"""Read-only command-line queries for the paper index.""" import argparse import json import sqlite3 from pathlib import Path def main(): parser = argparse.ArgumentParser() parser.add_argument('--db', required=True) parser.add_argument('--query', help='SQLite FTS5 query over title and abstract') parser.add_argument('--tag', help='Filter as namespace=value, e.g. arxiv:category=cs.AI') parser.add_argument('--venue', help='Conference acronym') parser.add_argument('--year', type=int) parser.add_argument('--status', choices=['accepted','rejected','desk_rejected','withdrawn','under_review','unknown']) parser.add_argument('--limit', type=int, default=20) parser.add_argument('--stats', action='store_true') args = parser.parse_args() conn = sqlite3.connect(Path(args.db).resolve().as_uri()+'?mode=ro', uri=True) conn.row_factory = sqlite3.Row if args.stats: result = {name:conn.execute('SELECT count(*) FROM '+name).fetchone()[0] for name in ('papers','source_records','submissions','decisions','tags','match_candidates')} result['coverage'] = [dict(r) for r in conn.execute('SELECT status,count(*) AS sources FROM edition_sources GROUP BY status')] result['runs'] = [dict(r) for r in conn.execute('SELECT * FROM ingest_runs ORDER BY id DESC LIMIT 10')] else: where = []; params = [] if args.query: where.append('p.id IN (SELECT rowid FROM papers_fts WHERE papers_fts MATCH ?)'); params.append(args.query) if args.tag: namespace,value = args.tag.split('=',1) where.append('EXISTS(SELECT 1 FROM paper_tags pt JOIN tags t ON t.id=pt.tag_id WHERE pt.paper_id=p.id AND t.namespace=? AND t.value=?)'); params.extend([namespace,value]) if args.venue or args.year or args.status: clause = ['s.paper_id=p.id'] if args.venue: clause.append('v.acronym=?'); params.append(args.venue) if args.year: clause.append('e.year=?'); params.append(args.year) if args.status: clause.append('EXISTS(SELECT 1 FROM decisions d WHERE d.submission_id=s.id AND d.status=? AND NOT EXISTS(SELECT 1 FROM decisions newer WHERE newer.submission_id=d.submission_id AND (newer.observed_at>d.observed_at OR (newer.observed_at=d.observed_at AND newer.id>d.id))))'); params.append(args.status) where.append('EXISTS(SELECT 1 FROM submissions s JOIN editions e ON e.id=s.edition_id JOIN venues v ON v.id=e.venue_id WHERE '+' AND '.join(clause)+')') sql = 'SELECT p.* FROM papers p'+(' WHERE '+' AND '.join(where) if where else '')+' ORDER BY p.id LIMIT ?' params.append(max(1,min(args.limit,200))) result = [] for row in conn.execute(sql,params): paper = dict(row) paper['identifiers'] = [dict(r) for r in conn.execute('SELECT scheme,value FROM identifiers WHERE paper_id=?',(row['id'],))] result.append(paper) print(json.dumps(result,ensure_ascii=False,indent=2)) if __name__ == '__main__': main()