NG4R3P

Linux 4gvps.4gvps.com 3.10.0-1127.18.2.vz7.163.46 #1 SMP Fri Nov 20 21:47:55 MSK 2020 x86_64
SOFT : Apache PHP : 7.4.33
/proc/self/root/opt/alt/python35/lib64/python3.5/

38.135.39.45

[ NAME ]	[ SIZE ]	[ PERM ]	[ DATE ]	[ ACT ]
+FILE +DIR
__pycache__	dir	drwxr-xr-x	2024-08-13 01:15	R D
asyncio	dir	drwxr-xr-x	2024-08-13 01:15	R D
collections	dir	drwxr-xr-x	2024-08-13 01:15	R D
concurrent	dir	drwxr-xr-x	2024-08-13 01:15	R D
config-3.5m	dir	drwxr-xr-x	2024-08-13 01:15	R D
ctypes	dir	drwxr-xr-x	2024-08-13 01:15	R D
curses	dir	drwxr-xr-x	2024-08-13 01:15	R D
dbm	dir	drwxr-xr-x	2024-08-13 01:15	R D
distutils	dir	drwxr-xr-x	2024-08-13 01:15	R D
email	dir	drwxr-xr-x	2024-08-13 01:15	R D
encodings	dir	drwxr-xr-x	2024-08-13 01:15	R D
ensurepip	dir	drwxr-xr-x	2024-08-13 01:15	R D
html	dir	drwxr-xr-x	2024-08-13 01:15	R D
http	dir	drwxr-xr-x	2024-08-13 01:15	R D
idlelib	dir	drwxr-xr-x	2024-08-13 01:15	R D
importlib	dir	drwxr-xr-x	2024-08-13 01:15	R D
json	dir	drwxr-xr-x	2024-08-13 01:15	R D
lib-dynload	dir	drwxr-xr-x	2024-08-13 01:15	R D
lib2to3	dir	drwxr-xr-x	2024-08-13 01:16	R D
logging	dir	drwxr-xr-x	2024-08-13 01:15	R D
multiprocessing	dir	drwxr-xr-x	2024-08-13 01:15	R D
plat-linux	dir	drwxr-xr-x	2024-08-13 01:15	R D
pydoc_data	dir	drwxr-xr-x	2024-08-13 01:15	R D
site-packages	dir	drwxr-xr-x	2024-08-13 01:16	R D
sqlite3	dir	drwxr-xr-x	2024-08-13 01:15	R D
test	dir	drwxr-xr-x	2024-08-13 01:15	R D
unittest	dir	drwxr-xr-x	2024-08-13 01:15	R D
urllib	dir	drwxr-xr-x	2024-08-13 01:15	R D
venv	dir	drwxr-xr-x	2024-08-13 01:15	R D
wsgiref	dir	drwxr-xr-x	2024-08-13 01:15	R D
xml	dir	drwxr-xr-x	2024-08-13 01:15	R D
xmlrpc	dir	drwxr-xr-x	2024-08-13 01:15	R D
__future__.py	4.728 KB	-rw-r--r--	2024-05-31 13:50	R E G D
__phello__.foo.py	0.063 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_bootlocale.py	1.271 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_collections_abc.py	24.213 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_compat_pickle.py	8.355 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_compression.py	5.215 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_dummy_thread.py	4.998 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_markupbase.py	14.256 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_osx_support.py	18.667 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_pydecimal.py	223.27 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_pyio.py	85.906 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_sitebuiltins.py	3.042 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_strptime.py	21.665 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_sysconfigdata.py	22.783 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_threading_local.py	7.236 KB	-rw-r--r--	2024-05-31 13:50	R E G D
_weakrefset.py	5.571 KB	-rw-r--r--	2024-05-31 13:50	R E G D
abc.py	8.426 KB	-rw-r--r--	2024-05-31 13:50	R E G D
aifc.py	31.218 KB	-rw-r--r--	2024-05-31 13:50	R E G D
antigravity.py	0.465 KB	-rw-r--r--	2024-05-31 13:50	R E G D
argparse.py	88.025 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ast.py	11.72 KB	-rw-r--r--	2024-05-31 13:50	R E G D
asynchat.py	11.69 KB	-rw-r--r--	2024-05-31 13:50	R E G D
asyncore.py	19.633 KB	-rw-r--r--	2024-05-31 13:50	R E G D
base64.py	20.041 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
bdb.py	22.807 KB	-rw-r--r--	2024-05-31 13:50	R E G D
binhex.py	13.627 KB	-rw-r--r--	2024-05-31 13:50	R E G D
bisect.py	2.534 KB	-rw-r--r--	2024-05-31 13:50	R E G D
bz2.py	12.133 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cProfile.py	5.199 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
calendar.py	22.459 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cgi.py	35.201 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
cgitb.py	11.741 KB	-rw-r--r--	2024-05-31 13:50	R E G D
chunk.py	5.298 KB	-rw-r--r--	2024-05-31 13:50	R E G D
cmd.py	14.512 KB	-rw-r--r--	2024-05-31 13:50	R E G D
code.py	9.881 KB	-rw-r--r--	2024-05-31 13:50	R E G D
codecs.py	35.382 KB	-rw-r--r--	2024-05-31 13:50	R E G D
codeop.py	5.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
colorsys.py	3.969 KB	-rw-r--r--	2024-05-31 13:50	R E G D
compileall.py	11.437 KB	-rw-r--r--	2024-05-31 13:50	R E G D
configparser.py	52.199 KB	-rw-r--r--	2024-05-31 13:50	R E G D
contextlib.py	12.159 KB	-rw-r--r--	2024-05-31 13:50	R E G D
copy.py	8.736 KB	-rw-r--r--	2024-05-31 13:50	R E G D
copyreg.py	6.673 KB	-rw-r--r--	2024-05-31 13:50	R E G D
crypt.py	1.835 KB	-rw-r--r--	2024-05-31 13:50	R E G D
csv.py	15.75 KB	-rw-r--r--	2024-05-31 13:50	R E G D
datetime.py	74.12 KB	-rw-r--r--	2024-05-31 13:50	R E G D
