NG4R3P

Linux 4gvps.4gvps.com 3.10.0-1127.18.2.vz7.163.46 #1 SMP Fri Nov 20 21:47:55 MSK 2020 x86_64
SOFT : Apache PHP : 7.4.33
/proc/self/root/opt/alt/python35/lib64/python3.5/

38.135.39.45

[ NAME ]	[ SIZE ]	[ PERM ]	[ DATE ]	[ ACT ]
+FILE +DIR
__pycache__	dir	drwxr-xr-x	2024-08-13 01:15	R D
asyncio	dir	drwxr-xr-x	2024-08-13 01:15	R D
collections	dir	drwxr-xr-x	2024-08-13 01:15	R D
concurrent	dir	drwxr-xr-x	2024-08-13 01:15	R D
config-3.5m	dir	drwxr-xr-x	2024-08-13 01:15	R D
ctypes	dir	drwxr-xr-x	2024-08-13 01:15	R D
curses	dir	drwxr-xr-x	2024-08-13 01:15	R D
dbm	dir	drwxr-xr-x	2024-08-13 01:15	R D
distutils	dir	drwxr-xr-x	2024-08-13 01:15	R D
email	dir	drwxr-xr-x	2024-08-13 01:15	R D
encodings	dir	drwxr-xr-x	2024-08-13 01:15	R D
ensurepip	dir	drwxr-xr-x	2024-08-13 01:15	R D
html	dir	drwxr-xr-x	2024-08-13 01:15	R D
http	dir	drwxr-xr-x	2024-08-13 01:15	R D
idlelib	dir	drwxr-xr-x	2024-08-13 01:15	R D
importlib	dir	drwxr-xr-x	2024-08-13 01:15	R D
json	dir	drwxr-xr-x	2024-08-13 01:15	R D
lib-dynload	dir	drwxr-xr-x	2024-08-13 01:15	R D
lib2to3	dir	drwxr-xr-x	2024-08-13 01:16	R D
logging	dir	drwxr-xr-x	2024-08-13 01:15	R D
multiprocessing	dir	drwxr-xr-x	2024-08-13 01:15	R D
plat-linux	dir	drwxr-xr-x	2024-08-13 01:15	R D
pydoc_data	dir	drwxr-xr-x	2024-08-13 01:15	R D
site-packages	dir	drwxr-xr-x	2024-08-13 01:16	R D
sqlite3	dir	drwxr-xr-x	2024-08-13 01:15	R D
test	dir	drwxr-xr-x	2024-08-13 01:15	R D
unittest	dir	drwxr-xr-x	2024-08-13 01:15	R D
urllib	dir	drwxr-xr-x	2024-08-13 01:15	R D
venv	dir	drwxr-xr-x	2024-08-13 01:15	R D
wsgiref	dir	drwxr-xr-x	2024-08-13 01:15	R D
xml	dir	drwxr-xr-x	2024-08-13 01:15	R D
xmlrpc	dir	drwxr-xr-x	2024-08-13 01:15	R D
__future__.py	4.728 KB	-rw-r--r--	2024-05-31 13:50	R E G D
__phello__.foo.py	0.063 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_bootlocale.py	1.271 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_collections_abc.py	24.213 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_compat_pickle.py	8.355 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_compression.py	5.215 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_dummy_thread.py	4.998 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_markupbase.py	14.256 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_osx_support.py	18.667 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_pydecimal.py	223.27 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_pyio.py	85.906 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_sitebuiltins.py	3.042 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_strptime.py	21.665 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_sysconfigdata.py	22.783 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_threading_local.py	7.236 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_weakrefset.py	5.571 KB	-rw-r--r--	2024-05-31 13:50	R E G D
abc.py	8.426 KB	-rw-r--r--	2024-05-31 13:50	R E G D
aifc.py	31.218 KB	-rw-r--r--	2024-05-31 13:50	R E G D
antigravity.py	0.465 KB	-rw-r--r--	2024-05-31 13:50	R E G D
argparse.py	88.025 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ast.py	11.72 KB	-rw-r--r--	2024-05-31 13:50	R E G D
asynchat.py	11.69 KB	-rw-r--r--	2024-05-31 13:50	R E G D
asyncore.py	19.633 KB	-rw-r--r--	2024-05-31 13:50	R E G D
base64.py	20.041 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
bdb.py	22.807 KB	-rw-r--r--	2024-05-31 13:50	R E G D
binhex.py	13.627 KB	-rw-r--r--	2024-05-31 13:50	R E G D
bisect.py	2.534 KB	-rw-r--r--	2024-05-31 13:50	R E G D
bz2.py	12.133 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cProfile.py	5.199 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
calendar.py	22.459 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cgi.py	35.201 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
cgitb.py	11.741 KB	-rw-r--r--	2024-05-31 13:50	R E G D
chunk.py	5.298 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cmd.py	14.512 KB	-rw-r--r--	2024-05-31 13:50	R E G D
code.py	9.881 KB	-rw-r--r--	2024-05-31 13:50	R E G D
codecs.py	35.382 KB	-rw-r--r--	2024-05-31 13:50	R E G D
