##// END OF EJS Templates
copies: iterate over children directly (instead of parents)...
copies: iterate over children directly (instead of parents) Before this change we would gather all parent → child edges and iterate on all parent, gathering copy information for children and aggregating them from there. They are not strict requirement for edges to be processed in that specific order. We could also simply iterate over all "children" revision and aggregate data from both parents at the same time. This patch does that. It make various things simpler: * since both parents are processed at the same time, we no longer need to cache data for merge (see next changeset for details), * we no longer need nested loop to process data, * we no longer need to store partial merge data for a rev from distinct loop interaction to another when processing merges, * we no longer need to build a full parent -> children mapping (we only rely on a simpler "parent -> number of children" map (for memory efficiency), * the data access pattern is now simpler (from lower revisions to higher revisions) and entirely predicable. That predictability open the way to prefetching and parallel processing. So that new iterations order requires simpler code and open the way to interesting optimisation. The effect on performance is quite good. In the worse case, we don't see any significant negative impact. And in the best case, the reduction of roundtrip to Python provide us with a significant speed. Some example below: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev # full comparison between the previous changeset and this one Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000048 s, 0.000041 s, -0.000007 s, × 0.8542, 41 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000153 s, 0.000102 s, -0.000051 s, × 0.6667, 17 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004209 s, 0.004254 s, +0.000045 s, × 1.0107, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000203 s, 0.000282 s, +0.000079 s, × 1.3892, 31 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000059 s, 0.000048 s, -0.000011 s, × 0.8136, 48 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000194 s, 0.000211 s, +0.000017 s, × 1.0876, 30 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000380 s, 0.000375 s, -0.000005 s, × 0.9868, 375 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010588 s, 0.010574 s, -0.000014 s, × 0.9987, 1762 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.048961 s, 0.049974 s, +0.001013 s, × 1.0207, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.083612 s, 0.084300 s, +0.000688 s, × 1.0082, 12 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.058579 s, 0.060128 s, +0.001549 s, × 1.0264, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.736783 s, 0.686542 s, -0.050241 s, × 0.9318, 15 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.022050 s, 0.009277 s, -0.012773 s, × 0.4207, 4638 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120800 s, 0.114733 s, -0.006067 s, × 0.9498, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000140 s, 0.000081 s, -0.000059 s, × 0.5786, 40 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000114 s, 0.000107 s, -0.000007 s, × 0.9386, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000224 s, 0.000173 s, -0.000051 s, × 0.7723, 57 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000723 s, 0.000698 s, -0.000025 s, × 0.9654, 77 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009665 s, 0.009248 s, -0.000417 s, × 0.9569, 6 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.014820 s, 0.015446 s, +0.000626 s, × 1.0422, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.076049 