html-to-markdown 2.29.0 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: be0f8ebfe65a05409b2ffd00ec9ef6d4df88a6fbcbaf5ca486066d50581d7343
-  data.tar.gz: 9096699b71d719c2d28d89067b26bafc629f86b3ee2632fa579fdbef2780823c
+  metadata.gz: 823ad44845a919191f6b64697599dab71cd1a6e0d6a9a1f222fa0500ef66eb9a
+  data.tar.gz: 360148ff88f88e404ef19f14baccec24b0fa2dfe21b5f601ffc2ae56a9420f52
 SHA512:
-  metadata.gz: ec0f48521c4aa8d5b5c87f39efc2862b60834f81e274a15b402bc387bfad3559564c0d6814b4419b1450b5bdea25a6c5534397634e03b5164ccd9b6433d0d559
-  data.tar.gz: 5ab62d25a86ad609bb5704470618aeae9d6bc5ce2e9a07adb0c88108938e6d893790ab4444847201fe9902671ba70ff0f81adc91e5588ca5823c15feb566e76f
+  metadata.gz: 664d63d8e57a17085da777089fff023db75b840f686ea84e12d9529bedc8d0405c4c9027f565d7c5cc8a5e01e42d3e7d81c356668b858f1f22451dd80349bceb
+  data.tar.gz: cd46a114ee8a200cbfa42e653b4ca24a2a2ef884c4981d366ab01dbd23e2bdc13f304bf12c9d6b367b480c3bca5e4e98f82805a8862320ac40931a42904b5ee6

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    html-to-markdown (2.29.0)
+    html-to-markdown (3.0.0)
       rb_sys (>= 0.9, < 1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (8.1.2)
+    activesupport (8.1.3)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.3.1)
@@ -20,28 +20,20 @@ GEM
       securerandom (>= 0.3)
       tzinfo (~> 2.0, >= 2.0.5)
       uri (>= 0.13.1)
-    addressable (2.8.9)
-      public_suffix (>= 2.0.2, < 8.0)
     ast (2.4.3)
     base64 (0.3.0)
-    bigdecimal (4.0.1)
+    bigdecimal (4.1.0)
     concurrent-ruby (1.3.6)
     connection_pool (3.0.2)
     csv (3.3.5)
     diff-lcs (1.6.2)
     drb (2.2.3)
-    ffi (1.17.3-aarch64-linux-gnu)
-    ffi (1.17.3-arm64-darwin)
-    ffi (1.17.3-x64-mingw-ucrt)
-    ffi (1.17.3-x86_64-darwin)
-    ffi (1.17.3-x86_64-linux-gnu)
+    ffi (1.17.4-arm64-darwin)
+    ffi (1.17.4-x86_64-linux-gnu)
     fileutils (1.8.0)
     i18n (1.14.8)
       concurrent-ruby (~> 1.0)
-    json (2.19.2)
-    json-schema (6.2.0)
-      addressable (~> 2.8)
-      bigdecimal (>= 3.1, < 5)
+    json (2.19.3)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
     listen (3.10.0)
@@ -49,18 +41,15 @@ GEM
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
     logger (1.7.0)
-    mcp (0.9.0)
-      json-schema (>= 4.1)
     minitest (6.0.2)
       drb (~> 2.0)
       prism (~> 1.5)
     mutex_m (0.3.0)
     parallel (1.27.0)
-    parser (3.3.10.2)
+    parser (3.3.11.1)
       ast (~> 2.4.1)
       racc
     prism (1.9.0)
-    public_suffix (7.0.5)
     racc (1.8.1)
     rainbow (3.1.1)
     rake (13.3.1)
@@ -72,7 +61,7 @@ GEM
       ffi (~> 1.0)
     rb_sys (0.9.124)
       rake-compiler-dock (= 1.11.0)
-    rbs (3.10.3)
+    rbs (3.10.4)
       logger
       tsort
     regexp_parser (2.11.3)
@@ -89,11 +78,10 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
     rspec-support (3.13.7)
-    rubocop (1.85.1)
+    rubocop (1.86.0)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
-      mcp (~> 0.6)
       parallel (~> 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
@@ -138,12 +126,8 @@ GEM
     uri (1.1.1)
 
 PLATFORMS
-  aarch64-linux
   arm64-darwin
-  x64-mingw-ucrt
-  x86_64-darwin
   x86_64-linux
-  x86_64-linux-gnu
 
