def get_doc_prov(j, gcis_url, refList):
"""Generate PROV-ES JSON from GCIS doc metadata."""
doc = ProvEsDocument()
name = " ".join(j[i]
for i in ('first_name', 'middle_name', 'last_name')
if j.get(i, None) is not None)
doc_attrs =[("prov:type", 'gcis:Person'),
("prov:label", name),#j['first_name']),
("prov:location", "%s%s"%(gcis_url,j['uri'])),
("gcis:id", j['id']),
("gcis:orcid", j["orcid"]),
#("prov:wasAttributedTo, contributors),
]
doc.agent('bibo:%s' % j['id'], doc_attrs)
del_id = GCIS["%s"%get_uuid("%s:%s:%s"%(j['id'], None, None))]
doc.delegation('bibo:%s'%j['id'], None, None, del_id, None)
#for org_id in agent_ids[agent_id]:
# del_id = GCIS["%s"%get_uuid("%s:%s:%s"%(agent_id, org_id, act_id))]
#doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type':'gcis:worksAt'})
prov_json = json.loads(doc.serialize())
return prov_json
def fix_hadMember_ids(prov_es_json):
"""Fix the id's of hadMember relationships."""
hm_ids = prov_es_json.get('hadMember', {}).keys()
for id in hm_ids:
hm = copy.deepcopy(prov_es_json['hadMember'][id])
new_id = "hysds:%s" % get_uuid("%s:%s" % (hm['prov:collection'], hm['prov:entity']))
prov_es_json['hadMember'][new_id] = hm
del prov_es_json['hadMember'][id]
def fix_hadMember_ids(prov_es_json):
"""Fix the id's of hadMember relationships."""
hm_ids = prov_es_json.get('hadMember', {}).keys()
for id in hm_ids:
hm = copy.deepcopy(prov_es_json['hadMember'][id])
new_id = "hysds:%s" % get_uuid(
"%s:%s" % (hm['prov:collection'], hm['prov:entity']))
prov_es_json['hadMember'][new_id] = hm
del prov_es_json['hadMember'][id]
def log_publish_prov_es(prov_es_info, prov_es_file, prod_path, pub_urls,
prod_metrics, objectid):
"""Log publish step in PROV-ES document."""
# create PROV-ES doc
doc = ProvEsDocument(namespaces=prov_es_info['prefix'])
# get bundle
#bndl = doc.bundle(bundle_id)
bndl = None
# add input entity
execute_node = socket.getfqdn()
prod_url = "file://%s%s" % (execute_node, prod_path)
input_id = "hysds:%s" % get_uuid(prod_url)
input_ent = doc.granule(input_id,
None, [prod_url], [],
None,
None,
None,
label=os.path.basename(prod_url),
bundle=bndl)
# add output entity
output_id = "hysds:%s" % get_uuid(pub_urls[0])
output_ent = doc.product(output_id,
None, [pub_urls[0]], [],
None,
None,
None,
label=objectid,
bundle=bndl)
# software and algorithm
algorithm = "eos:product_publishing"
software_version = hysds.__version__
software_title = "%s v%s" % (hysds.__description__, software_version)
software = "eos:HySDS-%s" % software_version
software_location = hysds.__url__
doc.software(software, [algorithm],
software_version,
label=software_title,
location=software_location,
bundle=bndl)
# create sofware agent
pid = os.getpid()
sa_label = "hysds:publish_dataset/%s/%d/%s" % (execute_node, pid,
prod_metrics['time_start'])
sa_id = "hysds:%s" % get_uuid(sa_label)
doc.softwareAgent(sa_id,
str(pid),
execute_node,
role="invoked",
label=sa_label,
bundle=bndl)
# create processStep
job_id = "publish_dataset-%s" % os.path.basename(prod_path)
doc.processStep("hysds:%s" % get_uuid(job_id),
prod_metrics['time_start'],
prod_metrics['time_end'], [software],
sa_id,
None, [input_id], [output_id],
label=job_id,
bundle=bndl,
prov_type="hysds:publish_dataset")
# get json
pd = json.loads(doc.serialize())
# update input entity
orig_ent = prov_es_info.get('entity', {}).get(input_id, {})
pd['entity'][input_id].update(orig_ent)
# update output entity
for attr in orig_ent:
if attr in ('prov:location', 'prov:label', 'prov:type'):
continue
pd['entity'][output_id][attr] = orig_ent[attr]
# write prov
with open(prov_es_file, 'w') as f:
json.dump(pd, f, indent=2)
def log_prov_es(job, prov_es_info, prov_es_file):
"""Log PROV-ES document. Create temp PROV-ES document to populate
attributes that only the worker has access to (e.g. PID)."""
# create PROV-ES doc to generate attributes that only verdi know
ps_id = "hysds:%s" % get_uuid(job['job_id'])
bundle_id = "hysds:%s" % get_uuid('bundle-%s' % job['job_id'])
doc = ProvEsDocument()
# get bundle
#bndl = doc.bundle(bundle_id)
bndl = None
# create sofware agent
sa_label = "hysds:pge_wrapper/%s/%d/%s" % (job['job_info']['execute_node'],
job['job_info']['pid'],
datetime.utcnow().isoformat())
sa_id = "hysds:%s" % get_uuid(sa_label)
doc.softwareAgent(sa_id,
str(job['job_info']['pid']),
job['job_info']['execute_node'],
role=job.get('username', None),
label=sa_label,
bundle=bndl)
# create processStep
doc.processStep(ps_id,
job['job_info']['cmd_start'],
job['job_info']['cmd_end'], [],
sa_id,
None, [], [],
bundle=bndl,
prov_type="hysds:%s" % job['type'])
# get json
pd = json.loads(doc.serialize())
# update software agent and process step
if 'bundle' in prov_es_info:
if len(prov_es_info['bundle']) == 1:
bundle_id_orig = list(prov_es_info['bundle'].keys())[0]
# update software agent
prov_es_info['bundle'][bundle_id_orig].setdefault(
'agent', {}).update(pd['bundle'][bundle_id]['agent'])
# update wasAssociatedWith
prov_es_info['bundle'][bundle_id_orig].setdefault(
'wasAssociatedWith',
{}).update(pd['bundle'][bundle_id]['wasAssociatedWith'])
# update activity
if 'activity' in prov_es_info['bundle'][bundle_id_orig]:
if len(prov_es_info['bundle'][bundle_id_orig]
['activity']) == 1:
ps_id_orig = list(prov_es_info['bundle'][bundle_id_orig]
['activity'].keys())[0]
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['prov:startTime'] = pd['bundle'][
bundle_id]['activity'][ps_id]['prov:startTime']
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['prov:endTime'] = pd['bundle'][bundle_id][
