Files
Mog-Squire/scripts/load_recipes_v2_to_db.py
2025-07-07 13:39:46 +01:00

168 lines
4.8 KiB
Python

#!/usr/bin/env python3
"""Load <Craft>_v2.csv into PostgreSQL.
Usage:
python load_recipes_v2_to_db.py <CRAFT>
The script drop-creates table `recipes_<craft>` (lowercased) with the generic
v2 schema, then bulk-loads from the CSV produced by recipes_to_csv_v2.py.
"""
from __future__ import annotations
import argparse
import asyncio
import csv
import json
import pathlib
import re
from typing import Dict
import asyncpg
PROJECT_ROOT = pathlib.Path(__file__).resolve().parents[1]
CONF_PATH = PROJECT_ROOT / "db.conf"
DATASETS_DIR = PROJECT_ROOT / "datasets"
RE_KEY = re.compile(r"^([A-Z0-9_]+)=(.*)$")
# ---------------------------------------------------------------------------
# Category mapping
# ---------------------------------------------------------------------------
CATEGORY_RANGES = [
("Amateur", 1, 10),
("Recruit", 8, 20),
("Initiate", 18, 30),
("Novice", 28, 40),
("Apprentice", 38, 50),
("Journeyman", 48, 60),
("Craftsman", 58, 70),
("Artisan", 68, 80),
("Adept", 78, 90),
("Veteran", 88, 100),
("Expert", 98, 110),
("Authority", 111, 120),
]
def category_for_level(level: int) -> str:
for name, lo, hi in CATEGORY_RANGES:
if lo <= level <= hi:
return name
return "Unknown"
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def parse_db_conf(path: pathlib.Path) -> Dict[str, str]:
conf: Dict[str, str] = {}
for line in path.read_text().splitlines():
line = line.strip()
if not line or line.startswith('#'):
continue
if (m := RE_KEY.match(line)):
k, v = m.group(1), m.group(2).strip().strip("'\"")
conf[k] = v
return conf
async def recreate_table(conn: asyncpg.Connection, craft: str):
table = f"recipes_{craft.lower()}"
await conn.execute(f"DROP TABLE IF EXISTS {table};")
await conn.execute(
f"""
CREATE TABLE {table} (
id SERIAL PRIMARY KEY,
category TEXT NOT NULL,
level INT NOT NULL,
subcrafts JSONB,
name TEXT NOT NULL,
crystal TEXT NOT NULL,
key_item TEXT,
ingredients JSONB,
hq_yields JSONB
);
"""
)
async def insert_csv(conn: asyncpg.Connection, craft: str, csv_path: pathlib.Path):
table = f"recipes_{craft.lower()}"
with csv_path.open(encoding="utf-8") as f:
reader = csv.DictReader(f)
records = []
for row in reader:
records.append(
(
category_for_level(int(row["level"])),
int(row["level"]),
json.dumps(json.loads(row["subcrafts"] or "[]")),
row["name"],
row["crystal"],
row["key_item"] or None,
json.dumps(json.loads(row["ingredients"] or "[]")),
json.dumps(json.loads(row["hq_yields"] or "[]")),
)
)
await conn.copy_records_to_table(
table,
records=records,
columns=[
"category",
"level",
"subcrafts",
"name",
"crystal",
"key_item",
"ingredients",
"hq_yields",
],
)
# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------
async def process_craft(conn: asyncpg.Connection, craft: str):
csv_path = DATASETS_DIR / f"{craft}_v2.csv"
if not csv_path.exists():
print(f"CSV not found for {craft}, skipping.")
return
await recreate_table(conn, craft)
await insert_csv(conn, craft, csv_path)
print(f"Loaded {craft} -> recipes_{craft.lower()} table.")
async def main_async(craft: str | None):
conf = parse_db_conf(CONF_PATH)
conn = await asyncpg.connect(
host=conf["PSQL_HOST"],
port=int(conf["PSQL_PORT"]),
user=conf["PSQL_USER"],
password=conf["PSQL_PASSWORD"],
database=conf["PSQL_DBNAME"],
)
try:
if craft:
await process_craft(conn, craft)
else:
# Scan datasets dir
for p in DATASETS_DIR.glob("*_v2.csv"):
c = p.stem.replace("_v2", "")
await process_craft(conn, c)
finally:
await conn.close()
def main() -> None:
p = argparse.ArgumentParser(description="Load <Craft>_v2.csv into DB")
p.add_argument("craft", nargs="?", help="Craft name; if omitted, load all *_v2.csv files")
args = p.parse_args()
craft_arg = args.craft.strip() if args.craft else None
asyncio.run(main_async(craft_arg))
if __name__ == "__main__":
main()