s, 0.074373 s, -0.001676 s, × 0.9780, 12 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.683603 s, 0.639870 s, -0.043733 s, × 0.9360, 9 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000161 s, 0.000088 s, -0.000073 s, × 0.5466, 44 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000234 s, 0.000199 s, -0.000035 s, × 0.8504, 24 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000247 s, 0.000171 s, -0.000076 s, × 0.6923, 19 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000630 s, 0.000592 s, -0.000038 s, × 0.9397, 84 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003286 s, 0.003151 s, -0.000135 s, × 0.9589, 1050 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062441 s, 0.061612 s, -0.000829 s, × 0.9867, 10268 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005423 s, 0.005381 s, -0.000042 s, × 0.9923, 3 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005919 s, 0.003742 s, -0.002177 s, × 0.6322, 91 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.062597 s, 0.061983 s, -0.000614 s, × 0.9902, 7 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.043551 s, 0.019861 s, -0.023690 s, × 0.4560, 32 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.192475 s, 0.188101 s, -0.004374 s, × 0.9773, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.955575 s, 1.806696 s, -0.148879 s, × 0.9239, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.886501 s, 2.682987 s, -0.203514 s, × 0.9295, 13 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.001181 s, 0.000852 s, -0.000329 s, × 0.7214, 426 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.001189 s, 0.000859 s, -0.000330 s, × 0.7225, 429 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000563 s, 0.000150 s, -0.000413 s, × 0.2664, 37 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001548 s, 0.001158 s, -0.000390 s, × 0.7481, 579 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027782 s, 0.027240 s, -0.000542 s, × 0.9805, 27240 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062781 s, 0.062824 s, +0.000043 s, × 1.0007, 10470 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005778 s, 0.005463 s, -0.000315 s, × 0.9455, 3 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.006192 s, 0.004238 s, -0.001954 s, × 0.6844, 103 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065391 s, 0.064113 s, -0.001278 s, × 0.9805, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.317216 s, 0.294063 s, -0.023153 s, × 0.9270, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.303119 s, 0.281493 s, -0.021626 s, × 0.9287, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.045739 s, 0.020390 s, -0.025349 s, × 0.4458, 33 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.098021 s, 3.023879 s, -0.074142 s, × 0.9761, 31 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.771480 s, 0.735549 s, -0.035931 s, × 0.9534, 14 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.813422 s, 18.568900 s, -0.244522 s, × 0.9870, 51 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.684923 s, 18.356645 s, -0.328278 s, × 0.9824, 50 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.296305 s, 18.250393 s, -0.045912 s, × 0.9975, 50 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 3.061887 s, 2.792459 s, -0.269428 s, × 0.9120, 14 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s, +3.827623 s, × 1.0369, 470 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 64.262957 s, 63.961040 s, -0.301917 s, × 0.9953, 167 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9422

File last commit:

r37513:b1fb341d default
r46764:294d5aca default
Show More
bufferutil.c
792 lines | 23.2 KiB | text/x-c | CLexer
/**
