Ordinary HEAD element test

From 822eabf32dd69346071bd25fc3639db252d2f346 Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Fri, 6 May 2016 09:06:51 +0100 Subject: bitbake: bitbake/bs4: Upgrade 4.3.2 -> 4.4.1 (python 3 version) Upgrade to 4.4.1 which has been run through 2to3 as per the maintainers recommendation for v3 use. (Bitbake rev: 2f4b98af93c971a8c466ffaf3c09cca0edb6e3ad) Signed-off-by: Richard Purdie --- bitbake/lib/bs4/testing.py | 129 +++++++++++++++++++++++++++++++++++++++------ 1 file changed, 112 insertions(+), 17 deletions(-) (limited to 'bitbake/lib/bs4/testing.py') diff --git a/bitbake/lib/bs4/testing.py b/bitbake/lib/bs4/testing.py index fd4495ac58..3a2f260e24 100644 --- a/bitbake/lib/bs4/testing.py +++ b/bitbake/lib/bs4/testing.py @@ -1,5 +1,8 @@ """Helper classes for tests.""" +__license__ = "MIT" + +import pickle import copy import functools import unittest @@ -43,6 +46,16 @@ class SoupTest(unittest.TestCase): self.assertEqual(obj.decode(), self.document_for(compare_parsed_to)) + def assertConnectedness(self, element): + """Ensure that next_element and previous_element are properly + set for all descendants of the given element. + """ + earlier = None + for e in element.descendants: + if earlier: + self.assertEqual(e, earlier.next_element) + self.assertEqual(earlier, e.previous_element) + earlier = e class HTMLTreeBuilderSmokeTest(object): @@ -54,6 +67,15 @@ class HTMLTreeBuilderSmokeTest(object): markup in these tests, there's not much room for interpretation. """ + def test_pickle_and_unpickle_identity(self): + # Pickling a tree, then unpickling it, yields a tree identical + # to the original. + tree = self.soup("foo") + dumped = pickle.dumps(tree, 2) + loaded = pickle.loads(dumped) + self.assertEqual(loaded.__class__, BeautifulSoup) + self.assertEqual(loaded.decode(), tree.decode()) + def assertDoctypeHandled(self, doctype_fragment): """Assert that a given doctype string is handled correctly.""" doctype_str, soup = self._document_with_doctype(doctype_fragment) @@ -114,6 +136,11 @@ class HTMLTreeBuilderSmokeTest(object): soup.encode("utf-8").replace(b"\n", b""), markup.replace(b"\n", b"")) + def test_processing_instruction(self): + markup = b"""""" + soup = self.soup(markup) + self.assertEqual(markup, soup.encode("utf8")) + def test_deepcopy(self): """Make sure you can copy the tree builder. @@ -155,6 +182,23 @@ class HTMLTreeBuilderSmokeTest(object): def test_nested_formatting_elements(self): self.assertSoupEquals("") + def test_double_head(self): + html = ''' + + +Ordinary HEAD element test + + + +Hello, world! + + +''' + soup = self.soup(html) + self.assertEqual("text/javascript", soup.find('script')['type']) + def test_comment(self): # Comments are represented as Comment objects. markup = "
foobaz
" @@ -221,18 +265,26 @@ class HTMLTreeBuilderSmokeTest(object): soup = self.soup(markup) self.assertEqual(["css"], soup.div.div['class']) + def test_multivalued_attribute_on_html(self): + # html5lib uses a different API to set the attributes ot the + # tag. This has caused problems with multivalued + # attributes. + markup = '' + soup = self.soup(markup) + self.assertEqual(["a", "b"], soup.html['class']) + def test_angle_brackets_in_attribute_values_are_escaped(self): self.assertSoupEquals('', '') def test_entities_in_attributes_converted_to_unicode(self): - expect = u'
' + expect = '
' self.assertSoupEquals('
', expect) self.assertSoupEquals('
', expect) self.assertSoupEquals('
', expect) self.assertSoupEquals('
', expect) def test_entities_in_text_converted_to_unicode(self): - expect = u'
pi\N{LATIN SMALL LETTER N WITH TILDE}ata
' + expect = '
pi\N{LATIN SMALL LETTER N WITH TILDE}ata
' self.assertSoupEquals("
piñata
", expect) self.assertSoupEquals("
piñata
", expect) self.assertSoupEquals("
piñata
", expect) @@ -243,7 +295,7 @@ class HTMLTreeBuilderSmokeTest(object): '
I said "good day!"
