def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check for a left and right BIN file - skip if not found
if not contains_required_files(resource, ['_left.tif', '_right.tif']):
self.log_skip(resource, "missing required files")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
if not self.force:
# Check NRMAC score > 15 before proceeding if available
nrmac_md = get_extractor_metadata(md, "terra.stereo-rgb.nrmac")
if not (nrmac_md and 'left_quality_score' in nrmac_md):
self.log_skip(resource,
"NRMAC quality score not available")
return CheckMessage.ignore
elif float(nrmac_md['left_quality_score']) > self.threshold:
self.log_skip(
resource,
"NRMAC quality score %s is above threshold of %s" %
(float(
nrmac_md['left_quality_score']), self.threshold))
return CheckMessage.ignore
if get_extractor_metadata(md, self.extractor_info['name'],
self.extractor_info['version']):
# Make sure outputs properly exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
left_enh_tiff = self.sensors.create_sensor_path(timestamp,
opts=['left'])
right_enh_tiff = self.sensors.create_sensor_path(
timestamp, opts=['right'])
if file_exists(left_enh_tiff) and file_exists(right_enh_tiff):
if contains_required_files(resource, [
os.path.basename(left_enh_tiff),
os.path.basename(right_enh_tiff)
]):
self.log_skip(
resource,
"metadata v%s and outputs already exist" %
self.extractor_info['version'])
return CheckMessage.ignore
else:
self.log_info(
resource,
"output files exist but not yet uploaded")
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
else:
self.log_error(resource, "no terraref metadata found")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check for a left and right BIN file - skip if not found
if not contains_required_files(resource, ['_left.bin', '_right.bin']):
self.log_skip(resource, "missing required files")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
if not self.overwrite and get_extractor_metadata(md, self.extractor_info['name'], self.extractor_info['version']):
# Make sure outputs properly exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
left_tiff = self.sensors.create_sensor_path(timestamp, opts=['left'])
right_tiff = self.sensors.create_sensor_path(timestamp, opts=['right'])
if file_exists(left_tiff) and file_exists(right_tiff):
self.log_skip(resource, "metadata v%s and outputs already exist" % self.extractor_info['version'])
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
else:
self.log_error(resource, "no terraref metadata found; sending to cleaner")
submit_extraction(connector, host, secret_key, resource['id'], "terra.metadata.cleaner")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check for an _ir.bin file before beginning processing
if not contains_required_files(resource, ['_ir.bin']):
self.log_skip(resource, "missing required files")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
if get_extractor_metadata(md, self.extractor_info['name'], self.extractor_info['version']):
# Make sure outputs properly exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
tif = self.sensors.get_sensor_path(timestamp)
png = tif.replace(".tif", ".png")
if file_exists(png) and file_exists(tif):
self.log_skip(resource, "metadata v%s and outputs already exist" % self.extractor_info['version'])
return CheckMessage.ignore
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
else:
self.log_skip(resource, "no terraref metadata found")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
if len(resource['files']) >= 23:
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(md, self.extractor_info['name'],
self.extractor_info['version']):
timestamp = resource['name'].split(" - ")[1]
out_fullday_netcdf = self.sensors.create_sensor_path(timestamp)
out_fullday_csv = out_fullday_netcdf.replace(".nc", "_geo.csv")
if file_exists(out_fullday_netcdf) and file_exists(
out_fullday_csv):
self.log_skip(
resource, "metadata v%s and outputs already exist" %
self.extractor_info['version'])
return CheckMessage.ignore
return CheckMessage.download
else:
