.dev)
-- **Discord:** [discord.gg/pXxagNK2zN](https://discord.gg/pXxagNK2zN)
-
-## Contributing
-
-We welcome contributions! Please see our [Contributing Guide](https://github.com/kreuzberg-dev/html-to-markdown/blob/main/CONTRIBUTING.md) for details on:
-
-- Setting up the development environment
-- Running tests locally
-- Submitting pull requests
-- Reporting issues
-
-All contributions must follow our code quality standards (enforced via pre-commit hooks):
-
-- Proper test coverage (Rust 95%+, language bindings 80%+)
-- Formatting and linting checks
-- Documentation for public APIs
-
-## License
-
-MIT License – see [LICENSE](https://github.com/kreuzberg-dev/html-to-markdown/blob/main/LICENSE).
-
-## Support
-
-If you find this library useful, consider [sponsoring the project](https://github.com/sponsors/kreuzberg-dev).
-
-Have questions or run into issues? We're here to help:
-
-- **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Discussions:** [github.com/kreuzberg-dev/html-to-markdown/discussions](https://github.com/kreuzberg-dev/html-to-markdown/discussions)
-- **Discord Community:** [discord.gg/pXxagNK2zN](https://discord.gg/pXxagNK2zN)

data/Rakefile

@@ -1,26 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler/gem_tasks'
-require 'rake/extensiontask'
-require 'rspec/core/rake_task'
-
-GEMSPEC = Gem::Specification.load(File.expand_path('html_to_markdown_rs.gemspec', __dir__))
-
-Rake::ExtensionTask.new('html_to_markdown_rb', GEMSPEC) do |ext|
-  ext.lib_dir = 'lib'
-  ext.ext_dir = 'ext/html_to_markdown_rb'
-  ext.cross_compile = true
-  ext.cross_platform = %w[
-    x86_64-linux
-    aarch64-linux
-    x86_64-darwin
-    arm64-darwin
-    x64-mingw32
-    x64-mingw-ucrt
-  ]
-end
-
-RSpec::Core::RakeTask.new(:spec)
-
-task spec: :compile
-task default: :spec

data/exe/html-to-markdown

@@ -1,6 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-require 'html_to_markdown/cli'
-
-exit HtmlToMarkdown::CLI.run(ARGV)

data/ext/html_to_markdown_rb/src/html_to_markdown_rs/version.rb

@@ -1,6 +0,0 @@
-# This file is auto-generated by alef. DO NOT EDIT.
-# frozen_string_literal: true
-
-module Html_to_markdown_rs
-  VERSION = "3.2.0"
-end

data/ext/html_to_markdown_rb/src/html_to_markdown_rs.rb

@@ -1,9 +0,0 @@
-# This file is auto-generated by alef. DO NOT EDIT.
-# frozen_string_literal: true
-
-require_relative 'html_to_markdown_rs/version'
-require_relative 'html_to_markdown_rs/native'
-
-module Html_to_markdown_rs
-  # Re-export all types and functions from native extension
-end

data/html-to-markdown-rb.gemspec

@@ -1,99 +0,0 @@
-# frozen_string_literal: true
-
-require_relative 'lib/html_to_markdown/version'
-
-repo_root = File.expand_path('../..', __dir__)
-crate_prefix = 'packages/ruby/'
-git_cmd = %(git -C "#{repo_root}" ls-files -z #{crate_prefix})
-ruby_files =
-  `#{git_cmd}`.split("\x0")
-              .select { |path| path.start_with?(crate_prefix) }
-              .map { |path| path.delete_prefix(crate_prefix) }
-
-fallback_files = Dir.chdir(__dir__) do
-  Dir.glob(
-    %w[
-      README.md
-      ext/**/*
-      exe/*
-      lib/**/*.rb
-      lib/bin/*
-      src/**/*.rs
-      spec/**/*.rb
-      sig/**/*.rbs
-    ]
-  )
-end
-
-# Vendor files: include vendored crates and workspace Cargo.toml
-vendor_files = Dir.chdir(__dir__) do
-  Dir.glob('vendor/html-to-markdown-rs/**/*', File::FNM_DOTMATCH)
-     .select { |f| File.file?(f) }
-     .grep_v(%r{/target/})
-     .grep_v(/\.(swp|bak|tmp)$/)
-end
-
-# Include vendor/Cargo.toml (workspace definition) if it exists
-workspace_toml = if File.exist?(File.join(__dir__, 'vendor/Cargo.toml'))
-                   ['vendor/Cargo.toml']
-                 else
-                   []
-                 end
-
-# When vendor exists, use ext/ files from filesystem (modified by vendor script)
-# instead of git (which has the unmodified Cargo.toml with workspace paths)
-ext_files_from_fs = Dir.chdir(__dir__) do
-  Dir.glob('ext/**/*', File::FNM_DOTMATCH)
-     .reject { |f| File.directory?(f) }
-     .reject { |f| f.include?('/target/') }
-end
-
-# Include native artifacts (.so, .bundle, .dylib) if present (for platform gems)
-native_files = Dir.chdir(__dir__) do
-  Dir.glob('lib/**/*.{so,bundle,dylib}')
-end
-
-files = if vendor_files.any?
-          # Vendor exists: use ext/ from filesystem (has modified Cargo.toml)
-          non_ext_ruby_files = (ruby_files.empty? ? fallback_files : ruby_files)
-                               .reject { |f| f.start_with?('ext/') }
-          non_ext_ruby_files + ext_files_from_fs + vendor_files + workspace_toml + native_files
-        else
-          ruby_files.empty? ? fallback_files : ruby_files
-        end
-
-files = files.uniq
-
-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   = <<~DESC.strip
-    html-to-markdown is a native Ruby extension built on the shared Rust engine that powers the html-to-markdown project.
-    It delivers identical HTML-to-Markdown output across languages, exposes inline image extraction, and ships with a CLI for automation workflows.
-  DESC
-  spec.homepage      = 'https://github.com/kreuzberg-dev/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 = files
-  spec.extra_rdoc_files = ['README.md']
-
-  spec.extensions = ['ext/html_to_markdown_rb/extconf.rb']
-
-  spec.add_dependency 'rb_sys', '>= 0.9', '< 1.0'
-  spec.metadata['rubygems_mfa_required'] = 'true'
-  spec.metadata['homepage_uri'] = 'https://github.com/kreuzberg-dev/html-to-markdown'
-  spec.metadata['source_code_uri'] = 'https://github.com/kreuzberg-dev/html-to-markdown'
-  spec.metadata['bug_tracker_uri'] = 'https://github.com/kreuzberg-dev/html-to-markdown/issues'
-  spec.metadata['changelog_uri'] = 'https://github.com/kreuzberg-dev/html-to-markdown/releases'
-  spec.metadata['documentation_uri'] = 'https://github.com/kreuzberg-dev/html-to-markdown/blob/main/packages/ruby/README.md'
-end

data/lib/html_to_markdown_rs.rb

@@ -1,3 +0,0 @@
-# frozen_string_literal: true
-
-require 'html_to_markdown_rb'