'activity'][ps_id]['prov:endTime']
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['hysds:job_id'] = job['job_id']
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['hysds:job_type'] = job['type']
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['hysds:job_url'] = job['job_info'][
'job_url']
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['hysds:mozart_url'] = app.conf.MOZART_URL
if 'prov:type' not in prov_es_info['bundle'][
bundle_id_orig]['activity'][ps_id_orig]:
prov_es_info['bundle'][bundle_id_orig]['activity'][
ps_id_orig]['prov:type'] = pd['bundle'][bundle_id][
'activity'][ps_id]['prov:type']
# update wasAssociatedWith activity ids
for waw_id in prov_es_info['bundle'][bundle_id_orig][
'wasAssociatedWith']:
if prov_es_info['bundle'][bundle_id_orig][
'wasAssociatedWith'][waw_id][
'prov:activity'] == ps_id:
prov_es_info['bundle'][bundle_id_orig][
'wasAssociatedWith'][waw_id][
'prov:activity'] = ps_id_orig
else:
prov_es_info['bundle'][bundle_id_orig]['activity'].update(
pd['bundle'][bundle_id]['activity'])
else:
prov_es_info['bundle'][bundle_id_orig]['activity'] = pd[
'bundle'][bundle_id]['activity']
else:
# update software agent
prov_es_info.setdefault('agent', {}).update(pd['agent'])
# update wasAssociatedWith
prov_es_info.setdefault('wasAssociatedWith',
{}).update(pd['wasAssociatedWith'])
# update process step
if 'activity' in prov_es_info:
if len(prov_es_info['activity']) == 1:
ps_id_orig = list(prov_es_info['activity'].keys())[0]
prov_es_info['activity'][ps_id_orig]['prov:startTime'] = pd[
'activity'][ps_id]['prov:startTime']
prov_es_info['activity'][ps_id_orig]['prov:endTime'] = pd[
'activity'][ps_id]['prov:endTime']
prov_es_info['activity'][ps_id_orig]['hysds:job_id'] = job[
'job_id']
prov_es_info['activity'][ps_id_orig]['hysds:job_type'] = job[
'type']
prov_es_info['activity'][ps_id_orig]['hysds:job_url'] = job[
'job_info']['job_url']
prov_es_info['activity'][ps_id_orig][
'hysds:mozart_url'] = app.conf.MOZART_URL
if 'prov:type' not in prov_es_info['activity'][ps_id_orig]:
prov_es_info['activity'][ps_id_orig]['prov:type'] = pd[
'activity'][ps_id]['prov:type']
# update wasAssociatedWith activity ids
for waw_id in prov_es_info['wasAssociatedWith']:
if prov_es_info['wasAssociatedWith'][waw_id][
'prov:activity'] == ps_id:
prov_es_info['wasAssociatedWith'][waw_id][
'prov:activity'] = ps_id_orig
else:
prov_es_info['activity'].update(pd['activity'])
else:
prov_es_info['activity'] = pd['activity']
# write prov
with open(prov_es_file, 'w') as f:
json.dump(prov_es_info, f, indent=2)
def create_prov_es_json(id, url, prod_dir, prov_file):
"""Create provenance JSON file."""
# get info
csk_files = glob(os.path.join(prod_dir, "CSKS*"))
pf = "CSKS?"
dtype = "NA"
repo_dir = "?"
if len(csk_files) > 0:
match = CSK_RE.search(os.path.basename(csk_files[0]))
if match: pf, dtype = match.groups()
if dtype == "RAW":
dtype = "RAW_B"
repo_dir = "csk_rawb"
elif dtype == "SCS":
dtype = "SCS_B"
repo_dir = "csk_scsb"
platform = "eos:%s" % pf
platform_title = "COSMO-SkyMed Satellite %s" % pf[-1]
instrument = "eos:%s-SAR" % pf
instrument_title = "%s-SAR" % pf
level = "L0"
version = "v1.0"
collection = "eos:CSK-%s-%s" % (dtype, version)
collection_shortname = "CSK-%s-%s" % (dtype, version)
collection_label = "CSK %s Scenes %s" % (dtype, version)
collection_loc = "https://aria-dav.jpl.nasa.gov/repository/products/%s/%s" % (
repo_dir, version)
sensor = "eos:SAR"
sensor_title = "Synthetic-aperture radar (SAR)"
gov_org = "eos:ASI"
gov_org_title = "Agenzia Spaziale Italiana"
software_version = "2.0.0_201604"
software_title = "InSAR SCE (InSAR Scientific Computing Environment) v%s" % software_version
software = "eos:ISCE-%s" % software_version
software_location = "https://winsar.unavco.org/isce.html"
algorithm = "eos:metadata_extraction"
prod_dir = "file://%s%s" % (socket.getfqdn(), prod_dir)
# put in fake start/end times so that prov:used and prov:generated
# are properly created by the prov lib
fake_time = datetime.utcnow().isoformat() + 'Z'
job_id = "ingest-%s-%s" % (id, fake_time)
bundle_id = "bundle-ingest-%s-%s" % (id, fake_time)
doc = ProvEsDocument()
#bndl = doc.bundle("hysds:%s" % get_uuid(bundle_id))
bndl = None
input_id = "hysds:%s" % get_uuid(url)
input_ds = doc.granule(input_id,
None, [url], [instrument],
None,
level,
None,
label=os.path.basename(url),
bundle=bndl)
doc.collection(collection,
None,
collection_shortname,
collection_label, [collection_loc], [instrument],
level,
version,
label=collection_label,
bundle=bndl)
output_id = "hysds:%s" % get_uuid(prod_dir)
output_ds = doc.granule(output_id,
None, [prod_dir], [instrument],
collection,
level,
version,
label=id,
bundle=bndl)
doc.governingOrganization(gov_org, label=gov_org_title, bundle=bndl)
doc.platform(platform, [instrument], label=platform_title, bundle=bndl)
doc.instrument(instrument,
platform, [sensor], [gov_org],
label=instrument_title,
bundle=bndl)
doc.sensor(sensor, instrument, label=sensor_title, bundle=bndl)
doc.software(software, [algorithm],
software_version,
label=software_title,
location=software_location,
bundle=bndl)
doc.processStep("hysds:%s" % get_uuid(job_id),
fake_time,
fake_time, [software],
None,
None, [input_ds.identifier], [output_ds.identifier],
label=job_id,
bundle=bndl,
prov_type="hysds:ingest")
with open(prov_file, 'w') as f:
json.dump(json.loads(doc.serialize()), f, indent=2, sort_keys=True)
def get_doc_prov(j, gcis_url):
"""Generate PROV-ES JSON from GCIS doc metadata."""
