def slugify(s, delete_chars=SlugDeleteChars, subst_char=SubstChar):
"""
Convert (unicode) string to slug.
* This only handles Western-language strings with very basic
accents.
"""
from garage.html_utils import strip_tags, unescape
def convert_unwanted_chars(txt):
converted = []
for ch in txt:
if ch in delete_chars:
ch = subst_char
converted.append(ch)
return ''.join(converted)
s = s.strip("\r\n")
s = s.replace("\n", " ")
s = strip_accents(s)
s = strip_tags(unescape(s))
s = re.sub(r"['’]s", 's', s)
s = re.sub(r'([0-9\.]+)%', '\\1-percent', s)
s = s.replace("&", " and ")
s = s.replace("&", " and ")
s = s.replace("/", " ")
s = s.replace(" ", "-")
s = s.replace("_", "-")
s = convert_unwanted_chars(s)
s = re.sub(r'\.\.+', '.', s)
s = re.sub(r'--+', '-', s)
s = s.strip('.')
s = s.strip('-')
s = s.lower()
return s
def slugify(s, delete_chars=SlugDeleteChars, subst_char=SubstChar):
"""
Convert (unicode) string to slug.
"""
def convert_unwanted_chars(txt):
converted = []
for ch in txt:
if ch in delete_chars:
ch = subst_char
converted.append(ch)
return u''.join(converted)
s = s.decode("utf-8")
s = s.strip(u"\r\n")
s = s.replace(u"\n", u" ")
s = strip_accents(s)
s = strip_tags(unescape(s))
s = re.sub(r"[']s", u's', s)
s = re.sub(r'([0-9\.]+)%', u'\\1-percent', s)
s = s.replace(u"&", u" and ")
s = s.replace(u"&", u" and ")
s = s.replace(u"/", u" ")
s = s.replace(u" ", u"-")
s = s.replace(u"_", u"-")
s = convert_unwanted_chars(s)
s = re.sub(r'\.\.+', u'.', s)
s = re.sub(r'--+', u'-', s)
s = s.strip(u'.')
s = s.strip(u'-')
s = s.lower()
return s
def test_unescape(self):
"""
Ensure unescape function is working properly.
"""
from garage.html_utils import unescape
self._msg('test', 'unescape', first=True)
txt = '<em>he said, "q & a"</em> <abc> écriture 寫作'
expected = '<em>he said, "q & a"</em> <abc> écriture 寫作'
result = unescape(txt)
self._msg('text', txt)
self._msg('result', result)
self._msg('expected', expected)
self.assertEqual(result, expected)
