feat: 益选 OCR 订单处理系统初始提交
- 智能供应商识别（蓉城易购/烟草/杨碧月/通用） - 百度 OCR 表格识别集成 - 规则引擎（列映射/数据清洗/单位转换/规格推断） - 条码映射管理与云端同步（Gitea REST API） - 云端同步支持：条码映射、供应商配置、商品资料、采购模板 - 拖拽一键处理（图片→OCR→Excel→合并） - 191 个单元测试 - 移除无用的模板管理功能 - 清理 IDE 产物目录 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,214 @@
|
||||
"""
|
||||
商品资料 SQLite 数据库
|
||||
|
||||
将商品资料 (条码/名称/进货价/单位) 存储在 SQLite 中，
|
||||
支持从 Excel 自动导入和按条码快速查询。
|
||||
"""
|
||||
|
||||
import os
|
||||
import sqlite3
|
||||
from datetime import datetime
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from ..utils.log_utils import get_logger
|
||||
from ..utils.file_utils import smart_read_excel
|
||||
from ...core.handlers.column_mapper import ColumnMapper
|
||||
|
||||
logger = get_logger(__name__)
|
||||
|
||||
|
||||
class ProductDatabase:
|
||||
"""商品资料 SQLite 数据库"""
|
||||
|
||||
SCHEMA = """
|
||||
CREATE TABLE IF NOT EXISTS products (
|
||||
barcode TEXT PRIMARY KEY,
|
||||
name TEXT DEFAULT '',
|
||||
price REAL DEFAULT 0.0,
|
||||
unit TEXT DEFAULT '',
|
||||
updated_at TEXT
|
||||
);
|
||||
"""
|
||||
|
||||
def __init__(self, db_path: str, excel_source: str):
|
||||
"""初始化数据库，如果 SQLite 不存在则自动从 Excel 导入
|
||||
|
||||
Args:
|
||||
db_path: SQLite 数据库文件路径
|
||||
excel_source: 商品资料 Excel 文件路径
|
||||
"""
|
||||
self.db_path = db_path
|
||||
self.excel_source = excel_source
|
||||
self._ensure_db()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
return sqlite3.connect(self.db_path)
|
||||
|
||||
def _ensure_db(self):
|
||||
"""确保数据库存在，不存在则从 Excel 导入"""
|
||||
if os.path.exists(self.db_path):
|
||||
return
|
||||
|
||||
if not os.path.exists(self.excel_source):
|
||||
logger.warning(f"商品资料 Excel 不存在，跳过导入: {self.excel_source}")
|
||||
self._create_empty_db()
|
||||
return
|
||||
|
||||
logger.info(f"首次运行，从 Excel 导入商品资料: {self.excel_source}")
|
||||
os.makedirs(os.path.dirname(self.db_path), exist_ok=True)
|
||||
self._create_empty_db()
|
||||
count = self.import_from_excel(self.excel_source)
|
||||
logger.info(f"商品资料导入完成: {count} 条记录")
|
||||
|
||||
def _create_empty_db(self):
|
||||
"""创建空数据库"""
|
||||
conn = self._connect()
|
||||
try:
|
||||
conn.executescript(self.SCHEMA)
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
def import_from_excel(self, excel_path: str) -> int:
|
||||
"""从 Excel 导入商品资料
|
||||
|
||||
Args:
|
||||
excel_path: Excel 文件路径
|
||||
|
||||
Returns:
|
||||
导入的记录数
|
||||
"""
|
||||
df = smart_read_excel(excel_path)
|
||||
if df is None or df.empty:
|
||||
logger.warning(f"Excel 文件为空或读取失败: {excel_path}")
|
||||
return 0
|
||||
|
||||
# 查找条码列
|
||||
barcode_col = ColumnMapper.find_column(list(df.columns), 'barcode')
|
||||
if not barcode_col:
|
||||
logger.error(f"Excel 中未找到条码列: {list(df.columns)}")
|
||||
return 0
|
||||
|
||||
# 查找进货价列
|
||||
price_col = ColumnMapper.find_column(list(df.columns), 'unit_price')
|
||||
# 进货价可能没有标准别名，补充查找
|
||||
if not price_col:
|
||||
for col in df.columns:
|
||||
col_str = str(col).strip()
|
||||
if '进货价' in col_str:
|
