8000 add lzma.py and test_lzma.py at 3.13.2 · RustPython/RustPython@33f659f · GitHub
[go: up one dir, main page]
Skip to content

Commit 33f659f

Browse files
arihant2matharihant2math
committed
add lzma.py and test_lzma.py at 3.13.2
Signed-off-by: Ashwin Naren <arihant2math@gmail.com>
1 parent c0bd4e4 commit 33f659f

File tree

2 files changed

+2459
-0
lines changed

2 files changed

+2459
-0
lines changed

‎Lib/lzma.py

Lines changed: 364 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,364 @@
1+
"""Interface to the liblzma compression library.
2+
3+
This module provides a class for reading and writing compressed files,
4+
classes for incremental (de)compression, and convenience functions for
5+
one-shot (de)compression.
6+
7+
These classes and functions support both the XZ and legacy LZMA
8+
container formats, as well as raw compressed data streams.
9+
"""
10+
11+
__all__ = [
12+
"CHECK_NONE", "CHECK_CRC32", "CHECK_CRC64", "CHECK_SHA256",
13+
"CHECK_ID_MAX", "CHECK_UNKNOWN",
14+
"FILTER_LZMA1", "FILTER_LZMA2", "FILTER_DELTA", "FILTER_X86", "FILTER_IA64",
15+
"FILTER_ARM", "FILTER_ARMTHUMB", "FILTER_POWERPC", "FILTER_SPARC",
16+
"FORMAT_AUTO", "FORMAT_XZ", "FORMAT_ALONE", "FORMAT_RAW",
17+
"MF_HC3", "MF_HC4", "MF_BT2", "MF_BT3", "MF_BT4",
18+
"MODE_FAST", "MODE_NORMAL", "PRESET_DEFAULT", "PRESET_EXTREME",
19+
20+
"LZMACompressor", "LZMADecompressor", "LZMAFile", "LZMAError",
21+
"open", "compress", "decompress", "is_check_supported",
22+
]
23+
24+
import builtins
25+
import io
26+
import os
27+
from _lzma import *
28+
from _lzma import _encode_filter_properties, _decode_filter_properties
29+
import _compression
30+
31+
32+
# Value 0 no longer used
33+
_MODE_READ = 1
34+
# Value 2 no longer used
35+
_MODE_WRITE = 3
36+
37+
38+
class LZMAFile(_compression.BaseStream):
39+
40+
"""A file object providing transparent LZMA (de)compression.
41+
42+
An LZMAFile can act as a wrapper for an existing file object, or
43+
refer directly to a named file on disk.
44+
45+
Note that LZMAFile provides a *binary* file interface - data read
46+
is returned as bytes, and data to be written must be given as bytes.
47+
"""
48+
49+
def __init__(self, filename=None, mode="r", *,
50+
format=None, check=-1, preset=None, filters=None):
51+
"""Open an LZMA-compressed file in binary mode.
52+
53+
filename can be either an actual file name (given as a str,
54+
bytes, or PathLike object), in which case the named file is
55+
opened, or it can be an existing file object to read from or
56+
write to.
57+
58+
mode can be "r" for reading (default), "w" for (over)writing,
59+
"x" for creating exclusively, or "a" for appending. These can
60+
equivalently be given as "rb", "wb", "xb" and "ab" respectively.
61+
62+
format specifies the container format to use for the file.
63+
If mode is "r", this defaults to FORMAT_AUTO. Otherwise, the
64+
default is FORMAT_XZ.
65+
66+
check specifies the integrity check to use. This argument can
67+
only be used when opening a file for writing. For FORMAT_XZ,
68+
the default is CHECK_CRC64. FORMAT_ALONE and FORMAT_RAW do not
69+
support integrity checks - for these formats, check must be
70+
omitted, or be CHECK_NONE.
71+
72+
When opening a file for reading, the *preset* argument is not
73+
meaningful, and should be omitted. The *filters* argument should
74+
also be omitted, except when format is FORMAT_RAW (in which case
75+
it is required).
76+
77+
When opening a file for writing, the settings used by the
78+
compressor can be specified either as a preset compression
79+
level (with the *preset* argument), or in detail as a custom
80+
filter chain (with the *filters* argument). For FORMAT_XZ and
81+
FORMAT_ALONE, the default is to use the PRESET_DEFAULT preset
82+
level. For FORMAT_RAW, the caller must always specify a filter
83+
chain; the raw compressor does not support preset compression
84+
levels.
85+
86+
preset (if provided) should be an integer in the range 0-9,
87+
optionally OR-ed with the constant PRESET_EXTREME.
88+
89+
filters (if provided) should be a sequence of dicts. Each dict
90+
should have an entry for "id" indicating ID of the filter, plus
91+
additional entries for options to the filter.
92+
"""
93+
self._fp = None
94+
self._closefp = False
95+
self._mode = None
96+
97+
if mode in ("r", "rb"):
98+
if check != -1:
99+
raise ValueError("Cannot specify an integrity check "
100+
"when opening a file for reading")