codeop.py	5.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
colorsys.py	3.969 KB	-rw-r--r--	2024-05-31 13:50	R E G D
compileall.py	11.437 KB	-rw-r--r--	2024-05-31 13:50	R E G D
configparser.py	52.199 KB	-rw-r--r--	2024-05-31 13:50	R E G D
contextlib.py	12.159 KB	-rw-r--r--	2024-05-31 13:50	R E G D
copy.py	8.736 KB	-rw-r--r--	2024-05-31 13:50	R E G D
copyreg.py	6.673 KB	-rw-r--r--	2024-05-31 13:50	R E G D
crypt.py	1.835 KB	-rw-r--r--	2024-05-31 13:50	R E G D
csv.py	15.75 KB	-rw-r--r--	2024-05-31 13:50	R E G D
datetime.py	74.12 KB	-rw-r--r--	2024-05-31 13:50	R E G D
decimal.py	0.313 KB	-rw-r--r--	2024-05-31 13:50	R E G D
difflib.py	82.23 KB	-rw-r--r--	2024-05-31 13:50	R E G D
dis.py	16.943 KB	-rw-r--r--	2024-05-31 13:50	R E G D
doctest.py	101.598 KB	-rw-r--r--	2024-05-31 13:50	R E G D
dummy_threading.py	2.749 KB	-rw-r--r--	2024-05-31 13:50	R E G D
enum.py	21.705 KB	-rw-r--r--	2024-05-31 13:50	R E G D
filecmp.py	9.6 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fileinput.py	13.925 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fnmatch.py	3.089 KB	-rw-r--r--	2024-05-31 13:50	R E G D
formatter.py	14.788 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fractions.py	24.035 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ftplib.py	34.132 KB	-rw-r--r--	2024-05-31 13:50	R E G D
functools.py	28.266 KB	-rw-r--r--	2024-05-31 13:50	R E G D
genericpath.py	4.262 KB	-rw-r--r--	2024-05-31 13:50	R E G D
getopt.py	7.313 KB	-rw-r--r--	2024-05-31 13:50	R E G D
getpass.py	5.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
gettext.py	21.025 KB	-rw-r--r--	2024-05-31 13:50	R E G D
glob.py	4.953 KB	-rw-r--r--	2024-05-31 13:50	R E G D
gzip.py	19.785 KB	-rw-r--r--	2024-05-31 13:50	R E G D
hashlib.py	7.792 KB	-rw-r--r--	2024-05-31 13:50	R E G D
heapq.py	22.392 KB	-rw-r--r--	2024-05-31 13:50	R E G D
hmac.py	4.944 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imaplib.py	50.96 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imghdr.py	3.67 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imp.py	10.426 KB	-rw-r--r--	2024-05-31 13:50	R E G D
inspect.py	111.522 KB	-rw-r--r--	2024-05-31 13:50	R E G D
io.py	3.316 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ipaddress.py	73.958 KB	-rw-r--r--	2024-05-31 13:50	R E G D
keyword.py	2.17 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
linecache.py	5.188 KB	-rw-r--r--	2024-05-31 13:50	R E G D
locale.py	72.962 KB	-rw-r--r--	2024-05-31 13:50	R E G D
lzma.py	12.622 KB	-rw-r--r--	2024-05-31 13:50	R E G D
macpath.py	5.769 KB	-rw-r--r--	2024-05-31 13:50	R E G D
macurl2path.py	2.668 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mailbox.py	76.58 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mailcap.py	7.914 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mimetypes.py	20.358 KB	-rw-r--r--	2024-05-31 13:50	R E G D
modulefinder.py	22.544 KB	-rw-r--r--	2024-05-31 13:50	R E G D
netrc.py	5.613 KB	-rw-r--r--	2024-05-31 13:50	R E G D
nntplib.py	42.068 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ntpath.py	22.259 KB	-rw-r--r--	2024-05-31 13:50	R E G D
nturl2path.py	2.387 KB	-rw-r--r--	2024-05-31 13:50	R E G D
numbers.py	10.003 KB	-rw-r--r--	2024-05-31 13:50	R E G D
opcode.py	5.747 KB	-rw-r--r--	2024-05-31 13:50	R E G D
operator.py	10.608 KB	-rw-r--r--	2024-05-31 13:50	R E G D
optparse.py	58.93 KB	-rw-r--r--	2024-05-31 13:50	R E G D
os.py	36.165 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pathlib.py	45.899 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pdb.py	59.716 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
pickle.py	54.859 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pickletools.py	89.61 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pipes.py	8.707 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pkgutil.py	20.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
platform.py	45.065 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
plistlib.py	31.064 KB	-rw-r--r--	2024-05-31 13:50	R E G D
poplib.py	14.372 KB	-rw-r--r--	2024-05-31 13:50	R E G D
