io.py 51.4 KB
Newer Older
(no author)'s avatar
(no author) committed
1
2
3
4
5
6
7
8
9
#!/usr/bin/env python
# encoding: utf-8
"""
I/O routines supporting reading a number of file formats.

Created by rayg Apr 2009.
Copyright (c) 2009 University of Wisconsin SSEC. All rights reserved.
"""

10
import os, logging
(no author)'s avatar
   
(no author) committed
11
12
13
import numpy as np

LOG = logging.getLogger(__name__)
(no author)'s avatar
(no author) committed
14

(no author)'s avatar
   
(no author) committed
15
16
17
18
19
20
21
22
23
try:
    import pyhdf
    from pyhdf.SD import SD,SDC, SDS, HDF4Error
except:
    LOG.info('no pyhdf module available for HDF4')
    pyhdf = None
    SD = SDC = SDS = object
    HDF4Error = EnvironmentError
    
24
25
try:
    import h5py
26
    from h5py import h5d
27
except ImportError:
(no author)'s avatar
   
(no author) committed
28
29
    LOG.info('no h5py module available for reading HDF5')
    h5py = None
(no author)'s avatar
(no author) committed
30

31
32
33
34
35
36
37
38
# the newer netCDF library that replaced pycdf
try:
    import netCDF4
except:
    LOG.info("unable to import netcdf4 library")
    netCDF4 = None

""" this is the previous netCDF library, remove this once the new one is fully tested
(no author)'s avatar
   
(no author) committed
39
40
41
42
43
44
45
46
47
try:    
    import pycdf
    from pycdf import CDF, NC, strerror
except:
    LOG.info('no pycdf module available')
    pycdf = None
    CDF = NC = object
    def strerror(*args):
        return 'no pycdf module installed'
48
"""
(no author)'s avatar
(no author) committed
49

(no author)'s avatar
(no author) committed
50
51
52
53
54
55
56
try:
    import dmv as dmvlib
    LOG.info('loaded dmv module for AERI data file access')
except ImportError:
    LOG.info('no AERI dmv data file format module')
    dmvlib = None

(no author)'s avatar
   
(no author) committed
57
58
59
60
61
62
63
try:
    import adl_blob
    LOG.info('adl_blob module found for JPSS ADL data file access')
except ImportError:
    LOG.info('no adl_blob format handler available')
    adl_blob = None

64
65
66
67
68
69
70
try :
    from osgeo import gdal
    LOG.info('loading osgeo module for GeoTIFF data file access')
except :
    LOG.info('no osgeo available for reading GeoTIFF data files')
    gdal = None

71
UNITS_CONSTANT = "units"
(no author)'s avatar
(no author) committed
72

73
74
75
fillValConst1 = '_FillValue'
fillValConst2 = 'missing_value'

76
77
78
79
ADD_OFFSET_STR   = 'add_offset'
SCALE_FACTOR_STR = 'scale_factor'
SCALE_METHOD_STR = 'scaling_method'

80
81
82
83
84
85
86
87
88
UNSIGNED_ATTR_STR = "_unsigned"

SIGNED_TO_UNSIGNED_DTYPES = {
                                np.dtype(np.int8):   np.dtype(np.uint8),
                                np.dtype(np.int16):   np.dtype(np.uint16),
                                np.dtype(np.int32):   np.dtype(np.uint32),
                                np.dtype(np.int64):   np.dtype(np.uint64),
                            }

89
90
91
92
93
94
95
96
97
98
99
class IOUnimplimentedError(Exception):
    """
    The exception raised when a requested io operation is not yet available.
    
        msg  -- explanation of the problem
    """
    def __init__(self, msg):
        self.msg = msg
    def __str__(self):
        return self.msg

