claudetools/temp/bardach_temp_check_current.py

"""Check current state of Bardach Temp contacts folder and compare to previous snapshot."""
import subprocess, json, sys, os
from collections import Counter, defaultdict

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

SELECT = ("id,displayName,givenName,surname,emailAddresses,"
          "homePhones,businessPhones,companyName,jobTitle,"
          "personalNotes,lastModifiedDateTime")

# --- 1. Get token ---
r = 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)
tok_data = json.loads(r.stdout)
if 'access_token' not in tok_data:
    print(f"[ERROR] Token failed: {tok_data.get('error_description', tok_data)}")
    sys.exit(1)
token = tok_data['access_token']
print("[OK] Token acquired")

# --- 2. Get Temp folder ID ---
r2 = subprocess.run(['curl', '-s', '-H', f'Authorization: Bearer {token}',
    f'https://graph.microsoft.com/v1.0/users/{USER}/contactFolders?$select=displayName,id'],
    capture_output=True, text=True)
folders = json.loads(r2.stdout).get('value', [])
temp_id = None
for f in folders:
    if f['displayName'] == 'Temp':
        temp_id = f['id']
        break
if not temp_id:
    print("[ERROR] Temp folder not found. Folders:", [f['displayName'] for f in folders])
    sys.exit(1)
print(f"[OK] Temp folder ID: {temp_id[:20]}...")

# --- 3. Pull ALL contacts with pagination ---
print("Pulling Temp contacts...")
url = f"https://graph.microsoft.com/v1.0/users/{USER}/contactFolders/{temp_id}/contacts?$top=100&$select={SELECT}"
all_contacts = []
page = 0

while url:
    page += 1
    r = subprocess.run(['curl', '-s', '-H', f'Authorization: Bearer {token}', url],
                      capture_output=True, text=True)
    data = json.loads(r.stdout)
    if 'error' in data:
        print(f"[ERROR] Page {page}: {data['error'].get('message','')[:200]}")
        break
    items = data.get('value', [])
    all_contacts.extend(items)
    url = data.get('@odata.nextLink')
    if page % 10 == 0:
        print(f"  Page {page}: {len(all_contacts)} contacts so far...")
    if not items:
        break

print(f"[OK] Total Temp contacts pulled: {len(all_contacts)} ({page} pages)")

# --- 4. Duplicate analysis ---
print(f"\n{'='*60}")
print("DUPLICATE ANALYSIS BY displayName")
print(f"{'='*60}")

name_groups = defaultdict(list)
no_name_contacts = []
for c in all_contacts:
    name = (c.get('displayName') or '').strip()
    if name:
        name_groups[name.lower()].append(c)
    else:
        no_name_contacts.append(c)

unique_names = len(name_groups)
dupe_names = {k: v for k, v in name_groups.items() if len(v) > 1}
single_names = {k: v for k, v in name_groups.items() if len(v) == 1}
total_dupe_entries = sum(len(v) for v in dupe_names.values())
total_removable = sum(len(v) - 1 for v in dupe_names.values())

print(f"Total contacts:              {len(all_contacts)}")
print(f"Contacts with no name:       {len(no_name_contacts)}")
print(f"Unique display names:        {unique_names}")
print(f"  - Names appearing once:    {len(single_names)}")
print(f"  - Names with duplicates:   {len(dupe_names)}")
print(f"Total entries in dupe groups: {total_dupe_entries}")
print(f"Removable duplicates:        {total_removable}")
print(f"Estimated after dedup:       {len(single_names) + len(dupe_names) + len(no_name_contacts)}")

# Duplicate distribution
dupe_dist = Counter(len(v) for v in dupe_names.values())
print(f"\nDuplicate distribution (how many names appear N times):")
for count, num_names in sorted(dupe_dist.items()):
    print(f"  {count}x: {num_names} names")

# Top 20 most duplicated
sorted_dupes = sorted(dupe_names.items(), key=lambda x: -len(x[1]))
print(f"\nTop 20 most duplicated names:")
print(f"  {'Count':<6} {'Name':<35} {'Emails'}")
print(f"  {'-'*5:<6} {'-'*34:<35} {'-'*30}")
for name, contacts in sorted_dupes[:20]:
    emails = set()
    for c in contacts:
        for e in c.get('emailAddresses', []):
            if e.get('address'):
                emails.add(e['address'].lower())
    email_str = ', '.join(sorted(emails)[:3]) if emails else '(no email)'
    # Grab original-case name from first contact
    orig_name = contacts[0].get('displayName', name)
    print(f"  {len(contacts):<6} {orig_name[:34]:<35} {email_str[:60]}")

# --- 5. Compare to previous snapshot ---
print(f"\n{'='*60}")
print("COMPARISON TO PREVIOUS SNAPSHOT")
print(f"{'='*60}")

prev_file = 'D:/ClaudeTools/temp/bardach_temp_all.json'
if os.path.exists(prev_file):
    with open(prev_file, 'r') as f:
        prev_contacts = json.load(f)
    prev_count = len(prev_contacts)
    curr_count = len(all_contacts)
    diff = curr_count - prev_count
    sign = '+' if diff > 0 else ''
    print(f"Previous count: {prev_count}")
    print(f"Current count:  {curr_count}")
    print(f"Difference:     {sign}{diff}")

    # Check IDs overlap
    prev_ids = set(c.get('id') for c in prev_contacts)
    curr_ids = set(c.get('id') for c in all_contacts)
    removed = prev_ids - curr_ids
    added = curr_ids - prev_ids
    unchanged = prev_ids & curr_ids
    print(f"\nBy contact ID:")
    print(f"  Still present (unchanged ID): {len(unchanged)}")
    print(f"  Removed since last snapshot:  {len(removed)}")
    print(f"  New since last snapshot:      {len(added)}")
else:
    print(f"[WARNING] Previous file not found: {prev_file}")
    print("No comparison available.")

print(f"\n[INFO] Script complete.")