io.py 48.9 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
11
import numpy
12
from functools import reduce
(no author)'s avatar
   
(no author) committed
13
14

LOG = logging.getLogger(__name__)
(no author)'s avatar
(no author) committed
15

16
Loadable_Types = set()
(no author)'s avatar
   
(no author) committed
17
    
18
19
try:
    import h5py
20
    from h5py import h5d
21
    Loadable_Types.add("h5")
22
except ImportError:
(no author)'s avatar
   
(no author) committed
23
24
    LOG.info('no h5py module available for reading HDF5')
    h5py = None
(no author)'s avatar
(no author) committed
25

26
27
28
# the newer netCDF library that replaced pycdf
try:
    import netCDF4
29
    Loadable_Types.update(["nc", "nc4", "cdf", "hdf", ])
30
31
32
33
except:
    LOG.info("unable to import netcdf4 library")
    netCDF4 = None

(no author)'s avatar
(no author) committed
34
35
36
try:
    import dmv as dmvlib
    LOG.info('loaded dmv module for AERI data file access')
37
    Loadable_Types.update(["cxs", "rnc", "cxv", "csv", "spc", "sum", "uvs", "aeri", ])
(no author)'s avatar
(no author) committed
38
39
40
41
except ImportError:
    LOG.info('no AERI dmv data file format module')
    dmvlib = None

42
# DEPRECATED, will be removed in future!
(no author)'s avatar
   
(no author) committed
43
44
45
try:
    import adl_blob
    LOG.info('adl_blob module found for JPSS ADL data file access')
46
47
48
    LOG.warning('DEPRECATED: you have an adl_blob module installed; '
                'loading JPSS ADL data files is DEPRECATED and will be '
                'removed in a future version of Glance')
(no author)'s avatar
   
(no author) committed
49
50
51
52
except ImportError:
    LOG.info('no adl_blob format handler available')
    adl_blob = None

53
54
55
try :
    from osgeo import gdal
    LOG.info('loading osgeo module for GeoTIFF data file access')
56
    Loadable_Types.update(["tiff", "tif", "tifa", ])
57
58
59
60
except :
    LOG.info('no osgeo available for reading GeoTIFF data files')
    gdal = None

61
UNITS_CONSTANT = "units"
(no author)'s avatar
(no author) committed
62

63
64
65
fillValConst1 = '_FillValue'
fillValConst2 = 'missing_value'

66
67
68
69
ADD_OFFSET_STR   = 'add_offset'
SCALE_FACTOR_STR = 'scale_factor'
SCALE_METHOD_STR = 'scaling_method'

70
71
72
UNSIGNED_ATTR_STR = "_unsigned"

SIGNED_TO_UNSIGNED_DTYPES = {
73
74
75
76
                                numpy.dtype(numpy.int8):    numpy.dtype(numpy.uint8),
                                numpy.dtype(numpy.int16):   numpy.dtype(numpy.uint16),
                                numpy.dtype(numpy.int32):   numpy.dtype(numpy.uint32),
                                numpy.dtype(numpy.int64):   numpy.dtype(numpy.uint64),
77
78
                            }

79
80
81
82
83
84
85
86
87
88
89
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

90
91
92
93
94
95
class IONonnumericalTypeError(Exception):
    """
    A type was encountered that numpy doesn't know how to deal with - e.g. netCDF variable-length string arrays
    """
    pass

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
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
Eva Schiffer's avatar
Eva Schiffer committed
137
        if tempVariableName not in self.variableAttributesLower :
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
            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
194
195
196
197
198
199
200
201
    
    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
202

203
204
205
206
207
208
209
210
211
212
213
214
215
def _get_data_uptype (input_dtype) :
    """
    Given an input data type, figure out what type we need to upcast it to.

