File: h5d.pyx

package info (click to toggle)
h5py 2.10.0-9
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 2,320 kB
  • sloc: python: 8,594; ansic: 718; makefile: 387; sh: 26
file content (498 lines) | stat: -rw-r--r-- 17,227 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
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
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
# This file is part of h5py, a Python interface to the HDF5 library.
#
# http://www.h5py.org
#
# Copyright 2008-2013 Andrew Collette and contributors
#
# License:  Standard 3-clause BSD; see "license.txt" for full license terms
#           and contributor agreement.
"""
    Provides access to the low-level HDF5 "H5D" dataset interface.
"""

include "config.pxi"

# Compile-time imports
from _objects cimport pdefault
from numpy cimport ndarray, import_array, PyArray_DATA, NPY_WRITEABLE
from cpython cimport array
from utils cimport  check_numpy_read, check_numpy_write, \
                    convert_tuple, emalloc, efree
from h5t cimport TypeID, typewrap, py_create
from h5s cimport SpaceID
from h5p cimport PropID, propwrap
from _proxy cimport dset_rw

from ._objects import phil, with_phil

# Initialization
import_array()

# === Public constants and data structures ====================================

COMPACT     = H5D_COMPACT
CONTIGUOUS  = H5D_CONTIGUOUS
CHUNKED     = H5D_CHUNKED

ALLOC_TIME_DEFAULT  = H5D_ALLOC_TIME_DEFAULT
ALLOC_TIME_LATE     = H5D_ALLOC_TIME_LATE
ALLOC_TIME_EARLY    = H5D_ALLOC_TIME_EARLY
ALLOC_TIME_INCR     = H5D_ALLOC_TIME_INCR

SPACE_STATUS_NOT_ALLOCATED  = H5D_SPACE_STATUS_NOT_ALLOCATED
SPACE_STATUS_PART_ALLOCATED = H5D_SPACE_STATUS_PART_ALLOCATED
SPACE_STATUS_ALLOCATED      = H5D_SPACE_STATUS_ALLOCATED

FILL_TIME_ALLOC = H5D_FILL_TIME_ALLOC
FILL_TIME_NEVER = H5D_FILL_TIME_NEVER
FILL_TIME_IFSET = H5D_FILL_TIME_IFSET

FILL_VALUE_UNDEFINED    = H5D_FILL_VALUE_UNDEFINED
FILL_VALUE_DEFAULT      = H5D_FILL_VALUE_DEFAULT
FILL_VALUE_USER_DEFINED = H5D_FILL_VALUE_USER_DEFINED

IF HDF5_VERSION >= VDS_MIN_HDF5_VERSION:
    VIRTUAL = H5D_VIRTUAL
    VDS_FIRST_MISSING   = H5D_VDS_FIRST_MISSING
    VDS_LAST_AVAILABLE  = H5D_VDS_LAST_AVAILABLE

# === Dataset operations ======================================================

@with_phil
def create(ObjectID loc not None, object name, TypeID tid not None,
               SpaceID space not None, PropID dcpl=None, PropID lcpl=None, PropID dapl = None):
        """ (objectID loc, STRING name or None, TypeID tid, SpaceID space,
             PropDCID dcpl=None, PropID lcpl=None) => DatasetID

        Create a new dataset.  If "name" is None, the dataset will be
        anonymous.
        """
        cdef hid_t dsid
        cdef char* cname = NULL
        if name is not None:
            cname = name

        if cname != NULL:
            dsid = H5Dcreate2(loc.id, cname, tid.id, space.id,
                     pdefault(lcpl), pdefault(dcpl), pdefault(dapl))
        else:
            dsid = H5Dcreate_anon(loc.id, tid.id, space.id,
                     pdefault(dcpl), pdefault(dapl))
        return DatasetID(dsid)

@with_phil
def open(ObjectID loc not None, char* name, PropID dapl=None):
    """ (ObjectID loc, STRING name, PropID dapl=None) => DatasetID

    Open an existing dataset attached to a group or file object, by name.

    If specified, dapl may be a dataset access property list.
    """
    return DatasetID(H5Dopen2(loc.id, name, pdefault(dapl)))

# --- Proxy functions for safe(r) threading -----------------------------------


cdef class DatasetID(ObjectID):

    """
        Represents an HDF5 dataset identifier.