posixpath.py	14.562 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pprint.py	20.371 KB	-rw-r--r--	2024-05-31 13:50	R E G D
profile.py	21.516 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
pstats.py	25.941 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pty.py	4.651 KB	-rw-r--r--	2024-05-31 13:50	R E G D
py_compile.py	7.013 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pyclbr.py	13.246 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pydoc.py	101.223 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
queue.py	8.574 KB	-rw-r--r--	2024-05-31 13:50	R E G D
quopri.py	7.095 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
random.py	25.843 KB	-rw-r--r--	2024-05-31 13:50	R E G D
re.py	15.138 KB	-rw-r--r--	2024-05-31 13:50	R E G D
reprlib.py	5.211 KB	-rw-r--r--	2024-05-31 13:50	R E G D
rlcompleter.py	6.159 KB	-rw-r--r--	2024-05-31 13:50	R E G D
runpy.py	11.679 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sched.py	6.07 KB	-rw-r--r--	2024-05-31 13:50	R E G D
selectors.py	18.982 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shelve.py	8.328 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shlex.py	11.18 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shutil.py	39.109 KB	-rw-r--r--	2024-05-31 13:50	R E G D
signal.py	2.073 KB	-rw-r--r--	2024-05-31 13:50	R E G D
site.py	21.005 KB	-rw-r--r--	2024-05-31 13:50	R E G D
smtpd.py	34.544 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
smtplib.py	42.612 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
sndhdr.py	6.268 KB	-rw-r--r--	2024-05-31 13:50	R E G D
socket.py	26.499 KB	-rw-r--r--	2024-05-31 13:50	R E G D
socketserver.py	24.088 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_compile.py	17.979 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_constants.py	6.661 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_parse.py	34.294 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ssl.py	41.359 KB	-rw-r--r--	2024-05-31 13:50	R E G D
stat.py	4.92 KB	-rw-r--r--	2024-05-31 13:50	R E G D
statistics.py	19.075 KB	-rw-r--r--	2024-05-31 13:50	R E G D
string.py	11.576 KB	-rw-r--r--	2024-05-31 13:50	R E G D
stringprep.py	12.614 KB	-rw-r--r--	2024-05-31 13:50	R E G D
struct.py	0.251 KB	-rw-r--r--	2024-05-31 13:50	R E G D
subprocess.py	57.531 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sunau.py	17.671 KB	-rw-r--r--	2024-05-31 13:50	R E G D
symbol.py	2.057 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
symtable.py	7.022 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sysconfig.py	23.889 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tabnanny.py	11.146 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
tarfile.py	90.889 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
telnetlib.py	22.477 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tempfile.py	26.012 KB	-rw-r--r--	2024-05-31 13:50	R E G D
textwrap.py	19.1 KB	-rw-r--r--	2024-05-31 13:50	R E G D
this.py	0.979 KB	-rw-r--r--	2024-05-31 13:50	R E G D
threading.py	47.878 KB	-rw-r--r--	2024-05-31 13:50	R E G D
timeit.py	12.112 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
token.py	3.003 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tokenize.py	27.139 KB	-rw-r--r--	2024-05-31 13:50	R E G D
trace.py	30.813 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
traceback.py	21.655 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tracemalloc.py	15.274 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tty.py	0.858 KB	-rw-r--r--	2024-05-31 13:50	R E G D
types.py	8.593 KB	-rw-r--r--	2024-05-31 13:50	R E G D
typing.py	78.257 KB	-rw-r--r--	2024-05-31 13:50	R E G D
uu.py	6.607 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
uuid.py	22.716 KB	-rw-r--r--	2024-05-31 13:50	R E G D
warnings.py	15.479 KB	-rw-r--r--	2024-05-31 13:50	R E G D
wave.py	17.268 KB	-rw-r--r--	2024-05-31 13:50	R E G D
weakref.py	19.986 KB	-rw-r--r--	2024-05-31 13:50	R E G D
webbrowser.py	21.316 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
xdrlib.py	5.774 KB	-rw-r--r--	2024-05-31 13:50	R E G D
zipapp.py	6.989 KB	-rw-r--r--	2024-05-31 13:50	R E G D
