def test_get_docs_by_audit_id(self):
audits = get_audits()
if len(audits) == 0:
logger.warning('no audits')
return
audit_id = audits[0]['_id']
docs = get_docs_by_audit_id(audit_id, kind='PROTOCOL')
for a in docs:
print(a['_id'], a['filename'])
def test_process_charters_phase_1(self):
audits = get_audits()
if len(audits) == 0:
logger.warning('no audits')
return
audit_id = audits[0]['_id']
docs: [dict] = get_docs_by_audit_id(audit_id, kind='CHARTER')
processor = document_processors.get('CHARTER')
for _doc in docs:
jdoc = DbJsonDoc(_doc)
processor.preprocess(jdoc, AuditContext())
def _get_doc_from_db(self, kind):
audits = get_mongodb_connection()['audits'].find().sort([
("createDate", pymongo.ASCENDING)
]).limit(1)
for audit in audits:
doc_ids = get_docs_by_audit_id(audit['_id'],
kind=kind,
states=[15],
id_only=True)
if len(doc_ids) > 0:
print(doc_ids[0])
doc = finalizer.get_doc_by_id(doc_ids[0])
# jdoc = DbJsonDoc(doc)
yield doc
def test_process_contracts_phase_1(self):
# runner = Runner.get_instance()
audits = get_audits()
if len(audits) == 0:
logger.warning('no audits')
return
audit_id = audits[0]['_id']
docs = get_docs_by_audit_id(audit_id, kind='CONTRACT')
processor = document_processors.get('CONTRACT')
for _doc in docs:
jdoc = DbJsonDoc(_doc)
processor.preprocess(jdoc, AuditContext())
def test_process_protocols_phase_1(self):
runner = get_runner_instance_no_embedder()
for audit in get_audits():
audit_id = audit['_id']
docs = get_docs_by_audit_id(audit_id, kind='PROTOCOL')
for doc in docs:
# charter = runner.make_legal_doc(doc)
jdoc = DbJsonDoc(doc)
legal_doc = jdoc.asLegalDoc()
runner.protocol_parser.find_org_date_number(
legal_doc, AuditContext())
save_analysis(jdoc, legal_doc, -1)
def test_get_org_names(self):
parser = CharterParser()
audits = get_audits()
if len(audits) == 0:
logger.warning('no audits')
return
audit_id = audits[0]['_id']
docs = get_docs_by_audit_id(audit_id, kind=CHARTER)
for db_document in docs:
print(db_document['filename'])
parsed_p_json = db_document['parse']
charter: CharterDocument = join_paragraphs(
parsed_p_json, doc_id=db_document['_id'])
# TODO: mind, this could be slow if embedding is required
parser.find_org_date_number(charter, AuditContext())
for tag in charter.get_tags():
print(tag)