From 1d0305fc2a563beafb6170801aa115510209147b Mon Sep 17 00:00:00 2001
From: fastmikey99 <218057203+fastmikey99@users.noreply.github.com>
Date: Fri, 9 Oct 2026 17:11:07 +1300
Subject: [PATCH] PDF import: clip art reaching past the page to the crop box

A clip to the page box is dropped as redundant (by hayro, and by
push_clip_path), so art a file hides outside the page - a mock-up backdrop
thousands of points across, say - came in unclipped: it showed, and it sized
Fit to Artwork Bounds and CropTo::Bounding to metres. Viewers show a page
through its crop box, so each object reaching past it now keeps its own clip
to it, with a warning. Art inside the page is unchanged (no clip groups).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 crates/pdf/src/import.rs                | 24 ++++++++++++++++++++++++
 crates/pdf/src/tests_import_fidelity.rs | 18 ++++++++++++++++++
 crates/pdf/src/tests_import_layers.rs   |  3 ++-
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/crates/pdf/src/import.rs b/crates/pdf/src/import.rs
index b59f28c3..a570db28 100644
--- a/crates/pdf/src/import.rs
+++ b/crates/pdf/src/import.rs
@@ -135,6 +135,9 @@ fn group_layer(
 pub const OFF_ARTBOARD_NOTE: &str =
     "only the PDF-compatible part of this file was read: art outside its artboards is kept in the editor's private data alone, so it doesn't open";
 
+/// Warning: art reaching past the page box was clipped to it.
+pub(crate) const PAST_PAGE_NOTE: &str = "art reaching past the page was clipped to it, as PDF viewers show it";
+
 /// Import a PDF, returning the document plus warnings about content that was approximated or skipped.
 pub fn import_with_report(bytes: &[u8], opts: &ImportOptions) -> Result<ImportReport, PdfError> {
     let original = crate::pages::open(bytes, opts.password.as_deref())?;
@@ -227,6 +230,27 @@ pub fn import_with_report(bytes: &[u8], opts: &ImportOptions) -> Result<ImportRe
             }
             parts.retain(|(_, art)| !art.is_empty());
         }
+        // Viewers show a page through its crop box, so art reaching past it (a mock-up backdrop
+        // around the page, say) never showed. A clip to the page box that the file states is
+        // dropped as redundant (by hayro and by `push_clip_path`), so restore the box here:
+        // each object reaching past it keeps its own clip, which Fit to Artwork Bounds and
+        // `CropTo::Bounding` then respect.
+        // The crop box is what viewers show, whichever box the artboard takes.
+        let shown = xf.transform_rect_bbox(crate::pages::page_box(page, CropTo::Crop));
+        let page_box = shown.inflate(0.01, 0.01);
+        let mut clipped = false;
+        for (_, art) in &mut parts {
+            for n in art.iter_mut() {
+                if n.visual_bounds().is_some_and(|r| !contains(page_box, r)) {
+                    let clip = Arc::new(b.clip_node(&shown.to_path(0.1), FillRule::NonZero));
+                    *n = Arc::new(Node::new(b.id(), NodeKind::Group { children: vec![clip, n.clone()], clip: true }));
+                    clipped = true;
+                }
+            }
+        }
+        if clipped {
+            b.warn(PAST_PAGE_NOTE);
+        }
         let children: Vec<Arc<Node>> = parts.iter().flat_map(|(_, v)| v.iter().cloned()).collect();
         placeholder &= ai && only_text(&children);
         let mut right = ab.x1;
diff --git a/crates/pdf/src/tests_import_fidelity.rs b/crates/pdf/src/tests_import_fidelity.rs
index b6098eed..1881bfa4 100644
--- a/crates/pdf/src/tests_import_fidelity.rs
+++ b/crates/pdf/src/tests_import_fidelity.rs
@@ -446,3 +446,21 @@ fn a_stroke_under_a_stretched_transform_stays_a_stroke() {
     let b = objs[0].geometric_bounds().unwrap();
     assert!((b.x0 - 20.0).abs() < 1e-6 && (b.x1 - 80.0).abs() < 1e-6, "{b:?}");
 }
+
+#[test]
+fn art_past_the_page_clip_keeps_the_clip() {
+    // A page-sized clip, then a backdrop far larger than the page and a square on it: the square
+    // needs no clip, the backdrop keeps it, so the art's bounds stay on the page.
+    let r = open_with(&one_page("0 0 100 100 re W n 0 g -500 -500 1100 1100 re f 1 0 0 rg 10 10 20 20 re f", "", &[]), |_| {});
+    let d = &r.document;
+    let art = d.art_bounds().expect("art");
+    assert!(art.x0 >= -0.01 && art.y0 >= -0.01 && art.x1 <= 100.01 && art.y1 <= 100.01, "the art stays on the page: {art:?}");
+    let clips: Vec<Node> = all(d).into_iter().filter(|n| matches!(n.kind, NodeKind::Group { clip: true, .. })).collect();
+    let [c] = clips.as_slice() else { panic!("one clip group, the backdrop's: {clips:?}") };
+    assert_eq!(c.children().map(Vec::len), Some(2), "the clip path and the backdrop");
+    assert!(r.warnings.iter().any(|w| w == crate::import::PAST_PAGE_NOTE), "{:?}", r.warnings);
+    // Art inside the page gets no clip and no warning.
+    let r = open_with(&one_page("0 0 100 100 re W n 1 0 0 rg 10 10 20 20 re f", "", &[]), |_| {});
+    assert!(!all(&r.document).iter().any(|n| matches!(n.kind, NodeKind::Group { clip: true, .. })));
+    assert!(!r.warnings.iter().any(|w| w == crate::import::PAST_PAGE_NOTE), "{:?}", r.warnings);
+}
diff --git a/crates/pdf/src/tests_import_layers.rs b/crates/pdf/src/tests_import_layers.rs
index 937a65d9..690ff1b0 100644
--- a/crates/pdf/src/tests_import_layers.rs
+++ b/crates/pdf/src/tests_import_layers.rs
@@ -165,9 +165,10 @@ fn an_ai_file_notes_that_its_art_off_the_artboards_is_not_read() {
     }
 }
 
+/// Paths that are art (not clipping paths: art reaching past the page keeps a clip to it).
 fn path_count(d: &Document) -> usize {
     let mut n = 0;
-    d.walk(|c| n += usize::from(matches!(c.kind, NodeKind::Path { .. })));
+    d.walk(|c| n += usize::from(matches!(c.kind, NodeKind::Path { clipping: false, .. })));
     n
 }