def get_or_create(self,
uri,
n_points=10,
uri_filter_args=None,
*args,
**kwargs):
''' Create dataset and corresponding metadata
Parameters:
----------
uri : str
URI to file or stream openable by Nansat
n_points : int
Number of border points (default is 10)
uri_filter_args : dict
Extra DatasetURI filter arguments if several datasets can refer to the same URI
Returns:
-------
dataset and flag
'''
if not uri_filter_args:
uri_filter_args = {}
# Validate uri - this should raise an exception if the uri doesn't point to a valid
# file or stream
validate_uri(uri)
# Several datasets can refer to the same uri (e.g., scatterometers and svp drifters), so we
# need to pass uri_filter_args
uris = DatasetURI.objects.filter(uri=uri, **uri_filter_args)
if len(uris) > 0:
return uris[0].dataset, False
# Open file with Nansat
n = Nansat(nansat_filename(uri), **kwargs)
# get metadata from Nansat and get objects from vocabularies
n_metadata = n.get_metadata()
# set compulsory metadata (source)
platform, _ = Platform.objects.get_or_create(
json.loads(n_metadata['platform']))
instrument, _ = Instrument.objects.get_or_create(
json.loads(n_metadata['instrument']))
specs = n_metadata.get('specs', '')
source, _ = Source.objects.get_or_create(platform=platform,
instrument=instrument,
specs=specs)
default_char_fields = {
'entry_id': lambda: 'NERSC_' + str(uuid.uuid4()),
'entry_title': lambda: 'NONE',
'summary': lambda: 'NONE',
}
# set optional CharField metadata from Nansat or from default_char_fields
options = {}
for name in default_char_fields:
if name not in n_metadata:
warnings.warn('%s is not provided in Nansat metadata!' % name)
options[name] = default_char_fields[name]()
else:
options[name] = n_metadata[name]
default_foreign_keys = {
'gcmd_location': {
'model': Location,
'value': pti.get_gcmd_location('SEA SURFACE')
},
'data_center': {
'model': DataCenter,
'value': pti.get_gcmd_provider('NERSC')
},
'ISO_topic_category': {
'model': ISOTopicCategory,
'value': pti.get_iso19115_topic_category('Oceans')
},
}
# set optional ForeignKey metadata from Nansat or from default_foreign_keys
for name in default_foreign_keys:
value = default_foreign_keys[name]['value']
model = default_foreign_keys[name]['model']
if name not in n_metadata:
warnings.warn('%s is not provided in Nansat metadata!' % name)
else:
try:
value = json.loads(n_metadata[name])
except:
warnings.warn(
'%s value of %s metadata provided in Nansat is wrong!'
% (n_metadata[name], name))
options[name], _ = model.objects.get_or_create(value)
# Find coverage to set number of points in the geolocation
if len(n.vrt.dataset.GetGCPs()) > 0:
n.reproject_gcps()
geolocation = GeographicLocation.objects.get_or_create(
geometry=WKTReader().read(n.get_border_wkt(nPoints=n_points)))[0]
# create dataset
ds, created = Dataset.objects.get_or_create(
time_coverage_start=n.get_metadata('time_coverage_start'),
time_coverage_end=n.get_metadata('time_coverage_end'),
source=source,
geographic_location=geolocation,
**options)
# create dataset URI
ds_uri, _ = DatasetURI.objects.get_or_create(uri=uri, dataset=ds)
return ds, created
def get_or_create(self,
uri,
n_points=10,
uri_filter_args=None,
uri_service_name=FILE_SERVICE_NAME,
uri_service_type=LOCAL_FILE_SERVICE,
*args,
**kwargs):
""" Create dataset and corresponding metadata
Parameters:
----------
uri : str
URI to file or stream openable by Nansat
n_points : int
Number of border points (default is 10)
uri_filter_args : dict
Extra DatasetURI filter arguments if several datasets can refer to the same URI
uri_service_name : str
name of the service which is used ('dapService', 'fileService', 'http' or 'wms')
uri_service_type : str
type of the service which is used ('OPENDAP', 'local', 'HTTPServer' or 'WMS')
Returns:
-------
dataset and flag
"""
if not uri_filter_args:
uri_filter_args = {}
# Validate uri - this should raise an exception if the uri doesn't point to a valid
# file or stream
validate_uri(uri)
# Several datasets can refer to the same uri (e.g., scatterometers and svp drifters), so we
# need to pass uri_filter_args
uris = DatasetURI.objects.filter(uri=uri, **uri_filter_args)
if len(uris) > 0:
return uris[0].dataset, False
# Open file with Nansat
n = Nansat(nansat_filename(uri), **kwargs)
# get metadata from Nansat and get objects from vocabularies
n_metadata = n.get_metadata()
entry_id = n_metadata.get('entry_id', None)
# set compulsory metadata (source)
platform, _ = Platform.objects.get_or_create(
json.loads(n_metadata['platform']))