# create doc
gcis_ns = "http://data.globalchange.gov/gcis.owl#"
doc = ProvEsDocument(namespaces={
"gcis": gcis_ns,
"bibo": "http://purl.org/ontology/bibo/"
})
bndl = None
# create journal
r = requests.get("%s/journal/%s.json" %
(gcis_url, j['journal_identifier']),
params={'all': 1},
verify=False)
r.raise_for_status()
journal_md = r.json()
doc_attrs = [
("prov:type", 'gcis:Journal'),
("prov:label", j['title']),
]
journal_id = GCIS[j['journal_identifier']]
if journal_id not in journal_ids:
if journal_md.get('url', None) is not None:
doc_attrs.append(("prov:location", journal_md['url']))
if journal_md.get('online_issn', None) is not None:
doc_attrs.append(("gcis:online_issn", journal_md['online_issn']))
if journal_md.get('print_issn', None) is not None:
doc_attrs.append(("gcis:print_issn", journal_md['print_issn']))
doc.entity(journal_id, doc_attrs)
journal_ids[journal_id] = True
# create agents or organizations
agent_ids = {}
org_ids = {}
for cont in j.get('contributors', []):
# replace slashes because we get prov.model.ProvExceptionInvalidQualifiedName errors
agent_id = GCIS["%s" % cont['uri'][1:].replace('/', '-')]
# create person
if len(cont['person']) > 0:
# agent
agent_name = " ".join([
cont['person'][i]
for i in ('first_name', 'middle_name', 'last_name')
if cont['person'].get(i, None) is not None
])
doc.agent(agent_id, [
(PROV_TYPE, GCIS["Person"]),
(PROV_LABEL, agent_name),
(PROV_LOCATION, "%s%s" % (gcis_url, cont['uri'])),
])
agent_ids[agent_id] = []
# organization
if cont['organization'] is not None and len(cont['organization']) > 0:
org = cont['organization']
org_id = GCIS["%s" % cont['organization']['identifier']]
if org_id not in org_ids:
doc.governingOrganization(org_id, cont['organization']['name'])
org_ids[org_id] = True
if agent_id in agent_ids: agent_ids[agent_id].append(org_id)
# create article
article_id = 'bibo:%s' % j['identifier']
doc_attrs = [
("prov:type", 'gcis:Article'),
("prov:label", j['title']),
("dcterms:isPartOf", journal_id),
]
if j.get('doi', "") == "":
doc_attrs.append(("bibo:doi", j['doi']))
doc.entity(article_id, doc_attrs)
# link
doc.hadMember(journal_id, article_id)
# create activity
if isinstance(j['year'], int):
start_time = str(j['year'])
end_time = str(j['year'])
else:
start_time = None
end_time = None
act_id = GCIS["generate-%s" % j['identifier'].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id,
{'prov:role': GCIS['Author']})
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s" % get_uuid("%s:%s:%s" %
(agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id,
{'prov:type': 'gcis:worksAt'})
for org_id in org_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id,
{'prov:role': GCIS['Contributor']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.wasGeneratedBy(article_id, act, end_time,
GCIS["%s" % get_uuid("%s:%s" % (article_id, act_id))])
# serialize
prov_json = json.loads(doc.serialize())
return prov_json
def create_prov_es_json(id, project, master_orbit_file, slave_orbit_file,
aria_dem_xml, aria_dem_file, work_dir, prov_file):
"""Create provenance JSON file."""
# get abs paths
work_dir = os.path.abspath(work_dir)
prod_dir = os.path.join(work_dir, id)
# get context
ctx_file = os.path.join(prod_dir, "%s.context.json" % id)
with open(ctx_file) as f:
context = json.load(f)
# put in fake start/end times so that prov:used and prov:generated
# are properly created by the prov lib
fake_time = datetime.utcnow().isoformat() + 'Z'
job_id = "create_interferogram-%s" % fake_time
bundle_id = "bundle-create_interferogram-%s" % fake_time
# create PROV-ES doc
doc = ProvEsDocument()
#bndl = doc.bundle("hysds:%s" % get_uuid(bundle_id))
bndl = None
# input and output identifiers
input_ids = {}
platform_ids = {}
instrument_ids = {}
# full url paths
work_url = "file://%s%s" % (socket.getfqdn(), work_dir)
prod_url = "%s/%s" % (work_url, id)
# add sentinel.ini file
ini_ent = doc.file("hysds:%s" % get_uuid("%s/sentinel.ini" % work_url),
["%s/sentinel.ini" % work_url],
label="sentinel.ini")
input_ids[ini_ent.identifier] = True
# add orbit files
master_orbit_ent = doc.file(
"hysds:%s" % get_uuid("%s/%s" % (work_url, master_orbit_file)),
["%s/%s" % (work_url, master_orbit_file)],
label=os.path.basename(master_orbit_file))
input_ids[master_orbit_ent.identifier] = True
slave_orbit_ent = doc.file(
"hysds:%s" % get_uuid("%s/%s" % (work_url, slave_orbit_file)),
["%s/%s" % (work_url, slave_orbit_file)],
label=os.path.basename(slave_orbit_file))
input_ids[slave_orbit_ent.identifier] = True
# get list of S1A urls
level = "L0"
version = "v1.0"
sensor = "eos:SAR"
sensor_title = "Synthetic-aperture radar (SAR)"
gov_org = "eos:ESA"
gov_org_title = "European Space Agency"
doc.governingOrganization(gov_org, label=gov_org_title, bundle=bndl)
instrument = ""
for i, url in enumerate(
[context.get('master_zip_url', ''),
context.get('slave_zip_url', '')]):
match = PLATFORM_RE.search(url)
if not match: continue
pf = match.group(1)
platform = "eos:%s" % pf
platform_title = "Sentinel1A Satellite"
instrument = "eos:%s-SAR" % pf
instrument_title = "%s-SAR" % pf
input_ds = doc.product("hysds:%s" % get_uuid(url),
None, [url], [instrument],
None,
level,
None,
label=os.path.basename(url),
bundle=bndl)
input_ids[input_ds.identifier] = True
if platform not in platform_ids:
doc.platform(platform, [instrument],
label=platform_title,
bundle=bndl)
platform_ids[platform] = True
if instrument not in instrument_ids:
doc.instrument(instrument,
platform, [sensor], [gov_org],
label=instrument_title,
bundle=bndl)
doc.sensor(sensor, instrument, label=sensor_title, bundle=bndl)
instrument_ids[instrument] = True
# add dem xml, file and related provenance
srtm_platform = "eos:SpaceShuttleEndeavour"
srtm_platform_title = "USS Endeavour"
srtm_instrument = "eos:SRTM"
srtm_instrument_title = "Shuttle Radar Topography Mission (SRTM)"
srtm_sensor = "eos:radar"
srtm_sensor_title = "radar"
srtm_gov_org = "eos:JPL"
srtm_gov_org_title = "Jet Propulsion Laboratory"
doc.governingOrganization(srtm_gov_org,
label=srtm_gov_org_title,
bundle=bndl)
dem_xml_ent = doc.file("hysds:%s" % get_uuid("%s/%s" %
(work_url, aria_dem_xml)),
["%s/%s" % (work_url, aria_dem_xml)],
label=os.path.basename(aria_dem_xml))
input_ids[dem_xml_ent.identifier] = True
dem_file_ent = doc.file("hysds:%s" % get_uuid("%s/%s" %
(work_url, aria_dem_file)),
["%s/%s" % (work_url, aria_dem_file)],
label=os.path.basename(aria_dem_file))
input_ids[dem_file_ent.identifier] = True
doc.platform(srtm_platform, [srtm_instrument],
label=srtm_platform_title,
bundle=bndl)
doc.instrument(srtm_instrument,
srtm_platform, [srtm_sensor], [srtm_gov_org],
label=srtm_instrument_title,
bundle=bndl)
doc.sensor(srtm_sensor,
srtm_instrument,
label=srtm_sensor_title,
bundle=bndl)
instrument_ids[srtm_instrument] = True
# software and algorithm
algorithm = "eos:interferogram_generation"
software_version = "2.0.0_201604"
software_title = "InSAR SCE (InSAR Scientific Computing Environment) v%s" % software_version
software = "eos:ISCE-%s" % software_version
software_location = "https://winsar.unavco.org/isce.html"
doc.software(software, [algorithm],
software_version,
label=software_title,
location=software_location,
bundle=bndl)
# output
int_level = "L2"
int_version = "v1.0"
int_collection = "eos:S1A-interferograms-%s" % int_version
int_collection_shortname = "S1A-interferograms-%s" % int_version
int_collection_label = "ISCE generated S1A interferograms %s" % int_version
int_collection_loc = "https://aria-dst-dav.jpl.nasa.gov/products/s1a_ifg/%s" % int_version
doc.collection(int_collection,
None,
int_collection_shortname,
int_collection_label, [int_collection_loc],
instrument_ids.keys(),
int_level,
int_version,
label=int_collection_label,
bundle=bndl)
output_ds = doc.granule("hysds:%s" % get_uuid(prod_url),
None, [prod_url],
instrument_ids.keys(),
int_collection,
int_level,
int_version,
label=id,
bundle=bndl)
# runtime context
rt_ctx_id = "hysds:runtimeContext-sentinel_ifg-%s" % project
doc.runtimeContext(rt_ctx_id, [project], label=project, bundle=bndl)
# create process
doc.processStep("hysds:%s" % get_uuid(job_id),
fake_time,
fake_time, [software],
None,
rt_ctx_id,
input_ids.keys(), [output_ds.identifier],
label=job_id,
bundle=bndl,
prov_type="hysds:create_interferogram")
# write
with open(prov_file, 'w') as f:
json.dump(json.loads(doc.serialize()), f, indent=2, sort_keys=True)
def get_doc_prov(j, gcis_url):
"""Generate PROV-ES JSON from GCIS doc metadata."""
