def test_empty_doc(self):
emptydoc1 = fixtures.dumpdocs('empty-doc')['http://aero-comlab.stanford.edu/sichoi/tet_mesh.html']
# should not raise 'ParserError: Document is empty'
self.assertEquals([], emptydoc1.link_uris)
# should not raise "AttributeError: 'NoneType' object has no attribute
# 'text_content'"
self.assertEquals([], emptydoc1.tokens())
def test_writes_file1(self):
out = StringIO.StringIO()
writer = LinkFileOutputStream(out)
docs = fixtures.dumpdocs("small1")
writer.add("http://example.com/", docs["http://example.com/"].link_uris)
writer.add("http://example.com/about", docs["http://example.com/about"].link_uris)
writer.add("http://example.com/contact", docs["http://example.com/contact"].link_uris)
self.assertEquals(small1_links, out.getvalue())
def test_parses_file1(self):
linkfile = LinkFile(small1_links.splitlines(True))
doclinks = dict((doc.uri, list(doc.link_uris)) for doc in linkfile)
exp_doclinks = dict((uri, list(doc.link_uris)) for (uri, doc) in fixtures.dumpdocs("small1").items())
self.assertEquals(exp_doclinks, doclinks)
def test_raw_None(self):
rawNone = fixtures.dumpdocs('raw-None')['http://cse.stanford.edu/class/cs201/projects-00-01/napster/index.html']
self.assertEquals(None, rawNone.html_parser)