 DEPENDENCIES
   html-to-markdown!
@@ -156,37 +140,30 @@ DEPENDENCIES
   steep
 
 CHECKSUMS
-  activesupport (8.1.2) sha256=88842578ccd0d40f658289b0e8c842acfe9af751afee2e0744a7873f50b6fdae
-  addressable (2.8.9) sha256=cc154fcbe689711808a43601dee7b980238ce54368d23e127421753e46895485
+  activesupport (8.1.3) sha256=21a5e0dfbd4c3ddd9e1317ec6a4d782fa226e7867dc70b0743acda81a1dca20e
   ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
   base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
-  bigdecimal (4.0.1) sha256=8b07d3d065a9f921c80ceaea7c9d4ae596697295b584c296fe599dd0ad01c4a7
+  bigdecimal (4.1.0) sha256=6dc07767aa3dc456ccd48e7ae70a07b474e9afd7c5bc576f80bd6da5c8dd6cae
   concurrent-ruby (1.3.6) sha256=6b56837e1e7e5292f9864f34b69c5a2cbc75c0cf5338f1ce9903d10fa762d5ab
   connection_pool (3.0.2) sha256=33fff5ba71a12d2aa26cb72b1db8bba2a1a01823559fb01d29eb74c286e62e0a
   csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
   diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
   drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
-  ffi (1.17.3-aarch64-linux-gnu) sha256=28ad573df26560f0aedd8a90c3371279a0b2bd0b4e834b16a2baa10bd7a97068
-  ffi (1.17.3-arm64-darwin) sha256=0c690555d4cee17a7f07c04d59df39b2fba74ec440b19da1f685c6579bb0717f
-  ffi (1.17.3-x64-mingw-ucrt) sha256=5f1d7d067a9a1058ad183dba25b05557cd51c85fc1768c49338eabc1cf242d7c
-  ffi (1.17.3-x86_64-darwin) sha256=1f211811eb5cfaa25998322cdd92ab104bfbd26d1c4c08471599c511f2c00bb5
-  ffi (1.17.3-x86_64-linux-gnu) sha256=3746b01f677aae7b16dc1acb7cb3cc17b3e35bdae7676a3f568153fb0e2c887f
+  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 (2.29.0)
+  html-to-markdown (3.0.0)
   i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
-  json (2.19.2) sha256=e7e1bd318b2c37c4ceee2444841c86539bc462e81f40d134cf97826cb14e83cf
-  json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
+  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
-  mcp (0.9.0) sha256=a0a3737b0ac9df0772f4ef7e2b013c260ddbcf217a5d50a66bff0baeddf03e47
   minitest (6.0.2) sha256=db6e57956f6ecc6134683b4c87467d6dd792323c7f0eea7b93f66bd284adbc3d
   mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
   parallel (1.27.0) sha256=4ac151e1806b755fb4e2dc2332cbf0e54f2e24ba821ff2d3dcf86bf6dc4ae130
-  parser (3.3.10.2) sha256=6f60c84aa4bdcedb6d1a2434b738fe8a8136807b6adc8f7f53b97da9bc4e9357
+  parser (3.3.11.1) sha256=d17ace7aabe3e72c3cc94043714be27cc6f852f104d81aa284c2281aecc65d54
   prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
-  public_suffix (7.0.5) sha256=1a8bb08f1bbea19228d3bed6e5ed908d1cb4f7c2726d18bd9cadf60bc676f623
   racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
   rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
   rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
@@ -195,14 +172,14 @@ CHECKSUMS
   rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
   rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
   rb_sys (0.9.124) sha256=513476557b12eaf73764b3da9f8746024558fe8699bda785fb548c9aa3877ae7
-  rbs (3.10.3) sha256=70627f3919016134d554e6c99195552ae3ef6020fe034c8e983facc9c192daa6
+  rbs (3.10.4) sha256=b17d7c4be4bb31a11a3b529830f0aa206a807ca42f2e7921a3027dfc6b7e5ce8
   regexp_parser (2.11.3) sha256=ca13f381a173b7a93450e53459075c9b76a10433caadcb2f1180f2c741fc55a4
   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 (1.85.1) sha256=3dbcf9e961baa4c376eeeb2a03913dca5e3987033b04d38fa538aa1e7406cc77
+  rubocop (1.86.0) sha256=4ff1186fe16ebe9baff5e7aad66bb0ad4cabf5cdcd419f773146dbba2565d186
   rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
   rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
   ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33

data/README.md

@@ -17,8 +17,8 @@
   <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/v2/htmltomarkdown">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/html-to-markdown?label=Go&color=007ec6&filter=v2.29.0" alt="Go">
+  <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=v3.0.0" 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#">
@@ -87,7 +87,6 @@ Apple M4 • Real Wikipedia documents • `convert()` (Ruby)
 | Mixed (Python wiki) | 656KB | 4.89ms | 134 MB/s |
 
 
-See [Performance Guide](../../examples/performance/) for detailed benchmarks.
 