instrument, _ = Instrument.objects.get_or_create(
json.loads(n_metadata['instrument']))
specs = n_metadata.get('specs', '')
source, _ = Source.objects.get_or_create(platform=platform,
instrument=instrument,
specs=specs)
default_char_fields = {
# Adding NERSC_ in front of the id violates the string representation of the uuid
#'entry_id': lambda: 'NERSC_' + str(uuid.uuid4()),
'entry_id': lambda: str(uuid.uuid4()),
'entry_title': lambda: 'NONE',
'summary': lambda: 'NONE',
}
# set optional CharField metadata from Nansat or from default_char_fields
options = {}
try:
existing_ds = Dataset.objects.get(entry_id=entry_id)
except Dataset.DoesNotExist:
existing_ds = None
for name in default_char_fields:
if name not in n_metadata:
warnings.warn('%s is not provided in Nansat metadata!' % name)
# prevent overwriting of existing values by defaults
if existing_ds:
options[name] = existing_ds.__getattribute__(name)
else:
options[name] = default_char_fields[name]()
else:
options[name] = n_metadata[name]
default_foreign_keys = {
'gcmd_location': {
'model': Location,
'value': pti.get_gcmd_location('SEA SURFACE')
},
'data_center': {
'model': DataCenter,
'value': pti.get_gcmd_provider('NERSC')
},
'ISO_topic_category': {
'model': ISOTopicCategory,
'value': pti.get_iso19115_topic_category('Oceans')
},
}
# set optional ForeignKey metadata from Nansat or from default_foreign_keys
for name in default_foreign_keys:
value = default_foreign_keys[name]['value']
model = default_foreign_keys[name]['model']
if name not in n_metadata:
warnings.warn('%s is not provided in Nansat metadata!' % name)
else:
try:
value = json.loads(n_metadata[name])
except:
warnings.warn(
'%s value of %s metadata provided in Nansat is wrong!'
% (n_metadata[name], name))
if existing_ds:
options[name] = existing_ds.__getattribute__(name)
else:
options[name], _ = model.objects.get_or_create(value)
# Find coverage to set number of points in the geolocation
if len(n.vrt.dataset.GetGCPs()) > 0:
n.reproject_gcps()
geolocation = GeographicLocation.objects.get_or_create(
geometry=WKTReader().read(n.get_border_wkt(nPoints=n_points)))[0]
# create dataset
# - the get_or_create method should use get_or_create here as well,
# or its name should be changed - see issue #127
ds, created = Dataset.objects.update_or_create(
entry_id=options['entry_id'],
defaults={
'time_coverage_start': n.get_metadata('time_coverage_start'),
'time_coverage_end': n.get_metadata('time_coverage_end'),
'source': source,
'geographic_location': geolocation,
'gcmd_location': options["gcmd_location"],
'ISO_topic_category': options["ISO_topic_category"],
"data_center": options["data_center"],
'entry_title': options["entry_title"],
'summary': options["summary"]
})
# create parameter
all_band_meta = n.bands()
for band_id in range(1, len(all_band_meta) + 1):
band_meta = all_band_meta[band_id]
standard_name = band_meta.get('standard_name', None)
short_name = band_meta.get('short_name', None)
units = band_meta.get('units', None)
if standard_name in ['latitude', 'longitude', None]:
continue
params = Parameter.objects.filter(standard_name=standard_name)
if params.count() > 1 and short_name is not None:
params = params.filter(short_name=short_name)
if params.count() > 1 and units is not None:
params = params.filter(units=units)
if params.count() >= 1:
ds.parameters.add(params[0])
# create dataset URI
DatasetURI.objects.get_or_create(name=uri_service_name,
service=uri_service_type,
uri=uri,
dataset=ds)
return ds, created
def get_or_create(self, uri, reprocess=False, *args, **kwargs):
# ingest file to db
ds, created = super(DatasetManager,
self).get_or_create(uri, *args, **kwargs)
# set Dataset entry_title
ds.entry_title = 'SAR NRCS'
ds.save()
# Unless reprocess==True, we may not need to do the following... (see
# managers.py in sar doppler processor)
#visExists = ... # check if visualization(s) already created
#if visExists and not reprocess:
# warnings.warn('NO VISUALISATIONS CREATED - update managers.py')
# return ds, created
n = Nansat(nansat_filename(uri))
n.reproject_GCPs()
n.resize(pixelsize=500)
lon, lat = n.get_corners()
lat_max = min(lat.max(), 85)
d = Domain(
NSR(3857), '-lle %f %f %f %f -ts %d %d' %
(lon.min(), lat.min(), lon.max(), lat_max, n.shape()[1],
n.shape()[0]))
# Get all NRCS bands
s0bands = []
pp = []
for key, value in n.bands().iteritems():
try:
if value['standard_name'] == standard_name:
s0bands.append(key)
pp.append(value['polarization'])
except KeyError:
continue
''' Create data products
'''
mm = self.__module__.split('.')
