M3: a stacked, raised or squeezed combining mark stays with its letter (view.copy-text, view.find)

A second mark stacked on a letter now rides on the letter as well as on the
mark before it; a mark drawn up to an em above or below its letter stays on
the letter's line, and the glyph after it continues from the letter; marks in
a zero-width run are ordered by their letter; and a word gap after a mark is
measured from the letter's advance, not the mark's offset start.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pq7HyCHD1R3rywQBPCHXZA

crates/render/src/text/layout.rs

@@ -130,12 +130,23 @@ fn rides_on(p: &TextGlyph, m: &TextGlyph) -> bool {
         && m.rect[0] <= p.rect[2] + reach
 }
 
-/// Glyph `i` continues the run of glyph `i - 1`: when it is a combining mark on that glyph, it joins its cluster.
+/// How far, as a fraction of its letter's height, a combining mark's em box may sit above or below the letter's and
+/// still ride on it. A tone mark lifted over an upper vowel can be drawn more than half an em higher, past where a
+/// glyph of its own would start a new line.
+const MARK_RISE: f32 = 1.0;
+
+/// Whether glyph `m`, drawn right after glyph `p` (a letter, or a mark riding on letter `a`), rides on that cluster:
+/// on `p` itself, or, for a mark stacked on another one, on its letter `a`.
+fn rides_on_cluster(glyphs: &[&TextGlyph], p: usize, a: usize, m: &TextGlyph) -> bool {
+    glyphs.get(p).is_some_and(|pg| rides_on(pg, m)) || (a != p && glyphs.get(a).is_some_and(|ag| rides_on(ag, m)))
+}
+
+/// Glyph `i` continues the run of glyph `i - 1`: when it is a combining mark on that glyph's cluster, it joins it.
 fn attach_mark(glyphs: &[&TextGlyph], anchor: &mut [usize], i: usize) {
     let Some(p) = i.checked_sub(1) else { return };
-    if let (Some(pg), Some(mg)) = (glyphs.get(p), glyphs.get(i))
-        && rides_on(pg, mg)
-        && let Some(&a) = anchor.get(p)
+    let Some(&a) = anchor.get(p) else { return };
+    if let Some(mg) = glyphs.get(i)
+        && rides_on_cluster(glyphs, p, a, mg)
         && let Some(slot) = anchor.get_mut(i)
     {
         *slot = a;
@@ -221,7 +232,13 @@ fn arrange(glyphs: &[TextGlyph]) -> (Vec<usize>, Vec<u32>, Vec<bool>) {
         let g = glyphs[i].rect;
         let hi = height(i);
         let cont = segs.last().is_some_and(|s| {
-            let Some(p) = s.first.end.checked_sub(1) else { return false };
+            let Some(last) = s.first.end.checked_sub(1) else { return false };
+            // A glyph after a combining mark continues from the mark's letter, and a mark on that letter's cluster
+            // stays on its line even when drawn raised or lowered by up to an em (`MARK_RISE`).
+            let p = anchor.get(last).copied().unwrap_or(last);
+            if rides_on_cluster(&glyphs, last, p, glyphs[i]) && (cy(i) - cy(p)).abs() < height(p) * MARK_RISE {
+                return true;
+            }
             let ph = height(p).min(hi);
             let sh = s.h.min(hi);
             let gap = g[0] - glyphs[p].rect[2];