101+
if preset is not None:
102+
raise ValueError("Cannot specify a preset compression "
103+
"level when opening a file for reading")
104+
if format is None:
105+
format = FORMAT_AUTO
106+
mode_code = _MODE_READ
107+
elif mode in ("w", "wb", "a", "ab", "x", "xb"):
108+
if format is None:
109+
format = FORMAT_XZ
110+
mode_code = _MODE_WRITE
111+
self._compressor = LZMACompressor(format=format, check=check,
112+
preset=preset, filters=filters)
113+
self._pos = 0
114+
else:
115+
raise ValueError("Invalid mode: {!r}".format(mode))
116+
117+
if isinstance(filename, (str, bytes, os.PathLike)):
118+
if "b" not in mode:
119+
mode += "b"
120+
self._fp = builtins.open(filename, mode)
121+
self._closefp = True
122+
self._mode = mode_code
123+
elif hasattr(filename, "read") or hasattr(filename, "write"):
124+
self._fp = filename
125+
self._mode = mode_code
126+
else:
127+
raise TypeError("filename must be a str, bytes, file or PathLike object")
128+
129+
if self._mode == _MODE_READ:
130+
raw = _compression.DecompressReader(self._fp, LZMADecompressor,
131+
trailing_error=LZMAError, format=format, filters=filters)
132+
self._buffer = io.BufferedReader(raw)
133+
134+
def close(self):
135+
"""Flush and close the file.
136+
137+
May be called more than once without error. Once the file is
138+
closed, any other operation on it will raise a ValueError.
139+
"""
140+
if self.closed:
141+
return
142+
try:
143+
if self._mode == _MODE_READ:
144+
self._buffer.close()
145+
self._buffer = None
146+
elif self._mode == _MODE_WRITE:
147+
self._fp.write(self._compressor.flush())
148+
self._compressor = None
149+
finally:
150+
try:
151+
if self._closefp:
152+
self._fp.close()
153+
finally:
154+
self._fp = None
155+
self._closefp = False
156+
157+
@property
158+
def closed(self):
159+
"""True if this file is closed."""
160+
return self._fp is None
161+
162+
@property
163+
def name(self):
164+
self._check_not_closed()
165+
return self._fp.name
166+
167+
@property
168+
def mode(self):
169+
return 'wb' if self._mode == _MODE_WRITE else 'rb'
170+
171+
def fileno(self):
172+
"""Return the file descriptor for the underlying file."""
173+
self._check_not_closed()
174+
return self._fp.fileno()
175+
176+
def seekable(self):
177+
"""Return whether the file supports seeking."""
178+
return self.readable() and self._buffer.seekable()
179+
180+
def readable(self):
181+
"""Return whether the file was opened for reading."""
182+
self._check_not_closed()
183+
return self._mode == _MODE_READ
184+
185+
def writable(self):
186+
"""Return whether the file was opened for writing."""
187+
self._check_not_closed()
188+
return self._mode == _MODE_WRITE
189+
190+
def peek(self, size=-1):
191+
"""Return buffered data without advancing the file position.
192+
193+
Always returns at least one byte of data, unless at EOF.
194+
The exact number of bytes returned is unspecified.
195+
"""
196+
self._check_can_read()
197+
# Relies on the undocumented fact that BufferedReader.peek() always
198+
# returns at least one byte (except at EOF)
199+
return self._buffer.peek(size)
200+
201+
def read(self, size=-1):
202+
"""Read up to size uncompressed bytes from the file.
203+
204+
If size is negative or omitted, read until EOF is reached.
205+
Returns b"" if the file is already at EOF.
206+
"""
207+
self._check_can_read()
208+
return self._buffer.read(size)
209+
210+
def read1(self, size=-1):
211+
"""Read up to size uncompressed bytes, while trying to avoid
212+
making multiple reads from the underlying stream. Reads up to a
213+
buffer's worth of data if size is negative.
214+
215+
Returns b"" if the file is at EOF.
216+
"""
217+
self._check_can_read()
218+
if size < 0:
219+
size = io.DEFAULT_BUFFER_SIZE
220+
return self._buffer.read1(size)
221+
222+
def readline(self, size=-1):
223+
"""Read a line of uncompressed bytes from the file.
224+
225+
The terminating newline (if present) is retained. If size is
226+
non-negative, no more than size bytes will be read (in which
227+
case the line may be incomplete). Returns b'' if already at EOF.
228+
"""
229+
self._check_can_read()
230+
return self._buffer.readline(size)
231+
232+
def write(self, data):
233+
"""Write a bytes object to the file.
234+
235+
Returns the number of uncompressed bytes written, which is
236+
always the length of data in bytes. Note that due to buffering,
237+
the file on disk may not reflect the data written until close()
238+
is called.
