rmancinasandClaude Opus 4.8
a680ad2bb0
migration/transform_properties.py loads properties, property_services and trust_accounts from staged DATMEX/PROFILE, resolving each property's customer FK through customer_legacy_refs. Services are derived from DATMEX's own account/route/meter fields (the authoritative data); PROFILE flags — merged best-effort on (numer_id,casa,direccion), which matched 1519/1519 — only refine each service's `active`. Trust accounts are 1:1 from DATMEX trust fields; TRUSTVENCE (overlapping) deferred to reconciliation; blobs are step 4. Loaded/validated (dev): 1519 properties (0 orphans, 1 blank id skipped), 3486 services (ELECTRIC 1118 / PROPERTY_TAX 939 / WATER 859 / GAS 335 / OTHER 115 / FEDERAL_ZONE 76 / CABLE 41 / ALARM 3), 553 trust accounts — counts track the PROFILE enrollment flags. Reproducibility (asked: dev must be redoable in prod): - migration/dbenv.py: single DB-target source = deploy/.env.<env>'s DATABASE_URL; connect(env) + env_arg() (--env, default dev). - transform_customers.py / transform_properties.py now take --env instead of hardcoding .env.dev. - migration/run_all.py: runs every step in dependency order against --env (optional --stage re-extracts from Access first). Reproducing dev->prod is `run_all.py --env prod` after deploying the prod stack + prisma db push. All steps are idempotent (truncate+rebuild); re-run yields identical counts. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
64 lines
2.1 KiB
Python
64 lines
2.1 KiB
Python
"""
|
|
Run the full data migration against one environment, in dependency order.
|
|
|
|
Every step is idempotent (truncate + rebuild), so this is safe to re-run. The
|
|
target DB is chosen with --env (reads deploy/.env.<env>); the same staged
|
|
Parquet feeds every environment.
|
|
|
|
Prerequisites (once per environment, NOT done here):
|
|
1. DB stack deployed (deploy/jorgecuadros-db.stack.yml) and deploy/.env.<env> written.
|
|
2. Prisma schema pushed to it:
|
|
DATABASE_URL="<that env's url>" \
|
|
npx prisma@5 db push --schema=packages/database/prisma/schema.prisma
|
|
|
|
Then:
|
|
./.venv/bin/python run_all.py --env dev # data only (staging already present)
|
|
./.venv/bin/python run_all.py --env prod --stage # re-extract from Access first, then load
|
|
|
|
Reproducing dev -> prod is exactly `--env prod` (plus --stage if the staged
|
|
Parquet isn't present on the machine running it).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
HERE = Path(__file__).parent
|
|
PY = sys.executable # the venv python running this orchestrator
|
|
|
|
# Dependency order — extend as later modules land (policies, transactions, bank).
|
|
STEPS = [
|
|
"transform_customers.py", # customers + customer_legacy_refs (everything FKs to these)
|
|
"transform_properties.py", # properties + services + trust accounts
|
|
]
|
|
|
|
|
|
def run(cmd: list[str]) -> None:
|
|
print("+ " + " ".join(cmd), flush=True)
|
|
r = subprocess.run(cmd)
|
|
if r.returncode:
|
|
sys.exit(r.returncode)
|
|
|
|
|
|
def main() -> None:
|
|
ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
ap.add_argument("--env", default="dev", help="target environment (reads deploy/.env.<env>)")
|
|
ap.add_argument("--stage", action="store_true",
|
|
help="re-run the raw staging load first (needs the Access files + mdbtools)")
|
|
args = ap.parse_args()
|
|
|
|
if args.stage:
|
|
run([PY, str(HERE / "load_staging.py"), "--output-dir", str(HERE / "output")])
|
|
|
|
for step in STEPS:
|
|
run([PY, str(HERE / step), "--env", args.env])
|
|
|
|
print(f"\n✓ migration complete for env={args.env}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|