io.py 52.4 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
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
    _var_map = None
232
    _path = None
233
234
235

    # walk down through all groups and get variable names and objects
    def _walkgroups(self, start_at, prefix=None, ):
236
        # look through the variables that are here
Eva Schiffer's avatar
Eva Schiffer committed
237
        for var_name in start_at.variables:
238
239
            temp_name = var_name if prefix is None or len(prefix) <= 0 else prefix + "/" + var_name
            yield temp_name, start_at[var_name]
240
        # look through the groups that are here
Eva Schiffer's avatar
Eva Schiffer committed
241
        for group_name in start_at.groups:
242
243
244
            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
245
    
246
247
    def __init__(self, filename, allowWrite=False):
        
248
249
250
        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
251
        
252
        mode = 'r'
253
        if allowWrite :
254
255
            mode = 'a' # a is for append, if I use w it creates a whole new file, deleting the old one

256
        self._path = filename
257
        self._nc = netCDF4.Dataset(filename, mode)
258
        self.attributeCache = CaseInsensitiveAttributeCache(self)
259
260
261
        self._var_map = { }
        for var_name, var_obj in self._walkgroups(self._nc,) :
            self._var_map[var_name] = var_obj
262

(no author)'s avatar
(no author) committed
263
    def __call__(self):
264
265
266
267
        """
        yield names of variables in this file
        """

Eva Schiffer's avatar
Eva Schiffer committed
268
        return list(self._var_map)
269

(no author)'s avatar
(no author) committed
270
    def __getitem__(self, name):
271
272
273
274
275
276
277
        """
        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)
        """

278
279
        LOG.debug("loading variable data for: " + name)

280
281
282
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
283

284
285
        # 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
286
287
        temp_input_data = variable_object[:]
        LOG.debug("Native input dtype: " + str(temp_input_data.dtype))
288
289
        # if this is object data, stop because we can't run our regular analysis on that kind
        if temp_input_data.dtype == object :
290
291
            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.")
292
293
294
295
296
297
298
299
            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.
        """
300
301
302
        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,)
303
304

        # get the attribute cache so we can check on loading related attributes
305
        temp = self.attributeCache.get_variable_attributes(name)
306
307
308

        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
309
        missing_mask = numpy.zeros(scaled_data_copy.shape, dtype=numpy.bool)
310
311
        if missing_val is not None:
            missing_mask[scaled_data_copy == missing_val] = True
312
313
314
315

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

        # if our data is labeled as being unsigned by the appropriately set attribute
316
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == "true":
317
318
            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
319
            scaled_data_copy[where_temp] += (numpy.iinfo(numpy.uint16).max + 1.0) # add the 2's complement
320
321
322
323
324
325
326

        #***** 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
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
        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')
350

351
352
        # don't do work if we don't need to unpack things
        if (scale_factor != 1.0) or (add_offset != 0.0) :
353

354
            LOG.debug("Manually applying scale (" + str(scale_factor) + ") and add offset (" + str(add_offset) + ").")
355

356
357
358
359
360
361
362
            # 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
363
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == ( "true" ) :
364
365
366
367
368
369
370

            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
371
            if SCALE_FACTOR_STR in temp :
372
                scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
373
            if ADD_OFFSET_STR in temp :
374
375
376
377
                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)
378
            orig_dtype   = numpy.array([missing_val,]).dtype
Eva Schiffer's avatar
Eva Schiffer committed
379
            needed_dtype = SIGNED_TO_UNSIGNED_DTYPES[orig_dtype] if orig_dtype in SIGNED_TO_UNSIGNED_DTYPES else None
380
381
382

            if needed_dtype is not None :
                # now figure out where all the corrupted values are, and shift them up to be positive
383
                needs_fix_mask = (scaled_data_copy < add_offset) & (scaled_data_copy != missing_val)
384
                # we are adding the 2's complement, but first we're scaling it appropriately
385
                scaled_data_copy[needs_fix_mask] += ((numpy.iinfo(numpy.uint16).max + 1.0) * scale_factor)
386
        """
387

388
        return scaled_data_copy
389
    
390
391
392
393
    # TODO, this hasn't been supported in other file types
    def close (self) :
        self._nc.close()
        self._nc = None
394
        self._var_map = None
395

396
    def get_variable_object(self, name):
397

398
        return self._var_map[name]
399
    
(no author)'s avatar
(no author) committed
400
    def missing_value(self, name):
401
        
402
403
404
405
406
407
408
409
410
411
412
        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
413

