Addresses snap to runes, not grapheme clusters

sam and acme address runes; pardes snapped #n, line:col, dot and data's
reads to grapheme clusters, so a lone combining mark or a CRLF's \r could
not be addressed. #n, line:col, a search's match, dot (both ways) and data
now land on rune boundaries (modal.runeStart and friends), and the tty's
cell drawing is untouched. The README, fs.md and the skill say so.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

1 files changed, 38 insertions, 7 deletions

diff --git a/src/ninep/pane.zig b/src/ninep/pane.zig
index c594c7a3..902f4f2a 100644
--- a/src/ninep/pane.zig
+++ b/src/ninep/pane.zig
@@ -128,11 +128,12 @@ pub fn clip(n: usize) u32 {
 
 pub fn dotOf(pane: *Pane) State.Range {
     const text = bodyOf(pane);
-    const head = modal.offsetAt(text, .{ .row = @intCast(@max(0, pane.body.cur_row)), .col = @intCast(@max(0, pane.body.cur_col)) });
+    // In runes, as every address is (modal.runeStart).
+    const head = modal.runeOffsetAt(text, .{ .row = @intCast(@max(0, pane.body.cur_row)), .col = @intCast(@max(0, pane.body.cur_col)) });
     if (!pane.body.vsel.active) return .{ .q0 = clip(head), .q1 = clip(head) };
-    const anchor = modal.offsetAt(text, .{ .row = @intCast(@max(0, pane.body.vsel.row)), .col = @intCast(@max(0, pane.body.vsel.col)) });
+    const anchor = modal.runeOffsetAt(text, .{ .row = @intCast(@max(0, pane.body.vsel.row)), .col = @intCast(@max(0, pane.body.vsel.col)) });
     var hi = @max(head, anchor);
-    if (hi < text.len) hi = modal.nextGrapheme(text, hi);
+    if (hi < text.len) hi = modal.nextRune(text, hi);
     return .{ .q0 = clip(@min(head, anchor)), .q1 = clip(hi) };
 }
 
@@ -140,9 +141,9 @@ pub fn setDot(pane: *Pane, r: State.Range) void {
     const text = bodyOf(pane);
     const q0 = @min(@as(usize, r.q0), text.len);
     const q1 = @max(q0, @min(@as(usize, r.q1), text.len));
-    const a = modal.positionAt(text, q0);
+    const a = modal.runePositionAt(text, q0);
     pane.body.vsel = .{ .active = q1 > q0, .row = @intCast(a.row), .col = @intCast(a.col), .explicit = true };
-    const h = modal.positionAt(text, if (q1 > q0) modal.prevGrapheme(text, q1) else q0);
+    const h = modal.runePositionAt(text, if (q1 > q0) modal.prevRune(text, q1) else q0);
     pane.body.cur_row = @intCast(h.row);
     pane.body.cur_col = @intCast(h.col);
     pane.body.cur_pinned = true;
@@ -369,7 +370,7 @@ fn readData(req: Req, id: usize, pane: *Pane, pf: *State, stop_at_end: bool) Rep
     const q0: usize = pf.addr.q0;
     const hi: usize = if (stop_at_end) @max(q0, @as(usize, pf.addr.q1)) else text.len;
     var end = @min(hi, q0 +| req.size);
-    end = @max(q0, modal.graphemeStart(text, end));
+    end = @max(q0, modal.runeStart(text, end));
     pf.addr.q0 = clip(end);
     if (!stop_at_end) pf.addr.q1 = clip(end);
     if (pane.file == null) return .{ .tag = req.tag };
@@ -858,7 +859,7 @@ test "data and xdata read from addr, move it, and write through it" {
     try testing.expectEqual(@as(u32, 4), p.panes[0].?.fs.addr.q0);
 }
 
-test "data never splits a grapheme, in either direction" {
+test "data never splits a rune, in either direction" {
     const gpa = testing.allocator;
     const p = try withFile(gpa, "\u{00e9}x\n");
     defer p.deinit();
@@ -1205,3 +1206,33 @@ test "setattr truncation empties the body and answers fresh attributes" {
     const noop = call(p, .{ .tag = 8, .op = .setattr, .node = Node.of(serial, .body) });
     try testing.expectEqual(@as(u64, 9), noop.reply.attr.size);
 }
+
+test "addresses are in runes: a combining mark and a lone \\r are places of their own" {
+    const gpa = testing.allocator;
+    // e, U+0301 (two bytes, 1-2), x, \r, \n
+    const p = try withFile(gpa, "e\u{0301}x\r\n");
+    defer p.deinit();
+    const serial = serialOf(p);
+    const addr_node = Node.of(serial, .addr);
+    const dot = Node.of(serial, .dot);
+    const Case = struct { expr: []const u8, q0: u32, q1: u32 };
+    for ([_]Case{
+        .{ .expr = "#1,#3", .q0 = 1, .q1 = 3 }, // the mark alone
+        .{ .expr = "#2", .q0 = 1, .q1 = 1 }, // inside it: back to its start
+        .{ .expr = "#4,#5", .q0 = 4, .q1 = 5 }, // the \r alone
+        .{ .expr = "1:2", .q0 = 1, .q1 = 1 }, // line:col the same
+        .{ .expr = "1:3", .q0 = 1, .q1 = 1 },
+        .{ .expr = "0/\xCC/", .q0 = 1, .q1 = 3 }, // a match inside a rune covers it
+    }) |c| {
+        try testing.expectEqual(Status.ok, wr(p, addr_node, c.expr).reply.status);
+        try testing.expectEqual(c.q0, p.panes[0].?.fs.addr.q0);
+        try testing.expectEqual(c.q1, p.panes[0].?.fs.addr.q1);
+    }
+    // Copied to dot, it reads back the same.
+    _ = wr(p, addr_node, "#1,#3");
+    try testing.expectEqual(Status.ok, wr(p, dot, "          1           3 ").reply.status);
+    p.sync();
+    try testing.expectEqualStrings("          1           3 ", rd(p, dot, 0, 100).bytes);
+    _ = wr(p, addr_node, "#4,#5");
+    try testing.expectEqualStrings("\r", rd(p, Node.of(serial, .xdata), 0, 100).bytes);
+}