# create doc
gcis_ns = "http://data.globalchange.gov/gcis.owl#"
doc = ProvEsDocument(namespaces={ "gcis": gcis_ns, "bibo": "http://purl.org/ontology/bibo/" })
bndl = None
# create journal
r = requests.get("%s/journal/%s.json" % (gcis_url, j['journal_identifier']), params={ 'all': 1 }, verify=False)
r.raise_for_status()
journal_md = r.json()
doc_attrs = [
( "prov:type", 'gcis:Journal' ),
( "prov:label", j['title'] ),
]
journal_id = GCIS[j['journal_identifier']]
if journal_id not in journal_ids:
if journal_md.get('url', None) is not None:
doc_attrs.append( ("prov:location", journal_md['url'] ) )
if journal_md.get('online_issn', None) is not None:
doc_attrs.append( ("gcis:online_issn", journal_md['online_issn'] ) )
if journal_md.get('print_issn', None) is not None:
doc_attrs.append( ("gcis:print_issn", journal_md['print_issn'] ) )
doc.entity(journal_id, doc_attrs)
journal_ids[journal_id] = True
# create agents or organizations
agent_ids = {}
org_ids = {}
for cont in j.get('contributors', []):
# replace slashes because we get prov.model.ProvExceptionInvalidQualifiedName errors
agent_id = GCIS["%s" % cont['uri'][1:].replace('/', '-')]
# create person
if len(cont['person']) > 0:
# agent
agent_name = " ".join([cont['person'][i] for i in
('first_name', 'middle_name', 'last_name')
if cont['person'].get(i, None) is not None])
doc.agent(agent_id, [
( PROV_TYPE, GCIS["Person"] ),
( PROV_LABEL, agent_name ),
( PROV_LOCATION, "%s%s" % (gcis_url, cont['uri']) ),
])
agent_ids[agent_id] = []
# organization
if cont['organization'] is not None and len(cont['organization']) > 0:
org = cont['organization']
org_id = GCIS["%s" % cont['organization']['identifier']]
if org_id not in org_ids:
doc.governingOrganization(org_id, cont['organization']['name'])
org_ids[org_id] = True
if agent_id in agent_ids: agent_ids[agent_id].append(org_id)
# create article
article_id = 'bibo:%s' % j['identifier']
doc_attrs = [
( "prov:type", 'gcis:Article' ),
( "prov:label", j['title'] ),
( "dcterms:isPartOf", journal_id ),
]
if j.get('doi', "") == "":
doc_attrs.append( ("bibo:doi", j['doi'] ) )
doc.entity(article_id, doc_attrs)
# link
doc.hadMember(journal_id, article_id)
# create activity
if isinstance(j['year'], int):
start_time = str(j['year'])
end_time = str(j['year'])
else:
start_time = None
end_time = None
act_id = GCIS["generate-%s" % j['identifier'].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id, {'prov:role': GCIS['Author']})
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s" % get_uuid("%s:%s:%s" % (agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type': 'gcis:worksAt'})
for org_id in org_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id, {'prov:role': GCIS['Contributor']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.wasGeneratedBy(article_id, act, end_time, GCIS["%s" % get_uuid("%s:%s" % (article_id, act_id))])
# serialize
prov_json = json.loads(doc.serialize())
return prov_json
def log_prov_es(job, prov_es_info, prov_es_file):
"""Log PROV-ES document. Create temp PROV-ES document to populate
attributes that only the worker has access to (e.g. PID)."""
# create PROV-ES doc to generate attributes that only verdi know
ps_id = "hysds:%s" % get_uuid(job["job_id"])
bundle_id = "hysds:%s" % get_uuid("bundle-%s" % job["job_id"])
doc = ProvEsDocument()
# get bundle
# bndl = doc.bundle(bundle_id)
bndl = None
# create sofware agent
sa_label = "hysds:pge_wrapper/%s/%d/%s" % (
job["job_info"]["execute_node"],
job["job_info"]["pid"],
datetime.utcnow().isoformat(),
)
sa_id = "hysds:%s" % get_uuid(sa_label)
doc.softwareAgent(
sa_id,
str(job["job_info"]["pid"]),
job["job_info"]["execute_node"],
role=job.get("username", None),
label=sa_label,
bundle=bndl,
)
# create processStep
doc.processStep(
ps_id,
job["job_info"]["cmd_start"],
job["job_info"]["cmd_end"],
[],
sa_id,
None,
[],
[],
bundle=bndl,
prov_type="hysds:%s" % job["type"],
)
# get json
pd = json.loads(doc.serialize())
# update software agent and process step
if "bundle" in prov_es_info:
if len(prov_es_info["bundle"]) == 1:
bundle_id_orig = list(prov_es_info["bundle"].keys())[0]
# update software agent
prov_es_info["bundle"][bundle_id_orig].setdefault(
"agent", {}).update(pd["bundle"][bundle_id]["agent"])
# update wasAssociatedWith
prov_es_info["bundle"][bundle_id_orig].setdefault(
"wasAssociatedWith",
{}).update(pd["bundle"][bundle_id]["wasAssociatedWith"])
# update activity
if "activity" in prov_es_info["bundle"][bundle_id_orig]:
if len(prov_es_info["bundle"][bundle_id_orig]
["activity"]) == 1:
ps_id_orig = list(prov_es_info["bundle"][bundle_id_orig]
["activity"].keys())[0]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["prov:startTime"] = pd["bundle"][
bundle_id]["activity"][ps_id]["prov:startTime"]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["prov:endTime"] = pd["bundle"][bundle_id][
"activity"][ps_id]["prov:endTime"]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["hysds:job_id"] = job["job_id"]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["hysds:job_type"] = job["type"]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["hysds:job_url"] = job["job_info"][
"job_url"]
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["hysds:mozart_url"] = app.conf.MOZART_URL
if ("prov:type" not in prov_es_info["bundle"]
[bundle_id_orig]["activity"][ps_id_orig]):
prov_es_info["bundle"][bundle_id_orig]["activity"][
ps_id_orig]["prov:type"] = pd["bundle"][bundle_id][
"activity"][ps_id]["prov:type"]
# update wasAssociatedWith activity ids
for waw_id in prov_es_info["bundle"][bundle_id_orig][
"wasAssociatedWith"]:
if (prov_es_info["bundle"][bundle_id_orig]
["wasAssociatedWith"][waw_id]["prov:activity"] ==
ps_id):
prov_es_info["bundle"][bundle_id_orig][
"wasAssociatedWith"][waw_id][
"prov:activity"] = ps_id_orig
else:
prov_es_info["bundle"][bundle_id_orig]["activity"].update(
pd["bundle"][bundle_id]["activity"])
else:
prov_es_info["bundle"][bundle_id_orig]["activity"] = pd[
"bundle"][bundle_id]["activity"]
else:
# update software agent
prov_es_info.setdefault("agent", {}).update(pd["agent"])
# update wasAssociatedWith
prov_es_info.setdefault("wasAssociatedWith",
{}).update(pd["wasAssociatedWith"])
# update process step
if "activity" in prov_es_info:
if len(prov_es_info["activity"]) == 1:
ps_id_orig = list(prov_es_info["activity"].keys())[0]
prov_es_info["activity"][ps_id_orig]["prov:startTime"] = pd[
"activity"][ps_id]["prov:startTime"]
prov_es_info["activity"][ps_id_orig]["prov:endTime"] = pd[
"activity"][ps_id]["prov:endTime"]