decimal.py	0.313 KB	-rw-r--r--	2024-05-31 13:50	R E G D
difflib.py	82.23 KB	-rw-r--r--	2024-05-31 13:50	R E G D
dis.py	16.943 KB	-rw-r--r--	2024-05-31 13:50	R E G D
doctest.py	101.598 KB	-rw-r--r--	2024-05-31 13:50	R E G D
dummy_threading.py	2.749 KB	-rw-r--r--	2024-05-31 13:50	R E G D
enum.py	21.705 KB	-rw-r--r--	2024-05-31 13:50	R E G D
filecmp.py	9.6 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fileinput.py	13.925 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fnmatch.py	3.089 KB	-rw-r--r--	2024-05-31 13:50	R E G D
formatter.py	14.788 KB	-rw-r--r--	2024-05-31 13:50	R E G D
fractions.py	24.035 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ftplib.py	34.132 KB	-rw-r--r--	2024-05-31 13:50	R E G D
functools.py	28.266 KB	-rw-r--r--	2024-05-31 13:50	R E G D
genericpath.py	4.262 KB	-rw-r--r--	2024-05-31 13:50	R E G D
getopt.py	7.313 KB	-rw-r--r--	2024-05-31 13:50	R E G D
getpass.py	5.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
gettext.py	21.025 KB	-rw-r--r--	2024-05-31 13:50	R E G D
glob.py	4.953 KB	-rw-r--r--	2024-05-31 13:50	R E G D
gzip.py	19.785 KB	-rw-r--r--	2024-05-31 13:50	R E G D
hashlib.py	7.792 KB	-rw-r--r--	2024-05-31 13:50	R E G D
heapq.py	22.392 KB	-rw-r--r--	2024-05-31 13:50	R E G D
hmac.py	4.944 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imaplib.py	50.96 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imghdr.py	3.67 KB	-rw-r--r--	2024-05-31 13:50	R E G D
imp.py	10.426 KB	-rw-r--r--	2024-05-31 13:50	R E G D
inspect.py	111.522 KB	-rw-r--r--	2024-05-31 13:50	R E G D
io.py	3.316 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ipaddress.py	73.958 KB	-rw-r--r--	2024-05-31 13:50	R E G D
keyword.py	2.17 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
linecache.py	5.188 KB	-rw-r--r--	2024-05-31 13:50	R E G D
locale.py	72.962 KB	-rw-r--r--	2024-05-31 13:50	R E G D
lzma.py	12.622 KB	-rw-r--r--	2024-05-31 13:50	R E G D
macpath.py	5.769 KB	-rw-r--r--	2024-05-31 13:50	R E G D
macurl2path.py	2.668 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mailbox.py	76.58 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mailcap.py	7.914 KB	-rw-r--r--	2024-05-31 13:50	R E G D
mimetypes.py	20.358 KB	-rw-r--r--	2024-05-31 13:50	R E G D
modulefinder.py	22.544 KB	-rw-r--r--	2024-05-31 13:50	R E G D
netrc.py	5.613 KB	-rw-r--r--	2024-05-31 13:50	R E G D
nntplib.py	42.068 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ntpath.py	22.259 KB	-rw-r--r--	2024-05-31 13:50	R E G D
nturl2path.py	2.387 KB	-rw-r--r--	2024-05-31 13:50	R E G D
numbers.py	10.003 KB	-rw-r--r--	2024-05-31 13:50	R E G D
opcode.py	5.747 KB	-rw-r--r--	2024-05-31 13:50	R E G D
operator.py	10.608 KB	-rw-r--r--	2024-05-31 13:50	R E G D
optparse.py	58.93 KB	-rw-r--r--	2024-05-31 13:50	R E G D
os.py	36.165 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pathlib.py	45.899 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pdb.py	59.716 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
pickle.py	54.859 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pickletools.py	89.61 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pipes.py	8.707 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pkgutil.py	20.854 KB	-rw-r--r--	2024-05-31 13:50	R E G D
platform.py	45.065 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
plistlib.py	31.064 KB	-rw-r--r--	2024-05-31 13:50	R E G D
poplib.py	14.372 KB	-rw-r--r--	2024-05-31 13:50	R E G D
posixpath.py	14.562 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pprint.py	20.371 KB	-rw-r--r--	2024-05-31 13:50	R E G D
profile.py	21.516 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
pstats.py	25.941 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pty.py	4.651 KB	-rw-r--r--	2024-05-31 13:50	R E G D
py_compile.py	7.013 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pyclbr.py	13.246 KB	-rw-r--r--	2024-05-31 13:50	R E G D
pydoc.py	101.223 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
queue.py	8.574 KB	-rw-r--r--	2024-05-31 13:50	R E G D
quopri.py	7.095 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
random.py	25.843 KB	-rw-r--r--	2024-05-31 13:50	R E G D
re.py	15.138 KB	-rw-r--r--	2024-05-31 13:50	R E G D
reprlib.py	5.211 KB	-rw-r--r--	2024-05-31 13:50	R E G D
rlcompleter.py	6.159 KB	-rw-r--r--	2024-05-31 13:50	R E G D
runpy.py	11.679 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sched.py	6.07 KB	-rw-r--r--	2024-05-31 13:50	R E G D
selectors.py	18.982 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shelve.py	8.328 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shlex.py	11.18 KB	-rw-r--r--	2024-05-31 13:50	R E G D