    Note: Glance expects all it's data to get upcast into floats for the purposes of it's
    later math manipulations.
    """

    default_uptype = numpy.float32
    default_finfo  = numpy.finfo(default_uptype)
    input_info     = numpy.finfo(input_dtype) if  numpy.issubdtype(input_dtype, numpy.floating,) else numpy.iinfo(input_dtype)

    # if our input won't fit into the default, pick a bigger type
216
    if (default_finfo.min > input_info.min) or (default_finfo.max < input_info.max) :
217
218
219
220
221
222
223
        LOG.debug("Input data will not fit in default float32 data type, using larger type.")
        default_uptype = numpy.float64

    # FUTURE, if we reach a point where a float64 isn't big enough, this will need to be revisited

    return default_uptype

224
class nc (object):
225
    """wrapper for netcdf4-python data access for comparison
(no author)'s avatar
(no author) committed
226
227
228
229
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
230
    _nc = None
231
232
233
234
    _var_map = None

    # walk down through all groups and get variable names and objects
    def _walkgroups(self, start_at, prefix=None, ):
235
        # look through the variables that are here
Eva Schiffer's avatar
Eva Schiffer committed
236
        for var_name in start_at.variables:
237
238
            temp_name = var_name if prefix is None or len(prefix) <= 0 else prefix + "/" + var_name
            yield temp_name, start_at[var_name]
239
        # look through the groups that are here
Eva Schiffer's avatar
Eva Schiffer committed
240
        for group_name in start_at.groups:
241
242
243
            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
244
    
245
246
    def __init__(self, filename, allowWrite=False):
        
247
248
249
        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
250
        
251
        mode = 'r'
252
        if allowWrite :
253
254
            mode = 'a' # a is for append, if I use w it creates a whole new file, deleting the old one

255
        self._nc = netCDF4.Dataset(filename, mode)
256
        self.attributeCache = CaseInsensitiveAttributeCache(self)
257
258
259
        self._var_map = { }
        for var_name, var_obj in self._walkgroups(self._nc,) :
            self._var_map[var_name] = var_obj
260

(no author)'s avatar
(no author) committed
261
    def __call__(self):
262
263
264
265
        """
        yield names of variables in this file
        """

Eva Schiffer's avatar
Eva Schiffer committed
266
        return list(self._var_map)
267

(no author)'s avatar
(no author) committed
268
    def __getitem__(self, name):
269
270
271
272
273
274
275
        """
        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)
        """

276
277
        LOG.debug("loading variable data for: " + name)

278
279
280
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
281

282
283
        # 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
284
285
        temp_input_data = variable_object[:]
        LOG.debug("Native input dtype: " + str(temp_input_data.dtype))
286
287
        # if this is object data, stop because we can't run our regular analysis on that kind
        if temp_input_data.dtype == object :
288
289
            LOG.warning("Variable '" + name + "' has a data type of 'object'. This type of data cannot be analyzed by Glance. "
                        "This variable will not be analyzed.")
290
291
292
293
294
295
296
297
            raise IONonnumericalTypeError("Variable '" + name + "' is of data type 'object'. "
                                          "This program can't analyze non-numerical data.")
        """
            Note to self, if we ever do want to access data in a numpy array with dtype=object, for some
            reason this library is packing that into a a zero dimensional tuple or something similar.
            I was able to unpack the data using a construction like: temp_input_data = temp_input_data[()]
            After that the array can be indexed into as normal for a numpy array.
        """
298
299
300
        dtype_to_use = _get_data_uptype(temp_input_data.dtype)
        LOG.debug("Choosing dtype " + str(dtype_to_use) + " for our internal representation of this data.")
        scaled_data_copy = numpy.array(temp_input_data, dtype=dtype_to_use,)
301
302

        # get the attribute cache so we can check on loading related attributes
303
        temp = self.attributeCache.get_variable_attributes(name)
304
305
306

        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
307
        missing_mask = numpy.zeros(scaled_data_copy.shape, dtype=numpy.bool)
308
309
        if missing_val is not None:
            missing_mask[scaled_data_copy == missing_val] = True
310
311
312
313

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

        # if our data is labeled as being unsigned by the appropriately set attribute
314
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == "true":
315
316
            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
317
            scaled_data_copy[where_temp] += (numpy.iinfo(numpy.uint16).max + 1.0) # add the 2's complement
318
319
320
321
322
323
324

        #***** 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
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
        scale_factor = 1.0 if SCALE_FACTOR_STR not in temp else temp[SCALE_FACTOR_STR]
        add_offset = 0.0 if ADD_OFFSET_STR not in temp else temp[ADD_OFFSET_STR]
        scaling_method = None if SCALE_METHOD_STR not in temp else temp[SCALE_METHOD_STR]

