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
python类string()的实例源码
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 token_repr(tok_type, string):
"""Returns a human-friendly representation of a token with the given type and string."""
# repr() prefixes unicode with 'u' on Python2 but not Python3; strip it out for consistency.
return '%s:%s' % (token.tok_name[tok_type], repr(string).lstrip('u'))
def __str__(self):
return token_repr(self.type, self.string)
def match_token(token, tok_type, tok_str=None):
"""Returns true if token is of the given type and, if a string is given, has that string."""
return token.type == tok_type and (tok_str is None or token.string == tok_str)
def expect_token(token, tok_type, tok_str=None):
"""
Verifies that the given token is of the expected type. If tok_str is given, the token string
is verified too. If the token doesn't match, raises an informative ValueError.
"""
if not match_token(token, tok_type, tok_str):
raise ValueError("Expected token %s, got %s on line %s col %s" % (
token_repr(tok_type, tok_str), str(token),
token.start[0], token.start[1] + 1))
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))
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 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 __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))
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 _all_string_prefixes():
# The valid string prefixes. Only contain the lower case versions,
# and don't contain any permuations (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 = set([''])
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).
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 _all_string_prefixes():
# The valid string prefixes. Only contain the lower case versions,
# and don't contain any permuations (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 = set([''])
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).
def _all_string_prefixes():
# The valid string prefixes. Only contain the lower case versions,
# and don't contain any permuations (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 = set([''])
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).
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))
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 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 __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))
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 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 __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))
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 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 __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))
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 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)