prov_es_info["activity"][ps_id_orig]["hysds:job_id"] = job[
"job_id"]
prov_es_info["activity"][ps_id_orig]["hysds:job_type"] = job[
"type"]
prov_es_info["activity"][ps_id_orig]["hysds:job_url"] = job[
"job_info"]["job_url"]
prov_es_info["activity"][ps_id_orig][
"hysds:mozart_url"] = app.conf.MOZART_URL
if "prov:type" not in prov_es_info["activity"][ps_id_orig]:
prov_es_info["activity"][ps_id_orig]["prov:type"] = pd[
"activity"][ps_id]["prov:type"]
# update wasAssociatedWith activity ids
for waw_id in prov_es_info["wasAssociatedWith"]:
if (prov_es_info["wasAssociatedWith"][waw_id]
["prov:activity"] == ps_id):
prov_es_info["wasAssociatedWith"][waw_id][
"prov:activity"] = ps_id_orig
else:
prov_es_info["activity"].update(pd["activity"])
else:
prov_es_info["activity"] = pd["activity"]
# write prov
with open(prov_es_file, "w") as f:
json.dump(prov_es_info, f, indent=2)
def get_doc_prov(j, gcis_url, refList, personList, reportList, webpageList):#organizationList, activityList):
"""Generate PROV-ES JSON from GCIS doc metadata."""
gcis_ns = "http://data.globalchange.gov/gcis.owl#"
doc = ProvEsDocument()
dataset = requests.get(j['href']).json()
datasetID = 'bibo:%s' % j['identifier']
doc_attrs = [
("prov:type", 'gcis:Dataset'),
("prov:label", j['name']),
("prov:location", "%s%s"%(gcis_url, j['uri'])),
]
doc.entity('bibo:%s' % j['identifier'], doc_attrs)
agent_ids = {}
org_ids = {}
#contributors
if 'contributors' in dataset:
for contributor in dataset['contributors']:
personID = None
if contributor['person_uri'] is not None:
name = " ".join([contributor['person'][i]
for i in ('first_name', 'middle_name', 'last_name')
if contributor['person'].get(i, None) is not None])
personAttrs = [
("prov:type", 'gcis:Person'),
("prov:label", "%s"%name),# %s"%(contributor['person']['first_name'],contributor['person']['last_name'])),
("prov:location", "%s%s"%(gcis_url,contributor['person_uri'])),
("gcis:id", str(contributor['person_id'])),
("gcis:orcid", contributor['person']['orcid'])
]
personID = 'bibo:%s'%contributor['person_id']
agent_ids[personID] = []
doc.agent(personID, personAttrs)
if contributor['organization'] is not None:
#make org
org_attrs = [
("prov:type", "gcis:organization"),
("prov:label", contributor["organization"]["name"]),
("prov:location", "%s%s"%(gcis_url, contributor["organization_uri"])),
("gcis:organization_type_identifier", contributor["organization"]["organization_type_identifier"]),
("gcis:country_code", contributor["organization"]["country_code"]),
]
orgID = 'bibo:%s'%contributor['organization']['identifier']
#doc.entity(orgID, org_attrs)
doc.governingOrganization(orgID, contributor['organization']['name'])
org_ids[orgID] = True
if personID in agent_ids:
agent_ids[personID].append(orgID)
#create actvity
if dataset['start_time'] is not None:
start_time = str(dataset['start_time'])
else:
start_time = ""
if dataset['end_time'] is not None:
end_time = str(dataset['end_time'])
else:
end_time = ""
act_id = GCIS["generate-%s"%j['identifier'].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id, {'prov:role':GCIS['Author']})
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s"%get_uuid("%s:%s:%s"%(agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type':'gcis:worksAt'})
for org_id in org_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id, {'prov:role':GCIS['Contributor']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.wasGeneratedBy(datasetID, act, end_time, GCIS["%s"%get_uuid("%s:%s"%(datasetID, act_id))])
#aliases
#instrument measurements
"""
role_ids = {}
agent_ids = {}
org_ids = {}
personID = None
#contributors
if 'contributors' in dataset:
for contributor in dataset['contributors']:
if contributor['person_uri'] is not None:
name = " ".join([contributor['person'][i]
for i in ('first_name', 'middle_name', 'last_name')
if contributor['person'].get(i, None) is not None])
personAttrs = [
("prov:type", 'gcis:Person'),
("prov:label", "%s"%name),# %s"%(contributor['person']['first_name'],contributor['person']['last_name'])),
("prov:location", "%s%s"%(gcis_url,contributor['person_uri'])),
("gcis:id", str(contributor['person_id'])),
("gcis:orcid", contributor['person']['orcid'])
]
personID = 'bibo:%s'%contributor['person_id']
role_ids[personID] = contributor['role_type_identifier']
doc.agent(personID, personAttrs)
agent_ids[personID] = []
#doc.wasAssociatedWith(datasetID, personID, None, None,{"prov:role": contributor['role_type_identifier']} )
if contributor['organization'] is not None:
org_attrs = [
("prov:type", "gcis:organization"),
("prov:label", contributor["organization"]["name"]),
("prov:location", "%s%s"%(gcis_url, contributor["organization_uri"])),
("gcis:organization_type_identifier", contributor["organization"]["organization_type_identifier"]),
("gcis:country_code", contributor["organization"]["country_code"]),
]
orgID = 'bibo:%s'%contributor['organization']['identifier']
doc.agent(orgID, org_attrs)
doc.governingOrganization(orgID, contributor['organization']['name'])
if personID in agent_ids:
agent_ids[personID].append(orgID)
if dataset['start_time'] is not None:
start_time = str(dataset['start_time'])
else:
start_time = ""
if dataset['end_time'] is not None:
end_time = str(dataset['end_time'])
else:
end_time = ""
# print j['identifier']
#else:
# start_time = None
# end_time = None
act_id = GCIS["generate-%s"%j['identifier'].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id, {'prov:role': GCIS[role_ids[agent_id]] })
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s"%get_uuid("%s:%s:%s"%(agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type':'gcis:worksAt'})
for org_id in org_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id, {'prov:role':GCIS['Contributor']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.wasGeneratedBy(datasetID, act, end_time, GCIS["%s"%get_uuid("%s:%s"%(datasetID, act_id))])
"""
#cited by
if 'cited_by' in dataset:
for citation in dataset['cited_by']:
if 'publication' in citation:
#pub_uri = "%s%s"%(gcis_url, citation['publication'])
itemType = citation['publication'].split("/")[1]
itemList = get_itemList(dump_dir, itemType)
if any(item['uri'] == citation['publication'] for item in itemList):
item = next(obj for obj in itemList if obj['uri'] == citation['publication'])
item_id = 'bibo:%s'%item['identifier']
doc.wasDerivedFrom(item_id, datasetID)
prov_json = json.loads(doc.serialize())
return prov_json
def create_prov_es_json(ctx_file, id, prod_dir, prov_file):
"""Create provenance JSON file."""
