fix(model,oracle): read a page box only when it has four entries; skip empty images (#5941)

crates/model/src/lib.rs

@@ -24,8 +24,12 @@ const MIN_BOX_SIDE: f64 = 1.0 / 4096.0;
 
 fn rect(doc: &Document, o: Option<&Object>) -> Option<[f64; 4]> {
     let o = doc.resolve(o?);
-    let v: Vec<f64> = o.as_array()?.iter().filter_map(|x| doc.resolve(x).as_f64()).collect();
-    (v.len() == 4 && v.iter().all(|x| x.is_finite())).then(|| [v[0].min(v[2]), v[1].min(v[3]), v[0].max(v[2]), v[1].max(v[3])])
+    // Four entries, or not a rectangle: a longer array (one shared by many pages, say) is not
+    // resolved entry by entry only to be discarded.
+    let [a, b, c, d] = o.as_array()?.as_slice() else { return None };
+    let v = [a, b, c, d].map(|x| doc.resolve(x).as_f64());
+    let [Some(x0), Some(y0), Some(x1), Some(y1)] = v else { return None };
+    [x0, y0, x1, y1].iter().all(|x| x.is_finite()).then(|| [x0.min(x1), y0.min(y1), x0.max(x1), y0.max(y1)])
 }
 
 impl Page {

crates/oracle/src/pixels.rs

@@ -105,6 +105,10 @@ pub fn compare(a: Gray<'_>, b: Gray<'_>, tolerance: u8) -> Result<Diff, SizeMism
 
 /// Pixels of `a` with no pixel within `tolerance` anywhere in `b`'s surrounding 3x3.
 fn unmatched(a: Gray<'_>, b: Gray<'_>, tolerance: u8) -> usize {
+    // No pixels, nothing to match: a zero-width image of enormous height is not walked row by row.
+    if a.pixels.is_empty() {
+        return 0;
+    }
     let mut count = 0usize;
     for y in 0..a.height {
         for x in 0..a.width {
@@ -210,6 +214,14 @@ fn find(haystack: &[u8], needle: &[u8]) -> Option<usize> {
 
 #[cfg(test)]
 mod tests {
+    /// A zero-width image of enormous height has no pixels to walk.
+    #[test]
+    fn an_image_without_pixels_compares_at_once() {
+        let a = Gray { width: 0, height: usize::MAX, pixels: &[] };
+        let d = compare(a, a, 0).unwrap();
+        assert_eq!((d.differing, d.total), (0, 0));
+    }
+
     use super::*;
 
     fn gray(w: usize, h: usize, fill: u8) -> Vec<u8> {