def seo_tokenize(title, lower=True):
"""Get SEO-tokenized version of a string, typically a name or title
`title` the string to tokenize
`lower` whether to lowercase the string
e.g.
<- "The World's Greatest Establishment"
-> 'the-worlds-greatest-establishment'
<- 'Recreational Sports Facility, Berkeley, CA', lower=False
-> 'Recreational-Sports-Facility-Berkeley-CA'
"""
cleaned_title = title.strip()
try:
cleaned_title = unicode_to_ascii(cleaned_title)
except:
pass
if lower:
cleaned_title = cleaned_title.lower()
else:
pass
# allow only spaces, alpha-numeric
cleaned_title = re.sub('[^ A-Za-z0-9]', '', cleaned_title)
tokenized_title = '-'.join(cleaned_title.split())
return tokenized_title
def seo_tokenize(title, lower=True):
"""Get SEO-tokenized version of a string, typically a name or title
`title` the string to tokenize
`lower` whether to lowercase the string
e.g.
<- "The World's Greatest Establishment"
-> 'the-worlds-greatest-establishment'
<- 'Recreational Sports Facility, Berkeley, CA', lower=False
-> 'Recreational-Sports-Facility-Berkeley-CA'
"""
cleaned_title = title.strip()
try:
cleaned_title = unicode_to_ascii(cleaned_title)
except:
pass
if lower:
cleaned_title = cleaned_title.lower()
else:
pass
# allow only spaces, hyphens, alpha-numeric
cleaned_title = re.sub('[^ \-A-Za-z0-9]', '', cleaned_title)
tokenized_title = '-'.join(cleaned_title.split())
return tokenized_title
def seo_tokenize(title,
lower=True,
preserve_ascii_extended=False,
preserve_unicode=False):
"""Get SEO-tokenized version of a string, typically a name or title
`title` the string to tokenize
`lower` whether to lowercase the string
`preserve_ascii_extended` will preserve extended ASCII characters if `True`
`preserve_unicode` will preserve Unicode if `True`
e.g.
<- "The World's Greatest Establishment"
-> 'the-worlds-greatest-establishment'
<- 'Recreational Sports Facility, Berkeley, CA', lower=False
-> 'Recreational-Sports-Facility-Berkeley-CA'
"""
cleaned_title = title.strip()
try:
if preserve_ascii_extended or preserve_unicode:
# do nothing, keep extended ASCII and Unicode in title
pass
else:
cleaned_title = unicode_to_ascii(cleaned_title)
except:
pass
if lower:
cleaned_title = cleaned_title.lower()
else:
pass
def _repl(matchobj):
c = matchobj.group(0)
if is_ascii_extended(c):
replaced_c = c if preserve_ascii_extended else ''
elif is_ascii(c):
# it is ASCII, but not one of the accepted ASCII characters
replaced_c = ''
else:
replaced_c = c if preserve_unicode else ''
return replaced_c
cleaned_title = re.sub(r'[^ \-A-Za-z0-9]', _repl, cleaned_title)
# replace whitespace in string with hyphens
tokenized_title = '-'.join(cleaned_title.split())
return tokenized_title
def ssml_sanitized(s):
sanitized = re.sub(r'&', 'and', unicode_to_ascii(s))
return sanitized