module = '%s.%s' % (mm[0], mm[1])
mp = media_path(module, n.fileName)
# ppath = product_path(module, n.fileName)
# Create png's for each band
num_products = 0
for band in s0bands:
print 'Visualize', band
s0_tmp = n[band]
n_tmp = Nansat(domain=n, array=s0_tmp)
n_tmp.reproject_GCPs()
n_tmp.reproject(d)
s0 = n_tmp[1]
n_tmp = None
mask = np.ones(s0.shape, np.uint8)
mask[np.isnan(s0) + (s0 <= 0)] = 0
s0 = np.log10(s0) * 10.
meta = n.bands()[band]
product_filename = '%s_%s.png' % (meta['short_name'],
meta['polarization'])
nansatFigure(s0, mask, polarization_clims[meta['polarization']][0],
polarization_clims[meta['polarization']][1], mp,
product_filename)
# Get DatasetParameter
param = Parameter.objects.get(short_name=meta['short_name'])
dsp, created = DatasetParameter.objects.get_or_create(
dataset=ds, parameter=param)
# Create Visualization
geom, created = GeographicLocation.objects.get_or_create(
geometry=WKTReader().read(n.get_border_wkt()))
vv, created = Visualization.objects.get_or_create(
uri='file://localhost%s/%s' % (mp, product_filename),
title='%s %s polarization' %
(param.standard_name, meta['polarization']),
geographic_location=geom)
# Create VisualizationParameter
vp, created = VisualizationParameter.objects.get_or_create(
visualization=vv, ds_parameter=dsp)
return ds, True
def get_or_create(self, uri, reprocess=False, *args, **kwargs):
# ingest file to db
ds, created = super(DatasetManager,
self).get_or_create(uri, *args, **kwargs)
fn = nansat_filename(uri)
n = Nansat(fn)
# Reproject to leaflet projection
xlon, xlat = n.get_corners()
d = Domain(
NSR(3857), '-lle %f %f %f %f -tr 1000 1000' %
(xlon.min(), xlat.min(), xlon.max(), xlat.max()))
n.reproject(d)
# Get band numbers of required bands according to standard names
speedBandNum = n._get_band_number({'standard_name': 'wind_speed'})
dirBandNum = n._get_band_number(
{'standard_name': 'wind_from_direction'})
# Get numpy arrays of the bands
speed = n[speedBandNum]
dir = n[dirBandNum]
## It probably wont work with nansatmap...
#nmap = Nansatmap(n, resolution='l')
#nmap.pcolormesh(speed, vmax=18)
#nmap.quiver(-speed*np.sin(dir), speed*np.cos(dir), step=10, scale=300,
# width=0.002)
# Set paths - this code should be inherited but I think there is an
# issue in generalising the first line that defines the current module
mm = self.__module__.split('.')
