diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-13 20:00:33 -0500 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-13 20:00:33 -0500 |
| commit | 5aa0e5ba8ec6a590c673db54c60ff2a76544f14f (patch) | |
| tree | bf0637e79bc667a1b5ae08ca4794df414f169992 /beautifulsoup/builder/lxml_builder.py | |
| parent | 87a55b145f0a73e6fc9ede9a762d81d2527161b6 (diff) | |
| parent | bc97bb3a83ee9fb4c8e31d11069ccf1cda61d4ff (diff) | |
Fixed handling of doctypes and added tests for nonsensical declarations.
Diffstat (limited to 'beautifulsoup/builder/lxml_builder.py')
| -rw-r--r-- | beautifulsoup/builder/lxml_builder.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/beautifulsoup/builder/lxml_builder.py b/beautifulsoup/builder/lxml_builder.py index 4e83bba..9ced9f0 100644 --- a/beautifulsoup/builder/lxml_builder.py +++ b/beautifulsoup/builder/lxml_builder.py @@ -6,8 +6,8 @@ class LXMLTreeBuilder(HTMLTreeBuilder): def __init__(self, parser_class=etree.HTMLParser): # etree.HTMLParser's constructor has an argument strip_cdata, - # but it does nothing. CDATA sections will become text when - # passed through etree.HTMLParser. + # but it does nothing. CDATA sections are always stripped when + # passed through HTMLParser. self.parser = parser_class(target=self) self.soup = None @@ -32,8 +32,8 @@ class LXMLTreeBuilder(HTMLTreeBuilder): def doctype(self, name, pubid, system): self.soup.endData() - self.soup.handle_data(name) - self.soup.endData(Doctype) + doctype = Doctype.for_name_and_ids(name, pubid, system) + self.soup.object_was_parsed(doctype) def comment(self, content): "Handle comments as Comment objects." |