def compress(self, data, allow_empty=False):
if len(data
) == 0 and self._fparams.contentSizeFlag and not allow_empty:
raise ValueError(
'cannot write empty inputs when writing content sizes')
if self._multithreaded and self._dict_data:
raise ZstdError(
'compress() cannot be used with both dictionaries and multi-threaded compression'
)
if self._multithreaded and self._cparams:
raise ZstdError(
'compress() cannot be used with both compression parameters and multi-threaded compression'
)
# TODO use a CDict for performance.
dict_data = ffi.NULL
dict_size = 0
if self._dict_data:
dict_data = self._dict_data.as_bytes()
dict_size = len(self._dict_data)
params = ffi.new('ZSTD_parameters *')[0]
if self._cparams:
params.cParams = self._cparams.as_compression_parameters()
else:
params.cParams = lib.ZSTD_getCParams(self._compression_level,
len(data), dict_size)
params.fParams = self._fparams
dest_size = lib.ZSTD_compressBound(len(data))
out = new_nonzero('char[]', dest_size)
if self._multithreaded:
zresult = lib.ZSTDMT_compressCCtx(self._cctx, ffi.addressof(out),
dest_size, data, len(data),
self._compression_level)
else:
zresult = lib.ZSTD_compress_advanced(self._cctx,
ffi.addressof(out), dest_size,
data, len(data), dict_data,
dict_size, params)
if lib.ZSTD_isError(zresult):
raise ZstdError('cannot compress: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
return ffi.buffer(out, zresult)[:]
def decompress(self, data):
if self._finished:
raise ZstdError('cannot use a decompressobj multiple times')
assert (self._decompressor._dstream)
in_buffer = ffi.new('ZSTD_inBuffer *')
out_buffer = ffi.new('ZSTD_outBuffer *')
data_buffer = ffi.from_buffer(data)
in_buffer.src = data_buffer
in_buffer.size = len(data_buffer)
in_buffer.pos = 0
dst_buffer = ffi.new('char[]', DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE)
out_buffer.dst = dst_buffer
out_buffer.size = len(dst_buffer)
out_buffer.pos = 0
chunks = []
while in_buffer.pos < in_buffer.size:
zresult = lib.ZSTD_decompressStream(self._decompressor._dstream,
out_buffer, in_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('zstd decompressor error: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if zresult == 0:
self._finished = True
self._decompressor = None
if out_buffer.pos:
chunks.append(ffi.buffer(out_buffer.dst, out_buffer.pos)[:])
out_buffer.pos = 0
return b''.join(chunks)
def get_frame_parameters(data):
if not isinstance(data, bytes_type):
raise TypeError('argument must be bytes')
params = ffi.new('ZSTD_frameParams *')
zresult = lib.ZSTD_getFrameParams(params, data, len(data))
if lib.ZSTD_isError(zresult):
raise ZstdError('cannot get frame parameters: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if zresult:
raise ZstdError('not enough data for frame parameters; need %d bytes' %
zresult)
return FrameParameters(params[0])
def train_dictionary(dict_size,
samples,
selectivity=0,
level=0,
notifications=0,
dict_id=0):
if not isinstance(samples, list):
raise TypeError('samples must be a list')
total_size = sum(map(len, samples))
samples_buffer = new_nonzero('char[]', total_size)
sample_sizes = new_nonzero('size_t[]', len(samples))
offset = 0
for i, sample in enumerate(samples):
if not isinstance(sample, bytes_type):
raise ValueError('samples must be bytes')
l = len(sample)
ffi.memmove(samples_buffer + offset, sample, l)
offset += l
sample_sizes[i] = l
dict_data = new_nonzero('char[]', dict_size)
dparams = ffi.new('ZDICT_params_t *')[0]
dparams.selectivityLevel = selectivity
dparams.compressionLevel = level
dparams.notificationLevel = notifications
dparams.dictID = dict_id
zresult = lib.ZDICT_trainFromBuffer_advanced(
ffi.addressof(dict_data), dict_size, ffi.addressof(samples_buffer),
ffi.addressof(sample_sizes, 0), len(samples), dparams)
if lib.ZDICT_isError(zresult):
raise ZstdError('Cannot train dict: %s' %
ffi.string(lib.ZDICT_getErrorName(zresult)))
return ZstdCompressionDict(ffi.buffer(dict_data, zresult)[:])
def __init__(self,
level=3,
dict_data=None,
compression_params=None,
write_checksum=False,
write_content_size=False,
write_dict_id=True,
threads=0):
if level < 1:
raise ValueError('level must be greater than 0')
elif level > lib.ZSTD_maxCLevel():
raise ValueError('level must be less than %d' %
lib.ZSTD_maxCLevel())
if threads < 0:
threads = _cpu_count()
self._compression_level = level
self._dict_data = dict_data
