import re
def preprocess(text):
#remove all non-alpha characters but - between letters
text = re.sub(r'[\W\d_](?<![^\W\d_]-(?=[^\W\d_]))', r' ', text)
return " ".join(text.split())
print(preprocess("Attended pre-tender, etc meetings."))
aW1wb3J0IHJlCgpkZWYgcHJlcHJvY2Vzcyh0ZXh0KToKICAjcmVtb3ZlIGFsbCBub24tYWxwaGEgY2hhcmFjdGVycyBidXQgLSBiZXR3ZWVuIGxldHRlcnMKICB0ZXh0ID0gcmUuc3ViKHInW1xXXGRfXSg/PCFbXlxXXGRfXS0oPz1bXlxXXGRfXSkpJywgcicgJywgdGV4dCkKICByZXR1cm4gIiAiLmpvaW4odGV4dC5zcGxpdCgpKQoKcHJpbnQocHJlcHJvY2VzcygiQXR0ZW5kZWQgcHJlLXRlbmRlciwgZXRjIG1lZXRpbmdzLiIpKQoK