From 67fc76e4e450d9963a8cf4e50b110998f6abcc3d Mon Sep 17 00:00:00 2001
From: lakshit verma <vermalucky2004@gmail.com>
Date: Thu, 13 Aug 2026 16:06:51 +0530
Subject: [PATCH] build_oss_db: derive default output dir from data_root

The default --output-dir hardcoded a path constructed from parents[2],
duplicating the floss/tags/data root that data_root() already provides.
Use data_root() / "oss" so the script follows the same source of truth
as query_string.py.
---
 scripts/tags/build_oss_db.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/scripts/tags/build_oss_db.py b/scripts/tags/build_oss_db.py
index e103e18..8c4017e 100644
--- a/scripts/tags/build_oss_db.py
+++ b/scripts/tags/build_oss_db.py
@@ -49,6 +49,8 @@ import subprocess
 from typing import Set, Dict, List, Tuple, Callable, Optional
 from dataclasses import dataclass
 
+from floss.tags import data_root
+
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
@@ -1099,7 +1101,7 @@ def parse_args(argv: Optional[List[str]] = None) -> argparse.Namespace:
     parser.add_argument(
         "--output-dir",
         type=pathlib.Path,
-        default=pathlib.Path(__file__).resolve().parents[2] / "floss" / "tags" / "data" / "oss",
+        default=data_root() / "oss",
         help="directory for generated .jsonl.gz files and metrics",
     )
     parser.add_argument(