self.log_skip(resource, "found less than 23 files")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
# First, check if we have the correct sensor type
md = download_metadata(connector, host, secret_key,
resource['parent']['id'])
ds_info = get_info(connector, host, secret_key,
resource['parent']['id'])
sensortype = self.determineSensorType(ds_info['name'])
if sensortype in ["ndvi", "pri"]:
if get_extractor_metadata(
md, self.extractor_info['name']) and not self.overwrite:
logging.info("skipping dataset %s, already processed" %
resource['id'])
return CheckMessage.ignore
# Check if output already exists
timestamp = ds_info['name'].split(" - ")[1]
out_file = self.get_sensor_path(timestamp,
opts=['extracted_values'])
if os.path.isfile(out_file) and not self.overwrite:
logging.info("skipping %s, outputs already exist" %
resource['id'])
return CheckMessage.ignore
return CheckMessage.download
else:
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
self.start_check(resource)
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(md, self.extractor_info['name']) and not self.overwrite:
self.log_skip(resource,"metadata indicates it was already processed")
return CheckMessage.ignore
return CheckMessage.download
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
if not contains_required_files(
resource,
['raw', 'raw.hdr', 'image.jpg', 'frameIndex.txt', 'settings.txt']):
self.log_skip(resource, "missing required files")
return CheckMessage.ignore
if resource['dataset_info']['name'].find("SWIR") > -1:
sensor_fullname = 'swir_netcdf'
else:
sensor_fullname = 'vnir_netcdf'
timestamp = resource['dataset_info']['name'].split(" - ")[1]
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
if get_extractor_metadata(md, self.extractor_info['name'],
self.extractor_info['version']):
# Make sure outputs properly exist
out_nc = self.sensors.get_sensor_path(timestamp,
sensor=sensor_fullname)
if file_exists(out_nc):
self.log_skip(
resource, "metadata v%s and outputs already exist" %
self.extractor_info['version'])
return CheckMessage.ignore
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
else:
self.log_skip(resource, "no terraref metadata found")
# See if we can recover it from disk
if sensor_fullname == 'vnir_netcdf':
date = timestamp.split("__")[0]
source_dir = "/home/extractor/sites/ua-mac/raw_data/VNIR/%s/%s/" % (
date, timestamp)
for f in os.listdir(source_dir):
if f.endswith("_metadata.json"):
self.log_info(resource,
"updating metadata from %s" % f)
raw_dsmd = load_json_file(os.path.join(source_dir, f))
clean_md = clean_metadata(raw_dsmd, 'VNIR')
complete_md = build_metadata(host, self.extractor_info,
resource['id'], clean_md,
'dataset')
remove_metadata(connector, host, secret_key,
resource['id'])
upload_metadata(connector, host, secret_key,
resource['id'], complete_md)
return CheckMessage.download
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if resource['name'].find('fullfield') > -1 and re.match("^.*\d+_ir_.*.tif", resource['name']):
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(md, self.extractor_info['name']) and not self.overwrite:
self.log_skip(resource,"metadata indicates it was already processed")
return CheckMessage.ignore
return CheckMessage.download
else:
self.log_skip(resource,"regex not matched for %s" % resource['name'])
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check for a left and right BIN file - skip if not found
found_left = False
found_right = False
for f in resource['files']:
if 'filename' in f:
if f['filename'].endswith('_left.bin'):
found_left = True
elif f['filename'].endswith('_right.bin'):
found_right = True
if not (found_left and found_right):
self.log_skip(
resource,
"found left: %s, right: %s" % (found_left, found_right))
return CheckMessage.ignore
# Check if outputs already exist unless overwrite is forced - skip if found
if not self.overwrite:
timestamp = resource['dataset_info']['name'].split(" - ")[1]
lbase = self.sensors.get_sensor_path(timestamp,
opts=['left'],
ext='')
rbase = self.sensors.get_sensor_path(timestamp,
opts=['right'],
