|
|
|
@ -1,5 +1,37 @@
|
|
|
|
|
# -*- coding: utf8 -*-
|
|
|
|
|
|
|
|
|
|
from __future__ import absolute_import
|
|
|
|
|
from __future__ import division, print_function, unicode_literals
|
|
|
|
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def is_blank(text):
|
|
|
|
|
"""
|
|
|
|
|
Returns ``True`` if string contains only whitespace characters
|
|
|
|
|
or is empty. Otherwise ``False`` is returned.
|
|
|
|
|
"""
|
|
|
|
|
return not text or text.isspace()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
MULTIPLE_WHITESPACE_PATTERN = re.compile(r"\s+", re.UNICODE)
|
|
|
|
|
def normalize_whitespace(text):
|
|
|
|
|
"""
|
|
|
|
|
Translates multiple whitespace into single space character.
|
|
|
|
|
If there is at least one new line character chunk is replaced
|
|
|
|
|
by single LF (Unix new line) character.
|
|
|
|
|
"""
|
|
|
|
|
return MULTIPLE_WHITESPACE_PATTERN.sub(_replace_whitespace, text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _replace_whitespace(match):
|
|
|
|
|
text = match.group()
|
|
|
|
|
|
|
|
|
|
if "\n" in text or "\r" in text:
|
|
|
|
|
return "\n"
|
|
|
|
|
else:
|
|
|
|
|
return " "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def cached_property(getter):
|
|
|
|
|
"""
|
|
|
|
|