From 845dbe03bee981bcc5d24ef06ca868042968aa4c Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Fri, 18 Feb 2011 12:21:18 -0500 Subject: Made Unicode, Dammit more PEP-8 compliant. --- tests/test_soup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tests/test_soup.py') diff --git a/tests/test_soup.py b/tests/test_soup.py index 4fb2142..7414403 100644 --- a/tests/test_soup.py +++ b/tests/test_soup.py @@ -27,7 +27,7 @@ class TestUnicodeDammit(unittest.TestCase): def test_smart_quotes_to_html_entities(self): markup = "\x91\x92\x93\x94" - dammit = UnicodeDammit(markup, smartQuotesTo="html") + dammit = UnicodeDammit(markup, smart_quotes_to="html") self.assertEquals( dammit.unicode, "‘’“”") -- cgit v1.2.3 From d35e92875c62cf43227ccc6fca75b5e74a6350e8 Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Fri, 18 Feb 2011 12:23:37 -0500 Subject: Made Unicode, Dammit more PEP-8 compliant. --- tests/test_soup.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'tests/test_soup.py') diff --git a/tests/test_soup.py b/tests/test_soup.py index 7414403..c3a19e1 100644 --- a/tests/test_soup.py +++ b/tests/test_soup.py @@ -35,27 +35,27 @@ 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') -- cgit v1.2.3 From b5fa9d7f5579f22f5fe0f7c9dc63e0aa7d29262f Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Fri, 18 Feb 2011 12:53:33 -0500 Subject: By default, Unicode Dammit converts smart quotes to Unicode characters, not XML entities. --- tests/test_soup.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tests/test_soup.py') diff --git a/tests/test_soup.py b/tests/test_soup.py index c3a19e1..01dff53 100644 --- a/tests/test_soup.py +++ b/tests/test_soup.py @@ -19,9 +19,15 @@ 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 = "\x91\x92\x93\x94" dammit = UnicodeDammit(markup) + self.assertEquals( + dammit.unicode, u"\u2018\u2019\u201c\u201d") + + def test_smart_quotes_to_xml_entities(self): + markup = "\x91\x92\x93\x94" + dammit = UnicodeDammit(markup, smart_quotes_to="xml") self.assertEquals( dammit.unicode, "‘’“”") -- cgit v1.2.3