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
class CaseInsensitiveAttributeCache (object) :
    """
    A cache of attributes for a single file and all of it's variables.
    This cache is considered uncased, it will store all attributes it caches
    in lower case and will lower case any strings it is asked to search for
    in the cache.
    When variable or global attribute sets are not yet loaded and something
    from that part of the file is requested the cache will transparently load
    attributes from the file behind the scenes and build the cache for that
    part of the file.
    """
    
    def __init__(self, fileObject) :
        """
        set up the empty cache and hang on to the file object we'll be caching
        """
        
        self.fileToCache             = fileObject
        self.globalAttributesLower   = None
        self.variableAttributesLower = { }
    
    def _load_global_attributes_if_needed (self) :
        """
        load up the global attributes if they need to be cached
        """
        
        # load the attributes from the file if they aren't cached
        if self.globalAttributesLower is None :
            LOG.debug ("Loading file global attributes into case-insensitive cache.")
            tempAttrs                  = self.fileToCache.get_global_attributes(caseInsensitive=False)
            self.globalAttributesLower = dict((k.lower(), v) for k, v in tempAttrs.items())
    
    def _load_variable_attributes_if_needed (self, variableName) :
        """
        load up the variable attributes if they need to be cached
        """
        
        # make a lower cased version of the variable name
        tempVariableName = variableName.lower()
        
        # load the variable's attributes from the file if they aren't cached
        if tempVariableName not in self.variableAttributesLower.keys() :
            LOG.debug ("Loading attributes for variable \"" + variableName + "\" into case-insensitive cache.")
            tempAttrs = self.fileToCache.get_variable_attributes(variableName, caseInsensitive=False)
            # now if there are any attributes, make a case insensitive version
            self.variableAttributesLower[tempVariableName] = dict((k.lower(), v) for k, v in tempAttrs.items())
    
    def get_variable_attribute (self, variableName, attributeName) :
        """
        get the specified attribute for the specified variable,
        if this variable's attributes have not yet been loaded
        they will be loaded and cached
        """
        
        self._load_variable_attributes_if_needed(variableName)
        
        toReturn = None
        tempVariableName  =  variableName.lower()
        tempAttributeName = attributeName.lower()
        if (tempVariableName in self.variableAttributesLower) and (tempAttributeName in self.variableAttributesLower[tempVariableName]) :
            toReturn = self.variableAttributesLower[tempVariableName][tempAttributeName]
        else:
            LOG.debug ("Attribute \"" + attributeName + "\" was not present for variable \"" + variableName + "\".")
        
        return toReturn
    
    def get_variable_attributes (self, variableName) :
        """
        get the variable attributes for the variable name given
        """
        
        self._load_variable_attributes_if_needed(variableName)
        
        toReturn = self.variableAttributesLower[variableName.lower()] if (variableName.lower() in self.variableAttributesLower) else None
        
        return toReturn
    
    def get_global_attribute (self, attributeName) :
        """
        get a global attribute with the given name
        """
        
        self._load_global_attributes_if_needed()
        
        toReturn = self.globalAttributesLower[attributeName.lower()] if (attributeName.lower() in self.globalAttributesLower) else None
        
        return toReturn
    
    def get_global_attributes (self) :
        """
        get the global attributes,
        """
        
        self._load_global_attributes_if_needed()
        
        toReturn = self.globalAttributesLower
        
        return toReturn
198
199
200
201
202
203
204
205
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
206
207

class hdf (object):
(no author)'s avatar
(no author) committed
208
209
210
211
212
    """wrapper for HDF4 dataset for comparison
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
213
214
    _hdf = None
    
215
    def __init__(self, filename, allowWrite=False):
216
        
(no author)'s avatar
   
(no author) committed
217
218
219
        if pyhdf is None:
            LOG.error('pyhdf is not installed and is needed in order to read hdf4 files')
            assert(pyhdf is not None)
220
221
222
        mode = SDC.READ
        if allowWrite:
            mode = mode | SDC.WRITE
223
224
225
        
        self._hdf = SD(filename, mode)
        self.attributeCache = CaseInsensitiveAttributeCache(self)
(no author)'s avatar
(no author) committed
226
227
228

    def __call__(self):
        "yield names of variables to be compared"
229
        return self._hdf.datasets().keys()
(no author)'s avatar
(no author) committed
230
    
