def injection_check(filename: str):
"""Checks whether given code file does not contain harmful code to server
operation.
Args:
filename (str): the code file to check
Raises:
ARgorithmError: Raised if possible harmful code injection
"""
count = 0
with open(filename, 'r') as f:
lines = f.readlines()
for line in lines:
if "import ARgorithmToolkit" in line or "from ARgorithmToolkit" in line:
count += 1
if count == 0:
raise ARgorithmError("ARgorithmToolkit not imported")
for line in lines:
if line.startswith("from"):
if not re.search(r"^from\s+ARgorithmToolkit", line):
raise ARgorithmError("invalid module imported")
for line in lines:
if line.startswith("import"):
if not re.search(r"^import\s+ARgorithmToolkit", line):
raise ARgorithmError("invalid module imported")
text = '\n'.join(lines)
file_tokens = checker.make_tokens(text)
tokens = [token[1] for token in file_tokens if token[0] == 1]
not_allowed = list(set(tokens) & set(FORBIDDEN))
if len(not_allowed) > 0:
raise ARgorithmError('possible code injection')
def flakes(self, input, *expectedOutputs, **kw):
tree = ast.parse(textwrap.dedent(input))
file_tokens = checker.make_tokens(textwrap.dedent(input))
if kw.get("is_segment"):
tree = tree.body[0]
kw.pop("is_segment")
w = checker.Checker(
tree, file_tokens=file_tokens, withDoctest=self.withDoctest, **kw
)
outputs = [type(o) for o in w.messages]
expectedOutputs = list(expectedOutputs)
outputs.sort(key=lambda t: t.__name__)
expectedOutputs.sort(key=lambda t: t.__name__)
self.assertEqual(
outputs,
expectedOutputs,
"""\
for input:
%s
expected outputs:
%r
but got:
%s"""
% (input, expectedOutputs, "\n".join([str(o) for o in w.messages])),
)
return w
def check(codeString, filename, reporter=None):
"""
Check the Python source given by C{codeString} for flakes.
@param codeString: The Python source to check.
@type codeString: C{str}
@param filename: The name of the file the source came from, used to report
errors.
@type filename: C{str}
@param reporter: A L{Reporter} instance, where errors and warnings will be
reported.
@return: The number of warnings emitted.
@rtype: C{int}
"""
if reporter is None:
reporter = modReporter._makeDefaultReporter()
# First, compile into an AST and handle syntax errors.
try:
tree = ast.parse(codeString, filename=filename)
except SyntaxError:
value = sys.exc_info()[1]
msg = value.args[0]
(lineno, offset, text) = value.lineno, value.offset, value.text
if checker.PYPY:
if text is None:
lines = codeString.splitlines()
if len(lines) >= lineno:
text = lines[lineno - 1]
if sys.version_info >= (3, ) and isinstance(text, bytes):
try:
text = text.decode('ascii')
except UnicodeDecodeError:
text = None
offset -= 1
# If there's an encoding problem with the file, the text is None.
if text is None:
# Avoid using msg, since for the only known case, it contains a
# bogus message that claims the encoding the file declared was
# unknown.
reporter.unexpectedError(filename, 'problem decoding source')
else:
reporter.syntaxError(filename, msg, lineno, offset, text)
return 1
except Exception:
reporter.unexpectedError(filename, 'problem decoding source')
return 1
# Okay, it's syntactically valid. Now check it.
file_tokens = checker.make_tokens(codeString)
w = checker.Checker(tree, file_tokens=file_tokens, filename=filename)
w.messages.sort(key=lambda m: m.lineno)
for warning in w.messages:
reporter.flake(warning)
return len(w.messages)
def check(codeString, filename, reporter=None):
"""
Check the Python source given by C{codeString} for flakes.
@param codeString: The Python source to check.
@type codeString: C{str}
@param filename: The name of the file the source came from, used to report
errors.
@type filename: C{str}
@param reporter: A L{Reporter} instance, where errors and warnings will be
reported.
@return: The number of warnings emitted.
