fix(annot): read a shared page tree Kids array once

The page walk pushed a node's /Kids array for every new node, so many page
tree nodes sharing one indirect /Kids array re-read it for each node:
quadratic work while the seen check skipped every entry. A shared array
object is read under the first node that lists it, and the walk stops
after four million /Kids entries.

crates/annot/src/lib.rs

@@ -665,17 +665,20 @@ pub fn page_refs(doc: &Document) -> Result<Vec<ObjRef>, AnnotError> {
 /// Depth-first walk over the leaf pages under `top`. It keeps one cursor per open `/Kids` array,
 /// never one entry per child, so a child listed many times or shared between nodes is skipped by
 /// the seen check without being queued first (`pdfcraft_model::pages` walks the same way).
-/// Cycles end at the seen check and at most a million nodes are visited.
+/// Cycles end at the seen check, a `/Kids` array object shared by several nodes is read once,
+/// and at most a million nodes and four million `/Kids` entries are read.
 struct PageWalk<'a> {
     doc: &'a Document,
     seen: std::collections::HashSet<ObjRef>,
     pending: Vec<(std::sync::Arc<Object>, usize)>,
+    /// `/Kids` entries read so far.
+    examined: usize,
 }
 
 impl<'a> PageWalk<'a> {
     fn new(doc: &'a Document, top: ObjRef) -> Self {
         let top = std::sync::Arc::new(Object::Array(vec![Object::Ref(top)]));
-        Self { doc, seen: Default::default(), pending: vec![(top, 0)] }
+        Self { doc, seen: Default::default(), pending: vec![(top, 0)], examined: 0 }
     }
 }
 
@@ -690,8 +693,9 @@ impl Iterator for PageWalk<'_> {
             };
             let node = kid.as_ref();
             *next += 1;
+            self.examined += 1;
             let Some(node) = node else { continue };
-            if self.seen.len() >= 1_000_000 {
+            if self.seen.len() >= 1_000_000 || self.examined > 4_000_000 {
                 self.pending.clear();
                 return None;
             }
@@ -700,8 +704,15 @@ impl Iterator for PageWalk<'_> {
             }
             let obj = self.doc.get(node);
             let Some(d) = obj.as_dict() else { continue };
-            match d.get(b"Kids").map(|k| self.doc.resolve(k)) {
-                Some(kids) if d.name(b"Type") != Some(b"Page") => self.pending.push((kids, 0)),
+            match d.get(b"Kids") {
+                // A `/Kids` array object shared by several nodes is read under the first: under
+                // the others it would only list nodes already seen.
+                Some(Object::Ref(array)) if d.name(b"Type") != Some(b"Page") => {
+                    if self.seen.insert(*array) {
+                        self.pending.push((self.doc.get(*array), 0));
+                    }
+                }
+                Some(kids) if d.name(b"Type") != Some(b"Page") => self.pending.push((self.doc.resolve(kids), 0)),
                 _ => return Some(node),
             }
         }

crates/annot/src/tests.rs

@@ -1504,3 +1504,25 @@ fn typed_signature_uses_nonzero_winding_fill() {
     assert!(ap.ends_with("h\nf\n"), "expected non-zero winding fill (`f`), got: {ap}");
     assert!(!ap.contains("f*"), "must not use even-odd fill (`f*`): {ap}");
 }
+
+/// Many page tree nodes sharing one `/Kids` array read it once, not once per node.
+#[test]
+fn page_walk_reads_a_shared_kids_array_once() {
+    let mut doc = fixture();
+    let root = ObjRef { num: 2, generation: 0 };
+    let (first, second) = (ObjRef { num: 3, generation: 0 }, ObjRef { num: 4, generation: 0 });
+    let shared = doc.add(Object::Array([Object::Ref(first), Object::Ref(second)].into_iter().cycle().take(2_000).collect()));
+    let nodes: Vec<Object> = (0..1_000)
+        .map(|_| {
+            let mut d = Dict::new();
+            d.set(b"Type".to_vec(), Object::name("Pages"));
+            d.set(b"Kids".to_vec(), Object::Ref(shared));
+            Object::Ref(doc.add(d))
+        })
+        .collect();
+    doc.update_dict(root, |d| d.set(b"Kids".to_vec(), Object::Array(nodes))).unwrap();
+    let mut walk = PageWalk::new(&doc, root);
+    let pages: Vec<ObjRef> = walk.by_ref().collect();
+    assert_eq!(pages, [first, second]);
+    assert!(walk.examined <= 10_000, "{} kids entries read", walk.examined);
+}