html-to-markdown 3.19.0 → 3.21.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e42d1e5a9c4cab13d5840556d5e6a518aa98576495b6fe08cf376a93392d8ba5
-  data.tar.gz: 7e20b6da6705d9bcf643ee55dccd5b0de4131b170236c2bf9785eed5dd048133
+  metadata.gz: 15f402f9dda7241decfc22f13ad4914661924ac16828888e8869be4a330c58e6
+  data.tar.gz: a4160304d6e89d800d30c873fa836ba9bbabb99ef7abbbcb14deba9598dce74a
 SHA512:
-  metadata.gz: 9510c005552e50c8397a8db398cc8f63e5d57dbd5ca889c96077019d2db9f60f63fd1a14a234d3836752aedae0620919a07d6c90b8bf5fce5dbded58c0d49f1a
-  data.tar.gz: a79521d8aa524eb9261167d71fd56a1fffa31ec7a1f2a4458ba3076d968d1361f18b96ca5f907d596120f0ad84e743ecd2e1d62f78f0582af1dd3b523845fb6c
+  metadata.gz: 22e024bb02c9080414e5fef70298f95616659360925644fa2ae4112455bba6ebf4f69e44ae8200185bd94226249ec58d0db4b0637895caff975d4efcc3f1f3cd
+  data.tar.gz: e1317218cd188ffa0da59e86110f70a1a262fe6bfbe266297993e7518a68a7b30345117157456e69968165ca2210a06125e27d9752fa324c572ff4a3dfbeafaa

data/README.md

@@ -1,5 +1,5 @@
 <!-- This file is auto-generated by alef — DO NOT EDIT. -->
-<!-- alef:hash:cb80328456dcb271efa3f7851e475022ff26cfe3112b09a2e41384313ff520d0 -->
+<!-- alef:hash:cef2039678dca43690ca25831e1f26c8093fb9ed088d15c4faa6cfd46a216194 -->
 <!-- To regenerate: alef readme -->
 <!-- To verify freshness: alef verify -->
 
@@ -100,7 +100,7 @@ Ship identical Markdown across every runtime while enjoying native extension per
 gem install html-to-markdown
 ```
 
-Requires Ruby 3.2+ with Magnus native extension bindings. Published for Linux, macOS.
+Requires Ruby 3.3+ with Magnus native extension bindings. Published for Linux, macOS.
 
 ## Performance Snapshot
 

data/ext/html_to_markdown_rb/native/Cargo.lock

@@ -31,10 +31,10 @@ dependencies = [
 ]
 
 [[package]]
-name = "astral-tl"
-version = "0.8.0"
+name = "astral-html"
+version = "0.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "04d4bb5df351abb6758a04240b0193794ddaf34a7c0b9452fab3c25dcce39e88"
+checksum = "d050c4dc17bfd8bf50da08bda9ef724b44a1b4ec09a5811f193f978cb6fbadbb"
 dependencies = [
  "memchr",
 ]
@@ -252,7 +252,7 @@ checksum = "491194d601b4fa9fac3c9571e014070a0ad1bc3392d1bc10419695196a8b3cc3"
 
 [[package]]
 name = "html-to-markdown-rb"
-version = "3.19.0"
+version = "3.21.0"
 dependencies = [
  "async-trait",
  "html-to-markdown-rs",
@@ -266,12 +266,12 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "3.19.0"
+version = "3.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ddada45be32a036999fbda2be5df286dc2001816e60099ec3fd445fc6c3bb69b"
+checksum = "1508f37b10916e398625bcce1e4d19da5a04786d25de2996e2e4579c0e800a22"
 dependencies = [
  "ahash",
- "astral-tl",
+ "astral-html",
  "base64",
  "bitflags",
  "html-escape",
@@ -283,6 +283,7 @@ dependencies = [
  "regex",
  "serde",
  "serde_json",
+ "smallvec",
  "thiserror",
  "tracing",
  "url",
@@ -485,9 +486,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.34"
+version = "0.4.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9f8bd3e56ce4dfc153cf470fffbfa98c7620958b312ca5c3a4b8d5181fd13c6"
+checksum = "5d15f86d12da44cd8d4ec3c73984537eb7f4cadcb9776a575a0a8a05ca11005c"
 
 [[package]]
 name = "magnus"
@@ -1072,9 +1073,18 @@ dependencies = [
 
 [[package]]
 name = "utf8_iter"
-version = "1.0.4"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af3bd9d3e571c26fcce9d033b87ea5ab061b8d2ffe9b7a5675d810d68f03edf0"
+dependencies = [
+ "utf_types",
+]
+
+[[package]]
+name = "utf_types"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
+checksum = "3a3b425286980a367278453f3b6d28cdcb134b574e5a35824a6ff5eebad50bb6"
 
 [[package]]
 name = "version_check"

