/
opt
/
alt
/
python34
/
lib64
/
python3.4
/
/opt/alt/python34/lib64/python3.4
mkdir
upload
Name
Size
Mode
Actions
asyncio/
-
0755
rm
collections/
-
0755
rm
concurrent/
-
0755
rm
config-3.4m/
-
0755
rm
ctypes/
-
0755
rm
curses/
-
0755
rm
dbm/
-
0755
rm
distutils/
-
0755
rm
email/
-
0755
rm
encodings/
-
0755
rm
ensurepip/
-
0755
rm
html/
-
0755
rm
http/
-
0755
rm
idlelib/
-
0755
rm
importlib/
-
0755
rm
json/
-
0755
rm
lib-dynload/
-
0755
rm
lib2to3/
-
0755
rm
logging/
-
0755
rm
multiprocessing/
-
0755
rm
plat-linux/
-
0755
rm
pydoc_data/
-
0755
rm
site-packages/
-
0755
rm
sqlite3/
-
0755
rm
test/
-
0755
rm
unittest/
-
0755
rm
urllib/
-
0755
rm
venv/
-
0755
rm
wsgiref/
-
0755
rm
xml/
-
0755
rm
xmlrpc/
-
0755
rm
__pycache__/
-
0755
rm
abc.py
8624
0644
edit
dl
rm
aifc.py
31578
0644
edit
dl
rm
antigravity.py
475
0644
edit
dl
rm
argparse.py
90027
0644
edit
dl
rm
ast.py
12034
0644
edit
dl
rm
asynchat.py
11825
0644
edit
dl
rm
asyncore.py
20998
0644
edit
dl
rm
base64.py
20180
0755
edit
dl
rm
bdb.py
23354
0644
edit
dl
rm
binhex.py
13928
0644
edit
dl
rm
bisect.py
2595
0644
edit
dl
rm
bz2.py
18860
0644
edit
dl
rm
calendar.py
22941
0644
edit
dl
rm
cgi.py
35941
0755
edit
dl
rm
cgitb.py
12041
0644
edit
dl
rm
chunk.py
5425
0644
edit
dl
rm
cmd.py
14860
0644
edit
dl
rm
code.py
10037
0644
edit
dl
rm
codecs.py
35910
0644
edit
dl
rm
codeop.py
5994
0644
edit
dl
rm
colorsys.py
4064
0644
edit
dl
rm
compileall.py
9618
0644
edit
dl
rm
configparser.py
49698
0644
edit
dl
rm
contextlib.py
11639
0644
edit
dl
rm
copy.py
9005
0644
edit
dl
rm
copyreg.py
6833
0644
edit
dl
rm
cProfile.py
5324
0755
edit
dl
rm
crypt.py
1879
0644
edit
dl
rm
csv.py
16185
0644
edit
dl
rm
datetime.py
75804
0644
edit
dl
rm
decimal.py
228688
0644
edit
dl
rm
difflib.py
81684
0644
edit
dl
rm
dis.py
17160
0644
edit
dl
rm
doctest.py
104492
0644
edit
dl
rm
dummy_threading.py
2815
0644
edit
dl
rm
enum.py
21538
0644
edit
dl
rm
filecmp.py
9830
0644
edit
dl
rm
fileinput.py
14865
0644
edit
dl
rm
fnmatch.py
3163
0644
edit
dl
rm
formatter.py
15173
0644
edit
dl
rm
fractions.py
23203
0644
edit
dl
rm
ftplib.py
38532
0644
edit
dl
rm
functools.py
28511
0644
edit
dl
rm
genericpath.py
3882
0644
edit
dl
rm
getopt.py
7489
0644
edit
dl
rm
getpass.py
6069
0644
edit
dl
rm
gettext.py
20767
0644
edit
dl
rm
glob.py
3461
0644
edit
dl
rm
gzip.py
24314
0644
edit
dl
rm
hashlib.py
9850
0644
edit
dl
rm
heapq.py
17997
0644
edit
dl
rm
hmac.py
5063
0644
edit
dl
rm
imaplib.py
50267
0644
edit
dl
rm
imghdr.py
3528
0644
edit
dl
rm
imp.py
9984
0644
edit
dl
rm
inspect.py
104640
0644
edit
dl
rm
io.py
3396
0644
edit
dl
rm
ipaddress.py
71598
0644
edit
dl
rm
keyword.py
2222
0755
edit
dl
rm
linecache.py
3953
0644
edit
dl
rm
locale.py
74530
0644
edit
dl
rm
lzma.py
19371
0644
edit
dl
rm
macpath.py
5619
0644
edit
dl
rm
macurl2path.py
2732
0644
edit
dl
rm
mailbox.py
78382
0644
edit
dl
rm
mailcap.py
7437
0644
edit
dl
rm
mimetypes.py
20781
0644
edit
dl
rm
modulefinder.py
23421
0644
edit
dl
rm
netrc.py
5748
0644
edit
dl
rm
nntplib.py
43082
0644
edit
dl
rm
ntpath.py
20477
0644
edit
dl
rm
nturl2path.py
2444
0644
edit
dl
rm
numbers.py
10243
0644
edit
dl
rm
opcode.py
5442
0644
edit
dl
rm
operator.py
9195
0644
edit
dl
rm
optparse.py
60346
0644
edit
dl
rm
os.py
33882
0644
edit
dl
rm
pathlib.py
42467
0644
edit
dl
rm
pdb.py
60992
0755
edit
dl
rm
pickle.py
55989
0644
edit
dl
rm
pickletools.py
91762
0644
edit
dl
rm
pipes.py
8916
0644
edit
dl
rm
pkgutil.py
21215
0644
edit
dl
rm
platform.py
46761
0755
edit
dl
rm
plistlib.py
31791
0644
edit
dl
rm
poplib.py
14319
0644
edit
dl
rm
posixpath.py
13448
0644
edit
dl
rm
pprint.py
14919
0644
edit
dl
rm
profile.py
22032
0755
edit
dl
rm
pstats.py
26316
0644
edit
dl
rm
pty.py
4763
0644
edit
dl
rm
pyclbr.py
13520
0644
edit
dl
rm
pydoc.py
103011
0755
edit
dl
rm
py_compile.py
7103
0644
edit