* Copyright (c) 2017-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(BufferWithSegments__doc__,
"BufferWithSegments - A memory buffer holding known sub-segments.\n"
"\n"
"This type represents a contiguous chunk of memory containing N discrete\n"
"items within sub-segments of that memory.\n"
"\n"
"Segments within the buffer are stored as an array of\n"
"``(offset, length)`` pairs, where each element is an unsigned 64-bit\n"
"integer using the host/native bit order representation.\n"
"\n"
"The type exists to facilitate operations against N>1 items without the\n"
"overhead of Python object creation and management.\n"
);
static void BufferWithSegments_dealloc(ZstdBufferWithSegments* self) {
/* Backing memory is either canonically owned by a Py_buffer or by us. */
if (self->parent.buf) {
PyBuffer_Release(&self->parent);
}
else if (self->useFree) {
free(self->data);
}
else {
PyMem_Free(self->data);
}
self->data = NULL;
if (self->useFree) {
free(self->segments);
}
else {
PyMem_Free(self->segments);
}
self->segments = NULL;
PyObject_Del(self);
}
static int BufferWithSegments_init(ZstdBufferWithSegments* self, PyObject* args, PyObject* kwargs) {
static char* kwlist[] = {
"data",
"segments",
NULL
};
Py_buffer segments;
Py_ssize_t segmentCount;
Py_ssize_t i;
memset(&self->parent, 0, sizeof(self->parent));
#if PY_MAJOR_VERSION >= 3
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y*y*:BufferWithSegments",
#else
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s*s*:BufferWithSegments",
#endif
kwlist, &self->parent, &segments)) {
return -1;
}
if (!PyBuffer_IsContiguous(&self->parent, 'C') || self->parent.ndim > 1) {
PyErr_SetString(PyExc_ValueError, "data buffer should be contiguous and have a single dimension");
goto except;
}
if (!PyBuffer_IsContiguous(&segments, 'C') || segments.ndim > 1) {
PyErr_SetString(PyExc_ValueError, "segments buffer should be contiguous and have a single dimension");
goto except;
}
if (segments.len % sizeof(BufferSegment)) {
PyErr_Format(PyExc_ValueError, "segments array size is not a multiple of %zu",
sizeof(BufferSegment));
goto except;
}
segmentCount = segments.len / sizeof(BufferSegment);
/* Validate segments data, as blindly trusting it could lead to arbitrary
memory access. */
for (i = 0; i < segmentCount; i++) {
BufferSegment* segment = &((BufferSegment*)(segments.buf))[i];
if (segment->offset + segment->length > (unsigned long long)self->parent.len) {
PyErr_SetString(PyExc_ValueError, "offset within segments array references memory outside buffer");
goto except;
return -1;
}
}
/* Make a copy of the segments data. It is cheap to do so and is a guard
against caller changing offsets, which has security implications. */
self->segments = PyMem_Malloc(segments.len);
if (!self->segments) {
PyErr_NoMemory();
goto except;
}
memcpy(self->segments, segments.buf, segments.len);
PyBuffer_Release(&segments);
self->data = self->parent.buf;
self->dataSize = self->parent.len;
self->segmentCount = segmentCount;
return 0;
except:
PyBuffer_Release(&self->parent);
PyBuffer_Release(&segments);
return -1;
}
/**
* Construct a BufferWithSegments from existing memory and offsets.
*
* Ownership of the backing memory and BufferSegments will be transferred to
* the created object and freed when the BufferWithSegments is destroyed.
*/
ZstdBufferWithSegments* BufferWithSegments_FromMemory(void* data, unsigned long long dataSize,
BufferSegment* segments, Py_ssize_t segmentsSize) {
ZstdBufferWithSegments* result = NULL;
Py_ssize_t i;
if (NULL == data) {
PyErr_SetString(PyExc_ValueError, "data is NULL");
return NULL;
}
if (NULL == segments) {
PyErr_SetString(PyExc_ValueError, "segments is NULL");
return NULL;
}
for (i = 0; i < segmentsSize; i++) {
