contrib/python-zstandard/c-ext/compressobj.c
author Gregory Szorc <gregory.szorc@gmail.com>
Tue, 07 Feb 2017 23:24:47 -0800
changeset 30895 c32454d69b85
parent 30822 b54a2984cdd4
child 31796 e0dc40530c5a
permissions -rw-r--r--
zstd: vendor python-zstandard 0.7.0 Commit 3054ae3a66112970a091d3939fee32c2d0c1a23e from https://github.com/indygreg/python-zstandard is imported without modifications (other than removing unwanted files). The vendored zstd library within has been upgraded from 1.1.2 to 1.1.3. This version introduced new APIs for threads, thread pools, multi-threaded compression, and a new dictionary builder (COVER). These features are not yet used by python-zstandard (or Mercurial for that matter). However, that will likely change in the next python-zstandard release (and I think there are opportunities for Mercurial to take advantage of the multi-threaded APIs). Relevant to Mercurial, the CFFI bindings are now fully implemented. This means zstd should "just work" with PyPy (although I haven't tried). The python-zstandard test suite also runs all tests against both the C extension and CFFI bindings to ensure feature parity. There is also a "decompress_content_dict_chain()" API. This was derived from discussions with Yann Collet on list about alternate ways of encoding delta chains. The change most relevant to Mercurial is a performance enhancement in the simple decompression API to reuse a data structure across operations. This makes decompression of multiple inputs significantly faster. (This scenario occurs when reading revlog delta chains, for example.) Using python-zstandard's bench.py to measure the performance difference... On changelog chunks in the mozilla-unified repo: decompress discrete decompress() reuse zctx 1.262243 wall; 1.260000 CPU; 1.260000 user; 0.000000 sys 170.43 MB/s (best of 3) 0.949106 wall; 0.950000 CPU; 0.950000 user; 0.000000 sys 226.66 MB/s (best of 4) decompress discrete dict decompress() reuse zctx 0.692170 wall; 0.690000 CPU; 0.690000 user; 0.000000 sys 310.80 MB/s (best of 5) 0.437088 wall; 0.440000 CPU; 0.440000 user; 0.000000 sys 492.17 MB/s (best of 7) On manifest chunks in the mozilla-unified repo: decompress discrete decompress() reuse zctx 1.367284 wall; 1.370000 CPU; 1.370000 user; 0.000000 sys 274.01 MB/s (best of 3) 1.086831 wall; 1.080000 CPU; 1.080000 user; 0.000000 sys 344.72 MB/s (best of 3) decompress discrete dict decompress() reuse zctx 0.993272 wall; 0.990000 CPU; 0.990000 user; 0.000000 sys 377.19 MB/s (best of 3) 0.678651 wall; 0.680000 CPU; 0.680000 user; 0.000000 sys 552.06 MB/s (best of 5) That should make reads on zstd revlogs a bit faster ;) # no-check-commit

/**
* Copyright (c) 2016-present, Gregory Szorc
* All rights reserved.
*
* This software may be modified and distributed under the terms
* of the BSD license. See the LICENSE file for details.
*/

#include "python-zstandard.h"

extern PyObject* ZstdError;

PyDoc_STRVAR(ZstdCompressionObj__doc__,
"Perform compression using a standard library compatible API.\n"
);

static void ZstdCompressionObj_dealloc(ZstdCompressionObj* self) {
	PyMem_Free(self->output.dst);
	self->output.dst = NULL;

	if (self->cstream) {
		ZSTD_freeCStream(self->cstream);
		self->cstream = NULL;
	}

	Py_XDECREF(self->compressor);

	PyObject_Del(self);
}

static PyObject* ZstdCompressionObj_compress(ZstdCompressionObj* self, PyObject* args) {
	const char* source;
	Py_ssize_t sourceSize;
	ZSTD_inBuffer input;
	size_t zresult;
	PyObject* result = NULL;
	Py_ssize_t resultSize = 0;

	if (self->finished) {
		PyErr_SetString(ZstdError, "cannot call compress() after compressor finished");
		return NULL;
	}

#if PY_MAJOR_VERSION >= 3
	if (!PyArg_ParseTuple(args, "y#:compress", &source, &sourceSize)) {
#else
	if (!PyArg_ParseTuple(args, "s#:compress", &source, &sourceSize)) {
#endif
		return NULL;
	}

	input.src = source;
	input.size = sourceSize;
	input.pos = 0;

	while ((ssize_t)input.pos < sourceSize) {
		Py_BEGIN_ALLOW_THREADS
		zresult = ZSTD_compressStream(self->cstream, &self->output, &input);
		Py_END_ALLOW_THREADS

		if (ZSTD_isError(zresult)) {
			PyErr_Format(ZstdError, "zstd compress error: %s", ZSTD_getErrorName(zresult));
			return NULL;
		}

		if (self->output.pos) {
			if (result) {
				resultSize = PyBytes_GET_SIZE(result);
				if (-1 == _PyBytes_Resize(&result, resultSize + self->output.pos)) {
					return NULL;
				}

				memcpy(PyBytes_AS_STRING(result) + resultSize,
					self->output.dst, self->output.pos);
			}
			else {
				result = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
				if (!result) {
					return NULL;
				}
			}

