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>
73 lines
2.4 KiB
Python
73 lines
2.4 KiB
Python
"""
|
|
Environment selection for the migration scripts.
|
|
|
|
Every transform is environment-agnostic: it reads the staged Parquet (same for
|
|
all environments) and writes to whichever database `--env` selects. The target
|
|
is defined entirely by `deploy/.env.<env>` (the same file Portainer is fed at
|
|
deploy time), whose `DATABASE_URL` is the single source of truth for host /
|
|
port / credentials / database.
|
|
|
|
Reproduce the whole migration in a new environment (e.g. prod) by:
|
|
1. deploy the DB stack for that env (deploy/jorgecuadros-db.stack.yml)
|
|
2. write deploy/.env.<env> with its DATABASE_URL
|
|
3. push the schema: DATABASE_URL=... npx prisma@5 db push --schema=packages/database/prisma/schema.prisma
|
|
4. run: ./.venv/bin/python run_all.py --env <env>
|
|
|
|
Usage in a script:
|
|
from dbenv import connect, env_arg
|
|
env = env_arg() # --env dev|prod (default dev)
|
|
conn = connect(env)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
from pathlib import Path
|
|
from urllib.parse import unquote, urlparse
|
|
|
|
import pymysql
|
|
|
|
REPO = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
def load_env(env: str) -> dict:
|
|
f = REPO / "deploy" / f".env.{env}"
|
|
if not f.exists():
|
|
raise SystemExit(
|
|
f"missing {f} — deploy the '{env}' DB stack and write its .env first "
|
|
f"(see dbenv.py header)."
|
|
)
|
|
out = {}
|
|
for line in f.read_text().splitlines():
|
|
line = line.strip()
|
|
if line and not line.startswith("#") and "=" in line:
|
|
k, v = line.split("=", 1)
|
|
out[k] = v
|
|
if "DATABASE_URL" not in out:
|
|
raise SystemExit(f"{f} has no DATABASE_URL")
|
|
return out
|
|
|
|
|
|
def connect(env: str):
|
|
url = load_env(env)["DATABASE_URL"]
|
|
u = urlparse(url) # mysql://user:pass@host:port/db
|
|
return pymysql.connect(
|
|
host=u.hostname,
|
|
port=u.port or 3306,
|
|
user=unquote(u.username or ""),
|
|
password=unquote(u.password or ""),
|
|
database=(u.path or "/").lstrip("/"),
|
|
autocommit=False,
|
|
charset="utf8mb4",
|
|
)
|
|
|
|
|
|
def env_arg(extra_args=None) -> str:
|
|
"""Parse --env (default 'dev') and return it. Scripts that need more args
|
|
can pass an argparse parser via extra_args(parser)."""
|
|
p = argparse.ArgumentParser()
|
|
p.add_argument("--env", default="dev", help="target environment (dev|prod|...): reads deploy/.env.<env>")
|
|
if extra_args:
|
|
extra_args(p)
|
|
return p.parse_args().env
|