def open_dataset(self,
time_range: TimeRangeLike.TYPE = None,
region: PolygonLike.TYPE = None,
var_names: VarNamesLike.TYPE = None,
protocol: str = None) -> Any:
time_range = TimeRangeLike.convert(time_range) if time_range else None
var_names = VarNamesLike.convert(var_names) if var_names else None
selected_file_list = self._find_files(time_range)
if not selected_file_list:
msg = 'CCI Open Data Portal data source "{}"\ndoes not seem to have any datasets'.format(self.id)
if time_range is not None:
msg += ' in given time range {}'.format(TimeRangeLike.format(time_range))
raise DataAccessError(msg)
files = self._get_urls_list(selected_file_list, _ODP_PROTOCOL_OPENDAP)
try:
ds = open_xarray_dataset(files)
if region:
ds = normalize_impl(ds)
ds = subset_spatial_impl(ds, region)
if var_names:
ds = ds.drop([var_name for var_name in ds.data_vars.keys() if var_name not in var_names])
return ds
except OSError as e:
if time_range:
raise DataAccessError("Cannot open remote dataset for time range {}:\n"
"{}"
.format(TimeRangeLike.format(time_range), e), source=self) from e
else:
raise DataAccessError("Cannot open remote dataset:\n"
"{}"
.format(TimeRangeLike.format(time_range), e), source=self) from e
def open_dataset(self,
time_range: TimeRangeLike.TYPE = None,
region: PolygonLike.TYPE = None,
var_names: VarNamesLike.TYPE = None,
protocol: str = None) -> Any:
time_range = TimeRangeLike.convert(time_range) if time_range else None
if region:
region = PolygonLike.convert(region)
if var_names:
var_names = VarNamesLike.convert(var_names)
paths = []
if time_range:
time_series = list(self._files.values())
file_paths = list(self._files.keys())
for i in range(len(time_series)):
if time_series[i]:
if isinstance(time_series[i], Tuple) and \
time_series[i][0] >= time_range[0] and \
time_series[i][1] <= time_range[1]:
paths.extend(self._resolve_file_path(file_paths[i]))
elif isinstance(
time_series[i], datetime
) and time_range[0] <= time_series[i] < time_range[1]:
paths.extend(self._resolve_file_path(file_paths[i]))
else:
for file in self._files.items():
paths.extend(self._resolve_file_path(file[0]))
if paths:
paths = sorted(set(paths))
try:
ds = open_xarray_dataset(paths)
if region:
ds = normalize_impl(ds)
ds = subset_spatial_impl(ds, region)
if var_names:
ds = ds.drop([
var_name for var_name in ds.data_vars.keys()
if var_name not in var_names
])
return ds
except OSError as e:
if time_range:
raise DataAccessError(
"Cannot open local dataset for time range {}:\n"
"{}".format(TimeRangeLike.format(time_range), e),
source=self) from e
else:
raise DataAccessError("Cannot open local dataset:\n"
"{}".format(e),
source=self) from e
else:
if time_range:
raise DataAccessError(
"No local datasets available for\nspecified time range {}".
format(TimeRangeLike.format(time_range)),
source=self)
else:
raise DataAccessError("No local datasets available",
source=self)
def normalize(ds: xr.Dataset) -> xr.Dataset:
"""
Normalize the geo- and time-coding upon opening the given dataset w.r.t.
to a common (CF-compatible) convention used within Cate. This will maximize the compatibility of
a dataset for usage with Cate's operations.
That is,
* variables named "latitude" will be renamed to "lat";
* variables named "longitude" or "long" will be renamed to "lon";
Then, for equi-rectangular grids,
* Remove 2D "lat" and "lon" variables;
* Two new 1D coordinate variables "lat" and "lon" will be generated from original 2D forms.
Finally, it will be ensured that a "time" coordinate variable will be of type *datetime*.
:param ds: The dataset to normalize.
:return: The normalized dataset, or the original dataset, if it is already "normal".
"""
return normalize_impl(ds)
def normalize(ds: xr.Dataset) -> xr.Dataset:
"""
Normalize the geo- and time-coding upon opening the given dataset w.r.t.
to a common (CF-compatible) convention used within Cate. This will maximize the compatibility of
a dataset for usage with Cate's operations.
That is,
* variables named "latitude" will be renamed to "lat";
* variables named "longitude" or "long" will be renamed to "lon";
Then, for equi-rectangular grids,
* Remove 2D "lat" and "lon" variables;
* Two new 1D coordinate variables "lat" and "lon" will be generated from original 2D forms.
Finally, it will be ensured that a "time" coordinate variable will be of type *datetime*.
:param ds: The dataset to normalize.
:return: The normalized dataset, or the original dataset, if it is already "normal".
