fix(a11y): mark_decorative finds MCIDs in named property lists (#1813) (#2106)

A BDC may name its property list in /Resources /Properties instead of
writing it inline. Marking a figure decorative and placing figures only
matched inline lists, so a figure tagged through a named list kept its
MCID content and parent-tree entry while its element was removed.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Brandon Thomas <echelon@gmail.com>

crates/a11y/src/alt.rs

@@ -140,6 +140,22 @@ fn mcids(d: &Dict) -> Vec<i64> {
     out
 }
 
+/// The page's named property lists (`/Resources /Properties`), which a `BDC` can name instead of
+/// writing its property list inline.
+fn page_properties(doc: &Document, page: &Dict) -> Dict {
+    let res = page.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default();
+    res.get(b"Properties").map(|p| doc.resolve(p)).and_then(|p| p.as_dict().cloned()).unwrap_or_default()
+}
+
+/// The marked-content id a `BDC` opens, whether its property list is inline or named in `props`.
+fn bdc_mcid(doc: &Document, props: &Dict, op: &pdfcraft_content::Op) -> Option<i64> {
+    match op.operands.get(1)? {
+        Object::Dict(d) => d.get(b"MCID").and_then(Object::as_int),
+        Object::Name(n) => props.get(n).map(|x| doc.resolve(x)).and_then(|x| x.as_dict().and_then(|d| d.get(b"MCID").and_then(Object::as_int))),
+        _ => None,
+    }
+}
+
 pub(crate) fn page_content(doc: &Document, page: &Dict) -> Vec<u8> {
     let Some(c) = page.get(b"Contents") else { return Vec::new() };
     match &*doc.resolve(c) {
@@ -170,6 +186,7 @@ fn union(a: Option<[f64; 4]>, b: [f64; 4]) -> [f64; 4] {
 fn content_bbox(doc: &Document, page: &Dict, ids: &HashSet<i64>) -> Option<[f64; 4]> {
     let res = page.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default();
     let xobjects = res.get(b"XObject").map(|x| doc.resolve(x)).and_then(|x| x.as_dict().cloned()).unwrap_or_default();
+    let props = page_properties(doc, page);
     let mut ctm = vec![Matrix([1.0, 0.0, 0.0, 1.0, 0.0, 0.0])];
     let mut marks: Vec<bool> = Vec::new();
     let mut bbox = None;
@@ -190,9 +207,7 @@ fn content_bbox(doc: &Document, page: &Dict, ids: &HashSet<i64>) -> Option<[f64;
                 }
             }
             b"BMC" => marks.push(false),
-            b"BDC" => marks.push(
-                matches!(op.operands.get(1), Some(Object::Dict(d)) if d.get(b"MCID").and_then(Object::as_int).is_some_and(|n| ids.contains(&n))),
-            ),
+            b"BDC" => marks.push(bdc_mcid(doc, &props, &op).is_some_and(|n| ids.contains(&n))),
             b"EMC" => {
                 marks.pop();
             }
@@ -295,12 +310,11 @@ pub fn mark_decorative(doc: &mut Document, obj: ObjRef) -> Result<(), AltError>
     let pages = pdfcraft_model::pages(doc);
     let pg = d.get(b"Pg").and_then(Object::as_ref).or_else(|| elements(doc).into_iter().find(|e| e.object == obj).and_then(|e| e.page));
     if let Some(page) = pg.and_then(|p| pages.iter().find(|x| x.obj == p)).filter(|_| !ids.is_empty()) {
+        let props = page_properties(doc, &page.dict);
         let mut ops = pdfcraft_content::parse(&page_content(doc, &page.dict)).ops;
         let mut changed = false;
         for op in ops.iter_mut() {
-            let ours = op.op == b"BDC"
-                && matches!(op.operands.get(1), Some(Object::Dict(m)) if m.get(b"MCID").and_then(Object::as_int).is_some_and(|n| ids.contains(&n)));
-            if ours {
+            if op.op == b"BDC" && bdc_mcid(doc, &props, op).is_some_and(|n| ids.contains(&n)) {
                 *op = pdfcraft_content::Op::new("BMC", vec![Object::name("Artifact")]);
                 changed = true;
             }

crates/a11y/src/tests.rs

@@ -624,6 +624,62 @@ fn marking_decorative_survives_a_parent_tree_with_an_unpaired_key() {
     }
 }
 
