def runTreewalkerTest(innerHTML, input, expected, errors, treeClass):
warnings.resetwarnings()
warnings.simplefilter("error")
try:
p = html5parser.HTMLParser(tree=treeClass["builder"])
if innerHTML:
document = p.parseFragment(input, innerHTML)
else:
document = p.parse(input)
except constants.DataLossWarning:
# Ignore testcases we know we don't pass
return
document = treeClass.get("adapter", lambda x: x)(document)
try:
output = treewalkers.pprint(treeClass["walker"](document))
output = attrlist.sub(sortattrs, output)
expected = attrlist.sub(sortattrs, convertExpected(expected))
diff = "".join(unified_diff([line + "\n" for line in expected.splitlines()],
[line + "\n" for line in output.splitlines()],
"Expected", "Received"))
assert expected == output, "\n".join([
"", "Input:", input,
"", "Expected:", expected,
"", "Received:", output,
"", "Diff:", diff,
])
except NotImplementedError:
pass # Amnesty for those that confess...
def runTreewalkerTest(innerHTML, input, expected, errors, treeClass):
warnings.resetwarnings()
warnings.simplefilter("error")
try:
p = html5parser.HTMLParser(tree=treeClass["builder"])
if innerHTML:
document = p.parseFragment(input, innerHTML)
else:
document = p.parse(input)
except constants.DataLossWarning:
# Ignore testcases we know we don't pass
return
document = treeClass.get("adapter", lambda x: x)(document)
try:
output = treewalkers.pprint(Lint(treeClass["walker"](document)))
output = attrlist.sub(sortattrs, output)
expected = attrlist.sub(sortattrs, convertExpected(expected))
diff = "".join(unified_diff([line + "\n" for line in expected.splitlines()],
[line + "\n" for line in output.splitlines()],
"Expected", "Received"))
assert expected == output, "\n".join([
"", "Input:", input,
"", "Expected:", expected,
"", "Received:", output,
"", "Diff:", diff,
])
except NotImplementedError:
pass # Amnesty for those that confess...
def runtest(self):
if self.treeAPIs is None:
pytest.skip("Treebuilder not loaded")
p = html5parser.HTMLParser(tree=self.treeAPIs["builder"])
input = self.test['data']
fragmentContainer = self.test['document-fragment']
expected = convertExpected(self.test['document'])
scripting = False
if 'script-on' in self.test:
scripting = True
with warnings.catch_warnings():
warnings.simplefilter("error")
try:
if fragmentContainer:
document = p.parseFragment(input,
fragmentContainer,
scripting=scripting)
else:
document = p.parse(input, scripting=scripting)
except constants.DataLossWarning:
pytest.skip("data loss warning")
poutput = convertTreeDump(p.tree.testSerializer(document))
namespace_expected = namespaceExpected(r"\1<html \2>", expected)
if poutput != namespace_expected:
pytest.skip("parser output incorrect")
document = self.treeAPIs.get("adapter", lambda x: x)(document)
try:
output = treewalkers.pprint(Lint(
self.treeAPIs["walker"](document)))
output = sortattrs(output)
expected = sortattrs(expected)
diff = "".join(
unified_diff([line + "\n" for line in expected.splitlines()],
[line + "\n" for line in output.splitlines()],
"Expected", "Received"))
assert expected == output, "\n".join([
"",
"Input:",
input,
"",
"Expected:",
expected,
"",
"Received:",
output,
"",
"Diff:",
diff,
])
except NotImplementedError:
pytest.skip("tree walker NotImplementedError")
def runTreewalkerEditTest(intext, expected, attrs_to_add, tree):
"""tests what happens when we add attributes to the intext"""
treeName, treeClass = tree
parser = html5parser.HTMLParser(tree=treeClass["builder"])
document = parser.parseFragment(intext)
for nom, val in attrs_to_add:
set_attribute_on_first_child(document, nom, val, treeName)
document = treeClass.get("adapter", lambda x: x)(document)
output = treewalkers.pprint(treeClass["walker"](document))
output = attrlist.sub(sortattrs, output)
if not output in expected:
raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
def runTreewalkerEditTest(intext, expected, attrs_to_add, tree):
"""tests what happens when we add attributes to the intext"""
treeName, treeClass = tree
parser = html5parser.HTMLParser(tree=treeClass["builder"])
document = parser.parseFragment(intext)
for nom, val in attrs_to_add:
set_attribute_on_first_child(document, nom, val, treeName)
document = treeClass.get("adapter", lambda x: x)(document)
output = treewalkers.pprint(treeClass["walker"](document))
output = attrlist.sub(sortattrs, output)
if not output in expected:
raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
def runtest(self):
p = html5parser.HTMLParser(tree=self.treeAPIs["builder"])
input = self.test['data']
fragmentContainer = self.test['document-fragment']
expected = convertExpected(self.test['document'])
scripting = False
if 'script-on' in self.test:
scripting = True
with warnings.catch_warnings():
warnings.simplefilter("error")
try:
if fragmentContainer:
document = p.parseFragment(input, fragmentContainer, scripting=scripting)
else:
document = p.parse(input, scripting=scripting)
except constants.DataLossWarning:
pytest.skip("data loss warning")
poutput = convertTreeDump(p.tree.testSerializer(document))
namespace_expected = namespaceExpected(r"\1<html \2>", expected)
if poutput != namespace_expected:
pytest.skip("parser output incorrect")
document = self.treeAPIs.get("adapter", lambda x: x)(document)
try:
output = treewalkers.pprint(Lint(self.treeAPIs["walker"](document)))
output = sortattrs(output)
expected = sortattrs(expected)
diff = "".join(unified_diff([line + "\n" for line in expected.splitlines()],
[line + "\n" for line in output.splitlines()],
"Expected", "Received"))
assert expected == output, "\n".join([
"", "Input:", input,
"", "Expected:", expected,
"", "Received:", output,
"", "Diff:", diff,
])
except NotImplementedError:
pytest.skip("tree walker NotImplementedError")
def runTreewalkerTest(innerHTML, input, expected, errors, treeClass):
warnings.resetwarnings()
warnings.simplefilter('error')
try:
p = html5parser.HTMLParser(tree=treeClass['builder'])
if innerHTML:
document = p.parseFragment(input, innerHTML)
else:
document = p.parse(input)
except constants.DataLossWarning:
# Ignore testcases we know we don't pass
return
document = treeClass.get('adapter', lambda x: x)(document)
try:
output = treewalkers.pprint(treeClass['walker'](document))
output = attrlist.sub(sortattrs, output)
expected = attrlist.sub(sortattrs, convertExpected(expected))
diff = ''.join(
unified_diff([line + '\n' for line in expected.splitlines()],
[line + '\n' for line in output.splitlines()],
'Expected', 'Received'))
assert expected == output, '\n'.join([
'',
'Input:',
input,
'',
'Expected:',
expected,
'',
'Received:',
output,
'',
'Diff:',
diff,
])
except NotImplementedError:
pass # Amnesty for those that confess...
