html-to-markdown 3.6.10 → 3.6.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 91c79ad314d7c648cf3f5d4f826170c1c5234a889a325597887b39f04f42ead9
-  data.tar.gz: e540404974b9692e9adce99200cbab29b38c835a7bfcf3bf56534e199188b38f
+  metadata.gz: 70d67eb7df250429349103b104af5bb9118d742d947020ffc9d0768fc632a086
+  data.tar.gz: ca87f0babd9da500f417d89727e143c9f0ebbaef5766184fd45737e39794a0a5
 SHA512:
-  metadata.gz: 3278ce32f1ee099f7e96e98b5ba9f7e46c58a822aa2d32f24d0443f032036745b6e8eb471c0fbe8a102b505fd4bb12ee0af22aa49afc6c88a0535968a25b1482
-  data.tar.gz: 1654d4528e34ec8b434f3acd55713cc62f428cbabb3874285125640ba6b19e72478efaeef921acdaf2183e36821299f22f632889afc09161bf66695745b88cd5
+  metadata.gz: '090e40fd52c42ad51e9988d14c195482a857d2793d7cebe746c83e44e0376aa5954298aa1ba4abd7063f7fb69eedcd3cc1a9bb0b447324a1dd5ef5c143343006'
+  data.tar.gz: db8c7e520b5bde43566ff153d77ef56a401fb530ebbc329eb23dbad46b4e6bbfef892d50d8515158a4c10696eca408161722206e5842403812dd3a89aa6e9ecc

data/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -161,7 +161,7 @@ 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)
+tables   = result[:tables]        # Structured table data
 document = result[:document]      # Document-level info
 images   = result[:images]        # Extracted images
 warnings = result[:warnings]      # Any conversion warnings
@@ -171,14 +171,13 @@ warnings = result[:warnings]      # Any conversion warnings
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `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`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -205,11 +204,13 @@ require 'html_to_markdown'
 html = "<p>This is <strong>bold</strong> and <em>italic</em> text.</p>"
 
 # Default Markdown output
-markdown = HtmlToMarkdown.convert(html)
+markdown_result = HtmlToMarkdown.convert(html)
+markdown = markdown_result[:content]
 # Result: "This is **bold** and *italic* text."
 
 # Djot output
-djot = HtmlToMarkdown.convert(html, output_format: 'djot')
+djot_result = HtmlToMarkdown.convert(html, output_format: 'djot')
+djot = djot_result[:content]
 # Result: "This is *bold* and _italic_ text."
 ```
 
@@ -224,7 +225,8 @@ 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 = HtmlToMarkdown.convert(html, output_format: 'plain')
+plain = result[:content]
 # Result: "Title\n\nThis is bold and italic text."
 ```
 
@@ -309,13 +311,13 @@ markdown = result[:content]
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -343,5 +345,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 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)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

data/ext/html_to_markdown_rb/Cargo.toml

@@ -1,7 +1,7 @@
 
 [package]
 name = "html-to-markdown-rb"
-version = "3.6.10"
+version = "3.6.11"
 edition = "2024"
 license = "MIT"
 [workspace]

data/ext/html_to_markdown_rb/native/Cargo.lock

@@ -263,7 +263,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rb"
-version = "3.6.10"
+version = "3.6.11"
 dependencies = [
  "async-trait",
  "html-to-markdown-rs",
@@ -276,9 +276,9 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "3.6.10"
+version = "3.6.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "061bf88c7bb26bcad8f42ff109663b65e4ccdc7844a07acf7a1769712ca72277"
+checksum = "32027e930a32dd01839a07405eae5e482ff507ccc4ca6fd1a89091304bd7ba22"
 dependencies = [
  "ahash",
  "astral-tl",

data/ext/html_to_markdown_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "3.6.10"
+version = "3.6.11"
 edition = "2024"
 license = "MIT"
 description = "High-performance HTML to Markdown converter"
@@ -16,9 +16,16 @@ name = "html_to_markdown_rb"
 path = "../src/lib.rs"
 crate-type = ["cdylib"]
 
+[features]
+default = ["inline-images", "metadata", "testkit", "visitor"]
+inline-images = ["html-to-markdown-rs/inline-images"]
+metadata = ["html-to-markdown-rs/metadata"]
+testkit = ["html-to-markdown-rs/testkit"]
+visitor = ["html-to-markdown-rs/visitor"]
+
 [dependencies]
 async-trait = "0.1"
-html-to-markdown-rs = { version = "3.6.10", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
+html-to-markdown-rs = { version = "3.6.11", 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:4ba300ecbb725eb266bbcd4f47e9bc50e560372ba8b6f9d9f93c785e8758cdc8
+// alef:hash:7d62cf0c304e24a167a710e943106d8203118ef6cb83aa812f3133c24bfa7c7f
 // 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:4ba300ecbb725eb266bbcd4f47e9bc50e560372ba8b6f9d9f93c785e8758cdc8
+# alef:hash:7d62cf0c304e24a167a710e943106d8203118ef6cb83aa812f3133c24bfa7c7f
 # 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:4ba300ecbb725eb266bbcd4f47e9bc50e560372ba8b6f9d9f93c785e8758cdc8
+# alef:hash:7d62cf0c304e24a167a710e943106d8203118ef6cb83aa812f3133c24bfa7c7f
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
 module HtmlToMarkdown
   ## The version string for this package.
-  VERSION = "3.6.10"
+  VERSION = "3.6.11"
 end

data/lib/html_to_markdown.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:4ba300ecbb725eb266bbcd4f47e9bc50e560372ba8b6f9d9f93c785e8758cdc8
+# alef:hash:7d62cf0c304e24a167a710e943106d8203118ef6cb83aa812f3133c24bfa7c7f
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:4ba300ecbb725eb266bbcd4f47e9bc50e560372ba8b6f9d9f93c785e8758cdc8
+# alef:hash:7d62cf0c304e24a167a710e943106d8203118ef6cb83aa812f3133c24bfa7c7f
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 3.6.10
+  version: 3.6.11
 platform: ruby
 authors:
 - Na'aman Hirschfeld <naaman@kreuzberg.dev>