commonmarker 2.10.0 → 2.10.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 23a7f4c3d26ba5e9b9301c9af8db67520fdda959f6cf8faab5564e9276d8d7bc
-  data.tar.gz: 7ee7de8566813969b327b94d3e0c8b6a8e536a38906522cb7eb9f13206186811
+  metadata.gz: 4d5e959f519ad6befde6dac13c3d66d8df0eb8a5607553466d49544d75fb53dd
+  data.tar.gz: c4b1fa07305b5781a5a4ddb94090e474221df13ca946724068407b925d7c7e57
 SHA512:
-  metadata.gz: eafbbb68ab07ac0ab161437cb6327ea55e232d6c412ea1be6f7d4b6474fae61607d905efc028000c5be2a9c193719e7b5dda16b69d4be2dbcdef112c65c82ed5
-  data.tar.gz: f2c79a17c4dec72cdd65979d59952097a286f125a593935986088788cb936f1a99e0dc13f2493afc8c96e309dc175900989956e39fa0044bc9bc8bbd893578c2
+  metadata.gz: 0e91a96c44c65c948f9e4631ca57f4e0a735f6e23ca5f8eb76e8d5a1ae7f5909b102712501a3a01abc25109e18830333f7557ed676a87bd1b458bdc6f0ed61a3
+  data.tar.gz: 858617c6e1444fafaa3fa8b70ee128ed4ad4fe9e5802ff1155adb2102a209cc53d4721ae85c78392fc2f26a7b8c386bcdd6a84cc7e0e38411ddae389bb06e87e

data/Cargo.lock

@@ -47,7 +47,7 @@ dependencies = [
  "regex",
  "rustc-hash",
  "shlex 1.3.0",
- "syn",
+ "syn 2.0.118",
 ]
 
 [[package]]
@@ -124,23 +124,22 @@ dependencies = [
  "magnus",
  "rb-allocator",
  "rb-sys",
- "rctree",
  "syntect",
  "typed-arena",
 ]
 
 [[package]]
 name = "comrak"
-version = "0.54.0"
+version = "0.56.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d5910408554659ed848ff469e67ec83b30f179e72cec286cfdae64d1616f466"
+checksum = "2544c4d6b6da7d54e95ac2833b464bf3dffa0666237868f2bf4ec5e11c9ba8cc"
 dependencies = [
  "caseless",
  "emojis",
  "entities",
  "finl_unicode",
- "jetscii",
- "phf",
+ "memchr-n",
+ "phf 0.14.0",
  "phf_codegen",
  "rustc-hash",
  "smallvec",
@@ -171,11 +170,11 @@ checksum = "91622ff5e7162018101f2fea40d6ebf4a78bbe5a49736a2020649edf9693679e"
 
 [[package]]
 name = "emojis"
-version = "0.8.2"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0a4d5d50b0b58df5173d8ff1192b4d1422ceae5d981b30d4b6f8ed1d673a2bc4"
+checksum = "0b1514ced566c94991ed9563258ecf61e311fd773bf0a3f20606830386bf66e3"
 dependencies = [
- "phf",
+ "phf 0.13.1",
 ]
 
 [[package]]
@@ -207,6 +206,23 @@ version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
 
+[[package]]
+name = "fearless_simd"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3296eb97d869113eaf148a6bdf01884e90b3828ad7ae2340b0f93362fc158611"
+
+[[package]]
+name = "fearless_simd_macros"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3e91d94c6885390b81782d7ee60fd6583b33907333a8b340de25ccf468353315"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.9",
+]
+
 [[package]]
 name = "find-msvc-tools"
 version = "0.1.9"
@@ -272,12 +288,6 @@ version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
-[[package]]
-name = "jetscii"
-version = "0.5.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47f142fe24a9c9944451e8349de0a56af5f3e7226dc46f3ed4d4ecc0b85af75e"
-
 [[package]]
 name = "lazy_static"
 version = "1.5.0"
@@ -308,9 +318,9 @@ checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f"
 
 [[package]]
 name = "magnus"
-version = "0.8.2"
+version = "0.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b36a5b126bbe97eb0d02d07acfeb327036c6319fd816139a49824a83b7f9012"
+checksum = "40ef424404d166cbb71c8b8d19c9c589c748c4547c1afa1928c5504299f6c713"
 dependencies = [
  "magnus-macros",
  "rb-sys",
@@ -320,13 +330,13 @@ dependencies = [
 
 [[package]]
 name = "magnus-macros"
-version = "0.8.0"
+version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47607461fd8e1513cb4f2076c197d8092d921a1ea75bd08af97398f593751892"
+checksum = "9dafde2eeb66f090e0f326112323eb8324b12cb32b5d1210e541d3df6b0ce77e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.118",
 ]
 
