M6: detect a row of comb boxes as one comb text field (#2111)

* M6: detect a row of comb boxes as one comb text field (fixes #1887)

* M6: keep empty tables of wide cells out of comb detection (#1887)

---------

Co-authored-by: Brandon Thomas <echelon@gmail.com>

crates/engine/src/js.rs

@@ -6,7 +6,7 @@
 //! Preferences ▸ JavaScript ▸ Enable Acrobat JavaScript is [`Session::set_javascript`]; with it
 //! off, scripts don't run and AF calls keep working natively.
 
-use pdfcraft_forms::{Field, FieldChange, FieldEvent, FieldKind, ScriptResult, Scripts};
+use pdfcraft_forms::{Field, FieldChange, FieldEvent, FieldKind, FieldProps, ScriptResult, Scripts};
 pub use pdfcraft_js::{Limits, Outcome, Request};
 
 use crate::{DocId, Edit, EditError, Session};
@@ -343,19 +343,24 @@ impl Session {
         let names = found.iter().map(|(_, c, _)| c.name.clone()).collect();
         let mut edits = Vec::with_capacity(found.len());
         for (page, c, turn) in found {
-            // A turned field keeps its place: the rectangle is already the one on the page.
-            let props = (turn != 0).then(|| pdfcraft_forms::FieldProps { rotation: Some((0, turn)), rect: Some((0, c.rect)), ..Default::default() });
             let tall = if turn % 180 == 0 { c.rect[3] - c.rect[1] } else { c.rect[2] - c.rect[0] };
-            edits.push(Edit::AddField {
-                page,
-                rect: c.rect,
-                kind: match c.kind {
-                    pdfcraft_forms::detect::Kind::Text => pdfcraft_forms::NewField::Text { multiline: tall > 30.0 },
-                    pdfcraft_forms::detect::Kind::CheckBox => pdfcraft_forms::NewField::CheckBox,
-                },
-                name: Some(c.name.clone()),
-            });
-            if let Some(props) = props {
+            let (kind, comb) = match c.kind {
+                pdfcraft_forms::detect::Kind::Text => (pdfcraft_forms::NewField::Text { multiline: tall > 30.0 }, None),
+                pdfcraft_forms::detect::Kind::CheckBox => (pdfcraft_forms::NewField::CheckBox, None),
+                pdfcraft_forms::detect::Kind::Comb { cells } => (pdfcraft_forms::NewField::Text { multiline: false }, Some(cells)),
+            };
+            let mut props = FieldProps::default();
+            if turn != 0 {
+                // A turned field keeps its place: the rectangle is already the one on the page.
+                props.rotation = Some((0, turn));
+                props.rect = Some((0, c.rect));
+            }
+            if let Some(cells) = comb {
+                props.max_len = Some(Some(cells));
+                props.flags = vec![(pdfcraft_forms::flags::COMB, true)];
+            }
+            edits.push(Edit::AddField { page, rect: c.rect, kind, name: Some(c.name.clone()) });
+            if turn != 0 || comb.is_some() {
                 edits.push(Edit::SetFieldProps { name: c.name, props: Box::new(props) });
             }
         }

crates/engine/src/tests.rs

@@ -3691,6 +3691,34 @@ fn detecting_fields_on_a_scanned_form() {
     }
 }
 
+#[test]
+fn detecting_comb_boxes_adds_one_comb_field_per_row() {
+    // The rows from #1887: five 18 x 22 cells and ten 16 x 20 cells, each a stroked `re`.
+    let mut body = String::from("BT /F1 10 Tf 40 205 Td (Postcode A) Tj ET BT /F1 10 Tf 40 105 Td (Postcode B) Tj ET\n");
+    for i in 0..5 {
+        body.push_str(&format!("{} 200 18 22 re S\n", 120 + i * 18));
+    }
+    for i in 0..10 {
+        body.push_str(&format!("{} 100 16 20 re S\n", 120 + i * 16));
+    }
+    let mut s = Session::new().with_clock(|| 1_700_000_000);
+    let id = s.open("comb.pdf", None, Arc::new(one_line_page("/Font << /F1 4 0 R >>", &body)), None).unwrap();
+    let found: Vec<(String, pdfcraft_forms::detect::Kind)> = s.detect_fields(id, &[]).into_iter().map(|(_, c)| (c.name, c.kind)).collect();
+    assert_eq!(
+        found,
+        [
+            ("Postcode A".to_string(), pdfcraft_forms::detect::Kind::Comb { cells: 5 }),
+            ("Postcode B".to_string(), pdfcraft_forms::detect::Kind::Comb { cells: 10 })
+        ]
+    );
+    s.auto_detect_fields(id, &[]).unwrap();
+    let d = s.get(id).unwrap();
+    let combs: Vec<(&str, FormFieldKind, bool, Option<usize>)> =
+        d.form.iter().map(|f| (f.name.as_str(), f.kind, f.has(pdfcraft_forms::flags::COMB), f.max_len)).collect();
+    assert_eq!(combs, [("Postcode A", FormFieldKind::Text, true, Some(5)), ("Postcode B", FormFieldKind::Text, true, Some(10))]);
+    assert_eq!(d.can_undo(), Some("Detect form fields"));
+}
+
 #[test]
 fn comparing_two_versions_of_a_document() {
     let mut s = Session::new().with_clock(|| 1_700_000_000);