self._cparams = compression_params
self._fparams = ffi.new('ZSTD_frameParameters *')[0]
self._fparams.checksumFlag = write_checksum
self._fparams.contentSizeFlag = write_content_size
self._fparams.noDictIDFlag = not write_dict_id
if threads:
cctx = lib.ZSTDMT_createCCtx(threads)
if cctx == ffi.NULL:
raise MemoryError()
self._cctx = ffi.gc(cctx, lib.ZSTDMT_freeCCtx)
self._multithreaded = True
else:
cctx = lib.ZSTD_createCCtx()
if cctx == ffi.NULL:
raise MemoryError()
self._cctx = ffi.gc(cctx, lib.ZSTD_freeCCtx)
self._multithreaded = False
self._cstream = None
def _init_mtcstream(self, size):
assert self._multithreaded
dict_data = ffi.NULL
dict_size = 0
if self._dict_data:
dict_data = self._dict_data.as_bytes()
dict_size = len(self._dict_data)
zparams = ffi.new('ZSTD_parameters *')[0]
if self._cparams:
zparams.cParams = self._cparams.as_compression_parameters()
else:
zparams.cParams = lib.ZSTD_getCParams(self._compression_level,
size, dict_size)
zparams.fParams = self._fparams
zresult = lib.ZSTDMT_initCStream_advanced(self._cctx, dict_data,
dict_size, zparams, size)
if lib.ZSTD_isError(zresult):
raise ZstdError('cannot init CStream: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
def _ensure_cstream(self, size):
if self._cstream:
zresult = lib.ZSTD_resetCStream(self._cstream, size)
if lib.ZSTD_isError(zresult):
raise ZstdError('could not reset CStream: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
return
cstream = lib.ZSTD_createCStream()
if cstream == ffi.NULL:
raise MemoryError()
cstream = ffi.gc(cstream, lib.ZSTD_freeCStream)
dict_data = ffi.NULL
dict_size = 0
if self._dict_data:
dict_data = self._dict_data.as_bytes()
dict_size = len(self._dict_data)
zparams = ffi.new('ZSTD_parameters *')[0]
if self._cparams:
zparams.cParams = self._cparams.as_compression_parameters()
else:
zparams.cParams = lib.ZSTD_getCParams(self._compression_level,
size, dict_size)
zparams.fParams = self._fparams
zresult = lib.ZSTD_initCStream_advanced(cstream, dict_data, dict_size,
zparams, size)
if lib.ZSTD_isError(zresult):
raise Exception('cannot init CStream: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
self._cstream = cstream
def train_cover_dictionary(dict_size,
samples,
k=0,
d=0,
notifications=0,
dict_id=0,
level=0,
optimize=False,
steps=0,
threads=0):
if not isinstance(samples, list):
raise TypeError('samples must be a list')
if threads < 0:
threads = _cpu_count()
total_size = sum(map(len, samples))
samples_buffer = new_nonzero('char[]', total_size)
sample_sizes = new_nonzero('size_t[]', len(samples))
offset = 0
for i, sample in enumerate(samples):
if not isinstance(sample, bytes_type):
raise ValueError('samples must be bytes')
l = len(sample)
ffi.memmove(samples_buffer + offset, sample, l)
offset += l
sample_sizes[i] = l
dict_data = new_nonzero('char[]', dict_size)
dparams = ffi.new('COVER_params_t *')[0]
dparams.k = k
dparams.d = d
dparams.steps = steps
dparams.nbThreads = threads
dparams.notificationLevel = notifications
dparams.dictID = dict_id
dparams.compressionLevel = level
if optimize:
zresult = lib.COVER_optimizeTrainFromBuffer(
ffi.addressof(dict_data), dict_size, ffi.addressof(samples_buffer),
ffi.addressof(sample_sizes, 0), len(samples),
ffi.addressof(dparams))
else:
zresult = lib.COVER_trainFromBuffer(ffi.addressof(dict_data),
dict_size,
ffi.addressof(samples_buffer),
ffi.addressof(sample_sizes, 0),
len(samples), dparams)
if lib.ZDICT_isError(zresult):
raise ZstdError('cannot train dict: %s' %
ffi.string(lib.ZDICT_getErrorName(zresult)))
return ZstdCompressionDict(ffi.buffer(dict_data, zresult)[:],
k=dparams.k,
d=dparams.d)
def read_from(self,
reader,
size=0,
read_size=COMPRESSION_RECOMMENDED_INPUT_SIZE,
write_size=COMPRESSION_RECOMMENDED_OUTPUT_SIZE):
if hasattr(reader, 'read'):
have_read = True
elif hasattr(reader, '__getitem__'):
have_read = False
buffer_offset = 0
size = len(reader)
else:
raise ValueError('must pass an object with a read() method or '
'conforms to buffer protocol')
if self._multithreaded:
self._init_mtcstream(size)
else:
self._ensure_cstream(size)
in_buffer = ffi.new('ZSTD_inBuffer *')
out_buffer = ffi.new('ZSTD_outBuffer *')
in_buffer.src = ffi.NULL
in_buffer.size = 0
in_buffer.pos = 0
dst_buffer = ffi.new('char[]', write_size)
out_buffer.dst = dst_buffer
out_buffer.size = write_size
out_buffer.pos = 0
while True:
