mirror of
https://github.com/python/cpython.git
synced 2025-07-28 13:44:43 +00:00
38 lines
1 KiB
Python
38 lines
1 KiB
Python
import re
|
|
import unicodedata
|
|
import functools
|
|
|
|
ANSI_ESCAPE_SEQUENCE = re.compile(r"\x1b\[[ -@]*[A-~]")
|
|
ZERO_WIDTH_BRACKET = re.compile(r"\x01.*?\x02")
|
|
ZERO_WIDTH_TRANS = str.maketrans({"\x01": "", "\x02": ""})
|
|
|
|
|
|
@functools.cache
|
|
def str_width(c: str) -> int:
|
|
if ord(c) < 128:
|
|
return 1
|
|
w = unicodedata.east_asian_width(c)
|
|
if w in ("N", "Na", "H", "A"):
|
|
return 1
|
|
return 2
|
|
|
|
|
|
def wlen(s: str) -> int:
|
|
if len(s) == 1 and s != "\x1a":
|
|
return str_width(s)
|
|
length = sum(str_width(i) for i in s)
|
|
# remove lengths of any escape sequences
|
|
sequence = ANSI_ESCAPE_SEQUENCE.findall(s)
|
|
ctrl_z_cnt = s.count("\x1a")
|
|
return length - sum(len(i) for i in sequence) + ctrl_z_cnt
|
|
|
|
|
|
def unbracket(s: str, including_content: bool = False) -> str:
|
|
r"""Return `s` with \001 and \002 characters removed.
|
|
|
|
If `including_content` is True, content between \001 and \002 is also
|
|
stripped.
|
|
"""
|
|
if including_content:
|
|
return ZERO_WIDTH_BRACKET.sub("", s)
|
|
return s.translate(ZERO_WIDTH_TRANS)
|