html-to-markdown 3.10.4 → 3.10.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2890030d32e03328ad17607655c944c1cfa52b66bc995f0c6a2be27d4e74c4bc
-  data.tar.gz: d300b5b60b90df9913fd29c266244e0cf0f10fc9e491f9627379c5efce2ba51c
+  metadata.gz: 5d86281ca72b53b8f6b281a4243f7545dba4b495ff3363a0ea06f86e54be0c5e
+  data.tar.gz: ede622514b81fcba60b1afc2226ecb7f301396826c546628b889048fad0b634b
 SHA512:
-  metadata.gz: 556ed54ead9067bb60a413f341e970322bf690a9c4a095355f2c29fcef18664863d06e03894d7a166efeffcfadd06787c4275f72da0fe7ec1bee7ed1357858f0
-  data.tar.gz: cadd2c07a91b7d2f4db8c6e6ec5fd5cd40d56f0baab0c64f250bb7c2147680c2d5a45f320ae63311d29970a63319400805f00d9cfb24f860f3d6e28696b1e4d9
+  metadata.gz: 34cae0f9407bc236abaa39293815457b9a8137dcd9fcd43ae5e07963645eaf0fee3c5fcc74af8dc42794341822fcd6d07e89e67cb93023bc944b6145236b0e86
+  data.tar.gz: 4c16de0839f8aecd191202bc0dbf3ea54788a4f26f224221cb31025e1b4a10a4f71e626c78bb7c0f51a38a1f5501c9c6699adda0b9ab5a4dc0ae7a56492c4bf1

data/README.md

@@ -111,11 +111,23 @@ Requires Ruby 3.2+ with Magnus native extension bindings. Published for Linux, m
 
 Basic conversion:
 
-<!-- snippet not found: getting-started/basic_usage.md -->
+```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:
 
-<!-- snippet not found: getting-started/with_options.md -->
+```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
+```
 
 ## Architecture
 
@@ -140,20 +152,19 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 ### Core Function
 
-**`convert(html, options: nil, visitor: nil) -> ConversionResult`**
+**`convert(html, options_or_visitor = nil) -> ConversionResult`**
 
-Converts HTML to Markdown. Returns a `ConversionResult` hash with all results in a single call.
+Converts HTML to Markdown. Returns a `ConversionResult` object with accessor methods for all results in a single call. The second positional argument accepts either an options `Hash`/`ConversionOptions` or a visitor object — not both.
 
 ```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
-document = result[:document]      # Document-level info
-images   = result[:images]        # Extracted images
-warnings = result[:warnings]      # Any conversion warnings
+markdown = result.content       # Converted Markdown string
+metadata = result.metadata      # Metadata (when extract_metadata: true)
+tables   = result.tables        # Structured table data (when include_document_structure: true)
+document = result.document      # Document-level info
+warnings = result.warnings      # Any conversion warnings
 ```
 
 ### Options
@@ -194,12 +205,12 @@ html = "<p>This is <strong>bold</strong> and <em>italic</em> text.</p>"
 
 # Default Markdown output
 markdown_result = HtmlToMarkdown.convert(html)
-markdown = markdown_result[:content]
+markdown = markdown_result.content
 # Result: "This is **bold** and *italic* text."
 
 # Djot output
 djot_result = HtmlToMarkdown.convert(html, output_format: 'djot')
-djot = djot_result[:content]
+djot = djot_result.content
 # Result: "This is *bold* and _italic_ text."
 ```
 
@@ -215,7 +226,7 @@ require 'html_to_markdown'
 html = "<h1>Title</h1><p>This is <strong>bold</strong> and <em>italic</em> text.</p>"
 
 result = HtmlToMarkdown.convert(html, output_format: 'plain')
-plain = result[:content]
+plain = result.content
 # Result: "Title\n\nThis is bold and italic text."
 ```
 
@@ -243,12 +254,12 @@ 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
+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
@@ -276,18 +287,21 @@ class MyVisitor
     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})" }
+    # Directive keys/symbols are matched case-sensitively: :Custom, :Skip, :Continue.
+    { Custom: "[#{text}](#{href})" }
   end
 
   def visit_image(ctx, src, alt = nil, title = nil)
     # Skip tracking pixels
-    src.include?('tracking') ? { type: :skip } : { type: :continue }
+    src.include?('tracking') ? :Skip : :Continue
   end
 end
 
