#!/usr/bin/env python3
"""
Merge IT enriched institutions back into unified global dataset.
"""

import yaml
from datetime import datetime, timezone

def merge_it_enriched():
    print("=" * 80)
    print("🔀 Merging IT enriched data into unified dataset")
    print("=" * 80)
    
    # Load unified dataset
    print("\n📂 Loading unified dataset...")
    with open('data/instances/all/globalglam-20251111.yaml', 'r', encoding='utf-8') as f:
        all_institutions = yaml.safe_load(f)
    print(f"   ✅ Loaded {len(all_institutions)} institutions")
    
    # Load enriched IT data
    print("\n📂 Loading IT enriched data...")
    with open('data/instances/italy/it_institutions_enriched_manual.yaml', 'r', encoding='utf-8') as f:
        it_enriched = yaml.safe_load(f)
    print(f"   ✅ Loaded {len(it_enriched)} enriched IT institutions")
    
    # Create lookup by ID URL for quick matching
    it_by_id = {inst['id']: inst for inst in it_enriched}
    
    # Merge enriched data
    print("\n🔄 Merging enriched data...")
    merged_count = 0
    
    for i, inst in enumerate(all_institutions):
        inst_id = inst.get('id')
        if inst_id in it_by_id:
            # Preserve GHCID from original if it exists
            enriched_inst = it_by_id[inst_id].copy()
            if 'ghcid' in inst:
                enriched_inst['ghcid'] = inst['ghcid']
            if 'ghcid_uuid' in inst:
                enriched_inst['ghcid_uuid'] = inst['ghcid_uuid']
            if 'ghcid_uuid_sha256' in inst:
                enriched_inst['ghcid_uuid_sha256'] = inst['ghcid_uuid_sha256']
            if 'ghcid_numeric' in inst:
                enriched_inst['ghcid_numeric'] = inst['ghcid_numeric']
            
            # Replace with enriched version
            all_institutions[i] = enriched_inst
            merged_count += 1
            print(f"   ✅ Merged: {inst['name']}")
    
    print(f"\n   📊 Total merged: {merged_count}")
    
    # Save unified dataset with timestamp
    timestamp = datetime.now(timezone.utc).strftime('%Y%m%d')
    output_path = f'data/instances/all/globalglam-{timestamp}.yaml'
    
    print(f"\n💾 Saving updated unified dataset to {output_path}...")
    with open(output_path, 'w', encoding='utf-8') as f:
        yaml.dump(all_institutions, f, allow_unicode=True, sort_keys=False, default_flow_style=False)
    
    print("   ✅ Saved")
    
    # Verify IT coverage
    it_institutions = [
        inst for inst in all_institutions 
        if any(loc.get('country') == 'IT' for loc in inst.get('locations', []))
    ]
    
    it_with_wikidata = sum(
        1 for inst in it_institutions 
        if any(i.get('identifier_scheme') == 'Wikidata' for i in inst.get('identifiers', []))
    )
    
    print("\n" + "=" * 80)
    print("📊 VERIFICATION - IT Institutions in Unified Dataset")
    print("=" * 80)
    print(f"Total IT institutions:       {len(it_institutions)}")
    print(f"With Wikidata identifiers:   {it_with_wikidata}")
    print(f"Coverage:                    {it_with_wikidata/len(it_institutions)*100:.1f}%")
    
    if it_with_wikidata == len(it_institutions):
        print("\n✅ SUCCESS: 100% Wikidata coverage verified in unified dataset!")
        print("🇮🇹 Phase 1 Italy: COMPLETE")
    
    print("\n")

if __name__ == '__main__':
    merge_it_enriched()