Skip to content

Commit

Permalink
Merge pull request #26 from FranklinChen/fix-regexes-again
Browse files Browse the repository at this point in the history
Fix bugs in regex strings.
  • Loading branch information
Jemoka authored Feb 22, 2025
2 parents c172ad3 + adf8edd commit 7d4e7cb
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 4 deletions.
4 changes: 2 additions & 2 deletions batchalign/pipelines/fa/wave2vec_fa.py
Original file line number Diff line number Diff line change
Expand Up @@ -154,9 +154,9 @@ def process(self, doc:Document, **kwargs):
if '\x15' not in ut.text:
ut.text = (ut.text+f" \x15{ut.alignment[0]}_{ut.alignment[1]}\x15").strip()
else:
ut.text = re.sub("\x15\d+_\d+\x15",
ut.text = re.sub(r"\x15\d+_\d+\x15",
f"\x15{ut.alignment[0]}_{ut.alignment[1]}\x15", ut.text).strip()
elif ut.text != None:
ut.text = re.sub("\x15\d+_\d+\x15", f"", ut.text).strip()
ut.text = re.sub(r"\x15\d+_\d+\x15", f"", ut.text).strip()

return doc
4 changes: 2 additions & 2 deletions batchalign/pipelines/fa/whisper_fa.py
Original file line number Diff line number Diff line change
Expand Up @@ -179,9 +179,9 @@ def process(self, doc:Document, **kwargs):
if '\x15' not in ut.text:
ut.text = (ut.text+f" \x15{ut.alignment[0]}_{ut.alignment[1]}\x15").strip()
else:
ut.text = re.sub("\x15\d+_\d+\x15",
ut.text = re.sub(r"\x15\d+_\d+\x15",
f"\x15{ut.alignment[0]}_{ut.alignment[1]}\x15", ut.text).strip()
elif ut.text != None:
ut.text = re.sub("\x15\d+_\d+\x15", f"", ut.text).strip()
ut.text = re.sub(r"\x15\d+_\d+\x15", f"", ut.text).strip()

return doc

0 comments on commit 7d4e7cb

Please sign in to comment.