fix(core): preserve unicode in grep previews (#42356)

packages/core/src/ripgrep.ts

@@ -264,7 +264,10 @@ const layer = Layer.effect(
                 }),
                 line: match.line_number,
                 offset: match.absolute_offset,
-                text: match.lines.text.length > 2_000 ? match.lines.text.slice(0, 2_000) + "..." : match.lines.text,
+                text:
+                  match.lines.text.length > 2_000
+                    ? match.lines.text.slice(0, 2_000).replace(/[\uD800-\uDBFF]$/, "") + "..."
+                    : match.lines.text,
                 submatches: match.submatches.map((submatch) => ({
                   text: submatch.match.text,
                   start: submatch.start,

packages/core/test/ripgrep.test.ts

@@ -62,4 +62,24 @@ describe("Ripgrep", () => {
       (tmp) => Effect.promise(() => tmp[Symbol.asyncDispose]()),
     ),
   )
+  it.live("does not split surrogate pairs in oversized line previews", () =>
+    Effect.acquireUseRelease(
+      Effect.promise(() => tmpdir()),
+      (tmp) =>
+        Effect.gen(function* () {
+          yield* Effect.promise(() =>
+            fs.writeFile(path.join(tmp.path, "unicode.txt"), `needle${"x".repeat(1_993)}😀\n`),
+          )
+
+          const matches = yield* (yield* Ripgrep.Service).grep({
+            cwd: tmp.path,
+            pattern: "needle",
+            limit: 10,
+          })
+
+          expect(matches[0]?.text).toBe(`needle${"x".repeat(1_993)}...`)
+        }),
+      (tmp) => Effect.promise(() => tmp[Symbol.asyncDispose]()),
+    ),
+  )
 })