 [[package]]
@@ -335,6 +345,16 @@ version = "2.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
 
+[[package]]
+name = "memchr-n"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1805571b8e7b1284ad43f27c88477840c1c0e5807c150021ac83d2228806540e"
+dependencies = [
+ "fearless_simd",
+ "fearless_simd_macros",
+]
+
 [[package]]
 name = "minimal-lexical"
 version = "0.2.1"
@@ -401,28 +421,37 @@ version = "0.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1562dc717473dbaa4c1f85a36410e03c047b2e7df7f45ee938fbef64ae7fadf"
 dependencies = [
- "phf_shared",
+ "phf_shared 0.13.1",
+]
+
+[[package]]
+name = "phf"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "010378780309880b08997fae13be7834dba947d36393bd372f2b1556deb2a2f6"
+dependencies = [
+ "phf_shared 0.14.0",
  "serde",
 ]
 
 [[package]]
 name = "phf_codegen"
-version = "0.13.1"
+version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
+checksum = "41b585a510fb76fdebead6897982ef2a03a21d8e6cbcca904999742a4afc6ffe"
 dependencies = [
  "phf_generator",
- "phf_shared",
+ "phf_shared 0.14.0",
 ]
 
 [[package]]
 name = "phf_generator"
-version = "0.13.1"
+version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "135ace3a761e564ec88c03a77317a7c6b80bb7f7135ef2544dbe054243b89737"
+checksum = "aeb62e0959d5a1bebc965f4d15d9e2b7cea002b6b0f5ba8cde6cc26738467100"
 dependencies = [
  "fastrand",
- "phf_shared",
+ "phf_shared 0.14.0",
 ]
 
 [[package]]
@@ -434,6 +463,15 @@ dependencies = [
  "siphasher",
 ]
 
+[[package]]
+name = "phf_shared"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c6fd9027e2d9319be6349febd1db4e8d02aa544921200c9b777720ac34a3aa89"
+dependencies = [
+ "siphasher",
+]
+
 [[package]]
 name = "pkg-config"
 version = "0.3.33"
@@ -497,18 +535,18 @@ dependencies = [
 
 [[package]]
 name = "rb-sys"
-version = "0.9.128"
+version = "0.9.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45ca28513560e56cfb79a62b1fce363c73af170a182024ce880c77ee9429920a"
+checksum = "02faf625bb10ba893e3ae620f19c9fb1b5f8fcae0fe4eb86bb3f2230fad75edb"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.128"
+version = "0.9.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce04b2c55eff3a21aaa623fcc655d94373238e72cac6b3e1a3641ff31649f99a"
+checksum = "05be6f9c86fe5482808162826f6c047d093b3670582296c770de1d94f8066694"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -516,7 +554,7 @@ dependencies = [
  "quote",
  "regex",
  "shell-words",
- "syn",
+ "syn 2.0.118",
 ]
 
 [[package]]
@@ -525,12 +563,6 @@ version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cca7ad6a7e21e72151d56fe2495a259b5670e204c3adac41ee7ef676ea08117a"
 
-[[package]]
-name = "rctree"
-version = "0.6.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e03e7866abec1101869ffa8e2c8355c4c2419d0214ece0cc3e428e5b94dea6e9"
-
 [[package]]
 name = "regex"
 version = "1.13.0"
@@ -607,7 +639,7 @@ checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.118",
 ]
 
 [[package]]
@@ -670,6 +702,17 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "syn"
+version = "3.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d78c8dee4c7bf0e14673097256fed6142ce9d3b85a408189d07482442145823b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
 [[package]]
 name = "syntect"
 version = "5.3.0"
@@ -709,7 +752,7 @@ checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.118",
 ]
 
 [[package]]

data/README.md

@@ -5,7 +5,7 @@ Ruby wrapper for Rust's [comrak](https://github.com/kivikakk/comrak) crate.
 It passes all of the CommonMark test suite, and is therefore spec-complete. It also includes extensions to the CommonMark spec as documented in the [GitHub Flavored Markdown spec](http://github.github.com/gfm/), such as support for tables, strikethroughs, and autolinking.
 
 > [!NOTE]
-> By default, the following extensions are enabled for end user convenience: `strikethrough`, `tagfilter`, `table`, `autolink`, `tasklist` (all from the [GFM spec](http://github.github.com/gfm/)), and `shortcodes`. The `syntax_highlighter` plugin is also enabled by default, using the `"base16-ocean.dark"` theme.
+> By default, the following extensions are enabled for end user convenience: `strikethrough`, `table`, `autolink`, `tasklist` (all from the [GFM spec](http://github.github.com/gfm/)), and `shortcodes`. The `syntax_highlighter` plugin is also enabled by default, using the `"base16-ocean.dark"` theme.
 >
 > For more information on the available options and extensions, see [the documentation below](#options-and-plugins).
 
