Marking a tag as an artifact refuses content past the page's decode budget

crates/a11y/src/alt.rs

@@ -50,6 +50,8 @@ pub enum ArtifactError {
     AmbiguousParent,
     #[error("couldn't update the parent tree: {0}")]
     ParentTree(String),
+    #[error("the page has more content than can be edited")]
+    TooLarge,
     #[error(transparent)]
     Cos(#[from] pdfcraft_cos::CosError),
 }
@@ -483,7 +485,23 @@ pub fn mark_tag_artifact(doc: &mut Document, obj: ObjRef) -> Result<(), Artifact
     let pages = pdfcraft_model::pages(doc);
     let page_ref = element.page.ok_or(ArtifactError::NoPage)?;
     let page = pages.iter().find(|page| page.obj == page_ref).ok_or(ArtifactError::NoPage)?;
-    let mut ops = pdfcraft_content::parse(&page_content(doc, &page.dict)).ops;
+    let mut content = Vec::new();
+    if let Some(c) = page.dict.get(b"Contents") {
+        let mut budget = DecodeBudget::page();
+        for data in budget.decode_contents(doc, c) {
+            match data {
+                Ok(data) => {
+                    content.extend_from_slice(&data);
+                    content.push(b' ');
+                }
+                // The page's /Contents is replaced with what was decoded: content past the
+                // budget would be dropped from the page.
+                Err(_) if budget.exhausted() => return Err(ArtifactError::TooLarge),
+                Err(_) => {}
+            }
+        }
+    }
+    let mut ops = pdfcraft_content::parse(&content).ops;
     let mut found = HashSet::new();
     for op in &mut ops {
         let id = (op.op == b"BDC")

crates/a11y/src/tests.rs

@@ -1307,3 +1307,20 @@ fn content_past_the_decode_budget_needs_a_manual_check() {
     assert_eq!(status(&report, Rule::ImageOnly), Status::Manual);
     assert_eq!(status(&report, Rule::TaggedContent), Status::Manual);
 }
+
+/// Marking a tag as an artifact replaces the page's content with what it decoded, so content past
+/// the page's decode budget is refused rather than dropped from the page.
+#[test]
+fn marking_a_tag_artifact_refuses_content_past_the_decode_budget() {
+    use pdfcraft_cos::{Dict, ObjRef, Object, Stream};
+    let mut doc = figures_doc();
+    let filler = doc.add(Stream::flate(Dict::new(), &vec![b' '; 1 << 20]));
+    let last = doc.add(Stream::from_raw(Dict::new(), b"0 0 5 5 re f".to_vec()));
+    let mut contents = vec![Object::Ref(ObjRef::new(4, 0))];
+    contents.extend(std::iter::repeat_n(Object::Ref(filler), 256));
+    contents.push(Object::Ref(last));
+    let contents = Object::Array(contents);
+    doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), contents.clone())).unwrap();
+    assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::TooLarge));
+    assert_eq!(doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents"), Some(&contents), "the page keeps its content");
+}