data/ext/html_to_markdown_rb/native/Cargo.toml

@@ -1,11 +1,11 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:fa3a53f518517843e506e230f22cd23c0afd1bcead1c05e1f1d17a72039f3f7d
+# alef:hash:99bb12a622d006aa5ffe8246e71c811f228cb7525070d61578a5fb1e85c3be45
 # To regenerate: alef generate
 # To verify freshness: alef verify
 
 [package]
 name = "html-to-markdown-rb"
-version = "3.19.0"
+version = "3.21.0"
 edition = "2024"
 authors = ["Na'aman Hirschfeld <naaman@xberg.io>", "Tobias Perlstein <tobias@xberg.io>"]
 license = "MIT"
@@ -31,7 +31,7 @@ visitor = ["html-to-markdown-rs/visitor"]
 
 [dependencies]
 async-trait = "0.1"
-html-to-markdown-rs = { version = "3.19.0", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
+html-to-markdown-rs = { version = "3.21.0", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
 magnus = "0.9"
 rb-sys = ">=0.9.130, <0.10"
 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:4b8dded025d0cab583492c692b2a248f959abe1e38e464768e056b4624f1bb5e
+// alef:hash:400e845c128395e5bc9553bc48841d62d847fc1925e8b1343b42e4926ac2fe5e
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(
@@ -2957,6 +2957,7 @@ pub struct NodeContext {
     index_in_parent: usize,
     parent_tag: Option<String>,
     is_inline: bool,
+    attributes: HashMap<String, String>,
 }
 
 #[cfg(feature = "visitor")]
@@ -3057,6 +3058,15 @@ impl NodeContext {
                 })?,
                 None => Default::default(),
             },
+            attributes: match kwargs.get(ruby.to_symbol("attributes")) {
+                Some(v) => <HashMap<String, String>>::try_convert(v).map_err(|e| {
+                    magnus::Error::new(
+                        unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
+                        format!("invalid value for `attributes`: {}", e),
+                    )
+                })?,
+                None => Default::default(),
+            },
         })
     }
 
@@ -3085,12 +3095,7 @@ impl NodeContext {
     }
 
     fn attributes(&self) -> HashMap<String, String> {
-        let core_self = html_to_markdown_rs::NodeContext::from(self.clone());
-        core_self
-            .attributes()
-            .iter()
-            .map(|(k, v)| (k.clone(), v.clone()))
-            .collect()
+        self.attributes.clone()
     }
 
     #[allow(
@@ -5411,6 +5416,11 @@ fn nodecontext_to_rb_hash(ctx: &html_to_markdown_rs::NodeContext) -> magnus::RHa
     )
     .ok();
     h.aset(ruby.to_symbol("is_inline"), ctx.is_inline).ok();
+    let attributes_hash = ruby.hash_new();
+    for (key, value) in ctx.attributes() {
+        attributes_hash.aset(ruby.str_new(key), ruby.str_new(value)).ok();
+    }
+    h.aset(ruby.to_symbol("attributes"), attributes_hash).ok();
     h
 }
 
@@ -7575,13 +7585,16 @@ impl From<html_to_markdown_rs::MetadataEntry> for MetadataEntry {
 }
 
 #[cfg(feature = "visitor")]
-#[allow(clippy::useless_conversion)]
+#[allow(clippy::redundant_closure, clippy::useless_conversion)]
 impl From<NodeContext> for html_to_markdown_rs::NodeContext<'_> {
     fn from(val: NodeContext) -> Self {
         html_to_markdown_rs::NodeContext::with_owned_attributes(
             val.node_type.into(),
             val.tag_name.into(),
-            std::collections::BTreeMap::new(),
+            val.attributes
+                .iter()
+                .map(|(k, v)| (k.clone(), v.clone()))
+                .collect::<std::collections::BTreeMap<_, _>>(),
             val.depth,
             val.index_in_parent,
             val.parent_tag.map(Into::into),
@@ -7595,6 +7608,12 @@ impl From<NodeContext> for html_to_markdown_rs::NodeContext<'_> {
