|
|
楼主 |
发表于 2004-5-16 09:09:22
|
显示全部楼层
ufo2000兄：多謝！我對比了好像跟你的一樣。
def open(filename, mode='rb', encoding=None, errors='strict', buffering=1):
""" Open an encoded file using the given mode and return
a wrapped version providing transparent encoding/decoding.
Note: The wrapped version will only accept the object format
defined by the codecs, i.e. Unicode objects for most builtin
codecs. Output is also codec dependent and will usually by
Unicode as well.
Files are always opened in binary mode, even if no binary mode
was specified. This is done to avoid data loss due to encodings
using 8-bit values. The default file mode is 'rb' meaning to
open the file in binary read mode.
encoding specifies the encoding which is to be used for the
file.
errors may be given to define the error handling. It defaults
to 'strict' which causes ValueErrors to be raised in case an
encoding error occurs.
buffering has the same meaning as for the builtin open() API.
It defaults to line buffered.
The returned wrapped file object provides an extra attribute
.encoding which allows querying the used encoding. This
attribute is only available if an encoding was specified as
parameter.
"""
if encoding is not None and \
'b' not in mode:
# Force opening of the file in binary mode
mode = mode + 'b'
file = __builtin__.open(filename, mode, buffering)
if encoding is None:
return file
(e, d, sr, sw) = lookup(encoding)
srw = StreamReaderWriter(file, sr, sw, errors)
# Add attributes to simplify introspection
srw.encoding = encoding
return srw
def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'):
""" Return a wrapped version of file which provides transparent
encoding translation.
Strings written to the wrapped file are interpreted according
to the given data_encoding and then written to the original
file as string using file_encoding. The intermediate encoding
will usually be Unicode but depends on the specified codecs.
Strings are read from the file using file_encoding and then
passed back to the caller as string using data_encoding.
If file_encoding is not given, it defaults to data_encoding.
errors may be given to define the error handling. It defaults
to 'strict' which causes ValueErrors to be raised in case an
encoding error occurs.
The returned wrapped file object provides two extra attributes
.data_encoding and .file_encoding which reflect the given
parameters of the same name. The attributes can be used for
introspection by Python programs.
"""
if file_encoding is None:
file_encoding = data_encoding
encode, decode = lookup(data_encoding)[:2]
Reader, Writer = lookup(file_encoding)[2:]
sr = StreamRecoder(file,
encode, decode, Reader, Writer,
errors)
# Add attributes to simplify introspection
sr.data_encoding = data_encoding
sr.file_encoding = file_encoding
return sr
### Helpers for codec lookup
def getencoder(encoding):
""" Lookup up the codec for the given encoding and return
its encoder function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding)[0]
def getdecoder(encoding):
""" Lookup up the codec for the given encoding and return
its decoder function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding)[1]
def getreader(encoding):
""" Lookup up the codec for the given encoding and return
its StreamReader class or factory function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding)[2]
def getwriter(encoding):
""" Lookup up the codec for the given encoding and return
its StreamWriter class or factory function.
Raises a LookupError in case the encoding cannot be found.
"""
return lookup(encoding)[3]
### Helpers for charmap-based codecs
def make_identity_dict(rng):
""" make_identity_dict(rng) -> dict
Return a dictionary where elements of the rng sequence are
mapped to themselves.
"""
res = {}
for i in rng:
res=i
return res
def make_encoding_map(decoding_map):
""" Creates an encoding map from a decoding map.
If a target mapping in the decoding map occurs multiple
times, then that target is mapped to None (undefined mapping),
causing an exception when encountered by the charmap codec
during translation.
One example where this happens is cp875.py which decodes
multiple character to \u001a.
"""
m = {}
for k,v in decoding_map.items():
if not v in m:
m[v] = k
else:
m[v] = None
return m
### error handlers
strict_errors = lookup_error("strict")
ignore_errors = lookup_error("ignore")
replace_errors = lookup_error("replace")
xmlcharrefreplace_errors = lookup_error("xmlcharrefreplace")
backslashreplace_errors = lookup_error("backslashreplace")
# Tell modulefinder that using codecs probably needs the encodings
# package
_false = 0
if _false:
import encodings
### Tests
if __name__ == '__main__':
# Make stdout translate Latin-1 output into UTF-8 output
sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8')
# Have stdin translate Latin-1 input into UTF-8 input
sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1')
file = __builtin__.open(filename, mode, buffering) |
|
IP卡
狗仔卡
发表于 2004-5-16 08:42:07
显身卡