glam/scripts/mark_virtual_itinerant_ar.py

#!/usr/bin/env python3
"""
Mark Argentina AR-XX-XXX files as VIRTUAL or ITINERANT based on their nature.

These institutions intentionally keep XX-XXX codes because they don't have
fixed physical locations.

Usage:
    python scripts/mark_virtual_itinerant_ar.py [--dry-run]
"""

import yaml
from pathlib import Path
from datetime import datetime, timezone

CUSTODIAN_DIR = Path("data/custodian")

# Institutions that are digital/virtual or itinerant
# These should remain AR-XX-XXX because they have no fixed physical location
VIRTUAL_OR_ITINERANT = {
    # Digital Platforms (VIRTUAL)
    "AR-XX-XXX-A-ADP.yaml": {
        "location_type": "VIRTUAL",
        "reason": "National Open Data Portal - datos.gob.ar - web platform with no physical collection location"
    },
    "AR-XX-XXX-A-RAA.yaml": {
        "location_type": "VIRTUAL", 
        "reason": "Repositorios de acceso abierto - digital repositories aggregator for Argentine open access materials"
    },
    "AR-XX-XXX-A-AMT.yaml": {
        "location_type": "VIRTUAL",
        "reason": "Archivo de la Memoria Trans - community archive primarily online (archivotrans.ar), preserves trans community history"
    },
    "AR-XX-XXX-A-PDDH1AVJML.yaml": {
        "location_type": "VIRTUAL",
        "reason": "UNESCO Memory of the World heritage - distributed archival network documenting human rights violations 1976-1983"
    },
    "AR-XX-XXX-A-MMD.yaml": {
        "location_type": "VIRTUAL",
        "reason": "Mapeo Mostri Disidente - digital mapping/archive project for LGBTQ+ dissident culture"
    },
    "AR-XX-XXX-A-PT.yaml": {
        "location_type": "VIRTUAL",
        "reason": "Potencia Tortillera - digital archive/collective (blogspot) for lesbian feminist activism and history"
    },
    
    # Itinerant Museums (no fixed location)
    "AR-XX-XXX-M-MDI.yaml": {
        "location_type": "ITINERANT",
        "reason": "Museo del Dibujo y la Ilustración (MuDi) - museo itinerante (itinerant museum) with no fixed location, holds exhibitions at various venues"
    },
}


def mark_file(filename: str, info: dict, dry_run: bool = False) -> bool:
    """Add location_type to a custodian file."""
    filepath = CUSTODIAN_DIR / filename
    
    if not filepath.exists():
        print(f"  ⚠️  File not found: {filename}")
        return False
    
    with open(filepath, 'r', encoding='utf-8') as f:
        data = yaml.safe_load(f)
    
    print(f"\n  📁 {filename}")
    print(f"     Name: {data.get('custodian_name', {}).get('claim_value', 'Unknown')}")
    print(f"     Type: {info['location_type']}")
    print(f"     Reason: {info['reason']}")
    
    if dry_run:
        print(f"     [DRY RUN] Would add location_type: {info['location_type']}")
        return True
    
    # Add location_type to location block (create if needed)
    if 'location' not in data:
        data['location'] = {'country': 'AR'}
    
    data['location']['location_type'] = info['location_type']
    data['location']['location_type_reason'] = info['reason']
    data['location']['location_type_date'] = datetime.now(timezone.utc).isoformat()
    
    # Also add a note to ghcid resolution explaining why XX-XXX is intentional
    if 'ghcid' in data and 'location_resolution' in data['ghcid']:
        data['ghcid']['location_resolution']['intentional_xx_xxx'] = True
        data['ghcid']['location_resolution']['xx_xxx_reason'] = info['reason']
    
    with open(filepath, 'w', encoding='utf-8') as f:
        yaml.dump(data, f, allow_unicode=True, sort_keys=False, default_flow_style=False)
    
    print(f"     ✅ Marked as {info['location_type']}")
    return True


def main():
    import sys
    
    dry_run = '--dry-run' in sys.argv
    
    print("=" * 60)
    print("Mark Virtual/Itinerant Argentina Institutions")
    print("=" * 60)
    
    if dry_run:
        print("\n🔍 DRY RUN MODE - No files will be modified\n")
    
    marked_count = 0
    error_count = 0
    
    for filename, info in VIRTUAL_OR_ITINERANT.items():
        try:
            if mark_file(filename, info, dry_run):
                marked_count += 1
        except Exception as e:
            print(f"\n  ❌ ERROR processing {filename}: {e}")
            error_count += 1
    
    print("\n" + "=" * 60)
    print("SUMMARY")
    print("=" * 60)
    print(f"  Total to mark: {len(VIRTUAL_OR_ITINERANT)}")
    print(f"  Successfully marked: {marked_count}")
    print(f"  Errors: {error_count}")
    
    if dry_run:
        print("\n  Run without --dry-run to apply changes.")
    
    # List remaining unknown AR-XX-XXX files
    print("\n" + "=" * 60)
    print("REMAINING AR-XX-XXX FILES (Need Research)")
    print("=" * 60)
    
    all_ar_xx = list(CUSTODIAN_DIR.glob("AR-XX-*.yaml"))
    marked_files = set(VIRTUAL_OR_ITINERANT.keys())
    
    remaining = [f for f in all_ar_xx if f.name not in marked_files]
    
    if remaining:
        for f in sorted(remaining):
            # Load to get name
            with open(f, 'r', encoding='utf-8') as fp:
                data = yaml.safe_load(fp)
            name = data.get('custodian_name', {}).get('claim_value', 'Unknown')
            wikidata = data.get('original_entry', {}).get('wikidata_id', 'N/A')
            print(f"  • {f.name}")
            print(f"    Name: {name}")
            print(f"    Wikidata: {wikidata}")
        print(f"\n  Total needing research: {len(remaining)}")
    else:
        print("  None! All AR-XX-XXX files have been categorized.")


if __name__ == "__main__":
    main()