Newer
Older
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
'''
Created on 13 nov. 2018
@author: QFAURE
'''
import os
import logging
import requests #sudo pip install requests
import json
from pathlib import Path
from properties.p import Property
from typing import Iterable
logging.basicConfig(filename='RestClient.log', level=logging.DEBUG, format='%(asctime)s %(levelname)-8s %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
url = os.environ['BMAP_BACKEND_URL'] + 'catalogue/granule/'
# gets a granule by name and returns the json containing the granule's metadata.
def get_granule_by_name(granule_name: str,formatmetadata=False) -> Iterable:
try:
response = requests.get(url + 'granulename/' + granule_name)
json_str = response.text
# if the response body contains something
if len(json_str) > 0:
json_obj = json.loads(json_str)
if formatmetadata==True :
return format_metadata([json_obj])
else :
return json_obj
else:
print('INFO: There is no data with ID: ' + granule_name)
logging.info('There is no data with ID: ' + granule_name)
return {}
except requests.exceptions.RequestException as e:
print('ERROR: ' + str(e))
logging.error(str(e))
# gets granules by criteria and returns json containing granules' metadata:
def get_granules_by_criteria(input_file: str='datacriteria.properties',formatmetadata=False) -> Iterable:
if Path(input_file).is_file():
# load properties file
data_criteria = Property().load_property_files(input_file)
# add the criteria from the properties file to the dictionary
criteria_list = {}
try :
start_date = data_criteria['start_date']
if len(start_date) > 0:
criteria_list['"startDate"'] = '"' + start_date + '"'
except:
pass
try :
end_date = data_criteria['end_date']
if len(end_date) > 0:
criteria_list['"endDate"'] = '"' + end_date + '"'
except:
pass
try :
product_types = data_criteria['product_types']
if len(product_types) > 0:
criteria_list['"productTypes"'] = to_table_string(product_types)
except:
pass
try :
instrument_names = data_criteria['instrument_names']
if len(instrument_names) > 0:
criteria_list['"instrumentNames"'] = to_table_string(instrument_names)
except:
pass
# location = data_criteria['location']
try :
polarizations = data_criteria['polarizations']
if len(polarizations) > 0:
criteria_list['"polarizations"'] = to_table_string(polarizations)
except:
pass
try :
geometry_types = data_criteria['geometry_types']
if len(geometry_types) > 0:
criteria_list['"geometryTypes"'] = to_table_string(geometry_types)
except:
pass
try :
processing_levels = data_criteria['processing_levels']
if len(processing_levels) > 0:
criteria_list['"processingLevels"'] = to_table_string(processing_levels)
except:
pass
try :
sub_region_names = data_criteria['sub_region_names']
if len(sub_region_names) > 0:
criteria_list['"subRegionNames"'] = to_table_string(sub_region_names)
except:
pass
try :
collectionNames = data_criteria['collection_names']
if len(collectionNames) > 0:
criteria_list['"collectionNames"'] = to_table_string(collectionNames)
except:
pass
# if there is at least one criterion besides scene
if len(criteria_list) >= 1:
# concatenate the criteria from the dictionary together in a string (i.e. "key1": "value1", "key2: "value2")
criteria_str = ""
for i in criteria_list:
key = i
value = criteria_list[i]
if len(value) > 0:
if len(criteria_str) > 0:
criteria_str += ', '
criteria_str += key + ': ' + value
# add the concatenated criteria string it inside a string representing a data criteria json
request_body = '{"GranuleCriteria": {' + criteria_str + '}}'
try:
response = requests.post(url, headers={'content-type': 'application/json'}, data=request_body)
json_str = response.text
# if the response body contains something
if len(json_str) > 0:
json_obj = json.loads(json_str)
#return filter_by_scene(json_obj, data_criteria['scene_name'].split(','))
if data_criteria['scene_name']:
json_obj=filter_by_scene(json_obj, data_criteria['scene_name'].split(','))
if formatmetadata == True:
return format_metadata(json_obj)
else:
return json_obj
else:
if formatmetadata==True:
return format_metadata(json_obj)
else :
return json_obj
else:
print('INFO: There is no data matching the given criteria.')
logging.info('There is no data matching the given criteria.')
return {}
except requests.exceptions.RequestException as e:
print('ERROR: ' + str(e))
logging.error(str(e))
else:
print('ERROR: You need to specify at least one search criteria besides scene name.')
logging.error('You need to specify at least one search criteria besides scene name.')
else:
print('ERROR: The file "' + input_file + '" does not exist.')
logging.error('The file "' + input_file + '" does not exist.')