') def test_out_of_range_entity(self): - expect = u"\N{REPLACEMENT CHARACTER}" + expect = "\N{REPLACEMENT CHARACTER}" self.assertSoupEquals("�", expect) self.assertSoupEquals("�", expect) self.assertSoupEquals("�", expect) @@ -253,6 +305,35 @@ class HTMLTreeBuilderSmokeTest(object): soup = self.soup("
\nfoo
") self.assertEqual("p", soup.h2.string.next_element.name) self.assertEqual("p", soup.p.name) + self.assertConnectedness(soup) + + def test_head_tag_between_head_and_body(self): + "Prevent recurrence of a bug in the html5lib treebuilder." + content = """ + + foo + +""" + soup = self.soup(content) + self.assertNotEqual(None, soup.html.body) + self.assertConnectedness(soup) + + def test_multiple_copies_of_a_tag(self): + "Prevent recurrence of a bug in the html5lib treebuilder." + content = """ + + +
+
+
+ +
+
+ + +""" + soup = self.soup(content) + self.assertConnectedness(soup.article) def test_basic_namespaces(self): """Parsers don't need to *understand* namespaces, but at the @@ -285,9 +366,9 @@ class HTMLTreeBuilderSmokeTest(object): # A seemingly innocuous document... but it's in Unicode! And # it contains characters that can't be represented in the # encoding found in the declaration! The horror! - markup = u'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!' + markup = 'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!' soup = self.soup(markup) - self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string) + self.assertEqual('Sacr\xe9 bleu!', soup.body.string) def test_soupstrainer(self): """Parsers should be able to work with SoupStrainers.""" @@ -327,7 +408,7 @@ class HTMLTreeBuilderSmokeTest(object): # Both XML and HTML entities are converted to Unicode characters # during parsing. text = "
<<sacré bleu!>>
" - expected = u"
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
" + expected = "
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
" self.assertSoupEquals(text, expected) def test_smart_quotes_converted_on_the_way_in(self): @@ -337,15 +418,15 @@ class HTMLTreeBuilderSmokeTest(object): soup = self.soup(quote) self.assertEqual( soup.p.string, - u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}") + "\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}") def test_non_breaking_spaces_converted_on_the_way_in(self): soup = self.soup(" ") - self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2) + self.assertEqual(soup.a.string, "\N{NO-BREAK SPACE}" * 2) 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") + expected = "
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
".encode("utf-8") soup = self.soup(text) self.assertEqual(soup.p.encode("utf-8"), expected) @@ -354,7 +435,7 @@ class HTMLTreeBuilderSmokeTest(object): # easy-to-understand document. # Here it is in Unicode. Note that it claims to be in ISO-Latin-1. - unicode_html = u'
Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!
' + unicode_html = '
Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!
' # That's because we're going to encode it into ISO-Latin-1, and use # that to test. @@ -463,11 +544,25 @@ class HTMLTreeBuilderSmokeTest(object): class XMLTreeBuilderSmokeTest(object): + def test_pickle_and_unpickle_identity(self): + # Pickling a tree, then unpickling it, yields a tree identical + # to the original. + tree = self.soup("foo") + dumped = pickle.dumps(tree, 2) + loaded = pickle.loads(dumped) + self.assertEqual(loaded.__class__, BeautifulSoup) + self.assertEqual(loaded.decode(), tree.decode()) + def test_docstring_generated(self): soup = self.soup("") self.assertEqual( soup.encode(), b'\n') + def test_xml_declaration(self): + markup = b"""\n""" + soup = self.soup(markup) + self.assertEqual(markup, soup.encode("utf8")) + def test_real_xhtml_document(self): """A real XHTML document should come out *exactly* the same as it went in.""" markup = b""" @@ -485,7 +580,7 @@ class XMLTreeBuilderSmokeTest(object): """ - soup = BeautifulSoup(doc, "xml") + soup = BeautifulSoup(doc, "lxml-xml") # lxml would have stripped this while parsing, but we can add # it later. soup.script.string = 'console.log("< < hey > > ");' @@ -493,15 +588,15 @@ class XMLTreeBuilderSmokeTest(object): self.assertTrue(b"< < hey > >" in encoded) def test_can_parse_unicode_document(self): - markup = u'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!' + markup = 'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!' soup = self.soup(markup) - self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string) + self.assertEqual('Sacr\xe9 bleu!', soup.root.string) def test_popping_namespaced_tag(self): markup = 'b2012-07-02T20:33:42Zcd' soup = self.soup(markup) self.assertEqual( - unicode(soup.rss), markup) + str(soup.rss), markup) def test_docstring_includes_correct_encoding(self): soup = self.soup("") @@ -532,17 +627,17 @@ class XMLTreeBuilderSmokeTest(object): def test_closing_namespaced_tag(self): markup = '
20010504
' soup = self.soup(markup) - self.assertEqual(unicode(soup.p), markup) + self.assertEqual(str(soup.p), markup) def test_namespaced_attributes(self): markup = '' soup = self.soup(markup) - self.assertEqual(unicode(soup.foo), markup) + self.assertEqual(str(soup.foo), markup) def test_namespaced_attributes_xml_namespace(self): markup = 'bar' soup = self.soup(markup) - self.assertEqual(unicode(soup.foo), markup) + self.assertEqual(str(soup.foo), markup) class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest): """Smoke test for a tree builder that supports HTML5.""" -- cgit v1.2.3-54-g00ecf