1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
from numpy.ma import masked_where as numpy_ma_masked_where
from ..constants import _file_to_fh
from ..functions import (open_files_threshold_exceeded,
close_one_file,
parse_indices,
get_subspace)
from ..data.filearray import FileArray
from .functions import _open_um_file, _close_um_file
from .umread.umfile import Rec
_filename_to_file = _file_to_fh.setdefault('UM', {})
# ====================================================================
#
# UMFileArray object
#
# ====================================================================
class UMFileArray(FileArray):
'''A sub-array stored in a PP or UM fields file.
**Initialization**
:Parameters:
file : str
The file name in normalized, absolute form.
dtype : numpy.dtype
The data type of the data array on disk.
ndim : int
The number of dimensions in the unpacked data array.
shape : tuple
The shape of the unpacked data array.
size : int
The number of elements in the unpacked data array.
header_offset : int
The start position in the file of the header.
data_offset : int
The start position in the file of the data array.
disk_length : int
The number of words on disk for the data array, usually
LBLREC-LBEXT. If set to 0 then `!size` is used.
:Examples:
>>> a = UMFileArray(file='file.pp', header_offset=3156, data_offset=3420,
... dtype=numpy.dtype('float32'), shape=(30, 24),
... size=720, ndim=2, disk_length=0)
>>> a = UMFileArray(file='packed_file.pp', header_offset=3156, data_offset=3420,
... dtype=numpy.dtype('float32'), shape=(30, 24),
... size=720, ndim=2, disk_length=423)
'''
def __getitem__(self, indices):
'''
Implement indexing
x.__getitem__(indices) <==> x[indices]
Returns a numpy array.
'''
f = self.open()
rec = Rec.from_file_and_offsets(f, self.header_offset,
self.data_offset,
self.disk_length)
int_hdr = rec.int_hdr
real_hdr = rec.real_hdr
array = rec.get_data().reshape(int_hdr.item(17,), int_hdr.item(18,))
if indices is not Ellipsis:
indices = parse_indices(array, indices)
array = get_subspace(array, indices)
LBUSER2 = int_hdr.item(38,)
if LBUSER2 == 3:
# Return the numpy array now if it is a boolean array
return array.astype(bool)
integer_array = LBUSER2 == 2
# ------------------------------------------------------------
# Convert to a masked array
# ------------------------------------------------------------
# Set the fill_value from BMDI
fill_value = real_hdr.item(17,)
if fill_value != -1.0e30:
# -1.0e30 is the flag for no missing data
if integer_array:
# The fill_value must be of the same type as the data
# values
fill_value = int(fill_value)
# Mask any missing values
mask = (array == fill_value)
if mask.any():
array = numpy_ma_masked_where(mask, array, copy=False)
#--- End: if
# ------------------------------------------------------------
# Unpack the array using the scale_factor and add_offset, if
# either is available
# ------------------------------------------------------------
# Treat BMKS as a scale_factor if it is neither 0 nor 1
scale_factor = real_hdr.item(18,)
if scale_factor != 1.0 and scale_factor != 0.0:
if integer_array:
scale_factor = int(scale_factor)
array *= scale_factor
# Treat BDATUM as an add_offset if it is not 0
add_offset = real_hdr.item(4,)
if add_offset != 0.0:
if integer_array:
add_offset = int(add_offset)
array += add_offset
# Return the numpy array
return array
#--- End: def
def __str__(self):
'''
x.__str__() <==> str(x)
'''
return "%s%s in %s" % (self.header_offset, self.shape, self.file)
#--- End: def
@property
def file_pointer(self):
'''
'''
return (self.file, self.header_offset)
#--- End: def
def close(self):
'''
Close the file containing the data array.
If the file is not open then no action is taken.
:Returns:
None
:Examples:
>>> f.close()
'''
_close_um_file(self.file)
#--- End: def
def open(self):
'''
Open the file containing the data array.
:Returns:
out : um.umread.umfile.File
:Examples:
>>> f.open()
'''
return _open_um_file(self.file)
#--- End: def
#--- End: class
|
