Created
September 15, 2021 09:18
-
-
Save kindly/4f9dc74d35fa401b5bbced818448b90d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import jsonlines | |
| import flatterer | |
| from pathlib import Path | |
| import subprocess | |
| def flatten_iterator(statement_type): | |
| with jsonlines.open('statements.2021-08-31T08 14 34Z.jsonl') as f: | |
| for object in f: | |
| if object["statementType"] == statement_type: | |
| yield object | |
| p = Path('.') | |
| flatterer.iterator_flatten(flatten_iterator("personStatement"), 'output_person', main_table_name='statement', force=True) | |
| flatterer.iterator_flatten(flatten_iterator("ownershipOrControlStatement"), 'output_ooc', main_table_name='statement', force=True) | |
| flatterer.iterator_flatten(flatten_iterator("entityStatement"), 'output_entity', main_table_name='statement', force=True) | |
| for path in p.glob('output_person/csv/*.csv'): | |
| parts = list(path.parts) | |
| parts[-1] = 'person_' + parts[-1] | |
| path.rename("/".join(parts)) | |
| for path in p.glob('output_ooc/csv/*.csv'): | |
| parts = list(path.parts) | |
| parts[-1] = 'ooc_' + parts[-1] | |
| path.rename("/".join(parts)) | |
| for path in p.glob('output_entity/csv/*.csv'): | |
| parts = list(path.parts) | |
| parts[-1] = 'entity_' + parts[-1] | |
| path.rename("/".join(parts)) | |
| for path in p.glob('*/csv/*.csv'): | |
| print(path) | |
| name = path.parts[-1].split('.')[0] | |
| subprocess.run(['sqlite-utils', 'insert', '--silent', '-d', '-c', 'register.db', name, f'{str(path)}']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment