test_basic.py 12.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
# Wendeling.core.bigarray | Basic tests
# Copyright (C) 2014-2015  Nexedi SA and Contributors.
#                          Kirill Smelkov <kirr@nexedi.com>
#
# This program is free software: you can Use, Study, Modify and Redistribute
# it under the terms of the GNU General Public License version 3, or (at your
# option) any later version, as published by the Free Software Foundation.
#
# You can also Link and Combine this program with other software covered by
# the terms of any of the Open Source Initiative approved licenses and Convey
# the resulting work. Corresponding source of such a combination shall include
# the source code for all other software used.
#
# This program is distributed WITHOUT ANY WARRANTY; without even the implied
# warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#
# See COPYING file for full licensing terms.

from wendelin.bigarray import BigArray
from wendelin.bigfile import BigFile
from wendelin.lib.mem import memcpy
22
from wendelin.lib.calc import mul
23 24
from numpy import ndarray, dtype, int32, uint32, uint8, all, zeros, arange, \
        multiply, array_equal, asarray
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40

from pytest import raises


# Synthetic bigfile that just loads zeros, and ignores writes (= a-la /dev/zero)
class BigFile_Zero(BigFile):

    def loadblk(self, blk, buf):
        # Nothing to do here - the memory buf obtained from OS comes pre-cleared
        # XXX reenable once/if memory comes uninitialized here
        return

    def storeblk(self, blk, buf):
        return


41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
# Synthetic bigfile that loads/stores data from/to numpy array
class BigFile_Data(BigFile):

    def __new__(cls, data, blksize):
        obj = BigFile.__new__(cls, blksize)
        obj.datab = data.view(uint8)
        return obj

    def loadblk(self, blk, buf):
        x = self.datab[self.blksize * blk : self.blksize * (blk+1)]
        memcpy(buf, x)

    def storeblk(self, blk, buf):
        memcpy(self.datab[self.blksize * blk : self.blksize * (blk+1)], buf)


57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
PS = 2*1024*1024    # FIXME hardcoded, TODO -> ram.pagesize


# basic ndarray-compatibility attributes of BigArray
def test_bigarray_basic():
    Z  = BigFile_Zero(PS)
    Zh = Z.fileh_open()

    A = BigArray((10,3), int32, Zh)

    raises(TypeError, "A.data")
    assert A.strides    == (12, 4)
    assert A.dtype      == dtype(int32)
    # XXX .flags?
    # XXX .flat?    (non-basic)
    # XXX .imag?    (non-basic)
    # XXX .real?    (non-basic)
    assert A.size       == 10*3
    assert len(A)       == 10
    assert A.itemsize   == 4
    assert A.nbytes     == 4*10*3
    assert A.ndim       == 2
    assert A.shape      == (10,3)
    # XXX .ctypes   (non-basic)
    # TODO .base



# DoubleGet(obj1, obj2)[key] -> obj1[key], obj2[key]
class DoubleGet:
    def __init__(self, obj1, obj2):
        self.obj1 = obj1
        self.obj2 = obj2

    def __getitem__(self, key):
        return self.obj1[key], self.obj2[key]


# getitem/setitem (1d case)
def test_bigarray_indexing_1d():
    Z  = BigFile_Zero(PS)
    Zh = Z.fileh_open()

    A = BigArray((10*PS,), uint8, Zh)

    # ndarray of the same shape - we'll use it to get slices and compare result
    # shape/stride against BigArray.__getitem__
    A_= ndarray ((10*PS,), uint8)

    # AA[key] -> A[key], A_[key]
    AA = DoubleGet(A, A_)


110 111 112 113 114 115
    # BigArray does not support advanced indexes
    # (in numpy they create _copy_ picking up elements)
    A_[0:5] = range(0,10,2)
    assert array_equal(A_[[0,1,2,3,4]], [0,2,4,6,8])
    raises (TypeError, 'A[[0,1,2,3,4]]')

