html-to-markdown 2.9.1 → 2.10.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8e4b858a910ecf3f0bdbc020b6815e59e4350ff603a45480adf52bd0cc8f1af7
-  data.tar.gz: 75c4596c2e3d7490b317e31869bfe0cf995ebc7fb5ed14a4011b1829ff2d16b2
+  metadata.gz: d3d074895d2d481529034534a5d788509ec845973fcfb5ed9b987218f1b526c9
+  data.tar.gz: f43ecf9a97013f806132fd9dbec4cc58ad644feeaef8cd8ac0f3409c9bdb4675
 SHA512:
-  metadata.gz: 7178c3fcf3abe87a2b49350c7a328f2ce31755ad2907c6a6920e60d17700e3cbc475078f9505bf146a1b6358375e79c04421a1e69b2e3666db9a2a15bde54947
-  data.tar.gz: 5eb86a9c629a0d4bc0f8cb0ee05562f28ad5c4c73bcde98013b5283281df0064de489ee0130911cfe24c8817fcad69a96da00c89be278f3d784e0db45fdc68b9
+  metadata.gz: f702eb6c46d5c8cb15d1dfcf20fc7af0fa31ca499de696c79266e9763fa1b4e6914fdba8d1c33543b8e45303474c90d0ef1840f1c2af8e2526f390126b91c6f0
+  data.tar.gz: 7213faa4510619678b4336affd9f913cca36414526669b79db136c3960ed9d50b1483d5c31620d41e03496dd5c92938bdb28cb91e0dc073d377b2a72d4d2ad39

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    html-to-markdown (2.9.1)
+    html-to-markdown (2.10.1)
       rb_sys (>= 0.9, < 1.0)
 
 GEM
@@ -24,7 +24,7 @@ GEM
     base64 (0.3.0)
     bigdecimal (3.3.1)
     concurrent-ruby (1.3.5)
-    connection_pool (2.5.4)
+    connection_pool (2.5.5)
     csv (3.3.5)
     diff-lcs (1.6.2)
     drb (2.2.3)

data/ext/html-to-markdown-rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "2.9.1"
+version = "2.10.1"
 edition = "2024"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 license = "MIT"
@@ -21,7 +21,7 @@ crate-type = ["cdylib", "rlib"]
 default = []
 
 [dependencies]
-html-to-markdown-rs = { version = "2.9.1", features = ["inline-images"] }
+html-to-markdown-rs = { version = "2.10.1", features = ["inline-images"] }
 magnus = { git = "https://github.com/matsadler/magnus", rev = "f6db11769efb517427bf7f121f9c32e18b059b38", features = ["rb-sys"] }
 
 [dev-dependencies]

data/ext/html-to-markdown-rb/native/src/lib.rs

@@ -2,7 +2,7 @@ use html_to_markdown_rs::{
     CodeBlockStyle, ConversionOptions, HeadingStyle, HighlightStyle, HtmlExtraction, InlineImage, InlineImageConfig,
     InlineImageFormat, InlineImageSource, InlineImageWarning, ListIndentType, NewlineStyle, PreprocessingOptions,
     PreprocessingPreset, WhitespaceMode, convert as convert_inner,
-    convert_with_inline_images as convert_with_inline_images_inner, error::ConversionError,
+    convert_with_inline_images as convert_with_inline_images_inner, error::ConversionError, safety::guard_panic,
 };
 use magnus::prelude::*;
 use magnus::r_hash::ForEach;
@@ -17,6 +17,9 @@ const DEFAULT_INLINE_IMAGE_LIMIT: u64 = 5 * 1024 * 1024;
 fn conversion_error(err: ConversionError) -> Error {
     match err {
         ConversionError::ConfigError(msg) => arg_error(msg),
+        ConversionError::Panic(message) => {
+            runtime_error(format!("html-to-markdown panic during conversion: {message}"))
+        }
         other => runtime_error(other.to_string()),
     }
 }
@@ -390,7 +393,7 @@ fn convert_fn(ruby: &Ruby, args: &[Value]) -> Result<String, Error> {
     let html = parsed.required.0;
     let options = build_conversion_options(ruby, parsed.optional.0)?;
 
-    convert_inner(&html, Some(options)).map_err(conversion_error)
+    guard_panic(|| convert_inner(&html, Some(options))).map_err(conversion_error)
 }
 
 fn options_handle_fn(ruby: &Ruby, args: &[Value]) -> Result<OptionsHandle, Error> {
@@ -403,7 +406,9 @@ fn convert_with_options_handle_fn(_ruby: &Ruby, args: &[Value]) -> Result<String
     let parsed = scan_args::<(String, &OptionsHandle), (), (), (), (), ()>(args)?;
     let html = parsed.required.0;
     let handle = parsed.required.1;
-    convert_inner(&html, Some(handle.0.clone())).map_err(conversion_error)
+    let options = handle.0.clone();
+
+    guard_panic(|| convert_inner(&html, Some(options))).map_err(conversion_error)
 }
 
 fn convert_with_inline_images_fn(ruby: &Ruby, args: &[Value]) -> Result<Value, Error> {
@@ -412,7 +417,8 @@ fn convert_with_inline_images_fn(ruby: &Ruby, args: &[Value]) -> Result<Value, E
     let options = build_conversion_options(ruby, parsed.optional.0)?;
     let config = build_inline_image_config(ruby, parsed.optional.1)?;
 
-    let extraction = convert_with_inline_images_inner(&html, Some(options), config).map_err(conversion_error)?;
+    let extraction =
+        guard_panic(|| convert_with_inline_images_inner(&html, Some(options), config)).map_err(conversion_error)?;
 
     extraction_to_value(ruby, extraction)
 }

data/lib/html_to_markdown/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HtmlToMarkdown
-  VERSION = '2.9.1'
+  VERSION = '2.10.1'
 end

data/spec/convert_spec.rb

@@ -35,4 +35,43 @@ RSpec.describe HtmlToMarkdown do
       expect(result).to include('# Hello #')
     end
   end
+
+  describe 'panic handling' do
+    context 'when a Rust panic would occur' do
+      it 'catches panics in convert method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+
+        begin
+          result = described_class.convert(malformed_html)
+          expect(result).to be_a(String)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+
+      it 'catches panics in convert_with_options method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+        handle = described_class.options(heading_style: :atx)
+
+        begin
+          result = described_class.convert_with_options(malformed_html, handle)
+          expect(result).to be_a(String)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+
+      it 'catches panics in convert_with_inline_images method' do
+        malformed_html = "#{'<' * 100_000}div#{'>' * 100_000}"
+
+        begin
+          result = described_class.convert_with_inline_images(malformed_html)
+          expect(result).to be_a(Hash)
+          expect(result).to include(:markdown, :inline_images, :warnings)
+        rescue RuntimeError => e
+          expect(e.message).to match(/html-to-markdown panic during conversion/)
+        end
+      end
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 2.9.1
+  version: 2.10.1
 platform: ruby
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-11-21 00:00:00.000000000 Z
+date: 2025-12-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys