chore: commented regex
This commit is contained in:
@@ -31,8 +31,19 @@ from pipecat.utils.utils import exp_smoothing
|
|||||||
import re
|
import re
|
||||||
|
|
||||||
|
|
||||||
endofsentence_pattern = r"(?<![A-Z])(?<!\d)(?<!\d\s[ap])(?<!Mr|Ms|Dr)(?<!Mrs)(?<!Prof)[\.\?\!:]$"
|
endofsentence_pattern = r"""
|
||||||
endofsentence_re = re.compile(endofsentence_pattern)
|
(?<![A-Z]) # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
|
||||||
|
(?<!\d) # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
|
||||||
|
(?<!\d\s[ap]) # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
|
||||||
|
(?<!Mr) # Negative lookbehind: not preceded by "Mr"
|
||||||
|
(?<!Ms) # Negative lookbehind: not preceded by "Ms"
|
||||||
|
(?<!Dr) # Negative lookbehind: not preceded by "Dr"
|
||||||
|
(?<!Mrs) # Negative lookbehind: not preceded by "Mrs"
|
||||||
|
(?<!Prof) # Negative lookbehind: not preceded by "Prof"
|
||||||
|
[\.\?\!:] # Match a period, question mark, exclamation point, or colon
|
||||||
|
$ # End of string
|
||||||
|
"""
|
||||||
|
endofsentence_re = re.compile(endofsentence_pattern, re.VERBOSE)
|
||||||
|
|
||||||
|
|
||||||
def match_endofsentence(text: str) -> bool:
|
def match_endofsentence(text: str) -> bool:
|
||||||
|
|||||||
Reference in New Issue
Block a user