 impl From<html_to_markdown_rs::NodeContext<'_>> for NodeContext {
     fn from(val: html_to_markdown_rs::NodeContext<'_>) -> Self {
         Self {
+            attributes: val
+                .attributes()
+                .clone()
+                .into_iter()
+                .map(|(k, v)| (k.into(), v.into()))
+                .collect(),
             node_type: val.node_type.into(),
             tag_name: val.tag_name.to_string(),
             depth: val.depth,
@@ -9104,14 +9123,15 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
     )?;
 
     let conversion_error_class = module.define_error("ConversionError", ruby.exception_standard_error())?;
-    let parse_error_class = module.define_error("ParseError", conversion_error_class)?;
-    let sanitization_error_class = module.define_error("SanitizationError", conversion_error_class)?;
-    let config_error_class = module.define_error("ConfigError", conversion_error_class)?;
-    let io_error_class = module.define_error("IoError", conversion_error_class)?;
-    let panic_error_class = module.define_error("PanicError", conversion_error_class)?;
-    let invalid_input_error_class = module.define_error("InvalidInputError", conversion_error_class)?;
-    let input_too_large_error_class = module.define_error("InputTooLargeError", conversion_error_class)?;
-    let other_error_class = module.define_error("OtherError", conversion_error_class)?;
+    module.define_error("ParseError", conversion_error_class)?;
+    module.define_error("SanitizationError", conversion_error_class)?;
+    module.define_error("ConfigError", conversion_error_class)?;
+    module.define_error("IoError", conversion_error_class)?;
+    module.define_error("PanicError", conversion_error_class)?;
+    module.define_error("InvalidInputError", conversion_error_class)?;
+    module.define_error("InputTooLargeError", conversion_error_class)?;
+    module.define_error("OtherError", conversion_error_class)?;
+    module.funcall::<_, _, magnus::Value>("module_eval", ("class ConversionError\n  module Family; end\n  include Family\n  def self.===(other)\n    super || (equal?(ConversionError) && Family === other)\n  end\nend",))?;
 
     Ok(())
 }

data/lib/html_to_markdown/native.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:09a04cb502ed10072dd986b919b61b19dd89f1684de6b0ec0ad98dbc4a7f9805
+# alef:hash:299c795cac1725ee5096f21cf00f81cdcbd4aff13fae056be3fb44d637926bea
 # To regenerate: alef generate
 # To verify freshness: alef verify
 # frozen_string_literal: true
@@ -386,7 +386,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(url: hash[:url] || hash["url"], title: hash[:title] || hash["title"])
+      new(url: hash.key?(:url) ? hash[:url] : hash["url"], title: hash.key?(:title) ? hash[:title] : hash["title"])
     end
   end
 end
@@ -480,7 +480,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(level: hash[:level] || hash["level"], text: hash[:text] || hash["text"])
+      new(level: hash.key?(:level) ? hash[:level] : hash["level"], text: hash.key?(:text) ? hash[:text] : hash["text"])
     end
   end
   ## A paragraph of text.
@@ -521,7 +521,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(text: hash[:text] || hash["text"])
+      new(text: hash.key?(:text) ? hash[:text] : hash["text"])
     end
   end
   ## A list container (ordered or unordered). Children are `ListItem` nodes.
@@ -562,7 +562,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(ordered: hash[:ordered] || hash["ordered"])
+      new(ordered: hash.key?(:ordered) ? hash[:ordered] : hash["ordered"])