231
232
233
234
    # this returns a numpy array with a copy of the full, scaled
    # data for this variable, if the data type must be changed to allow
    # for scaling it will be (so the return type may not reflect the
    # type found in the original file)
(no author)'s avatar
(no author) committed
235
    def __getitem__(self, name):
236
237
238
        # defaults
        scale_factor = 1.0
        add_offset = 0.0
239
        data_type = None 
(no author)'s avatar
(no author) committed
240
        scaling_method = None
241
242
243
244
245
246
247
248
249
        
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
        raw_data_copy = variable_object[:]
        try :
            # TODO, this currently won't work with geocat data, work around it for now
            scale_factor, scale_factor_error, add_offset, add_offset_error, data_type = SDS.getcal(variable_object)
        except HDF4Error:
250
251
252
253
            # load just the scale factor and add offset information by hand
            temp = self.attributeCache.get_variable_attributes(name)
            if ADD_OFFSET_STR in temp.keys() :
                add_offset = temp[ADD_OFFSET_STR]
254
                data_type = np.dtype(type(add_offset))
255
256
            if SCALE_FACTOR_STR in temp.keys() :
                scale_factor = temp[SCALE_FACTOR_STR]
257
                data_type = np.dtype(type(scale_factor))
258
259
            if SCALE_METHOD_STR in temp.keys() :
                scaling_method = temp[SCALE_METHOD_STR]
260
        SDS.endaccess(variable_object)
(no author)'s avatar
(no author) committed
261
        
262
263
264
265
        # don't do lots of work if we don't need to scale things
        if (scale_factor == 1.0) and (add_offset == 0.0) :
            return raw_data_copy
        
266
267
268
269
270
271
272
273
274
275
        # at the moment geocat has several scaling methods that don't match the normal standards for hdf
        """
        please see constant.f90 for a more up to date version of this information:
            INTEGER(kind=int1) :: NO_SCALE              ! 0
            INTEGER(kind=int1) :: LINEAR_SCALE          ! 1
            INTEGER(kind=int1) :: LOG_SCALE             ! 2
            INTEGER(kind=int1) :: SQRT_SCALE            ! 3 
        """
        if (scaling_method == 0) :
            return raw_data_copy
276
        if not ((scaling_method is None) or (int(scaling_method) <= 1)) :
277
278
            LOG.warn ('Scaling method of \"' + str(scaling_method) + '\" will be ignored in favor of hdf standard method. '
                      + 'This may cause problems with data consistency')
279
        
280
281
282
        # if we don't have a data type something strange has gone wrong
        assert(not (data_type is None))
        
283
284
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
285
        missing_mask = np.zeros(raw_data_copy.shape, dtype=np.bool)
286
287
        if missing_val is not None :
            missing_mask[raw_data_copy == missing_val] = True
288
        
289
        # create the scaled version of the data
290
        scaled_data_copy                = np.array(raw_data_copy, dtype=data_type)
291
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
292
293
294
295
        
        return scaled_data_copy 
    
    def get_variable_object(self, name):
296
        return self._hdf.select(name)
297
    
(no author)'s avatar
(no author) committed
298
    def missing_value(self, name):
299
        
300
        return self.get_attribute(name, fillValConst1)
301
302
303
304
305
306
307
308
309
    
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
(no author)'s avatar
(no author) committed
310
        
311
        raise IOUnimplimentedError('Unable to create variable in hdf file, this functionality is not yet available.')
312
313
314
315
316
317
318
319
        
        return None
    
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
320
321
        
        raise IOUnimplimentedError('Unable add attribute to hdf file, this functionality is not yet available.')
322
323
        
        return
324
    
325
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
326
327
328
329
        """
        returns all the attributes associated with a variable name
        """
        
