def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
python类BytesIO()的实例源码
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
#print formatter, 'using', formatter.encoding
realoutfile = formatter.encoding and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError, err:
if isinstance(err.args[0], str) and \
'unbound method format' in err.args[0]:
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if (isinstance(err.args[0], str) and
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0])):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if (isinstance(err.args[0], str) and
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0])):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
#print formatter, 'using', formatter.encoding
realoutfile = formatter.encoding and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError, err:
if isinstance(err.args[0], str) and \
'unbound method format' in err.args[0]:
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if (isinstance(err.args[0], str) and
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0])):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if isinstance(err.args[0], str) and \
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0]):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def get_tokens(self, text):
if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def format(tokens, formatter, outfile=None): # pylint: disable=redefined-builtin
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
realoutfile = getattr(formatter, 'encoding', None) and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError as err:
if (isinstance(err.args[0], str) and
('unbound method format' in err.args[0] or
'missing 1 required positional argument' in err.args[0])):
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