BufferSegment* segment = &segments[i];
if (segment->offset + segment->length > dataSize) {
PyErr_SetString(PyExc_ValueError, "offset in segments overflows buffer size");
return NULL;
}
}
result = PyObject_New(ZstdBufferWithSegments, &ZstdBufferWithSegmentsType);
if (NULL == result) {
return NULL;
}
result->useFree = 0;
memset(&result->parent, 0, sizeof(result->parent));
result->data = data;
result->dataSize = dataSize;
result->segments = segments;
result->segmentCount = segmentsSize;
return result;
}
static Py_ssize_t BufferWithSegments_length(ZstdBufferWithSegments* self) {
return self->segmentCount;
}
static ZstdBufferSegment* BufferWithSegments_item(ZstdBufferWithSegments* self, Py_ssize_t i) {
ZstdBufferSegment* result = NULL;
if (i < 0) {
PyErr_SetString(PyExc_IndexError, "offset must be non-negative");
return NULL;
}
if (i >= self->segmentCount) {
PyErr_Format(PyExc_IndexError, "offset must be less than %zd", self->segmentCount);
return NULL;
}
if (self->segments[i].length > PY_SSIZE_T_MAX) {
PyErr_Format(PyExc_ValueError,
"item at offset %zd is too large for this platform", i);
return NULL;
}
result = (ZstdBufferSegment*)PyObject_CallObject((PyObject*)&ZstdBufferSegmentType, NULL);
if (NULL == result) {
return NULL;
}
result->parent = (PyObject*)self;
Py_INCREF(self);
result->data = (char*)self->data + self->segments[i].offset;
result->dataSize = (Py_ssize_t)self->segments[i].length;
result->offset = self->segments[i].offset;
return result;
}
#if PY_MAJOR_VERSION >= 3
static int BufferWithSegments_getbuffer(ZstdBufferWithSegments* self, Py_buffer* view, int flags) {
if (self->dataSize > PY_SSIZE_T_MAX) {
view->obj = NULL;
PyErr_SetString(PyExc_BufferError, "buffer is too large for this platform");
return -1;
}
return PyBuffer_FillInfo(view, (PyObject*)self, self->data, (Py_ssize_t)self->dataSize, 1, flags);
}
#else
static Py_ssize_t BufferWithSegments_getreadbuffer(ZstdBufferWithSegments* self, Py_ssize_t segment, void **ptrptr) {
if (segment != 0) {
PyErr_SetString(PyExc_ValueError, "segment number must be 0");
return -1;
}
if (self->dataSize > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_ValueError, "buffer is too large for this platform");
return -1;
}
*ptrptr = self->data;
return (Py_ssize_t)self->dataSize;
}
static Py_ssize_t BufferWithSegments_getsegcount(ZstdBufferWithSegments* self, Py_ssize_t* len) {
if (len) {
*len = 1;
}
return 1;
}
#endif
PyDoc_STRVAR(BufferWithSegments_tobytes__doc__,
"Obtain a bytes instance for this buffer.\n"
);
static PyObject* BufferWithSegments_tobytes(ZstdBufferWithSegments* self) {
if (self->dataSize > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_ValueError, "buffer is too large for this platform");
return NULL;
}
return PyBytes_FromStringAndSize(self->data, (Py_ssize_t)self->dataSize);
}
PyDoc_STRVAR(BufferWithSegments_segments__doc__,
"Obtain a BufferSegments describing segments in this sintance.\n"
);
static ZstdBufferSegments* BufferWithSegments_segments(ZstdBufferWithSegments* self) {
ZstdBufferSegments* result = (ZstdBufferSegments*)PyObject_CallObject((PyObject*)&ZstdBufferSegmentsType, NULL);
if (NULL == result) {
return NULL;
}
result->parent = (PyObject*)self;
Py_INCREF(self);
result->segments = self->segments;
result->segmentCount = self->segmentCount;
return result;
}
static PySequenceMethods BufferWithSegments_sq = {
(lenfunc)BufferWithSegments_length, /* sq_length */
0, /* sq_concat */
0, /* sq_repeat */
(ssizeargfunc)BufferWithSegments_item, /* sq_item */
0, /* sq_ass_item */
0, /* sq_contains */
0, /* sq_inplace_concat */
0 /* sq_inplace_repeat */
};
static PyBufferProcs BufferWithSegments_as_buffer = {
#if PY_MAJOR_VERSION >= 3
