"""E: same cached crop evidence, alter only which real OCR reads are available."""
from pathlib import Path
import json
import copy
import statistics
from analyze import decide,propagate,metrics,infer_groups

DIR=Path(__file__).resolve().parent
OUT=DIR/'evidence'


def main():
    data=json.loads((OUT/'observations.json').read_text()); analysis=json.loads((OUT/'analysis.json').read_text())
    families=json.loads((DIR/'group-truth.json').read_text())['families']
    report={'provenance':data['provenance'],'arms':{}}
    for res,d in data['resolutions'].items():
        obs=d['observations']; sig=data['signatures']; groups=analysis['resolutions'][res]['appearance_groups']
        lookup={o['id']:o for o in obs}
        visual={o['id']:decide(o,'strict',sig,use_text=False) for o in obs}
        # Only uncertainty in the visual evidence schedules expensive text.
        ambiguous={o['id'] for o in obs if not visual[o['id']] or len(o['rank'])>1 and o['rank'][0][1]<5}
        arms={
            'every_attempt':{'ocr_ids':{o['id'] for o in obs},'attempts':2},
            'once_per_track':{'ocr_ids':{o['id'] for o in obs},'attempts':2},
            'ambiguous_track':{'ocr_ids':ambiguous,'attempts':2},
            'group_representative':{'ocr_ids':{max(group,key=lambda i:lookup[i]['sharpness']) for group in groups if any(i in ambiguous for i in group)},'attempts':2},
        }
        result={}
        for name,arm in arms.items():
            if name=='group_representative':
                source={i:max(g,key=lambda k:lookup[k]['sharpness']) for g in groups for i in g}
            else:source={i:i for i in lookup}
            masked=[]
            for o in obs:
                clone=copy.deepcopy(o); origin=source[o['id']]
                # Representative's read is reusable only when its group
                # correspondence passed the boundary guard. Read is not a
                # perfect label; it goes through the unchanged policy.
                if origin not in arm['ocr_ids']:
                    clone['text']={};clone['read']=''
                else:
                    clone['text']=lookup[origin]['text'];clone['read']=lookup[origin]['read']
                masked.append(clone)
            bases={o['id']:decide(o,'coverage-first',sig) for o in masked}
            available_groups=infer_groups(d,analysis['resolutions'][res]['guarded_edges'],{o['id']:decide(o,'strict',sig) for o in masked})
            fused,changes=propagate(masked,available_groups,bases,sig,guarded=True)
            number=len(arm['ocr_ids'])*(arm['attempts'] if name=='every_attempt' else 1)
            ocr_ms=sum(lookup[i]['ocr_ms'] for i in arm['ocr_ids'])*(arm['attempts'] if name=='every_attempt' else 1)
            local_ms=sum(o['local_ms'] for o in obs)*arm['attempts']
            result[name]={'individual':metrics(masked,bases,families),'group':metrics(masked,fused,families,bases),'ocr_calls':number,'ocr_calls_per_facing':number/len(obs),'ocr_ms_serial_projection':round(ocr_ms,1),'matcher_calls':len(obs)*arm['attempts'],'matcher_ms_serial_projection':round(local_ms,1),'read_coverage':sum(bool(lookup[i]['read']) for i in arm['ocr_ids']),'ocr_ids':sorted(arm['ocr_ids']),'rescues':changes}
        report['arms'][res]=result
        print(res)
        for name,r in result.items():print(name,r['ocr_calls'],r['group']['shown'],r['group']['correct'],r['group']['wrong'],r['ocr_ms_serial_projection'])
    (OUT/'ocr-ablation.json').write_text(json.dumps(report,ensure_ascii=False,indent=2))

if __name__=='__main__':main()