claudetools/temp/bardach_dedup_step3b_retry_merge.py

#!/usr/bin/env python3
"""Step 3b: Retry failed merges with phone number limits applied."""

import json
import subprocess
import sys
import time

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"
PLAN_FILE = "D:/ClaudeTools/temp/bardach_dedup_plan.json"
MERGE_RESULTS = "D:/ClaudeTools/temp/bardach_dedup_merge_results.json"
RESULTS_FILE = "D:/ClaudeTools/temp/bardach_dedup_merge_results_retry.json"

PHONE_MAX = 2  # Graph API limit


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}")
        sys.exit(1)
    return data["access_token"]


def patch_contact(token, contact_id, body):
    url = f"https://graph.microsoft.com/v1.0/users/{USER}/contacts/{contact_id}"
    body_json = json.dumps(body)
    result = subprocess.run(
        ["curl", "-s", "-X", "PATCH", url,
         "-H", f"Authorization: Bearer {token}",
         "-H", "Content-Type: application/json",
         "-d", body_json,
         "-w", "\n%{http_code}"],
        capture_output=True, text=True
    )
    lines = result.stdout.strip().rsplit("\n", 1)
    status_code = int(lines[-1]) if len(lines) > 1 else 0
    response_body = lines[0] if len(lines) > 1 else result.stdout
    return status_code, response_body


def truncate_phones(updates):
    """Truncate phone arrays to max allowed by Graph API."""
    for field in ["homePhones", "businessPhones"]:
        if field in updates and len(updates[field]) > PHONE_MAX:
            updates[field] = updates[field][:PHONE_MAX]
    return updates


def main():
    print("=" * 60)
    print("STEP 3b: Retry failed merges with phone limits")
    print("=" * 60)

    # Load the original results to get failed contact names
    with open(MERGE_RESULTS, "r", encoding="utf-8") as f:
        merge_results = json.load(f)
    failed_names = {f["display_name"] for f in merge_results["failure_details"]}
    print(f"[INFO] Failed contacts to retry: {len(failed_names)}")

    # Load the plan to get updates for failed contacts
    with open(PLAN_FILE, "r", encoding="utf-8") as f:
        plan_data = json.load(f)

    to_retry = [e for e in plan_data["plan"]
                if e["display_name"] in failed_names and e["updates_to_apply"]]
    print(f"[INFO] Entries with updates to retry: {len(to_retry)}")

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

    successes = []
    failures = []

    for i, entry in enumerate(to_retry):
        contact_id = entry["keeper_id"]
        updates = truncate_phones(dict(entry["updates_to_apply"]))
        name = entry["display_name"]

        status_code, response = patch_contact(token, contact_id, updates)

        if 200 <= status_code < 300:
            successes.append({"display_name": name, "contact_id": contact_id, "status": status_code})
        else:
            failures.append({"display_name": name, "contact_id": contact_id, "status": status_code, "error": response[:500]})
            print(f"  [WARNING] Retry PATCH failed for '{name}': HTTP {status_code} - {response[:200]}")

        if (i + 1) % 50 == 0:
            print(f"  Progress: {i + 1}/{len(to_retry)}")

    results = {
        "total_retried": len(to_retry),
        "successes": len(successes),
        "failures": len(failures),
        "failure_details": failures
    }
    with open(RESULTS_FILE, "w", encoding="utf-8") as f:
        json.dump(results, f, indent=2, ensure_ascii=False)

    print(f"\n{'=' * 60}")
    print(f"RETRY MERGE RESULTS")
    print(f"{'=' * 60}")
    print(f"  Retried:   {len(to_retry)}")
    print(f"  Successes: {len(successes)}")
    print(f"  Failures:  {len(failures)}")
    print(f"\nCombined totals (original + retry):")
    print(f"  Total merges succeeded: {merge_results['successes'] + len(successes)}")
    print(f"  Total merges failed:    {len(failures)}")


if __name__ == "__main__":
    main()