module = '%s.%s' % (mm[0], mm[1])
mp = media_path(module, n.fileName)
ppath = product_path(module, n.fileName)
filename = os.path.basename(n.fileName).split('.')[0] + '.' + \
os.path.basename(n.fileName).split('.')[1] + '.png'
# check uniqueness of parameter
param1 = Parameter.objects.get(standard_name=n.get_metadata(
bandID=speedBandNum, key='standard_name'))
param2 = Parameter.objects.get(standard_name=n.get_metadata(
bandID=dirBandNum, key='standard_name'))
n.write_figure(os.path.join(mp, filename),
bands=speedBandNum,
mask_array=n['swathmask'],
mask_lut={0: [128, 128, 128]},
transparency=[128, 128, 128])
# Get DatasetParameter
dsp1, created = DatasetParameter.objects.get_or_create(
dataset=ds, parameter=param1)
# Create Visualization
geom, created = GeographicLocation.objects.get_or_create(
geometry=WKTReader().read(n.get_border_wkt()))
vv, created = Visualization.objects.get_or_create(
uri='file://localhost%s/%s' % (mp, filename),
title='%s' % (param1.standard_name),
geographic_location=geom)
# Create VisualizationParameter
vp, created = VisualizationParameter.objects.get_or_create(
visualization=vv, ds_parameter=dsp1)
return ds, True
def get_or_create(self, uri, *args, **kwargs):
""" Ingest gsar file to geo-spaas db
"""
ds, created = super(DatasetManager, self).get_or_create(uri, *args, **kwargs)
# TODO: Check if the following is necessary
if not type(ds) == Dataset:
return ds, False
# set Dataset entry_title
ds.entry_title = 'SAR Doppler'
ds.save()
fn = nansat_filename(uri)
n = Nansat(fn, subswath=0)
gg = WKTReader().read(n.get_border_wkt())
if ds.geographic_location.geometry.area>gg.area:
return ds, False
# Update dataset border geometry
# This must be done every time a Doppler file is processed. It is time
# consuming but apparently the only way to do it. Could be checked
# though...
swath_data = {}
lon = {}
lat = {}
astep = {}
rstep = {}
az_left_lon = {}
ra_upper_lon = {}
az_right_lon = {}
ra_lower_lon = {}
az_left_lat = {}
ra_upper_lat = {}
az_right_lat = {}
ra_lower_lat = {}
num_border_points = 10
border = 'POLYGON(('
for i in range(self.N_SUBSWATHS):
# Read subswaths
swath_data[i] = Nansat(fn, subswath=i)
# Should use nansat.domain.get_border - see nansat issue #166
# (https://github.com/nansencenter/nansat/issues/166)
lon[i], lat[i] = swath_data[i].get_geolocation_grids()
astep[i] = max(1, (lon[i].shape[0] / 2 * 2 - 1) / num_border_points)
rstep[i] = max(1, (lon[i].shape[1] / 2 * 2 - 1) / num_border_points)
az_left_lon[i] = lon[i][0:-1:astep[i], 0]
az_left_lat[i] = lat[i][0:-1:astep[i], 0]
az_right_lon[i] = lon[i][0:-1:astep[i], -1]
az_right_lat[i] = lat[i][0:-1:astep[i], -1]
ra_upper_lon[i] = lon[i][-1, 0:-1:rstep[i]]
ra_upper_lat[i] = lat[i][-1, 0:-1:rstep[i]]
ra_lower_lon[i] = lon[i][0, 0:-1:rstep[i]]
ra_lower_lat[i] = lat[i][0, 0:-1:rstep[i]]
lons = np.concatenate((az_left_lon[0], ra_upper_lon[0],
ra_upper_lon[1], ra_upper_lon[2],
ra_upper_lon[3], ra_upper_lon[4],
np.flipud(az_right_lon[4]), np.flipud(ra_lower_lon[4]),
np.flipud(ra_lower_lon[3]), np.flipud(ra_lower_lon[2]),
np.flipud(ra_lower_lon[1]), np.flipud(ra_lower_lon[0])))
# apply 180 degree correction to longitude - code copied from
# get_border_wkt...
# TODO: simplify using np.mod?
for ilon, llo in enumerate(lons):
lons[ilon] = copysign(acos(cos(llo * pi / 180.)) / pi * 180,
sin(llo * pi / 180.))