        # at the moment geocat has several scaling methods that don't match the normal standards for hdf
        # we don't ever expect to see this for netcdf files, but we are using the netcdf library for hdf 4 now
        """
        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 :
            if scale_factor != 1.0 or add_offset != 0.0 :
                LOG.warning(SCALE_METHOD_STR + " attribute indicates no scaling, but " + SCALE_FACTOR_STR +
                            " and " + ADD_OFFSET_STR +
                            " attributes will result in scaling. Defaulting to ignoring " +
                            SCALE_METHOD_STR + " attribute.")
        if (scaling_method is not None) and (int(scaling_method) > 1) :
            LOG.warning('Scaling method of \"' + str(
                scaling_method) + '\" will be ignored in favor of netCDF standard linear scaling. '
                        + 'This may cause problems with data consistency')
348

349
350
        # don't do work if we don't need to unpack things
        if (scale_factor != 1.0) or (add_offset != 0.0) :
351

352
            LOG.debug("Manually applying scale (" + str(scale_factor) + ") and add offset (" + str(add_offset) + ").")
353

354
355
356
357
358
359
360
            # 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
Eva Schiffer's avatar
Eva Schiffer committed
361
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == ( "true" ) :
362
363
364
365
366
367
368

            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)
Eva Schiffer's avatar
Eva Schiffer committed
369
            if SCALE_FACTOR_STR in temp :
370
                scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
371
            if ADD_OFFSET_STR in temp :
372
373
374
375
                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)
376
            orig_dtype   = numpy.array([missing_val,]).dtype
Eva Schiffer's avatar
Eva Schiffer committed
377
            needed_dtype = SIGNED_TO_UNSIGNED_DTYPES[orig_dtype] if orig_dtype in SIGNED_TO_UNSIGNED_DTYPES else None
378
379
380

            if needed_dtype is not None :
                # now figure out where all the corrupted values are, and shift them up to be positive
381
                needs_fix_mask = (scaled_data_copy < add_offset) & (scaled_data_copy != missing_val)
382
                # we are adding the 2's complement, but first we're scaling it appropriately
383
                scaled_data_copy[needs_fix_mask] += ((numpy.iinfo(numpy.uint16).max + 1.0) * scale_factor)
384
        """
385

386
        return scaled_data_copy
387
    
388
389
390
391
    # TODO, this hasn't been supported in other file types
    def close (self) :
        self._nc.close()
        self._nc = None
392
        self._var_map = None
393

394
    def get_variable_object(self, name):
395

396
        return self._var_map[name]
397
    
(no author)'s avatar
(no author) committed
398
    def missing_value(self, name):
399
        
400
401
402
403
404
405
406
407
408
409
410
        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
411

412
413
414
415
416
417
418
419
    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
        """
420
421

        # TODO, this will not work with groups
422
        #self._nc.nc_redef() # TODO?
423
424
        
        # if the variable already exists, stop with a warning
Eva Schiffer's avatar
Eva Schiffer committed
425
        if variablename in self._nc.variables :
426
427
            LOG.warning("New variable name requested (" + variablename + ") is already present in file. " +
                        "Skipping generation of new variable.")
428
            return None
429
430
        # 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) :
431
432
            LOG.warning("Data type for new variable (" + variablename + ") could not be determined. " +
                        "Skipping generation of new variable.")
433
            return None
Eva Schiffer's avatar
Eva Schiffer committed
434

435
        # TODO, the type managment here is going to cause problems with larger floats, review this
436
        #dataType = None
437
438
        if numpy.issubdtype(data.dtype, int) :
            dataType = numpy.int
439
440
            #print("Picked INT")
        # TODO, at the moment the fill type is forcing me to use a double, when sometimes I want a float
441
442
        #elif numpy.issubdtype(data.dtype, numpy.float32) :
        #    dataType = numpy.float
443
        #    print("Picked FLOAT")
444
445
        elif numpy.issubdtype(data.dtype, float) :
            dataType = numpy.float64
446
447
            #print("Picked DOUBLE")
        # what do we do if it's some other type?
448
449
        else :
            dataType = data.dtype
450
451
452
453
454
        