shutil.py	39.109 KB	-rw-r--r--	2024-05-31 13:50	R E G D
signal.py	2.073 KB	-rw-r--r--	2024-05-31 13:50	R E G D
site.py	21.005 KB	-rw-r--r--	2024-05-31 13:50	R E G D
smtpd.py	34.544 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
smtplib.py	42.612 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
sndhdr.py	6.268 KB	-rw-r--r--	2024-05-31 13:50	R E G D
socket.py	26.499 KB	-rw-r--r--	2024-05-31 13:50	R E G D
socketserver.py	24.088 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_compile.py	17.979 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_constants.py	6.661 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sre_parse.py	34.294 KB	-rw-r--r--	2024-05-31 13:50	R E G D
ssl.py	41.359 KB	-rw-r--r--	2024-05-31 13:50	R E G D
stat.py	4.92 KB	-rw-r--r--	2024-05-31 13:50	R E G D
statistics.py	19.075 KB	-rw-r--r--	2024-05-31 13:50	R E G D
string.py	11.576 KB	-rw-r--r--	2024-05-31 13:50	R E G D
stringprep.py	12.614 KB	-rw-r--r--	2024-05-31 13:50	R E G D
struct.py	0.251 KB	-rw-r--r--	2024-05-31 13:50	R E G D
subprocess.py	57.531 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sunau.py	17.671 KB	-rw-r--r--	2024-05-31 13:50	R E G D
symbol.py	2.057 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
symtable.py	7.022 KB	-rw-r--r--	2024-05-31 13:50	R E G D
sysconfig.py	23.889 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tabnanny.py	11.146 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
tarfile.py	90.889 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
telnetlib.py	22.477 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tempfile.py	26.012 KB	-rw-r--r--	2024-05-31 13:50	R E G D
textwrap.py	19.1 KB	-rw-r--r--	2024-05-31 13:50	R E G D
this.py	0.979 KB	-rw-r--r--	2024-05-31 13:50	R E G D
threading.py	47.878 KB	-rw-r--r--	2024-05-31 13:50	R E G D
timeit.py	12.112 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
token.py	3.003 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tokenize.py	27.139 KB	-rw-r--r--	2024-05-31 13:50	R E G D
trace.py	30.813 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
traceback.py	21.655 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tracemalloc.py	15.274 KB	-rw-r--r--	2024-05-31 13:50	R E G D
tty.py	0.858 KB	-rw-r--r--	2024-05-31 13:50	R E G D
types.py	8.593 KB	-rw-r--r--	2024-05-31 13:50	R E G D
typing.py	78.257 KB	-rw-r--r--	2024-05-31 13:50	R E G D
uu.py	6.607 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
uuid.py	22.716 KB	-rw-r--r--	2024-05-31 13:50	R E G D
warnings.py	15.479 KB	-rw-r--r--	2024-05-31 13:50	R E G D
wave.py	17.268 KB	-rw-r--r--	2024-05-31 13:50	R E G D
weakref.py	19.986 KB	-rw-r--r--	2024-05-31 13:50	R E G D
webbrowser.py	21.316 KB	-rwxr-xr-x	2024-05-31 13:50	R E G D
xdrlib.py	5.774 KB	-rw-r--r--	2024-05-31 13:50	R E G D
zipapp.py	6.989 KB	-rw-r--r--	2024-05-31 13:50	R E G D
zipfile.py	71.945 KB	-rw-r--r--	2024-05-31 13:50	R E G D
REQUEST EXIT

""" codecs -- Python Codec Registry, API and helpers. Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """#" import builtins, sys ### Registry and builtin stateless codec functions try: from _codecs import * except ImportError as why: raise SystemError('Failed to load the builtin codecs: %s' % why) __all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE", "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE", "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_LE", "BOM_UTF16_BE", "BOM_UTF32", "BOM_UTF32_LE", "BOM_UTF32_BE", "CodecInfo", "Codec", "IncrementalEncoder", "IncrementalDecoder", "StreamReader", "StreamWriter", "StreamReaderWriter", "StreamRecoder", "getencoder", "getdecoder", "getincrementalencoder", "getincrementaldecoder", "getreader", "getwriter", "encode", "decode", "iterencode", "iterdecode", "strict_errors", "ignore_errors", "replace_errors", "xmlcharrefreplace_errors", "backslashreplace_errors", "namereplace_errors", "register_error", "lookup_error"] ### Constants # # Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF) # and its possible byte string values # for UTF8/UTF16/UTF32 output and little/big endian machines # # UTF-8 BOM_UTF8 = b'\xef\xbb\xbf' # UTF-16, little endian BOM_LE = BOM_UTF16_LE = b'\xff\xfe' # UTF-16, big endian BOM_BE = BOM_UTF16_BE = b'\xfe\xff' # UTF-32, little endian BOM_UTF32_LE = b'\xff\xfe\x00\x00' # UTF-32, big endian BOM_UTF32_BE = b'\x00\x00\xfe\xff' if sys.byteorder == 'little': # UTF-16, native endianness BOM = BOM_UTF16 = BOM_UTF16_LE # UTF-32, native endianness BOM_UTF32 = BOM_UTF32_LE else: # UTF-16, native endianness BOM = BOM_UTF16 = BOM_UTF16_BE # UTF-32, native