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/builder/_lxml.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/builder/_lxml.py')
| -rw-r--r-- | bs4/builder/_lxml.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 11c9a69..1334f94 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -172,6 +172,12 @@ class LXMLTreeBuilderForXML(TreeBuilder): if isinstance(markup, str): # We were given Unicode. Maybe lxml can parse Unicode on # this system? + + # TODO: This is a workaround for + # https://bugs.launchpad.net/lxml/+bug/1948551. + # We can remove it once the upstream issue is fixed. + if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}': + markup = markup[1:] yield markup, None, document_declared_encoding, False if isinstance(markup, str): |