canteen-asset-tracker/scripts/populate_asset_company_place.py

#!/usr/bin/env python3
"""Populate company, place, customer_name on assets from MSFS extraction DB.

Maps each asset's connect_id → msdyn_customerasset → account to get:
  - company   = account name  (customer/location name, e.g. "Jeremy B - 1960 Broadway")
  - place     = city name     (e.g. "Orlando", "Lake Buena Vista")
  - customer_name = account name (same as company, for search/filter)
  - address   = line1 if empty

Skips assets that already have values in these fields.
"""

import sqlite3
import sys
from pathlib import Path

ASSETS_DB = Path.home() / "projects" / "canteen-asset-tracker" / "assets.db"
EXTRACTION_DB = (
    Path.home()
    / "projects"
    / "ms-field-service-extraction"
    / "data-samples"
    / "msfs_backup"
    / "fieldservicecanteen.crm.dynamics.com_9fc6c50c-b097-f011-b4cb-7ced8d1b15a2_data.db"
)


def get_mapping() -> dict[str, dict]:
    """Return {connect_id: {company, place, city, address}} from extraction DB."""
    conn = sqlite3.connect(str(EXTRACTION_DB))
    conn.row_factory = sqlite3.Row
    cur = conn.cursor()

    # We want the account info per customerasset.
    # If multiple customerassets share the same connect_id, pick the one
    # with the most recent createdon date to get freshest account link.
    rows = cur.execute("""
        SELECT
            ca.hsl_connectid,
            COALESCE(ca."msdyn_account!name", a.name, '') AS account_name,
            COALESCE(a.address1_city, '') AS city,
            COALESCE(a.address1_name, '') AS address1_name,
            COALESCE(a.address1_line1, '') AS line1,
            COALESCE(a.address1_line2, '') AS line2
        FROM msdyn_customerasset ca
        LEFT JOIN account a ON ca."msdyn_account!id" = a.accountid
        WHERE ca.hsl_connectid IS NOT NULL AND ca.hsl_connectid != ''
        ORDER BY ca.createdon DESC
    """).fetchall()

    conn.close()

    # Deduplicate: keep first (most recent createdon) per connect_id
    seen: set[str] = set()
    result: dict[str, dict] = {}
    for r in rows:
        cid = r["hsl_connectid"]
        if cid in seen:
            continue
        seen.add(cid)

        # Build address from available parts
        addr_parts = [p for p in [r["line1"], r["line2"]] if p]
        address = ", ".join(addr_parts) if addr_parts else ""

        result[cid] = {
            "company": r["account_name"],
            "place": r["city"],
            "customer_name": r["account_name"],
            "address": address,
        }

    print(f"📡 Loaded {len(result)} connect_id mappings from extraction DB")

    # Also build the branch cache for fallback on unmatched assets
    try:
        sys.path.insert(0, str(Path.home() / "projects" / "canteen-asset-tracker"))
        from server import _build_asset_branch_cache
        branch_cache = _build_asset_branch_cache()
        print(f"📡 Branch cache has {len(branch_cache)} prefix→territory mappings")
    except Exception as e:
        print(f"⚠️  Could not load branch cache: {e}")
        branch_cache = {}

    return result, branch_cache


def main():
    print("🔌 Connecting to assets.db...")
    conn = sqlite3.connect(str(ASSETS_DB))
    conn.row_factory = sqlite3.Row

    # Count assets with empty fields
    stats = conn.execute("""
        SELECT
            COUNT(*) AS total,
            SUM(CASE WHEN company IS NULL OR company = '' THEN 1 ELSE 0 END) AS empty_company,
            SUM(CASE WHEN place IS NULL OR place = '' THEN 1 ELSE 0 END) AS empty_place,
            SUM(CASE WHEN customer_name IS NULL OR customer_name = '' THEN 1 ELSE 0 END) AS empty_customer_name,
            SUM(CASE WHEN address IS NULL OR address = '' THEN 1 ELSE 0 END) AS empty_address
        FROM assets
    """).fetchone()
    print(f"📊 Before update:")
    print(f"   Total assets:       {stats['total']}")
    print(f"   Empty company:      {stats['empty_company']}")
    print(f"   Empty place:        {stats['empty_place']}")
    print(f"   Empty customer_name:{stats['empty_customer_name']}")
    print(f"   Empty address:      {stats['empty_address']}")

    mapping, branch_cache = get_mapping()

    # Fetch all assets with connect_id
    assets = conn.execute("""
        SELECT id, connect_id, company, place, customer_name, address
        FROM assets
        WHERE connect_id IS NOT NULL AND connect_id != ''
    """).fetchall()

    updates = {"company": 0, "place": 0, "customer_name": 0, "address": 0}
    skipped_no_match = 0
    skipped_has_data = 0
    branch_fallback = 0

    update_sqls = {
        "company": "UPDATE assets SET company = ? WHERE id = ?",
        "place": "UPDATE assets SET place = ? WHERE id = ?",
        "customer_name": "UPDATE assets SET customer_name = ? WHERE id = ?",
        "address": "UPDATE assets SET address = ? WHERE id = ?",
    }

    for a in assets:
        info = mapping.get(a["connect_id"])
        if not info:
            # No connect_id match in extraction DB at all
            skipped_no_match += 1
            continue

        # If account name is empty, try branch cache fallback
        if (not a["company"] or not a["company"].strip()) and (not info["company"] or not info["company"].strip()):
            pfx = a["connect_id"][:8]
            branch_name = branch_cache.get(pfx)
            if branch_name:
                info["company"] = branch_name
                info["customer_name"] = branch_name
                branch_fallback += 1

        if a["company"] and a["place"] and a["customer_name"] and a["address"]:
            skipped_has_data += 1
            continue

        batch: list[tuple[str, int]] = []  # (sql, (value, id))

        if (not a["company"] or not a["company"].strip()) and info["company"]:
            batch.append((update_sqls["company"], (info["company"], a["id"])))
            updates["company"] += 1

        if (not a["place"] or not a["place"].strip()) and info["place"]:
            batch.append((update_sqls["place"], (info["place"], a["id"])))
            updates["place"] += 1

        if (not a["customer_name"] or not a["customer_name"].strip()) and info["customer_name"]:
            batch.append((update_sqls["customer_name"], (info["customer_name"], a["id"])))
            updates["customer_name"] += 1

        if (not a["address"] or not a["address"].strip()) and info["address"]:
            batch.append((update_sqls["address"], (info["address"], a["id"])))
            updates["address"] += 1

        for sql, params in batch:
            conn.execute(sql, params)

    conn.commit()
    conn.close()

    print(f"\n✅ Migration complete:")
    print(f"   Matched & updated:  {len(assets) - skipped_no_match - skipped_has_data} assets")
    print(f"   No match in ext DB: {skipped_no_match}")
    print(f"   Already had data:   {skipped_has_data}")
    print(f"   Field updates:")
    for field, count in updates.items():
        print(f"     {field}: {count}")

    # Show some samples
    conn2 = sqlite3.connect(str(ASSETS_DB))
    conn2.row_factory = sqlite3.Row
    samples = conn2.execute("""
        SELECT machine_id, company, place, customer_name, address
        FROM assets
        WHERE company != '' AND place != ''
        LIMIT 5
    """).fetchall()
    conn2.close()
    print(f"\n📋 Sample updated rows:")
    for s in samples:
        print(f"   {s['machine_id']:>25} | company='{s['company']}' | place='{s['place']}'")


if __name__ == "__main__":
    main()