			self->output.pos = 0;
		}
	}

	if (result) {
		return result;
	}
	else {
		return PyBytes_FromString("");
	}
}

static PyObject* ZstdCompressionObj_flush(ZstdCompressionObj* self, PyObject* args) {
	int flushMode = compressorobj_flush_finish;
	size_t zresult;
	PyObject* result = NULL;
	Py_ssize_t resultSize = 0;

	if (!PyArg_ParseTuple(args, "|i:flush", &flushMode)) {
		return NULL;
	}

	if (flushMode != compressorobj_flush_finish && flushMode != compressorobj_flush_block) {
		PyErr_SetString(PyExc_ValueError, "flush mode not recognized");
		return NULL;
	}

	if (self->finished) {
		PyErr_SetString(ZstdError, "compressor object already finished");
		return NULL;
	}

	assert(self->output.pos == 0);

	if (flushMode == compressorobj_flush_block) {
		/* The output buffer is of size ZSTD_CStreamOutSize(), which is 
		   guaranteed to hold a full block. */
		Py_BEGIN_ALLOW_THREADS
		zresult = ZSTD_flushStream(self->cstream, &self->output);
		Py_END_ALLOW_THREADS

		if (ZSTD_isError(zresult)) {
			PyErr_Format(ZstdError, "zstd compress error: %s", ZSTD_getErrorName(zresult));
			return NULL;
		}

		/* Output buffer is guaranteed to hold full block. */
		assert(zresult == 0);

		if (self->output.pos) {
			result = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
			if (!result) {
				return NULL;
			}
		}

		self->output.pos = 0;

		if (result) {
			return result;
		}
		else {
			return PyBytes_FromString("");
		}
	}

	assert(flushMode == compressorobj_flush_finish);
	self->finished = 1;

	while (1) {
		zresult = ZSTD_endStream(self->cstream, &self->output);
		if (ZSTD_isError(zresult)) {
			PyErr_Format(ZstdError, "error ending compression stream: %s",
				ZSTD_getErrorName(zresult));
			return NULL;
		}

		if (self->output.pos) {
			if (result) {
				resultSize = PyBytes_GET_SIZE(result);
				if (-1 == _PyBytes_Resize(&result, resultSize + self->output.pos)) {
					return NULL;
				}

				memcpy(PyBytes_AS_STRING(result) + resultSize,
					self->output.dst, self->output.pos);
			}
			else {
				result = PyBytes_FromStringAndSize(self->output.dst, self->output.pos);
				if (!result) {
					return NULL;
				}
			}

			self->output.pos = 0;
		}

		if (!zresult) {
			break;
		}
	}

	ZSTD_freeCStream(self->cstream);
	self->cstream = NULL;

	if (result) {
		return result;
	}
	else {
		return PyBytes_FromString("");
	}
}

static PyMethodDef ZstdCompressionObj_methods[] = {
	{ "compress", (PyCFunction)ZstdCompressionObj_compress, METH_VARARGS,
	PyDoc_STR("compress data") },
	{ "flush", (PyCFunction)ZstdCompressionObj_flush, METH_VARARGS,
	PyDoc_STR("finish compression operation") },
	{ NULL, NULL }
};

PyTypeObject ZstdCompressionObjType = {
	PyVarObject_HEAD_INIT(NULL, 0)
	"zstd.ZstdCompressionObj",      /* tp_name */
	sizeof(ZstdCompressionObj),     /* tp_basicsize */
	0,                              /* tp_itemsize */
	(destructor)ZstdCompressionObj_dealloc, /* tp_dealloc */
	0,                              /* tp_print */
	0,                              /* tp_getattr */
	0,                              /* tp_setattr */
	0,                              /* tp_compare */
	0,                              /* tp_repr */
	0,                              /* tp_as_number */
	0,                              /* tp_as_sequence */
	0,                              /* tp_as_mapping */
	0,                              /* tp_hash */
	0,                              /* tp_call */
	0,                              /* tp_str */
	0,                              /* tp_getattro */
	0,                              /* tp_setattro */
	0,                              /* tp_as_buffer */
	Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */
	ZstdCompressionObj__doc__,      /* tp_doc */
	0,                              /* tp_traverse */
	0,                              /* tp_clear */
	0,                              /* tp_richcompare */
	0,                              /* tp_weaklistoffset */
	0,                              /* tp_iter */
	0,                              /* tp_iternext */
	ZstdCompressionObj_methods,     /* tp_methods */
	0,                              /* tp_members */
	0,                              /* tp_getset */
	0,                              /* tp_base */
	0,                              /* tp_dict */
	0,                              /* tp_descr_get */
	0,                              /* tp_descr_set */
	0,                              /* tp_dictoffset */
	0,                              /* tp_init */
	0,                              /* tp_alloc */
	PyType_GenericNew,              /* tp_new */
};

void compressobj_module_init(PyObject* module) {
	Py_TYPE(&ZstdCompressionObjType) = &PyType_Type;
	if (PyType_Ready(&ZstdCompressionObjType) < 0) {
		return;
	}
}