From 1f6ce5ecc707b93a4eb816fd101b0db8be8ab391 Mon Sep 17 00:00:00 2001
From: aiongg <aiongtaigi@gmail.com>
Date: Thu, 22 Oct 2026 15:26:10 +0000
Subject: [PATCH] fix(organize): analyse each form once when pruning unused
 XObjects

The pruner decoded and walked a form XObject again on every Do that drew
it, so a form drawing itself a few times per level was analysed
exponentially often within the depth limit. Forms are now remembered with
the resources owner they were drawn against, and a repeat records nothing
new.
---
 crates/organize/src/prune.rs | 11 ++++++++++-
 crates/organize/src/tests.rs | 25 +++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/crates/organize/src/prune.rs b/crates/organize/src/prune.rs
index b5f5e65ff..9b78a774b 100644
--- a/crates/organize/src/prune.rs
+++ b/crates/organize/src/prune.rs
@@ -29,7 +29,7 @@ enum XKey {
 }
 
 /// Who owns the resources currently being walked, for the key drawn names are recorded under.
-#[derive(Clone, Copy)]
+#[derive(Clone, Copy, PartialEq, Eq, Hash)]
 enum Owner {
     /// An indirect resources object (a page's, or a form XObject's own).
     Resources(ObjRef),
@@ -50,6 +50,9 @@ struct Pruner<'a> {
     glyph_seen: HashSet<ObjRef>,
     /// An indirect font's explicit resources have one owner regardless of which page uses it.
     glyph_fonts: HashSet<ObjRef>,
+    /// Forms already analysed, with the owner of the resources they drew against: drawing one
+    /// again records nothing new, and re-reading it on every `Do` is exponential in the nesting.
+    forms_seen: HashSet<(ObjRef, Owner)>,
 }
 
 impl Pruner<'_> {
@@ -211,6 +214,11 @@ impl Pruner<'_> {
                 // A form without its own resources draws against the ones it was invoked with.
                 None => (resources.clone(), owner),
             };
+            if !self.forms_seen.insert((r, inner_owner)) {
+                continue;
+            }
+            #[cfg(test)]
+            crate::work(1);
             match s.decoded() {
                 Ok(data) => self.content(&data, &inner, inner_owner, depth + 1),
                 // What the form draws is unknown: keep everything it could reach.
@@ -314,6 +322,7 @@ pub(crate) fn prune_unused_xobjects(doc: &mut Document) -> Result<usize, Organiz
         glyph_work_left: MAX_GLYPH_RESOURCE_WORK,
         glyph_seen: HashSet::new(),
         glyph_fonts: HashSet::new(),
+        forms_seen: HashSet::new(),
     };
     for (page, attrs) in &pages {
         let Some(res) = attrs.get(b"Resources") else { continue };
diff --git a/crates/organize/src/tests.rs b/crates/organize/src/tests.rs
index 5229379d8..2dbe8a4d6 100644
--- a/crates/organize/src/tests.rs
+++ b/crates/organize/src/tests.rs
@@ -3221,3 +3221,28 @@ fn name_trees_with_shared_kids_are_walked_once_per_node() {
     let tree = out.resolve(names.get(b"EmbeddedFiles").unwrap()).as_dict().cloned().unwrap();
     assert_eq!(tree.get(b"Names").and_then(|n| n.as_array()).map(Vec::len), Some(2), "one attachment, listed once");
 }
+
+#[test]
+fn a_form_drawing_itself_repeatedly_is_analysed_once() {
+    let form = "/F Do /F Do /F Do /F Do";
+    let b: Vec<String> = vec![
+        "<< /Type /Catalog /Pages 2 0 R >>".into(),
+        "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 300 400] >>".into(),
+        "<< /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /XObject << /F 5 0 R /Unused 6 0 R >> >> >>".into(),
+        "<< /Length 5 >>\nstream\n/F Do\nendstream".into(),
+        format!(
+            "<< /Type /XObject /Subtype /Form /BBox [0 0 10 10] /Resources << /XObject << /F 5 0 R >> >> /Length {} >>\nstream\n{form}\nendstream",
+            form.len()
+        ),
+        "<< /Type /XObject /Subtype /Form /BBox [0 0 10 10] /Length 0 >>\nstream\n\nendstream".into(),
+    ];
+    let src = open(build(&b, "/Root 1 0 R"));
+    take_work();
+    let out = extract_pages(&src, &[0]).unwrap();
+    let work = take_work();
+    assert!(work <= 4, "{work} form analyses");
+    let page = out.get(pages(&out).unwrap()[0].obj).as_dict().cloned().unwrap();
+    let res = out.resolve(page.get(b"Resources").unwrap()).as_dict().cloned().unwrap();
+    let x = out.resolve(res.get(b"XObject").unwrap()).as_dict().cloned().unwrap();
+    assert!(x.contains(b"F") && !x.contains(b"Unused"), "pruning still keeps what is drawn and drops the rest");
+}