        Objects of this class may be used in any HDF5 function which expects
        a dataset identifier.  Also, all H5D* functions which take a dataset
        instance as their first argument are presented as methods of this
        class.

        Properties:
        dtype:  Numpy dtype representing the dataset type
        shape:  Numpy-style shape tuple representing the dataspace
        rank:   Integer giving dataset rank

        * Hashable: Yes, unless anonymous
        * Equality: True HDF5 identity if unless anonymous
    """

    property dtype:
        """ Numpy dtype object representing the dataset type """
        def __get__(self):
            # Dataset type can't change
            cdef TypeID tid
            with phil:
                if self._dtype is None:
                    tid = self.get_type()
                    self._dtype = tid.dtype
                return self._dtype

    property shape:
        """ Numpy-style shape tuple representing the dataspace """
        def __get__(self):
            # Shape can change (DatasetID.extend), so don't cache it
            cdef SpaceID sid
            with phil:
                sid = self.get_space()
                return sid.get_simple_extent_dims()

    property rank:
        """ Integer giving the dataset rank (0 = scalar) """
        def __get__(self):
            cdef SpaceID sid
            with phil:
                sid = self.get_space()
                return sid.get_simple_extent_ndims()


    @with_phil
    def read(self, SpaceID mspace not None, SpaceID fspace not None,
                   ndarray arr_obj not None, TypeID mtype=None,
                   PropID dxpl=None):
        """ (SpaceID mspace, SpaceID fspace, NDARRAY arr_obj,
             TypeID mtype=None, PropDXID dxpl=None)

            Read data from an HDF5 dataset into a Numpy array.

            It is your responsibility to ensure that the memory dataspace
            provided is compatible with the shape of the Numpy array.  Since a
            wide variety of dataspace configurations are possible, this is not
            checked.  You can easily crash Python by reading in data from too
            large a dataspace.

            If a memory datatype is not specified, one will be auto-created
            based on the array's dtype.

            The provided Numpy array must be writable and C-contiguous.  If
            this is not the case, ValueError will be raised and the read will
            fail.  Keyword dxpl may be a dataset transfer property list.
        """
        cdef hid_t self_id, mtype_id, mspace_id, fspace_id, plist_id
        cdef void* data
        cdef int oldflags

        if mtype is None:
            mtype = py_create(arr_obj.dtype)
        check_numpy_write(arr_obj, -1)

        self_id = self.id
        mtype_id = mtype.id
        mspace_id = mspace.id
        fspace_id = fspace.id
        plist_id = pdefault(dxpl)
        data = PyArray_DATA(arr_obj)

        dset_rw(self_id, mtype_id, mspace_id, fspace_id, plist_id, data, 1)


    @with_phil
    def write(self, SpaceID mspace not None, SpaceID fspace not None,
                    ndarray arr_obj not None, TypeID mtype=None,
                    PropID dxpl=None):
        """ (SpaceID mspace, SpaceID fspace, NDARRAY arr_obj,
             TypeID mtype=None, PropDXID dxpl=None)

            Write data from a Numpy array to an HDF5 dataset. Keyword dxpl may
            be a dataset transfer property list.

            It is your responsibility to ensure that the memory dataspace
            provided is compatible with the shape of the Numpy array.  Since a
            wide variety of dataspace configurations are possible, this is not
            checked.  You can easily crash Python by writing data from too
            large a dataspace.

            If a memory datatype is not specified, one will be auto-created
            based on the array's dtype.

            The provided Numpy array must be C-contiguous.  If this is not the
            case, ValueError will be raised and the read will fail.
        """
        cdef hid_t self_id, mtype_id, mspace_id, fspace_id, plist_id
        cdef void* data
        cdef int oldflags

        if mtype is None:
            mtype = py_create(arr_obj.dtype)
        check_numpy_read(arr_obj, -1)

        self_id = self.id
        mtype_id = mtype.id
        mspace_id = mspace.id
        fspace_id = fspace.id
        plist_id = pdefault(dxpl)
        data = PyArray_DATA(arr_obj)

        dset_rw(self_id, mtype_id, mspace_id, fspace_id, plist_id, data, 0)


