open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-28 17:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: Update sentence extraction regex to preserve ending punctuation

Browse source
This commit is contained in:
Andreas Koepf (aider) 2025-01-26 15:56:03 +01:00
parent fa9465e6a9
commit b03b02f3a5
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
reasoning_gym/algorithmic/sentence_reordering.py
View file

@ -33,8 +33,8 @@ class SentenceReorderingDataset(ProceduralDataset):
# Extract sentences make sure they are greater than or equal to the number of words in a sentence # Extract sentences make sure they are greater than or equal to the number of words in a sentence
# Ensure that only the length of alphanumeric characters in the sentence is considered # Ensure that only the length of alphanumeric characters in the sentence is considered
self.sentences = [ self.sentences = [
sentence sentence.strip()
for sentence in re.findall(r"[^.!?]+", text) for sentence in re.findall(r"[^.!?]+[.!?]", text) # Changed pattern to include the ending punctuation
if self.config.min_words_in_sentence <= len(re.findall(r"\b\w+\b", sentence)) <= self.config.max_words_in_sentence if self.config.min_words_in_sentence <= len(re.findall(r"\b\w+\b", sentence)) <= self.config.max_words_in_sentence
] ]