zipfile.py	71.945 KB	-rw-r--r--	2024-05-31 13:50	R E G D
REQUEST EXIT

"""Tokenization help for Python programs. tokenize(readline) is a generator that breaks a stream of bytes into Python tokens. It decodes the bytes according to PEP-0263 for determining source file encoding. It accepts a readline-like method which is called repeatedly to get the next line of input (or b"" for EOF). It generates 5-tuples with these members: the token type (see token.py) the token (a string) the starting (row, column) indices of the token (a 2-tuple of ints) the ending (row, column) indices of the token (a 2-tuple of ints) the original line (string) It is designed to match the working of the Python tokenizer exactly, except that it produces COMMENT tokens for comments and gives type OP for all operators. Additionally, all token lists start with an ENCODING token which tells you which encoding was used to decode the bytes stream. """ __author__ = 'Ka-Ping Yee ' __credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, ' 'Skip Montanaro, Raymond Hettinger, Trent Nelson, ' 'Michael Foord') from builtins import open as _builtin_open from codecs import lookup, BOM_UTF8 import collections from io import TextIOWrapper from itertools import chain import re import sys from token import * cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII) blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII) import token __all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding", "NL", "untokenize", "ENCODING", "TokenInfo"] del token COMMENT = N_TOKENS tok_name[COMMENT] = 'COMMENT' NL = N_TOKENS + 1 tok_name[NL] = 'NL' ENCODING = N_TOKENS + 2 tok_name[ENCODING] = 'ENCODING' N_TOKENS += 3 EXACT_TOKEN_TYPES = { '(': LPAR, ')': RPAR, '[': LSQB, ']': RSQB, ':': COLON, ',': COMMA, ';': SEMI, '+': PLUS, '-': MINUS, '*': STAR, '/': SLASH, '|': VBAR, '&': AMPER, '<': LESS, '>': GREATER, '=': EQUAL, '.': DOT, '%': PERCENT, '{': LBRACE, '}': RBRACE, '==': EQEQUAL, '!=': NOTEQUAL, '<=': LESSEQUAL, '>=': GREATEREQUAL, '~': TILDE, '^': CIRCUMFLEX, '<<': LEFTSHIFT, '>>': RIGHTSHIFT, '**': DOUBLESTAR, '+=': PLUSEQUAL, '-=': MINEQUAL, '*=': STAREQUAL, '/=': SLASHEQUAL, '%=': PERCENTEQUAL, '&=': AMPEREQUAL, '|=': VBAREQUAL, '^=': CIRCUMFLEXEQUAL, '<<=': LEFTSHIFTEQUAL, '>>=': RIGHTSHIFTEQUAL, '**=': DOUBLESTAREQUAL, '//': DOUBLESLASH, '//=': DOUBLESLASHEQUAL, '@': AT, '@=': ATEQUAL, } class TokenInfo(collections.namedtuple('TokenInfo', 'type string start end line')): def __repr__(self): annotated_type = '%d (%s)' % (self.type, tok_name[self.type]) return ('TokenInfo(type=%s, string=%r, start=%r, end=%r, line=%r)' % self._replace(type=annotated_type)) @property def exact_type(self): if self.type == OP and self.string in EXACT_TOKEN_TYPES: return EXACT_TOKEN_TYPES[self.string] else: return self.type def group(*choices): return '(' + '|'.join(choices) + ')' def any(*choices): return group(*choices) + '*' def maybe(*choices): return group(*choices) + '?' # Note: we use unicode matching for names ("\w") but ascii matching for # number literals. Whitespace = r'[ \f\t]*' Comment = r'#[^\r\n]*' Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) Name = r'\w+' Hexnumber = r'0[xX][0-9a-fA-F]+' Binnumber = r'0[bB][01]+' Octnumber = r'0[oO][0-7]+' Decnumber = r'(?:0+|[1-9][0-9]*)' Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber) Exponent = r'[eE][-+]?[0-9]+' Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent) Expfloat = r'[0-9]+' + Exponent Floatnumber = group(Pointfloat, Expfloat) Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]') Number = group(Imagnumber, Floatnumber, Intnumber) StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?' # Tail end of ' string. Single = r"[^'\\]*(?:\\.[^'\\]*)*'" # Tail end of " string. Double = r'[^"\\]*(?:\\.[^"\\]*)*"' # Tail end of ''' string. Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''" # Tail end of """ string. Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""' Triple = group(StringPrefix + "'''", StringPrefix + '"""') # Single-line ' or " string. String = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'", StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"') # Because of leftmost-then-longest match semantics, be sure to put the # longest operators first (e.g., if = came before ==, == would get # recognized as two instances of =). Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=", r"//=?", r"->", r"[+\-*/%&@|^=<>]=?", r"~") Bracket = '[][(){}]' Special = group(r'\r?\n', r'\.\.\.', r'[:;.,@]') Funny = group(Operator, Bracket, Special) PlainToken = group(Number, Funny, String, Name) Token = Ignore + PlainToken # First (or only) line of ' or " string. ContStr = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" + group("'", r'\\\r?\n'), StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' + group('"', r'\\\r?\n')) PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple) PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name) def _compile(expr): return re.compile(expr, re.UNICODE) endpats = {"'": Single, '"': Double, "'''": Single3, '"""': Double3, "r'''": Single3, 'r"""': Double3, "b'''": Single3, 'b"""': Double3, "R'''": Single3, 'R"""': Double3, "B'''": Single3, 'B"""': Double3, "br'''": Single3, 'br"""': Double3, "bR'''": Single3, 'bR"""': Double3, "Br'''": Single3, 'Br"""': Double3, "BR'''": Single3, 'BR"""': Double3, "rb'''": Single3, 'rb"""': Double3, "Rb'''": Single3, 'Rb"""': Double3, "rB'''": Single3, 'rB"""': Double3, "RB'''": Single3, 'RB"""': Double3, "u'''": Single3, 'u"""': Double3, "U'''": Single3, 'U"""': Double3, 'r': None, 'R': None, 'b': None, 'B': None, 'u': None, 'U': None} triple_quoted = {} for t in ("'''", '"""', "r'''", 'r"""', "R'''", 'R"""', "b'''", 'b"""', "B'''", 'B"""', "br'''", 'br"""', "Br'''", 'Br"""', "bR'''", 'bR"""', "BR'''", 'BR"""', "rb'''", 'rb"""', "rB'''", 'rB"""', "Rb'''", 'Rb"""', "RB'''", 'RB"""', "u'''", 'u"""', "U'''", 'U"""', ): triple_quoted[t] = t single_quoted = {} for t in ("'", '"', "r'", 'r"', "R'", 'R"', "b'", 'b"', "B'", 'B"', "br'", 'br"', "Br'", 'Br"', "bR'", 'bR"', "BR'", 'BR"' , "rb'", 'rb"', "rB'", 'rB"', "Rb'", 'Rb"', "RB'", 'RB"' , "u'", 'u"', "U'", 'U"', ): single_quoted[t] = t tabsize = 8 class TokenError(Exception): pass class StopTokenizing(Exception): pass class Untokenizer: def __init__(self): self.tokens = [] self.prev_row = 1 self.prev_col = 0 self.encoding = None def add_whitespace(self, start): row, col = start if row < self.prev_row or row == self.prev_row and col < self.prev_col: raise ValueError("start ({},{}) precedes previous end ({},{})" .format(row, col, self.prev_row, self.prev_col)) row_offset = row - self.prev_row if row_offset: self.tokens.append("\\\n" * row_offset) self.prev_col = 0 col_offset = col - self.prev_col if col_offset: self.tokens.append(" " * col_offset) def untokenize(self, iterable): it = iter(iterable) indents = [] startline = False for t in it: if len(t) == 2: self.compat(t, it) break tok_type, token, start, end, line = t if tok_type == ENCODING: self.encoding = token continue if tok_type == ENDMARKER: break if tok_type == INDENT: indents.append(token) continue elif tok_type == DEDENT: indents.pop() self.prev_row, self.prev_col = end continue elif tok_type in (NEWLINE, NL): startline = True elif startline and indents: indent = indents[-1] if start[1] >= len(indent): self.tokens.append(indent) self.prev_col = len(indent) startline = False self.add_whitespace(start) self.tokens.append(token) self.prev_row, self.prev_col = end if tok_type in (NEWLINE, NL): self.prev_row += 1 self.prev_col = 0 return "".join(self.tokens) def compat(self, token, iterable): indents = [] toks_append = self.tokens.append startline = token[0] in (NEWLINE, NL) prevstring = False for tok in chain([token], iterable): toknum, tokval = tok[:2] if toknum == ENCODING: self.encoding = tokval continue if toknum in (NAME, NUMBER, ASYNC, AWAIT): tokval += ' ' # Insert a space between two consecutive strings if toknum == STRING: if prevstring: tokval = ' ' + tokval prevstring = True else: prevstring = False if toknum == INDENT: indents.append(tokval) continue