+/// `figures_doc` with its property lists named in the page resources (one inline, one indirect)
+/// instead of written inline in the content.
+fn named_figures_doc() -> Document {
+    pdf(
+        &[
+            "<< /Type /Catalog /Pages 2 0 R /MarkInfo << /Marked true >> /StructTreeRoot 5 0 R >>".into(),
+            "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(),
+            "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] /Contents 4 0 R /StructParents 0 \
+             /Resources << /XObject << /Im 10 0 R >> /Properties << /P0 << /MCID 0 >> /P1 11 0 R /Other << /Note (kept) >> >> >> >>"
+                .into(),
+            stream(
+                "/Figure /P0 BDC q 40 0 0 20 10 150 cm /Im Do Q EMC \
+                 /Photo /P1 BDC 100 100 50 30 re f EMC",
+            ),
+            "<< /Type /StructTreeRoot /K 6 0 R /ParentTree 9 0 R /RoleMap << /Photo /Figure >> >>".into(),
+            "<< /S /Document /P 5 0 R /K [7 0 R 8 0 R] >>".into(),
+            "<< /S /Figure /P 6 0 R /Pg 3 0 R /K 0 >>".into(),
+            "<< /S /Photo /P 6 0 R /Pg 3 0 R /Alt (A bar) /K 1 >>".into(),
+            "<< /Nums [0 [7 0 R 8 0 R]] >>".into(),
+            "<< /Type /XObject /Subtype /Image /Width 1 /Height 1 /ColorSpace /DeviceGray /BitsPerComponent 8 /Length 1 >>\nstream\n\u{0}\nendstream"
+                .into(),
+            "<< /MCID 1 >>".into(),
+        ],
+        "",
+    )
+}
+
+#[test]
+fn named_property_lists_are_found_and_marked_decorative_like_inline_ones() {
+    let (mut inline, mut named) = (figures_doc(), named_figures_doc());
+    let place = |doc: &Document| figures(doc).into_iter().map(|f| (f.obj, f.page, f.alt, f.bbox)).collect::<Vec<_>>();
+    assert_eq!(place(&named), place(&inline), "both figures, placed where their content is drawn");
+    for doc in [&mut inline, &mut named] {
+        mark_decorative(doc, pdfcraft_cos::ObjRef::new(8, 0)).unwrap();
+        let left = figures(doc);
+        assert_eq!((left.len(), left[0].obj.num, left[0].bbox), (1, 7, Some([10.0, 150.0, 50.0, 170.0])));
+        let pages = pdfcraft_model::pages(doc);
+        let c = doc.resolve(pages[0].dict.get(b"Contents").unwrap());
+        let Object::Stream(c) = &*c else { panic!("one content stream") };
+        let text = String::from_utf8(c.decoded().unwrap()).unwrap();
+        assert!(text.contains("/Artifact BMC") && !text.contains("/P1") && !text.contains("/MCID 1"), "{text}");
+        assert!(text.contains("/Im Do"), "the drawing itself stays: {text}");
+        let nums = doc.get(pdfcraft_cos::ObjRef::new(9, 0)).as_dict().and_then(|d| d.get(b"Nums").cloned());
+        assert_eq!(
+            nums,
+            Some(Object::Array(vec![Object::Int(0), Object::Array(vec![Object::Ref(pdfcraft_cos::ObjRef::new(7, 0)), Object::Null])])),
+            "the parent tree no longer points MCID 1 at the removed figure"
+        );
+        let r = check(doc, &Options { rules: [Rule::FiguresAltText, Rule::TaggedContent].into(), pages: None });
+        assert_eq!(r.result(Rule::TaggedContent).unwrap().status, Status::Passed, "{:?}", r.results);
+    }
+    let props = pdfcraft_model::pages(&named)[0].dict.get(b"Resources").and_then(|r| named.resolve(r).as_dict().cloned());
+    let props = props.and_then(|r| r.get(b"Properties").and_then(|p| named.resolve(p).as_dict().cloned())).unwrap();
+    assert!(props.contains(b"P0") && props.contains(b"P1") && props.contains(b"Other"), "resources are left as they were");
+}
+
 fn ref_(n: u32) -> Option<pdfcraft_cos::ObjRef> {
     Some(pdfcraft_cos::ObjRef::new(n, 0))
 }