endianness BOM_UTF32 = BOM_UTF32_BE # Old broken names (don't use in new code) BOM32_LE = BOM_UTF16_LE BOM32_BE = BOM_UTF16_BE BOM64_LE = BOM_UTF32_LE BOM64_BE = BOM_UTF32_BE ### Codec base classes (defining the API) class CodecInfo(tuple): """Codec details when looking up the codec registry""" # Private API to allow Python 3.4 to blacklist the known non-Unicode # codecs in the standard library. A more general mechanism to # reliably distinguish test encodings from other codecs will hopefully # be defined for Python 3.5 # # See http://bugs.python.org/issue19619 _is_text_encoding = True # Assume codecs are text encodings by default def __new__(cls, encode, decode, streamreader=None, streamwriter=None, incrementalencoder=None, incrementaldecoder=None, name=None, *, _is_text_encoding=None): self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter)) self.name = name self.encode = encode self.decode = decode self.incrementalencoder = incrementalencoder self.incrementaldecoder = incrementaldecoder self.streamwriter = streamwriter self.streamreader = streamreader if _is_text_encoding is not None: self._is_text_encoding = _is_text_encoding return self def __repr__(self): return "<%s.%s object for encoding %s at %#x>" % \ (self.__class__.__module__, self.__class__.__qualname__, self.name, id(self)) class Codec: """ Defines the interface for stateless encoders/decoders. The .encode()/.decode() methods may use different error handling schemes by providing the errors argument. These string values are predefined: 'strict' - raise a ValueError error (or a subclass) 'ignore' - ignore the character and continue with the next 'replace' - replace with a suitable replacement character; Python will use the official U+FFFD REPLACEMENT CHARACTER for the builtin Unicode codecs on decoding and '?' on encoding. 'surrogateescape' - replace with private code points U+DCnn. 'xmlcharrefreplace' - Replace with the appropriate XML character reference (only for encoding). 'backslashreplace' - Replace with backslashed escape sequences. 'namereplace' - Replace with \\N{...} escape sequences (only for encoding). The set of allowed values can be extended via register_error. """ def encode(self, input, errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling. The method may not store state in the Codec instance. Use StreamWriter for codecs which have to keep state in order to make encoding efficient. The encoder must be able to handle zero length input and return an empty object of the output object type in this situation. """ raise NotImplementedError def decode(self, input, errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling. The method may not store state in the Codec instance. Use StreamReader for codecs which have to keep state in order to make decoding efficient. The decoder must be able to handle zero length input and return an empty object of the output object type in this situation. """ raise NotImplementedError class IncrementalEncoder(object): """ An IncrementalEncoder encodes an input in multiple steps. The input can be passed piece by piece to the encode() method. The IncrementalEncoder remembers the state of the encoding process between calls to encode(). """ def __init__(self, errors='strict'): """ Creates an IncrementalEncoder instance. The IncrementalEncoder may use different error handling schemes by providing the errors keyword argument. See the module docstring for a list of possible values. """ self.errors = errors self.buffer = "" def encode(self, input, final=False): """ Encodes input and returns the resulting object. """ raise NotImplementedError def reset(self): """ Resets the encoder to the initial state. """ def getstate(self): """ Return the current state of the encoder. """ return 0 def setstate(self, state): """ Set the current state of the encoder. state must have been returned by getstate(). """ class BufferedIncrementalEncoder(IncrementalEncoder): """ This subclass of IncrementalEncoder can be used as the baseclass for an incremental encoder if the encoder must keep some of the output in a buffer between calls to encode(). """ def __init__(self, errors='strict'): IncrementalEncoder.