elif toknum == DEDENT: indents.pop() continue elif toknum in (NEWLINE, NL): startline = True elif startline and indents: toks_append(indents[-1]) startline = False toks_append(tokval) def untokenize(iterable): """Transform tokens back into Python source code. It returns a bytes object, encoded using the ENCODING token, which is the first token sequence output by tokenize. Each element returned by the iterable must be a token sequence with at least two elements, a token number and token value. If only two tokens are passed, the resulting output is poor. Round-trip invariant for full input: Untokenized source will match input source exactly Round-trip invariant for limited input: # Output bytes will tokenize back to the input t1 = [tok[:2] for tok in tokenize(f.readline)] newcode = untokenize(t1) readline = BytesIO(newcode).readline t2 = [tok[:2] for tok in tokenize(readline)] assert t1 == t2 """ ut = Untokenizer() out = ut.untokenize(iterable) if ut.encoding is not None: out = out.encode(ut.encoding) return out def _get_normal_name(orig_enc): """Imitates get_normal_name in tokenizer.c.""" # Only care about the first 12 characters. enc = orig_enc[:12].lower().replace("_", "-") if enc == "utf-8" or enc.startswith("utf-8-"): return "utf-8" if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \ enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")): return "iso-8859-1" return orig_enc def detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should be used to decode a Python source file. It requires one argument, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used (as a string) and a list of any lines (left as bytes) it has read in. It detects the encoding from the presence of a utf-8 bom or an encoding cookie as specified in pep-0263. If both a bom and a cookie are present, but disagree, a SyntaxError will be raised. If the encoding cookie is an invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. """ try: filename = readline.__self__.name except AttributeError: filename = None bom_found = False encoding = None default = 'utf-8' def read_or_stop(): try: return readline() except StopIteration: return b'' def find_cookie(line): try: # Decode as UTF-8. Either the line is an encoding declaration, # in which case it should be pure ASCII, or it must be UTF-8 # per default encoding. line_string = line.decode('utf-8') except UnicodeDecodeError: msg = "invalid or missing encoding declaration" if filename is not None: msg = '{} for {!r}'.format(msg, filename) raise SyntaxError(msg) match = cookie_re.match(line_string) if not match: return None encoding = _get_normal_name(match.group(1)) try: codec = lookup(encoding) except LookupError: # This behaviour mimics the Python interpreter if filename is None: msg = "unknown encoding: " + encoding else: msg = "unknown encoding for {!r}: {}".format(filename, encoding) raise SyntaxError(msg) if bom_found: if encoding != 'utf-8': # This behaviour mimics the Python interpreter if filename is None: msg = 'encoding problem: utf-8' else: msg = 'encoding problem for {!r}: utf-8'.format(filename) raise SyntaxError(msg) encoding += '-sig' return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] default = 'utf-8-sig' if not first: return default, [] encoding = find_cookie(first) if encoding: return encoding, [first] if not blank_re.match(first): return default, [first] second = read_or_stop() if not second: return default, [first] encoding = find_cookie(second) if encoding: return encoding, [first, second] return default, [first, second] def open(filename): """Open a file in read only mode using the encoding detected by detect_encoding(). """ buffer = _builtin_open(filename, 'rb') try: encoding, lines = detect_encoding(buffer.readline) buffer.seek(0) text = TextIOWrapper(buffer, encoding, line_buffering=True) text.mode = 'r' return text except: buffer.close() raise def tokenize(readline): """ The tokenize() generator requires one argument, readline, which must be a callable object which provides the same interface as the readline() method of built-in file objects. Each call to the function should return one line of input as bytes. Alternatively, readline can be a callable function terminating with StopIteration: readline = open(myfile, 'rb').