/
usr
/
lib64
/
python3.12
/
/usr/lib64/python3.12
mkdir
upload
Name
Size
Mode
Actions
asyncio/
-
0755
rm
collections/
-
0755
rm
concurrent/
-
0755
rm
config-3.12-x86_64-linux-gnu/
-
0755
rm
ctypes/
-
0755
rm
curses/
-
0755
rm
dbm/
-
0755
rm
email/
-
0755
rm
encodings/
-
0755
rm
ensurepip/
-
0755
rm
html/
-
0755
rm
http/
-
0755
rm
importlib/
-
0755
rm
json/
-
0755
rm
lib-dynload/
-
0755
rm
lib2to3/
-
0755
rm
logging/
-
0755
rm
multiprocessing/
-
0755
rm
pydoc_data/
-
0755
rm
re/
-
0755
rm
site-packages/
-
0755
rm
sqlite3/
-
0755
rm
tomllib/
-
0755
rm
unittest/
-
0755
rm
urllib/
-
0755
rm
venv/
-
0755
rm
wsgiref/
-
0755
rm
xml/
-
0755
rm
xmlrpc/
-
0755
rm
zipfile/
-
0755
rm
zoneinfo/
-
0755
rm
__pycache__/
-
0755
rm
abc.py
6538
0644
edit
dl
rm
aifc.py
34211
0644
edit
dl
rm
antigravity.py
500
0644
edit
dl
rm
argparse.py
101155
0644
edit
dl
rm
ast.py
64452
0644
edit
dl
rm
base64.py
20634
0755
edit
dl
rm
bdb.py
33573
0644
edit
dl
rm
bisect.py
3423
0644
edit
dl
rm
bz2.py
11847
0644
edit
dl
rm
calendar.py
25864
0644
edit
dl
rm
cgi.py
34418
0755
edit
dl
rm
cgitb.py
12421
0644
edit
dl
rm
chunk.py
5500
0644
edit
dl
rm
cmd.py
14873
0644
edit
dl
rm
code.py
10962
0644
edit
dl
rm
codecs.py
36870
0644
edit
dl
rm
codeop.py
5908
0644
edit
dl
rm
colorsys.py
4062
0644
edit
dl
rm
compileall.py
20507
0644
edit
dl
rm
configparser.py
53789
0644
edit
dl
rm
contextlib.py
27637
0644
edit
dl
rm
contextvars.py
129
0644
edit
dl
rm
copy.py
8412
0644
edit
dl
rm
copyreg.py
7614
0644
edit
dl
rm
cProfile.py
6555
0755
edit
dl
rm
crypt.py
3913
0644
edit
dl
rm
csv.py
16386
0644
edit
dl
rm
dataclasses.py
62085
0644
edit
dl
rm
datetime.py
268
0644
edit
dl
rm
decimal.py
2805
0644
edit
dl
rm
difflib.py
83368
0644
edit
dl
rm
dis.py
30227
0644
edit
dl
rm
doctest.py
106749
0644
edit
dl
rm
enum.py
81540
0644
edit
dl
rm
filecmp.py
10381
0644
edit
dl
rm
fileinput.py
15714
0644
edit
dl
rm
fnmatch.py
5999
0644
edit
dl
rm
fractions.py
38147
0644
edit
dl
rm
ftplib.py
34735
0644
edit
dl
rm
functools.py
37940
0644
edit
dl
rm
genericpath.py
5572
0644
edit
dl
rm
getopt.py
7488
0644
edit
dl
rm
getpass.py
5990
0644
edit
dl
rm
gettext.py
21320
0644
edit
dl
rm
glob.py
8732
0644
edit
dl
rm
graphlib.py
9648
0644
edit
dl
rm
gzip.py
25402
0644
edit
dl
rm
hashlib.py
9683
0644
edit
dl
rm
heapq.py
23024
0644
edit
dl
rm
hmac.py
8043
0644
edit
dl
rm
imaplib.py
54209
0644
edit
dl
rm
imghdr.py
4398
0644
edit
dl
rm
inspect.py
127125
0644
edit
dl
rm
io.py
3582
0644
edit
dl
rm
ipaddress.py
81414
0644
edit
dl
rm
keyword.py
1073
0644
edit
dl
rm
LICENSE.txt
13936
0644
edit
dl
rm
linecache.py
5800
0644
edit
dl
rm
locale.py
78599
0644
edit
dl
rm
lzma.py
13277
0644
edit
dl
rm
mailbox.py
78911
0644
edit
dl
rm
mailcap.py
9333
0644
edit
dl
rm
mimetypes.py
23037
0644
edit
dl
rm
modulefinder.py
23699
0644
edit
dl
rm
netrc.py
6922
0644
edit
dl
rm
nntplib.py
41087
0644
edit
dl
rm
ntpath.py
30404
0644
edit
dl
rm
nturl2path.py
2374
0644
edit
dl
rm
numbers.py
11467
0644
edit
dl
rm
opcode.py
13174
0644
edit
dl
rm
operator.py
10965
0644
edit
dl
rm
optparse.py
60369
0644
edit
dl
rm
os.py
40821
0644
edit
dl
rm
pathlib.py
51052
0644
edit
dl
rm
pdb.py
70297
0755
edit
dl
rm
pickle.py
66911
0644
edit
dl
rm
pickletools.py
94052
0644
edit
dl
rm
pipes.py
8978
0644
edit
dl
rm
pkgutil.py
18281
0644
edit
dl
rm
platform.py
43388
0755
edit
dl
rm
plistlib.py
28582
0644
edit
dl
rm
poplib.py
14742
0644
edit
dl
rm
posixpath.py
17356
0644
edit
dl
rm
pprint.py
24158
0644
edit
dl
rm
profile.py
23092
0755
edit
dl
rm
pstats.py
29289
0644
edit
dl
rm
pty.py
6137
0644
edit
dl
rm
pyclbr.py
11396
0644
edit