414
415
416
417
418
419
420
421
    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
        """
422
423

        # TODO, this will not work with groups
424
        #self._nc.nc_redef() # TODO?
425
426
        
        # if the variable already exists, stop with a warning
Eva Schiffer's avatar
Eva Schiffer committed
427
        if variablename in self._nc.variables :
428
429
            LOG.warning("New variable name requested (" + variablename + ") is already present in file. " +
                        "Skipping generation of new variable.")
430
            return None
431
432
        # 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) :
433
434
            LOG.warning("Data type for new variable (" + variablename + ") could not be determined. " +
                        "Skipping generation of new variable.")
435
            return None
Eva Schiffer's avatar
Eva Schiffer committed
436

437
        # TODO, the type managment here is going to cause problems with larger floats, review this
438
        #dataType = None
439
440
        if numpy.issubdtype(data.dtype, int) :
            dataType = numpy.int
441
442
            #print("Picked INT")
        # TODO, at the moment the fill type is forcing me to use a double, when sometimes I want a float
443
444
        #elif numpy.issubdtype(data.dtype, numpy.float32) :
        #    dataType = numpy.float
445
        #    print("Picked FLOAT")
446
447
        elif numpy.issubdtype(data.dtype, float) :
            dataType = numpy.float64
448
449
            #print("Picked DOUBLE")
        # what do we do if it's some other type?
450
451
        else :
            dataType = data.dtype
452
453
454
455
456
        
        # create and set all the dimensions
        dimensions = [ ]
        dimensionNum = 0
        for dimSize in data.shape :
457
458
459
            tempName = variablename + '-index' + str(dimensionNum)
            self._nc.createDimension(tempName, dimSize)
            dimensions.append(tempName)
460
461
462
            dimensionNum = dimensionNum + 1
        
        # create the new variable
463
464
465
        #print('variable name: ' + variablename)
        #print('data type:     ' + str(dataType))
        #print('dimensions:    ' + str(dimensions))
466
        # if a missing value was given, use that
467
468
469
470
        if missingvalue is None :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions))
        else :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions), fill_value=missingvalue, )
471
472
473
        
        # if we have a variable to copy attributes from, do so
        if variabletocopyattributesfrom is not None :
474
475
            attributes = self.get_variable_attributes(variabletocopyattributesfrom, caseInsensitive=False)

Eva Schiffer's avatar
Eva Schiffer committed
476
            for attribute in attributes :
477
478
                if attribute.lower() != "_fillvalue" :
                    setattr(newVariable, attribute, attributes[attribute])
479

480
        #self._nc.nc_enddef() # TODO?
481

482
483
        # if data was given, use that
        if data is not None :
484
485

            newVariable[:] = data
486

487
        return newVariable
488

489
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue, variableObject=None,) :
490
491
492
493
        """
        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
        """
494
495
        # TODO, this will not work with groups

496
497
        if variableObject is None :
            variableObject = self.get_variable_object(variableName)
498
        
499
        #self._nc.nc_redef() # TODO?
500
501
502

        setattr(variableObject, newAttributeName, newAttributeValue)

503
        #self._nc.nc_enddef() # TODO?
504

505
506
507
        # TODO, this will cause our attribute cache to be wrong!
        # TODO, for now, brute force clear the cache
        self.attributeCache = CaseInsensitiveAttributeCache(self)
508
509
        
        return
510
    
511
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
512
513
514
515
        """
        returns all the attributes associated with a variable name
        """
        
516
        #toReturn = None
517
518
519
520
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
521
522
523
524
525
            toReturn = { }
            tempVarObj   = self.get_variable_object(variableName)
            tempAttrKeys = tempVarObj.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(tempVarObj, attrKey)
526
527
        
        return toReturn
528
    
529
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
530
531
532
533
534
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
535
536
537
538
539
540
        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 :
541
                toReturn = getattr(self.get_variable_object, attributeName)
542
543
544
545
546
547
548
549
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
550
        #toReturn = None
551
        
552
        if caseInsensitive :
553
            toReturn = self.attributeCache.get_global_attributes()
554
        else :
555
556
557
558
            toReturn = { }
            tempAttrKeys = self._nc.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(self._nc, attrKey)
559

560
        return toReturn
561
    
562
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
563
564
565
566
567
568
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
569
570
571
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
572
            if attributeName in self._nc.ncattrs() :
573
                toReturn = getattr(self._nc, attributeName)
574
575
        
        return toReturn
576
577
578
579
580
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
581
582

        return True
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603

    def display_string (self, show_attrs=False, ) :
        """
        Create and return a display string that describes informational details but not
        the actual data that's inside the file.