116 117 118
    # index out of range
    # - element access  -> raises IndexError
    # - slice access    -> empty
119
    A_[-1] = 0
120 121 122 123 124 125 126 127 128
    assert AA[10*PS-1] == (0,0)
    raises(IndexError, 'A_[10*PS]')
    raises(IndexError, 'A [10*PS]')
    a, _ = AA[10*PS:10*PS+1]
    assert isinstance(a, ndarray)
    assert array_equal(a, _)
    assert a.dtype == dtype(uint8)
    assert a.shape == (0,)

129

130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
    # "empty" slices
    assert A[10:5:1]        .size == 0
    assert A[5:10:-1]       .size == 0
    assert A[5:5]           .size == 0
    assert A[100*PS:200*PS] .size == 0


    # whole array
    a, _ = AA[:]
    assert isinstance(a, ndarray)
    assert a.dtype   == dtype(uint8)
    assert a.shape   == _.shape
    assert a.strides == _.strides

    assert a[0] == 0
    assert a[5*PS] == 0
    assert a[10*PS-1] == 0


    # overlaps with a
    b, _ = AA[4*PS:]
    assert isinstance(b, ndarray)
    assert b.dtype   == dtype(uint8)
    assert b.shape   == _.shape
    assert b.strides == _.strides

    assert b[0] == 0
    assert b[1*PS] == 0
    assert b[5*PS-1] == 0

    # a <-> b
    assert b[1*PS] == 0
    a[5*PS] = 1
    assert b[1*PS] == 1


    # non-pagesize aligned slice
    c, _ = AA[4*PS+3 : 9*PS-3]
    assert isinstance(c, ndarray)
    assert c.dtype   == dtype(uint8)
    assert c.shape   == _.shape
    assert c.strides == _.strides

    assert c[0]  == 0
    assert c[-1] == 0

    # a <-> b <-> c
    assert b[3] == 0
    assert a[4*PS+3] == 0
    c[0] = 3
    assert b[3] == 3
    assert a[4*PS+3] == 3

    assert b[5*PS-4] == 0
    assert a[9*PS-4] == 0
    c[-1] = 99
    assert b[5*PS-4] == 99
    assert a[9*PS-4] == 99

    # negative stride
    d, _ = AA[9*PS+1:4*PS-1:-1]
    assert isinstance(d, ndarray)
    assert d.dtype   == dtype(uint8)
    assert d.shape   == _.shape
    assert d.strides == _.strides

    assert all(d[:5] == 0)
    assert d[5] == 99               # c[-1]
    assert all(d[6:-(PS+1)] == 0)
    assert d[-(PS+1)] == 1          # a[5*PS]
    assert all(d[-PS:-4] == 0)
    assert d[-4] == 3               # c[0]
    assert all(d[-3:] == 0)

    # like c, but stride > 1
    e, _ = AA [4*PS+3 : 9*PS-3 : 7]
    assert isinstance(e, ndarray)
    assert e.dtype   == dtype(uint8)
    assert e.shape   == _.shape
    assert e.strides == _.strides
    c[0] = 4
    assert e[0] == c[0]
    c[0] = 5
    assert e[0] == c[0]
    c[7] = 7
    assert e[1] == c[7]
    c[7] = 8
    assert e[1] == c[7]
    # TODO check more

    # like d, but stride < -1
    f, _ = AA[9*PS+1:4*PS-1:-11]
    assert isinstance(f, ndarray)
    assert f.dtype   == dtype(uint8)
    assert f.shape   == _.shape
    assert f.strides == _.strides
    d[0] = 11
    assert f[0] == d[0]
    d[0] = 12
    assert f[0] == d[0]
    d[11] = 13
    assert f[1] == d[11]
    d[11] = 14
    assert f[1] == d[11]
    # TODO check more