dl
rm
queue.py
8835
0644
edit
dl
rm
quopri.py
7265
0755
edit
dl
rm
random.py
26084
0644
edit
dl
rm
re.py
15604
0644
edit
dl
rm
reprlib.py
5110
0644
edit
dl
rm
rlcompleter.py
6069
0644
edit
dl
rm
runpy.py
10816
0644
edit
dl
rm
sched.py
6354
0644
edit
dl
rm
selectors.py
17097
0644
edit
dl
rm
shelve.py
8528
0644
edit
dl
rm
shlex.py
11548
0644
edit
dl
rm
shutil.py
39902
0644
edit
dl
rm
site.py
21553
0644
edit
dl
rm
smtpd.py
29991
0755
edit
dl
rm
smtplib.py
38971
0755
edit
dl
rm
sndhdr.py
6256
0644
edit
dl
rm
socket.py
19067
0644
edit
dl
rm
socketserver.py
24372
0644
edit
dl
rm
sre_compile.py
19903
0644
edit
dl
rm
sre_constants.py
7267
0644
edit
dl
rm
sre_parse.py
31429
0644
edit
dl
rm
ssl.py
34747
0644
edit
dl
rm
stat.py
4400
0644
edit
dl
rm
statistics.py
19556
0644
edit
dl
rm
string.py
11445
0644
edit
dl
rm
stringprep.py
12917
0644
edit
dl
rm
struct.py
257
0644
edit
dl
rm
subprocess.py
64549
0644
edit
dl
rm
sunau.py
18095
0644
edit
dl
rm
symbol.py
2053
0755
edit
dl
rm
symtable.py
7404
0644
edit
dl
rm
sysconfig.py
24632
0644
edit
dl
rm
tabnanny.py
11410
0755
edit
dl
rm
tarfile.py
91557
0755
edit
dl
rm
telnetlib.py
23074
0644
edit
dl
rm
tempfile.py
22525
0644
edit
dl
rm
textwrap.py
19282
0644
edit
dl
rm
this.py
1003
0644
edit
dl
rm
threading.py
48802
0644
edit
dl
rm
timeit.py
11972
0755
edit
dl
rm
token.py
3034
0644
edit
dl
rm
tokenize.py
25596
0644
edit
dl
rm
trace.py
31487
0755
edit
dl
rm
traceback.py
11167
0644
edit
dl
rm
tracemalloc.py
15651
0644
edit
dl
rm
tty.py
879
0644
edit
dl
rm
types.py
5411
0644
edit
dl
rm
uu.py
6766
0755
edit
dl
rm
uuid.py
23724
0644
edit
dl
rm
warnings.py
14303
0644
edit
dl
rm
wave.py
17682
0644
edit
dl
rm
weakref.py
19384
0644
edit
dl
rm
webbrowser.py
21432
0755
edit
dl
rm
xdrlib.py
5913
0644
edit
dl
rm
zipfile.py
68547
0644
edit
dl
rm
_bootlocale.py
1301
0644
edit
dl
rm
_collections_abc.py
19898
0644
edit
dl
rm
_compat_pickle.py
8318
0644
edit
dl
rm
_dummy_thread.py
4872
0644
edit
dl
rm
_markupbase.py
14598
0644
edit
dl
rm
_osx_support.py
19101
0644
edit
dl
rm
_pyio.py
73893
0644
edit
dl
rm
_sitebuiltins.py
3115
0644
edit
dl
rm
_strptime.py
22053
0644
edit
dl
rm
_sysconfigdata.py
24480
0644
edit
dl
rm
_threading_local.py
7410
0644
edit
dl
rm
_weakrefset.py
5705
0644
edit
dl
rm
__future__.py
4584
0644
edit
dl
rm
__phello__.foo.py
64
0644
edit
dl
rm
Edit:
/opt/alt/python34/lib64/python3.4/tokenize.py
(25596B)
"""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 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 } 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, "R'''": Single3, 'R"""': 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): 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 intput: # Output bytes will tokenize the 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 argment, 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. Alternately, 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] 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", ("<tokenize>", lnum, pos, line)) indents = indents[:-1] yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line) 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': yield TokenInfo(NL if parenlev > 0 else NEWLINE, token, spos, epos, line) elif initial == '#': assert not token.endswith("\n") 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 yield TokenInfo(NAME, token, spos, epos, line) elif initial == '\\': # continued stmt continued = 1 else: if initial in '([{': parenlev += 1 elif initial in ')]}': parenlev -= 1 yield TokenInfo(OP, token, spos, epos, line) else: yield TokenInfo(ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos+1), line) pos += 1 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 = "<stdin>" 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()
Save
cmd:
run