From d89c8878ea86a2575c87e9fad8081cfcd81e0bcd Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Thu, 10 Feb 2011 16:41:10 -0500 Subject: Added some elementary doctype handling. --- beautifulsoup/builder/lxml_builder.py | 41 +++++++++++++++++++++++++++++++++++ beautifulsoup/element.py | 5 +++++ tests/test_html5lib.py | 6 +++++ tests/test_lxml.py | 11 ++++++++++ 4 files changed, 63 insertions(+) create mode 100644 beautifulsoup/builder/lxml_builder.py diff --git a/beautifulsoup/builder/lxml_builder.py b/beautifulsoup/builder/lxml_builder.py new file mode 100644 index 0000000..8336ab4 --- /dev/null +++ b/beautifulsoup/builder/lxml_builder.py @@ -0,0 +1,41 @@ +from lxml import etree +from beautifulsoup.element import Comment, Doctype +from beautifulsoup.builder import HTMLTreeBuilder + +class LXMLTreeBuilder(HTMLTreeBuilder): + + def __init__(self, parser_class=etree.HTMLParser): + self.parser = parser_class(target=self) + self.soup = None + + def feed(self, markup): + self.parser.feed(markup) + self.parser.close() + + def close(self): + pass + + def start(self, name, attrs): + self.soup.handle_starttag(name, attrs) + + def end(self, name): + self.soup.handle_endtag(name) + + def data(self, content): + self.soup.handle_data(content) + + def doctype(self, name, pubid, system): + self.soup.endData() + self.soup.handle_data(name) + self.soup.endData(Doctype) + + def comment(self, content): + "Handle comments as Comment objects." + self.soup.endData() + self.soup.handle_data(content) + self.soup.endData(Comment) + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'%s' % fragment + diff --git a/beautifulsoup/element.py b/beautifulsoup/element.py index 7ecd482..b2e0e12 100644 --- a/beautifulsoup/element.py +++ b/beautifulsoup/element.py @@ -370,6 +370,11 @@ class Declaration(NavigableString): def decodeGivenEventualEncoding(self, eventualEncoding): return u'' +class Doctype(NavigableString): + + def decodeGivenEventualEncoding(self, eventualEncoding): + return u'' + class Tag(PageElement, Entities): """Represents a found HTML tag with its attributes and contents.""" diff --git a/tests/test_html5lib.py b/tests/test_html5lib.py index 3e35949..dada900 100644 --- a/tests/test_html5lib.py +++ b/tests/test_html5lib.py @@ -43,6 +43,8 @@ class TestHTML5Builder(TestLXMLBuilder): self.assertSoupEquals("

") self.assertSoupEquals(" ") + def test_cdata(self): + print self.soup("

") class TestHTML5BuilderInvalidMarkup(TestLXMLBuilderInvalidMarkup): """See `BuilderInvalidMarkupSmokeTest`.""" @@ -70,6 +72,10 @@ class TestHTML5BuilderInvalidMarkup(TestLXMLBuilderInvalidMarkup): ('

' '

')) + def test_doctype_in_body(self): + markup = "

onetwo

" + self.assertSoupEquals(markup, "

onetwo

") + def test_foo(self): isolatin = """Sacr\xe9 bleu!""" soup = self.soup(isolatin) diff --git a/tests/test_lxml.py b/tests/test_lxml.py index 2af952f..9a65f6a 100644 --- a/tests/test_lxml.py +++ b/tests/test_lxml.py @@ -198,6 +198,14 @@ class TestLXMLBuilder(SoupTest): # Tests below this line need work. + #def test_doctype(self): + # xml = 'foo

' + # self.assertSoupEquals(xml) + + + #def test_cdata(self): + # print self.soup("

") + def test_entities_converted_on_the_way_out(self): text = "

<<sacré bleu!>>

" expected = u"<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>".encode("utf-8") @@ -261,4 +269,7 @@ class TestLXMLBuilderInvalidMarkup(SoupTest): '

', '

') + def test_doctype_in_body(self): + markup = "

onetwo

" + self.assertSoupEquals(markup) -- cgit v1.2.3