
lib-python.2.7.gzip.py Maven / Gradle / Ivy
"""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
import zlib
import io
import __builtin__
__all__ = ["GzipFile","open"]
FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16
READ, WRITE = 1, 2
def write32u(output, value):
# The L format writes the bit pattern correctly whether signed
# or unsigned.
output.write(struct.pack("':
filename = fileobj.name
else:
filename = ''
if mode is None:
if hasattr(fileobj, 'mode'): mode = fileobj.mode
else: mode = 'rb'
if mode[0:1] == 'r':
self.mode = READ
# Set flag indicating start of a new member
self._new_member = True
# Buffer data read from gzip file. extrastart is offset in
# stream where buffer starts. extrasize is number of
# bytes remaining in buffer from current stream position.
self.extrabuf = ""
self.extrasize = 0
self.extrastart = 0
self.name = filename
# Starts small, scales exponentially
self.min_readsize = 100
elif mode[0:1] == 'w' or mode[0:1] == 'a':
self.mode = WRITE
self._init_write(filename)
self.compress = zlib.compressobj(compresslevel,
zlib.DEFLATED,
-zlib.MAX_WBITS,
zlib.DEF_MEM_LEVEL,
0)
else:
raise IOError, "Mode " + mode + " not supported"
self.fileobj = fileobj
self.offset = 0
self.mtime = mtime
if self.mode == WRITE:
self._write_gzip_header()
@property
def filename(self):
import warnings
warnings.warn("use the name attribute", DeprecationWarning, 2)
if self.mode == WRITE and self.name[-3:] != ".gz":
return self.name + ".gz"
return self.name
def __repr__(self):
s = repr(self.fileobj)
return ''
def _check_closed(self):
"""Raises a ValueError if the underlying file object has been closed.
"""
if self.closed:
raise ValueError('I/O operation on closed file.')
def _init_write(self, filename):
self.name = filename
self.crc = zlib.crc32("") & 0xffffffffL
self.size = 0
self.writebuf = []
self.bufsize = 0
def _write_gzip_header(self):
self.fileobj.write('\037\213') # magic header
self.fileobj.write('\010') # compression method
fname = os.path.basename(self.name)
if fname.endswith(".gz"):
fname = fname[:-3]
flags = 0
if fname:
flags = FNAME
self.fileobj.write(chr(flags))
mtime = self.mtime
if mtime is None:
mtime = time.time()
write32u(self.fileobj, long(mtime))
self.fileobj.write('\002')
self.fileobj.write('\377')
if fname:
self.fileobj.write(fname + '\000')
def _init_read(self):
self.crc = zlib.crc32("") & 0xffffffffL
self.size = 0
def _read_exact(self, n):
data = self.fileobj.read(n)
while len(data) < n:
b = self.fileobj.read(n - len(data))
if not b:
raise EOFError("Compressed file ended before the "
"end-of-stream marker was reached")
data += b
return data
def _read_gzip_header(self):
magic = self.fileobj.read(2)
if magic != '\037\213':
raise IOError, 'Not a gzipped file'
method, flag, self.mtime = struct.unpack(" 0:
self.size = self.size + len(data)
self.crc = zlib.crc32(data, self.crc) & 0xffffffffL
self.fileobj.write( self.compress.compress(data) )
self.offset += len(data)
return len(data)
def read(self, size=-1):
self._check_closed()
if self.mode != READ:
import errno
raise IOError(errno.EBADF, "read() on write-only GzipFile object")
if self.extrasize <= 0 and self.fileobj is None:
return ''
readsize = 1024
if size < 0: # get the whole thing
while self._read(readsize):
readsize = min(self.max_read_chunk, readsize * 2)
size = self.extrasize
else: # just get some more of it
while size > self.extrasize:
if not self._read(readsize):
if size > self.extrasize:
size = self.extrasize
break
readsize = min(self.max_read_chunk, readsize * 2)
offset = self.offset - self.extrastart
chunk = self.extrabuf[offset: offset + size]
self.extrasize = self.extrasize - size
self.offset += size
return chunk
def _unread(self, buf):
self.extrasize = len(buf) + self.extrasize
self.offset -= len(buf)
def _read(self, size=1024):
if self.fileobj is None:
return False
if self._new_member:
