#!/usr/bin/env python3
"""Step 5: Verify deduplication - pull contacts again and check for remaining duplicates."""

import json
import subprocess
import sys
from collections import defaultdict

TENANT_ID = "dd4a82e8-85a3-44ac-8800-07945ab4d95f"
CLIENT_ID = "fabb3421-8b34-484b-bc17-e46de9703418"
CLIENT_SECRET = "~QJ8Q~NyQSs4OcGqHZyPrA2CVnq9KBfKiimntbMO"
SCOPE = "https://graph.microsoft.com/.default"
USER = "barbara@bardach.net"
FOLDER_ID = "AAMkADNiYWE4ZDYxLWE4M2EtNGY1MS05YWQwLWY2OWYzMWI3YjZjNAAuAAAAAADrk4YN-mpcR5zROC2646l9AQCo_dM7bg-DQY5RuVpcPz_JAAQU2EZxAAA="
SELECT_FIELDS = "id,displayName"


def get_token():
    url = f"https://login.microsoftonline.com/{TENANT_ID}/oauth2/v2.0/token"
    result = subprocess.run(
        ["curl", "-s", "-X", "POST", url,
         "-H", "Content-Type: application/x-www-form-urlencoded",
         "-d", f"client_id={CLIENT_ID}&scope={SCOPE}&client_secret={CLIENT_SECRET}&grant_type=client_credentials"],
        capture_output=True, text=True
    )
    data = json.loads(result.stdout)
    if "access_token" not in data:
        print(f"[ERROR] Failed to get token: {data}", flush=True)
        sys.exit(1)
    return data["access_token"]


def graph_get(token, url):
    result = subprocess.run(
        ["curl", "-s", "-X", "GET", url,
         "-H", f"Authorization: Bearer {token}",
         "-H", "Content-Type: application/json"],
        capture_output=True, text=True
    )
    return json.loads(result.stdout)


def main():
    print("=" * 60, flush=True)
    print("STEP 5: Verify deduplication", flush=True)
    print("=" * 60, flush=True)

    token = get_token()
    print("[OK] Token acquired", flush=True)

    # Pull all contacts (just id and displayName for speed)
    contacts = []
    url = f"https://graph.microsoft.com/v1.0/users/{USER}/contactFolders/{FOLDER_ID}/contacts?$top=100&$select={SELECT_FIELDS}"
    page = 1
    while url:
        data = graph_get(token, url)
        if "value" not in data:
            print(f"[ERROR] {data}", flush=True)
            break
        contacts.extend(data["value"])
        if page % 20 == 0:
            print(f"  Page {page}, total so far: {len(contacts)}", flush=True)
        url = data.get("@odata.nextLink")
        page += 1
        if page % 50 == 0:
            token = get_token()

    new_count = len(contacts)
    old_count = 10404

    print(f"\n{'=' * 60}", flush=True)
    print(f"VERIFICATION RESULTS", flush=True)
    print(f"{'=' * 60}", flush=True)
    print(f"  Old count (pre-dedup):  {old_count}", flush=True)
    print(f"  New count (post-dedup): {new_count}", flush=True)
    print(f"  Contacts removed:       {old_count - new_count}", flush=True)

    # Check for remaining duplicates
    groups = defaultdict(list)
    for c in contacts:
        name = (c.get("displayName") or "").strip().lower()
        if name:
            groups[name].append(c["id"])

    remaining_dups = {name: ids for name, ids in groups.items() if len(ids) >= 2}
    if remaining_dups:
        print(f"\n[WARNING] Remaining duplicate groups: {len(remaining_dups)}", flush=True)
        for name, ids in sorted(remaining_dups.items())[:10]:
            print(f"  {name}: {len(ids)} copies", flush=True)
    else:
        print(f"\n[OK] No duplicates remain! Deduplication complete.", flush=True)

    print(f"\n  Unique contact names: {len(groups)}", flush=True)
    no_name = sum(1 for c in contacts if not (c.get("displayName") or "").strip())
    print(f"  Contacts without name: {no_name}", flush=True)


if __name__ == "__main__":
    main()