    # setitem
    A[2*PS+1:3*PS+2] = 5
    assert all(a[2*PS+1 : 3*PS+2] == 5)
    assert a[2*PS] == 0
    assert a[3*PS+3] == 0

    A[2*PS+2:2*PS+5] = [6,7,8]
    assert a[2*PS+0] == 0
    assert a[2*PS+1] == 5
    assert a[2*PS+2] == 6
    assert a[2*PS+3] == 7
    assert a[2*PS+4] == 8
    assert a[2*PS+5] == 5
    assert a[2*PS+6] == 5

    assert raises(ValueError, 'A[:4] = range(5)')


# given dimension length n, yield index variants to test
def indices_to_test(n):
    # ":"
    yield slice(None)

    # int
    yield 0
    yield -1
    yield n//2

    # start:stop:stride
    yield slice(1,-1)
    yield slice(n//4+1, n*3//4-1, 2)
    yield slice(n//5+1, n*4//5-1, 3)


# geven shape, yield all Nd idx variant, where every index iterates full indices_to_test
def idx_to_test(shape, idx_prefix=()):
    leaf = len(shape) <= 1
    for i in indices_to_test(shape[0]):
        idx = idx_prefix + (i,)
        if leaf:
            yield idx
        else:
            # = yield from
            for _ in idx_to_test(shape[1:], idx):
                yield _


# getitem/setitem (Nd case)
def test_bigarray_indexing_Nd():
    # shape of tested array - all primes, total size for uint32 ~ 7 2M pages
    # XXX even less dimensions (to speed up tests)?
    shape = tuple(reversed( (17,23,101,103) ))

    # test data - all items are unique - so we can check array by content
    # NOTE +PS so that BigFile_Data has no problem loading last blk
    #      (else data slice will be smaller than buf)
293
    data  = arange(mul(shape) + PS, dtype=uint32)
294

295 296
    # synthetic bigfile that only loads data from numpy array
    class BigFile_Data_RO(BigFile_Data):
297 298 299
        def storeblk(self, blk, buf):
            raise RuntimeError('tests should not try to change test data')

300
    f  = BigFile_Data_RO(data, PS)
301 302 303
    fh = f.fileh_open()

    A  = BigArray(shape, uint32, fh)                    # bigarray with test data and shape
304
    A_ = data[:mul(shape)].reshape(shape)               # ndarray  ----//----
305

306 307 308
    # AA[key] -> A[key], A_[key]
    AA = DoubleGet(A, A_)

309 310 311 312

    # now just go over combinations of various slice at each dimension, and see
    # whether slicing result is the same ndarray would do.
    for idx in idx_to_test(shape):
313 314 315
        a, a_ = AA[idx]
        assert array_equal(a, a_)

316

317 318 319 320 321 322 323 324 325 326 327 328
    # any part of index out of range
    # - element access  -> raises IndexError
    # - slice access    -> empty
    for idxpos in range(len(shape)):
        idx  = [0]*len(shape)
        # idx -> tuple(idx)
        # ( list would mean advanced indexing - not what we want )
        idxt = lambda : tuple(idx)

        # valid access element access
        idx[idxpos] = shape[idxpos] - 1     # 0, 0, 0,  Ni-1, 0 ,0, 0
        a, a_ = AA[idxt()]
329 330
        assert array_equal(a, a_)

331 332 333 334 335 336 337 338 339 340 341 342 343 344
        # out-of-range element access
        idx[idxpos] = shape[idxpos]         # 0, 0, 0,  Ni  , 0 ,0, 0
        raises(IndexError, 'A [idxt()]')
        raises(IndexError, 'A_[idxt()]')

        # out-of-range slice access
        idx[idxpos] = slice(shape[idxpos],  # 0, 0, 0,  Ni:Ni+1  , 0 ,0, 0
                            shape[idxpos]+1)
        a, a_ = AA[idxt()]
        assert array_equal(a, a_)
        assert a .size == 0
        assert a_.size == 0