# We should never have output data sitting around after a previous
# iteration.
assert out_buffer.pos == 0
# Collect input data.
if have_read:
read_result = reader.read(read_size)
else:
remaining = len(reader) - buffer_offset
slice_size = min(remaining, read_size)
read_result = reader[buffer_offset:buffer_offset + slice_size]
buffer_offset += slice_size
# No new input data. Break out of the read loop.
if not read_result:
break
# Feed all read data into the compressor and emit output until
# exhausted.
read_buffer = ffi.from_buffer(read_result)
in_buffer.src = read_buffer
in_buffer.size = len(read_buffer)
in_buffer.pos = 0
while in_buffer.pos < in_buffer.size:
if self._multithreaded:
zresult = lib.ZSTDMT_compressStream(
self._cctx, out_buffer, in_buffer)
else:
zresult = lib.ZSTD_compressStream(self._cstream,
out_buffer, in_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('zstd compress error: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if out_buffer.pos:
data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:]
out_buffer.pos = 0
yield data
assert out_buffer.pos == 0
# And repeat the loop to collect more data.
continue
# If we get here, input is exhausted. End the stream and emit what
# remains.
while True:
assert out_buffer.pos == 0
if self._multithreaded:
zresult = lib.ZSTDMT_endStream(self._cctx, out_buffer)
else:
zresult = lib.ZSTD_endStream(self._cstream, out_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('error ending compression stream: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if out_buffer.pos:
data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:]
out_buffer.pos = 0
yield data
if zresult == 0:
break
def copy_stream(self,
ifh,
ofh,
size=0,
read_size=COMPRESSION_RECOMMENDED_INPUT_SIZE,
write_size=COMPRESSION_RECOMMENDED_OUTPUT_SIZE):
if not hasattr(ifh, 'read'):
raise ValueError('first argument must have a read() method')
if not hasattr(ofh, 'write'):
raise ValueError('second argument must have a write() method')
mt = self._multithreaded
if mt:
self._init_mtcstream(size)
else:
self._ensure_cstream(size)
in_buffer = ffi.new('ZSTD_inBuffer *')
out_buffer = ffi.new('ZSTD_outBuffer *')
dst_buffer = ffi.new('char[]', write_size)
out_buffer.dst = dst_buffer
out_buffer.size = write_size
out_buffer.pos = 0
total_read, total_write = 0, 0
while True:
data = ifh.read(read_size)
if not data:
break
data_buffer = ffi.from_buffer(data)
total_read += len(data_buffer)
in_buffer.src = data_buffer
in_buffer.size = len(data_buffer)
in_buffer.pos = 0
while in_buffer.pos < in_buffer.size:
if mt:
zresult = lib.ZSTDMT_compressStream(
self._cctx, out_buffer, in_buffer)
else:
zresult = lib.ZSTD_compressStream(self._cstream,
out_buffer, in_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('zstd compress error: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if out_buffer.pos:
ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
total_write += out_buffer.pos
out_buffer.pos = 0
# We've finished reading. Flush the compressor.
while True:
if mt:
zresult = lib.ZSTDMT_endStream(self._cctx, out_buffer)
else:
zresult = lib.ZSTD_endStream(self._cstream, out_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('error ending compression stream: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if out_buffer.pos:
ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
total_write += out_buffer.pos
out_buffer.pos = 0
if zresult == 0:
break
return total_read, total_write
def decompress_content_dict_chain(self, frames):
if not isinstance(frames, list):
raise TypeError('argument must be a list')
if not frames:
raise ValueError('empty input chain')