"""
return normalize_impl(ds)
def _make_local(self,
local_ds: LocalDataSource,
time_range: TimeRangeLike.TYPE = None,
region: PolygonLike.TYPE = None,
var_names: VarNamesLike.TYPE = None,
monitor: Monitor = Monitor.NONE):
local_id = local_ds.id
time_range = TimeRangeLike.convert(time_range)
region = PolygonLike.convert(region)
var_names = VarNamesLike.convert(var_names)
time_range, region, var_names = self._apply_make_local_fixes(
time_range, region, var_names)
compression_level = get_config_value('NETCDF_COMPRESSION_LEVEL',
NETCDF_COMPRESSION_LEVEL)
compression_enabled = True if compression_level > 0 else False
do_update_of_verified_time_coverage_start_once = True
verified_time_coverage_start = None
verified_time_coverage_end = None
encoding_update = dict()
if compression_enabled:
encoding_update.update({
'zlib': True,
'complevel': compression_level
})
if region or var_names:
protocol = _ODP_PROTOCOL_OPENDAP
else:
protocol = _ODP_PROTOCOL_HTTP
local_path = os.path.join(local_ds.data_store.data_store_path,
local_id)
if not os.path.exists(local_path):
os.makedirs(local_path)
selected_file_list = self._find_files(time_range)
if not selected_file_list:
msg = 'CCI Open Data Portal data source "{}"\ndoes not seem to have any datasets'.format(
self.id)
if time_range is not None:
msg += ' in given time range {}'.format(
TimeRangeLike.format(time_range))
raise DataAccessError(msg)
try:
if protocol == _ODP_PROTOCOL_OPENDAP:
do_update_of_variables_meta_info_once = True
do_update_of_region_meta_info_once = True
files = self._get_urls_list(selected_file_list, protocol)
monitor.start('Sync ' + self.id, total_work=len(files))
for idx, dataset_uri in enumerate(files):
child_monitor = monitor.child(work=1)
file_name = os.path.basename(dataset_uri)
local_filepath = os.path.join(local_path, file_name)
time_coverage_start = selected_file_list[idx][1]
time_coverage_end = selected_file_list[idx][2]
try:
child_monitor.start(label=file_name, total_work=1)
remote_dataset = xr.open_dataset(dataset_uri)
if var_names:
remote_dataset = remote_dataset.drop([
var_name for var_name in
remote_dataset.data_vars.keys()
if var_name not in var_names
])
if region:
remote_dataset = normalize_impl(remote_dataset)
remote_dataset = subset_spatial_impl(
remote_dataset, region)
geo_lon_min, geo_lat_min, geo_lon_max, geo_lat_max = region.bounds
remote_dataset.attrs[
'geospatial_lat_min'] = geo_lat_min
remote_dataset.attrs[
'geospatial_lat_max'] = geo_lat_max
remote_dataset.attrs[
'geospatial_lon_min'] = geo_lon_min
remote_dataset.attrs[
'geospatial_lon_max'] = geo_lon_max
if do_update_of_region_meta_info_once:
local_ds.meta_info['bbox_maxx'] = geo_lon_max
local_ds.meta_info['bbox_minx'] = geo_lon_min
local_ds.meta_info['bbox_maxy'] = geo_lat_max
local_ds.meta_info['bbox_miny'] = geo_lat_min
do_update_of_region_meta_info_once = False
if compression_enabled:
for sel_var_name in remote_dataset.variables.keys(
):
remote_dataset.variables.get(
sel_var_name).encoding.update(
encoding_update)
remote_dataset.to_netcdf(local_filepath)
child_monitor.progress(work=1,
msg=str(time_coverage_start))
finally:
if do_update_of_variables_meta_info_once:
variables_info = local_ds.meta_info.get(
'variables', [])
local_ds.meta_info['variables'] = [
var_info for var_info in variables_info
if var_info.get('name') in remote_dataset.
variables.keys() and var_info.get(
'name') not in remote_dataset.dims.keys()
]
do_update_of_variables_meta_info_once = False
local_ds.add_dataset(
os.path.join(local_id, file_name),
(time_coverage_start, time_coverage_end))
if do_update_of_verified_time_coverage_start_once:
verified_time_coverage_start = time_coverage_start
do_update_of_verified_time_coverage_start_once = False
verified_time_coverage_end = time_coverage_end
child_monitor.done()
else:
outdated_file_list = []
for file_rec in selected_file_list:
filename, _, _, file_size, url = file_rec
dataset_file = os.path.join(local_path, filename)
# todo (forman, 20160915): must perform better checks on dataset_file if it is...
# ... outdated or incomplete or corrupted.
# JSON also includes "checksum" and "checksum_type" fields.
if not os.path.isfile(dataset_file) or (
file_size
and os.path.getsize(dataset_file) != file_size):
outdated_file_list.append(file_rec)
if outdated_file_list:
with monitor.starting('Sync ' + self.id,
len(outdated_file_list)):
bytes_to_download = sum(
[file_rec[3] for file_rec in outdated_file_list])
dl_stat = _DownloadStatistics(bytes_to_download)
file_number = 1
for filename, coverage_from, coverage_to, file_size, url in outdated_file_list:
dataset_file = os.path.join(local_path, filename)
sub_monitor = monitor.child(work=1.0)
# noinspection PyUnusedLocal
def reporthook(block_number, read_size,
total_file_size):
dl_stat.handle_chunk(read_size)
sub_monitor.progress(work=read_size,
msg=str(dl_stat))
sub_monitor_msg = "file %d of %d" % (
file_number, len(outdated_file_list))
with sub_monitor.starting(sub_monitor_msg,
file_size):
urllib.request.urlretrieve(
url[protocol],
filename=dataset_file,
reporthook=reporthook)
file_number += 1
local_ds.add_dataset(
os.path.join(local_id, filename),
(coverage_from, coverage_to))
if do_update_of_verified_time_coverage_start_once:
verified_time_coverage_start = coverage_from
do_update_of_verified_time_coverage_start_once = False
verified_time_coverage_end = coverage_to
except OSError as e:
raise DataAccessError(
"Copying remote data source failed: {}".format(e),
source=self) from e
local_ds.meta_info['temporal_coverage_start'] = TimeLike.format(
verified_time_coverage_start)
local_ds.meta_info['temporal_coverage_end'] = TimeLike.format(
verified_time_coverage_end)
local_ds.save(True)
def _make_local(self,
local_ds: 'LocalDataSource',
time_range: TimeRangeLike.TYPE = None,
region: PolygonLike.TYPE = None,
var_names: VarNamesLike.TYPE = None,
monitor: Monitor = Monitor.NONE):
local_id = local_ds.id
time_range = TimeRangeLike.convert(time_range) if time_range else None
region = PolygonLike.convert(region) if region else None
var_names = VarNamesLike.convert(
var_names) if var_names else None # type: Sequence
compression_level = get_config_value('NETCDF_COMPRESSION_LEVEL',
NETCDF_COMPRESSION_LEVEL)
compression_enabled = True if compression_level > 0 else False
encoding_update = dict()
if compression_enabled:
encoding_update.update({
'zlib': True,
'complevel': compression_level
})
local_path = os.path.join(local_ds.data_store.data_store_path,
local_id)
data_store_path = local_ds.data_store.data_store_path
if not os.path.exists(local_path):
os.makedirs(local_path)
monitor.start("Sync " + self.id, total_work=len(self._files.items()))
for remote_relative_filepath, coverage in self._files.items():
child_monitor = monitor.child(work=1)
file_name = os.path.basename(remote_relative_filepath)
local_relative_filepath = os.path.join(local_id, file_name)
local_absolute_filepath = os.path.join(data_store_path,
local_relative_filepath)
remote_absolute_filepath = os.path.join(
self._data_store.data_store_path, remote_relative_filepath)
if isinstance(coverage, Tuple):
time_coverage_start = coverage[0]
time_coverage_end = coverage[1]
if not time_range or time_coverage_start >= time_range[
0] and time_coverage_end <= time_range[1]:
if region or var_names:
do_update_of_variables_meta_info_once = True
do_update_of_region_meta_info_once = True
try:
remote_dataset = xr.open_dataset(
remote_absolute_filepath)
if var_names:
remote_dataset = remote_dataset.drop([
var_name for var_name in
remote_dataset.data_vars.keys()
if var_name not in var_names
])
if region:
remote_dataset = normalize_impl(remote_dataset)
remote_dataset = subset_spatial_impl(
remote_dataset, region)
geo_lon_min, geo_lat_min, geo_lon_max, geo_lat_max = region.bounds
remote_dataset.attrs[
'geospatial_lat_min'] = geo_lat_min
remote_dataset.attrs[
'geospatial_lat_max'] = geo_lat_max
remote_dataset.attrs[
'geospatial_lon_min'] = geo_lon_min
remote_dataset.attrs[
'geospatial_lon_max'] = geo_lon_max
if do_update_of_region_meta_info_once:
local_ds.meta_info[
'bbox_maxx'] = geo_lon_max
local_ds.meta_info[
'bbox_minx'] = geo_lon_min
local_ds.meta_info[
'bbox_maxy'] = geo_lat_max
local_ds.meta_info[
'bbox_miny'] = geo_lat_min
do_update_of_region_meta_info_once = False
if compression_enabled:
for sel_var_name in remote_dataset.variables.keys(
):
remote_dataset.variables.get(
sel_var_name).encoding.update(
encoding_update)
remote_dataset.to_netcdf(local_absolute_filepath)
child_monitor.progress(
work=1, msg=str(time_coverage_start))
finally:
if do_update_of_variables_meta_info_once:
variables_info = local_ds.meta_info.get(
'variables', [])
local_ds.meta_info['variables'] = [
var_info for var_info in variables_info
if var_info.get('name') in remote_dataset.