    @with_phil
    def extend(self, tuple shape):
        """ (TUPLE shape)

            Extend the given dataset so it's at least as big as "shape".  Note
            that a dataset may only be extended up to the maximum dimensions of
            its dataspace, which are fixed when the dataset is created.
        """
        cdef int rank
        cdef hid_t space_id = 0
        cdef hsize_t* dims = NULL

        try:
            space_id = H5Dget_space(self.id)
            rank = H5Sget_simple_extent_ndims(space_id)

            if len(shape) != rank:
                raise TypeError("New shape length (%d) must match dataset rank (%d)" % (len(shape), rank))

            dims = <hsize_t*>emalloc(sizeof(hsize_t)*rank)
            convert_tuple(shape, dims, rank)
            H5Dextend(self.id, dims)

        finally:
            efree(dims)
            if space_id:
                H5Sclose(space_id)


    @with_phil
    def set_extent(self, tuple shape):
        """ (TUPLE shape)

            Set the size of the dataspace to match the given shape.  If the new
            size is larger in any dimension, it must be compatible with the
            maximum dataspace size.
        """
        cdef int rank
        cdef hid_t space_id = 0
        cdef hsize_t* dims = NULL

        try:
            space_id = H5Dget_space(self.id)
            rank = H5Sget_simple_extent_ndims(space_id)

            if len(shape) != rank:
                raise TypeError("New shape length (%d) must match dataset rank (%d)" % (len(shape), rank))

            dims = <hsize_t*>emalloc(sizeof(hsize_t)*rank)
            convert_tuple(shape, dims, rank)
            H5Dset_extent(self.id, dims)

        finally:
            efree(dims)
            if space_id:
                H5Sclose(space_id)


    @with_phil
    def get_space(self):
        """ () => SpaceID

            Create and return a new copy of the dataspace for this dataset.
        """
        return SpaceID(H5Dget_space(self.id))


    @with_phil
    def get_space_status(self):
        """ () => INT space_status_code

            Determine if space has been allocated for a dataset.
            Return value is one of:

            * SPACE_STATUS_NOT_ALLOCATED
            * SPACE_STATUS_PART_ALLOCATED
            * SPACE_STATUS_ALLOCATED
        """
        cdef H5D_space_status_t status
        H5Dget_space_status(self.id, &status)
        return <int>status


    @with_phil
    def get_type(self):
        """ () => TypeID

            Create and return a new copy of the datatype for this dataset.
        """
        return typewrap(H5Dget_type(self.id))


    @with_phil
    def get_create_plist(self):
        """ () => PropDCID

            Create an return a new copy of the dataset creation property list
            used when this dataset was created.
        """
        return propwrap(H5Dget_create_plist(self.id))


    @with_phil
    def get_access_plist(self):
        """ () => PropDAID

            Create an return a new copy of the dataset access property list.
        """
        return propwrap(H5Dget_access_plist(self.id))


    @with_phil
    def get_offset(self):
        """ () => LONG offset or None

            Get the offset of this dataset in the file, in bytes, or None if
            it doesn't have one.  This is always the case for datasets which
            use chunked storage, compact datasets, and datasets for which space
            has not yet been allocated in the file.
        """
        cdef haddr_t offset
        offset = H5Dget_offset(self.id)
        if offset == HADDR_UNDEF:
            return None
        return offset


    @with_phil
    def get_storage_size(self):
        """ () => LONG storage_size

            Determine the amount of file space required for a dataset.  Note
            this only counts the space which has actually been allocated; it
            may even be zero.
        """
        return H5Dget_storage_size(self.id)

    IF HDF5_VERSION >= SWMR_MIN_HDF5_VERSION:

        @with_phil
        def flush(self):
            """ no return

            Flushes all buffers associated with a dataset to disk.

            This function causes all buffers associated with a dataset to be
            immediately flushed to disk without removing the data from the cache.

            Use this in SWMR write mode to allow readers to be updated with the
            dataset changes.

            Feature requires: 1.9.178 HDF5
            """
            H5Dflush(self.id)

        @with_phil
        def refresh(self):
            """ no return

            Refreshes all buffers associated with a dataset.