330
331
332
333
334
335
336
        toReturn = None
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attributes()
        
        return toReturn
337
    
338
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
339
340
341
342
343
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
344
345
346
347
348
349
350
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attributes = self.get_variable_attributes(variableName, caseInsensitive=False)
            
            if attributeName in temp_attributes :
                toReturn = temp_attributes[attributeName]
351
352
        
        return toReturn
(no author)'s avatar
(no author) committed
353
    
354
355
356
357
358
359
360
361
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
        toReturn = None
        
        if caseInsensitive :
362
            toReturn = self.attributeCache.get_global_attributes()
363
364
365
366
367
368
        else :
            toReturn = self._hdf.attributes()
        
        return toReturn
    
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
369
370
371
372
373
374
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
375
376
377
378
379
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
            if attributeName in self._hdf.attributes() :
                toReturn = self._hdf.attributes()[attributeName]
(no author)'s avatar
(no author) committed
380
381
        
        return toReturn
382
383
384
385
386
387
388
389
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
(no author)'s avatar
(no author) committed
390

391
class nc (object):
392
    """wrapper for netcdf4-python data access for comparison
(no author)'s avatar
(no author) committed
393
394
395
396
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
397
    _nc = None
398
399
400
401
402
403
404
405
406
407
408
409
410
    _var_map = None

    # walk down through all groups and get variable names and objects
    def _walkgroups(self, start_at, prefix=None, ):
        here_vars = start_at.variables.keys()
        for var_name in here_vars:
            temp_name = var_name if prefix is None or len(prefix) <= 0 else prefix + "/" + var_name
            yield temp_name, start_at[var_name]
        here_groups = start_at.groups.keys()
        for group_name in here_groups:
            grp_str = group_name if prefix is None or len(prefix) <= 0 else prefix + "/" + group_name
            for more_var_name, more_var_obj in self._walkgroups(start_at.groups[group_name], prefix=grp_str):
                yield more_var_name, more_var_obj
411
    
412
413
    def __init__(self, filename, allowWrite=False):
        
414
415
416
        if netCDF4 is None:
            LOG.error('netCDF4 is not installed and is needed in order to read NetCDF files')
            assert(netCDF4 is not None)
(no author)'s avatar
   
(no author) committed
417
        
418
        mode = 'r'
419
        if allowWrite :
420
            mode = 'w'
421
        
422
        self._nc = netCDF4.Dataset(filename, mode)
423
        self.attributeCache = CaseInsensitiveAttributeCache(self)
424
425
426
        self._var_map = { }
        for var_name, var_obj in self._walkgroups(self._nc,) :
            self._var_map[var_name] = var_obj
427

(no author)'s avatar
(no author) committed
428
    def __call__(self):
429
430
431
432
433
434
        """
        yield names of variables in this file
        """

        return self._var_map.keys()

(no author)'s avatar
(no author) committed
435
    def __getitem__(self, name):
436
437
438
439
440
441
442
        """
        this returns a numpy array with a copy of the full, scaled
        data for this variable, if the data type must be changed to allow
        for scaling it will be (so the return type may not reflect the
        type found in the original file)
        """

443
        # defaults
444
        data_type = np.float32 # TODO temporary this avoids type truncation issues, but is not a general solution
445
446
447
448
        
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
449

450
451
452
453
454
        # get our data, save the dtype, and make sure it's a more flexible dtype for now
        variable_object.set_auto_maskandscale(False)  # for now just do the darn calculations ourselves
        scaled_data_copy = np.array(variable_object[:], dtype=data_type)

        # get the attribute cache so we can check on loading related attributes
455
        temp = self.attributeCache.get_variable_attributes(name)
456
457
458
459

        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
        missing_mask = np.zeros(scaled_data_copy.shape, dtype=np.bool)
460
461
        if missing_val is not None:
            missing_mask[scaled_data_copy == missing_val] = True
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478

        #***** just do the darn unsigned handling ourselves, ugh

        # if our data is labeled as being unsigned by the appropriately set attribute
        if UNSIGNED_ATTR_STR in temp.keys() and str(temp[UNSIGNED_ATTR_STR]).lower() == ("true"):
            LOG.debug("Correcting for unsigned values in variable data.")
            where_temp = (scaled_data_copy < 0.0) & ~missing_mask # where we have negative but not missing data
            scaled_data_copy[where_temp] += (np.iinfo(np.uint16).max + 1.0) # add the 2's complement