# get abs path
prod_dir = os.path.abspath(prod_dir)
# get context
with open(ctx_file) as f:
context = json.load(f)
# get mission char
mis_char = MISSION_RE.search(context.get('file')).group(1)
mis_char_lc = mis_char.lower()
# get input url
input_url = context.get('localize_urls', [{'url': None}])[0]['url']
# get info
s1_files = glob(os.path.join(prod_dir, "s1%s-*.tiff" % mis_char_lc))
pf = "S1%s" % mis_char
dtype = "NA"
repo_dir = "?"
if len(s1_files) > 0:
match = S1_RE.search(os.path.basename(s1_files[0]))
if match: pf, swathnum, dtype = match.groups()
if dtype == "raw":
dtype = "RAW"
repo_dir = "s1%s_raw" % mis_char_lc
elif dtype == "slc":
dtype = "SLC"
repo_dir = "s1%s_slc" % mis_char_lc
platform = "eos:%s" % pf
platform_title = "Sentinel1%s Satellite" % mis_char
instrument = "eos:%s-SAR" % pf
instrument_title = "%s-SAR" % pf
level = "L0"
version = "v1.0"
collection = "eos:S1%s-%s-%s" % (mis_char, dtype, version)
collection_shortname = "S1%s-%s-%s" % (mis_char, dtype, version)
collection_label = "S1%s %s Scenes %s" % (mis_char, dtype, version)
collection_loc = "https://aria-dst-dav.jpl.nasa.gov/repository/products/%s/%s" % (
repo_dir, version)
sensor = "eos:SAR"
sensor_title = "Synthetic-aperture radar (SAR)"
gov_org = "eos:ESA"
gov_org_title = "European Space Agency"
software_version = "2.0.0_201604"
software_title = "InSAR SCE (InSAR Scientific Computing Environment) v%s" % software_version
software = "eos:ISCE-%s" % software_version
software_location = "https://winsar.unavco.org/isce.html"
algorithm = "eos:metadata_extraction"
prod_dir = "file://%s%s" % (socket.getfqdn(), prod_dir)
# put in fake start/end times so that prov:used and prov:generated
# are properly created by the prov lib
fake_time = datetime.utcnow().isoformat() + 'Z'
job_id = "ingest-%s-%s" % (id, fake_time)
bundle_id = "bundle-ingest-%s-%s" % (id, fake_time)
doc = ProvEsDocument()
#bndl = doc.bundle("hysds:%s" % get_uuid(bundle_id))
bndl = None
input_id = "hysds:%s" % get_uuid(input_url)
input_ds = doc.granule(input_id,
None, [input_url], [instrument],
None,
level,
None,
label=os.path.basename(input_url),
bundle=bndl)
doc.collection(collection,
None,
collection_shortname,
collection_label, [collection_loc], [instrument],
level,
version,
label=collection_label,
bundle=bndl)
output_id = "hysds:%s" % get_uuid(prod_dir)
output_ds = doc.granule(output_id,
None, [prod_dir], [instrument],
collection,
level,
version,
label=id,
bundle=bndl)
doc.governingOrganization(gov_org, label=gov_org_title, bundle=bndl)
doc.platform(platform, [instrument], label=platform_title, bundle=bndl)
doc.instrument(instrument,
platform, [sensor], [gov_org],
label=instrument_title,
bundle=bndl)
doc.sensor(sensor, instrument, label=sensor_title, bundle=bndl)
doc.software(software, [algorithm],
software_version,
label=software_title,
location=software_location,
bundle=bndl)
doc.processStep("hysds:%s" % get_uuid(job_id),
fake_time,
fake_time, [software],
None,
None, [input_ds.identifier], [output_ds.identifier],
label=job_id,
bundle=bndl,
prov_type="hysds:ingest")
with open(prov_file, 'w') as f:
json.dump(json.loads(doc.serialize()), f, indent=2, sort_keys=True)
def create_prov_es_json(id, netsel_file, jobdesc_file, project, aria_dem_xml,
aria_dem_file, prod_dir, work_dir, prov_file):
"""Create provenance JSON file."""
# put in fake start/end times so that prov:used and prov:generated
# are properly created by the prov lib
fake_time = datetime.utcnow().isoformat() + 'Z'
job_id = "create_interferogram-%s" % fake_time
bundle_id = "bundle-create_interferogram-%s" % fake_time
# create PROV-ES doc
doc = ProvEsDocument()
#bndl = doc.bundle("hysds:%s" % get_uuid(bundle_id))
bndl = None
# input and output identifiers
input_ids = {}
platform_ids = {}
instrument_ids = {}
# full url paths
work_url = "file://%s%s" % (socket.getfqdn(), work_dir)
prod_url = "%s/%s" % (work_url, prod_dir)
# add network selector file
#netsel_ent = bndl.entity("hysds:%s" % get_uuid("%s/%s" % (work_url, netsel_file)),
netsel_ent = doc.file("hysds:%s" % get_uuid("%s/%s" % (work_url, netsel_file)),
["%s/%s" % (work_url, netsel_file)],
label=os.path.basename(netsel_file))
input_ids[netsel_ent.identifier] = True
# add job description file
#jobdesc_ent = bndl.entity("hysds:%s" % get_uuid("%s/%s" % (work_url, jobdesc_file)),
jobdesc_ent = doc.file("hysds:%s" % get_uuid("%s/%s" % (work_url, jobdesc_file)),
["%s/%s" % (work_url, jobdesc_file)],
label=os.path.basename(jobdesc_file))
input_ids[jobdesc_ent.identifier] = True
# get list of CSK urls
level = "L0"
version = "v1.0"
sensor = "eos:SAR"
sensor_title = "Synthetic-aperture radar (SAR)"
gov_org = "eos:ASI"
gov_org_title = "Agenzia Spaziale Italiana"
doc.governingOrganization(gov_org, label=gov_org_title, bundle=bndl)
instrument = ""
for i, url in enumerate(get_netsel_urls(netsel_file)):
match = PLATFORM_RE.search(url)
if not match: continue
pf = match.group(1)
platform = "eos:%s" % pf
platform_title = "COSMO-SkyMed Satellite %s" % pf[-1]
instrument = "eos:%s-SAR" % pf
instrument_title = "%s-SAR" % pf
input_ds = doc.product("hysds:%s" % get_uuid(url), None,
[url], [instrument], None, level, version,
label=os.path.basename(url), bundle=bndl)
input_ids[input_ds.identifier] = True
if platform not in platform_ids:
doc.platform(platform, [instrument], label=platform_title,
bundle=bndl)
platform_ids[platform] = True
if instrument not in instrument_ids:
doc.instrument(instrument, platform, [sensor], [gov_org],
label=instrument_title, bundle=bndl)
doc.sensor(sensor, instrument, label=sensor_title, bundle=bndl)
instrument_ids[instrument] = True
# add dem xml, file and related provenance
srtm_platform = "eos:SpaceShuttleEndeavour"
srtm_platform_title = "USS Endeavour"
srtm_instrument = "eos:SRTM"
srtm_instrument_title = "Shuttle Radar Topography Mission (SRTM)"
srtm_sensor = "eos:radar"
srtm_sensor_title = "radar"
srtm_gov_org = "eos:JPL"
srtm_gov_org_title = "Jet Propulsion Laboratory"
doc.governingOrganization(srtm_gov_org, label=srtm_gov_org_title, bundle=bndl)
#dem_xml_ent = bndl.entity("hysds:%s" % get_uuid("%s/%s" % (work_url, aria_dem_xml)),
dem_xml_ent = doc.file("hysds:%s" % get_uuid("%s/%s" % (work_url, aria_dem_xml)),
