FM / python3.8

/snap/core20/2769/usr/lib/python3.8

Name	Size	Mode	Actions
asyncio/	-	0755	rm
collections/	-	0755	rm
concurrent/	-	0755	rm
ctypes/	-	0755	rm
curses/	-	0755	rm
dbm/	-	0755	rm
distutils/	-	0755	rm
email/	-	0755	rm
encodings/	-	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
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	4489	0644	edit dl rm
aifc.py	32814	0644	edit dl rm
antigravity.py	477	0644	edit dl rm
argparse.py	96311	0644	edit dl rm
ast.py	19234	0644	edit dl rm
asynchat.py	11328	0644	edit dl rm
asyncore.py	20094	0644	edit dl rm
base64.py	20382	0755	edit dl rm
bdb.py	32056	0644	edit dl rm
binhex.py	13954	0644	edit dl rm
bisect.py	2214	0644	edit dl rm
bz2.py	12558	0644	edit dl rm
calendar.py	24832	0644	edit dl rm
cgi.py	33932	0755	edit dl rm
cgitb.py	12096	0644	edit dl rm
chunk.py	5435	0644	edit dl rm
cmd.py	14860	0644	edit dl rm
code.py	10622	0644	edit dl rm
codecs.py	36667	0644	edit dl rm
codeop.py	6330	0644	edit dl rm
colorsys.py	4064	0644	edit dl rm
compileall.py	13678	0644	edit dl rm
configparser.py	54374	0644	edit dl rm
contextlib.py	24995	0644	edit dl rm
contextvars.py	129	0644	edit dl rm
copy.py	8661	0644	edit dl rm
copyreg.py	7135	0644	edit dl rm
cProfile.py	6998	0755	edit dl rm
crypt.py	3610	0644	edit dl rm
csv.py	16144	0644	edit dl rm
dataclasses.py	49973	0644	edit dl rm
datetime.py	88287	0644	edit dl rm
decimal.py	320	0644	edit dl rm
difflib.py	84058	0644	edit dl rm
dis.py	20570	0644	edit dl rm
doctest.py	104543	0644	edit dl rm
dummy_threading.py	2815	0644	edit dl rm
enum.py	38136	0644	edit dl rm
filecmp.py	9830	0644	edit dl rm
fileinput.py	14709	0644	edit dl rm
fnmatch.py	4079	0644	edit dl rm
formatter.py	15143	0644	edit dl rm
fractions.py	24329	0644	edit dl rm
ftplib.py	35129	0644	edit dl rm
functools.py	37406	0644	edit dl rm
genericpath.py	4975	0644	edit dl rm
getopt.py	7489	0644	edit dl rm
getpass.py	5994	0644	edit dl rm
gettext.py	27565	0644	edit dl rm
glob.py	5697	0644	edit dl rm
gzip.py	21413	0644	edit dl rm
hashlib.py	9730	0644	edit dl rm
heapq.py	22877	0644	edit dl rm
hmac.py	6629	0644	edit dl rm
imaplib.py	53775	0644	edit dl rm
imghdr.py	3808	0644	edit dl rm
imp.py	10536	0644	edit dl rm
inspect.py	118550	0644	edit dl rm
io.py	3541	0644	edit dl rm
ipaddress.py	76336	0644	edit dl rm
keyword.py	945	0644	edit dl rm
LICENSE.txt	13925	0644	edit dl rm
linecache.py	5330	0644	edit dl rm
locale.py	78195	0644	edit dl rm
lzma.py	12983	0644	edit dl rm
mailbox.py	78661	0644	edit dl rm
mailcap.py	9067	0644	edit dl rm
mimetypes.py	21664	0644	edit dl rm
modulefinder.py	24430	0644	edit dl rm
netrc.py	5566	0644	edit dl rm
nntplib.py	43261	0644	edit dl rm
ntpath.py	25814	0644	edit dl rm
nturl2path.py	2887	0644	edit dl rm
numbers.py	10244	0644	edit dl rm
opcode.py	5808	0644	edit dl rm
operator.py	10711	0644	edit dl rm
optparse.py	60369	0644	edit dl rm
os.py	38995	0644	edit dl rm
pathlib.py	52610	0644	edit dl rm
pdb.py	62738	0755	edit dl rm
pickle.py	64467	0644	edit dl rm
pickletools.py	93486	0644	edit dl rm
pipes.py	8916	0644	edit dl rm
pkgutil.py	21461	0644	edit dl rm
platform.py	40425	0755	edit dl rm
plistlib.py	32460	0644	edit dl rm
poplib.py	15200	0644	edit dl rm
posixpath.py	15500	0644	edit dl rm
pprint.py	21484	0644	edit dl rm
profile.py	23534	0755	edit dl rm
pstats.py	27345	0644	edit dl rm
pty.py	4807	0644	edit dl rm
pyclbr.py	15255	0644	edit dl rm
pydoc.py	106863	0755	edit dl rm
py_compile.py	8148	0644	edit dl rm
queue.py	11356	0644	edit dl rm
quopri.py	7252	0755	edit dl rm
random.py	28802	0644	edit dl rm
re.py	15861	0644	edit dl rm
reprlib.py	5267	0644	edit dl rm
rlcompleter.py	7097	0644	edit dl rm
runpy.py	12052	0644	edit dl rm
sched.py	6442	0644	edit dl rm
secrets.py	2038	0644	edit dl rm
selectors.py	18561	0644	edit dl rm
shelve.py	8527	0644	edit dl rm
shlex.py	13325	0644	edit dl rm
shutil.py	51474	0644	edit dl rm
signal.py	2273	0644	edit dl rm
site.py	22336	0644	edit dl rm
sitecustomize.py	-	0	edit dl rm
smtpd.py	34709	0755	edit dl rm
smtplib.py	44804	0755	edit dl rm
sndhdr.py	7099	0644	edit dl rm
socket.py	35243	0644	edit dl rm
socketserver.py	27296	0644	edit dl rm
sre_compile.py	26695	0644	edit dl rm
sre_constants.py	7154	0644	edit dl rm
sre_parse.py	40230	0644	edit dl rm
ssl.py	52363	0644	edit dl rm
stat.py	5485	0644	edit dl rm
statistics.py	39690	0644	edit dl rm
string.py	10535	0644	edit dl rm
stringprep.py	12917	0644	edit dl rm
struct.py	257	0644	edit dl rm
subprocess.py	77330	0644	edit dl rm
sunau.py	18375	0644	edit dl rm
symbol.py	2109	0644	edit dl rm
symtable.py	8021	0644	edit dl rm
sysconfig.py	25035	0644	edit dl rm
tabnanny.py	11406	0755	edit dl rm
tarfile.py	95580	0755	edit dl rm
telnetlib.py	23254	0644	edit dl rm
tempfile.py	32920	0644	edit dl rm
textwrap.py	19407	0644	edit dl rm
this.py	1003	0644	edit dl rm
threading.py	50820	0644	edit dl rm
timeit.py	13480	0755	edit dl rm
token.py	2368	0644	edit dl rm
tokenize.py	25841	0644	edit dl rm
trace.py	29858	0755	edit dl rm
traceback.py	23611	0644	edit dl rm
tracemalloc.py	17076	0644	edit dl rm
tty.py	879	0644	edit dl rm
turtle.py	143716	0644	edit dl rm
types.py	9713	0644	edit dl rm
typing.py	68962	0644	edit dl rm
uu.py	6957	0755	edit dl rm
uuid.py	30466	0644	edit dl rm
warnings.py	19688	0644	edit dl rm
wave.py	18230	0644	edit dl rm
weakref.py	21387	0644	edit dl rm
webbrowser.py	24083	0755	edit dl rm
xdrlib.py	5913	0644	edit dl rm
zipapp.py	7535	0644	edit dl rm
zipfile.py	89135	0644	edit dl rm
zipimport.py	30765	0644	edit dl rm
_bootlocale.py	1801	0644	edit dl rm
_collections_abc.py	26100	0644	edit dl rm
_compat_pickle.py	8749	0644	edit dl rm
_compression.py	5340	0644	edit dl rm
_dummy_thread.py	6027	0644	edit dl rm
_markupbase.py	14598	0644	edit dl rm
_osx_support.py	21774	0644	edit dl rm
_pydecimal.py	228666	0644	edit dl rm
_pyio.py	93177	0644	edit dl rm
_py_abc.py	6189	0644	edit dl rm
_sitebuiltins.py	3115	0644	edit dl rm
_strptime.py	25268	0644	edit dl rm
_sysconfigdata__linux_x86_64-linux-gnu.py	25834	0644	edit dl rm
_sysconfigdata__x86_64-linux-gnu.py	25834	0644	edit dl rm
_threading_local.py	7220	0644	edit dl rm
_weakrefset.py	5735	0644	edit dl rm
__future__.py	5147	0644	edit dl rm
__phello__.foo.py	64	0644	edit dl rm

