Set UTF-8 encoding when opening stop words (fixes Windows bug)

digitalmethodsinitiative · Aug 21, 2024 · 1d749c3 · 1d749c3
1 parent a03e5fd
commit 1d749c3
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/processors/text-analysis/tokenise.py b/processors/text-analysis/tokenise.py
@@ -239,7 +239,7 @@ def process(self):
 		numbers = re.compile(r"\b[0-9]+\b")
 
 		# load general stopwords dictionary
-		with config.get("PATH_ROOT").joinpath("common/assets/stopwords-iso.json").open() as infile:
+		with open(config.get("PATH_ROOT").joinpath("common/assets/stopwords-iso.json"), encoding="utf-8") as infile:
 			stopwords_iso = json.load(infile)
 
 		# Twitter tokenizer if indicated