# First chunk should not be using a dictionary. We handle it specially.
chunk = frames[0]
if not isinstance(chunk, bytes_type):
raise ValueError('chunk 0 must be bytes')
# All chunks should be zstd frames and should have content size set.
chunk_buffer = ffi.from_buffer(chunk)
params = ffi.new('ZSTD_frameParams *')
zresult = lib.ZSTD_getFrameParams(params, chunk_buffer,
len(chunk_buffer))
if lib.ZSTD_isError(zresult):
raise ValueError('chunk 0 is not a valid zstd frame')
elif zresult:
raise ValueError('chunk 0 is too small to contain a zstd frame')
if not params.frameContentSize:
raise ValueError('chunk 0 missing content size in frame')
dctx = lib.ZSTD_createDCtx()
if dctx == ffi.NULL:
raise MemoryError()
dctx = ffi.gc(dctx, lib.ZSTD_freeDCtx)
last_buffer = ffi.new('char[]', params.frameContentSize)
zresult = lib.ZSTD_decompressDCtx(dctx, last_buffer, len(last_buffer),
chunk_buffer, len(chunk_buffer))
if lib.ZSTD_isError(zresult):
raise ZstdError('could not decompress chunk 0: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
# Special case of chain length of 1
if len(frames) == 1:
return ffi.buffer(last_buffer, len(last_buffer))[:]
i = 1
while i < len(frames):
chunk = frames[i]
if not isinstance(chunk, bytes_type):
raise ValueError('chunk %d must be bytes' % i)
chunk_buffer = ffi.from_buffer(chunk)
zresult = lib.ZSTD_getFrameParams(params, chunk_buffer,
len(chunk_buffer))
if lib.ZSTD_isError(zresult):
raise ValueError('chunk %d is not a valid zstd frame' % i)
elif zresult:
raise ValueError(
'chunk %d is too small to contain a zstd frame' % i)
if not params.frameContentSize:
raise ValueError('chunk %d missing content size in frame' % i)
dest_buffer = ffi.new('char[]', params.frameContentSize)
zresult = lib.ZSTD_decompress_usingDict(dctx, dest_buffer,
len(dest_buffer),
chunk_buffer,
len(chunk_buffer),
last_buffer,
len(last_buffer))
if lib.ZSTD_isError(zresult):
raise ZstdError('could not decompress chunk %d' % i)
last_buffer = dest_buffer
i += 1
return ffi.buffer(last_buffer, len(last_buffer))[:]
def read_from(self,
reader,
read_size=DECOMPRESSION_RECOMMENDED_INPUT_SIZE,
write_size=DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE,
skip_bytes=0):
if skip_bytes >= read_size:
raise ValueError('skip_bytes must be smaller than read_size')
if hasattr(reader, 'read'):
have_read = True
elif hasattr(reader, '__getitem__'):
have_read = False
buffer_offset = 0
size = len(reader)
else:
raise ValueError('must pass an object with a read() method or '
'conforms to buffer protocol')
if skip_bytes:
if have_read:
reader.read(skip_bytes)
else:
if skip_bytes > size:
raise ValueError(
'skip_bytes larger than first input chunk')
buffer_offset = skip_bytes
self._ensure_dstream()
in_buffer = ffi.new('ZSTD_inBuffer *')
out_buffer = ffi.new('ZSTD_outBuffer *')
dst_buffer = ffi.new('char[]', write_size)
out_buffer.dst = dst_buffer
out_buffer.size = len(dst_buffer)
out_buffer.pos = 0
while True:
assert out_buffer.pos == 0
if have_read:
read_result = reader.read(read_size)
else:
remaining = size - buffer_offset
slice_size = min(remaining, read_size)
read_result = reader[buffer_offset:buffer_offset + slice_size]
buffer_offset += slice_size
# No new input. Break out of read loop.
if not read_result:
break
# Feed all read data into decompressor and emit output until
# exhausted.
read_buffer = ffi.from_buffer(read_result)
in_buffer.src = read_buffer
in_buffer.size = len(read_buffer)
in_buffer.pos = 0
while in_buffer.pos < in_buffer.size:
assert out_buffer.pos == 0
zresult = lib.ZSTD_decompressStream(self._dstream, out_buffer,
in_buffer)
if lib.ZSTD_isError(zresult):
raise ZstdError('zstd decompress error: %s' %
ffi.string(lib.ZSTD_getErrorName(zresult)))
if out_buffer.pos:
data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:]
out_buffer.pos = 0
yield data
if zresult == 0:
return
# Repeat loop to collect more input data.
continue