     end
   end
   ## A single list item.
@@ -603,7 +603,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(text: hash[:text] || hash["text"])
+      new(text: hash.key?(:text) ? hash[:text] : hash["text"])
     end
   end
   ## A table with structured cell data.
@@ -644,7 +644,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(grid: hash[:grid] || hash["grid"])
+      new(grid: hash.key?(:grid) ? hash[:grid] : hash["grid"])
     end
   end
   ## An image element.
@@ -692,9 +692,9 @@ module HtmlToMarkdown
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
       new(
-        description: hash[:description] || hash["description"],
-        src: hash[:src] || hash["src"],
-        image_index: hash[:image_index] || hash["image_index"]
+        description: hash.key?(:description) ? hash[:description] : hash["description"],
+        src: hash.key?(:src) ? hash[:src] : hash["src"],
+        image_index: hash.key?(:image_index) ? hash[:image_index] : hash["image_index"]
       )
     end
   end
@@ -739,7 +739,10 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(text: hash[:text] || hash["text"], language: hash[:language] || hash["language"])
+      new(
+        text: hash.key?(:text) ? hash[:text] : hash["text"],
+        language: hash.key?(:language) ? hash[:language] : hash["language"]
+      )
     end
   end
   ## A block quote container.
@@ -859,7 +862,10 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(term: hash[:term] || hash["term"], definition: hash[:definition] || hash["definition"])
+      new(
+        term: hash.key?(:term) ? hash[:term] : hash["term"],
+        definition: hash.key?(:definition) ? hash[:definition] : hash["definition"]
+      )
     end
   end
   ## A raw block preserved as-is (e.g. `<script>`, `<style>` content).
@@ -903,7 +909,10 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(format: hash[:format] || hash["format"], content: hash[:content] || hash["content"])
+      new(
+        format: hash.key?(:format) ? hash[:format] : hash["format"],
+        content: hash.key?(:content) ? hash[:content] : hash["content"]
+      )
     end
   end
   ## A block of key-value metadata pairs (from `<head>` meta tags).
@@ -944,7 +953,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(entries: hash[:entries] || hash["entries"])
+      new(entries: hash.key?(:entries) ? hash[:entries] : hash["entries"])
     end
   end
   ## A section grouping container (auto-generated from heading hierarchy).
@@ -992,9 +1001,9 @@ module HtmlToMarkdown
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
       new(
-        label: hash[:label] || hash["label"],
-        heading_level: hash[:heading_level] || hash["heading_level"],
-        heading_text: hash[:heading_text] || hash["heading_text"]
+        label: hash.key?(:label) ? hash[:label] : hash["label"],
+        heading_level: hash.key?(:heading_level) ? hash[:heading_level] : hash["heading_level"],
+        heading_text: hash.key?(:heading_text) ? hash[:heading_text] : hash["heading_text"]
       )
     end
   end
@@ -1081,7 +1090,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(value: hash[:output] || hash["output"])
+      new(value: hash.key?(:output) ? hash[:output] : hash["output"])
     end
   end
   ## Skip this element entirely (don't output anything)
@@ -1156,7 +1165,7 @@ module HtmlToMarkdown
     # @return [self]
     sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
     def self.from_hash(hash)
-      new(value: hash[:output] || hash["output"])
+      new(value: hash.key?(:output) ? hash[:output] : hash["output"])
     end
   end
 end

data/lib/html_to_markdown/version.rb

@@ -1,10 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:2af93614191f5e65ab3e6f136720482baa1b1ccd900ee7561aeb92a517ef3fe1
+# alef:hash:619922d1aadc86f33a41a722ca732e9be4b5b43e722e085969152b4b5dc3c502
 # To regenerate: alef generate
 # To verify freshness: alef verify
 # frozen_string_literal: true
 
 module HtmlToMarkdown
   ## The version string for this package.
-  VERSION = "3.19.0"
+  VERSION = "3.21.0"
 end

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:0715469498b948fa0fede0134e676b43663986d359510ac029708f761e5dd5eb
+# alef:hash:3268ce0b667ca8b7ee33bab52a6acdac2751438fa66a49e6165b34ea272253be
 # To regenerate: alef generate
 # To verify freshness: alef verify
 
@@ -238,9 +238,9 @@ def initialize: (href: String, text: String, ?title: String, link_type: enum_Lin
         attr_reader index_in_parent: Integer
         attr_reader parent_tag: String?
