'\U000e0076',
'\U000e0077',
'\U000e0078',
'\U000e0079',
'\U000e007a',
'\U000e007b',
'\U000e007c',
'\U000e007d',
'\U000e007e',
'\U000e007f',
])
# This is a set of all invisible characters
# At the moment we've only added the characters from the Cf category
_invisible_chars = _category_cf
invisible_regex = LazyRegex(lambda: '[' + ''.join(_invisible_chars) + ']')
def contains_invisible(text):
"""Return True if the text contain any of the invisible characters."""
return any(char in _invisible_chars for char in text)
def replace_invisible(text):
"""Replace invisible characters by '<codepoint>'."""
def replace(match):
match = match.group()
if sys.maxunicode < 0x10ffff and len(match) == 2:
mask = (1 << 10) - 1
assert (ord(match[0]) & ~mask == 0xd800)
assert (ord(match[1]) & ~mask == 0xdc00)
# This means ipaddress has correctly determined '1111' is invalid
pass
except ImportError as e:
warn('Importing ipaddress.ip_address failed: %s' % e, ImportWarning)
def ip_address(IP):
"""Fake ip_address method."""
warn('ipaddress backport not available.', DeprecationWarning)
if ip_regexp.match(IP) is None:
raise ValueError('Invalid IP address')
# The following flag is used by the unit tests
ip_address.__fake__ = True
# deprecated IP detector
ip_regexp = LazyRegex()
ip_regexp.flags = re.IGNORECASE
ip_regexp.raw = (r'^(?:(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}'
r'(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|'
r'(((?=(?=(.*?(::)))\3(?!.+\4)))\4?|[\dA-F]{1,4}:)'
r'([\dA-F]{1,4}(\4|:\b)|\2){5}'
r'(([\dA-F]{1,4}(\4|:\b|$)|\2){2}|'
r'(((2[0-4]|1\d|[1-9])?\d|25[0-5])\.?\b){4}))\Z')
def is_IP(IP):
"""
Verify the IP address provided is valid.
No logging is performed. Use ip_address instead to catch errors.
"""Character based helper functions (not wiki-dependent)."""
#
# (C) Pywikibot team, 2015-2021
#
# Distributed under the terms of the MIT license.
#
import sys
from pywikibot.tools._unidata import _category_cf
from pywikibot.tools import LazyRegex
# This is a set of all invisible characters
# At the moment we've only added the characters from the Cf category
_invisible_chars = _category_cf
invisible_regex = LazyRegex(lambda: '[{}]'.format(''.join(_invisible_chars)))
def contains_invisible(text):
"""Return True if the text contain any of the invisible characters."""
return any(char in _invisible_chars for char in text)
def replace_invisible(text):
"""Replace invisible characters by '<codepoint>'."""
def replace(match):
match = match.group()
if sys.maxunicode < 0x10ffff and len(match) == 2:
mask = (1 << 10) - 1
assert ord(match[0]) & ~mask == 0xd800
assert ord(match[1]) & ~mask == 0xdc00
'\U000e0053', '\U000e0054', '\U000e0055', '\U000e0056', '\U000e0057',
'\U000e0058', '\U000e0059', '\U000e005a', '\U000e005b', '\U000e005c',
'\U000e005d', '\U000e005e', '\U000e005f', '\U000e0060', '\U000e0061',
'\U000e0062', '\U000e0063', '\U000e0064', '\U000e0065', '\U000e0066',
'\U000e0067', '\U000e0068', '\U000e0069', '\U000e006a', '\U000e006b',
'\U000e006c', '\U000e006d', '\U000e006e', '\U000e006f', '\U000e0070',
'\U000e0071', '\U000e0072', '\U000e0073', '\U000e0074', '\U000e0075',
'\U000e0076', '\U000e0077', '\U000e0078', '\U000e0079', '\U000e007a',
'\U000e007b', '\U000e007c', '\U000e007d', '\U000e007e', '\U000e007f',
])
# This is a set of all invisible characters
# At the moment we've only added the characters from the Cf category
_invisible_chars = frozenset(_category_cf)
# TODO: Is that complex and a lazy regex justified?
invisible_regex = LazyRegex()
invisible_regex.raw = '[' + ''.join(_invisible_chars) + ']'
invisible_regex.flags = 0
def contains_invisible(text):
"""Return True if the text contain any of the invisible characters."""
return any(char in _invisible_chars for char in text)
def replace_invisible(text):
"""Replace invisible characters by '<codepoint>'."""
def replace(match):
match = match.group()
if sys.maxunicode < 0x10ffff and len(match) == 2:
mask = (1 << 10) - 1
pass
except ImportError as e:
warn('Importing ipaddress.ip_address failed: %s' % e,
ImportWarning)
def ip_address(IP):
"""Fake ip_address method."""
warn('ipaddress backport not available.', DeprecationWarning)
if ip_regexp.match(IP) is None:
raise ValueError('Invalid IP address')
# The following flag is used by the unit tests
ip_address.__fake__ = True
# deprecated IP detector
ip_regexp = LazyRegex()
ip_regexp.flags = re.IGNORECASE
ip_regexp.raw = (
r'^(?:(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}'
r'(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|'
r'(((?=(?=(.*?(::)))\3(?!.+\4)))\4?|[\dA-F]{1,4}:)'
r'([\dA-F]{1,4}(\4|:\b)|\2){5}'
r'(([\dA-F]{1,4}(\4|:\b|$)|\2){2}|'
r'(((2[0-4]|1\d|[1-9])?\d|25[0-5])\.?\b){4}))\Z')
def is_IP(IP):
"""
Verify the IP address provided is valid.
No logging is performed. Use ip_address instead to catch errors.
