diff options
Diffstat (limited to 'tests/test_lxml.py')
| -rw-r--r-- | tests/test_lxml.py | 65 |
1 files changed, 59 insertions, 6 deletions
diff --git a/tests/test_lxml.py b/tests/test_lxml.py index 4c11b1d..7e15dcf 100644 --- a/tests/test_lxml.py +++ b/tests/test_lxml.py @@ -376,6 +376,59 @@ class TestLXMLBuilderInvalidMarkup(SoupTest): markup = "<div><![CDATA[foo]]>" self.assertSoupEquals(markup, "<div></div>") + def test_attribute_value_never_got_closed(self): + markup = '<a href="http://foo.com/</a> and blah and blah' + soup = self.soup(markup) + self.assertEquals( + soup.a['href'], "http://foo.com/</a> and blah and blah") + + def test_attribute_value_was_closed_by_subsequent_tag(self): + markup = """<a href="foo</a>, </a><a href="bar">baz</a>""" + soup = self.soup(markup) + # The string between the first and second quotes was interpreted + # as the value of the 'href' attribute. + self.assertEquals(soup.a['href'], 'foo</a>, </a><a href=') + + #The string after the second quote (bar"), was treated as an + #empty attribute called bar. + self.assertEquals(soup.a['bar'], '') + self.assertEquals(soup.a.string, "baz") + + def test_attribute_value_with_embedded_brackets(self): + soup = self.soup('<a b="<a>">') + self.assertEquals(soup.a['b'], '<a>') + + def test_nonexistent_entity(self): + soup = self.soup("<p>foo&#bar;baz</p>") + self.assertEquals(soup.p.string, "foobar;baz") + + # Compare a real entity. + soup = self.soup("<p>foodbaz</p>") + self.assertEquals(soup.p.string, "foodbaz") + + # Also compare html5lib, which preserves the &# before the + # entity name. + + def test_entity_was_not_finished(self): + soup = self.soup("<p><Hello>") + # Compare html5lib, which completes the entity. + self.assertEquals(soup.p.string, "<Hello>") + + def test_document_ends_with_incomplete_declaration(self): + soup = self.soup('<p>a<!b') + # This becomes a string 'a'. The incomplete declaration is ignored. + # Compare html5lib, which turns it into a comment. + self.assertEquals(soup.p.contents, ['a']) + + def test_document_starts_with_bogus_declaration(self): + soup = self.soup('<! Foo ><p>a</p>') + # The declaration is ignored altogether. + self.assertEquals(soup.encode(), "<html><body><p>a</p></body></html>") + + def test_tag_name_contains_unicode(self): + # Unicode characters in tag names are stripped. + tag_name = u"<our\N{SNOWMAN}>Joe</our\N{SNOWMAN}>" + self.assertSoupEquals("<our>Joe</our>") class TestLXMLBuilderEncodingConversion(SoupTest): # Test Beautiful Soup's ability to decode and encode from various @@ -391,25 +444,25 @@ class TestLXMLBuilderEncodingConversion(SoupTest): "<html><head></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>") def test_ascii_in_unicode_out(self): - # ASCII input is converted to Unicode. The originalEncoding + # ASCII input is converted to Unicode. The original_encoding # attribute is set. ascii = "<foo>a</foo>" soup_from_ascii = self.soup(ascii) unicode_output = soup_from_ascii.decode() self.assertTrue(isinstance(unicode_output, unicode)) self.assertEquals(unicode_output, self.document_for(ascii)) - self.assertEquals(soup_from_ascii.originalEncoding, "ascii") + self.assertEquals(soup_from_ascii.original_encoding, "ascii") def test_unicode_in_unicode_out(self): - # Unicode input is left alone. The originalEncoding attribute + # Unicode input is left alone. The original_encoding attribute # is not set. soup_from_unicode = self.soup(self.unicode_data) self.assertEquals(soup_from_unicode.decode(), self.unicode_data) self.assertEquals(soup_from_unicode.foo.string, u'Sacr\xe9 bleu!') - self.assertEquals(soup_from_unicode.originalEncoding, None) + self.assertEquals(soup_from_unicode.original_encoding, None) def test_utf8_in_unicode_out(self): - # UTF-8 input is converted to Unicode. The originalEncoding + # UTF-8 input is converted to Unicode. The original_encoding # attribute is set. soup_from_utf8 = self.soup(self.utf8_data) self.assertEquals(soup_from_utf8.decode(), self.unicode_data) @@ -427,7 +480,7 @@ class TestLXMLBuilderEncodingConversion(SoupTest): # Hebrew encoding) to UTF-8. soup = self.soup(self.HEBREW_DOCUMENT, fromEncoding="iso-8859-8") - self.assertEquals(soup.originalEncoding, 'iso-8859-8') + self.assertEquals(soup.original_encoding, 'iso-8859-8') self.assertEquals( soup.encode('utf-8'), self.HEBREW_DOCUMENT.decode("iso-8859-8").encode("utf-8")) |