Merge pull request #1186 from storytold/fix/thai-caret-clusters

Type: the caret steps over whole clusters (Thai marks, accents, emoji)

Cargo.lock

@@ -4813,6 +4813,7 @@ dependencies = [
  "unicode-bidi",
  "unicode-general-category",
  "unicode-script",
+ "unicode-segmentation",
  "vectorcraft-doc",
  "vectorcraft-geom",
  "windows-registry",

crates/text/Cargo.toml

@@ -21,6 +21,9 @@ subsetter = { version = "0.2", default-features = false, features = ["variable-f
 unicode-bidi = "0.3.18"
 unicode-general-category = "1"
 unicode-script = "0.5"
+# Grapheme clusters (a Thai consonant with its vowel and tone marks, an accented letter, an emoji
+# sequence) for caret movement; MIT OR Apache-2.0, already in the build.
+unicode-segmentation = "1.13"
 # Builds a small variable font for tests (`test_fonts`; no font file is committed). MIT OR
 # Apache-2.0, already in the build through subsetter.
 write-fonts = { version = "0.48", optional = true }

crates/text/src/edit.rs

@@ -190,6 +190,21 @@ pub fn next_char(s: &str, i: usize) -> usize {
     s[i..].chars().next().map(|c| i + c.len_utf8()).unwrap_or(s.len())
 }
 
+/// The start of the grapheme cluster before `i` (Left arrow): a Thai consonant with its vowel and
+/// tone marks, an accented letter or an emoji sequence is passed over whole.
+pub fn prev_cluster(s: &str, i: usize) -> usize {
+    use unicode_segmentation::GraphemeCursor;
+    let i = floor_char(s, i);
+    GraphemeCursor::new(i, s.len(), true).prev_boundary(s, 0).ok().flatten().unwrap_or(0)
+}
+
+/// The end of the grapheme cluster at `i` (Right arrow, Delete): see [`prev_cluster`].
+pub fn next_cluster(s: &str, i: usize) -> usize {
+    use unicode_segmentation::GraphemeCursor;
+    let i = floor_char(s, i);
+    GraphemeCursor::new(i, s.len(), true).next_boundary(s, 0).ok().flatten().unwrap_or(s.len())
+}
+
 fn is_word_char(c: char) -> bool {
     c.is_alphanumeric() || c == '_' || c == '\'' || c == '’'
 }

crates/text/src/tests_typo.rs

@@ -791,3 +791,17 @@ fn proportional_metrics_set_full_width_glyphs_on_their_proportional_widths() {
     let moved = x0(&half)[1] - x0(&none)[1];
     assert!((moved - 10.0).abs() < 0.01, "〙's empty half goes past the line's end: あ moved {moved}");
 }
+
+/// The arrows pass a Thai consonant with its vowel and tone marks whole (น้ำ: no, mai tho, sara am),
+/// as an accented letter written with a combining mark; plain text moves a character at a time.
+#[test]
+fn caret_moves_over_whole_clusters() {
+    let s = "กน\u{0E49}\u{0E33}e\u{0301}x";
+    let stops: Vec<usize> = std::iter::successors(Some(0), |&i| (i < s.len()).then(|| edit::next_cluster(s, i))).collect();
+    assert_eq!(stops, [0, 3, 12, 15, 16]);
+    let back: Vec<usize> = std::iter::successors(Some(s.len()), |&i| (i > 0).then(|| edit::prev_cluster(s, i))).collect();
+    assert_eq!(back, [16, 15, 12, 3, 0]);
+    // Inside a cluster (a caret left there by a click), the arrows go to its edges.
+    assert_eq!((edit::prev_cluster(s, 6), edit::next_cluster(s, 6)), (3, 12));
+    assert_eq!((edit::next_cluster("", 0), edit::prev_cluster("ab", 99)), (0, 1));
+}

crates/tools/src/text.rs

@@ -530,8 +530,10 @@ impl Tool for TypeTool {
                 self.anchor = if word { edit::prev_word(&text, self.caret) } else { edit::prev_char(&text, self.caret) };
                 self.replace(cx, "", None)
             }
+            // Backspace takes back one character (a mistyped Thai tone mark, say); Delete, the
+            // Left and Right arrows a whole cluster.
             ToolKey::Delete if self.caret < len => {
-                self.anchor = if word { edit::next_word(&text, self.caret) } else { edit::next_char(&text, self.caret) };
+                self.anchor = if word { edit::next_word(&text, self.caret) } else { edit::next_cluster(&text, self.caret) };
                 self.replace(cx, "", None)
             }
             ToolKey::Left => {
@@ -549,7 +551,7 @@ impl Tool for TypeTool {
                     if lay.glyphs.iter().any(|g| g.rtl) {
                         vectorcraft_text::caret_horizontal(&lay, self.caret, false)
                     } else {
-                        edit::prev_char(&text, self.caret)
+                        edit::prev_cluster(&text, self.caret)
                     }
                 };
                 self.move_to(to, mods.shift)
@@ -569,7 +571,7 @@ impl Tool for TypeTool {
                     if lay.glyphs.iter().any(|g| g.rtl) {
                         vectorcraft_text::caret_horizontal(&lay, self.caret, true)
                     } else {
-                        edit::next_char(&text, self.caret)
+                        edit::next_cluster(&text, self.caret)
                     }
                 };
                 self.move_to(to, mods.shift)

docs/type-parity.md

@@ -1,5 +1,6 @@
 # Type parity
 
+> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-11 · **Change:** minor (the caret steps over whole clusters such as Thai consonants with their marks; earlier: Proportional Metrics in vertical type, `vpal`, #966) · **Target:** Adobe Illustrator 2026 (30.x)
 > **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-11 · **Change:** minor (Thai typed in a font without Thai falls back to a font made for Thai; earlier: Proportional Metrics in vertical type, `vpal`, #966) · **Target:** Adobe Illustrator 2026 (30.x)
 
 Type is Illustrator's largest single area by use (weight 13 of 105 across "Type core" and "Type advanced" in
@@ -37,6 +38,7 @@ against Illustrator's public documentation; **estimated** unless noted.
 | Hidden characters (Show Hidden Characters) | done | `type.hiddenCharacters` |
 | Spell check (Check Spelling, Auto Spell Check, custom dictionary) | missing | menu stubs; needs an openly licensed dictionary |
 | Smart Punctuation, Change Case, Find & Replace | done | |
+| Caret: the arrows and Delete step over whole clusters (Thai consonant with its marks, combining accents, emoji); Backspace removes one character | done | |
 | Touch Type tool | missing | listed in the toolbar, not implemented |
 | Retype (identify fonts in outlines/images) | missing | Illustrator's uses a cloud model |
 | Snap to Glyph | missing | menu stub |
@@ -52,6 +54,7 @@ against Illustrator's public documentation; **estimated** unless noted.
 
 | Date | Change | Summary |
 |---|---|---|
+| 2026-10-11 | minor | The Type tool's arrows and Delete move by grapheme cluster, never between a Thai consonant and its vowel or tone marks; score unchanged (estimated) |
 | 2026-10-11 | minor | Thai (Lao, Khmer, Myanmar) missing from the font in use falls back to an installed font made for the script instead of whichever face covering it loaded first; score unchanged (estimated) |
 | 2026-10-11 | minor | Proportional Metrics done: `palt` in horizontal type, `vpal` in vertical type (#966, #1082); ruby and manual tate-chu-yoko still missing |
 | 2026-10-10 | minor | #1034: transformed character controls and regression coverage; preserving group font sizes remains a separate enhancement. Scores/hours unchanged at this rounding. |