        If show_attrs is true, then global and variable attributes and their values will
        be included in the returned display string.

        returns a string, describing the file in a user readable format.
        """

        # TODO, this is a temporary implementation to be replaced with more details soon
        to_return = "File path: " + self._path + "\n"

        temp_vars = self()
        for var_name in temp_vars :
            to_return += "\t" + var_name + "\n"

        return to_return

604
# some other aliases for different valid netcdf file extentions
(no author)'s avatar
(no author) committed
605
606
nc4 = nc
cdf = nc
607
hdf = nc # we are now using the netcdf library to load hdf4 files
(no author)'s avatar
(no author) committed
608

609
610
# TODO remove
#FIXME_IDPS = [ '/All_Data/CrIS-SDR_All/ES' + ri + band for ri in ['Real','Imaginary'] for band in ['LW','MW','SW'] ] 
611

(no author)'s avatar
(no author) committed
612
class h5(object):
613
614
615
    """wrapper for HDF5 datasets
    """
    _h5 = None
616
    _path = None
617
    
618
    def __init__(self, filename, allowWrite=False):
619
        self.attributeCache = CaseInsensitiveAttributeCache(self)
620
621
622
623

        self._path = filename

        mode = 'r' if not allowWrite else 'r+'
(no author)'s avatar
   
(no author) committed
624
625
626
        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)
627
        self._h5 = h5py.File(filename, mode)
628
629
    
    def __call__(self):
630
631
632
633
        
        variableList = [ ]
        def testFn (name, obj) :
            #print ('checking name: ' + name)
634
            #print ('object: ' + str(obj))
635
636
637
638
            
            if isinstance(obj, h5py.Dataset) :
                try :
                    tempType = obj.dtype # this is required to provoke a type error for closed data sets
639
                    
640
                    #LOG.debug ('type: ' + str(tempType))
641
642
643
644
645
646
647
648
649
                    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))
        
650
        return variableList
651
652
653
654
655
    
    @staticmethod
    def trav(h5,pth): 
        return reduce( lambda x,a: x[a] if a else x, pth.split('/'), h5)
        
656
657
658
659
660
    # 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):
661
        
662
663
664
665
666
667
668
669
        # 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[:]
670
671
672
673

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

674
675
676
677
        #print ('*************************')
        #print (dir (variable_object.id)) # TODO, is there a way to get the scale and offset through this?
        #print ('*************************')
        
678
        # load the scale factor and add offset
679
        temp = self.attributeCache.get_variable_attributes(name)
Eva Schiffer's avatar
Eva Schiffer committed
680
        if SCALE_FACTOR_STR in temp :
681
            scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
682
        if ADD_OFFSET_STR in temp :
683
            add_offset = temp[ADD_OFFSET_STR]
684
685
686
687
688
689
        # 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
        
690
691
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
692
        missing_mask = numpy.zeros(raw_data_copy.shape, dtype=numpy.bool)
693
694
        if missing_val is not None:
            missing_mask[raw_data_copy == missing_val] = True
695
        
696
        # create the scaled version of the data
697
        scaled_data_copy = numpy.array(raw_data_copy, dtype=data_type)
698
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
699
700
701
702
        
        return scaled_data_copy
    
    def get_variable_object(self,name):
703
704
705
        return h5.trav(self._h5, name)
    
    def missing_value(self, name):
706
707
708
709
710
711
712
        
        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
713
        if (h5d.FILL_VALUE_DEFAULT == fillValueStatus) or (h5d.FILL_VALUE_USER_DEFINED == fillValueStatus) :
714
            temp = numpy.array((1), dtype=variableObject.dtype)
715
716
717
718
            pListObj.get_fill_value(temp)
            toReturn = temp
        
        return toReturn
719
720
721
722
723
724
725
726
727
    
    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
        """
728
        
729
        raise IOUnimplimentedError('Unable to create variable in hdf 5 file, this functionality is not yet available.')
730
        
731
        #return None
732
733
734
735
736
737
    
    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
        """
738
739
        
        raise IOUnimplimentedError('Unable to add attribute to hdf 5 file, this functionality is not yet available.')
740
        
741
        #return
742
    
743
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
744
745
746
747
        """
        returns all the attributes associated with a variable name
        """
        