        # create and set all the dimensions
        dimensions = [ ]
        dimensionNum = 0
        for dimSize in data.shape :
455
456
457
            tempName = variablename + '-index' + str(dimensionNum)
            self._nc.createDimension(tempName, dimSize)
            dimensions.append(tempName)
458
459
460
            dimensionNum = dimensionNum + 1
        
        # create the new variable
461
462
463
        #print('variable name: ' + variablename)
        #print('data type:     ' + str(dataType))
        #print('dimensions:    ' + str(dimensions))
464
        # if a missing value was given, use that
465
466
467
468
        if missingvalue is None :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions))
        else :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions), fill_value=missingvalue, )
469
470
471
        
        # if we have a variable to copy attributes from, do so
        if variabletocopyattributesfrom is not None :
472
473
            attributes = self.get_variable_attributes(variabletocopyattributesfrom, caseInsensitive=False)

Eva Schiffer's avatar
Eva Schiffer committed
474
            for attribute in attributes :
475
476
                if attribute.lower() != "_fillvalue" :
                    setattr(newVariable, attribute, attributes[attribute])
477

478
        #self._nc.nc_enddef() # TODO?
479

480
481
        # if data was given, use that
        if data is not None :
482
483

            newVariable[:] = data
484

485
        return newVariable
486

487
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue, variableObject=None,) :
488
489
490
491
        """
        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
        """
492
493
        # TODO, this will not work with groups

494
495
        if variableObject is None :
            variableObject = self.get_variable_object(variableName)
496
        
497
        #self._nc.nc_redef() # TODO?
498
499
500

        setattr(variableObject, newAttributeName, newAttributeValue)

501
        #self._nc.nc_enddef() # TODO?
502

503
504
505
        # TODO, this will cause our attribute cache to be wrong!
        # TODO, for now, brute force clear the cache
        self.attributeCache = CaseInsensitiveAttributeCache(self)
506
507
        
        return
508
    
509
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
510
511
512
513
        """
        returns all the attributes associated with a variable name
        """
        
514
        #toReturn = None
515
516
517
518
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
519
520
521
522
523
            toReturn = { }
            tempVarObj   = self.get_variable_object(variableName)
            tempAttrKeys = tempVarObj.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(tempVarObj, attrKey)
524
525
        
        return toReturn
526
    
527
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
528
529
530
531
532
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
533
534
535
536
537
538
        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 :
539
                toReturn = getattr(self.get_variable_object, attributeName)
540
541
542
543
544
545
546
547
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
548
        #toReturn = None
549
        
550
        if caseInsensitive :
551
            toReturn = self.attributeCache.get_global_attributes()
552
        else :
553
554
555
556
            toReturn = { }
            tempAttrKeys = self._nc.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(self._nc, attrKey)
557

558
        return toReturn
559
    
560
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
561
562
563
564
565
566
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
567
568
569
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
570
            if attributeName in self._nc.ncattrs() :
571
                toReturn = getattr(self._nc, attributeName)
572
573
        
        return toReturn
574
575
576
577
578
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
579
580

        return True
581
# some other aliases for different valid netcdf file extentions
(no author)'s avatar
(no author) committed
582
583
nc4 = nc
cdf = nc
584
hdf = nc # we are now using the netcdf library to load hdf4 files
(no author)'s avatar
(no author) committed
585

586
587
# TODO remove
#FIXME_IDPS = [ '/All_Data/CrIS-SDR_All/ES' + ri + band for ri in ['Real','Imaginary'] for band in ['LW','MW','SW'] ] 
588

(no author)'s avatar
(no author) committed
589
class h5(object):
590
591
592
593
    """wrapper for HDF5 datasets
    """
    _h5 = None
    
594
    def __init__(self, filename, allowWrite=False):
595
596
        self.attributeCache = CaseInsensitiveAttributeCache(self)
        
597
598
599
        mode = 'r'
        if allowWrite :
            mode = 'r+'
(no author)'s avatar
   
(no author) committed
600
601
602
        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)
603
        self._h5 = h5py.File(filename, mode)
604
605
    
    def __call__(self):
606
607
608
609
        
        variableList = [ ]
        def testFn (name, obj) :
            #print ('checking name: ' + name)
610
            #print ('object: ' + str(obj))
611
612
613
614
            
            if isinstance(obj, h5py.Dataset) :
                try :
                    tempType = obj.dtype # this is required to provoke a type error for closed data sets
615
                    