Edit: /snap/core20/2769/usr/lib/python3.8/tokenize.py (25841B)

"""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
import itertools as _itertools
import re
import sys
from token import *
from token import EXACT_TOKEN_TYPES

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

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

# 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)

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 _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 == 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
    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)
    empty = _itertools.repeat(b"")
    rl_gen = _itertools.chain(consumed, iter(readline, b""), empty)
    return _tokenize(rl_gen.__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), '')
    last_line = b''
    line = b''
    while True:                                # loop over lines in stream
        try:
            # We capture the value of the line variable here because
            # readline uses the empty string '' to signal end of input,
            # hence `line` itself will always be overwritten at the end
            # of this loop.
            last_line = line
            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')
                    yield TokenInfo(COMMENT, comment_token,
                           (lnum, pos), (lnum, pos + len(comment_token)), line)
                    pos += len(comment_token)

yield TokenInfo(NL, 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':
                    if parenlev > 0:
                        yield TokenInfo(NL, token, spos, epos, line)
                    else:
                        yield TokenInfo(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

# Check up to the first 3 chars of the token to see if
                #  they're in the single_quoted set. If so, they start
                #  a string.
                # We're using the first 3, because we're looking for
                #  "rb'" (for example) at the start of the token. If
                #  we switch to longer prefixes, this needs to be
                #  adjusted.
                # Note that initial == token[:1].
                # Also note that single quote checking must come after
                #  triple quote checking (above).
                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)
                        # Again, using the first 3 chars of the
                        #  token. This is looking for the matching end
                        #  regex for the correct type of quote
                        #  character. So it's really looking for
                        #  endpats["'"] or endpats['"'], by trying to
                        #  skip string prefix characters, if any.
                        endprog = _compile(endpats.get(initial) or
                                           endpats.get(token[1]) or
                                           endpats.get(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

# Add an implicit NEWLINE if the input doesn't end in one
    if last_line and last_line[-1] not in '\r\n':
        yield TokenInfo(NEWLINE, '', (lnum - 1, len(last_line)), (lnum - 1, len(last_line) + 1), '')
    for indent in indents[1:]:                 # pop remaining indent levels
        yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')
    yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')

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 _tokenize(readline, None)

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 = _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()

cmd: