def _(source, source_file):
source_string = python_bytes_to_unicode(source)
for token in tokenize(
source_string,
version_info=parse_version_string('3.10')
):
pass
def test_python_bytes_to_unicode_unicode_text():
source = (
b"# vim: fileencoding=utf-8\n"
b"# \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a\n")
actual = python_bytes_to_unicode(source)
expected = source.decode('utf-8')
assert actual == expected
def test_python_bytes_to_unicode_unicode_text():
source = (
b"# vim: fileencoding=utf-8\n"
b"# \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a\n"
)
actual = python_bytes_to_unicode(source)
expected = source.decode('utf-8')
assert actual == expected
def test_normalizer_issue(normalizer_issue_case):
def sort(issues):
issues = sorted(issues, key=lambda i: (i.start_pos, i.code))
return ["(%s, %s): %s" % (i.start_pos[0], i.start_pos[1], i.code)
for i in issues]
with open(normalizer_issue_case.path, 'rb') as f:
code = python_bytes_to_unicode(f.read())
desired = sort(collect_errors(code))
grammar = parso.load_grammar(version=normalizer_issue_case.python_version)
module = grammar.parse(code)
issues = grammar._get_normalizer_issues(module)
actual = sort(issues)
diff = '\n'.join(difflib.ndiff(desired, actual))
# To make the pytest -v diff a bit prettier, stop pytest to rewrite assert
# statements by executing the comparison earlier.
_bool = desired == actual
assert _bool, '\n' + diff
def _parse(self,
code=None,
error_recovery=True,
path=None,
start_symbol=None,
cache=False,
diff_cache=False,
cache_path=None,
start_pos=(1, 0)):
"""
Wanted python3.5 * operator and keyword only arguments. Therefore just
wrap it all.
start_pos here is just a parameter internally used. Might be public
sometime in the future.
"""
if code is None and path is None:
raise TypeError("Please provide either code or a path.")
if start_symbol is None:
start_symbol = self._start_symbol
if error_recovery and start_symbol != 'file_input':
raise NotImplementedError("This is currently not implemented.")
if cache and code is None and path is not None:
# With the current architecture we cannot load from cache if the
# code is given, because we just load from cache if it's not older than
# the latest change (file last modified).
module_node = load_module(self._hashed,
path,
cache_path=cache_path)
if module_node is not None:
return module_node
if code is None:
with open(path, 'rb') as f:
code = f.read()
code = python_bytes_to_unicode(code)
lines = split_lines(code, keepends=True)
if diff_cache:
if self._diff_parser is None:
raise TypeError("You have to define a diff parser to be able "
"to use this option.")
try:
module_cache_item = parser_cache[self._hashed][path]
except KeyError:
pass
else:
module_node = module_cache_item.node
old_lines = module_cache_item.lines
if old_lines == lines:
return module_node
new_node = self._diff_parser(
self._pgen_grammar, self._tokenizer,
module_node).update(old_lines=old_lines, new_lines=lines)
save_module(
self._hashed,
path,
new_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return new_node
tokens = self._tokenizer(lines, start_pos)
p = self._parser(self._pgen_grammar,
error_recovery=error_recovery,
start_symbol=start_symbol)
root_node = p.parse(tokens=tokens)
if cache or diff_cache:
save_module(
self._hashed,
path,
root_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return root_node
def _parse(self, code=None, error_recovery=True, path=None,
start_symbol=None, cache=False, diff_cache=False,
cache_path=None, file_io=None, start_pos=(1, 0)):
"""
Wanted python3.5 * operator and keyword only arguments. Therefore just
wrap it all.
start_pos here is just a parameter internally used. Might be public
sometime in the future.