# returns the string passed as parameter as a string representing a table (e.g. ["a", "b", "c"])
def to_table_string(string: str) -> str:
string_to_return = string.replace(', ', ',').replace(',', '", "')
return '["' + string_to_return + '"]'
def filter_by_scene(json_result, scene_list):
for granule in json_result[:] :
scene = granule['Granule']['granuleScene']
if scene:
scene=granule['Granule']['granuleScene']['Granule']['name']
if not scene in scene_list :
json_result.remove(granule)
return json_result
# download granule data(s) in a specified dir:
# granule_id: granuleID.
# target_Dir: directory the file(s) will be saved at".
def download_granule(granule_id: str, target_Dir: str) -> Iterable:
try:
response = requests.get(url + 'granulename/' + granule_id)
json_str = response.text
# if the response body contains something
if len(json_str) > 0:
json_obj = json.loads(response.text)
for data in json_obj['Granule']['dataList'][:] :
#print(target_Dir+'/'+data['Data']['fileName'])
my_file = Path(target_Dir+'/'+data['Data']['fileName'])
urlToData=''
if my_file.is_file():
print(data['Data']['fileName']+' already exists in targetDir: '+ target_Dir)
logging.info(data['Data']['fileName']+' already exists in targetDir: '+ target_Dir)
else:
urlToData = data['Data']['urlToData']
completeName = os.path.join(target_Dir, data['Data']['fileName'])
r = requests.get(urlToData, allow_redirects=True)
open(completeName, 'wb').write(r.content)
print(data['Data']['fileName']+' has been successfully downloaded in targetDir: '+ target_Dir)
logging.info(data['Data']['fileName']+' has been successfully downloaded in targetDir: '+ target_Dir)
return urlToData
else:
print('INFO: There is no data with ID: ' + granule_id)
logging.info('There is no data with ID: ' + granule_id)
return {}
except requests.exceptions.RequestException as e:
print('ERROR: ' + str(e))
logging.error(str(e))
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
#########################################################################
# -*- coding: utf-8 -*-
class dataset:
def __init__(self):
"""
This class contains the dataset and all the auxiliary information"""
self.campaign = ""
self.scenes = []
self.SLClist = {}
self.SLCFilenames = {}
self.heading={}
self.z_flight={}
self.z_terrain={}
self.GRD_resol={}
self.pixel_spacing = {}
self.surface_resol = {}
self.SLR_start = {}
self.master = {}
self.demname = {}
self.demFilenames= {}
self.incFilenames = {}
self.kzFilenames = {}
self.azimuthFiles = {}
self.rangeFiles = {}
def get_url(collection,granulename):
granule=get_granule_by_name(collection+':@'+granulename)
datalist=granule['Granule']['dataList']
url=datalist[0]['Data']['filePath']
return(url)
def format_metadata(json_result):
"""Parse configuration xml and init dataset class"""
import re
# Init
data_stack = dataset()
data_stack.campaign = json_result[0]['Granule']['collection']['Collection']['shortName']
#if the research asked some specific scenes
# All the data of the collections are returned and the scene list must be extract from the granules
for granule in json_result :
if granule['Granule']['productType']=='SLC':
scene=granule['Granule']['granuleScene']['Granule']['name']
#add scene in the list avoiding duplicates
## inputfilenames
polarisation=granule['Granule']['polarization']
key=(scene,polarisation)
value=granule['Granule']['name']
url=get_url(data_stack.campaign,value)
data_stack.SLClist.update(dict([(key,value)]))
data_stack.SLCFilenames.update(dict([(key,url)]))
if not scene in data_stack.scenes:
#append scenes and all metadata of the scene
data_stack.scenes.append(scene)
#### heading
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['heading'])])
data_stack.heading.update(keyval)
#z_flight
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['zFlight'])])
data_stack.z_flight.update(keyval)
##z_terrain
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['zTerrain'])])
data_stack.z_terrain.update(keyval)
##GRD_resol
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['grdResol'])])
data_stack.GRD_resol.update(keyval)