ext='')
out_dir = os.path.dirname(lbase)
if (os.path.isfile(lbase + 'tif')
and os.path.isfile(rbase + 'tif')):
self.log_skip(resource, "outputs found in %s" % out_dir)
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(
md, self.extractor_info['name']) and not self.overwrite:
self.log_skip("metadata indicates it was already processed")
return CheckMessage.ignore
if get_terraref_metadata(md):
return CheckMessage.download
else:
self.log_skip("no terraref metadata found")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters): if not is_latest_file(resource): return CheckMessage.ignore # Check for expected input files before beginning processing if len(get_all_files(resource)) >= 23: md = download_metadata(connector, host, secret_key, resource['id']) if get_extractor_metadata(md, self.extractor_info['name'], self.extractor_info['version']): self.log_skip(resource, "metadata v%s already exists" % self.extractor_info['version']) return CheckMessage.ignore return CheckMessage.download else: self.log_skip(resource, 'not all input files are ready') return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if resource['name'].find('fullfield') > -1 and re.match(
"^.*\d+_rgb_.*thumb.tif", resource['name']):
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key,
resource['parent']['id'])
if get_extractor_metadata(
md, self.extractor_info['name']) and not self.overwrite:
logging.info(
"skipping dataset %s; metadata indicates it was already processed"
% resource['id'])
return CheckMessage.ignore
return CheckMessage.download
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if parameters["rulechecked"]:
return CheckMessage.download
if not is_latest_file(resource):
return CheckMessage.ignore
# Check for an ir.BIN file and metadata before beginning processing
found_ir = None
found_md = None
for f in resource['files']:
if 'filename' in f and f['filename'].endswith('_ir.bin'):
found_ir = f['filepath']
elif 'filename' in f and f['filename'].endswith('_metadata.json'):
found_md = f['filepath']
if found_ir:
# Check if outputs already exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
png_path = self.sensors.get_sensor_path(timestamp, ext='png')
tiff_path = self.sensors.get_sensor_path(timestamp)
if os.path.exists(png_path) and os.path.exists(
tiff_path) and not self.overwrite:
logging.getLogger(__name__).info(
"skipping dataset %s, outputs already exist" %
resource['id'])
return CheckMessage.ignore
# If we don't find _metadata.json file, check if we have metadata attached to dataset instead
if not found_md:
md = download_metadata(connector, host, secret_key,
resource['id'])
if get_extractor_metadata(
md,
self.extractor_info['name']) and not self.overwrite:
logging.getLogger(__name__).info(
"skipping dataset %s, already processed" %
resource['id'])
return CheckMessage.ignore
if get_terraref_metadata(md):
return CheckMessage.download
return CheckMessage.ignore
else:
return CheckMessage.download
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
# Check for 0000-0101 bin files before beginning processing
if len(resource['files']) < 102:
self.log_skip(resource, "less than 102 files found")
return CheckMessage.ignore
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
timestamp = resource['dataset_info']['name'].split(" - ")[1]
hist_path = self.sensors.get_sensor_path(timestamp, opts=['combined_hist'])
coloredImg_path = self.sensors.get_sensor_path(timestamp, opts=['combined_pseudocolored'])
# Count number of bin files in dataset, as well as number of existing outputs
ind_add = 0
ind_output = 0
for ind in range(0, 102):
format_ind = "{0:0>4}".format(ind) # e.g. 1 becomes 0001
for f in resource['files']:
if f['filename'].endswith(format_ind+'.bin'):
ind_add += 1
out_png = self.sensors.get_sensor_path(timestamp, opts=[format_ind])
if os.path.exists(out_png) and not self.overwrite:
ind_output += 1
break
# Do the outputs already exist?
if ind_output == 102 and os.path.exists(hist_path) and os.path.exists(coloredImg_path):
self.log_skip(resource, "outputs already exist")