            This function causes all buffers associated with a dataset to be
            cleared and immediately re-loaded with updated contents from disk.

            This function essentially closes the dataset, evicts all metadata
            associated with it from the cache, and then re-opens the dataset.
            The reopened dataset is automatically re-registered with the same ID.

            Use this in SWMR read mode to poll for dataset changes.

            Feature requires: 1.9.178 HDF5
            """
            H5Drefresh(self.id)


    IF HDF5_VERSION >= (1, 8, 11):

        def write_direct_chunk(self, offsets, bytes data, filter_mask=0x00000000, PropID dxpl=None):
            """ (offsets, bytes data, uint32_t filter_mask=0x00000000, PropID dxpl=None)

            This function bypasses any filters HDF5 would normally apply to
            written data. However, calling code may apply filters (e.g. gzip
            compression) itself before writing the data.

            `filter_mask` is a bit field of up to 32 values. It records which
            filters have been applied to this chunk, of the filter pipeline
            defined for that dataset. Each bit set to `1` means that the filter
            in the corresponding position in the pipeline was not applied.
            So the default value of `0` means that all defined filters have
            been applied to the data before calling this function.

            Feature requires: 1.8.11 HDF5
            """

            cdef hid_t dset_id
            cdef hid_t dxpl_id
            cdef hid_t space_id = 0
            cdef hsize_t *offset = NULL
            cdef size_t data_size
            cdef int rank

            dset_id = self.id
            dxpl_id = pdefault(dxpl)
            space_id = H5Dget_space(self.id)
            rank = H5Sget_simple_extent_ndims(space_id)

            if len(offsets) != rank:
                raise TypeError("offset length (%d) must match dataset rank (%d)" % (len(offsets), rank))

            try:
                offset = <hsize_t*>emalloc(sizeof(hsize_t)*rank)
                convert_tuple(offsets, offset, rank)
                H5DOwrite_chunk(dset_id, dxpl_id, filter_mask, offset, len(data), <char *> data)
            finally:
                efree(offset)
                if space_id:
                    H5Sclose(space_id)

    IF HDF5_VERSION >= (1, 10, 2):

        def read_direct_chunk(self, offsets, PropID dxpl=None):
            """ (offsets, PropID dxpl=None)

            Reads data to a bytes array directly from a chunk at position
            specified by the `offsets` argument and bypasses any filters HDF5
            would normally apply to the written data. However, the written data
            may be compressed or not.

            Returns a tuple containing the `filter_mask` and the bytes data
            which are the raw data storing this chuck.

            `filter_mask` is a bit field of up to 32 values. It records which
            filters have been applied to this chunk, of the filter pipeline
            defined for that dataset. Each bit set to `1` means that the filter
            in the corresponding position in the pipeline was not applied to
            compute the raw data. So the default value of `0` means that all
            defined filters have been applied to the raw data.

            Feature requires: 1.10.2 HDF5
            """

            cdef hid_t dset_id
            cdef hid_t dxpl_id
            cdef hid_t space_id = 0
            cdef hsize_t *offset = NULL
            cdef size_t data_size
            cdef int rank
            cdef uint32_t filters
            cdef hsize_t read_chunk_nbytes
            cdef array.array data = array.array('B')

            dset_id = self.id
            dxpl_id = pdefault(dxpl)
            space_id = H5Dget_space(self.id)
            rank = H5Sget_simple_extent_ndims(space_id)

            if len(offsets) != rank:
                raise TypeError("offset length (%d) must match dataset rank (%d)" % (len(offsets), rank))

            try:
                offset = <hsize_t*>emalloc(sizeof(hsize_t)*rank)
                convert_tuple(offsets, offset, rank)
                H5Dget_chunk_storage_size(dset_id, offset, &read_chunk_nbytes)
                array.resize(data, read_chunk_nbytes)

                IF HDF5_VERSION >= (1, 10, 3):
                    H5Dread_chunk(dset_id, dxpl_id, offset, &filters, data.data.as_voidptr)
                ELSE:
                    H5DOread_chunk(dset_id, dxpl_id, offset, &filters, data.data.as_voidptr)
            finally:
                efree(offset)
                if space_id:
                    H5Sclose(space_id)

            return filters, bytes(data)