Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions chatterbot/preprocessors.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,21 @@
Statement pre-processors.
"""

from nltk import RegexpTokenizer


def remove_punctuation(statement):
"""
Remove any punctuation from the statement text
"""
# Make tokenizer
tokenizer = RegexpTokenizer(r"\w+")

#make a list of words without punctuation
statement.text = " ".join(tokenizer.tokenize(statement.text))

return statement


def clean_whitespace(statement):
"""
Expand Down