345 346 347 348 349 350 351 352 353 354 355
    # TODO ... -> expanded (0,1,2,negative), rejected if many
    # TODO newaxis
    # TODO nidx < len(shape)
    # TODO empty slice in major row, empty slice in secondary row
    """
    # ellipsis  - take some idx[a:b] and replace it by ...
    for ellipsis in range(2):   # 0 - no ellipsis

        # newaxis   - added after at some position(s)
        for newaxis in range(3):    # 0 - no newaxis
    """
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415


def test_bigarray_resize():
    data = zeros(8*PS, dtype=uint32)
    f   = BigFile_Data(data, PS)
    fh  = f.fileh_open()

    # set first part & ensure it is set correctly
    A   = BigArray((10,3), uint32, fh)
    A[:,:] = arange(10*3, dtype=uint32).reshape((10,3))

    a = A[:]
    assert array_equal(a.ravel(), arange(10*3, dtype=uint32))

    # grow array
    A.resize((11,3))

    # a as already mapped, should stay the same
    assert array_equal(a.ravel(), arange(10*3, dtype=uint32))

    # mapping it once again maps it whole with new size
    b = A[:]
    assert isinstance(b, ndarray)
    assert b.shape  == (11,3)
    assert b.dtype  == dtype(uint32)

    # head data is the same as a
    assert array_equal(a, b[:10,:])

    # tail is zeros
    assert array_equal(b[10,:], zeros(3, dtype=uint32))

    # old mapping stays valid and changes propageate to/from it
    assert a[0,0] == 0
    assert b[0,0] == 0
    a[0,0] = 1
    assert b[0,0] == 1
    b[0,0] = 2
    assert a[0,0] == 2
    a[0,0] = 0
    assert b[0,0] == 0

    assert a[  -1,-1] == 10*3-1
    assert b[10-1,-1] == 10*3-1
    a[  -1,-1] = 1
    assert b[10-1,-1] == 1
    b[10-1,-1] = 2
    assert a[  -1,-1] == 2
    a[  -1,-1] = 10*3-1
    assert b[10-1,-1] == 10*3-1

    # we cannot access old mapping beyond it's end
    assert raises(IndexError, 'a[10,:]')

    # we can change tail
    b[10,:] = arange(10*3, (10+1)*3)

    # map it whole again and ensure we have correct data
    c = A[:]
    assert array_equal(c.ravel(), arange(11*3, dtype=uint32))
416 417 418 419 420 421 422 423 424 425 426 427


def test_bigarray_list():
    Z  = BigFile_Zero(PS)
    Zh = Z.fileh_open()
    A = BigArray((10,), uint8, Zh)

    # the IndexError for out-of-bound scalar access should allow, though
    # inefficient, for list(A) to work (instead of looping inside forever)
    l  = list(A)
    assert isinstance(l, list)
    assert l == [0]*10
428 429 430 431 432 433 434 435 436 437 438


def test_bigarray_to_ndarray():
    Z  = BigFile_Zero(PS)
    Zh = Z.fileh_open()
    A = BigArray((10,), uint8, Zh)

    # without IndexError on out-of-bound scalar access, the following
    # - would work with numpy-1.8
    # - would loop forever eating memory with numpy-1.9
    a = asarray(A)
439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455
    assert array_equal(a, A[:])


    # "medium"-sized array of 1TB. converting it to ndarray should work here
    # without hanging, becuse initially all data are unmapped, and we don't
    # touch mapped memory.
    B = BigArray((1<<40,), uint8, Zh)
    b = asarray(B)
    assert isinstance(b, ndarray)
    assert b.nbytes == 1<<40


    # array of size larger than virtual address space (~ 2^47 on linux/amd64)
    # converting it to ndarray is should be not possible
    for i in range(48,65):
        C = BigArray(((1<<i)-1,), uint8, Zh)
        raises(MemoryError, 'asarray(C)')