616
                    #LOG.debug ('type: ' + str(tempType))
617
618
619
620
621
622
623
624
625
                    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))
        
626
        return variableList
627
628
629
630
631
    
    @staticmethod
    def trav(h5,pth): 
        return reduce( lambda x,a: x[a] if a else x, pth.split('/'), h5)
        
632
633
634
635
636
    # 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):
637
        
638
639
640
641
642
643
644
645
        # defaults
        scale_factor = 1.0
        add_offset = 0.0
        
        # 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[:]
646
647
648
649

        # pick a data type to use internally
        data_type = _get_data_uptype(raw_data_copy.dtype)

650
651
652
653
        #print ('*************************')
        #print (dir (variable_object.id)) # TODO, is there a way to get the scale and offset through this?
        #print ('*************************')
        
654
        # load the scale factor and add offset
655
        temp = self.attributeCache.get_variable_attributes(name)
Eva Schiffer's avatar
Eva Schiffer committed
656
        if SCALE_FACTOR_STR in temp :
657
            scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
658
        if ADD_OFFSET_STR in temp :
659
            add_offset = temp[ADD_OFFSET_STR]
660
661
662
663
664
665
        # 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
        
666
667
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
668
        missing_mask = numpy.zeros(raw_data_copy.shape, dtype=numpy.bool)
669
670
        if missing_val is not None:
            missing_mask[raw_data_copy == missing_val] = True
671
        
672
        # create the scaled version of the data
673
        scaled_data_copy = numpy.array(raw_data_copy, dtype=data_type)
674
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
675
676
677
678
        
        return scaled_data_copy
    
    def get_variable_object(self,name):
679
680
681
        return h5.trav(self._h5, name)
    
    def missing_value(self, name):
682
683
684
685
686
687
688
        
        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()
Eva Schiffer's avatar
Eva Schiffer committed
689
        if (h5d.FILL_VALUE_DEFAULT == fillValueStatus) or (h5d.FILL_VALUE_USER_DEFINED == fillValueStatus) :
690
            temp = numpy.array((1), dtype=variableObject.dtype)
691
692
693
694
            pListObj.get_fill_value(temp)
            toReturn = temp
        
        return toReturn
695
696
697
698
699
700
701
702
703
    
    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
        """
704
        
705
        raise IOUnimplimentedError('Unable to create variable in hdf 5 file, this functionality is not yet available.')
706
        
707
        #return None
708
709
710
711
712
713
    
    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
        """
714
715
        
        raise IOUnimplimentedError('Unable to add attribute to hdf 5 file, this functionality is not yet available.')
716
        
717
        #return
718
    
719
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
720
721
722
723
        """
        returns all the attributes associated with a variable name
        """
        
724
        #toReturn = None
725
726
727
728
729
730
731
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attrs
        
        return toReturn
732
    
733
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
734
735
736
737
738
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
739
740
741
742
743
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attrs = self.get_variable_attributes(variableName, caseInsensitive=False)
            
744
            if attributeName in temp_attrs :
745
746
747
748
749
750
751
752
753
                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
        """
        
754
        #toReturn = None
755
        
756
        if caseInsensitive :
757
            toReturn = self.attributeCache.get_global_attributes()
758
759
        else :
            toReturn = self._h5.attrs
760
761
        
        return toReturn
(no author)'s avatar
(no author) committed
762
    
763
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
764
765
766
767
768
769
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
770
771
772
773
774
        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
775
776
        
        return toReturn
777
778
779
780
781
782
783
784
    
    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
785

(no author)'s avatar
(no author) committed
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
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')
811
            assert (dmvlib is not None)
(no author)'s avatar
(no author) committed
812
813
814
815
816
817
818
819
820
        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):
Eva Schiffer's avatar
Eva Schiffer committed
821
        return list(self._vectors) + list(self._scalars)
(no author)'s avatar
(no author) committed
822
823
824
825
826
827
828
829
830
        
    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()
831
        recrange = list(range(1, nrecs+1))
(no author)'s avatar
(no author) committed
832
833
834
        if name in self._vectors:
            vid = self._vectors[name]
            vdata = [ fp.vectorDepValues(rec, vid) for rec in recrange ]
835
            return numpy.array(vdata)
(no author)'s avatar
(no author) committed
836
837
        elif name in self._scalars:
            vdata = fp.metaValueMatrix(recrange, [self._scalars[name]])
838
            return numpy.array(vdata)
(no author)'s avatar
(no author) committed
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
        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
855
856
857
858
        """
        
        raise IOUnimplimentedError('Unable to create variable in aeri file, this functionality is not yet available.')
        