return CheckMessage.ignore
# Do we have too few input BIN files?
if ind_add < 102:
self.log_skip(resource, "less than 102 .bin files found")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(md, self.extractor_info['name']) and not self.overwrite:
self.log_skip(resource, "metadata indicates it was already processed")
return CheckMessage.ignore
if get_terraref_metadata(md):
return CheckMessage.download
else:
self.log_skip(resource, "no terraref metadata found")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
#if not is_latest_file(resource):
# return CheckMessage.ignore
# Adjust sensor path based on VNIR vs SWIR
if resource['dataset_info']['name'].find("SWIR") > -1:
sensor_fullname = 'swir_netcdf'
else:
sensor_fullname = 'vnir_netcdf'
if has_all_files(resource):
# Check if output already exists
timestamp = resource['dataset_info']['name'].split(" - ")[1]
outFilePath = self.sensors.get_sensor_path(timestamp,
sensor=sensor_fullname)
if os.path.exists(outFilePath) and not self.overwrite:
logging.getLogger(__name__).info(
'skipping dataset %s, output file already exists' %
resource['id'])
return CheckMessage.ignore
else:
# Check if we have necessary metadata, either as a .json file or attached to dataset
md = download_metadata(connector, host, secret_key,
resource['id'],
self.extractor_info['name'])
if get_extractor_metadata(
md,
self.extractor_info['name']) and not self.overwrite:
logging.getLogger(__name__).info(
"skipping dataset %s, already processed" %
resource['id'])
return CheckMessage.ignore
elif get_terraref_metadata(md):
return CheckMessage.download
else:
for f in resource['files']:
if f['filename'] == 'metadata.json':
return CheckMessage.download
return CheckMessage.ignore
else:
logging.getLogger(__name__).info(
'skipping dataset %s, not all input files are ready' %
resource['id'])
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
self.start_check(resource)
if resource['name'].startswith('rgb_fullfield') > -1 and resource[
'name'].endswith('_mask.tif'):
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(
md, self.extractor_info['name'],
self.extractor_info['version']) and not self.overwrite:
self.log_skip(resource,
"metadata indicates it was already processed")
return CheckMessage.ignore
return CheckMessage.download
else:
self.log_skip(resource,
"expected filename mismatch: %s" % resource['name'])
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if resource['name'].endswith('_left.tif') or resource['name'].endswith(
'_right.tif'):
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_extractor_metadata(
md, self.extractor_info['name']) and not self.overwrite:
self.log_skip(resource,
"metadata indicates it was already processed")
return CheckMessage.ignore
return CheckMessage.download
else:
self.log_skip(resource, "not left/right geotiff")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check for a left and right BIN file - skip if not found
if not contains_required_files(resource, ['_left.tif', '_right.tif']):
self.log_skip(resource, "missing required files")
# Check for raw_data_source in metadata and resumbit to bin2tif if available...
md = download_metadata(connector, host, secret_key, resource['id'])
terra_md = get_terraref_metadata(md)
if 'raw_data_source' in terra_md:
raw_id = str(terra_md['raw_data_source'].split("/")[-1])
self.log_info(resource, "submitting raw source %s to bin2tif" % raw_id)
submit_extraction(connector, host, secret_key, raw_id, "terra.stereo-rgb.bin2tif")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
if get_extractor_metadata(md, self.extractor_info['name'], self.extractor_info['version']):
# Make sure outputs properly exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
left_nrmac_tiff = self.sensors.create_sensor_path(timestamp, opts=['left'])
right_nrmac_tiff = self.sensors.create_sensor_path(timestamp, opts=['right'])
if (self.leftonly and file_exists(left_nrmac_tiff)) or (
not self.leftonly and file_exists(left_nrmac_tiff) and file_exists(right_nrmac_tiff)):
if contains_required_files(resource, [os.path.basename(left_nrmac_tiff)]):