__next__ # Example of alternate readline The generator produces 5-tuples with these members: the token type; the token string; a 2-tuple (srow, scol) of ints specifying the row and column where the token begins in the source; a 2-tuple (erow, ecol) of ints specifying the row and column where the token ends in the source; and the line on which the token was found. The line passed is the logical line; continuation lines are included. The first token sequence will always be an ENCODING token which tells you which encoding was used to decode the bytes stream. """ # This import is here to avoid problems when the itertools module is not # built yet and tokenize is imported. from itertools import chain, repeat encoding, consumed = detect_encoding(readline) rl_gen = iter(readline, b"") empty = repeat(b"") return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding) def _tokenize(readline, encoding): lnum = parenlev = continued = 0 numchars = '0123456789' contstr, needcont = '', 0 contline = None indents = [0] # 'stashed' and 'async_*' are used for async/await parsing stashed = None async_def = False async_def_indent = 0 async_def_nl = False if encoding is not None: if encoding == "utf-8-sig": # BOM will already have been stripped. encoding = "utf-8" yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '') while True: # loop over lines in stream try: line = readline() except StopIteration: line = b'' if encoding is not None: line = line.decode(encoding) lnum += 1 pos, max = 0, len(line) if contstr: # continued string if not line: raise TokenError("EOF in multi-line string", strstart) endmatch = endprog.match(line) if endmatch: pos = end = endmatch.end(0) yield TokenInfo(STRING, contstr + line[:end], strstart, (lnum, end), contline + line) contstr, needcont = '', 0 contline = None elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n': yield TokenInfo(ERRORTOKEN, contstr + line, strstart, (lnum, len(line)), contline) contstr = '' contline = None continue else: contstr = contstr + line contline = contline + line continue elif parenlev == 0 and not continued: # new statement if not line: break column = 0 while pos < max: # measure leading whitespace if line[pos] == ' ': column += 1 elif line[pos] == '\t': column = (column//tabsize + 1)*tabsize elif line[pos] == '\f': column = 0 else: break pos += 1 if pos == max: break if line[pos] in '#\r\n': # skip comments or blank lines if line[pos] == '#': comment_token = line[pos:].rstrip('\r\n') nl_pos = pos + len(comment_token) yield TokenInfo(COMMENT, comment_token, (lnum, pos), (lnum, pos + len(comment_token)), line) yield TokenInfo(NL, line[nl_pos:], (lnum, nl_pos), (lnum, len(line)), line) else: yield TokenInfo((NL, COMMENT)[line[pos] == '#'], line[pos:], (lnum, pos), (lnum, len(line)), line) continue if column > indents[-1]: # count indents or dedents indents.append(column) yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line) while column < indents[-1]: if column not in indents: raise IndentationError( "unindent does not match any outer indentation level", ("", lnum, pos, line)) indents = indents[:-1] if async_def and async_def_indent >= indents[-1]: async_def = False async_def_nl = False async_def_indent = 0 yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line) if async_def and async_def_nl and async_def_indent >= indents[-1]: async_def = False async_def_nl = False async_def_indent = 0 else: # continued statement if not line: raise TokenError("EOF in multi-line statement", (lnum, 0)) continued = 0 while pos < max: pseudomatch = _compile(PseudoToken).match(line, pos) if pseudomatch: # scan for tokens start, end = pseudomatch.span(1) spos, epos, pos = (lnum, start), (lnum, end), end if start == end: continue token, initial = line[start:end], line[start] if (initial in numchars or # ordinary number (initial == '.' and token != '.' and token != '...')): yield TokenInfo(NUMBER, token, spos, epos, line) elif initial in '\r\n': if stashed: yield stashed stashed = None if parenlev > 0: yield TokenInfo(NL, token, spos, epos, line) else: yield TokenInfo(NEWLINE, token, spos, epos, line) if async_def: async_def_nl = True elif initial == '#': assert not token.endswith("\n") if stashed: yield stashed stashed = None yield TokenInfo(COMMENT, token, spos, epos, line) elif token in triple_quoted: endprog = _compile(endpats[token]) endmatch = endprog.match(line, pos) if endmatch: # all on one line pos = endmatch.end(0) token = line[start:pos] yield TokenInfo(STRING, token, spos, (lnum, pos), line) else: strstart = (lnum, start) # multiple lines contstr = line[start:] contline = line break elif initial in single_quoted or \ token[:2] in single_quoted or \ token[:3] in single_quoted: if token[-1] == '\n': # continued string strstart = (lnum, start) endprog = _compile(endpats[initial] or endpats[token[1]] or endpats[token[2]]) contstr, needcont = line[start:], 1 contline = line break else: # ordinary string yield TokenInfo(STRING, token, spos, epos, line) elif initial.isidentifier(): # ordinary name if token in ('async', 'await'): if async_def: yield TokenInfo( ASYNC if token == 'async' else AWAIT, token, spos, epos, line) continue tok = TokenInfo(NAME, token, spos, epos, line) if token == 'async' and not stashed: stashed = tok continue if token == 'def': if (stashed and stashed.type == NAME and stashed.string == 'async'): async_def = True async_def_indent = indents[-1] yield TokenInfo(ASYNC, stashed.string, stashed.start, stashed.end, stashed.line) stashed = None if stashed: yield stashed stashed = None yield tok elif initial == '\\': # continued stmt continued = 1 else: if initial in '([{': parenlev += 1 elif initial in ')]}': parenlev -= 1 if stashed: yield stashed stashed = None yield TokenInfo(OP, token, spos, epos, line) else: yield TokenInfo(ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos+1), line) pos += 1 if stashed: yield stashed stashed = None for indent in indents[1:]: # pop remaining indent levels yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '') yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '') # An undocumented, backwards compatible, API for all the places in the standard # library that expect to be able to use tokenize with strings def generate_tokens(readline): return _tokenize(readline, None) def main(): import argparse # Helper error handling routines def perror(message): print(message, file=sys.stderr) def error(message, filename=None, location=None): if location: args = (filename,) + location + (message,) perror("%s:%d:%d: error: %s" % args) elif filename: perror("%s: error: %s" % (filename, message)) else: perror("error: %s" % message) sys.exit(1) # Parse the arguments and options parser = argparse.ArgumentParser(prog='python -m tokenize') parser.add_argument(dest='filename', nargs='?', metavar='filename.py', help='the file to tokenize; defaults to stdin') parser.add_argument('-e', '--exact', dest='exact', action='store_true', help='display token names using the exact type') args = parser.parse_args() try: # Tokenize the input if args.filename: filename = args.filename with _builtin_open(filename, 'rb') as f: tokens = list(tokenize(f.readline)) else: filename = "" tokens = _tokenize(sys.stdin.readline, None) # Output the tokenization for token in tokens: token_type = token.type if args.exact: token_type = token.exact_type token_range = "%d,%d-%d,%d:" % (token.start + token.end) print("%-20s%-15s%-15r" % (token_range, tok_name[token_type], token.string)) except IndentationError as err: line, column = err.args[1][1:3] error(err.args[0], filename, (line, column)) except TokenError as err: line, column = err.args[1] error(err.args[0], filename, (line, column)) except SyntaxError as err: error(err, filename) except OSError as err: error(err) except KeyboardInterrupt: print("interrupted\n") except Exception as err: perror("unexpected error: %s" % err) raise if __name__ == "__main__": main()