@@ -184,6 +184,7 @@ Note that there is a distinction in comrak for "parse" options and "render" opti
 | `leave_footnote_definitions` | Allow footnote definitions to remain in their original positions instead of being moved to the document's end (only affects AST)            | `false` |
 | `ignore_setext`              | Ignores setext-style headings.                                                                                                              | `false` |
 | `sourcepos_chars`            | Use character-based column tracking in source positions instead of byte-based. Relevant for multi-byte UTF-8 documents with `sourcepos`.    | `false` |
+| `max_nesting_depth`          | The deepest a node may nest below the document. Deeper documents raise `Commonmarker::NestingDepthExceededError` instead of being parsed.  | `1000`  |
 
 ### Render options
 
@@ -218,7 +219,6 @@ Commonmarker.to_html('"Hi *there*"', options: {
 | Name                          | Description                                                                                                         | Default |
 | ----------------------------- | ------------------------------------------------------------------------------------------------------------------- | ------- |
 | `strikethrough`               | Enables the [strikethrough extension](https://github.github.com/gfm/#strikethrough-extension-) from the GFM spec.   | `true`  |
-| `tagfilter`                   | Enables the [tagfilter extension](https://github.github.com/gfm/#disallowed-raw-html-extension-) from the GFM spec. | `true`  |
 | `table`                       | Enables the [table extension](https://github.github.com/gfm/#tables-extension-) from the GFM spec.                  | `true`  |
 | `autolink`                    | Enables the [autolink extension](https://github.github.com/gfm/#autolinks-extension-) from the GFM spec.            | `true`  |
 | `tasklist`                    | Enables the [task list extension](https://github.github.com/gfm/#task-list-items-extension-) from the GFM spec.     | `true`  |

data/ext/commonmarker/Cargo.toml

@@ -6,12 +6,11 @@ rust-version = "1.75.0"
 publish = false
 
 [dependencies]
-magnus = { version = "0.8", features = ["rb-sys"] }
+magnus = { version = "0.9", features = ["rb-sys"] }
 rb-sys = { version = "*", default-features = false, features = [
     "stable-api-compiled-fallback",
 ] }
 typed-arena = "2.0"
-rctree = "0.6"
 rb-allocator = "0.9"
 
 syntect = { version = "5.3", default-features = false, features = [
@@ -21,7 +20,7 @@ syntect = { version = "5.3", default-features = false, features = [
 
 # Everywhere except Windows: Oniguruma, the faster engine.
 [target.'cfg(not(windows))'.dependencies]
-comrak = { version = "0.54", default-features = false, features = [
+comrak = { version = "0.56", default-features = false, features = [
     "shortcodes",
     "syntect-onig",
 ] }
@@ -30,7 +29,7 @@ comrak = { version = "0.54", default-features = false, features = [
 # linking a second copy (onig_sys) collides at link time and segfaults (xref #467).
 # syntect-fancy swaps in the pure-Rust fancy-regex backend instead.
 [target.'cfg(windows)'.dependencies]
-comrak = { version = "0.54", default-features = false, features = [
+comrak = { version = "0.56", default-features = false, features = [
     "shortcodes",
     "syntect-fancy",
 ] }

data/ext/commonmarker/src/lib.rs

@@ -16,7 +16,9 @@ use typed_arena::Arena;
 
 use crate::options::{iterate_extension_options, iterate_parse_options, iterate_render_options};
 
+mod nesting;
 mod node;
+mod rctree;
 mod utils;
 
 pub const EMPTY_STR: &str = "";
@@ -55,6 +57,8 @@ fn commonmark_parse(ruby: &Ruby, args: &[Value]) -> Result<CommonmarkerNode, mag
     )?;
     let (rb_parse, rb_render, rb_extension) = kwargs.optional;
 
+    let max_nesting_depth = nesting::max_nesting_depth(ruby, rb_parse)?;
+
     let mut comrak_parse_options = comrak::options::Parse::default();
     let mut comrak_render_options = comrak::options::Render::default();
     let mut comrak_extension_options = comrak::options::Extension::default();
@@ -78,7 +82,7 @@ fn commonmark_parse(ruby: &Ruby, args: &[Value]) -> Result<CommonmarkerNode, mag
     let arena = Arena::new();
     let root = parse_document(&arena, commonmark_str, &comrak_options);
 
