47 lines
3.1 KiB
Python
47 lines
3.1 KiB
Python
"""Show every target venue, including those with no imported records."""
|
|
import argparse
|
|
from paper_atlas.config import DEFAULT_REGISTRY
|
|
import json
|
|
from pathlib import Path
|
|
import sqlite3
|
|
|
|
from paper_atlas.db.submissions import timestamp
|
|
|
|
|
|
def report(db,registry):
|
|
registry=json.loads(Path(registry).read_text());targets=registry['venues']
|
|
names=[row['acronym'].casefold() for row in targets]
|
|
if len(names)!=len(set(names)):raise ValueError('Duplicate target venue')
|
|
scope='(v.acronym=? COLLATE NOCASE OR EXISTS(SELECT 1 FROM venue_aliases a WHERE a.venue_id=v.id AND a.alias=? COLLATE NOCASE))'
|
|
c=sqlite3.connect(Path(db).resolve().as_uri()+'?mode=ro',uri=True);c.row_factory=sqlite3.Row
|
|
try:
|
|
c.execute('BEGIN');venues=[]
|
|
for target in targets:
|
|
acronym=target['acronym'];params=(acronym,acronym)
|
|
editions=[]
|
|
for row in c.execute('SELECT e.id,v.acronym AS canonical_venue,e.year,e.track,count(s.id) AS submissions,count(DISTINCT s.paper_id) AS papers FROM editions e JOIN venues v ON v.id=e.venue_id LEFT JOIN submissions s ON s.edition_id=e.id WHERE '+scope+' GROUP BY e.id ORDER BY e.year,e.track',params):
|
|
edition=dict(row)
|
|
edition['sources']=[dict(source) for source in c.execute('SELECT so.name,es.status,es.expected_count,es.imported_count,es.list_url,es.last_success_at,es.last_error FROM edition_sources es JOIN sources so ON so.id=es.source_id WHERE es.edition_id=? ORDER BY so.name',(row['id'],))]
|
|
editions.append(edition)
|
|
totals=c.execute('SELECT count(s.id),count(DISTINCT s.paper_id) FROM submissions s JOIN editions e ON e.id=s.edition_id JOIN venues v ON v.id=e.venue_id WHERE '+scope,params).fetchone()
|
|
venues.append({'acronym':acronym,'field':target['field'],'imported_submissions':totals[0],'distinct_papers':totals[1],
|
|
'history_status':'partial_history_pending_independent_audit' if totals[0] else 'no_imported_records',
|
|
'discovery_sources':target.get('discovery_sources',[]),'editions':editions})
|
|
return {'checked_at':timestamp(),'target_venue_count':len(targets),'venues_with_imported_records':sum(bool(v['imported_submissions']) for v in venues),
|
|
'scope_note':registry['scope_note'],'interpretation':'All registry targets are listed. Edition source complete means that source file passed import checks; it does not prove full historical or abstract coverage. Papers can appear in multiple venues/years, so do not sum venue paper counts as a global total.',
|
|
'venues':venues}
|
|
finally:c.close()
|
|
|
|
|
|
def main(argv=None, *, prog=None):
|
|
parser=argparse.ArgumentParser(prog=prog);parser.add_argument('--db',required=True)
|
|
parser.add_argument('--registry',default=str(DEFAULT_REGISTRY));parser.add_argument('--out')
|
|
args=parser.parse_args(argv);result=report(args.db,args.registry);text=json.dumps(result,ensure_ascii=False,indent=2)
|
|
if args.out:
|
|
path=Path(args.out);stage=path.with_suffix('.part');stage.write_text(text+'\n');stage.replace(path)
|
|
else:print(text)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|