diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2021-10-23 17:13:58 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2021-10-23 17:13:58 -0400 |
| commit | 1b7c99d3dfc65e8b0448f06f084097947d3ce1a2 (patch) | |
| tree | 37e907220d500b38793be279ea1d2e454e8ca98a /bs4/tests/__init__.py | |
| parent | 0afd48f8b3069fb3577749374e20611b231cb829 (diff) | |
Added a workaround for an lxml bug (https://bugs.launchpad.net/lxml/+bug/1948551) that caused
problems when parsing a Unicode string beginning with BYTE ORDER MARK.
[bug=1947768]
Diffstat (limited to 'bs4/tests/__init__.py')
| -rw-r--r-- | bs4/tests/__init__.py | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/bs4/tests/__init__.py b/bs4/tests/__init__.py index 6677d2e..5147f0e 100644 --- a/bs4/tests/__init__.py +++ b/bs4/tests/__init__.py @@ -1024,6 +1024,11 @@ class XMLTreeBuilderSmokeTest(TreeBuilderSmokeTest): soup = self.soup(markup) assert 'Sacr\xe9 bleu!' == soup.root.string + def test_can_parse_unicode_document_begining_with_bom(self): + markup = '\N{BYTE ORDER MARK}<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>' + soup = self.soup(markup) + assert 'Sacr\xe9 bleu!' == soup.root.string + def test_popping_namespaced_tag(self): markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>' soup = self.soup(markup) |