748
        #toReturn = None
749
750
751
752
753
754
755
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attrs
        
        return toReturn
756
    
757
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
758
759
760
761
762
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
763
764
765
766
767
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attrs = self.get_variable_attributes(variableName, caseInsensitive=False)
            
768
            if attributeName in temp_attrs :
769
770
771
772
773
774
775
776
777
                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
        """
        
778
        #toReturn = None
779
        
780
        if caseInsensitive :
781
            toReturn = self.attributeCache.get_global_attributes()
782
783
        else :
            toReturn = self._h5.attrs
784
785
        
        return toReturn
(no author)'s avatar
(no author) committed
786
    
787
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
788
789
790
791
792
793
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
794
795
796
797
798
        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
799
800
        
        return toReturn
801
802
803
804
805
806
807
808
    
    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
809

810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
    def display_string (self, show_attrs=False, ) :
        """
        Create and return a display string that describes informational details but not
        the actual data that's inside the file.

        If show_attrs is true, then global and variable attributes and their values will
        be included in the returned display string.

        returns a string, describing the file in a user readable format.
        """

        # TODO, this is a temporary implementation to be replaced with more details soon
        to_return = "File path: " + self._path + "\n"

        temp_vars = self()
        for var_name in temp_vars :
            to_return += "\t" + var_name + "\n"

        return to_return

(no author)'s avatar
(no author) committed
830
831
832
833
834
835
class aeri(object):
    """wrapper for AERI RNC/SUM/CXS/etc datasets
    """
    _dmv = None
    _vectors = { }
    _scalars = { }
836
    _path = None
(no author)'s avatar
(no author) committed
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
    
    @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')
856
            assert (dmvlib is not None)
857
        self._path = filename
(no author)'s avatar
(no author) committed
858
859
860
861
862
863
864
865
866
        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
867
        return list(self._vectors) + list(self._scalars)
(no author)'s avatar
(no author) committed
868
869
870
871
872
873
874
875
876
        
    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()
877
        recrange = list(range(1, nrecs+1))
(no author)'s avatar
(no author) committed
878
879
880
        if name in self._vectors:
            vid = self._vectors[name]
            vdata = [ fp.vectorDepValues(rec, vid) for rec in recrange ]
881
            return numpy.array(vdata)
(no author)'s avatar
(no author) committed
882
883
        elif name in self._scalars:
            vdata = fp.metaValueMatrix(recrange, [self._scalars[name]])
884
            return numpy.array(vdata)
(no author)'s avatar
(no author) committed
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
        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
901
902
903
904
        """
        
        raise IOUnimplimentedError('Unable to create variable in aeri file, this functionality is not yet available.')
        
905
        #return None
(no author)'s avatar
(no author) committed
906
907
908
909
910
911
912
    
    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
        """
        
913
914
        raise IOUnimplimentedError('Unable to add attribute to aeri file, this functionality is not yet available.')
        
915
        #return
916
    
917
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
918
919
920
921
922
923
        """
        returns all the attributes associated with a variable name
        """
        toReturn = { }
        
        # TODO
924
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
925
926
927
        
        return toReturn
    
928
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
929
930
931
932
933
934
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
        # TODO
935
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
936
937
        
        return toReturn
(no author)'s avatar
(no author) committed
938
    
939
940
941
942
943
944
945
946
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
        toReturn = None
        
        # TODO
947
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
948
949
950
951
        
        return toReturn
    
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
952
953
954
955
956
957
958
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
        # TODO
959
        LOG.warning('Glance does not yet support attribute retrieval in AERI files. None will be used.')
(no author)'s avatar
(no author) committed
960
961
        
        return toReturn
962
963
964
965
966
967
968
969
    
    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
970

971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
    def display_string (self, show_attrs=False, ) :
        """
        Create and return a display string that describes informational details but not
        the actual data that's inside the file.

        If show_attrs is true, then global and variable attributes and their values will
        be included in the returned display string.

        returns a string, describing the file in a user readable format.
        """

        # TODO, this is a temporary implementation to be replaced with more details soon
        to_return = "File path: " + self._path + "\n"

        temp_vars = self()
        for var_name in temp_vars :
            to_return += "\t" + var_name + "\n"

        return to_return

(no author)'s avatar
(no author) committed
991
992
993
# handle the variety of file suffixes by building aliases to aeri class
cxs = rnc = cxv = csv = spc = sum = uvs = aeri

994
995
996
997
998
999
1000
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
For faster browsing, not all history is shown. View entire blame