        #***** end of handling the unsigned attribute

        ###### the start of the scaling code
        # Note, I had to turn this back on because the netcdf4 library is behaving erratically when unsigned is set

        # get the scale factor and add offset from the attributes
        scale_factor = 1.0
        add_offset = 0.0
479
480
481
482
        if SCALE_FACTOR_STR in temp.keys() :
            scale_factor = temp[SCALE_FACTOR_STR]
        if ADD_OFFSET_STR in temp.keys() :
            add_offset = temp[ADD_OFFSET_STR]
483

484
485
        # don't do work if we don't need to unpack things
        if (scale_factor != 1.0) or (add_offset != 0.0) :
486

487
            LOG.debug("Manually applying scale (" + str(scale_factor) + ") and add offset (" + str(add_offset) + ").")
488

489
490
491
492
493
494
495
            # unpack the data
            scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset

        ###### end of the scaling code

        """
        #TODO, this section was for when we had to do the unsigned correction after unpacking
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
        if UNSIGNED_ATTR_STR in temp.keys() and str(temp[UNSIGNED_ATTR_STR]).lower() == ( "true" ) :

            LOG.debug("fixing unsigned values in variable " + name)

            # load the scale factor and add offset
            scale_factor = 1.0
            add_offset = 0.0
            temp = self.attributeCache.get_variable_attributes(name)
            if SCALE_FACTOR_STR in temp.keys() :
                scale_factor = temp[SCALE_FACTOR_STR]
            if ADD_OFFSET_STR in temp.keys() :
                add_offset = temp[ADD_OFFSET_STR]

            # get the missing value and figure out the dtype of the original data
            missing_val  = self.missing_value(name)
            orig_dtype   = np.array([missing_val,]).dtype
            needed_dtype = SIGNED_TO_UNSIGNED_DTYPES[orig_dtype] if orig_dtype in SIGNED_TO_UNSIGNED_DTYPES.keys() else None

            if needed_dtype is not None :
                # now figure out where all the corrupted values are, and shift them up to be positive
516
                needs_fix_mask = (scaled_data_copy < add_offset) & (scaled_data_copy != missing_val)
517
                # we are adding the 2's complement, but first we're scaling it appropriately
518
                scaled_data_copy[needs_fix_mask] += ((np.iinfo(np.uint16).max + 1.0) * scale_factor)
519
        """
520

521
        return scaled_data_copy
522
    
523
524
525
526
    # TODO, this hasn't been supported in other file types
    def close (self) :
        self._nc.close()
        self._nc = None
527
        self._var_map = None
528

529
    def get_variable_object(self, name):
530

531
        return self._var_map[name]
532
    
(no author)'s avatar
(no author) committed
533
    def missing_value(self, name):
534
        
535
536
537
538
539
540
541
542
543
544
545
        toReturn = None
        
        temp = self.attributeCache.get_variable_attribute(name, fillValConst1)
        if temp is not None :
            toReturn = temp
        else :
            temp = self.attributeCache.get_variable_attribute(name, fillValConst2)
            if temp is not None :
                toReturn = temp
        
        return toReturn
546

547
548
549
550
551
552
553
554
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
555
556

        # TODO, this will not work with groups
557
        self._nc.nc_redef()
558
559
        
        # if the variable already exists, stop with a warning
560
        if variablename in self._nc.variables.keys() :
561
562
563
            LOG.warn("New variable name requested (" + variablename + ") is already present in file. " +
                     "Skipping generation of new variable.")
            return None
564
565
566
567
568
        # if we have no data we won't be able to determine the data type to create the variable
        if (data is None) or (len(data) <= 0) :
            LOG.warn("Data type for new variable (" + variablename + ") could not be determined. " +
                     "Skipping generation of new variable.")
            return None
569
570
571
        
        dataType = None
        if np.issubdtype(data.dtype, int) :
572
            dataType = np.int
573
574
575
            #print("Picked INT")
        # TODO, at the moment the fill type is forcing me to use a double, when sometimes I want a float
        #elif np.issubdtype(data.dtype, np.float32) :
576
        #    dataType = np.float
577
578
        #    print("Picked FLOAT")
        elif np.issubdtype(data.dtype, float) :
579
            dataType = np.float64
580
581
582
583
584
585
586
            #print("Picked DOUBLE")
        # what do we do if it's some other type?
        