crates/render/src/text/order.rs

@@ -161,8 +161,9 @@ pub(super) struct Scratch {
 }
 
 /// Fills `sc.cluster_gap` with the gap left of each glyph of `sc.placed`, between clusters: a combining mark riding on a
-/// glyph has none (no word ever starts at it), and its cluster ends at the base's right edge or the furthest mark start.
-/// A zero-advance mark's box is no measure of where the pen went (`draw_glyph` widens it to its outline or half an em).
+/// glyph has none (no word ever starts at it), and its cluster ends at the base's right edge. A zero-advance mark's box
+/// is no measure of where the pen went (`draw_glyph` widens it to its outline or half an em), and its start is only
+/// the base's advance moved by a mark-positioning offset.
 pub(super) fn measure_cluster_gaps(glyphs: &[&TextGlyph], sc: &mut Scratch) {
     sc.cluster_gap.clear();
     let mut right = f32::NEG_INFINITY;
@@ -172,7 +173,6 @@ pub(super) fn measure_cluster_gaps(glyphs: &[&TextGlyph], sc: &mut Scratch) {
             continue;
         };
         if anchor_of(&sc.anchor, c) != c {
-            right = right.max(g.rect[0]);
             sc.cluster_gap.push(None);
         } else {
             sc.cluster_gap.push((w > 0).then_some(g.rect[0] - right));
@@ -304,14 +304,15 @@ pub(super) fn place_glyphs(glyphs: &[&TextGlyph], height: &dyn Fn(usize) -> f32,
     } else {
         collide(glyphs, height, s.h, sc);
     }
-    // Each mark goes before the first placed glyph whose x is greater than its own. Marks are visited in x order, and
-    // that position never moves back, so one pass over `placed` puts all of them in.
-    sc.marks.sort_by(|a, b| x0(*a).total_cmp(&x0(*b)));
+    // Each mark goes before the first placed glyph whose x is greater than its own, or its letter's when it is a
+    // combining mark riding on one. Marks are visited in that order, and that position never moves back, so one pass
+    // over `placed` puts all of them in.
+    sc.marks.sort_by(|a, b| by_cluster(glyphs, &sc.anchor, *a, *b));
     if !sc.marks.is_empty() {
         sc.merged.clear();
         let mut next = 0;
         for &m in &sc.marks {
-            while next < sc.placed.len() && x0(anchor_of(&sc.anchor, sc.placed[next])) <= x0(m) {
+            while next < sc.placed.len() && x0(anchor_of(&sc.anchor, sc.placed[next])) <= x0(anchor_of(&sc.anchor, m)) {
                 sc.merged.push(sc.placed[next]);
                 next += 1;
             }

crates/render/src/text/tests.rs

@@ -2064,3 +2064,33 @@ fn a_mark_moves_with_its_letter_in_a_line_drawn_backwards() {
     let v = vec![g("a", 12.0, 10.0, 18.0), g("b", 18.0, 10.0, 24.0), g("c", 24.0, 10.0, 30.0), g("\u{301}", 13.0, 10.0, 18.0)];
     assert_eq!(layout(v).plain_text(), "a\u{301}bc");
 }
+
+/// A second mark stacked on a letter rides on the letter, not only on the mark before it: a mark drawn back over its
+/// base, then a tone mark a hair past the base's advance, both stay before the next letter.
+#[test]
+fn a_stacked_mark_rides_on_its_base_letter() {
+    let v = vec![g("ก", 12.0, 10.0, 18.0), g("\u{e34}", 10.0, 10.0, 15.0), g("\u{e48}", 19.5, 10.0, 24.5), g("ข", 18.0, 10.0, 24.0)];
+    assert_eq!(layout(v).plain_text(), "ก\u{e34}\u{e48}ข");
+}
+
+/// A mark drawn raised by more than half an em over its letter (a tone mark lifted above an upper vowel) stays on the
+/// letter's line and before the next letter.
+#[test]
+fn a_raised_mark_stays_with_its_letter() {
+    let v = vec![g("ก", 12.0, 10.0, 18.0), g("\u{e48}", 18.4, 16.0, 23.4), g("ข", 18.0, 10.0, 24.0), g("ค", 24.0, 10.0, 30.0)];
+    assert_eq!(layout(v).plain_text(), "ก\u{e48}ขค");
+}
+
+/// A word gap after a mark is measured from its letter's advance: a mark drawn a hair past the pen does not narrow it.
+#[test]
+fn a_word_gap_after_a_mark_is_measured_from_its_letter() {
+    let v = vec![g("a", 0.0, 10.0, 6.0), g("b", 6.0, 10.0, 12.0), g("\u{301}", 12.4, 10.0, 17.4), g("c", 13.8, 10.0, 19.8), g("d", 19.8, 10.0, 25.8)];
+    assert_eq!(layout(v).plain_text(), "ab\u{301} cd");
+}
+
+/// In a run squeezed to no width, a mark still follows its letter, even when it is drawn past the next letter.
+#[test]
+fn a_mark_in_a_zero_width_run_follows_its_letter() {
+    let v = vec![g("a", 10.0, 10.0, 10.0), g("\u{301}", 10.6, 10.0, 10.6), g("b", 10.3, 10.0, 10.3)];
+    assert_eq!(layout(v).plain_text(), "a\u{301}b");
+}