||||
price_col = col
|
||||
break
|
||||
|
||||
# 查找名称列和单位列 (可选)
|
||||
name_col = ColumnMapper.find_column(list(df.columns), 'name')
|
||||
unit_col = ColumnMapper.find_column(list(df.columns), 'unit')
|
||||
|
||||
now = datetime.now().isoformat()
|
||||
rows = []
|
||||
for _, row in df.iterrows():
|
||||
barcode = str(row.get(barcode_col, '')).strip()
|
||||
if not barcode or barcode == 'nan':
|
||||
continue
|
||||
|
||||
price = 0.0
|
||||
if price_col:
|
||||
try:
|
||||
p = row.get(price_col)
|
||||
if p is not None and str(p).strip() not in ('', 'nan', 'None'):
|
||||
price = float(p)
|
||||
except (ValueError, TypeError):
|
||||
pass
|
||||
|
||||
name = str(row.get(name_col, '')).strip() if name_col else ''
|
||||
if name == 'nan':
|
||||
name = ''
|
||||
unit = str(row.get(unit_col, '')).strip() if unit_col else ''
|
||||
if unit == 'nan':
|
||||
unit = ''
|
||||
|
||||
rows.append((barcode, name, price, unit, now))
|
||||
|
||||
if not rows:
|
||||
logger.warning(f"Excel 中未解析出有效记录: {excel_path}")
|
||||
return 0
|
||||
|
||||
conn = self._connect()
|
||||
try:
|
||||
conn.executemany(
|
||||
"INSERT OR REPLACE INTO products (barcode, name, price, unit, updated_at) "
|
||||
"VALUES (?, ?, ?, ?, ?)",
|
||||
rows
|
||||
)
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
return len(rows)
|
||||
|
||||
def reimport(self) -> int:
|
||||
"""重新从 Excel 导入（清空现有数据后重新导入）
|
||||
|
||||
Returns:
|
||||
导入的记录数
|
||||
"""
|
||||
conn = self._connect()
|
||||
try:
|
||||
conn.execute("DELETE FROM products")
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
return self.import_from_excel(self.excel_source)
|
||||
|
||||
def get_price(self, barcode: str) -> Optional[float]:
|
||||
"""按条码查询进货价
|
||||
|
||||
Args:
|
||||
barcode: 商品条码
|
||||
|
||||
Returns:
|
||||
进货价，未找到返回 None
|
||||
"""
|
||||
conn = self._connect()
|
||||
try:
|
||||
cursor = conn.execute(
|
||||
"SELECT price FROM products WHERE barcode = ?",
|
||||
(str(barcode).strip(),)
|
||||
)
|
||||
row = cursor.fetchone()
|
||||
return row[0] if row else None
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
def get_prices(self, barcodes: List[str]) -> Dict[str, float]:
|
||||
"""批量查询进货价
|
||||
|
||||
Args:
|
||||
barcodes: 条码列表
|
||||
|
||||
Returns:
|
||||
{条码: 进货价} 字典，未找到的不包含
|
||||
"""
|
||||
if not barcodes:
|
||||
return {}
|
||||
|
||||
conn = self._connect()
|
||||
try:
|
||||
placeholders = ','.join('?' * len(barcodes))
|
||||
cursor = conn.execute(
|
||||
f"SELECT barcode, price FROM products WHERE barcode IN ({placeholders})",
|
||||
[str(b).strip() for b in barcodes]
|
||||
)
|
||||
return {row[0]: row[1] for row in cursor.fetchall()}
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
def count(self) -> int:
|
||||
"""返回商品总数"""
|
||||
conn = self._connect()
|
||||
try:
|
||||
cursor = conn.execute("SELECT COUNT(*) FROM products")
|
||||
return cursor.fetchone()[0]
|
||||
finally:
|
||||
conn.close()
|
||||
Reference in New Issue
Block a user