(getbufferproc)BufferWithSegments_getbuffer, /* bf_getbuffer */
0 /* bf_releasebuffer */
#else
(readbufferproc)BufferWithSegments_getreadbuffer, /* bf_getreadbuffer */
0, /* bf_getwritebuffer */
(segcountproc)BufferWithSegments_getsegcount, /* bf_getsegcount */
0 /* bf_getcharbuffer */
#endif
};
static PyMethodDef BufferWithSegments_methods[] = {
{ "segments", (PyCFunction)BufferWithSegments_segments,
METH_NOARGS, BufferWithSegments_segments__doc__ },
{ "tobytes", (PyCFunction)BufferWithSegments_tobytes,
METH_NOARGS, BufferWithSegments_tobytes__doc__ },
{ NULL, NULL }
};
static PyMemberDef BufferWithSegments_members[] = {
{ "size", T_ULONGLONG, offsetof(ZstdBufferWithSegments, dataSize),
READONLY, "total size of the buffer in bytes" },
{ NULL }
};
PyTypeObject ZstdBufferWithSegmentsType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.BufferWithSegments", /* tp_name */
sizeof(ZstdBufferWithSegments),/* tp_basicsize */
0, /* tp_itemsize */
(destructor)BufferWithSegments_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
&BufferWithSegments_sq, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
&BufferWithSegments_as_buffer, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
BufferWithSegments__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
BufferWithSegments_methods, /* tp_methods */
BufferWithSegments_members, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc)BufferWithSegments_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
PyDoc_STRVAR(BufferSegments__doc__,
"BufferSegments - Represents segments/offsets within a BufferWithSegments\n"
);
static void BufferSegments_dealloc(ZstdBufferSegments* self) {
Py_CLEAR(self->parent);
PyObject_Del(self);
}
#if PY_MAJOR_VERSION >= 3
static int BufferSegments_getbuffer(ZstdBufferSegments* self, Py_buffer* view, int flags) {
return PyBuffer_FillInfo(view, (PyObject*)self,
(void*)self->segments, self->segmentCount * sizeof(BufferSegment),
1, flags);
}
#else
static Py_ssize_t BufferSegments_getreadbuffer(ZstdBufferSegments* self, Py_ssize_t segment, void **ptrptr) {
if (segment != 0) {
PyErr_SetString(PyExc_ValueError, "segment number must be 0");
return -1;
}
*ptrptr = (void*)self->segments;
return self->segmentCount * sizeof(BufferSegment);
}
static Py_ssize_t BufferSegments_getsegcount(ZstdBufferSegments* self, Py_ssize_t* len) {
if (len) {
*len = 1;
}
return 1;
}
#endif
static PyBufferProcs BufferSegments_as_buffer = {
#if PY_MAJOR_VERSION >= 3
(getbufferproc)BufferSegments_getbuffer,
0
#else
(readbufferproc)BufferSegments_getreadbuffer,
0,
(segcountproc)BufferSegments_getsegcount,
0
#endif
};
PyTypeObject ZstdBufferSegmentsType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.BufferSegments", /* tp_name */
sizeof(ZstdBufferSegments),/* tp_basicsize */
0, /* tp_itemsize */
(destructor)BufferSegments_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 */
&BufferSegments_as_buffer, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
BufferSegments__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
0, /* 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 */
};
PyDoc_STRVAR(BufferSegment__doc__,
"BufferSegment - Represents a segment within a BufferWithSegments\n"
);
static void BufferSegment_dealloc(ZstdBufferSegment* self) {
Py_CLEAR(self->parent);
PyObject_Del(self);
}
static Py_ssize_t BufferSegment_length(ZstdBufferSegment* self) {
return self->dataSize;
}
#if PY_MAJOR_VERSION >= 3
static int BufferSegment_getbuffer(ZstdBufferSegment* self, Py_buffer* view, int flags) {
return PyBuffer_FillInfo(view, (PyObject*)self,
self->data, self->dataSize, 1, flags);
}
#else
static Py_ssize_t BufferSegment_getreadbuffer(ZstdBufferSegment* self, Py_ssize_t segment, void **ptrptr) {
