Skip to content

Commit

Permalink
Merge pull request #8 from pratikrelekar/xinyao
Browse files Browse the repository at this point in the history
Update module.py
  • Loading branch information
xinyaoq authored Dec 2, 2024
2 parents 1a8e12b + 9dc3099 commit 819bccf
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions module.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,8 @@ def clean_noisy_text(self, text):
return ""

def is_noisy(word):
# Allow specific patterns like "0000907471-18-000139" or "0000907471-18-000139.txt"
if re.match(r'^\d{10}-\d{2}-\d{6}(\.txt)?$', word):
# Allow specific patterns like "0000907471-18-000139", "0000907471-18-000139.txt", and "0001000015-98-000009.hdr.sgml"
if re.match(r'^\d{10}-\d{2}-\d{6}(\.txt|\.hdr\.sgml)?$', word):
return False

# Check for noisy conditions
Expand Down

0 comments on commit 819bccf

Please sign in to comment.