        # create and set all the dimensions
        dimensions = [ ]
        dimensionNum = 0
        for dimSize in data.shape :
587
            dimensions.append(self._nc.createDimension(variablename + '-index' + str(dimensionNum), dimSize))
588
589
590
            dimensionNum = dimensionNum + 1
        
        # create the new variable
591
592
593
        #print('variable name: ' + variablename)
        #print('data type:     ' + str(dataType))
        #print('dimensions:    ' + str(dimensions))
594
        newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions))
595
596
597
598
599
600
601
        
        # if a missing value was given, use that
        if missingvalue is not None :
            newVariable._FillValue = missingvalue
        
        # if we have a variable to copy attributes from, do so
        if variabletocopyattributesfrom is not None :
602
603
            attributes = self.get_variable_attributes(variabletocopyattributesfrom, caseInsensitive=False)

604
            for attribute in attributes.keys() :
605
606
607
608
                setattr(newVariable, attribute, attributes[attribute])

        self._nc.nc_enddef()

609
610
        # if data was given, use that
        if data is not None :
611
612
            newVariable[:](data.tolist())

613
        return newVariable
614

615
616
617
618
619
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
620
621
        # TODO, this will not work with groups

622
623
        variableObject = self.get_variable_object(variableName)
        
624
625
626
627
628
629
        self._nc.nc_redef()

        setattr(variableObject, newAttributeName, newAttributeValue)

        self._nc.nc_enddef()

630
631
632
        # TODO, this will cause our attribute cache to be wrong!
        # TODO, for now, brute force clear the cache
        self.attributeCache = CaseInsensitiveAttributeCache(self)
633
634
        
        return
635
    
636
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
637
638
639
640
        """
        returns all the attributes associated with a variable name
        """
        
641
642
643
644
645
        toReturn = None
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
646
647
648
649
650
            toReturn = { }
            tempVarObj   = self.get_variable_object(variableName)
            tempAttrKeys = tempVarObj.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(tempVarObj, attrKey)
651
652
        
        return toReturn
653
    
654
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
655
656
657
658
659
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
660
661
662
663
664
665
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attributes = self.get_variable_attributes(variableName, caseInsensitive=False)
            
            if attributeName in temp_attributes :
666
                toReturn = getattr(self.get_variable_object, attributeName)
667
668
669
670
671
672
673
674
675
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
        toReturn = None
676
        
677
        if caseInsensitive :
678
            toReturn = self.attributeCache.get_global_attributes()
679
        else :
680
681
682
683
            toReturn = { }
            tempAttrKeys = self._nc.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(self._nc, attrKey)
684

685
        return toReturn
686
    
687
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
688
689
690
691
692
693
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
694
695
696
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
697
            if attributeName in self._nc.ncattrs() :
698
                toReturn = getattr(self._nc, attributeName)
699
700
        
        return toReturn
701
702
703
704
705
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
706
707

        return True
708

(no author)'s avatar
(no author) committed
709
710
711
nc4 = nc
cdf = nc

712
713
# TODO remove
#FIXME_IDPS = [ '/All_Data/CrIS-SDR_All/ES' + ri + band for ri in ['Real','Imaginary'] for band in ['LW','MW','SW'] ] 
714

(no author)'s avatar
(no author) committed
715
class h5(object):
716
717
718
719
    """wrapper for HDF5 datasets
    """
    _h5 = None
    