self.log_skip(resource, "metadata v%s and outputs already exist" % self.extractor_info['version'])
return CheckMessage.ignore
else:
self.log_info(resource, "output file exists but not yet uploaded")
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
else:
self.log_skip(resource, "no terraref metadata found")
return CheckMessage.ignore
def check_message(self, connector, host, secret_key, resource, parameters):
if "rulechecked" in parameters and parameters["rulechecked"]:
return CheckMessage.download
self.start_check(resource)
if not is_latest_file(resource):
self.log_skip(resource, "not latest file")
return CheckMessage.ignore
# Check metadata to verify we have what we need
md = download_metadata(connector, host, secret_key, resource['id'])
if get_terraref_metadata(md):
# Check for a left and right TIF file - skip if not found
# If we're only processing the left files, don't check for the right file
needed_files = ['_left.tif']
if not self.leftonly:
needed_files.append('_right.tif')
if not contains_required_files(resource, needed_files):
self.log_skip(resource, "missing required files")
return CheckMessage.ignore
if get_extractor_metadata(md, self.extractor_info['name'],
self.extractor_info['version']):
# Make sure outputs properly exist
timestamp = resource['dataset_info']['name'].split(" - ")[1]
left_mask_tiff = self.sensors.create_sensor_path(timestamp, opts=['left'])
right_mask_tiff = self.sensors.create_sensor_path(timestamp, opts=['right'])
if (self.leftonly and file_exists(left_mask_tiff)) or \
(not (file_exists(left_mask_tiff) and file_exists(right_mask_tiff))):
self.log_skip(resource, "metadata v%s and outputs already exist" % \
self.extractor_info['version'])
return CheckMessage.ignore
# Check for other images to create a mask on
elif not contains_required_files(resource, ['.tif']):
self.log_skip(resource, "missing required tiff file")
return CheckMessage.ignore
# Have TERRA-REF metadata, but not any from this extractor
return CheckMessage.download
def check_message(self, connector, host, secret_key, resource, parameters):
if resource['type'] != "dataset":
if 'name' not in resource:
resource['name'] = resource["type"]
self.log_skip(resource,
"position is only logged for dataset metadata")
return CheckMessage.ignore
self.start_check(resource)
if 'spatial_metadata' in resource['metadata']:
ds_md = download_metadata(connector, host, secret_key,
resource['id'])
ext_md = get_extractor_metadata(ds_md, self.extractor_info['name'])
if not ext_md:
return CheckMessage.bypass
else:
self.log_skip(resource,
"sensorposition metadata already exists")
return CheckMessage.ignore
else:
self.log_skip(resource,
"newly added metadata is not from LemnaTec")
return CheckMessage.ignore
def process_message(self, connector, host, secret_key, resource, parameters):
self.start_message(resource)
# Get left/right files and metadata
img_left, img_right, terra_md_full = None, None, None
for fname in resource['local_paths']:
if fname.endswith('_dataset_metadata.json'):
all_dsmd = load_json_file(fname)
terra_md_full = get_terraref_metadata(all_dsmd, 'stereoTop')
elif fname.endswith('_left.bin'):
img_left = fname
elif fname.endswith('_right.bin'):
img_right = fname
if None in [img_left, img_right, terra_md_full]:
raise ValueError("could not locate all files & metadata in processing")
timestamp = resource['dataset_info']['name'].split(" - ")[1]
# Fetch experiment name from terra metadata
season_name, experiment_name, updated_experiment = get_season_and_experiment(timestamp, 'stereoTop', terra_md_full)
if None in [season_name, experiment_name]:
raise ValueError("season and experiment could not be determined")
# Determine output directory
self.log_info(resource, "Hierarchy: %s / %s / %s / %s / %s / %s / %s" % (season_name, experiment_name, self.sensors.get_display_name(),
timestamp[:4], timestamp[5:7], timestamp[8:10], timestamp))
target_dsid = build_dataset_hierarchy_crawl(host, secret_key, self.clowder_user, self.clowder_pass, self.clowderspace,
season_name, experiment_name, self.sensors.get_display_name(),
timestamp[:4], timestamp[5:7], timestamp[8:10],
