fix(engine): list a page truncated for both forms and pictures once

crates/engine/src/compare.rs

@@ -184,18 +184,18 @@ impl crate::Document {
     /// The pages as paragraphs and images (for Word, HTML and RTF export), including what
     /// form XObjects draw.
     pub fn export_pages(&self) -> Vec<pdfcraft_export::Page> {
-        self.export_pages_checked(true).0
+        self.export_pages_checked(true, MAX_EXPORT_IMAGE_BYTES).0
     }
 
     /// [`Self::export_pages`], and the pages whose forms were left partly unread or whose
-    /// pictures went past [`MAX_EXPORT_IMAGE_BYTES`] ([`OfficeExport::truncated_pages`]). Without
+    /// pictures went past `image_budget` bytes ([`OfficeExport::truncated_pages`]). Without
     /// `images` no picture is prepared.
-    fn export_pages_checked(&self, images: bool) -> (Vec<pdfcraft_export::Page>, Vec<usize>) {
+    pub(crate) fn export_pages_checked(&self, images: bool, image_budget: usize) -> (Vec<pdfcraft_export::Page>, Vec<usize>) {
         let Some(cos) = self.editor.as_ref().map(|e| &e.cos) else { return (Vec::new(), Vec::new()) };
         let mut truncated = Vec::new();
         // Each image object is encoded once and shared by every place that draws it.
         let mut encoded: HashMap<ObjRef, PreparedImage> = HashMap::new();
-        let mut image_bytes = MAX_EXPORT_IMAGE_BYTES;
+        let mut image_bytes = image_budget;
         let pages = self
             .info
             .pages
@@ -213,9 +213,7 @@ impl crate::Document {
                 let display_width = f64::from(if info.rotation % 180 == 0 { info.width } else { info.height });
                 let unit = if crop_width > 0.0 && crop_width.is_finite() && display_width.is_finite() { display_width / crop_width } else { 1.0 };
                 let reading = pdfcraft_edit::reading_blocks_checked(cos, i).unwrap_or_default();
-                if reading.truncated {
-                    truncated.push(i);
-                }
+                let forms_unread = reading.truncated;
                 let blocks = reading
                     .blocks
                     .into_iter()
@@ -255,10 +253,10 @@ impl crate::Document {
                         })
                     })
                     .collect();
-                // The page colour (Edit a PDF ▸ Background, a producer's page fill) for formats that keep one.
-                if over_budget {
+                if forms_unread || over_budget {
                     truncated.push(i);
                 }
+                // The page colour (Edit a PDF ▸ Background, a producer's page fill) for formats that keep one.
                 let background = pdfcraft_edit::page_background(cos, i).ok().flatten();
                 pdfcraft_export::Page { width: info.width as f64, height: info.height as f64, blocks, images, background }
             })
@@ -275,7 +273,7 @@ impl crate::Document {
     /// ([`OfficeExport::truncated_pages`]).
     pub fn export_office_checked(&self, format: OfficeFormat) -> OfficeExport {
         // RTF leaves pictures out.
-        let (pages, truncated_pages) = self.export_pages_checked(format != OfficeFormat::Rtf);
+        let (pages, truncated_pages) = self.export_pages_checked(format != OfficeFormat::Rtf, MAX_EXPORT_IMAGE_BYTES);
         let title = self.info.title.clone().unwrap_or_else(|| self.name.trim_end_matches(".pdf").to_string());
         let bytes = match format {
             OfficeFormat::Docx => pdfcraft_export::docx(&pages, &title),

crates/engine/src/tests.rs

@@ -7283,3 +7283,47 @@ fn exporting_office_keeps_dotted_leader_entries_as_paragraphs() {
     let positions: Vec<_> = entries.iter().map(|entry| html.find(&format!("<p>{entry}</p>")).expect("one paragraph per entry")).collect();
     assert!(positions.windows(2).all(|pair| pair[0] < pair[1]), "reading order: {html}");
 }
+
+/// A page whose forms go past the reading limit and whose picture goes past the image budget is
+/// listed once among the truncated pages.
+#[test]
+fn a_page_truncated_for_forms_and_pictures_is_listed_once() {
+    let depth = compare::MAX_FORM_DEPTH + 1;
+    let mut objs: Vec<String> = vec![
+        "<< /Type /Catalog /Pages 2 0 R >>".into(),
+        "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 200] >>".into(),
+        String::new(),
+        "<< /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Length 4 >>\nstream\n\0\x40\u{80}\u{ff}\nendstream".into(),
+        "<< /Length 34 >>\nstream\nq 10 0 0 10 0 0 cm /Im Do Q /D1 Do\nendstream".into(),
+    ];
+    // Forms D1..D{depth}, objects 6 onwards, each drawing the next.
+    let xobjects: String = (1..=depth).map(|i| format!("/D{i} {} 0 R ", 5 + i)).collect();
+    let resources = format!("<< /XObject << /Im 4 0 R {xobjects}>> >>");
+    for i in 1..=depth {
+        let body = if i == depth { "q Q".to_string() } else { format!("/D{} Do", i + 1) };
+        objs.push(format!(
+            "<< /Type /XObject /Subtype /Form /BBox [0 0 200 200] /Resources {resources} /Length {} >>\nstream\n{body}\nendstream",
+            body.len()
+        ));
+    }
+    objs[2] = format!("<< /Type /Page /Parent 2 0 R /Contents 5 0 R /Resources {resources} >>");
+    let mut bytes = b"%PDF-1.7\n".to_vec();
+    let mut offsets = Vec::new();
+    for (i, o) in objs.iter().enumerate() {
+        offsets.push(bytes.len());
+        bytes.extend_from_slice(format!("{} 0 obj\n{o}\nendobj\n", i + 1).as_bytes());
+    }
+    let xref = bytes.len();
+    bytes.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.len() + 1).as_bytes());
+    for o in offsets {
+        bytes.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes());
+    }
+    bytes.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objs.len() + 1).as_bytes());
+    let mut s = Session::new();
+    let id = s.open("both.pdf", None, Arc::new(bytes), None).unwrap();
+    let doc = s.get(id).unwrap();
+    assert_eq!(doc.export_pages_checked(false, 0).1, [0], "the forms alone truncate the page");
+    let (pages, truncated) = doc.export_pages_checked(true, 0);
+    assert!(pages[0].images.is_empty(), "the picture is past the budget");
+    assert_eq!(truncated, [0]);
+}