         attr_reader is_inline: bool
+    attr_reader attributes: Hash[String, String]
 
-    def initialize: (node_type: enum_NodeType, tag_name: String, depth: Integer, index_in_parent: Integer, ?parent_tag: String, is_inline: bool) -> void
-def attributes: () -> Hash[String, String]
+def initialize: (node_type: enum_NodeType, tag_name: String, depth: Integer, index_in_parent: Integer, ?parent_tag: String, is_inline: bool, ?attributes: Hash[String, String]) -> void
     def into_owned: () -> NodeContext
     end
 
@@ -451,7 +451,7 @@ def initialize: (?rows: Integer, ?cols: Integer, ?cells: Array[GridCell]) -> voi
     def link?: () -> bool
 
     def self.from_hash: (untyped hash) -> untyped
-    def self.new: (url: String, title: String) -> AnnotationKindLink
+    def self.new: (url: String, title: String?) -> AnnotationKindLink
     end
 
     type enum_CodeBlockStyle = :Indented | :Backticks | :Tildes
@@ -610,7 +610,7 @@ def initialize: (?rows: Integer, ?cols: Integer, ?cells: Array[GridCell]) -> voi
     def group?: () -> bool
 
     def self.from_hash: (untyped hash) -> untyped
-    def self.new: (description: String, src: String, image_index: Integer) -> NodeContentImage
+    def self.new: (description: String?, src: String?, image_index: Integer?) -> NodeContentImage
     end
 
     class NodeContentCode
@@ -633,7 +633,7 @@ def initialize: (?rows: Integer, ?cols: Integer, ?cells: Array[GridCell]) -> voi
     def group?: () -> bool
 
     def self.from_hash: (untyped hash) -> untyped
-    def self.new: (text: String, language: String) -> NodeContentCode
+    def self.new: (text: String, language: String?) -> NodeContentCode
     end
 
     class NodeContentQuote
@@ -765,7 +765,7 @@ def self.new: (entries: Array[MetadataEntry]) -> NodeContentMetadataBlock
     def group?: () -> bool
 
     def self.from_hash: (untyped hash) -> untyped
-    def self.new: (label: String, heading_level: Integer, heading_text: String) -> NodeContentGroup
+    def self.new: (label: String?, heading_level: Integer?, heading_text: String?) -> NodeContentGroup
     end
 
     type enum_NodeType = :Text | :Element | :Heading | :Paragraph | :Div | :Blockquote | :Pre | :Hr | :List | :ListItem | :DefinitionList | :DefinitionTerm | :DefinitionDescription | :Table | :TableRow | :TableCell | :TableHeader | :TableBody | :TableHead | :TableFoot | :Link | :Image | :Strong | :Em | :Code | :Strikethrough | :Underline | :Subscript | :Superscript | :Mark | :Small | :Br | :Span | :Article | :Section | :Nav | :Aside | :Header | :Footer | :Main | :Figure | :Figcaption | :Time | :Details | :Summary | :Form | :Input | :Select | :Option | :Button | :Textarea | :Label | :Fieldset | :Legend | :Audio | :Video | :Picture | :Source | :Iframe | :Svg | :Canvas | :Ruby | :Rt | :Rp | :Abbr | :Kbd | :Samp | :Var | :Cite | :Q | :Del | :Ins | :Data | :Meter | :Progress | :Output | :Template | :Slot | :Html | :Head | :Body | :Title | :Meta | :LinkTag | :Style | :Script | :Base | :Custom

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 3.19.0
+  version: 3.21.0
 platform: ruby
 authors:
 - Na'aman Hirschfeld
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-10-27 00:00:00.000000000 Z
+date: 2026-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -83,7 +83,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.2.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="