"""
if code is None and path is None and file_io is None:
raise TypeError("Please provide either code or a path.")
if start_symbol is None:
start_symbol = self._start_nonterminal
if error_recovery and start_symbol != 'file_input':
raise NotImplementedError("This is currently not implemented.")
if file_io is None:
if code is None:
file_io = FileIO(path)
else:
file_io = KnownContentFileIO(path, code)
if cache and file_io.path is not None:
module_node = load_module(self._hashed, file_io, cache_path=cache_path)
if module_node is not None:
return module_node
if code is None:
code = file_io.read()
code = python_bytes_to_unicode(code)
lines = split_lines(code, keepends=True)
if diff_cache:
if self._diff_parser is None:
raise TypeError("You have to define a diff parser to be able "
"to use this option.")
try:
module_cache_item = parser_cache[self._hashed][file_io.path]
except KeyError:
pass
else:
module_node = module_cache_item.node
old_lines = module_cache_item.lines
if old_lines == lines:
return module_node
new_node = self._diff_parser(
self._pgen_grammar, self._tokenizer, module_node
).update(
old_lines=old_lines,
new_lines=lines
)
save_module(self._hashed, file_io, new_node, lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return new_node
tokens = self._tokenizer(lines, start_pos)
p = self._parser(
self._pgen_grammar,
error_recovery=error_recovery,
start_nonterminal=start_symbol
)
root_node = p.parse(tokens=tokens)
if cache or diff_cache:
save_module(self._hashed, file_io, root_node, lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return root_node
yield PythonToken(OP, token, spos, prefix)
if contstr:
yield PythonToken(ERRORTOKEN, contstr, contstr_start, prefix)
if contstr.endswith('\n') or contstr.endswith('\r'):
new_line = True
end_pos = lnum, max
# As the last position we just take the maximally possible position. We
# remove -1 for the last new line.
for indent in indents[1:]:
yield PythonToken(DEDENT, '', end_pos, '')
yield PythonToken(ENDMARKER, '', end_pos, additional_prefix)
if __name__ == "__main__":
if len(sys.argv) >= 2:
path = sys.argv[1]
with open(path) as f:
code = f.read()
else:
code = sys.stdin.read()
from parso.utils import python_bytes_to_unicode, parse_version_string
if isinstance(code, bytes):
code = python_bytes_to_unicode(code)
for token in tokenize(code, parse_version_string()):
print(token)
def _parse(self,
code=None,
error_recovery=True,
path=None,
start_symbol=None,
cache=False,
diff_cache=False,
cache_path=None,
file_io=None,
start_pos=(1, 0)):
"""
Wanted python3.5 * operator and keyword only arguments. Therefore just
wrap it all.
start_pos here is just a parameter internally used. Might be static
sometime in the future.
"""
if code is None and path is None and file_io is None:
raise TypeError("Please provide either code or a path.")
if start_symbol is None:
start_symbol = self._start_nonterminal
if error_recovery and start_symbol != 'file_input':
raise NotImplementedError("This is currently not implemented.")
if file_io is None:
if code is None:
file_io = FileIO(path)
else:
file_io = KnownContentFileIO(path, code)
if cache and file_io.path is not None:
module_node = load_module(self._hashed,
file_io,
cache_path=cache_path)
if module_node is not None:
return module_node
if code is None:
code = file_io.read()
code = python_bytes_to_unicode(code)
lines = split_lines(code, keepends=True)
if diff_cache:
if self._diff_parser is None:
raise TypeError("You have to define a diff parser to be able "
"to use this option.")
try:
module_cache_item = parser_cache[self._hashed][file_io.path]
except KeyError:
pass
else:
module_node = module_cache_item.node
old_lines = module_cache_item.lines
if old_lines == lines:
return module_node
new_node = self._diff_parser(
self._pgen_grammar, self._tokenizer,
module_node).update(old_lines=old_lines, new_lines=lines)
try_to_save_module(
self._hashed,
file_io,
new_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return new_node
tokens = self._tokenizer(lines, start_pos=start_pos)
p = self._parser(self._pgen_grammar,
error_recovery=error_recovery,
start_nonterminal=start_symbol)
root_node = p.parse(tokens=tokens)
if cache or diff_cache:
try_to_save_module(
self._hashed,
file_io,
root_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return root_node
yield PythonToken(typ, token, spos, prefix)
if contstr:
yield PythonToken(ERRORTOKEN, contstr, contstr_start, prefix)
if contstr.endswith('\n'):
