138 lines
4.0 KiB
Python
138 lines
4.0 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
导入采购订单参考表 → 更新 products 表的 supplier_name_match 和 cost_price
|
||
匹配规则:
|
||
1. 物料编码 精确匹配 product_code
|
||
2. 若未命中，去掉已知后缀后再匹配
|
||
"""
|
||
import csv
|
||
import pymysql
|
||
import sys
|
||
|
||
CSV_FILE = "/home/gxd/.openclaw/workspace-dingtalk-assistant/media/inbound/采购订单-20260531-1780213945661.csv"
|
||
|
||
# 已知后缀（顺序重要：长后缀优先）
|
||
SUFFIXES = [
|
||
'-FM/GZ', '-TMGJ-NL', '-ALJK-BT', '-ALJK-FM/GZ',
|
||
'-TM-BT', '-TM-PZ', '-TM-CH', '-TM-BQ', '-TM-SSM',
|
||
'-TM-HMT', '-TM-RG', '-TM-GZ', '-TM-FM/GZ',
|
||
'-PDD-BT', '-PDD-PZ', '-PDD-CH', '-PDD-HMT',
|
||
'-NL', '-BT', '-PZ', '-CH', '-BQ', '-SSM', '-HMT',
|
||
'-RG', '-GZ', '-JD', '-PDD', '-ALJK', '-TM',
|
||
'-WPH', '-DW', '-WPH-BT', '-WPH-PZ', '-WPH-CH', '-WPH-BQ',
|
||
'-WPH-MD', '-WPH-RG',
|
||
]
|
||
|
||
def strip_suffix(code):
|
||
"""去掉已知后缀，返回 base_code；没有匹配返回原 code"""
|
||
code = code.strip()
|
||
for s in SUFFIXES:
|
||
if code.endswith(s):
|
||
base = code[:-len(s)]
|
||
if base:
|
||
return base
|
||
return code
|
||
|
||
|
||
def main():
|
||
conn = pymysql.connect(
|
||
host="127.0.0.1",
|
||
port=3306,
|
||
user="dy_app",
|
||
password="dy_data_2026",
|
||
database="dy_data",
|
||
charset="utf8mb4"
|
||
)
|
||
cur = conn.cursor()
|
||
|
||
# 加载所有 product_code → id 映射
|
||
cur.execute("SELECT product_code, id FROM products")
|
||
all_products = {}
|
||
exact_index = {}
|
||
for code, pid in cur.fetchall():
|
||
code = code.strip()
|
||
all_products[code] = pid
|
||
exact_index[code] = pid
|
||
|
||
print(f"DB 中产品总数: {len(all_products)}")
|
||
|
||
# 读取 CSV
|
||
csv_rows = []
|
||
with open(CSV_FILE, encoding="utf-8-sig") as f:
|
||
reader = csv.DictReader(f)
|
||
for row in reader:
|
||
code = row["物料编码"].strip()
|
||
supplier = row["供应商"].strip()
|
||
price_str = row["含税单价"].strip()
|
||
try:
|
||
price = float(price_str) if price_str else None
|
||
except ValueError:
|
||
price = None
|
||
csv_rows.append({
|
||
"code": code,
|
||
"supplier": supplier,
|
||
"price": price,
|
||
})
|
||
|
||
print(f"CSV 总行数: {len(csv_rows)}")
|
||
print(f"CSV 唯一物料编码数: {len(set(r['code'] for r in csv_rows))}")
|
||
|
||
# 统计匹配
|
||
exact_hits = 0
|
||
prefix_hits = 0
|
||
no_hits = 0
|
||
|
||
# 批量更新
|
||
update_sql = "UPDATE products SET supplier_name_match=%s, cost_price=%s WHERE id=%s"
|
||
updates = []
|
||
seen_products = set()
|
||
|
||
for row in csv_rows:
|
||
code = row["code"]
|
||
# 1. 精确匹配
|
||
if code in exact_index:
|
||
pid = exact_index[code]
|
||
match_type = "exact"
|
||
else:
|
||
# 2. 剥离后缀后匹配
|
||
base = strip_suffix(code)
|
||
if base in exact_index:
|
||
pid = exact_index[base]
|
||
match_type = "prefix"
|
||
else:
|
||
# no match
|
||
no_hits += 1
|
||
continue
|
||
|
||
if match_type == "exact":
|
||
exact_hits += 1
|
||
else:
|
||
prefix_hits += 1
|
||
|
||
# 同一个 product 可能被 CSV 多行命中；保留最后一条（或可按需取最小价格）
|
||
updates.append((row["supplier"], row["price"], pid))
|
||
seen_products.add(pid)
|
||
|
||
print(f"\n======== 匹配结果 ========")
|
||
print(f"精确匹配: {exact_hits}")
|
||
print(f"后缀剥离后匹配: {prefix_hits}")
|
||
print(f"未匹配: {no_hits}")
|
||
print(f"涉及去重后产品数: {len(seen_products)}")
|
||
|
||
# 执行更新
|
||
updated = 0
|
||
batch_size = 500
|
||
for i in range(0, len(updates), batch_size):
|
||
batch = updates[i:i+batch_size]
|
||
cur.executemany(update_sql, batch)
|
||
conn.commit()
|
||
updated += len(batch)
|
||
print(f" 已更新 {updated}/{len(updates)}")
|
||
|
||
conn.close()
|
||
print(f"\n✅ 完成！共更新 {updated} 条记录")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|