859
        #return None
(no author)'s avatar
(no author) committed
860
861
862
863
864
865
866
    
    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
        """
        
867
868
        raise IOUnimplimentedError('Unable to add attribute to aeri file, this functionality is not yet available.')
        
869
        #return
870
    
871
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
872
873
874
875
876
877
        """
        returns all the attributes associated with a variable name
        """
        toReturn = { }
        
        # TODO
878
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
879
880
881
        
        return toReturn
    
882
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
883
884
885
886
887
888
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
        # TODO
889
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
890
891
        
        return toReturn
(no author)'s avatar
(no author) committed
892
    
893
894
895
896
897
898
899
900
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
        toReturn = None
        
        # TODO
901
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
902
903
904
905
        
        return toReturn
    
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
906
907
908
909
910
911
912
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
        # TODO
913
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
(no author)'s avatar
(no author) committed
914
915
        
        return toReturn
916
917
918
919
920
921
922
923
    
    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
924
925
926
927

# handle the variety of file suffixes by building aliases to aeri class
cxs = rnc = cxv = csv = spc = sum = uvs = aeri

928
929
930
931
932
933
934
935
class tiff (object):
    """wrapper for to open GeoTIFF data sets for comparison
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
    _tiff = None
    
936
937
938
939
940
941
942
943
    GRAY_NAME  = "grayscale value"
    RED_NAME   = "red"
    GREEN_NAME = "green"
    BLUE_NAME  = "blue"
    IR_NAME    = "infrared"
    ALPHA_NAME = "alpha"
    
    
944
945
946
    # if we are using meaningful names, we will translate between
    # the band index numbers and these names (otherwise bands use generic names)
    EXPECTED_BAND_NAME_KEY = {
947
948
949
950
951
                                1: [GRAY_NAME],
                                2: [GRAY_NAME, ALPHA_NAME],
                                3: [RED_NAME, GREEN_NAME, BLUE_NAME],
                                4: [RED_NAME, GREEN_NAME, BLUE_NAME, ALPHA_NAME],
                                5: [RED_NAME, GREEN_NAME, BLUE_NAME, IR_NAME, ALPHA_NAME],
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
980
981
982
983
    
    # a reverse look up to help disambigurate what meaningful name goes with
    # which number (one of these dictionaries will be selected based on the
    # number of bands in the geotiff)
    REV_INFO               = {
                                1: {
                                    GRAY_NAME:  1,
                                    },
                                2: {
                                    GRAY_NAME:  1,
                                    ALPHA_NAME: 2,
                                    },
                                3: {
                                    RED_NAME:   1,
                                    GREEN_NAME: 2,
                                    BLUE_NAME:  3,
                                    },
                                4: {
                                    RED_NAME:   1,
                                    GREEN_NAME: 2,
                                    BLUE_NAME:  3,
                                    ALPHA_NAME: 4,
                                    },
                                5: {
                                    RED_NAME:   1,
                                    GREEN_NAME: 2,
                                    BLUE_NAME:  3,
                                    IR_NAME:    4,
                                    ALPHA_NAME: 5,
                                    },
                                
984
985
986
987
988
                              }
    
    def _get_generic_band_name (self, number) :
        """get a generic band name for this number"""
        
989
        return "band at index " + str(number)
990
991
992
993
994
    
    def _get_band_index_from_name (self, name) :
        """get an index for the band from a name
        
        name may be either a meaningful name from the list that shows
995
        up in the reverse index keys or a generic name that was
996
997
998
999
1000
        generated by _get_generic_band_name
        """
        
        to_return = None
        
For faster browsing, not all history is shown. View entire blame