["%s/%s" % (work_url, aria_dem_xml)],
label=os.path.basename(aria_dem_xml))
input_ids[dem_xml_ent.identifier] = True
#dem_file_ent = bndl.entity("hysds:%s" % get_uuid("%s/%s" % (work_url, aria_dem_file)),
dem_file_ent = doc.file("hysds:%s" % get_uuid("%s/%s" % (work_url, aria_dem_file)),
["%s/%s" % (work_url, aria_dem_file)],
label=os.path.basename(aria_dem_file))
input_ids[dem_file_ent.identifier] = True
doc.platform(srtm_platform, [srtm_instrument], label=srtm_platform_title,
bundle=bndl)
doc.instrument(srtm_instrument, srtm_platform, [srtm_sensor], [srtm_gov_org],
label=srtm_instrument_title, bundle=bndl)
doc.sensor(srtm_sensor, srtm_instrument, label=srtm_sensor_title, bundle=bndl)
instrument_ids[srtm_instrument] = True
# software and algorithm
algorithm = "eos:interferogram_generation"
software_version = "2.0.0_201604"
software_title = "InSAR SCE (InSAR Scientific Computing Environment) v%s" % software_version
software = "eos:ISCE-%s" % software_version
software_location = "https://winsar.unavco.org/isce.html"
doc.software(software, [algorithm], software_version, label=software_title,
location=software_location, bundle=bndl)
# output
int_level = "L2"
int_version = "v1.0"
int_collection = "eos:CSK-interferograms-%s" % int_version
int_collection_shortname = "CSK-interferograms-%s" % int_version
int_collection_label = "ISCE generated CSK interferograms %s" % int_version
int_collection_loc = "https://aria-dav.jpl.nasa.gov/repository/products/interferogram/%s" % int_version
doc.collection(int_collection, None, int_collection_shortname,
int_collection_label, [int_collection_loc],
instrument_ids.keys(), int_level, int_version,
label=int_collection_label, bundle=bndl)
output_ds = doc.granule("hysds:%s" % get_uuid(prod_url), None, [prod_url],
instrument_ids.keys(), int_collection, int_level,
int_version, label=id, bundle=bndl)
# runtime context
rt_ctx_id = "hysds:runtimeContext-ariamh-%s" % project
doc.runtimeContext(rt_ctx_id, [project], label=project, bundle=bndl)
# create process
doc.processStep("hysds:%s" % get_uuid(job_id), fake_time, fake_time,
[software], None, rt_ctx_id, input_ids.keys(),
[output_ds.identifier], label=job_id, bundle=bndl,
prov_type="hysds:create_interferogram")
# write
with open(prov_file, 'w') as f:
json.dump(json.loads(doc.serialize()), f, indent=2, sort_keys=True)
def get_image_prov(j, gcis_url):
"""Generate PROV-ES JSON from GCIS image metadata."""
# create doc
doc = ProvEsDocument()
bndl = None
# create image, figure, chapter and report entities
img_id = GCIS["%s" % j['uri'][1:].replace('/', '-')]
img_title = j['title']
img_url = None
img_thumbnail_url = None
for file_md in j.get('files', []):
img_url = file_md['href']
img_thumbnail_url = file_md['thumbnail_href']
img_attrs = [
( PROV_TYPE, GCIS['Image'] ),
( PROV_LABEL, img_title ),
]
if img_url is None:
img_attrs.append(( PROV_LOCATION, "%s%s" % (gcis_url, j['uri']) ))
else:
img_attrs.append(( PROV_LOCATION, img_url ))
if img_thumbnail_url is None:
img_attrs.append(( HYSDS['thumbnail'], img_thumbnail_url ))
doc.entity(img_id, img_attrs)
reports = []
chapters = []
findings = []
figures = []
for figure in j.get('figures', []):
report_uri = "/report/%s" % figure['report_identifier']
chapter_uri = "/chapter/%s" % figure['chapter_identifier']
figure_uri = "/figure/%s" % figure['identifier']
# create report
r = requests.get('%s%s.json' % (gcis_url, report_uri))
r.raise_for_status()
report = r.json()
report_id = GCIS["%s" % report_uri[1:].replace('/', '-')]
if report_id not in reports:
doc.entity(report_id, [
( PROV_TYPE, GCIS['Report'] ),
( PROV_LABEL, report['title'] ),
( PROV_LOCATION, report['url'] ),
])
reports.append(report_id)
# create chapter
r = requests.get('%s%s%s.json' % (gcis_url, report_uri, chapter_uri))
if r.status_code != 200:
print("Failed with %d code: %s" % (r.status_code, r.content))
continue
r.raise_for_status()
chapter = r.json()
chapter_id = GCIS["%s" % chapter_uri[1:].replace('/', '-')]
if chapter_id not in chapters:
doc.entity(chapter_id, [
( PROV_TYPE, GCIS['Chapter'] ),
( PROV_LABEL, chapter['title'] ),
( PROV_LOCATION, chapter['url'] ),
])
chapters.append(chapter_id)
doc.hadMember(report_id, chapter_id)
# create findings
r = requests.get('%s%s%s/finding.json' % (gcis_url, report_uri, chapter_uri))
r.raise_for_status()
for f in r.json():
finding_id = GCIS["%s" % f['identifier']]
if finding_id not in findings:
doc.entity(finding_id, [
( PROV_TYPE, GCIS['Finding'] ),
( PROV_LABEL, f['identifier'] ),
( PROV_LOCATION, f['href'] ),
])
findings.append(finding_id)
doc.hadMember(report_id, finding_id)
doc.hadMember(chapter_id, finding_id)
# create figure
r = requests.get('%s%s%s%s.json' % (gcis_url, report_uri, chapter_uri, figure_uri))
r.raise_for_status()
figure_md = r.json()
figure_id = GCIS["%s" % figure_uri[1:].replace('/', '-')]
if figure_id not in figures:
doc.entity(figure_id, [
( PROV_TYPE, GCIS['Figure'] ),
( PROV_LABEL, figure_md['title'] ),
( PROV_LOCATION, "%s%s" % (gcis_url, figure_md['uri']) ),
])
figures.append(figure_id)
doc.hadMember(chapter_id, figure_id)
doc.hadMember(figure_id, img_id)
# create agents or organizations
agent_ids = {}
org_ids = {}
for cont in j.get('contributors', []):
# replace slashes because we get prov.model.ProvExceptionInvalidQualifiedName errors
agent_id = GCIS["%s" % cont['uri'][1:].replace('/', '-')]
# create person
if len(cont['person']) > 0:
# agent
agent_name = " ".join([cont['person'][i] for i in
('first_name', 'middle_name', 'last_name')
if cont['person'].get(i, None) is not None])
doc.agent(agent_id, [
( PROV_TYPE, GCIS["Person"] ),
( PROV_LABEL, agent_name ),
( PROV_LOCATION, "%s%s" % (gcis_url, cont['uri']) ),
])
agent_ids[agent_id] = []
# organization
if len(cont['organization']) > 0:
org = cont['organization']
org_id = GCIS["%s" % cont['organization']['identifier']]
if org_id not in org_ids:
doc.governingOrganization(org_id, cont['organization']['name'])
org_ids[org_id] = True
if agent_id in agent_ids: agent_ids[agent_id].append(org_id)
# create activity
start_time = j['create_dt']
end_time = j['create_dt']
for parent in j.get('parents', []):
input_id = GCIS["%s" % parent['url'][1:].replace('/', '-')]