dl
rm
pydoc.py
113508
0755
edit
dl
rm
py_compile.py
7837
0644
edit
dl
rm
queue.py
11496
0644
edit
dl
rm
quopri.py
7183
0755
edit
dl
rm
random.py
34689
0644
edit
dl
rm
reprlib.py
7148
0644
edit
dl
rm
rlcompleter.py
7827
0644
edit
dl
rm
runpy.py
12885
0644
edit
dl
rm
sched.py
6351
0644
edit
dl
rm
secrets.py
1984
0644
edit
dl
rm
selectors.py
19671
0644
edit
dl
rm
shelve.py
8560
0644
edit
dl
rm
shlex.py
13353
0644
edit
dl
rm
shutil.py
56762
0644
edit
dl
rm
signal.py
2495
0644
edit
dl
rm
site.py
23439
0644
edit
dl
rm
smtplib.py
43531
0755
edit
dl
rm
sndhdr.py
7448
0644
edit
dl
rm
socket.py
37815
0644
edit
dl
rm
socketserver.py
28065
0644
edit
dl
rm
sre_compile.py
231
0644
edit
dl
rm
sre_constants.py
232
0644
edit
dl
rm
sre_parse.py
229
0644
edit
dl
rm
ssl.py
50904
0644
edit
dl
rm
stat.py
5485
0644
edit
dl
rm
statistics.py
50227
0644
edit
dl
rm
string.py
11786
0644
edit
dl
rm
stringprep.py
12917
0644
edit
dl
rm
struct.py
257
0644
edit
dl
rm
subprocess.py
88747
0644
edit
dl
rm
sunau.py
18478
0644
edit
dl
rm
symtable.py
12477
0644
edit
dl
rm
sysconfig.py
33773
0644
edit
dl
rm
tabnanny.py
11531
0755
edit
dl
rm
tarfile.py
114250
0755
edit
dl
rm
telnetlib.py
23334
0644
edit
dl
rm
tempfile.py
32386
0644
edit
dl
rm
textwrap.py
19718
0644
edit
dl
rm
this.py
1003
0644
edit
dl
rm
threading.py
59742
0644
edit
dl
rm
timeit.py
13463
0755
edit
dl
rm
token.py
2511
0644
edit
dl
rm
tokenize.py
21570
0644
edit
dl
rm
trace.py
29352
0755
edit
dl
rm
traceback.py
46393
0644
edit
dl
rm
tracemalloc.py
18047
0644
edit
dl
rm
tty.py
2035
0644
edit
dl
rm
types.py
10993
0644
edit
dl
rm
typing.py
118836
0644
edit
dl
rm
uu.py
7341
0644
edit
dl
rm
uuid.py
29656
0644
edit
dl
rm
warnings.py
21909
0644
edit
dl
rm
wave.py
22769
0644
edit
dl
rm
weakref.py
21513
0644
edit
dl
rm
webbrowser.py
24169
0755
edit
dl
rm
xdrlib.py
5942
0644
edit
dl
rm
zipapp.py
7543
0644
edit
dl
rm
zipimport.py
27840
0644
edit
dl
rm
_aix_support.py
4021
0644
edit
dl
rm
_collections_abc.py
32089
0644
edit
dl
rm
_compat_pickle.py
8761
0644
edit
dl
rm
_compression.py
5681
0644
edit
dl
rm
_markupbase.py
14653
0644
edit
dl
rm
_osx_support.py
22023
0644
edit
dl
rm
_pydatetime.py
92087
0644
edit
dl
rm
_pydecimal.py
227283
0644
edit
dl
rm
_pyio.py
93593
0644
edit
dl
rm
_pylong.py
10790
0644
edit
dl
rm
_py_abc.py
6189
0644
edit
dl
rm
_sitebuiltins.py
3128
0644
edit
dl
rm
_strptime.py
28393
0644
edit
dl
rm
_sysconfigdata__linux_x86_64-linux-gnu.py
72132
0644
edit
dl
rm
_threading_local.py
7220
0644
edit
dl
rm
_weakrefset.py
5893
0644
edit
dl
rm
__future__.py
5218
0644
edit
dl
rm
__hello__.py
227
0644
edit
dl
rm
Edit:
/usr/lib64/python3.12/tokenize.py
(21570B)
"""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 <ping@lfw.org>' __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 import functools from io import TextIOWrapper import itertools as _itertools import re import sys from token import * from token import EXACT_TOKEN_TYPES import _tokenize 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__ + ["tokenize", "generate_tokens", "detect_encoding", "untokenize", "TokenInfo"] del token 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(?:_?0)*|[1-9](?:_?[0-9])*)' Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber) Exponent = r'[eE][-+]?[0-9](?:_?[0-9])*' Pointfloat = group(r'[0-9](?:_?[0-9])*\.(?:[0-9](?:_?[0-9])*)?', r'\.[0-9](?:_?[0-9])*') + maybe(Exponent) Expfloat = r'[0-9](?:_?[0-9])*' + Exponent Floatnumber = group(Pointfloat, Expfloat) Imagnumber = group(r'[0-9](?:_?