def valid_username(self):
if not self.text:
return False
extracted = Extractor(self.text).extract_mentioned_screen_names()
return len(extracted) == 1 and extracted[0] == self.text[1:]
def tweet_length(self, options = {}):
"""
Returns the length of the string as it would be displayed. This is equivilent to the length of the Unicode NFC
(See: http://www.unicode.org/reports/tr15). This is needed in order to consistently calculate the length of a
string no matter which actual form was transmitted. For example:
U+0065 Latin Small Letter E
+ U+0301 Combining Acute Accent
----------
= 2 bytes, 2 characters, displayed as é (1 visual glyph)
… The NFC of {U+0065, U+0301} is {U+00E9}, which is a single chracter and a +display_length+ of 1
The string could also contain U+00E9 already, in which case the canonicalization will not change the value.
"""
assert (not self.parent or not getattr(self.parent, 'has_been_linked', False) ), 'The validator should only be run on text before it has been modified.'
for key in DEFAULT_TCO_URL_LENGTHS:
if not key in options:
options[key] = DEFAULT_TCO_URL_LENGTHS[key]
length = len(self.text)
# thanks force_unicode for making this so much simpler than the ruby version
for url in Extractor(self.text).extract_urls_with_indices():
# remove the link of the original URL
length += url['indices'][0] - url['indices'][1]
# add the length of the t.co URL that will replace it
length += options.get('short_url_length_https') if url['url'].lower().find('https://') > -1 else options.get('short_url_length')
if self.parent and hasattr(self.parent, 'tweet_length'):
self.parent.tweet_length = length
return length
def valid_hashtag(self):
if not self.text:
return False
extracted = Extractor(self.text).extract_hashtags()
return len(extracted) == 1 and extracted[0] == self.text[1:]
def __init__(self, text, **kwargs):
self.text = force_unicode(text)
self.parent = kwargs.get('parent', False)
self.extractor = Extractor(self.text)
def extractor(self):
return Extractor(self.text)
