diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-18 11:29:43 -0500 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-18 11:29:43 -0500 |
| commit | 75c5891980c961dfe36745c1934010560666f938 (patch) | |
| tree | fa62ea107db97916fa538883ae561fba64ea13d9 /tests/test_html5lib.py | |
| parent | ddf9d04e42168fdb25b742b35efc891789a4b6c9 (diff) | |
Pass the user-specified encoding in to html5lib rather than dropping it on the floor.
Diffstat (limited to 'tests/test_html5lib.py')
| -rw-r--r-- | tests/test_html5lib.py | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/tests/test_html5lib.py b/tests/test_html5lib.py index 1034720..59d84a3 100644 --- a/tests/test_html5lib.py +++ b/tests/test_html5lib.py @@ -146,4 +146,12 @@ class TestHTML5LibEncodingConversion(TestLXMLBuilderEncodingConversion): def default_builder(self): return HTML5TreeBuilder() - pass + def test_real_hebrew_document(self): + # A real-world test to make sure we can convert ISO-8859-9 (a + # Hebrew encoding) to UTF-8. + soup = self.soup(self.HEBREW_DOCUMENT, + fromEncoding="iso-8859-8") + self.assertEquals(soup.originalEncoding, 'iso8859-8') + self.assertEquals( + soup.encode('utf-8'), + self.HEBREW_DOCUMENT.decode("iso-8859-8").encode("utf-8")) |