class TextExtractionMixin():
def _prepare_dom(self, html):
self.last_html = '' + html + ''
def _simple_test(self, html, expected_sq, expected_nosq, **kwargs):
raise NotImplementedError
def test_inline_tags(self):
self._simple_test(
'Phasellus eget sem facilisis justo',
'Phasellus eget sem facilisis justo',
'Phasellus eget sem facilisis justo',
)
self._simple_test(
'Phasellus eget sem facilisis\n justo',
'Phasellus eget sem facilisis justo',
'Phasellus eget sem facilisis\n justo',
)
self._simple_test(
('Phasellus \n eget\n '
'sem\n\tfacilisis justo'),
'Phasellus eget sem facilisis justo',
'Phasellus \n eget\n sem\n\tfacilisis justo'
)
def test_block_tags(self):
self._simple_test(
'Phasell
us eget
sem facilisis
justo',
'Phas\nell\nus\neget\nsem\nfacilisis\njusto',
'Phas\nell\nus\n eget \nsem \nfacilisis\n justo',
)
self._simple_test(
'In sagittis
rutrum
condimentum
',
'In sagittis\nrutrum\ncondimentum',
'In sagittis\n \nrutrum\n\ncondimentum',
)
self._simple_test(
'In \nultricies
\n erat et \n\n\nmaximus\n\n
mollis',
'In\nultricies\nerat et\nmaximus\nmollis',
'In \n\nultricies\n\n erat et \n\n\n\nmaximus\n\n\n mollis',
)
self._simple_test(
('Integer libero'),
'Integer\nquis commodo\nlibero',
'Integer \n\n\n \nquis commodo\n\n \n libero',
)
self._simple_test(
'Heading',
'Heading\none\ntwo\nthree',
'Heading\n\none\n\ntwo\n\nthree',
)
def test_separators(self):
self._simple_test(
'Some words
test. Another word
test.',
'Some words\ntest. Another word\n\n\ntest.',
'Some words\ntest. Another word\n\n \n test.',
)
self._simple_test(
'Inline splitted by\nbr
tag test',
'Inline splitted by br\ntag test',
'Inline splitted by\nbr\ntag test',
)
self._simple_test(
'Some words
test. Another word
test.',
'Some words\ntest. Another word\ntest.',
'Some words\n\ntest. Another word\n\n\n\n \n\n test.',
)
def test_strip(self):
self._simple_test(
' text\n',
'text',
' text\n',
)
def test_ul_li(self):
self._simple_test(
'',
'',
' \n \n '
)