leaf_ds_name=self.sensors.get_display_name() + ' - ' + timestamp)
left_tiff = self.sensors.create_sensor_path(timestamp, opts=['left'])
right_tiff = self.sensors.create_sensor_path(timestamp, opts=['right'])
uploaded_file_ids = []
# Attach LemnaTec source metadata to Level_1 product if necessary
target_md = download_metadata(connector, host, secret_key, target_dsid)
if not get_extractor_metadata(target_md, self.extractor_info['name']):
self.log_info(resource, "uploading LemnaTec metadata to ds [%s]" % target_dsid)
remove_metadata(connector, host, secret_key, target_dsid, self.extractor_info['name'])
terra_md_trim = get_terraref_metadata(all_dsmd)
if updated_experiment is not None:
terra_md_trim['experiment_metadata'] = updated_experiment
terra_md_trim['raw_data_source'] = host + ("" if host.endswith("/") else "/") + "datasets/" + resource['id']
level1_md = build_metadata(host, self.extractor_info, target_dsid, terra_md_trim, 'dataset')
upload_metadata(connector, host, secret_key, target_dsid, level1_md)
try:
left_shape = terraref.stereo_rgb.get_image_shape(terra_md_full, 'left')
gps_bounds_left = geojson_to_tuples(terra_md_full['spatial_metadata']['left']['bounding_box'])
right_shape = terraref.stereo_rgb.get_image_shape(terra_md_full, 'right')
gps_bounds_right = geojson_to_tuples(terra_md_full['spatial_metadata']['right']['bounding_box'])
except KeyError:
self.log_error(resource, "spatial metadata not properly identified; sending to cleaner")
submit_extraction(connector, host, secret_key, resource['id'], "terra.metadata.cleaner")
return
if (not file_exists(left_tiff)) or self.overwrite:
# Perform actual processing
self.log_info(resource, "creating %s" % left_tiff)
left_image = terraref.stereo_rgb.process_raw(left_shape, img_left, None)
create_geotiff(left_image, gps_bounds_left, left_tiff, None, True,
self.extractor_info, terra_md_full, compress=True)
self.created += 1
self.bytes += os.path.getsize(left_tiff)
# Check if the file should be uploaded, even if it was already created
found_in_dest = check_file_in_dataset(connector, host, secret_key, target_dsid, left_tiff)
if not found_in_dest:
self.log_info(resource, "uploading %s" % left_tiff)
fileid = upload_to_dataset(connector, host, self.clowder_user, self.clowder_pass, target_dsid, left_tiff)
uploaded_file_ids.append(host + ("" if host.endswith("/") else "/") + "files/" + fileid)
if (not file_exists(right_tiff)) or self.overwrite:
# Perform actual processing
self.log_info(resource, "creating %s" % right_tiff)
right_image = terraref.stereo_rgb.process_raw(right_shape, img_right, None)
create_geotiff(right_image, gps_bounds_right, right_tiff, None, True,
self.extractor_info, terra_md_full, compress=True)
self.created += 1
self.bytes += os.path.getsize(right_tiff)
# Check if the file should be uploaded, even if it was already created
found_in_dest = check_file_in_dataset(connector, host, secret_key, target_dsid, right_tiff)
if not found_in_dest:
self.log_info(resource, "uploading %s" % right_tiff)
fileid = upload_to_dataset(connector, host, self.clowder_user, self.clowder_pass, target_dsid, right_tiff)
uploaded_file_ids.append(host + ("" if host.endswith("/") else "/") + "files/" + fileid)
# Trigger additional extractors
self.log_info(resource, "triggering downstream extractors")
submit_extraction(connector, host, secret_key, target_dsid, "terra.stereo-rgb.rgbmask")
submit_extraction(connector, host, secret_key, target_dsid, "terra.stereo-rgb.nrmac")
submit_extraction(connector, host, secret_key, target_dsid, "terra.plotclipper_tif")
# Tell Clowder this is completed so subsequent file updates don't daisy-chain
if len(uploaded_file_ids) > 0:
extractor_md = build_metadata(host, self.extractor_info, target_dsid, {
"files_created": uploaded_file_ids
}, 'dataset')
self.log_info(resource, "uploading extractor metadata to raw dataset")
remove_metadata(connector, host, secret_key, resource['id'], self.extractor_info['name'])
try:
upload_metadata(connector, host, secret_key, resource['id'], extractor_md)
except:
self.log_info(resource, "problem uploading extractor metadata...")
self.end_message(resource)
