Merge a116211 into 65ae0d1

deanmalmgren · Aug 15, 2021 · a8cfaed · a8cfaed
2 parents 65ae0d1 + a116211
commit a8cfaed
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/textract/parsers/utils.py b/textract/parsers/utils.py
@@ -66,7 +66,8 @@ def decode(self, text, input_encoding=None):
 
         # use chardet to automatically detect the encoding text if no encoding is provided
         result = chardet.detect(text)
-        return text.decode(result['encoding'], errors="replace")
+        encoding = result['encoding'] if result['confidence'] > 0.80 else 'utf8'
+        return text.decode(encoding, errors="replace")
 
 
 class ShellParser(BaseParser):