__init__(self, errors) # unencoded input that is kept between calls to encode() self.buffer = "" def _buffer_encode(self, input, errors, final): # Overwrite this method in subclasses: It must encode input # and return an (output, length consumed) tuple raise NotImplementedError def encode(self, input, final=False): # encode input (taking the buffer into account) data = self.buffer + input (result, consumed) = self._buffer_encode(data, self.errors, final) # keep unencoded input until the next call self.buffer = data[consumed:] return result def reset(self): IncrementalEncoder.reset(self) self.buffer = "" def getstate(self): return self.buffer or 0 def setstate(self, state): self.buffer = state or "" class IncrementalDecoder(object): """ An IncrementalDecoder decodes an input in multiple steps. The input can be passed piece by piece to the decode() method. The IncrementalDecoder remembers the state of the decoding process between calls to decode(). """ def __init__(self, errors='strict'): """ Create an IncrementalDecoder instance. The IncrementalDecoder may use different error handling schemes by providing the errors keyword argument. See the module docstring for a list of possible values. """ self.errors = errors def decode(self, input, final=False): """ Decode input and returns the resulting object. """ raise NotImplementedError def reset(self): """ Reset the decoder to the initial state. """ def getstate(self): """ Return the current state of the decoder. This must be a (buffered_input, additional_state_info) tuple. buffered_input must be a bytes object containing bytes that were passed to decode() that have not yet been converted. additional_state_info must be a non-negative integer representing the state of the decoder WITHOUT yet having processed the contents of buffered_input. In the initial state and after reset(), getstate() must return (b"", 0). """ return (b"", 0) def setstate(self, state): """ Set the current state of the decoder. state must have been returned by getstate(). The effect of setstate((b"", 0)) must be equivalent to reset(). """ class BufferedIncrementalDecoder(IncrementalDecoder): """ This subclass of IncrementalDecoder can be used as the baseclass for an incremental decoder if the decoder must be able to handle incomplete byte sequences. """ def __init__(self, errors='strict'): IncrementalDecoder.__init__(self, errors) # undecoded input that is kept between calls to decode() self.buffer = b"" def _buffer_decode(self, input, errors, final): # Overwrite this method in subclasses: It must decode input # and return an (output, length consumed) tuple raise NotImplementedError def decode(self, input, final=False): # decode input (taking the buffer into account) data = self.buffer + input (result, consumed) = self._buffer_decode(data, self.errors, final) # keep undecoded input until the next call self.buffer = data[consumed:] return result def reset(self): IncrementalDecoder.reset(self) self.buffer = b"" def getstate(self): # additional state info is always 0 return (self.buffer, 0) def setstate(self, state): # ignore additional state info self.buffer = state[0] # # The StreamWriter and StreamReader class provide generic working # interfaces which can be used to implement new encoding submodules # very easily. See encodings/utf_8.py for an example on how this is # done. # class StreamWriter(Codec): def __init__(self, stream, errors='strict'): """ Creates a StreamWriter instance. stream must be a file-like object open for writing. The StreamWriter may use different error handling schemes by providing the errors keyword argument. These parameters are predefined: 'strict' - raise a ValueError (or a subclass) 'ignore' - ignore the character and continue with the next 'replace'- replace with a suitable replacement character 'xmlcharrefreplace' - Replace with the appropriate XML character reference. 'backslashreplace' - Replace with backslashed escape sequences. 'namereplace' - Replace with \\N{...} escape sequences. The set of allowed parameter values can be extended via register_error. """ self.stream = stream self.errors = errors def write(self, object): """ Writes the object's contents encoded to self.stream. """ data, consumed = self.encode(object, self.errors) self.stream.write(data) def writelines(self, list): """ Writes the concatenated list of strings to the stream using .write(). """ self.write(''.join(list)) def reset(self): """ Flushes and resets the codec buffers used for keeping state. Calling this method should ensure that the data on the output is put into a clean state, that allows appending of new fresh data without having to rescan the whole stream to recover state. """ pass def seek(self, offset, whence=0): self.stream.seek(offset, whence) if whence == 0 and offset == 0: self.