chore: update redb for performance

utils/rev_hashed_userid.py

@@ -0,0 +1,20 @@
+from sys import argv
+import polars as pl
+import polars_hash as pl_hash
+
+file = argv[1]
+
+user_ids = (
+    pl.DataFrame({"user_id_num": range(11000000, 13000001)})
+    .with_columns(
+        pl.col("user_id_num")
+        .cast(pl.String)
+        .add("Lt2N5xgjJOqRsT5qVt7wWYw6SqOPZDI7")
+        .alias("user_id"),
+    )
+    .with_columns(pl_hash.col("user_id").chash.sha2_256().str.head(16))
+    .join(pl.read_parquet(file), on="user_id", how="inner")["user_id_num"]
+)
+
+with open("id.txt", "w", encoding="utf-8") as f:
+    f.write("\n".join(map(str, user_ids)))