ascii filter

3def65b7 · jyong · 2ede27d3 · 3def65b7
Commit 3def65b7 authored Jan 14, 2024 by jyong
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

indexing_runner.py api/core/indexing_runner.py +2 -1

No files found.
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@@ -531,7 +531,8 @@ class IndexingRunner:
    def filter_string(self, text):
        text = re.sub(r'<\|', '<', text)
        text = re.sub(r'\|>', '>', text)
-        text = re.sub(r'[\x00-\x08\x0B\x0C\x0E-\x1F\x7F\x80-\xFF]', '', text)
+        text = re.sub(r'[\x00-\x08\x0B\x0C\x0E-\x1F\x7F\xA0-\xFF]', '', text)
+
        return text

    def _get_splitter(self, processing_rule: DatasetProcessRule,