rusteerio 1.1.0 → 1.1.1

package/Cargo.lock

@@ -720,7 +720,7 @@ dependencies = [
 
 [[package]]
 name = "rusteerio"
-version = "1.1.0"
+version = "1.1.1"
 dependencies = [
  "ego-tree",
  "html5ever",

package/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "rusteerio"
-version = "1.1.0"
+version = "1.1.1"
 edition = "2021"
 description = "Rust HTML5 parser and CSS selector engine for the rusteerio Node.js package"
 license = "MIT"

package/THIRD_PARTY_NOTICES.md

@@ -4,7 +4,7 @@ This file preserves third-party license and attribution notices for the Rust nat
 
 Generated by `node scripts/generate-notices.mjs` from `cargo metadata --locked`, crate license files, and the pinned supplemental sources recorded in `scripts/notices/sources.json`. It includes build dependencies and dependencies for all target platforms; a particular binary may use a subset. Identical notice texts are reproduced once and referenced below. The html5ever, markup5ever and html5gum crates contain local observer-hook and opt-in UTF-16 transport patches; their complete patched source and original notices are included in `native/vendor`. Other dependency source files are unmodified.
 
-Cargo.lock SHA-256: `a7962957958e0640ea9e40f025e877864c03bd5934a1ca2e19df80a5481d72ff`.
+Cargo.lock SHA-256: `db632d8fb3f5612f4e34f742fdde2b58d27cd17b7132583c28f183f00005ae19`.
 
 ## Source availability
 

package/native/src/snapshot.rs

@@ -24,8 +24,9 @@ use crate::id_hash::IdMap;
 use crate::NativeDocument;
 
 pub(crate) const STRIDE: usize = 15;
-/// Text longer than this stays out of snapshots: such nodes, mostly inline
-/// scripts and styles, are read individually if JavaScript asks for them.
+/// Text or attribute values longer than this stay out of snapshots: such
+/// nodes, mostly inline scripts, styles, SVG paths and embedded data, are read
+/// individually if JavaScript asks for them.
 const LARGE_TEXT_BYTES: usize = 4096;
 const ABSENT: u32 = u32::MAX;
 const HAS_START_INDEX: u32 = 1;
@@ -297,8 +298,17 @@ impl Builder {
             None => {}
         }
         fields[8] = (self.attributes.len() / 2) as u32;
-        fields[9] = node.attribs.len() as u32;
-        for (name, value) in &node.attribs {
+        let has_large_attribute = node.attribs.values().any(|value| {
+            value
+                .as_str()
+                .is_some_and(|value| value.len() > LARGE_TEXT_BYTES)
+        });
+        if has_large_attribute {
+            flags |= OPAQUE;
+        } else {
+            fields[9] = node.attribs.len() as u32;
+        }
+        for (name, value) in node.attribs.iter().filter(|_| !has_large_attribute) {
             let Some(value) = value.as_str() else {
                 flags |= OPAQUE;
                 break;
@@ -454,12 +464,20 @@ impl Builder {
                         _ => tag_type,
                     };
                     fields[6] = self.local_name(&element.name.local) + 1;
-                    for (attribute, value) in &element.attrs {
-                        let attribute = self.local_name(&attribute.local);
-                        let value = self.string(value);
-                        self.attributes.extend_from_slice(&[attribute, value]);
+                    if element
+                        .attrs
+                        .iter()
+                        .any(|(_, value)| value.len() > LARGE_TEXT_BYTES)
+                    {
+                        flags |= OPAQUE;
+                    } else {
+                        for (attribute, value) in &element.attrs {
+                            let attribute = self.local_name(&attribute.local);
+                            let value = self.string(value);
+                            self.attributes.extend_from_slice(&[attribute, value]);
+                        }
+                        fields[9] = element.attrs.len() as u32;
                     }
-                    fields[9] = element.attrs.len() as u32;
                     fields[13] = self.namespace(&element.name.ns);
                     flags |= HAS_NAMESPACE | EMPTY_ATTRIBUTE_MAPS;
                 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rusteerio",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "description": "Cheerio-compatible HTML processing with a Rust engine and parallel, non-blocking extraction",
   "license": "MIT",
   "repository": {