if (segment != 0) {
PyErr_SetString(PyExc_ValueError, "segment number must be 0");
return -1;
}
*ptrptr = self->data;
return self->dataSize;
}
static Py_ssize_t BufferSegment_getsegcount(ZstdBufferSegment* self, Py_ssize_t* len) {
if (len) {
*len = 1;
}
return 1;
}
#endif
PyDoc_STRVAR(BufferSegment_tobytes__doc__,
"Obtain a bytes instance for this segment.\n"
);
static PyObject* BufferSegment_tobytes(ZstdBufferSegment* self) {
return PyBytes_FromStringAndSize(self->data, self->dataSize);
}
static PySequenceMethods BufferSegment_sq = {
(lenfunc)BufferSegment_length, /* sq_length */
0, /* sq_concat */
0, /* sq_repeat */
0, /* sq_item */
0, /* sq_ass_item */
0, /* sq_contains */
0, /* sq_inplace_concat */
0 /* sq_inplace_repeat */
};
static PyBufferProcs BufferSegment_as_buffer = {
#if PY_MAJOR_VERSION >= 3
(getbufferproc)BufferSegment_getbuffer,
0
#else
(readbufferproc)BufferSegment_getreadbuffer,
0,
(segcountproc)BufferSegment_getsegcount,
0
#endif
};
static PyMethodDef BufferSegment_methods[] = {
{ "tobytes", (PyCFunction)BufferSegment_tobytes,
METH_NOARGS, BufferSegment_tobytes__doc__ },
{ NULL, NULL }
};
static PyMemberDef BufferSegment_members[] = {
{ "offset", T_ULONGLONG, offsetof(ZstdBufferSegment, offset), READONLY,
"offset of segment within parent buffer" },
{ NULL }
};
PyTypeObject ZstdBufferSegmentType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.BufferSegment", /* tp_name */
sizeof(ZstdBufferSegment),/* tp_basicsize */
0, /* tp_itemsize */
(destructor)BufferSegment_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
&BufferSegment_sq, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
&BufferSegment_as_buffer, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
BufferSegment__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
BufferSegment_methods, /* tp_methods */
BufferSegment_members, /* 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 */
};
PyDoc_STRVAR(BufferWithSegmentsCollection__doc__,
"Represents a collection of BufferWithSegments.\n"
);
static void BufferWithSegmentsCollection_dealloc(ZstdBufferWithSegmentsCollection* self) {
Py_ssize_t i;
if (self->firstElements) {
PyMem_Free(self->firstElements);
self->firstElements = NULL;
}
if (self->buffers) {
for (i = 0; i < self->bufferCount; i++) {
Py_CLEAR(self->buffers[i]);
}
PyMem_Free(self->buffers);
self->buffers = NULL;
}
PyObject_Del(self);
}
static int BufferWithSegmentsCollection_init(ZstdBufferWithSegmentsCollection* self, PyObject* args) {
Py_ssize_t size;
Py_ssize_t i;
Py_ssize_t offset = 0;
size = PyTuple_Size(args);
if (-1 == size) {
return -1;
}
if (0 == size) {
PyErr_SetString(PyExc_ValueError, "must pass at least 1 argument");
return -1;
}
for (i = 0; i < size; i++) {
PyObject* item = PyTuple_GET_ITEM(args, i);
if (!PyObject_TypeCheck(item, &ZstdBufferWithSegmentsType)) {
PyErr_SetString(PyExc_TypeError, "arguments must be BufferWithSegments instances");
return -1;
}
if (0 == ((ZstdBufferWithSegments*)item)->segmentCount ||
0 == ((ZstdBufferWithSegments*)item)->dataSize) {
PyErr_SetString(PyExc_ValueError, "ZstdBufferWithSegments cannot be empty");
return -1;
}
}
self->buffers = PyMem_Malloc(size * sizeof(ZstdBufferWithSegments*));
if (NULL == self->buffers) {
PyErr_NoMemory();
return -1;
}
self->firstElements = PyMem_Malloc(size * sizeof(Py_ssize_t));
if (NULL == self->firstElements) {
PyMem_Free(self->buffers);
self->buffers = NULL;
PyErr_NoMemory();
return -1;
}
self->bufferCount = size;
for (i = 0; i < size; i++) {
ZstdBufferWithSegments* item = (ZstdBufferWithSegments*)PyTuple_GET_ITEM(args, i);
self->buffers[i] = item;
Py_INCREF(item);
if (i > 0) {
self->firstElements[i - 1] = offset;