 html = '<a href="https://old-cdn.com/file.pdf">Download</a>'
-result = HtmlToMarkdown.convert(html, visitor: MyVisitor.new)
-markdown = result[:content]
+# The visitor is the second positional argument — it cannot be combined
+# with an options Hash in the same call.
+result = HtmlToMarkdown.convert(html, MyVisitor.new)
+markdown = result.content
 ```
 
 ## Examples

data/ext/html_to_markdown_rb/Cargo.toml

@@ -1,7 +1,7 @@
 
 [package]
 name = "html-to-markdown-rb"
-version = "3.10.4"
+version = "3.10.5"
 edition = "2024"
 license = "MIT"
 [workspace]

data/ext/html_to_markdown_rb/native/Cargo.lock

@@ -260,7 +260,7 @@ checksum = "46c1ff2d1cbf39efe5af0900ced8a069b5e61557a17544eb0c4a50239937389e"
 
 [[package]]
 name = "html-to-markdown-rb"
-version = "3.10.2"
+version = "3.10.4"
 dependencies = [
  "async-trait",
  "html-to-markdown-rs",
@@ -274,9 +274,9 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "3.10.4"
+version = "3.10.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b0fdf3ba00130a03686f79af007ba066f13e2b0ea3d736ede049cfd8b55015a"
+checksum = "8d8796ce09cd945c9c31d0b7f273304768a54bfe95c6383e31fd09fef80fcb49"
 dependencies = [
  "ahash",
  "astral-tl",

data/ext/html_to_markdown_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "3.10.2"
+version = "3.10.4"
 edition = "2024"
 license = "MIT"
 description = "High-performance HTML to Markdown converter"
@@ -25,7 +25,7 @@ visitor = ["html-to-markdown-rs/visitor"]
 
 [dependencies]
 async-trait = "0.1"
-html-to-markdown-rs = { version = "3.10.4", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
+html-to-markdown-rs = { version = "3.10.5", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
 magnus = "0.8"
 rb-sys = ">=0.9, <0.9.128"
 serde = { version = "1", features = ["derive"] }

data/ext/html_to_markdown_rb/src/lib.rs

@@ -1,5 +1,5 @@
 // This file is auto-generated by alef. DO NOT EDIT.
-// alef:hash:9fe2f7328e5ff759a03fb0c68b0bd7281cbe14bbf83d07480cf79d29af39167b
+// alef:hash:f44000653901d10b61e9069d2e901a11b70b0e643ba63d75f2222729c924ae82
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(

data/lib/html_to_markdown/native.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:9fe2f7328e5ff759a03fb0c68b0bd7281cbe14bbf83d07480cf79d29af39167b
+# alef:hash:f44000653901d10b61e9069d2e901a11b70b0e643ba63d75f2222729c924ae82
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/lib/html_to_markdown/version.rb

@@ -1,10 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:bc59c59d83dd11947315504c8b33d8146488c6506d5ccc0f1f36a602630a84d4
+# alef:hash:f44000653901d10b61e9069d2e901a11b70b0e643ba63d75f2222729c924ae82
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
 module HtmlToMarkdown
   ## The version string for this package.
-  VERSION = "3.10.4"
+  VERSION = "3.10.5"
 end

data/lib/html_to_markdown.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:9fe2f7328e5ff759a03fb0c68b0bd7281cbe14bbf83d07480cf79d29af39167b
+# alef:hash:f44000653901d10b61e9069d2e901a11b70b0e643ba63d75f2222729c924ae82
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
@@ -17,11 +17,5 @@ module HtmlToMarkdown
   # Re-export all types and functions from native extension
 end
 
-# Bring top-level HtmlToMarkdown classes into the global namespace so callers
-# (and the generated e2e suite) can reference them unqualified. The native
-# extension has already been required above, so every type constant is defined
-# under HtmlToMarkdown by this point.
-HtmlToMarkdown.constants.each do |const_name|
-  value = HtmlToMarkdown.const_get(const_name)
-  ::Object.const_set(const_name, value) if value.is_a?(Module) && !::Object.const_defined?(const_name)
-end
+# Keep generated types under HtmlToMarkdown. Publishing generated constants
+# into Object makes generic names collide with unrelated Ruby libraries.

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:9fe2f7328e5ff759a03fb0c68b0bd7281cbe14bbf83d07480cf79d29af39167b
+# alef:hash:f44000653901d10b61e9069d2e901a11b70b0e643ba63d75f2222729c924ae82
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 3.10.4
+  version: 3.10.5
 platform: ruby
 authors:
 - Na'aman Hirschfeld <naaman@xberg.io>
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-08-04 00:00:00.000000000 Z
+date: 2026-08-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys