def buildTestSuite():
sys.stdout.write('Testing tree walkers ' +
" ".join(list(treeTypes.keys())) + "\n")
for treeName, treeCls in treeTypes.items():
files = html5lib_test_files('tree-construction')
files = [
f for f in files
if not f.split(".")[-2][-2:] in ("s9", "10", "11", "12")
] #skip namespace tests for now
for filename in files:
testName = os.path.basename(filename).replace(".dat", "")
if testName == "tests5": continue # TODO
tests = TestData(filename, "data")
for index, test in enumerate(tests):
(input, errors, innerHTML, expected) = [
test[key] for key in ("data", "errors",
"document-fragment", "document")
]
def testFunc(self,
innerHTML=innerHTML,
input=input,
expected=expected,
errors=errors,
treeCls=treeCls):
self.runTest(innerHTML, input, expected, errors, treeCls)
setattr(TestCase,
"test_%s_%d_%s" % (testName, index + 1, treeName),
testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
sys.stdout.write('Testing tree builders '+ " ".join(treeTypes.keys()) + "\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files('tree-construction')
files = [f for f in files if
not f.split(".")[-2][-2:] in ("s9", "10", "11", "12")] #skip namespace tests for now
for filename in files:
testName = os.path.basename(filename).replace(".dat","")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
input, errors, innerHTML, expected = [test[key] for key in
'data', 'errors',
'document-fragment',
'document']
if errors:
errors = errors.split("\n")
def testFunc(self, innerHTML=innerHTML, input=input,
expected=expected, errors=errors, treeCls=treeCls):
return self.runParserTest(innerHTML, input, expected, errors, treeCls)
setattr(TestCase, "test_%s_%d_%s" % (testName,index+1,treeName),
testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files("encoding"):
test_name = os.path.basename(filename).replace('.dat',''). \
replace('-','')
tests = TestData(filename, "data")
for idx, test in enumerate(tests):
def encodingTest(self, data=test['data'],
encoding=test['encoding']):
p = HTMLParser()
t = p.parse(data, useChardet=False)
errorMessage = ("Input:\n%s\nExpected:\n%s\nRecieved\n%s\n"%
(data, repr(encoding.lower()),
repr(p.tokenizer.stream.charEncoding)))
self.assertEquals(encoding.lower(),
p.tokenizer.stream.charEncoding[0],
errorMessage)
setattr(Html5EncodingTestCase, 'test_%s_%d' % (test_name, idx+1),
encodingTest)
try:
import chardet
def test_chardet(self):
data = open(os.path.join(test_dir, "encoding" , "chardet", "test_big5.txt")).read()
encoding = inputstream.HTMLInputStream(data).charEncoding
assert encoding[0].lower() == "big5"
setattr(Html5EncodingTestCase, 'test_chardet', test_chardet)
except ImportError:
print "chardet not found, skipping chardet tests"
return unittest.defaultTestLoader.loadTestsFromName(__name__)
def main(out_path):
if not os.path.exists(out_path):
sys.stderr.write("Path %s does not exist" % out_path)
sys.exit(1)
for filename in support.html5lib_test_files('tokenizer', '*.test'):
run_file(filename, out_path)
def buildTestSuite():
for filename in html5lib_test_files('tokenizer', '*.test'):
tests = simplejson.load(file(filename))
testName = os.path.basename(filename).replace(".test", "")
if 'tests' in tests:
for index, test in enumerate(tests['tests']):
#Skip tests with a self closing flag
skip = False
for token in test["output"]:
if token[0] == "StartTag" and len(token) == 4:
skip = True
break
if skip:
continue
if 'contentModelFlags' not in test:
test["contentModelFlags"] = ["PCDATA"]
for contentModelFlag in test["contentModelFlags"]:
test["contentModelFlag"] = contentModelFlag
def testFunc(self, test=test):
self.runTokenizerTest(test)
testFunc.__doc__ = "\t".join(
[testName, test['description']])
setattr(TestCase, 'test_%s_%d' % (testName, index),
testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def main(out_path):
if not os.path.exists(out_path):
sys.stderr.write("Path %s does not exist"%out_path)
sys.exit(1)
for filename in support.html5lib_test_files('tokenizer', '*.test'):
run_file(filename, out_path)
def buildTestSuite():
sys.stdout.write('Testing tree builders '+ " ".join(treeTypes.keys()) + "\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files('tree-construction')
for filename in files:
testName = os.path.basename(filename).replace(".dat","")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
input, errors, innerHTML, expected = [test[key] for key in
'data', 'errors',
'document-fragment',
'document']
if errors:
errors = errors.split("\n")
for namespaceHTMLElements in (True, False):
def testFunc(self, innerHTML=innerHTML, input=input,
expected=expected, errors=errors, treeCls=treeCls,
namespaceHTMLElements=namespaceHTMLElements):
return self.runParserTest(innerHTML, input, expected,
errors, treeCls,
namespaceHTMLElements)
testFunc.__name__ = "test_%s_%d_%s_%s" % (testName,index+1,treeName, namespaceHTMLElements and "namespaced" or "no_html_namespace")
setattr(TestCase, testFunc.__name__,
testFunc)
break
break
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
sys.stdout.write('Testing tree builders '+ " ".join(treeTypes.keys()) + "\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files('tree-construction')
for filename in files:
testName = os.path.basename(filename).replace(".dat","")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
input, errors, innerHTML, expected = [test[key] for key in
'data', 'errors',
'document-fragment',
'document']
if errors:
errors = errors.split("\n")
for namespaceHTMLElements in (True, False):
def testFunc(self, innerHTML=innerHTML, input=input,
expected=expected, errors=errors, treeCls=treeCls,
namespaceHTMLElements=namespaceHTMLElements):
return self.runParserTest(innerHTML, input, expected,
errors, treeCls,
namespaceHTMLElements)
testFunc.__name__ = "test_%s_%d_%s_%s" % (testName,index+1,treeName, namespaceHTMLElements and "namespaced" or "no_html_namespace")
setattr(TestCase, testFunc.__name__,
testFunc)
break
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files("sanitizer"):
for test in json.load(file(filename)):
SanitizeTest.addTest('test_' + test['name'], test['output'],
test['input'])
return unittest.TestLoader().loadTestsFromTestCase(SanitizeTest)
def buildTestSuite():
for filename in html5lib_test_files("sanitizer"):
for test in simplejson.load(file(filename)):
SanitizeTest.addTest("test_" + test["name"], test["output"], test["input"])
for test in simplejson.load(file(filename)):
SanitizeTest.addTest("test_strip_" + test["name"], test["stripped"], test["input"], strip=True)
return unittest.TestLoader().loadTestsFromTestCase(SanitizeTest)
def test_serializer():
for filename in html5lib_test_files('serializer', '*.test'):
tests = json.load(file(filename))
test_name = os.path.basename(filename).replace('.test','')
for index, test in enumerate(tests['tests']):
xhtml = test.get("xhtml", test["expected"])
if test_name == 'optionaltags':
xhtml = None
yield make_test, test["input"], test["expected"], xhtml, test.get("options", {})
def buildTestSuite():
for filename in html5lib_test_files('validator', '*.test'):
tests = simplejson.load(file(filename))
testName = os.path.basename(filename).replace(".test","")
for index,test in enumerate(tests['tests']):
def testFunc(self, test=test):
self.runValidatorTest(test)
testFunc.__doc__ = "\t".join([testName, test['description']])
setattr(TestCase, 'test_%s_%d' % (testName, index), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files('serializer', '*.test'):
test_name = os.path.basename(filename).replace('.test','')
tests = simplejson.load(file(filename))
for index, test in enumerate(tests['tests']):
xhtml = test.get("xhtml", test["expected"])
if test_name == 'optionaltags': xhtml = None
TestCase.addTest('test_%s_%d' % (test_name, index+1),
test["description"], test["input"], test["expected"], xhtml,
test.get("options", {}))
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files('serializer', '*.test'):
test_name = os.path.basename(filename).replace('.test', '')
tests = simplejson.load(file(filename))
for index, test in enumerate(tests['tests']):
xhtml = test.get("xhtml", test["expected"])
if test_name == 'optionaltags': xhtml = None
TestCase.addTest('test_%s_%d' % (test_name, index + 1),
test["description"], test["input"],
test["expected"], xhtml, test.get("options", {}))
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files('validator', '*.test'):
tests = simplejson.load(file(filename))
testName = os.path.basename(filename).replace(".test", "")
for index, test in enumerate(tests['tests']):
def testFunc(self, test=test):
self.runValidatorTest(test)
testFunc.__doc__ = "\t".join([testName, test['description']])
setattr(TestCase, 'test_%s_%d' % (testName, index), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def test_tokenizer():
for filename in html5lib_test_files("tokenizer", "*.test"):
tests = json.load(file(filename))
testName = os.path.basename(filename).replace(".test", "")
if "tests" in tests:
for index, test in enumerate(tests["tests"]):
# Skip tests with a self closing flag
skip = False
if "initialStates" not in test:
test["initialStates"] = ["Data state"]
for initialState in test["initialStates"]:
test["initialState"] = capitalize(initialState)
yield runTokenizerTest, test
def test_treewalker():
sys.stdout.write('Testing tree walkers '+ " ".join(treeTypes.keys()) + "\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files('tree-construction')
for filename in files:
testName = os.path.basename(filename).replace(".dat","")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
(input, errors,