lats = np.concatenate((az_left_lat[0], ra_upper_lat[0],
ra_upper_lat[1], ra_upper_lat[2],
ra_upper_lat[3], ra_upper_lat[4],
np.flipud(az_right_lat[4]), np.flipud(ra_lower_lat[4]),
np.flipud(ra_lower_lat[3]), np.flipud(ra_lower_lat[2]),
np.flipud(ra_lower_lat[1]), np.flipud(ra_lower_lat[0])))
poly_border = ','.join(str(llo) + ' ' + str(lla) for llo, lla in zip(lons, lats))
wkt = 'POLYGON((%s))' % poly_border
new_geometry = WKTReader().read(wkt)
# Get geolocation of dataset - this must be updated
geoloc = ds.geographic_location
# Check geometry, return if it is the same as the stored one
created = False
if geoloc.geometry != new_geometry:
# Change the dataset geolocation to cover all subswaths
geoloc.geometry = new_geometry
geoloc.save()
created = True
return ds, created
def get_or_create(self, uri, *args, **kwargs):
""" Ingest gsar file to geo-spaas db
"""
ds, created = super(DatasetManager,
self).get_or_create(uri, *args, **kwargs)
connection.close()
# TODO: Check if the following is necessary
if not type(ds) == Dataset:
return ds, False
fn = nansat_filename(uri)
n = Nansat(fn, subswath=0)
# set Dataset entry_title
ds.entry_title = n.get_metadata('title')
ds.save()
if created:
from sar_doppler.models import SARDopplerExtraMetadata
# Store the polarization and associate the dataset
extra, _ = SARDopplerExtraMetadata.objects.get_or_create(
dataset=ds, polarization=n.get_metadata('polarization'))
if not _:
raise ValueError(
'Created new dataset but could not create instance of ExtraMetadata'
)
ds.sardopplerextrametadata_set.add(extra)
connection.close()
gg = WKTReader().read(n.get_border_wkt())
#lon, lat = n.get_border()
#ind_near_range = 0
#ind_far_range = int(lon.size/4)
#import pyproj
#geod = pyproj.Geod(ellps='WGS84')
#angle1,angle2,img_width = geod.inv(lon[ind_near_range], lat[ind_near_range],
# lon[ind_far_range], lat[ind_far_range])
# If the area of the dataset geometry is larger than the area of the subswath border, it means that the dataset
# has already been created (the area should be the total area of all subswaths)
if np.floor(ds.geographic_location.geometry.area) > np.round(gg.area):
return ds, False
swath_data = {}
lon = {}
lat = {}
astep = {}
rstep = {}
az_left_lon = {}
ra_upper_lon = {}
az_right_lon = {}
ra_lower_lon = {}
az_left_lat = {}
ra_upper_lat = {}
az_right_lat = {}
ra_lower_lat = {}
num_border_points = 10
border = 'POLYGON(('
for i in range(self.N_SUBSWATHS):
# Read subswaths
swath_data[i] = Nansat(fn, subswath=i)
lon[i], lat[i] = swath_data[i].get_geolocation_grids()
astep[i] = int(
max(1, (lon[i].shape[0] / 2 * 2 - 1) / num_border_points))
rstep[i] = int(
max(1, (lon[i].shape[1] / 2 * 2 - 1) / num_border_points))
az_left_lon[i] = lon[i][0:-1:astep[i], 0]
az_left_lat[i] = lat[i][0:-1:astep[i], 0]
az_right_lon[i] = lon[i][0:-1:astep[i], -1]
az_right_lat[i] = lat[i][0:-1:astep[i], -1]
ra_upper_lon[i] = lon[i][-1, 0:-1:rstep[i]]
ra_upper_lat[i] = lat[i][-1, 0:-1:rstep[i]]
ra_lower_lon[i] = lon[i][0, 0:-1:rstep[i]]
ra_lower_lat[i] = lat[i][0, 0:-1:rstep[i]]
lons = np.concatenate(
(az_left_lon[0], ra_upper_lon[0], ra_upper_lon[1], ra_upper_lon[2],
ra_upper_lon[3], ra_upper_lon[4], np.flipud(az_right_lon[4]),
np.flipud(ra_lower_lon[4]), np.flipud(ra_lower_lon[3]),
np.flipud(ra_lower_lon[2]), np.flipud(ra_lower_lon[1]),
np.flipud(ra_lower_lon[0]))).round(decimals=3)
# apply 180 degree correction to longitude - code copied from
# get_border_wkt...
# TODO: simplify using np.mod?
for ilon, llo in enumerate(lons):
lons[ilon] = copysign(
acos(cos(llo * pi / 180.)) / pi * 180, sin(llo * pi / 180.))
lats = np.concatenate(
(az_left_lat[0], ra_upper_lat[0], ra_upper_lat[1], ra_upper_lat[2],
ra_upper_lat[3], ra_upper_lat[4], np.flipud(az_right_lat[4]),
np.flipud(ra_lower_lat[4]), np.flipud(ra_lower_lat[3]),
np.flipud(ra_lower_lat[2]), np.flipud(ra_lower_lat[1]),
np.flipud(ra_lower_lat[0]))).round(decimals=3)
poly_border = ','.join(
str(llo) + ' ' + str(lla) for llo, lla in zip(lons, lats))
wkt = 'POLYGON((%s))' % poly_border
new_geometry = WKTReader().read(wkt)
# Get or create new geolocation of dataset
# Returns False if it is the same as an already created one (this may happen when a lot of data is processed)
ds.geographic_location, cr = GeographicLocation.objects.get_or_create(
geometry=new_geometry)
connection.close()
return ds, True