720
    def __init__(self, filename, allowWrite=False):
721
722
        self.attributeCache = CaseInsensitiveAttributeCache(self)
        
723
724
725
        mode = 'r'
        if allowWrite :
            mode = 'r+'
(no author)'s avatar
   
(no author) committed
726
727
728
        if h5py is None:
            LOG.error('h5py module is not installed and is needed in order to read h5 files')
            assert(h5py is not None)
729
        self._h5 = h5py.File(filename, mode)
730
731
    
    def __call__(self):
732
733
734
735
        
        variableList = [ ]
        def testFn (name, obj) :
            #print ('checking name: ' + name)
736
            #print ('object: ' + str(obj))
737
738
739
740
            
            if isinstance(obj, h5py.Dataset) :
                try :
                    tempType = obj.dtype # this is required to provoke a type error for closed data sets
741
                    
742
                    #LOG.debug ('type: ' + str(tempType))
743
744
745
746
747
748
749
750
751
752
                    variableList.append(name)
                except TypeError :
                    LOG.debug('TypeError prevents the use of variable ' + name
                              + '. This variable will be ignored')
        
        self._h5.visititems(testFn)
        
        LOG.debug('variables from visiting h5 file structure: ' + str(variableList))
        
        return(variableList)
753
754
755
756
757
    
    @staticmethod
    def trav(h5,pth): 
        return reduce( lambda x,a: x[a] if a else x, pth.split('/'), h5)
        
758
759
760
761
762
    # this returns a numpy array with a copy of the full, scaled
    # data for this variable, if the data type must be changed to allow
    # for scaling it will be (so the return type may not reflect the
    # type found in the original file)
    def __getitem__(self, name):
763
        
764
765
766
767
768
769
770
771
772
        # defaults
        scale_factor = 1.0
        add_offset = 0.0
        data_type = np.float32 # TODO temporary
        
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
        raw_data_copy = variable_object[:]
773
774
775
776
777
        
        #print ('*************************')
        #print (dir (variable_object.id)) # TODO, is there a way to get the scale and offset through this?
        #print ('*************************')
        
778
        # load the scale factor and add offset
779
780
781
782
783
        temp = self.attributeCache.get_variable_attributes(name)
        if (SCALE_FACTOR_STR in temp.keys()) :
            scale_factor = temp[SCALE_FACTOR_STR]
        if (ADD_OFFSET_STR in temp.keys()) :
            add_offset = temp[ADD_OFFSET_STR]
784
785
786
787
788
789
        # todo, does cdf have an equivalent of endaccess to close the variable?
        
        # don't do lots of work if we don't need to scale things
        if (scale_factor == 1.0) and (add_offset == 0.0) :
            return raw_data_copy
        
790
791
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
792
        missing_mask = np.zeros(raw_data_copy.shape, dtype=np.bool)
793
794
        if missing_val is not None:
            missing_mask[raw_data_copy == missing_val] = True
795
        
796
797
        # create the scaled version of the data
        scaled_data_copy = np.array(raw_data_copy, dtype=data_type)
798
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
799
800
801
802
        
        return scaled_data_copy
    
    def get_variable_object(self,name):
803
804
805
        return h5.trav(self._h5, name)
    
    def missing_value(self, name):
806
807
808
809
810
811
812
813
814
815
816
817
818
        
        toReturn = None
        
        # get the missing value if it has been set
        variableObject = self.get_variable_object(name)
        pListObj = variableObject.id.get_create_plist()
        fillValueStatus = pListObj.fill_value_defined()
        if (h5d.FILL_VALUE_DEFAULT is fillValueStatus) or (h5d.FILL_VALUE_USER_DEFINED is fillValueStatus) :
            temp = np.array((1), dtype=variableObject.dtype)
            pListObj.get_fill_value(temp)
            toReturn = temp
        
        return toReturn
819
820
821
822
823
824
825
826
827
    
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
828
        
829
        raise IOUnimplimentedError('Unable to create variable in hdf 5 file, this functionality is not yet available.')
830
831
832
833
834
835
836
837
        
        return None
    
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
838
839
        
        raise IOUnimplimentedError('Unable to add attribute to hdf 5 file, this functionality is not yet available.')
840
841
        
        return
842
    
843
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
844
845
846
847
        """
        returns all the attributes associated with a variable name
        """
        
