"""Pull all deleted contacts from Barbara's mailbox."""
import subprocess, json

TENANT_ID = "dd4a82e8-85a3-44ac-8800-07945ab4d95f"
CLAUDE_APP = "fabb3421-8b34-484b-bc17-e46de9703418"
CLAUDE_SECRET = "~QJ8Q~NyQSs4OcGqHZyPrA2CVnq9KBfKiimntbMO"
USER = "barbara@bardach.net"

# Get token
token_cmd = subprocess.run([
    'curl', '-s', '-X', 'POST',
    f'https://login.microsoftonline.com/{TENANT_ID}/oauth2/v2.0/token',
    '-d', f'client_id={CLAUDE_APP}&client_secret={CLAUDE_SECRET}&scope=https://graph.microsoft.com/.default&grant_type=client_credentials'
], capture_output=True, text=True)
token = json.loads(token_cmd.stdout)['access_token']

# Page through all deleted contacts
url = (f"https://graph.microsoft.com/beta/users/{USER}/contacts"
       f"?$filter=parentFolderId%20eq%20'deleteditems'"
       f"&$top=100"
       f"&$select=displayName,emailAddresses,companyName,lastModifiedDateTime")

all_deleted = []
page = 0

while url:
    page += 1
    cmd = ['curl', '-s', '-H', f'Authorization: Bearer {token}', url]
    result = subprocess.run(cmd, capture_output=True, text=True)
    data = json.loads(result.stdout)

    if 'error' in data:
        print(f"Error on page {page}: {data['error'].get('message','')[:200]}")
        break

    items = data.get('value', [])
    all_deleted.extend(items)
    url = data.get('@odata.nextLink')

    if page % 5 == 0:
        print(f"  Page {page}: {len(all_deleted)} deleted contacts so far...")

    if not items:
        break

print(f"\nTotal deleted contacts found: {len(all_deleted)}")

# Analyze
from collections import Counter

if all_deleted:
    # Save full data
    with open('D:/ClaudeTools/temp/bardach_deleted_contacts.json', 'w') as f:
        json.dump(all_deleted, f, indent=2)

    # Name analysis
    names = [c.get('displayName', '').strip() for c in all_deleted if c.get('displayName')]
    name_counts = Counter([n.lower() for n in names])
    dupes = {k: v for k, v in name_counts.items() if v > 1}

    print(f"\nUnique names: {len(set(n.lower() for n in names))}")
    print(f"Names with duplicates: {len(dupes)}")

    # Check overlap with active contacts
    active_file = 'D:/ClaudeTools/temp/bardach_contacts.json'
    try:
        with open(active_file) as f:
            active = json.load(f)
        active_names = set(c.get('displayName', '').strip().lower() for c in active if c.get('displayName'))
        deleted_names = set(n.lower() for n in names)

        overlap = active_names & deleted_names
        only_deleted = deleted_names - active_names

        print(f"\nActive contacts: {len(active_names)}")
        print(f"Deleted contacts (unique names): {len(deleted_names)}")
        print(f"Names in BOTH active and deleted: {len(overlap)}")
        print(f"Names ONLY in deleted (not in active): {len(only_deleted)}")

        if only_deleted:
            print(f"\nSample of contacts only in Deleted Items (not in active contacts):")
            for name in sorted(only_deleted)[:50]:
                print(f"  - {name}")
            if len(only_deleted) > 50:
                print(f"  ... and {len(only_deleted) - 50} more")

    except FileNotFoundError:
        print("\n(Active contacts file not found for comparison)")

    # Show date range
    dates = [c.get('lastModifiedDateTime', '')[:10] for c in all_deleted if c.get('lastModifiedDateTime')]
    if dates:
        print(f"\nDate range of deleted contacts: {min(dates)} to {max(dates)}")

    # Sample
    print(f"\nFirst 30 deleted contacts:")
    for c in all_deleted[:30]:
        name = c.get('displayName', '(no name)')
        emails = ', '.join([e.get('address', '') for e in c.get('emailAddresses', [])])
        company = c.get('companyName', '')
        modified = c.get('lastModifiedDateTime', '?')[:10]
        detail = emails or company or ''
        print(f"  {modified} - {name}" + (f" ({detail})" if detail else ""))