innerHTML, expected) = [test[key] for key in ("data", "errors",
"document-fragment",
"document")]
errors = errors.split("\n")
yield run_test, innerHTML, input, expected, errors, treeCls
def test_treewalker():
sys.stdout.write('Testing tree walkers ' + " ".join(treeTypes.keys()) +
"\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files('tree-construction')
for filename in files:
testName = os.path.basename(filename).replace(".dat", "")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
(input, errors, innerHTML, expected) = [
test[key] for key in ("data", "errors",
"document-fragment", "document")
]
errors = errors.split("\n")
yield run_test, innerHTML, input, expected, errors, treeCls
def buildTestSuite():
for filename in html5lib_test_files('tokenizer', '*.test'):
tests = json.load(file(filename))
testName = os.path.basename(filename).replace(".test","")
if 'tests' in tests:
for index,test in enumerate(tests['tests']):
#Skip tests with a self closing flag
skip = False
if 'initialStates' not in test:
test["initialStates"] = ["Data state"]
for initialState in test["initialStates"]:
test["initialState"] = capitalize(initialState)
def testFunc(self, test=test):
self.runTokenizerTest(test)
testFunc.__doc__ = "\t".join([testName,
test['description']])
setattr(TestCase, 'test_%s_%d_%s' % (testName, index, test["initialState"]), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files('tokenizer', '*.test'):
tests = simplejson.load(open(filename))
testName = os.path.basename(filename).replace(".test","")
if 'tests' in tests:
for index,test in enumerate(tests['tests']):
#Skip tests with a self closing flag
skip = False
if 'contentModelFlags' not in test:
test["contentModelFlags"] = ["PCDATA"]
for contentModelFlag in test["contentModelFlags"]:
test["contentModelFlag"] = contentModelFlag
def testFunc(self, test=test):
self.runTokenizerTest(test)
testFunc.__doc__ = "\t".join([testName,
test['description']])
setattr(TestCase, 'test_%s_%d' % (testName, index), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
sys.stdout.write("Testing tree walkers " + " ".join(treeTypes.keys()) + "\n")
for treeName, treeCls in treeTypes.iteritems():
files = html5lib_test_files("tree-construction")
for filename in files:
testName = os.path.basename(filename).replace(".dat", "")
tests = TestData(filename, "data")
for index, test in enumerate(tests):
(input, errors, innerHTML, expected) = [
test[key] for key in ("data", "errors", "document-fragment", "document")
]
errors = errors.split("\n")
def testFunc(self, innerHTML=innerHTML, input=input, expected=expected, errors=errors, treeCls=treeCls):
self.runTest(innerHTML, input, expected, errors, treeCls)
setattr(TestCase, "test_%s_%d_%s" % (testName, index + 1, treeName), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files('tokenizer', '*.test'):
tests = json.load(file(filename))
testName = os.path.basename(filename).replace(".test", "")
if 'tests' in tests:
for index, test in enumerate(tests['tests']):
#Skip tests with a self closing flag
skip = False
if 'initialStates' not in test:
test["initialStates"] = ["Data state"]
for initialState in test["initialStates"]:
test["initialState"] = capitalize(initialState)
def testFunc(self, test=test):
self.runTokenizerTest(test)
testFunc.__doc__ = "\t".join(
[testName, test['description']])
setattr(
TestCase, 'test_%s_%d_%s' %
(testName, index, test["initialState"]), testFunc)
return unittest.TestLoader().loadTestsFromTestCase(TestCase)
def buildTestSuite():
for filename in html5lib_test_files("encoding"):
test_name = os.path.basename(filename).replace('.dat',''). \
replace('-','')
tests = TestData(filename, "data")
for idx, test in enumerate(tests):
def encodingTest(self,
data=test['data'],
encoding=test['encoding']):
p = HTMLParser()
t = p.parse(data, useChardet=False)
errorMessage = ("Input:\n%s\nExpected:\n%s\nRecieved\n%s\n" %
(data, repr(encoding.lower()),
repr(p.tokenizer.stream.charEncoding)))
self.assertEquals(encoding.lower(),
p.tokenizer.stream.charEncoding[0],
errorMessage)
setattr(Html5EncodingTestCase, 'test_%s_%d' % (test_name, idx + 1),
encodingTest)
try:
import chardet
def test_chardet(self):
data = open(
os.path.join(test_dir, "encoding", "chardet",
"test_big5.txt")).read()
encoding = inputstream.HTMLInputStream(data).charEncoding
assert encoding[0].lower() == "big5"
setattr(Html5EncodingTestCase, 'test_chardet', test_chardet)
except ImportError:
print "chardet not found, skipping chardet tests"
return unittest.defaultTestLoader.loadTestsFromName(__name__)
def buildTestSuite():
for filename in html5lib_test_files("sanitizer"):
for test in json.load(file(filename)):
SanitizeTest.addTest('test_' + test['name'], test['output'], test['input'])
return unittest.TestLoader().loadTestsFromTestCase(SanitizeTest)