"""Functions that read and write gzipped files.
The user of the file doesn't have to worry about the compression,
but random access is not allowed."""
# based on Andrew Kuchling's minigzip.py distributed with the zlib module
import struct, sys, time, os
__all__ = ["GzipFile", "open", "compress", "decompress"]
FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16
def open(filename, mode="rb", compresslevel=9,
encoding=None, errors=None, newline=None):
"""Open a gzip-compressed file in binary or text mode.
The filename argument can be an actual filename (a str or bytes object), or
an existing file object to read from or write to.
The mode argument can be "r", "rb", "w", "wb", "x", "xb", "a" or "ab" for
binary mode, or "rt", "wt", "xt" or "at" for text mode. The default mode is
"rb", and the default compresslevel is 9.
For binary mode, this function is equivalent to the GzipFile constructor:
GzipFile(filename, mode, compresslevel). In this case, the encoding, errors
and newline arguments must not be provided.
For text mode, a GzipFile object is created, and wrapped in an
io.TextIOWrapper instance with the specified encoding, error handling
behavior, and line ending(s).
raise ValueError("Invalid mode: %r" % (mode,))
raise ValueError("Argument 'encoding' not supported in binary mode")
raise ValueError("Argument 'errors' not supported in binary mode")
raise ValueError("Argument 'newline' not supported in binary mode")
gz_mode = mode.replace("t", "")
if isinstance(filename, (str, bytes, os.PathLike)):
binary_file = GzipFile(filename, gz_mode, compresslevel)
elif hasattr(filename, "read") or hasattr(filename, "write"):
binary_file = GzipFile(None, gz_mode, compresslevel, filename)
raise TypeError("filename must be a str or bytes object, or a file")
return io.TextIOWrapper(binary_file, encoding, errors, newline)
def write32u(output, value):
# The L format writes the bit pattern correctly whether signed
output.write(struct.pack("<L", value))
"""Minimal read-only file object that prepends a string to the contents
of an actual file. Shouldn't be used outside of gzip.py, as it lacks
essential functionality."""
def __init__(self, f, prepend=b''):
self._length = len(prepend)
return self.file.read(size)
if self._read + size <= self._length:
return self._buffer[read:self._read]
return self._buffer[read:] + \
self.file.read(size-self._length+read)
def prepend(self, prepend=b''):
else: # Assume data was read since the last prepend() call
self._read -= len(prepend)
self._length = len(self._buffer)
return self.file.seek(off)
return True # Allows fast-forwarding even in unseekable streams
class GzipFile(_compression.BaseStream):
"""The GzipFile class simulates most of the methods of a file object with
the exception of the truncate() method.
This class only supports opening files in binary mode. If you need to open a
compressed file in text mode, use the gzip.open() function.
# Overridden with internal file object to be closed, if only a filename
def __init__(self, filename=None, mode=None,
compresslevel=9, fileobj=None, mtime=None):
"""Constructor for the GzipFile class.
At least one of fileobj and filename must be given a
The new class instance is based on fileobj, which can be a regular
file, an io.BytesIO object, or any other object which simulates a file.
It defaults to None, in which case filename is opened to provide
When fileobj is not None, the filename argument is only used to be
included in the gzip file header, which may include the original
filename of the uncompressed file. It defaults to the filename of
fileobj, if discernible; otherwise, it defaults to the empty string,
and in this case the original filename is not included in the header.
The mode argument can be any of 'r', 'rb', 'a', 'ab', 'w', 'wb', 'x', or
'xb' depending on whether the file will be read or written. The default
is the mode of fileobj if discernible; otherwise, the default is 'rb'.
A mode of 'r' is equivalent to one of 'rb', and similarly for 'w' and
'wb', 'a' and 'ab', and 'x' and 'xb'.
The compresslevel argument is an integer from 0 to 9 controlling the
level of compression; 1 is fastest and produces the least compression,
and 9 is slowest and produces the most compression. 0 is no compression
at all. The default is 9.
The mtime argument is an optional numeric timestamp to be written
to the last modification time field in the stream when compressing.
If omitted or None, the current time is used.
if mode and ('t' in mode or 'U' in mode):
raise ValueError("Invalid mode: {!r}".format(mode))
if mode and 'b' not in mode:
fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
filename = getattr(fileobj, 'name', '')
if not isinstance(filename, (str, bytes)):
filename = os.fspath(filename)
mode = getattr(fileobj, 'mode', 'rb')
raw = _GzipReader(fileobj)
self._buffer = io.BufferedReader(raw)
elif mode.startswith(('w', 'a', 'x')):
self._init_write(filename)
self.compress = zlib.compressobj(compresslevel,
self._write_mtime = mtime
raise ValueError("Invalid mode: {!r}".format(mode))
self._write_gzip_header()
warnings.warn("use the name attribute", DeprecationWarning, 2)
if self.mode == WRITE and self.name[-3:] != ".gz":
"""Last modification time read from stream, or None"""
return self._buffer.raw._last_mtime
return '<gzip ' + s[1:-1] + ' ' + hex(id(self)) + '>'
def _init_write(self, filename):
self.crc = zlib.crc32(b"")
self.offset = 0 # Current file offset for seek(), tell(), etc
def _write_gzip_header(self):
