"""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('--paper',type=int,help='Paper ID; include sources, tags and submission history')
    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('--track',help='Exact track, e.g. main, findings, workshop')
    parser.add_argument('--status', choices=['accepted','rejected','desk_rejected','withdrawn','under_review','unknown'])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
    conn.execute('BEGIN')  # One consistent read snapshot while ingestion continues.
    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['records_by_source'] = [dict(r) for r in conn.execute('SELECT s.name,count(r.id) AS imported_records FROM sources s LEFT JOIN source_records r ON r.source_id=s.id GROUP BY s.id ORDER BY s.name')]
        result['decision_events_by_status'] = [dict(r) for r in conn.execute('SELECT status,count(*) AS events FROM decisions GROUP BY status')]
        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.paper is not None:
            where.append('p.id=?'); params.append(args.paper)
        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 or args.track:
            clause = ['1=1']
            if args.venue:
                if conn.execute("SELECT 1 FROM sqlite_master WHERE type='table' AND name='venue_aliases'").fetchone():
                    clause.append('(v.acronym=? COLLATE NOCASE OR EXISTS(SELECT 1 FROM venue_aliases va WHERE va.venue_id=v.id AND va.alias=? COLLATE NOCASE))'); params.extend([args.venue,args.venue])
                else:
                    clause.append('v.acronym=? COLLATE NOCASE');params.append(args.venue)
            if args.track:
                clause.append('e.track=?');params.append(args.track)
            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('p.id IN (SELECT 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 '+' 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['authors'] = json.loads(paper.pop('authors_json'))
            paper['identifiers'] = [dict(r) for r in conn.execute('SELECT scheme,value FROM identifiers WHERE paper_id=?',(row['id'],))]
            if args.paper is not None:
                paper['tags'] = [dict(r) for r in conn.execute('SELECT t.namespace,t.value,pt.evidence_key FROM paper_tags pt JOIN tags t ON t.id=pt.tag_id WHERE pt.paper_id=?',(row['id'],))]
                paper['sources'] = [dict(r) for r in conn.execute('SELECT s.name,r.external_id,r.url,r.title,r.abstract,r.retrieved_at FROM source_records r JOIN sources s ON s.id=r.source_id WHERE r.paper_id=?',(row['id'],))]
                submissions = []
                for sub in conn.execute('SELECT s.id,s.source_submission_id,s.submitted_at,v.acronym,e.year,e.track FROM submissions s JOIN editions e ON e.id=s.edition_id JOIN venues v ON v.id=e.venue_id WHERE s.paper_id=? ORDER BY e.year,s.id',(row['id'],)):
                    submission = dict(sub)
                    submission['decisions'] = [dict(d) for d in conn.execute('SELECT status,raw_value,evidence_url,observed_at,decision_date FROM decisions WHERE submission_id=? ORDER BY observed_at,id',(sub['id'],))]
                    submissions.append(submission)
                paper['submissions'] = submissions
            result.append(paper)
    print(json.dumps(result,ensure_ascii=False,indent=2))
    conn.close()


if __name__ == '__main__':
    main()