fix(cursor): keep the visual selection whole over characters outside the BMP (#2683)

* fix(cursor): keep the visual selection whole over characters outside the BMP

The inclusive Nvim end column was turned into an exclusive VSCode one by
adding a single UTF-16 unit. A character outside the BMP is two of them, so
the selection ended in the middle of a surrogate pair and drifted away from
where Nvim had the cursor: moving right over it took two presses and the
selected region no longer matched.

Step over the whole character instead, using its byte length.

Closes #2535

* test(cursor): add visual selection tests for non-BMP characters

* test(cursor): expect the astral pair to be whole in the mixed-character selection

---------

Co-authored-by: wongxy <xiyao.wong@foxmail.com>

runtime/lua/vscode/util.lua

@@ -63,6 +63,17 @@ function M.utf16_col(text, byte_col)
   return byte_col == 0 and 0 or str_utf16index(text, byte_col)
 end
 
+---@param text string the line the column belongs to
+---@param byte_col integer zero-indexed byte column, clamped to `text`
+---@return integer zero-indexed byte column just past the character byte_col points into
+local function byte_after_char(text, byte_col)
+  byte_col = math.max(0, math.min(byte_col, #text))
+  if byte_col == #text then
+    return byte_col
+  end
+  return byte_col + vim.str_utf_end(text, byte_col + 1) + 1
+end
+
 ---@param buf integer
 ---@param line integer one-indexed line
 ---@param byte_col integer zero-indexed byte column
@@ -84,10 +95,11 @@ end
 ---@return lsp.Range
 function M.lsp_range(buf, start_line, start_col, end_line, end_col)
   local end_text = M.get_line(buf, end_line - 1) or ""
-  local end_char = M.utf16_col(end_text, end_col)
   if vim.o.selection ~= "exclusive" then
-    end_char = math.min(end_char + 1, M.utf16_col(end_text, #end_text))
+    -- step over the whole character: adding one UTF-16 unit splits a surrogate pair
+    end_col = byte_after_char(end_text, end_col)
   end
+  local end_char = M.utf16_col(end_text, end_col)
   return {
     start = M.lsp_position(buf, start_line, start_col),
     ["end"] = { line = end_line - 1, character = end_char },

src/test/integ/multi-byte-chars.test.ts

@@ -1,4 +1,5 @@
 import { NeovimClient } from "neovim";
+import vscode from "vscode";
 
 import {
     attachTestNvimClient,
@@ -286,4 +287,54 @@ describe("Multi-width characters", () => {
             client,
         );
     });
+
+    it("Works - visual mode over chars outside the BMP", async () => {
+        // 𝕜 is U+1D55C: one Nvim character, but two UTF-16 units for VSCode
+        await openTextDocument({ content: ["a𝕜b"].join("\n") });
+
+        await assertContent({ content: ["a𝕜b"], cursor: [0, 0] }, client);
+
+        await sendVSCodeKeys("v");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 1)] }, client);
+
+        await sendVSCodeKeys("l");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 3)] }, client);
+
+        await sendVSCodeKeys("l");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 4)] }, client);
+
+        await sendEscapeKey();
+    });
+
+    it("Works - visual mode over consecutive non-BMP chars", async () => {
+        await openTextDocument({ content: ["a𝕜𝕝b"].join("\n") });
+
+        await sendVSCodeKeys("v");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 1)] }, client);
+
+        await sendVSCodeKeys("ll");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 5)] }, client);
+
+        await sendVSCodeKeys("l");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 6)] }, client);
+
+        await sendEscapeKey();
+    });
+
+    it("Works - visual mode across mixed BMP and non-BMP chars", async () => {
+        await openTextDocument({ content: ["aᵩ𝕜b"].join("\n") });
+
+        await sendVSCodeKeys("v");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 1)] }, client);
+
+        // the cursor sits on the astral char, whose two UTF-16 units both belong to
+        // the selection: a, the modifier letter and the pair take offsets 0 to 4
+        await sendVSCodeKeys("ll");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 4)] }, client);
+
+        await sendVSCodeKeys("l");
+        await assertContent({ vsCodeSelections: [new vscode.Selection(0, 0, 0, 5)] }, client);
+
+        await sendEscapeKey();
+    });
 });