@rtype: C{int}
"""
if reporter is None:
reporter = modReporter._makeDefaultReporter()
# First, compile into an AST and handle syntax errors.
try:
tree = ast.parse(codeString, filename=filename)
except SyntaxError:
value = sys.exc_info()[1]
msg = value.args[0]
(lineno, offset, text) = value.lineno, value.offset, value.text
if checker.PYPY:
if text is None:
lines = codeString.splitlines()
if len(lines) >= lineno:
text = lines[lineno - 1]
if sys.version_info >= (3, ) and isinstance(text, bytes):
try:
text = text.decode('ascii')
except UnicodeDecodeError:
text = None
offset -= 1
# If there's an encoding problem with the file, the text is None.
if text is None:
# Avoid using msg, since for the only known case, it contains a
# bogus message that claims the encoding the file declared was
# unknown.
reporter.unexpectedError(filename, 'problem decoding source')
else:
reporter.syntaxError(filename, msg, lineno, offset, text)
return 1
except Exception:
reporter.unexpectedError(filename, 'problem decoding source')
return 1
# Okay, it's syntactically valid. Now check it.
file_tokens = checker.make_tokens(codeString)
w = checker.Checker(tree, file_tokens=file_tokens, filename=filename)
w.messages.sort(key=lambda m: m.lineno)
for warning in w.messages:
reporter.flake(warning)
return len(w.messages)
def _collect(s):
"""
Run L{_collect_type_comments} on the parsed source and return the
mapping from nodes to comments. The return value is converted to
a set: {(node_type, tuple of comments), ...}
"""
tree = ast.parse(s)
tokens = checker.make_tokens(s)
ret = checker._collect_type_comments(tree, tokens)
return {(type(k), tuple(s for _, s in v)) for k, v in ret.items()}
def _collect(s):
"""
Run L{_collect_type_comments} on the parsed source and return the
mapping from nodes to comments. The return value is converted to
a set: {(node_type, tuple of comments), ...}
"""
tree = ast.parse(s)
tokens = checker.make_tokens(s)
ret = checker._collect_type_comments(tree, tokens)
return {(type(k), tuple(s for _, s in v)) for k, v in ret.items()}
def test_impossibleContext(self):
"""
A Name node with an unrecognized context results in a RuntimeError being
raised.
"""
tree = ast.parse("x = 10")
file_tokens = checker.make_tokens("x = 10")
# Make it into something unrecognizable.
tree.body[0].targets[0].ctx = object()
self.assertRaises(RuntimeError, checker.Checker, tree, file_tokens=file_tokens)
def test_impossibleContext(self):
"""
A Name node with an unrecognized context results in a RuntimeError being
raised.
"""
tree = ast.parse("x = 10")
tokens = checker.make_tokens("x = 10")
# Make it into something unrecognizable.
tree.body[0].targets[0].ctx = object()
self.assertRaises(RuntimeError, checker.Checker, tree, tokens=tokens)
def flakes(self, input, *expectedOutputs, **kw):
tree = ast.parse(textwrap.dedent(input))
file_tokens = checker.make_tokens(textwrap.dedent(input))
if kw.get('is_segment'):
tree = tree.body[0]
kw.pop('is_segment')
w = checker.Checker(
tree, file_tokens=file_tokens, withDoctest=self.withDoctest, **kw
)
outputs = [type(o) for o in w.messages]
expectedOutputs = list(expectedOutputs)
outputs.sort(key=lambda t: t.__name__)
expectedOutputs.sort(key=lambda t: t.__name__)
self.assertEqual(outputs, expectedOutputs, '''\
for input:
%s
expected outputs:
%r
but got:
%s''' % (input, expectedOutputs, '\n'.join([str(o) for o in w.messages])))
return w
def to_output(self):
"""
Produce json output
:return: json result report
"""
results = []
cli = {'cli': results}
warning_dict = {}
try:
tree = ast.parse(self.codeString, filename=self.filename)
file_tokens = checker.make_tokens(self.codeString)
w = checker.Checker(tree,
file_tokens=file_tokens,
filename=self.filename)
w.messages.sort(key=lambda m: m.lineno)
for warning in w.messages:
warning_dict['message'] = str(warning).split(' ', 1)[1]
warning = str(warning).split(' ', 1)[0]
loc = str(warning).split(':')
warning_dict['file'] = loc[0] if loc[0] else None
warning_dict['line'] = loc[1] if loc[1] else None
warning_dict['column'] = loc[2] if loc[2] else None
results.append(warning_dict.copy())
except SyntaxError:
value = sys.exc_info()[1]
msg = value.args[0]
warning_dict['message'] = msg
warning_dict['file'] = self.filename
warning_dict['line'] = value.lineno if value.lineno else None
warning_dict['column'] = value.offset if value.offset else None
results.append(warning_dict.copy())
flakes_json = {'results': cli}
flakes_json = json.dumps(flakes_json,
sort_keys=True,
indent=2,
separators=(',', ': '))
return flakes_json + '\n'
