Merge remote-tracking branch 'origin/main' into pr-5374

# Conflicts:
#	ROADMAP.md
#	docs/gaps.md

crates/docbin/src/table.rs

@@ -101,6 +101,12 @@ impl RowInfo {
         self.widths.iter().rfind(|(k, _)| *k == i).map(|(_, w)| *w)
     }
 
+    /// How many per-cell overrides the row keeps, for tests.
+    #[cfg(test)]
+    pub(crate) fn overrides(&self) -> usize {
+        self.vmerge.len() + self.shading.len() + self.widths.len() + self.width_pcts.len() + self.valign.len() + self.merges.len()
+    }
+
     /// The width percentage cell `i` ends up with, for tests.
     #[cfg(test)]
     pub(crate) fn width_pct_of(&self, i: u8) -> Option<f32> {
@@ -108,6 +114,15 @@ impl RowInfo {
     }
 }
 
+/// Set cell `c`'s override to `v`, replacing an earlier one: one slot per cell, however often
+/// a PAPX repeats the sprm, so a shared PAPX can't pile up copies on every paragraph mark.
+fn set<T>(slots: &mut Vec<(u8, T)>, c: u8, v: T) {
+    match slots.iter_mut().find(|(k, _)| *k == c) {
+        Some(slot) => slot.1 = v,
+        None => slots.push((c, v)),
+    }
+}
+
 pub(crate) fn decode(papx: &[u8]) -> RowInfo {
     let mut r = RowInfo::default();
     let mut gap_half: Option<i16> = None;
@@ -144,8 +159,10 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
             T_DXA_GAP_HALF => gap_half = s16(&prl),
             T_TABLE_BORDERS_80 => r.borders = table_borders(prl.operand),
             T_MERGE => {
+                // Rows apply only the first MAX_COLS merges.
                 if let [a, b, ..] = prl.operand
                     && b > a
+                    && r.merges.len() < MAX_COLS
                 {
                     r.merges.push((*a, *b));
                 }
@@ -158,7 +175,8 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                         1 => VMerge::Continue,
                         _ => VMerge::None,
                     };
-                    if m != VMerge::None {
+                    // The first override for a cell wins.
+                    if m != VMerge::None && !r.vmerge.iter().any(|(k, _)| k == itc) {
                         r.vmerge.push((*itc, m));
                     }
                 }
@@ -168,7 +186,7 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                     && let [a, b, ..] = prl.operand.get(1..3).unwrap_or(&[])
                 {
                     for c in *a..(*b).min(MAX_COLS as u8) {
-                        r.shading.push((c, Some(rgb)));
+                        set(&mut r.shading, c, Some(rgb));
                     }
                 }
             }
@@ -176,7 +194,7 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                 let cells = prl.operand.get(1..).unwrap_or(&[]);
                 for (i, b) in cells.as_chunks::<2>().0.iter().take(MAX_COLS).enumerate() {
                     if let Some(rgb) = shd80_rgb(b) {
-                        r.shading.push((i as u8, Some(rgb)));
+                        set(&mut r.shading, i as u8, Some(rgb));
                     }
                 }
             }
@@ -196,7 +214,7 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                     if raw && b.get(8..10) == Some(&[0xFF, 0xFF]) {
                         continue;
                     }
-                    r.shading.push(((first + i) as u8, shd_rgb(b)));
+                    set(&mut r.shading, (first + i) as u8, shd_rgb(b));
                 }
             }
             T_CELL_WIDTH => {
@@ -207,12 +225,12 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                     if *fts == 3 {
                         let w = (i16::from_le_bytes([*w0, *w1]) as f32 / 20.0).clamp(0.0, 1584.0);
                         for c in *a..(*b).min(MAX_COLS as u8) {
-                            r.widths.push((c, w));
+                            set(&mut r.widths, c, w);
                         }
                     } else if *fts == 2 {
                         let pct = (u16::from_le_bytes([*w0, *w1]) as f32 / 50.0).clamp(0.0, 100.0);
                         for c in *a..(*b).min(MAX_COLS as u8) {
-                            r.width_pcts.push((c, pct));
+                            set(&mut r.width_pcts, c, pct);
                         }
                     }
                 }
@@ -224,8 +242,8 @@ pub(crate) fn decode(papx: &[u8]) -> RowInfo {
                         2 => VAlign::Bottom,
                         _ => VAlign::Top,
                     };
-                    for c in *a..*b {
-                        r.valign.push((c, v));
+                    for c in *a..(*b).min(MAX_COLS as u8) {
+                        set(&mut r.valign, c, v);
                     }
                 }
             }

crates/docbin/src/tests.rs

@@ -2401,6 +2401,23 @@ fn second_table_gets_its_own_grid() {
     assert_eq!(tables[1].props.indent, None, "indent reset");
 }
 
+#[test]
+fn repeated_cell_sprms_keep_one_override_per_cell() {
+    // A PAPX repeating cell-range sprms (shared by every paragraph mark that names it) keeps one
+    // slot per cell, the last value winning, instead of a copy per repetition.
+    let mut sprms = Vec::new();
+    for w in 0..200u16 {
+        let [w0, w1] = (w * 20).to_le_bytes();
+        sprms.push(sprm_cb(0xD635, &[0, 63, 3, w0, w1]));
+        sprms.push(sprm_cb(0xD62C, &[0, 255, 1]));
+        sprms.push([0x24, 0x56, 0, 2].to_vec());
+    }
+    let row = crate::table::decode(&sprms.concat());
+    assert_eq!(row.width_of(0), Some(199.0), "the last width wins");
+    assert_eq!(row.width_of(62), Some(199.0));
+    assert!(row.overrides() <= 63 + 255 + 63, "{}", row.overrides());
+}
+
 #[test]
 fn sprm_t_cell_width_twips_and_percentage() {
     // [MS-DOC] §2.9.290 sprmTCellWidth (0xD635):