848
849
850
851
852
853
854
855
        toReturn = None
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attrs
        
        return toReturn
856
    
857
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
858
859
860
861
862
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attrs = self.get_variable_attributes(variableName, caseInsensitive=False)
            
            if (attributeName in temp_attrs) :
                toReturn = temp_attrs[attributeName]
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
        toReturn = None
879
        
880
        if caseInsensitive :
881
            toReturn = self.attributeCache.get_global_attributes()
882
883
        else :
            toReturn = self._h5.attrs
884
885
        
        return toReturn
(no author)'s avatar
(no author) committed
886
    
887
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
888
889
890
891
892
893
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
894
895
896
897
898
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
            if attributeName in self._h5.attrs :
                toReturn = self._h5.attrs[attributeName]
(no author)'s avatar
(no author) committed
899
900
        
        return toReturn
901
902
903
904
905
906
907
908
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
(no author)'s avatar
(no author) committed
909

(no author)'s avatar
(no author) committed
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979

class aeri(object):
    """wrapper for AERI RNC/SUM/CXS/etc datasets
    """
    _dmv = None
    _vectors = { }
    _scalars = { }
    
    @staticmethod
    def _meta_mapping(fp):
        ids = fp.metaIDs()
        names = [fp.queryMetaDescString(1, id_, fp.SHORTNAME) for id_ in ids]
        assert len(ids) == len(names)
        return (dict((n, i) for n, i in zip(names, ids)))
    
    def _inventory(self):
        fp = self._dmv
        assert(fp is not None)
        # get list of vectors and scalars
        self._vectors = dict( (fp.queryVectorDescString(n,fp.SHORTNAME), n) for n in fp.vectorIDs() )
        self._scalars = self._meta_mapping(fp)

    def __init__(self, filename, allowWrite=False):
        assert(allowWrite==False)
        if dmvlib is None:
            LOG.error('cannot open AERI files without dmv module being available')
            return
        self._dmv = dmvlib.dmv()
        rc = self._dmv.openFile(filename)
        if rc!=0:
            LOG.error("unable to open file, rc=%d" % rc)
            self._dmv = None        
        else:
            self._inventory()
    
    def __call__(self):
        return list(self._vectors.keys()) + list(self._scalars.keys())
        
    def __getitem__(self, name):
        fp = self._dmv
        assert(fp is not None)
        if 'DMV_RECORDS' in os.environ:
            nrecs = int(os.environ['DMV_RECORDS'])
            LOG.warning('overriding dmv record count to %d' % nrecs)
        else:
            nrecs = self._dmv.recordCount()
        recrange = range(1, nrecs+1)
        if name in self._vectors:
            vid = self._vectors[name]
            vdata = [ fp.vectorDepValues(rec, vid) for rec in recrange ]
            return np.array(vdata)
        elif name in self._scalars:
            vdata = fp.metaValueMatrix(recrange, [self._scalars[name]])
            return np.array(vdata)
        else:
            raise LookupError('cannot find variable %s' % name)
       
    def get_variable_object(self,name):
        return None
    
    def missing_value(self, name):
        return float('nan')
    
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
980
981
982
983
        """
        
        raise IOUnimplimentedError('Unable to create variable in aeri file, this functionality is not yet available.')
        
(no author)'s avatar
(no author) committed
984
985
986
987
988
989
990
991
        return None
    
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
        
992
993
        raise IOUnimplimentedError('Unable to add attribute to aeri file, this functionality is not yet available.')
        
(no author)'s avatar
(no author) committed
994
        return
995
    
996
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
997
998
999
1000
        """
        returns all the attributes associated with a variable name
        """
        toReturn = { }
For faster browsing, not all history is shown. View entire blame