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamReader(Codec): charbuffertype = str def __init__(self, stream, errors='strict'): """ Creates a StreamReader instance. stream must be a file-like object open for reading. The StreamReader may use different error handling schemes by providing the errors keyword argument. These parameters are predefined: 'strict' - raise a ValueError (or a subclass) 'ignore' - ignore the character and continue with the next 'replace'- replace with a suitable replacement character 'backslashreplace' - Replace with backslashed escape sequences; The set of allowed parameter values can be extended via register_error. """ self.stream = stream self.errors = errors self.bytebuffer = b"" self._empty_charbuffer = self.charbuffertype() self.charbuffer = self._empty_charbuffer self.linebuffer = None def decode(self, input, errors='strict'): raise NotImplementedError def read(self, size=-1, chars=-1, firstline=False): """ Decodes data from the stream self.stream and returns the resulting object. chars indicates the number of decoded code points or bytes to return. read() will never return more data than requested, but it might return less, if there is not enough available. size indicates the approximate maximum number of decoded bytes or code points to read for decoding. The decoder can modify this setting as appropriate. The default value -1 indicates to read and decode as much as possible. size is intended to prevent having to decode huge files in one step. If firstline is true, and a UnicodeDecodeError happens after the first line terminator in the input only the first line will be returned, the rest of the input will be kept until the next call to read(). The method should use a greedy read strategy, meaning that it should read as much data as is allowed within the definition of the encoding and the given size, e.g. if optional encoding endings or state markers are available on the stream, these should be read too. """ # If we have lines cached, first merge them back into characters if self.linebuffer: self.charbuffer = self._empty_charbuffer.join(self.linebuffer) self.linebuffer = None # read until we get the required number of characters (if available) while True: # can the request be satisfied from the character buffer? if chars >= 0: if len(self.charbuffer) >= chars: break elif size >= 0: if len(self.charbuffer) >= size: break # we need more data if size < 0: newdata = self.stream.read() else: newdata = self.stream.read(size) # decode bytes (those remaining from the last call included) data = self.bytebuffer + newdata if not data: break try: newchars, decodedbytes = self.decode(data, self.errors) except UnicodeDecodeError as exc: if firstline: newchars, decodedbytes = \ self.decode(data[:exc.start], self.errors) lines = newchars.splitlines(keepends=True) if len(lines)<=1: raise else: raise # keep undecoded bytes until the next call self.bytebuffer = data[decodedbytes:] # put new characters in the character buffer self.charbuffer += newchars # there was no data available if not newdata: break if chars < 0: # Return everything we've got result = self.charbuffer self.charbuffer = self._empty_charbuffer else: # Return the first chars characters result = self.charbuffer[:chars] self.charbuffer = self.charbuffer[chars:] return result def readline(self, size=None, keepends=True): """ Read one line from the input stream and return the decoded data. size, if given, is passed as size argument to the read() method. """ # If we have lines cached from an earlier read, return # them unconditionally if self.linebuffer: line = self.linebuffer[0] del self.linebuffer[0] if len(self.linebuffer) == 1: # revert to charbuffer mode; we might need more data # next time self.charbuffer = self.linebuffer[0] self.linebuffer = None if not keepends: line = line.splitlines(keepends=False)[0] return line readsize = size or 72 line = self._empty_charbuffer # If size is given, we call read() only once while True: data = self.read(readsize, firstline=True) if data: # If we're at a "\r" read one extra character (which might # be a "\n") to get a proper line ending. If the stream is # temporarily exhausted we return the wrong line ending. if (isinstance(data, str) and data.endswith("\r")) or \ (isinstance(data, bytes) and data.endswith(b"\r")): data += self.read(size=1, chars=1) line += data lines = line.splitlines(keepends=True) if lines: if len(lines) > 1: # More than one line result; the first line is a full line # to return line = lines[0] del lines[0] if len(lines) > 1: # cache the remaining lines lines[-1] += self.charbuffer self.linebuffer = lines self.charbuffer = None else: # only one remaining line, put it back into charbuffer self.charbuffer = lines[0] + self.charbuffer if not keepends: line = line.splitlines(keepends=False)[0] break line0withend = lines[0] line0withoutend = lines[0].splitlines(keepends=False)[0] if line0withend != line0withoutend: # We really have a line end # Put the rest back together and keep it until the next call self.charbuffer = self._empty_charbuffer.join(lines[1:]) + \ self.charbuffer if keepends: line = line0withend else: line = line0withoutend break # we didn't get anything or this was our only try if not data or size is not None: if line and not keepends: line = line.splitlines(keepends=False)[0] break if readsize < 8000: readsize *= 2 return line def readlines(self, sizehint=None, keepends=True): """ Read all lines available on the input stream and return them as a list. Line breaks are implemented using the codec's decoder method and are included in the list entries. sizehint, if given, is ignored since there is no efficient way to finding the true end-of-line. """ data = self.read() return data.splitlines(keepends) def reset(self): """ Resets the codec buffers used for keeping state. Note that no stream repositioning should take place. This method is primarily intended to be able to recover from decoding errors. """ self.bytebuffer = b"" self.charbuffer = self._empty_charbuffer self.linebuffer = None def seek(self, offset, whence=0): """ Set the input stream's current position. Resets the codec buffers used for keeping state. """ self.stream.seek(offset, whence) self.reset() def __next__(self): """ Return the next decoded line from the input stream.""" line = self.readline() if line: return line raise StopIteration def __iter__(self): return self def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamReaderWriter: """ StreamReaderWriter instances allow wrapping streams which work in both read and write modes. The design is such that one can use the factory functions returned by the codec.lookup() function to construct the instance. """ # Optional attributes set by the file wrappers below encoding = 'unknown' def __init__(self, stream, Reader, Writer, errors='strict'): """ Creates a StreamReaderWriter instance. stream must be a Stream-like object. Reader, Writer must be factory functions or classes providing the StreamReader, StreamWriter interface resp. Error handling is done in the same way as defined for the StreamWriter/Readers. """ self.stream = stream self.reader = Reader(stream, errors) self.writer = Writer(stream, errors) self.errors = errors def read(self, size=-1): return self.reader.read(size) def readline(self, size=None): return self.reader.readline(size) def readlines(self, sizehint=None): return self.reader.readlines(sizehint) def __next__(self): """ Return the next decoded line from the input stream.""" return next(self.reader) def __iter__(self): return self def write(self, data): return self.writer.write(data) def writelines(self, list): return self.writer.writelines(list) def reset(self): self.reader.reset() self.writer.reset() def seek(self, offset, whence=0): self.stream.seek(offset, whence) self.reader.reset() if whence == 0 and offset == 0: self.writer.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) # these are needed to make "with codecs.open(...)" work properly def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamRecoder: """ StreamRecoder instances translate data from one encoding to another. They use the complete set of APIs returned by the codecs.lookup() function to implement their task. Data written to the StreamRecoder is first decoded into an intermediate format (depending on the "decode" codec) and then written to the underlying stream using an instance of the provided Writer class. In the other direction, data is read from the underlying stream using a Reader instance and then encoded and returned to the caller. """ # Optional attributes set by the file wrappers below data_encoding = 'unknown' file_encoding = 'unknown' def __init__(self, stream, encode, decode, Reader, Writer, errors='strict'): """ Creates a StreamRecoder instance which implements a two-way conversion: encode and decode work on the frontend (the data visible to .read() and .write()) while Reader and Writer work on the backend (the data in stream). You can use these objects to do transparent transcodings from e.g. latin-1 to utf-8 and back. stream must be a file-like object. encode and decode must adhere to the Codec interface; Reader and Writer must be factory functions or classes providing the StreamReader and StreamWriter interfaces resp. Error handling is done in the same way as defined for the StreamWriter/Readers. """ self.stream = stream self.encode = encode