new_line = True
end_pos = lnum, max
# As the last position we just take the maximally possible position. We
# remove -1 for the last new line.
for indent in indents[1:]:
yield PythonToken(DEDENT, '', end_pos, '')
yield PythonToken(ENDMARKER, '', end_pos, additional_prefix)
if __name__ == "__main__":
if len(sys.argv) >= 2:
path = sys.argv[1]
with open(path) as f:
code = f.read()
else:
code = sys.stdin.read()
from parso.utils import python_bytes_to_unicode, parse_version_string
if isinstance(code, bytes):
code = python_bytes_to_unicode(code)
for token in tokenize(code, parse_version_string()):
print(token)
def parse(self,
code: Union[str, bytes] = None,
*,
error_recovery=True,
path: Union[os.PathLike, str] = None,
start_symbol: str = None,
cache=False,
diff_cache=False,
cache_path: Union[os.PathLike, str] = None,
file_io: FileIO = None) -> _NodeT:
"""
If you want to parse a Python file you want to start here, most likely.
If you need finer grained control over the parsed instance, there will be
other ways to access it.
:param str code: A unicode or bytes string. When it's not possible to
decode bytes to a string, returns a
:py:class:`UnicodeDecodeError`.
:param bool error_recovery: If enabled, any code will be returned. If
it is invalid, it will be returned as an error node. If disabled,
you will get a ParseError when encountering syntax errors in your
code.
:param str start_symbol: The grammar rule (nonterminal) that you want
to parse. Only allowed to be used when error_recovery is False.
:param str path: The path to the file you want to open. Only needed for caching.
:param bool cache: Keeps a copy of the parser tree in RAM and on disk
if a path is given. Returns the cached trees if the corresponding
files on disk have not changed. Note that this stores pickle files
on your file system (e.g. for Linux in ``~/.cache/parso/``).
:param bool diff_cache: Diffs the cached python module against the new
code and tries to parse only the parts that have changed. Returns
the same (changed) module that is found in cache. Using this option
requires you to not do anything anymore with the cached modules
under that path, because the contents of it might change. This
option is still somewhat experimental. If you want stability,
please don't use it.
:param bool cache_path: If given saves the parso cache in this
directory. If not given, defaults to the default cache places on
each platform.
:return: A subclass of :py:class:`parso.tree.NodeOrLeaf`. Typically a
:py:class:`parso.python.tree.Module`.
"""
if code is None and path is None and file_io is None:
raise TypeError("Please provide either code or a path.")
if isinstance(path, str):
path = Path(path)
if isinstance(cache_path, str):
cache_path = Path(cache_path)
if start_symbol is None:
start_symbol = self._start_nonterminal
if error_recovery and start_symbol != 'file_input':
raise NotImplementedError("This is currently not implemented.")
if file_io is None:
if code is None:
file_io = FileIO(path) # type: ignore
else:
file_io = KnownContentFileIO(path, code)
if cache and file_io.path is not None:
module_node = load_module(self._hashed,
file_io,
cache_path=cache_path)
if module_node is not None:
return module_node # type: ignore
if code is None:
code = file_io.read()
code = python_bytes_to_unicode(code)
lines = split_lines(code, keepends=True)
if diff_cache:
if self._diff_parser is None:
raise TypeError("You have to define a diff parser to be able "
"to use this option.")
try:
module_cache_item = parser_cache[self._hashed][file_io.path]
except KeyError:
pass
else:
module_node = module_cache_item.node
old_lines = module_cache_item.lines
if old_lines == lines:
return module_node # type: ignore
new_node = self._diff_parser(
self._pgen_grammar, self._tokenizer,
module_node).update(old_lines=old_lines, new_lines=lines)
try_to_save_module(
self._hashed,
file_io,
new_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return new_node # type: ignore
tokens = self._tokenizer(lines)
p = self._parser(self._pgen_grammar,
error_recovery=error_recovery,
start_nonterminal=start_symbol)
root_node = p.parse(tokens=tokens)
if cache or diff_cache:
try_to_save_module(
self._hashed,
file_io,
root_node,
lines,
# Never pickle in pypy, it's slow as hell.
pickling=cache and not is_pypy,
cache_path=cache_path)
return root_node # type: ignore
def test_bytes_to_unicode_failing_encoding(code, errors):
if errors == 'strict':
with pytest.raises(LookupError):
python_bytes_to_unicode(code, errors=errors)
else:
python_bytes_to_unicode(code, errors=errors)