##pixel_spacing
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['pixelSpacing'])])
data_stack.pixel_spacing.update(keyval)
##surface_resol
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['surfaceResol'])])
data_stack.surface_resol.update(keyval)
##SLR_start
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['slrStart'])])
data_stack.SLR_start.update(keyval)
##master
#search for the presence of az files in the file list of the granule
#bool_list=bool(re.search("az.tiff",data)) for data in granule['Granule']['granuleScene']['Granule']['granuleList']]
#if True in bool_list :
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['master'])])
data_stack.master.update(keyval)
##demname
keyval=dict([(scene,granule['Granule']['granuleScene']['Granule']['dem'])])
data_stack.demname.update(keyval)
##demFilenames
demname=granule['Granule']['granuleScene']['Granule']['dem']
#if a dem is referenced, try to get its filename
if len(demname)>0:
try :
demfilename=get_url(data_stack.campaign,data_stack.campaign+'_'+demname+'_dem.tiff')
except:
demfilename=''
else :
demfilename=''
keyval=dict([(scene,demfilename)])
data_stack.demFilenames.update(keyval)
##azfilenames
#search for the presence of az files in the file list of the granule
bool_list=[bool(re.search("az.tiff",data)) for data in granule['Granule']['granuleScene']['Granule']['granuleList']]
if True in bool_list :
azfile=granule['Granule']['granuleScene']['Granule']['granuleList'][bool_list.index(True)]
azfile=get_url(data_stack.campaign,azfile)
elif granule['Granule']['granuleScene']['Granule']['master']!='n/a':
#get master name and get its azimtuh
master=granule['Granule']['granuleScene']['Granule']['master']
if len(master)>0:
try :
master_granules=get_granule_by_name(data_stack.campaign+':@'+master)['Granule']['granuleList']
azfile=[file for file in master_granules if "az" in file][0]
azfile=get_url(data_stack.campaign,azfile)
except:
azfile=''
else:
azfile=''
else:
azfile=''
keyval=dict([(scene,azfile)])
data_stack.azimuthFiles.update(keyval)
##rgfilenames
bool_list=[bool(re.search("rg.tiff",data)) for data in granule['Granule']['granuleScene']['Granule']['granuleList']]
if True in bool_list :
rgfile=granule['Granule']['granuleScene']['Granule']['granuleList'][bool_list.index(True)]
rgfile=get_url(data_stack.campaign,rgfile)
elif granule['Granule']['granuleScene']['Granule']['master']!='n/a':
#get master name and get its azimtuh
master=granule['Granule']['granuleScene']['Granule']['master']
if len(master)>0:
try :
master_granules=get_granule_by_name(data_stack.campaign+':@'+master)['Granule']['granuleList']
rgfile=[file for file in master_granules if "rg" in file][0]
rgfile=get_url(data_stack.campaign,rgfile)
except:
rgfile=''
else:
rgfile=''
else:
rgfile=''
keyval=dict([(scene,rgfile)])
data_stack.rangeFiles.update(keyval)
##incfilenames
bool_list=[bool(re.search("inc.tiff",data)) for data in granule['Granule']['granuleScene']['Granule']['granuleList']]
if True in bool_list :
incfile=granule['Granule']['granuleScene']['Granule']['granuleList'][bool_list.index(True)]
incfile=get_url(data_stack.campaign,incfile)
elif granule['Granule']['granuleScene']['Granule']['master']!='n/a':
#get master name and get its azimtuh
master=granule['Granule']['granuleScene']['Granule']['master']
if len(master)>0:
try :
master_granules=get_granule_by_name(data_stack.campaign+':@'+master)['Granule']['granuleList']
incfile=[file for file in master_granules if "inc" in file][0]
incfile=get_url(data_stack.campaign,incfile)
except:
incfile=''
else:
incfile=''
else:
incfile=''
keyval=dict([(scene,incfile)])
data_stack.incFilenames.update(keyval)
##kzfilenames
bool_list=[bool(re.search("kz.tiff",data)) for data in granule['Granule']['granuleScene']['Granule']['granuleList']]
if True in bool_list :
kzfile=granule['Granule']['granuleScene']['Granule']['granuleList'][bool_list.index(True)]
kzfile=get_url(data_stack.campaign,kzfile)
else:
kzfile=''
keyval=dict([(scene,kzfile)])
data_stack.kzFilenames.update(keyval)
return data_stack