Apply Qwen NFC normalization before token splitting

Cargo.lock

@@ -834,6 +834,7 @@ dependencies = [
  "shlex",
  "time",
  "turbovault-parser",
+ "unicode-normalization-alignments",
  "ureq",
  "url",
  "usvg",
@@ -3948,6 +3949,15 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3b09c83c3c29d37506a3e260c08c03743a6bb66a9cd432c6934ab501a190571f"
 
+[[package]]
+name = "unicode-normalization-alignments"
+version = "0.1.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43f613e4fa046e69818dd287fdc4bc78175ff20331479dab6e1b0f98d57062de"
+dependencies = [
+ "smallvec",
+]
+
 [[package]]
 name = "unicode-properties"
 version = "0.1.4"