"""Interface to the libbzip2 compression library.
This module provides a file interface, classes for incremental
(de)compression, and functions for one-shot (de)compression.
__all__ = ["BZ2File", "BZ2Compressor", "BZ2Decompressor",
"open", "compress", "decompress"]
__author__ = "Nadeem Vawda <nadeem.vawda@gmail.com>"
from builtins import open as _builtin_open
from threading import RLock
from _bz2 import BZ2Compressor, BZ2Decompressor
class BZ2File(_compression.BaseStream):
"""A file object providing transparent bzip2 (de)compression.
A BZ2File can act as a wrapper for an existing file object, or refer
directly to a named file on disk.
Note that BZ2File provides a *binary* file interface - data read is
returned as bytes, and data to be written should be given as bytes.
def __init__(self, filename, mode="r", buffering=_sentinel, compresslevel=9):
"""Open a bzip2-compressed file.
If filename is a str, bytes, or PathLike object, it gives the
name of the file to be opened. Otherwise, it should be a file
object, which will be used to read or write the compressed data.
mode can be 'r' for reading (default), 'w' for (over)writing,
'x' for creating exclusively, or 'a' for appending. These can
equivalently be given as 'rb', 'wb', 'xb', and 'ab'.
buffering is ignored since Python 3.0. Its use is deprecated.
If mode is 'w', 'x' or 'a', compresslevel can be a number between 1
and 9 specifying the level of compression: 1 produces the least
compression, and 9 (default) produces the most compression.
If mode is 'r', the input file may be the concatenation of
multiple compressed streams.
# This lock must be recursive, so that BufferedIOBase's
# writelines() does not deadlock.
self._mode = _MODE_CLOSED
if buffering is not _sentinel:
warnings.warn("Use of 'buffering' argument is deprecated and ignored "
if not (1 <= compresslevel <= 9):
raise ValueError("compresslevel must be between 1 and 9")
if mode in ("", "r", "rb"):
elif mode in ("w", "wb"):
self._compressor = BZ2Compressor(compresslevel)
elif mode in ("x", "xb"):
self._compressor = BZ2Compressor(compresslevel)
elif mode in ("a", "ab"):
self._compressor = BZ2Compressor(compresslevel)
raise ValueError("Invalid mode: %r" % (mode,))
if isinstance(filename, (str, bytes, os.PathLike)):
self._fp = _builtin_open(filename, mode)
elif hasattr(filename, "read") or hasattr(filename, "write"):
raise TypeError("filename must be a str, bytes, file or PathLike object")
if self._mode == _MODE_READ:
raw = _compression.DecompressReader(self._fp,
BZ2Decompressor, trailing_error=OSError)
self._buffer = io.BufferedReader(raw)
"""Flush and close the file.
May be called more than once without error. Once the file is
closed, any other operation on it will raise a ValueError.
if self._mode == _MODE_CLOSED:
if self._mode == _MODE_READ:
elif self._mode == _MODE_WRITE:
self._fp.write(self._compressor.flush())
self._mode = _MODE_CLOSED
"""True if this file is closed."""
return self._mode == _MODE_CLOSED
"""Return the file descriptor for the underlying file."""
"""Return whether the file supports seeking."""
return self.readable() and self._buffer.seekable()
"""Return whether the file was opened for reading."""
return self._mode == _MODE_READ
"""Return whether the file was opened for writing."""
return self._mode == _MODE_WRITE
"""Return buffered data without advancing the file position.
Always returns at least one byte of data, unless at EOF.
The exact number of bytes returned is unspecified.
# Relies on the undocumented fact that BufferedReader.peek()
# always returns at least one byte (except at EOF), independent
return self._buffer.peek(n)
"""Read up to size uncompressed bytes from the file.
If size is negative or omitted, read until EOF is reached.
Returns b'' if the file is already at EOF.
return self._buffer.read(size)
def read1(self, size=-1):
"""Read up to size uncompressed bytes, while trying to avoid
making multiple reads from the underlying stream. Reads up to a
buffer's worth of data if size is negative.
Returns b'' if the file is at EOF.
size = io.DEFAULT_BUFFER_SIZE
return self._buffer.read1(size)
Returns the number of bytes read (0 for EOF).
return self._buffer.readinto(b)
def readline(self, size=-1):
"""Read a line of uncompressed bytes from the file.
The terminating newline (if present) is retained. If size is
non-negative, no more than size bytes will be read (in which
case the line may be incomplete). Returns b'' if already at EOF.
if not isinstance(size, int):
if not hasattr(size, "__index__"):
raise TypeError("Integer argument expected")
return self._buffer.readline(size)
def readlines(self, size=-1):
"""Read a list of lines of uncompressed bytes from the file.
size can be specified to control the number of lines read: no
further lines will be read once the total size of the lines read
so far equals or exceeds size.
if not isinstance(size, int):
if not hasattr(size, "__index__"):
raise TypeError("Integer argument expected")
return self._buffer.readlines(size)
"""Write a byte string to the file.
Returns the number of uncompressed bytes written, which is
always len(data). Note that due to buffering, the file on disk
may not reflect the data written until close() is called.
compressed = self._compressor.compress(data)
self._fp.write(compressed)
def writelines(self, seq):
"""Write a sequence of byte strings to the file.
Returns the number of uncompressed bytes written.
seq can be any iterable yielding byte strings.
Line separators are not added between the written byte strings.
return _compression.BaseStream.writelines(self, seq)
def seek(self, offset, whence=io.SEEK_SET):
"""Change the file position.
The new position is specified by offset, relative to the
position indicated by whence. Values for whence are:
0: start of stream (default); offset must not be negative
1: current stream position
2: end of stream; offset must not be positive
Returns the new file position.
Note that seeking is emulated, so depending on the parameters,
this operation may be extremely slow.
return self._buffer.seek(offset, whence)
"""Return the current file position."""
if self._mode == _MODE_READ:
return self._buffer.tell()
def open(filename, mode="rb", compresslevel=9,
encoding=None, errors=None, newline=None):
"""Open a bzip2-compressed file in binary or text mode.
The filename argument can be an actual filename (a str, bytes, or
PathLike object), or an existing file object to read from or write
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 BZ2File
constructor: BZ2File(filename, mode, compresslevel). In this case,
the encoding, errors and newline arguments must not be provided.
For text mode, a BZ2File 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")
bz_mode = mode.replace("t", "")
binary_file = BZ2File(filename, bz_mode, compresslevel=compresslevel)
return io.TextIOWrapper(binary_file, encoding, errors, newline)
def compress(data, compresslevel=9):
"""Compress a block of data.
compresslevel, if given, must be a number between 1 and 9.
For incremental compression, use a BZ2Compressor object instead.
comp = BZ2Compressor(compresslevel)
return comp.compress(data) + comp.flush()
"""Decompress a block of data.
For incremental decompression, use a BZ2Decompressor object instead.
decomp = BZ2Decompressor()
res = decomp.decompress(data)
break # Leftover data is not a valid bzip2 stream; ignore it.
raise # Error on the first iteration; bail out.
raise ValueError("Compressed data ended before the "
"end-of-stream marker was reached")
data = decomp.unused_data
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