[0-9])*[jJ]', Floatnumber + r'[jJ]') Number = group(Imagnumber, Floatnumber, Intnumber) # Return the empty string, plus all of the valid string prefixes. def _all_string_prefixes(): # The valid string prefixes. Only contain the lower case versions, # and don't contain any permutations (include 'fr', but not # 'rf'). The various permutations will be generated. _valid_string_prefixes = ['b', 'r', 'u', 'f', 'br', 'fr'] # if we add binary f-strings, add: ['fb', 'fbr'] result = {''} for prefix in _valid_string_prefixes: for t in _itertools.permutations(prefix): # create a list with upper and lower versions of each # character for u in _itertools.product(*[(c, c.upper()) for c in t]): result.add(''.join(u)) return result @functools.lru_cache def _compile(expr): return re.compile(expr, re.UNICODE) # Note that since _all_string_prefixes includes the empty string, # StringPrefix can be the empty string (making it optional). StringPrefix = group(*_all_string_prefixes()) # 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"\\]*)*"') # Sorting in reverse order puts the long operators before their prefixes. # Otherwise if = came before ==, == would get recognized as two instances # of =. Special = group(*map(re.escape, sorted(EXACT_TOKEN_TYPES, reverse=True))) Funny = group(r'\r?\n', 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) # For a given string prefix plus quotes, endpats maps it to a regex # to match the remainder of that string. _prefix can be empty, for # a normal single or triple quoted string (with no prefix). endpats = {} for _prefix in _all_string_prefixes(): endpats[_prefix + "'"] = Single endpats[_prefix + '"'] = Double endpats[_prefix + "'''"] = Single3 endpats[_prefix + '"""'] = Double3 del _prefix # A set of all of the single and triple quoted string prefixes, # including the opening quotes. single_quoted = set() triple_quoted = set() for t in _all_string_prefixes(): for u in (t + '"', t + "'"): single_quoted.add(u) for u in (t + '"""', t + "'''"): triple_quoted.add(u) del t, u 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.prev_type = None self.prev_line = "" 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)) self.add_backslash_continuation(start) col_offset = col - self.prev_col if col_offset: self.tokens.append(" " * col_offset) def add_backslash_continuation(self, start): """Add backslash continuation characters if the row has increased without encountering a newline token. This also inserts the correct amount of whitespace before the backslash. """ row = start[0] row_offset = row - self.prev_row if row_offset == 0: return newline = '\r\n' if self.prev_line.endswith('\r\n') else '\n' line = self.prev_line.rstrip('\\\r\n') ws = ''.join(_itertools.takewhile(str.isspace, reversed(line))) self.tokens.append(ws + f"\\{newline}" * row_offset) self.prev_col = 0 def escape_brackets(self, token): characters = [] consume_until_next_bracket = False for character in token: if character == "}": if consume_until_next_bracket: consume_until_next_bracket = False else: characters.append(character) if character == "{": n_backslashes = sum( 1 for char in _itertools.takewhile( "\\".