From 51445c69c0191719f56a90ed8b19ab78dd626305 Mon Sep 17 00:00:00 2001
From: Brian Sam-Bodden <bsb@redis.com>
Date: Mon, 16 Feb 2026 17:23:13 -0700
Subject: [PATCH] fix: avoid NLTK download race condition in parallel test
 workers

Try loading stopwords before downloading to prevent concurrent
pytest-xdist workers from racing on nltk.download(), which raises
FileExistsError when multiple processes write to the same path.
---
 redisvl/query/query.py                  | 10 ++++++++--
 redisvl/utils/full_text_query_helper.py | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/redisvl/query/query.py b/redisvl/query/query.py
index 7d4cbe88..e96ffd78 100644
--- a/redisvl/query/query.py
+++ b/redisvl/query/query.py
@@ -1460,8 +1460,14 @@ def _set_stopwords(self, stopwords: Optional[Union[str, Set[str]]] = "english"):
             self._stopwords = set()
         elif isinstance(stopwords, str):
             try:
-                nltk.download("stopwords", quiet=True)
-                self._stopwords = set(nltk_stopwords.words(stopwords))
+                # Try loading first; only download if not already present.
+                # This avoids race conditions when parallel workers (e.g.
+                # pytest-xdist) call nltk.download() concurrently.
+                try:
+                    self._stopwords = set(nltk_stopwords.words(stopwords))
+                except LookupError:
+                    nltk.download("stopwords", quiet=True)
+                    self._stopwords = set(nltk_stopwords.words(stopwords))
             except ImportError:
                 raise ValueError(
                     f"Loading stopwords for {stopwords} failed: nltk is not installed."
diff --git a/redisvl/utils/full_text_query_helper.py b/redisvl/utils/full_text_query_helper.py
index ee5b8cb7..cdb6877c 100644
--- a/redisvl/utils/full_text_query_helper.py
+++ b/redisvl/utils/full_text_query_helper.py
@@ -93,8 +93,14 @@ def _get_stopwords(
             return set()
         elif isinstance(stopwords, str):
             try:
-                nltk.download("stopwords", quiet=True)
-                return set(nltk_stopwords.words(stopwords))
+                # Try loading first; only download if not already present.
+                # This avoids race conditions when parallel workers (e.g.
+                # pytest-xdist) call nltk.download() concurrently.
+                try:
+                    return set(nltk_stopwords.words(stopwords))
+                except LookupError:
+                    nltk.download("stopwords", quiet=True)
+                    return set(nltk_stopwords.words(stopwords))
             except ImportError:
                 raise ValueError(
                     f"Loading stopwords for {stopwords} failed: nltk is not installed."