def test_render_token_with_punctuation(self):
token_text = "')."
expected_text = token_text
token_dict = self._maketokendict(token=token_text, tokentype=tokenizer.TOKEN_SPACE)
rendered = htmlgenerator.render_token(token_dict)
self.assertEqual(htmlgenerator.TEXT_NODE, rendered['node_type'])
self.assertEqual(expected_text, rendered['text'])
def test_render_token_with_multiple_spaces(self):
token_text = " " * 3
expected_text = token_text.replace(" ", "\u00A0\u00A0")
token_dict = self._maketokendict(token=token_text, tokentype=tokenizer.TOKEN_SPACE)
rendered = htmlgenerator.render_token(token_dict)
self.assertEqual(htmlgenerator.TEXT_NODE, rendered['node_type'])
self.assertEqual(expected_text, rendered['text'])
def test_render_token_english_word(self):
token_text = "hypothetical"
token_dict = self._maketokendict(token=token_text, tokentype=tokenizer.TOKEN_WORD)
rendered = htmlgenerator.render_token(token_dict)
node_type, el = rendered['node_type'], rendered['element']
self.assertEqual(htmlgenerator.ELEMENT_NODE, node_type)
self.assertEqual("span", el.tag)
self.assertEqual({"class": "word"}, el.attrib)
self.assertEqual(token_text, el.text)
def test_render_token_russian_word(self):
token_text = "первоку́рсник"
token_dict = self._maketokendict(token=token_text, tokentype=tokenizer.TOKEN_RUS, level="3A", form_ids=["174128"])
rendered = htmlgenerator.render_token(token_dict)
node_type, el = rendered['node_type'], rendered['element']
self.assertEqual(htmlgenerator.ELEMENT_NODE, node_type)
self.assertEqual("span", el.tag)
self.assertEqual({
"class": "word parsed level3",
"data-form-ids": ",".join(token_dict['form_ids']),
"data-level": token_dict['level']
}, el.attrib)
self.assertEqual(token_text, el.text)