variables.keys() and var_info.get('name')
not in remote_dataset.dims.keys()
]
do_update_of_variables_meta_info_once = False
local_ds.add_dataset(
os.path.join(local_id, file_name),
(time_coverage_start, time_coverage_end))
child_monitor.done()
else:
shutil.copy(remote_absolute_filepath,
local_absolute_filepath)
local_ds.add_dataset(
local_relative_filepath,
(time_coverage_start, time_coverage_end))
child_monitor.done()
monitor.done()
return local_id
def _make_local(self,
local_ds: 'LocalDataSource',
time_range: TimeRangeLike.TYPE = None,
region: PolygonLike.TYPE = None,
var_names: VarNamesLike.TYPE = None,
monitor: Monitor = Monitor.NONE):
local_id = local_ds.id
time_range = TimeRangeLike.convert(time_range) if time_range else None
var_names = VarNamesLike.convert(var_names) if var_names else None # type: Sequence
compression_level = get_config_value('NETCDF_COMPRESSION_LEVEL', NETCDF_COMPRESSION_LEVEL)
compression_enabled = True if compression_level > 0 else False
encoding_update = dict()
if compression_enabled:
encoding_update.update({'zlib': True, 'complevel': compression_level})
local_path = os.path.join(local_ds.data_store.data_store_path, local_id)
data_store_path = local_ds.data_store.data_store_path
if not os.path.exists(local_path):
os.makedirs(local_path)
monitor.start("Sync " + self.id, total_work=len(self._files.items()))
for remote_relative_filepath, coverage in self._files.items():
child_monitor = monitor.child(work=1)
file_name = os.path.basename(remote_relative_filepath)
local_relative_filepath = os.path.join(local_id, file_name)
local_absolute_filepath = os.path.join(data_store_path, local_relative_filepath)
remote_absolute_filepath = os.path.join(self._data_store.data_store_path, remote_relative_filepath)
if isinstance(coverage, Tuple):
time_coverage_start = coverage[0]
time_coverage_end = coverage[1]
if not time_range or time_coverage_start >= time_range[0] and time_coverage_end <= time_range[1]:
if region or var_names:
do_update_of_variables_meta_info_once = True
do_update_of_region_meta_info_once = True
remote_dataset = None
try:
remote_dataset = xr.open_dataset(remote_absolute_filepath)
if var_names:
remote_dataset = remote_dataset.drop(
[var_name for var_name in remote_dataset.data_vars.keys()
if var_name not in var_names])
if region:
remote_dataset = normalize_impl(remote_dataset)
remote_dataset = adjust_spatial_attrs_impl(subset_spatial_impl(remote_dataset, region),
allow_point=False)
if do_update_of_region_meta_info_once:
# subset_spatial_impl
local_ds.meta_info['bbox_maxx'] = remote_dataset.attrs['geospatial_lon_max']
local_ds.meta_info['bbox_minx'] = remote_dataset.attrs['geospatial_lon_min']
local_ds.meta_info['bbox_maxy'] = remote_dataset.attrs['geospatial_lat_max']
local_ds.meta_info['bbox_miny'] = remote_dataset.attrs['geospatial_lat_min']
do_update_of_region_meta_info_once = False
if compression_enabled:
for sel_var_name in remote_dataset.variables.keys():
remote_dataset.variables.get(sel_var_name).encoding.update(encoding_update)
remote_dataset.to_netcdf(local_absolute_filepath)
child_monitor.progress(work=1, msg=str(time_coverage_start))
finally:
if do_update_of_variables_meta_info_once and remote_dataset is not None:
variables_info = local_ds.meta_info.get('variables', [])
local_ds.meta_info['variables'] = [var_info for var_info in variables_info
if var_info.get('name')
in remote_dataset.variables.keys()
and var_info.get('name')
not in remote_dataset.dims.keys()]
# noinspection PyUnusedLocal
do_update_of_variables_meta_info_once = False
local_ds.add_dataset(os.path.join(local_id, file_name),
(time_coverage_start, time_coverage_end))
child_monitor.done()
else:
shutil.copy(remote_absolute_filepath, local_absolute_filepath)
local_ds.add_dataset(local_relative_filepath, (time_coverage_start, time_coverage_end))
child_monitor.done()
monitor.done()
return local_id