diff options
Diffstat (limited to 'tests/test_soup.py')
| -rw-r--r-- | tests/test_soup.py | 20 |
1 files changed, 13 insertions, 7 deletions
diff --git a/tests/test_soup.py b/tests/test_soup.py index 4fb2142..01dff53 100644 --- a/tests/test_soup.py +++ b/tests/test_soup.py @@ -19,15 +19,21 @@ class TestSelectiveParsing(SoupTest): class TestUnicodeDammit(unittest.TestCase): """Standalone tests of Unicode, Dammit.""" - def test_smart_quotes_to_xml_entities(self): + def test_smart_quotes_to_unicode(self): markup = "<foo>\x91\x92\x93\x94</foo>" dammit = UnicodeDammit(markup) self.assertEquals( + dammit.unicode, u"<foo>\u2018\u2019\u201c\u201d</foo>") + + def test_smart_quotes_to_xml_entities(self): + markup = "<foo>\x91\x92\x93\x94</foo>" + dammit = UnicodeDammit(markup, smart_quotes_to="xml") + self.assertEquals( dammit.unicode, "<foo>‘’“”</foo>") def test_smart_quotes_to_html_entities(self): markup = "<foo>\x91\x92\x93\x94</foo>" - dammit = UnicodeDammit(markup, smartQuotesTo="html") + dammit = UnicodeDammit(markup, smart_quotes_to="html") self.assertEquals( dammit.unicode, "<foo>‘’“”</foo>") @@ -35,27 +41,27 @@ class TestUnicodeDammit(unittest.TestCase): utf8 = "\xc3\xa9" dammit = UnicodeDammit(utf8) self.assertEquals(dammit.unicode, u'\xe9') - self.assertEquals(dammit.originalEncoding, 'utf-8') + self.assertEquals(dammit.original_encoding, 'utf-8') def test_convert_hebrew(self): hebrew = "\xed\xe5\xec\xf9" dammit = UnicodeDammit(hebrew, ["iso-8859-8"]) - self.assertEquals(dammit.originalEncoding, 'iso-8859-8') + self.assertEquals(dammit.original_encoding, 'iso-8859-8') self.assertEquals(dammit.unicode, u'\u05dd\u05d5\u05dc\u05e9') def test_dont_see_smart_quotes_where_there_are_none(self): utf_8 = "\343\202\261\343\203\274\343\202\277\343\202\244 Watch" dammit = UnicodeDammit(utf_8) - self.assertEquals(dammit.originalEncoding, 'utf-8') + self.assertEquals(dammit.original_encoding, 'utf-8') self.assertEquals(dammit.unicode.encode("utf-8"), utf_8) def test_ignore_inappropriate_codecs(self): utf8_data = u"Räksmörgås".encode("utf-8") dammit = UnicodeDammit(utf8_data, ["iso-8859-8"]) - self.assertEquals(dammit.originalEncoding, 'utf-8') + self.assertEquals(dammit.original_encoding, 'utf-8') def test_ignore_invalid_codecs(self): utf8_data = u"Räksmörgås".encode("utf-8") for bad_encoding in ['.utf8', '...', 'utF---16.!']: dammit = UnicodeDammit(utf8_data, [bad_encoding]) - self.assertEquals(dammit.originalEncoding, 'utf-8') + self.assertEquals(dammit.original_encoding, 'utf-8') |