self.fileobj.write(b'\037\213') # magic header
self.fileobj.write(b'\010') # compression method
# RFC 1952 requires the FNAME field to be Latin-1. Do not
# include filenames that cannot be represented that way.
fname = os.path.basename(self.name)
if not isinstance(fname, bytes):
fname = fname.encode('latin-1')
if fname.endswith(b'.gz'):
except UnicodeEncodeError:
self.fileobj.write(chr(flags).encode('latin-1'))
mtime = self._write_mtime
write32u(self.fileobj, int(mtime))
self.fileobj.write(b'\002')
self.fileobj.write(b'\377')
self.fileobj.write(fname + b'\000')
raise OSError(errno.EBADF, "write() on read-only GzipFile object")
raise ValueError("write() on closed GzipFile object")
if isinstance(data, bytes):
# accept any data that supports the buffer protocol
self.fileobj.write(self.compress.compress(data))
self.crc = zlib.crc32(data, self.crc)
raise OSError(errno.EBADF, "read() on write-only GzipFile object")
return self._buffer.read(size)
def read1(self, size=-1):
"""Implements BufferedIOBase.read1()
Reads up to a buffer's worth of data is size is negative."""
raise OSError(errno.EBADF, "read1() on write-only GzipFile object")
size = io.DEFAULT_BUFFER_SIZE
return self._buffer.read1(size)
raise OSError(errno.EBADF, "peek() on write-only GzipFile object")
return self._buffer.peek(n)
return self.fileobj is None
fileobj.write(self.compress.flush())
write32u(fileobj, self.crc)
# self.size may exceed 2GB, or even 4GB
write32u(fileobj, self.size & 0xffffffff)
myfileobj = self.myfileobj
def flush(self,zlib_mode=zlib.Z_SYNC_FLUSH):
# Ensure the compressor's buffer is flushed
self.fileobj.write(self.compress.flush(zlib_mode))
"""Invoke the underlying file object's fileno() method.
This will raise AttributeError if the underlying file object
doesn't support fileno().
return self.fileobj.fileno()
'''Return the uncompressed stream file position indicator to the
raise OSError("Can't rewind in write mode")
return self.mode == WRITE
def seek(self, offset, whence=io.SEEK_SET):
if whence != io.SEEK_SET:
if whence == io.SEEK_CUR:
offset = self.offset + offset
raise ValueError('Seek from end not supported')
raise OSError('Negative seek in write mode')
count = offset - self.offset
for i in range(count // 1024):
self.write(b'\0' * (count % 1024))
return self._buffer.seek(offset, whence)
def readline(self, size=-1):
return self._buffer.readline(size)
class _GzipReader(_compression.DecompressReader):
super().__init__(_PaddedFile(fp), zlib.decompressobj,
# Set flag indicating start of a new member
self._crc = zlib.crc32(b"")
self._stream_size = 0 # Decompressed size of unconcatenated stream
def _read_exact(self, n):
'''Read exactly *n* bytes from `self._fp`
This method is required because self._fp may be unbuffered,
b = self._fp.read(n - len(data))
raise EOFError("Compressed file ended before the "
"end-of-stream marker was reached")
def _read_gzip_header(self):
raise OSError('Not a gzipped file (%r)' % magic)
self._last_mtime) = struct.unpack("<BBIxx", self._read_exact(8))
raise OSError('Unknown compression method')
# Read & discard the extra field, if present
extra_len, = struct.unpack("<H", self._read_exact(2))
self._read_exact(extra_len)
# Read and discard a null-terminated string containing the filename
# Read and discard a null-terminated string containing a comment
self._read_exact(2) # Read & discard the 16-bit header CRC
# size=0 is special because decompress(max_length=0) is not supported
# For certain input data, a single
# call to decompress() may not return
# any data. In this case, retry until we get some data or reach EOF.
if self._decompressor.eof:
# Ending case: we've come to the end of a member in the file,
# so finish up this member, and read a new gzip header.
# Check the CRC and file size, and set the flag so we read
self._decompressor = self._decomp_factory(
# If the _new_member flag is set, we have to
# jump to the next member, if there is one.
if not self._read_gzip_header():
# Read a chunk of data from the file
buf = self._fp.read(io.DEFAULT_BUFFER_SIZE)
uncompress = self._decompressor.decompress(buf, size)
if self._decompressor.unconsumed_tail != b"":
self._fp.prepend(self._decompressor.unconsumed_tail)
elif self._decompressor.unused_data != b"":
# Prepend the already read bytes to the fileobj so they can
# be seen by _read_eof() and _read_gzip_header()
self._fp.prepend(self._decompressor.unused_data)
raise EOFError("Compressed file ended before the "
"end-of-stream marker was reached")
self._add_read_data( uncompress )
self._pos += len(uncompress)
def _add_read_data(self, data):
self._crc = zlib.crc32(data, self._crc)
self._stream_size = self._stream_size + len(data)
# We've read to the end of the file
# We check the that the computed CRC and size of the
# uncompressed data matches the stored values. Note that the size
# stored is the true file size mod 2**32.
crc32, isize = struct.unpack("<II", self._read_exact(8))
raise OSError("CRC check failed %s != %s" % (hex(crc32),
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
