"""Interface to the liblzma compression library.
This module provides a class for reading and writing compressed files,
classes for incremental (de)compression, and convenience functions for
one-shot (de)compression.
These classes and functions support both the XZ and legacy LZMA
container formats, as well as raw compressed data streams.
"CHECK_NONE", "CHECK_CRC32", "CHECK_CRC64", "CHECK_SHA256",
"CHECK_ID_MAX", "CHECK_UNKNOWN",
"FILTER_LZMA1", "FILTER_LZMA2", "FILTER_DELTA", "FILTER_X86", "FILTER_IA64",
"FILTER_ARM", "FILTER_ARMTHUMB", "FILTER_POWERPC", "FILTER_SPARC",
"FORMAT_AUTO", "FORMAT_XZ", "FORMAT_ALONE", "FORMAT_RAW",
"MF_HC3", "MF_HC4", "MF_BT2", "MF_BT3", "MF_BT4",
"MODE_FAST", "MODE_NORMAL", "PRESET_DEFAULT", "PRESET_EXTREME",
"LZMACompressor", "LZMADecompressor", "LZMAFile", "LZMAError",
"open", "compress", "decompress", "is_check_supported",
from _lzma import _encode_filter_properties, _decode_filter_properties
class LZMAFile(_compression.BaseStream):
"""A file object providing transparent LZMA (de)compression.
An LZMAFile can act as a wrapper for an existing file object, or
refer directly to a named file on disk.
Note that LZMAFile provides a *binary* file interface - data read
is returned as bytes, and data to be written must be given as bytes.
def __init__(self, filename=None, mode="r", *,
format=None, check=-1, preset=None, filters=None):
"""Open an LZMA-compressed file in binary mode.
filename can be either an actual file name (given as a str,
bytes, or PathLike object), in which case the named file is
opened, or it can be an existing file object to read from or
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" respectively.
format specifies the container format to use for the file.
If mode is "r", this defaults to FORMAT_AUTO. Otherwise, the
check specifies the integrity check to use. This argument can
only be used when opening a file for writing. For FORMAT_XZ,
the default is CHECK_CRC64. FORMAT_ALONE and FORMAT_RAW do not
support integrity checks - for these formats, check must be
omitted, or be CHECK_NONE.
When opening a file for reading, the *preset* argument is not
meaningful, and should be omitted. The *filters* argument should
also be omitted, except when format is FORMAT_RAW (in which case
When opening a file for writing, the settings used by the
compressor can be specified either as a preset compression
level (with the *preset* argument), or in detail as a custom
filter chain (with the *filters* argument). For FORMAT_XZ and
FORMAT_ALONE, the default is to use the PRESET_DEFAULT preset
level. For FORMAT_RAW, the caller must always specify a filter
chain; the raw compressor does not support preset compression
preset (if provided) should be an integer in the range 0-9,
optionally OR-ed with the constant PRESET_EXTREME.
filters (if provided) should be a sequence of dicts. Each dict
should have an entry for "id" indicating ID of the filter, plus
additional entries for options to the filter.
self._mode = _MODE_CLOSED
raise ValueError("Cannot specify an integrity check "
"when opening a file for reading")
raise ValueError("Cannot specify a preset compression "
"level when opening a file for reading")
elif mode in ("w", "wb", "a", "ab", "x", "xb"):
self._compressor = LZMACompressor(format=format, check=check,
preset=preset, filters=filters)
raise ValueError("Invalid mode: {!r}".format(mode))
if isinstance(filename, (str, bytes, os.PathLike)):
self._fp = builtins.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, LZMADecompressor,
trailing_error=LZMAError, format=format, filters=filters)
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)
return self._buffer.peek(size)
"""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)
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.
return self._buffer.readline(size)
"""Write a bytes object to the file.
Returns the number of uncompressed bytes written, which is
always the length of data in bytes. Note that due to buffering,
the file on disk may not reflect the data written until close()
if isinstance(data, (bytes, bytearray)):
# accept any data that supports the buffer protocol
compressed = self._compressor.compress(data)
self._fp.write(compressed)
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. Possible 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", *,
format=None, check=-1, preset=None, filters=None,
encoding=None, errors=None, newline=None):
"""Open an LZMA-compressed file in binary or text mode.
filename can be either an actual file name (given as a str, bytes,
or PathLike object), in which case the named file is opened, or it
can be an existing file object to read from or write to.
The mode argument can be "r", "rb" (default), "w", "wb", "x", "xb",
"a", or "ab" for binary mode, or "rt", "wt", "xt", or "at" for text
The format, check, preset and filters arguments specify the
compression settings, as for LZMACompressor, LZMADecompressor and
For binary mode, this function is equivalent to the LZMAFile
constructor: LZMAFile(filename, mode, ...). In this case, the
encoding, errors and newline arguments must not be provided.
For text mode, an LZMAFile 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")
lz_mode = mode.replace("t", "")
binary_file = LZMAFile(filename, lz_mode, format=format, check=check,
preset=preset, filters=filters)
return io.TextIOWrapper(binary_file, encoding, errors, newline)
def compress(data, format=FORMAT_XZ, check=-1, preset=None, filters=None):
"""Compress a block of data.
Refer to LZMACompressor's docstring for a description of the
optional arguments *format*, *check*, *preset* and *filters*.
For incremental compression, use an LZMACompressor instead.
comp = LZMACompressor(format, check, preset, filters)
return comp.compress(data) + comp.flush()
def decompress(data, format=FORMAT_AUTO, memlimit=None, filters=None):
"""Decompress a block of data.
Refer to LZMADecompressor's docstring for a description of the
optional arguments *format*, *check* and *filters*.
For incremental decompression, use an LZMADecompressor instead.
decomp = LZMADecompressor(format, memlimit, filters)
res = decomp.decompress(data)
break # Leftover data is not a valid LZMA/XZ stream; ignore it.
raise # Error on the first iteration; bail out.
raise LZMAError("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