input_name = parent['label']
doc.entity(input_id, [
( PROV_TYPE, GCIS["Dataset"] ),
( PROV_LABEL, input_name ),
( PROV_LOCATION, "%s%s" % (gcis_url, parent['url']) ),
])
# some activity uri's are null
if parent['activity_uri'] is None:
act_id = GCIS["derive-from-%s" % input_id]
else:
act_id = GCIS["%s" % parent['activity_uri'][1:].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id, {'prov:role': GCIS['Contributor']})
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s" % get_uuid("%s:%s:%s" % (agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type': GCIS['worksAt']})
for org_id in org_ids:
waw_id = GCIS["%s" % get_uuid("%s:%s" % (act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id, {'prov:role': GCIS['Funder']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.used(act, input_id, start_time, GCIS["%s" % get_uuid("%s:%s" % (act_id, input_id))])
doc.wasGeneratedBy(img_id, act, end_time, GCIS["%s" % get_uuid("%s:%s" % (img_id, act_id))])
# serialize
prov_json = json.loads(doc.serialize())
# for hadMember relations, add prov:type
for hm_id in prov_json.get('hadMember', {}):
hm = prov_json['hadMember'][hm_id]
col = hm['prov:collection']
ent = hm['prov:entity']
if col in reports and ent in chapters:
hm['prov:type'] = GCIS['hasChapter']
elif col in chapters and ent in figures:
hm['prov:type'] = GCIS['hasFigure']
elif col in figures and ent == img_id:
hm['prov:type'] = GCIS['hasImage']
#print(json.dumps(prov_json, indent=2))
return prov_json
def get_doc_prov(j, gcis_url, refList, journalList, organizationList, personList, dump_dir):
"""Generate PROV-ES JSON from GCIS doc metadata."""
gcis_ns = "https://gcis-search-stage.jpl.net:3000/gcis.owl#"
doc = ProvEsDocument()
bndl = None
article = requests.get(j['href']).json()
journalID = None
#make journal
if any(journal['identifier'] == article['journal_identifier'] for journal in journalList):
journal = next(jour for jour in journalList if jour['identifier'] == article['journal_identifier'])
journalAttrs = [
("prov:type", 'gcis:Journal'),
("prov:label", journal['title']),
("prov:location", "%s%s"%(gcis_url,journal['uri'])),
("gcis:online_issn", journal['online_issn']),
("gcis:print_issn", journal['print_issn']),
("gcis:publisher", journal['publisher']),
]
journalID = 'bibo:%s'%journal['identifier']
doc.entity(journalID, journalAttrs)
#get organization/publisher if any
if journal['publisher'] is not None:
if any(organization['name'] == journal['publisher'] for organization in organizationList):
organization = next(org for org in organizationList if org['name'] == journal['publisher'])
org_attrs = [
("prov:type", 'gcis:organization'),
("prov:label", organization['name']),
("prov:location", "%s%s"%(gcis_url,organization['uri'])),
("gcis:organization_type_identifier", organization['organization_type_identifier']),
("gcis:country_code", organization['country_code']),
]
org_id = 'bibo:%s'%organization['identifier']
doc.entity(org_id, org_attrs)
doc.governingOrganization(org_id, organization['name'])
#make article
articleAttrs = [
("prov:type", 'gcis:Article'),
("prov:label", article['title']),
("prov:location","%s%s"%(gcis_url, article['uri'])),
("dcterms:isPartOf", journalID),
]
articleID = 'bibo:%s'%article['identifier']
doc.entity(articleID, articleAttrs)
#link journal to article
if journalID is not None:
doc.hadMember(journalID, articleID)
agent_ids = {}
org_ids = {}
#contributors
if 'contributors' in article:
for contributor in article['contributors']:
personID = None
if contributor['person_uri'] is not None:
name = " ".join([contributor['person'][i]
for i in ('first_name', 'middle_name', 'last_name')
if contributor['person'].get(i, None) is not None])
personAttrs = [
("prov:type", 'gcis:Person'),
("prov:label", "%s"%name),# %s"%(contributor['person']['first_name'],contributor['person']['last_name'])),
("prov:location", "%s%s"%(gcis_url,contributor['person_uri'])),
("gcis:id", str(contributor['person_id'])),
("gcis:orcid", contributor['person']['orcid'])
]
personID = 'bibo:%s'%contributor['person_id']
agent_ids[personID] = []
doc.agent(personID, personAttrs)
if contributor['organization'] is not None:
#make org
org_attrs = [
("prov:type", "gcis:organization"),
("prov:label", contributor["organization"]["name"]),
("prov:location", "%s%s"%(gcis_url, contributor["organization_uri"])),
("gcis:organization_type_identifier", contributor["organization"]["organization_type_identifier"]),
("gcis:country_code", contributor["organization"]["country_code"]),
]
orgID = 'bibo:%s'%contributor['organization']['identifier']
#doc.entity(orgID, org_attrs)
doc.governingOrganization(orgID, contributor['organization']['name'])
org_ids[orgID] = True
if personID in agent_ids:
agent_ids[personID].append(orgID)
#create actvity
if isinstance(j['year'], int):
start_time = str(j['year'])
end_time = str(j['year'])
else:
start_time = None
end_time = None
act_id = GCIS["generate-%s"%j['identifier'].replace('/', '-')]
attrs = []
for agent_id in agent_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, agent_id))]
doc.wasAssociatedWith(act_id, agent_id, None, waw_id, {'prov:role':GCIS['Author']})
for org_id in agent_ids[agent_id]:
del_id = GCIS["%s"%get_uuid("%s:%s:%s"%(agent_id, org_id, act_id))]
doc.delegation(agent_id, org_id, act_id, del_id, {'prov:type':'gcis:worksAt'})
for org_id in org_ids:
waw_id = GCIS["%s"%get_uuid("%s:%s"%(act_id, org_id))]
doc.wasAssociatedWith(act_id, org_id, None, waw_id, {'prov:role':GCIS['Contributor']})
act = doc.activity(act_id, start_time, end_time, attrs)
doc.wasGeneratedBy(articleID, act, end_time, GCIS["%s"%get_uuid("%s:%s"%(articleID, act_id))])
#cited by?
if 'cited_by' in article:
for citation in article['cited_by']:
if 'publication' in citation:
#pub_uri = "%s%s"%(gcis_url, citation['publication'])
itemType = citation['publication'].split("/")[1]
itemList = get_itemList(dump_dir, itemType)
if any(item['uri'] == citation['publication'] for item in itemList):
item = next(obj for obj in itemList if obj['uri'] == citation['publication'])
item_id = 'bibo:%s'%item['identifier']
doc.wasDerivedFrom(item_id, articleID)
print articleID
prov_json = json.loads(doc.serialize())
return prov_json