-    CommonmarkerNode::new_from_comrak_node(root)
+    CommonmarkerNode::new_from_comrak_node(ruby, root, max_nesting_depth)
 }
 
 fn commonmark_to_html(ruby: &Ruby, args: &[Value]) -> Result<RString, magnus::Error> {
@@ -107,6 +111,8 @@ fn commonmark_to_html(ruby: &Ruby, args: &[Value]) -> Result<RString, magnus::Er
     )?;
     let (rb_render, rb_parse, rb_extension, rb_plugins) = kwargs.optional;
 
+    let max_nesting_depth = nesting::max_nesting_depth(ruby, rb_parse)?;
+
     let mut comrak_parse_options = comrak::options::Parse::default();
     let mut comrak_render_options = comrak::options::Render::default();
     let mut comrak_extension_options = comrak::options::Extension::default();
@@ -130,7 +136,9 @@ fn commonmark_to_html(ruby: &Ruby, args: &[Value]) -> Result<RString, magnus::Er
     };
 
     match syntect_adapter {
-        Some(ref adapter) => comrak_plugins.render.codefence_syntax_highlighter = Some(adapter),
+        Some(ref adapter) => {
+            comrak_plugins.render.codefence_syntax_highlighter = Some(adapter.as_ref())
+        }
         None => comrak_plugins.render.codefence_syntax_highlighter = None,
     }
 
@@ -148,6 +156,8 @@ fn commonmark_to_html(ruby: &Ruby, args: &[Value]) -> Result<RString, magnus::Er
     let arena = Arena::new();
     let root = parse_document(&arena, commonmark_str, &comrak_options);
 
+    nesting::check(ruby, root, max_nesting_depth)?;
+
     comrak::html::format_document_with_plugins(root, &comrak_options, &mut writer, &comrak_plugins)
         .map_err(|e| magnus::Error::new(ruby.exception_runtime_error(), e.to_string()))?;
 

data/ext/commonmarker/src/nesting.rs

@@ -0,0 +1,71 @@
+use comrak::arena_tree::NodeEdge;
+use comrak::nodes::AstNode;
+use magnus::value::ReprValue;
+use magnus::{ExceptionClass, Module, RHash, Ruby, TryConvert};
+
+/// Default for the `max_nesting_depth` parse option. Mirrors
+/// `Commonmarker::Config::OPTIONS[:parse][:max_nesting_depth]`, and also applies
+/// when the option is passed as `nil`, which `Commonmarker::Config` strips.
+pub const DEFAULT_MAX_NESTING_DEPTH: usize = 1000;
+
+const PARSE_MAX_NESTING_DEPTH: &str = "max_nesting_depth";
+
+/// Reads the `max_nesting_depth` parse option, falling back to the default.
+pub fn max_nesting_depth(ruby: &Ruby, rb_parse: Option<RHash>) -> Result<usize, magnus::Error> {
+    let value = rb_parse.and_then(|options| options.get(ruby.to_symbol(PARSE_MAX_NESTING_DEPTH)));
+
+    match value {
+        Some(value) if !value.is_nil() => {
+            let depth: i64 = TryConvert::try_convert(value)?;
+            usize::try_from(depth).map_err(|_| {
+                magnus::Error::new(
+                    ruby.exception_arg_error(),
+                    format!("parse option `:max_nesting_depth` must be a non-negative Integer; got {depth}"),
+                )
+            })
+        }
+        _ => Ok(DEFAULT_MAX_NESTING_DEPTH),
+    }
+}
+
+/// The error raised when a document nests deeper than `max_nesting_depth`.
+pub fn exceeded_error(ruby: &Ruby, max_nesting_depth: usize) -> magnus::Error {
+    let class = ruby
+        .define_module("Commonmarker")
+        .and_then(|module| module.const_get::<_, ExceptionClass>("NestingDepthExceededError"));
+
+    match class {
+        Ok(class) => magnus::Error::new(
+            class,
+            format!(
+                "nesting depth exceeds the max_nesting_depth parse option ({max_nesting_depth})"
+            ),
+        ),
+        Err(error) => error,
+    }
+}
+
+/// Fails if any node sits more than `max_nesting_depth` levels below the
+/// document root. `traverse` is iterative, so this is safe on arbitrarily deep
+/// trees.
+pub fn check<'a>(
+    ruby: &Ruby,
+    root: &'a AstNode<'a>,
+    max_nesting_depth: usize,
+) -> Result<(), magnus::Error> {
+    let mut depth: usize = 0;
+
+    for edge in root.traverse() {
+        match edge {
+            NodeEdge::Start(_) => {
+                if depth > max_nesting_depth {
+                    return Err(exceeded_error(ruby, max_nesting_depth));
+                }
+                depth += 1;
+            }
+            NodeEdge::End(_) => depth -= 1,
+        }
+    }
+
+    Ok(())
+}