"""Meaningful checks for scoring, alignment, ontology mapping and publication safety."""
from benchmark_schema import make_schema
from prepare_benchmarks import bio_document
from evaluate_model import chunks,counts,Adapter
from collections import defaultdict
import json
from pathlib import Path

def main():
    d=bio_document(['New','York','and','York'],['B-place','I-place','O','B-place'],'test')
    assert d['entities']==[[0,8,'place'],[13,17,'place']]
    assert counts(d['entities'],[[0,8,'place'],[13,17,'wrong']])==[1,1,1]
    assert counts([[0,5,'x']],[[0,4,'x']])==[0,1,1]
    long=' '.join('t'+str(i) for i in range(180));parts=chunks(long)
    assert all(long[o:o+len(t)]==t for o,t in parts)
    covered=set(i for o,t in parts for i in range(o,o+len(t)))
    assert all(i in covered for i,c in enumerate(long) if not c.isspace())
    a=Adapter.__new__(Adapter);a.events=defaultdict(int)
    assert a.parse_json('York York','{"place":["York","York"]}',{'place':'Named place'})==[[0,4,'place'],[5,9,'place']]
    assert a.parse_json('York','{"place":["Paris"]}',{'place':'Named place'})[0][0]<0
    assert a.parse_gner('New York is large','New(B-place), York(I-place), is(O), large(O)',{'place':'Named place'})==[[0,8,'place']]
    assert a.parse_gner('New York is large','New(B-place) York(I-place) is(O) large(O)',{'place':'Named place'})==[[0,8,'place']]
    assert a.parse_gner('New , York','New(B-place) ,(O) York(B-place)',{'place':'Named place'})==[[0,3,'place'],[6,10,'place']]
    inv=json.loads((Path(__file__).resolve().parents[1]/'audit/labels.json').read_text())
    s=make_schema(['Actor','Rating','Chemical','Year'],inv)
    assert s['Actor']['status']=='new_specific_type_related'
    assert s['Rating']['status']=='scope_mismatch_or_unresolved'
    assert s['Chemical']['training_definition'] in [x['definition'] for x in inv['chemical_compound']['definitions']]
    semantic=make_schema(['chemicalelement','theory'],inv)
    assert semantic['chemicalelement']['training_definition']=='Chemical element from periodic table'
    assert semantic['theory']['training_definition']=='Scientific theory or hypothesis'
    from investigate_models import flat_predictions
    flat=flat_predictions([[[0,5,'person',.7],[0,5,'scientist',.9],[6,10,'company',.8],[1,4,'other',.4]]])
    assert flat==[[[0,5,'scientist',.9],[6,10,'company',.8]]]
    print('Protocol checks passed',flush=True)

if __name__=='__main__':main()