annotate contrib/python-zstandard/c-ext/compressionwriter.c @ 30435:b86a448a2965

zstd: vendor python-zstandard 0.5.0

As the commit message for the previous changeset says, we wish
for zstd to be a 1st class citizen in Mercurial. To make that
happen, we need to enable Python to talk to the zstd C API. And
that requires bindings.

This commit vendors a copy of existing Python bindings. Why do we
need to vendor? As the commit message of the previous commit says,
relying on systems in the wild to have the bindings or zstd present
is a losing proposition. By distributing the zstd and bindings with
Mercurial, we significantly increase our chances that zstd will
work. Since zstd will deliver a better end-user experience by
achieving better performance, this benefits our users. Another
reason is that the Python bindings still aren't stable and the
API is somewhat fluid. While Mercurial could be coded to target
multiple versions of the Python bindings, it is safer to bundle
an explicit, known working version.

The added Python bindings are mostly a fully-featured interface
to the zstd C API. They allow one-shot operations, streaming,
reading and writing from objects implements the file object
protocol, dictionary compression, control over low-level compression
parameters, and more. The Python bindings work on Python 2.6,
2.7, and 3.3+ and have been tested on Linux and Windows. There are
CFFI bindings, but they are lacking compared to the C extension.
Upstream work will be needed before we can support zstd with PyPy.
But it will be possible.

The files added in this commit come from Git commit
e637c1b214d5f869cf8116c550dcae23ec13b677 from
https://github.com/indygreg/python-zstandard and are added without
modifications. Some files from the upstream repository have been
omitted, namely files related to continuous integration.

In the spirit of full disclosure, I'm the maintainer of the
"python-zstandard" project and have authored 100% of the code
added in this commit. Unfortunately, the Python bindings have
not been formally code reviewed by anyone. While I've tested
much of the code thoroughly (I even have tests that fuzz APIs),
there's a good chance there are bugs, memory leaks, not well
thought out APIs, etc. If someone wants to review the code and
send feedback to the GitHub project, it would be greatly
appreciated.

Despite my involvement with both projects, my opinions of code
style differ from Mercurial's. The code in this commit introduces
numerous code style violations in Mercurial's linters. So, the code
is excluded from most lints. However, some violations I agree with.
These have been added to the known violations ignore list for now.

/**
* 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(ZstdCompresssionWriter__doc__,
"""A context manager used for writing compressed output to a writer.\n"
);

static void ZstdCompressionWriter_dealloc(ZstdCompressionWriter* self) {
	Py_XDECREF(self->compressor);
	Py_XDECREF(self->writer);

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

	PyObject_Del(self);
}

static PyObject* ZstdCompressionWriter_enter(ZstdCompressionWriter* self) {
	if (self->entered) {
		PyErr_SetString(ZstdError, "cannot __enter__ multiple times");
		return NULL;
	}

	self->cstream = CStream_from_ZstdCompressor(self->compressor, self->sourceSize);
	if (!self->cstream) {
		return NULL;
	}

	self->entered = 1;

	Py_INCREF(self);
	return (PyObject*)self;
}

static PyObject* ZstdCompressionWriter_exit(ZstdCompressionWriter* self, PyObject* args) {
	PyObject* exc_type;
	PyObject* exc_value;
	PyObject* exc_tb;
	size_t zresult;

	ZSTD_outBuffer output;
	PyObject* res;

	if (!PyArg_ParseTuple(args, "OOO", &exc_type, &exc_value, &exc_tb)) {
		return NULL;
	}

	self->entered = 0;

	if (self->cstream && exc_type == Py_None && exc_value == Py_None &&
		exc_tb == Py_None) {

		output.dst = malloc(self->outSize);
		if (!output.dst) {
			return PyErr_NoMemory();
		}
		output.size = self->outSize;
		output.pos = 0;

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

			if (output.pos) {
#if PY_MAJOR_VERSION >= 3
				res = PyObject_CallMethod(self->writer, "write", "y#",
#else
				res = PyObject_CallMethod(self->writer, "write", "s#",
#endif
					output.dst, output.pos);
				Py_XDECREF(res);
			}

			if (!zresult) {
				break;
			}

			output.pos = 0;
		}

		free(output.dst);
		ZSTD_freeCStream(self->cstream);
		self->cstream = NULL;
	}

	Py_RETURN_FALSE;
}

static PyObject* ZstdCompressionWriter_memory_size(ZstdCompressionWriter* self) {
	if (!self->cstream) {
		PyErr_SetString(ZstdError, "cannot determine size of an inactive compressor; "
			"call when a context manager is active");
		return NULL;
	}

	return PyLong_FromSize_t(ZSTD_sizeof_CStream(self->cstream));
}

static PyObject* ZstdCompressionWriter_write(ZstdCompressionWriter* self, PyObject* args) {
	const char* source;
	Py_ssize_t sourceSize;
	size_t zresult;
	ZSTD_inBuffer input;
	ZSTD_outBuffer output;
	PyObject* res;

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

	if (!self->entered) {
		PyErr_SetString(ZstdError, "compress must be called from an active context manager");
		return NULL;
	}

	output.dst = malloc(self->outSize);
	if (!output.dst) {
		return PyErr_NoMemory();
	}
	output.size = self->outSize;
	output.pos = 0;

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

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

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

		/* Copy data from output buffer to writer. */
		if (output.pos) {
#if PY_MAJOR_VERSION >= 3
			res = PyObject_CallMethod(self->writer, "write", "y#",
#else
			res = PyObject_CallMethod(self->writer, "write", "s#",
#endif
				output.dst, output.pos);
			Py_XDECREF(res);
		}
		output.pos = 0;
	}

	free(output.dst);

	/* TODO return bytes written */
	Py_RETURN_NONE;
	}

static PyMethodDef ZstdCompressionWriter_methods[] = {
	{ "__enter__", (PyCFunction)ZstdCompressionWriter_enter, METH_NOARGS,
	PyDoc_STR("Enter a compression context.") },
	{ "__exit__", (PyCFunction)ZstdCompressionWriter_exit, METH_VARARGS,
	PyDoc_STR("Exit a compression context.") },
	{ "memory_size", (PyCFunction)ZstdCompressionWriter_memory_size, METH_NOARGS,
	PyDoc_STR("Obtain the memory size of the underlying compressor") },
	{ "write", (PyCFunction)ZstdCompressionWriter_write, METH_VARARGS,
	PyDoc_STR("Compress data") },
	{ NULL, NULL }
};

PyTypeObject ZstdCompressionWriterType = {
	PyVarObject_HEAD_INIT(NULL, 0)
	"zstd.ZstdCompressionWriter",  /* tp_name */
	sizeof(ZstdCompressionWriter),  /* tp_basicsize */
	0,                              /* tp_itemsize */
	(destructor)ZstdCompressionWriter_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 */
	ZstdCompresssionWriter__doc__,  /* tp_doc */
	0,                              /* tp_traverse */
	0,                              /* tp_clear */
	0,                              /* tp_richcompare */
	0,                              /* tp_weaklistoffset */
	0,                              /* tp_iter */
	0,                              /* tp_iternext */
	ZstdCompressionWriter_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 compressionwriter_module_init(PyObject* mod) {
	Py_TYPE(&ZstdCompressionWriterType) = &PyType_Type;
	if (PyType_Ready(&ZstdCompressionWriterType) < 0) {
		return;
	}
}