# If the _new_member flag is set, we have to
# jump to the next member, if there is one.
#
# First, check if we're at the end of the file;
# if so, it's time to stop; no more members to read.
pos = self.fileobj.tell() # Save current position
self.fileobj.seek(0, 2) # Seek to end of file
if pos == self.fileobj.tell():
return False
else:
self.fileobj.seek( pos ) # Return to original position
self._init_read()
self._read_gzip_header()
self.decompress = zlib.decompressobj(-zlib.MAX_WBITS)
self._new_member = False
# Read a chunk of data from the file
buf = self.fileobj.read(size)
# If the EOF has been reached, flush the decompression object
# and mark this object as finished.
if buf == "":
uncompress = self.decompress.flush()
self.fileobj.seek(-len(self.decompress.unused_data), 1)
self._read_eof()
self._add_read_data( uncompress )
return False
uncompress = self.decompress.decompress(buf)
self._add_read_data( uncompress )
if self.decompress.unused_data != "":
# Ending case: we've come to the end of a member in the file,
# so seek back to the start of the unused data, finish up
# this member, and read a new gzip header.
# (The number of bytes to seek back is the length of the unused
# data)
self.fileobj.seek(-len(self.decompress.unused_data), 1)
# Check the CRC and file size, and set the flag so we read
# a new member on the next call
self._read_eof()
self._new_member = True
return True
def _add_read_data(self, data):
self.crc = zlib.crc32(data, self.crc) & 0xffffffffL
offset = self.offset - self.extrastart
self.extrabuf = self.extrabuf[offset:] + data
self.extrasize = self.extrasize + len(data)
self.extrastart = self.offset
self.size = self.size + len(data)
def _read_eof(self):
# 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(" 0:
self.extrasize -= i - offset
self.offset += i - offset
return self.extrabuf[offset: i]
size = sys.maxint
readsize = self.min_readsize
else:
readsize = size
bufs = []
while size != 0:
c = self.read(readsize)
i = c.find('\n')
# We set i=size to break out of the loop under two
# conditions: 1) there's no newline, and the chunk is
# larger than size, or 2) there is a newline, but the
# resulting line would be longer than 'size'.
if (size <= i) or (i == -1 and len(c) > size):
i = size - 1
if i >= 0 or c == '':
bufs.append(c[:i + 1]) # Add portion of last chunk
self._unread(c[i + 1:]) # Push back rest of chunk
break
# Append chunk to list, decrease 'size',
bufs.append(c)
size = size - len(c)
readsize = min(size, readsize * 2)
if readsize > self.min_readsize:
self.min_readsize = min(readsize, self.min_readsize * 2, 512)
return ''.join(bufs) # Return resulting line
def _test():
# Act like gzip; with -d, act like gunzip.
# The input file is not deleted, however, nor are any other gzip
# options or features supported.
args = sys.argv[1:]
decompress = args and args[0] == "-d"
if decompress:
args = args[1:]
if not args:
args = ["-"]
for arg in args:
if decompress:
if arg == "-":
f = GzipFile(filename="", mode="rb", fileobj=sys.stdin)
g = sys.stdout
else:
if arg[-3:] != ".gz":
print "filename doesn't end in .gz:", repr(arg)
continue
f = open(arg, "rb")
g = __builtin__.open(arg[:-3], "wb")
else:
if arg == "-":
f = sys.stdin
g = GzipFile(filename="", mode="wb", fileobj=sys.stdout)
else:
f = __builtin__.open(arg, "rb")
g = open(arg + ".gz", "wb")
while True:
chunk = f.read(1024)
if not chunk:
break
g.write(chunk)
if g is not sys.stdout:
g.close()
if f is not sys.stdin:
f.close()
if __name__ == '__main__':
_test()
© 2015 - 2025 Weber Informatics LLC | Privacy Policy