 
 ## Quick Start
@@ -98,7 +97,8 @@ Basic conversion:
 require 'html_to_markdown'
 
 html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
-markdown = HtmlToMarkdown.convert(html)
+result = HtmlToMarkdown.convert(html)
+markdown = result[:content]
 ```
 
 
@@ -109,60 +109,50 @@ With conversion options:
 require 'html_to_markdown'
 
 html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
-markdown = HtmlToMarkdown.convert(html, heading_style: :atx, code_block_style: :fenced)
+result = HtmlToMarkdown.convert(html, heading_style: :atx, code_block_style: :fenced)
+markdown = result[:content]
 ```
 
 
 
 
-
-
 ## API Reference
 
-### Core Functions
-
-
-**`convert(html, options: nil) -> String`**
+### Core Function
 
-Basic HTML-to-Markdown conversion. Fast and simple.
 
-**`convert_with_metadata(html, options: nil, config: nil) -> [String, Hash]`**
+**`convert(html, options: nil, visitor: nil) -> ConversionResult`**
 
-Extract Markdown plus metadata (headers, links, images, structured data) in a single pass. See [Metadata Extraction Guide](../../examples/metadata-extraction/).
+Converts HTML to Markdown. Returns a `ConversionResult` hash with all results in a single call.
 
-**`convert_with_visitor(html, visitor:, options: nil) -> String`**
-
-Customize conversion with visitor callbacks for element interception. See [Visitor Pattern Guide](../../examples/visitor-pattern/).
-
-**`convert_with_inline_images(html, config: nil) -> [String, Array, Array]`**
-
-Extract base64-encoded inline images with metadata.
-
-**`convert_with_tables(html, options: nil, config: nil) -> ConversionWithTables`**
+```ruby
+require 'html_to_markdown'
 
-Extract structured table data (cells, headers, rendered markdown) alongside conversion.
+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`: Embed metadata as YAML frontmatter — default: `false`
+- `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"`
 
-**`MetadataConfig`** – Selective metadata extraction:
-- `extract_headers`: h1-h6 elements — default: `true`
-- `extract_links`: Hyperlinks — default: `true`
-- `extract_images`: Image elements — default: `true`
-- `extract_structured_data`: JSON-LD, Microdata, RDFa — default: `true`
-- `max_structured_data_size`: Size limit in bytes — default: `100KB`
-
 
 ## Djot Output Format
 
@@ -222,16 +212,17 @@ Plain text mode is useful for search indexing, text extraction, and feeding cont
 
 ## 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.
+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. Disable unused metadata types in `MetadataConfig` to optimize further.
+**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
 
@@ -240,27 +231,27 @@ The metadata extraction feature enables comprehensive document analysis during c
 require 'html_to_markdown'
 
 html = '<h1>Article</h1><img src="test.jpg" alt="test">'
-markdown, metadata = HtmlToMarkdown.convert_with_metadata(html)
-
-puts metadata[:document][:title]           # Document title
-puts metadata[:headers]                    # All h1-h6 elements
-puts metadata[:links]                      # All hyperlinks
-puts metadata[:images]                     # All images with alt text
-puts metadata[:structured_data]            # JSON-LD, Microdata, RDFa
+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
 ```
 
 
 
-For detailed examples including SEO extraction, table-of-contents generation, link validation, and accessibility audits, see the [Metadata Extraction Guide](../../examples/metadata-extraction/).
-
 
 
 
 ## Visitor Pattern
 
-The visitor pattern enables custom HTML→Markdown conversion logic by providing callbacks for specific HTML elements during traversal. Use visitors to transform content, filter elements, validate structure, or collect analytics.
+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
@@ -291,20 +282,16 @@ class MyVisitor
 end
 
 html = '<a href="https://old-cdn.com/file.pdf">Download</a>'
-markdown = HtmlToMarkdown.convert_with_visitor(html, visitor: MyVisitor.new)
+result = HtmlToMarkdown.convert(html, visitor: MyVisitor.new)
+markdown = result[:content]
 ```
 
 
 
-For comprehensive examples including content filtering, link footnotes, accessibility validation, and asynchronous URL validation, see the [Visitor Pattern Guide](../../examples/visitor-pattern/).
-
 
 
 ## Examples
 
-- [Visitor Pattern Guide](../../examples/visitor-pattern/)
-- [Metadata Extraction Guide](../../examples/metadata-extraction/)
-- [Performance Guide](../../examples/performance/)
 
 ## Links