__eq__, characters[-2::-1] ) ) if n_backslashes % 2 == 0 or characters[-1] != "N": characters.append(character) else: consume_until_next_bracket = True characters.append(character) return "".join(characters) 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 elif tok_type == FSTRING_MIDDLE: if '{' in token or '}' in token: token = self.escape_brackets(token) last_line = token.splitlines()[-1] end_line, end_col = end extra_chars = last_line.count("{{") + last_line.count("}}") end = (end_line, end_col + extra_chars) 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 self.prev_type = tok_type self.prev_line = line return "".join(self.tokens) def compat(self, token, iterable): indents = [] toks_append = self.tokens.append startline = token[0] in (NEWLINE, NL) prevstring = False in_fstring = 0 for tok in _itertools.chain([token], iterable): toknum, tokval = tok[:2] if toknum == ENCODING: self.encoding = tokval continue if toknum in (NAME, NUMBER): tokval += ' ' # Insert a space between two consecutive strings if toknum == STRING: if prevstring: tokval = ' ' + tokval prevstring = True else: prevstring = False if toknum == FSTRING_START: in_fstring += 1 elif toknum == FSTRING_END: in_fstring -= 1 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 elif toknum == FSTRING_MIDDLE: tokval = self.escape_brackets(tokval) # Insert a space between two consecutive brackets if we are in an f-string if tokval in {"{", "}"} and self.tokens and self.tokens[-1] == tokval and in_fstring: tokval = ' ' + tokval # Insert a space between two consecutive f-strings if toknum in (STRING, FSTRING_START) and self.prev_type in (STRING, FSTRING_END): self.tokens.append(" ") toks_append(tokval) self.prev_type = toknum 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. The result is guaranteed to tokenize back to match the input so that the conversion is lossless and round-trips are assured. The guarantee applies only to the token type and token string as the spacing between tokens (column positions) may change. """ 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 physical line. The first token sequence will always be an ENCODING token which tells you which encoding was used to decode the bytes stream. """ encoding, consumed = detect_encoding(readline) rl_gen = _itertools.chain(consumed, iter(readline, b"")) 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), '') yield from _generate_tokens_from_c_tokenizer(rl_gen.__next__, encoding, extra_tokens=True) def generate_tokens(readline): """Tokenize a source reading Python code as unicode strings. This has the same API as tokenize(), except that it expects the *readline* callable to return str objects instead of bytes. """ return _generate_tokens_from_c_tokenizer(readline, extra_tokens=True) def main(): import argparse # Helper error handling routines def perror(message): sys.stderr.write(message) sys.stderr.write('\n') 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 = "<stdin>" tokens = _generate_tokens_from_c_tokenizer( sys.stdin.readline, extra_tokens=True) # 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 def _transform_msg(msg): """Transform error messages from the C tokenizer into the Python tokenize The C tokenizer is more picky than the Python one, so we need to massage the error messages a bit for backwards compatibility. """ if "unterminated triple-quoted string literal" in msg: return "EOF in multi-line string" return msg def _generate_tokens_from_c_tokenizer(source, encoding=None, extra_tokens=False): """Tokenize a source reading Python code as unicode strings using the internal C tokenizer""" if encoding is None: it = _tokenize.TokenizerIter(source, extra_tokens=extra_tokens) else: it = _tokenize.TokenizerIter(source, encoding=encoding, extra_tokens=extra_tokens) try: for info in it: yield TokenInfo._make(info) except SyntaxError as e: if type(e) != SyntaxError: raise e from None msg = _transform_msg(e.msg) raise TokenError(msg, (e.lineno, e.offset)) from None if __name__ == "__main__": main()
Save
cmd:
run