}
offset += item->segmentCount;
}
self->firstElements[size - 1] = offset;
return 0;
}
static PyObject* BufferWithSegmentsCollection_size(ZstdBufferWithSegmentsCollection* self) {
Py_ssize_t i;
Py_ssize_t j;
unsigned long long size = 0;
for (i = 0; i < self->bufferCount; i++) {
for (j = 0; j < self->buffers[i]->segmentCount; j++) {
size += self->buffers[i]->segments[j].length;
}
}
return PyLong_FromUnsignedLongLong(size);
}
Py_ssize_t BufferWithSegmentsCollection_length(ZstdBufferWithSegmentsCollection* self) {
return self->firstElements[self->bufferCount - 1];
}
static ZstdBufferSegment* BufferWithSegmentsCollection_item(ZstdBufferWithSegmentsCollection* self, Py_ssize_t i) {
Py_ssize_t bufferOffset;
if (i < 0) {
PyErr_SetString(PyExc_IndexError, "offset must be non-negative");
return NULL;
}
if (i >= BufferWithSegmentsCollection_length(self)) {
PyErr_Format(PyExc_IndexError, "offset must be less than %zd",
BufferWithSegmentsCollection_length(self));
return NULL;
}
for (bufferOffset = 0; bufferOffset < self->bufferCount; bufferOffset++) {
Py_ssize_t offset = 0;
if (i < self->firstElements[bufferOffset]) {
if (bufferOffset > 0) {
offset = self->firstElements[bufferOffset - 1];
}
return BufferWithSegments_item(self->buffers[bufferOffset], i - offset);
}
}
PyErr_SetString(ZstdError, "error resolving segment; this should not happen");
return NULL;
}
static PySequenceMethods BufferWithSegmentsCollection_sq = {
(lenfunc)BufferWithSegmentsCollection_length, /* sq_length */
0, /* sq_concat */
0, /* sq_repeat */
(ssizeargfunc)BufferWithSegmentsCollection_item, /* sq_item */
0, /* sq_ass_item */
0, /* sq_contains */
0, /* sq_inplace_concat */
0 /* sq_inplace_repeat */
};
static PyMethodDef BufferWithSegmentsCollection_methods[] = {
{ "size", (PyCFunction)BufferWithSegmentsCollection_size,
METH_NOARGS, PyDoc_STR("total size in bytes of all segments") },
{ NULL, NULL }
};
PyTypeObject ZstdBufferWithSegmentsCollectionType = {
PyVarObject_HEAD_INIT(NULL, 0)
"zstd.BufferWithSegmentsCollection", /* tp_name */
sizeof(ZstdBufferWithSegmentsCollection),/* tp_basicsize */
0, /* tp_itemsize */
(destructor)BufferWithSegmentsCollection_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
&BufferWithSegmentsCollection_sq, /* 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, /* tp_flags */
BufferWithSegmentsCollection__doc__, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
/* TODO implement iterator for performance. */
0, /* tp_iter */
0, /* tp_iternext */
BufferWithSegmentsCollection_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 */
(initproc)BufferWithSegmentsCollection_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
void bufferutil_module_init(PyObject* mod) {
Py_TYPE(&ZstdBufferWithSegmentsType) = &PyType_Type;
if (PyType_Ready(&ZstdBufferWithSegmentsType) < 0) {
return;
}
Py_INCREF(&ZstdBufferWithSegmentsType);
PyModule_AddObject(mod, "BufferWithSegments", (PyObject*)&ZstdBufferWithSegmentsType);
Py_TYPE(&ZstdBufferSegmentsType) = &PyType_Type;
if (PyType_Ready(&ZstdBufferSegmentsType) < 0) {
return;
}
Py_INCREF(&ZstdBufferSegmentsType);
PyModule_AddObject(mod, "BufferSegments", (PyObject*)&ZstdBufferSegmentsType);
Py_TYPE(&ZstdBufferSegmentType) = &PyType_Type;
if (PyType_Ready(&ZstdBufferSegmentType) < 0) {
return;
}
Py_INCREF(&ZstdBufferSegmentType);
PyModule_AddObject(mod, "BufferSegment", (PyObject*)&ZstdBufferSegmentType);
Py_TYPE(&ZstdBufferWithSegmentsCollectionType) = &PyType_Type;
if (PyType_Ready(&ZstdBufferWithSegmentsCollectionType) < 0) {
return;
}
Py_INCREF(&ZstdBufferWithSegmentsCollectionType);
PyModule_AddObject(mod, "BufferWithSegmentsCollection", (PyObject*)&ZstdBufferWithSegmentsCollectionType);
}