239+
"""
240+
self._check_can_write()
241+
if isinstance(data, (bytes, bytearray)):
242+
length = len(data)
243+
else:
244+
# accept any data that supports the buffer protocol
245+
data = memoryview(data)
246+
length = data.nbytes
247+
248+
compressed = self._compressor.compress(data)
249+
self._fp.write(compressed)
250+
self._pos += length
251+
return length
252+
253+
def seek(self, offset, whence=io.SEEK_SET):
254+
"""Change the file position.
255+
256+
The new position is specified by offset, relative to the
257+
position indicated by whence. Possible values for whence are:
258+
259+
0: start of stream (default): offset must not be negative
260+
1: current stream position
261+
2: end of stream; offset must not be positive
262+
263+
Returns the new file position.
264+
265+
Note that seeking is emulated, so depending on the parameters,
266+
this operation may be extremely slow.
267+
"""
268+
self._check_can_seek()
269+
return self._buffer.seek(offset, whence)
270+
271+
def tell(self):
272+
"""Return the current file position."""
273+
self._check_not_closed()
274+
if self._mode == _MODE_READ:
275+
return self._buffer.tell()
276+
return self._pos
277+
278+
279+
def open(filename, mode="rb", *,
280+
format=None, check=-1, preset=None, filters=None,
281+
encoding=None, errors=None, newline=None):
282+
"""Open an LZMA-compressed file in binary or text mode.
283+
284+
filename can be either an actual file name (given as a str, bytes,
285+
or PathLike object), in which case the named file is opened, or it
286+
can be an existing file object to read from or write to.
287+
288+
The mode argument can be "r", "rb" (default), "w", "wb", "x", "xb",
289+
"a", or "ab" for binary mode, or "rt", "wt", "xt", or "at" for text
290+
mode.
291+
292+
The format, check, preset and filters arguments specify the
293+
compression settings, as for LZMACompressor, LZMADecompressor and
294+
LZMAFile.
295+
296+
For binary mode, this function is equivalent to the LZMAFile
297+
constructor: LZMAFile(filename, mode, ...). In this case, the
298+
encoding, errors and newline arguments must not be provided.
299+
300+
For text mode, an LZMAFile object is created, and wrapped in an
301+
io.TextIOWrapper instance with the specified encoding, error
302+
handling behavior, and line ending(s).
303+
304+
"""
305+
if "t" in mode:
306+
if "b" in mode:
307+
raise ValueError("Invalid mode: %r" % (mode,))
308+
else:
309+
if encoding is not None:
310+
raise ValueError("Argument 'encoding' not supported in binary mode")
311+
if errors is not None:
312+
raise ValueError("Argument 'errors' not supported in binary mode")
313+
if newline is not None:
314+
raise ValueError("Argument 'newline' not supported in binary mode")
315+
316+
lz_mode = mode.replace("t", "")
317+
binary_file = LZMAFile(filename, lz_mode, format=format, check=check,
318+
preset=preset, filters=filters)
319+
320+
if "t" in mode:
321+
encoding = io.text_encoding(encoding)
322+
return io.TextIOWrapper(binary_file, encoding, errors, newline)
323+
else:
324+
return binary_file
325+
326+
327+
def compress(data, format=FORMAT_XZ, check=-1, preset=None, filters=None):
328+
"""Compress a block of data.
329+
330+
Refer to LZMACompressor's docstring for a description of the
331+
optional arguments *format*, *check*, *preset* and *filters*.
332+
333+
For incremental compression, use an LZMACompressor instead.
334+
"""
335+
comp = LZMACompressor(format, check, preset, filters)
336+
return comp.compress(data) + comp.flush()
337+
338+
339+
def decompress(data, format=FORMAT_AUTO, memlimit=None, filters=None):
340+
"""Decompress a block of data.
341+
342+
Refer to LZMADecompressor's docstring for a description of the
343+
optional arguments *format*, *check* and *filters*.
344+
345+
For incremental decompression, use an LZMADecompressor instead.
346+
"""
347+
results = []
348+
while True:
349+
decomp = LZMADecompressor(format, memlimit, filters)
350+
try:
351+
res = decomp.decompress(data)
352+
except LZMAError:
353+
if results:
354+
break # Leftover data is not a valid LZMA/XZ stream; ignore it.
355+
else:
356+
raise # Error on the first iteration; bail out.
357+
results.append(res)
358+
if not decomp.eof:
359+
raise LZMAError("Compressed data ended before the "
360+
"end-of-stream marker was reached")
361+
data = decomp.unused_data
362+
if not data:
363+
break
364+
return b"".join(results)

0 commit comments

Comments
 (0)
0