self.decode = decode self.reader = Reader(stream, errors) self.writer = Writer(stream, errors) self.errors = errors def read(self, size=-1): data = self.reader.read(size) data, bytesencoded = self.encode(data, self.errors) return data def readline(self, size=None): if size is None: data = self.reader.readline() else: data = self.reader.readline(size) data, bytesencoded = self.encode(data, self.errors) return data def readlines(self, sizehint=None): data = self.reader.read() data, bytesencoded = self.encode(data, self.errors) return data.splitlines(keepends=True) def __next__(self): """ Return the next decoded line from the input stream.""" data = next(self.reader) data, bytesencoded = self.encode(data, self.errors) return data def __iter__(self): return self def write(self, data): data, bytesdecoded = self.decode(data, self.errors) return self.writer.write(data) def writelines(self, list): data = ''.join(list) data, bytesdecoded = self.decode(data, self.errors) return self.writer.write(data) def reset(self): self.reader.reset() self.writer.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### Shortcuts def open(filename, mode='r', 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 be Unicode as well. Underlying encoded files are always opened in binary mode. The default file mode is 'r', meaning to open the file in 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 = builtins.open(filename, mode, buffering) if encoding is None: return file info = lookup(encoding) srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, 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. Data written to the wrapped file is decoded according to the given data_encoding and then encoded to the underlying file using file_encoding. The intermediate data type will usually be Unicode but depends on the specified codecs. Bytes read from the file are decoded using file_encoding and then passed back to the caller encoded 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 data_info = lookup(data_encoding) file_info = lookup(file_encoding) sr = StreamRecoder(file, data_info.encode, data_info.decode, file_info.streamreader, file_info.streamwriter, 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).encode 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).decode def getincrementalencoder(encoding): """ Lookup up the codec for the given encoding and return its IncrementalEncoder class or factory function. Raises a LookupError in case the encoding cannot be found or the codecs doesn't provide an incremental encoder. """ encoder = lookup(encoding).incrementalencoder if encoder is None: raise LookupError(encoding) return encoder def getincrementaldecoder(encoding): """ Lookup up the codec for the given encoding and return its IncrementalDecoder class or factory function. Raises a LookupError in case the encoding cannot be found or the codecs doesn't provide an incremental decoder. """ decoder = lookup(encoding).incrementaldecoder if decoder is None: raise LookupError(encoding) return decoder 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).streamreader 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).streamwriter def iterencode(iterator, encoding, errors='strict', **kwargs): """ Encoding iterator. Encodes the input strings from the iterator using an IncrementalEncoder. errors and kwargs are passed through to the IncrementalEncoder constructor. """ encoder = getincrementalencoder(encoding)(errors, **kwargs) for input in iterator: output = encoder.encode(input) if output: yield output output = encoder.encode("", True) if output: yield output def iterdecode(iterator, encoding, errors='strict', **kwargs): """ Decoding iterator. Decodes the input strings from the iterator using an IncrementalDecoder. errors and kwargs are passed through to the IncrementalDecoder constructor. """ decoder = getincrementaldecoder(encoding)(errors, **kwargs) for input in iterator: output = decoder.decode(input) if output: yield output output = decoder.decode(b"", True) if output: yield output ### 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. """ return {i:i for i in rng} 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 try: 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") namereplace_errors = lookup_error("namereplace") except LookupError: # In --disable-unicode builds, these error handler are missing strict_errors = None ignore_errors = None replace_errors = None xmlcharrefreplace_errors = None backslashreplace_errors = None namereplace_errors = None # 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')