feat: support both productionID and order number input formats
- Add identify_input_type() function to detect input format: - production_id: 2-digit + 1-letter + serial (e.g., 25A1, 25A12345) - order_number: SC + 14 digits (e.g., SC70202602120120) - Refactor MaterialStatusValidator to intelligently handle both input types in validate_from_database() and validate_from_database_enhanced() - Update log messages to reflect the new dual-input capability Co-Authored-By: Claude (glm-5) <noreply@anthropic.com>
This commit is contained in:
@@ -1,35 +1,62 @@
|
||||
"""
|
||||
生产订单号查询组件
|
||||
从 ProductionID.txt 读取总排号,查询数据库获取生产订单号
|
||||
从 ProductionID.txt 读取总排号或生产订单号,智能识别并处理
|
||||
"""
|
||||
|
||||
import re
|
||||
from db.connection import get_connection
|
||||
from config.schema import DatabaseType
|
||||
from config.loader import ConfigLoader
|
||||
|
||||
|
||||
def read_production_ids(file_path):
|
||||
def identify_input_type(input_str: str) -> str:
|
||||
"""
|
||||
读取 ProductionID.txt 文件,获取总排号列表
|
||||
识别输入字符串的类型
|
||||
|
||||
Args:
|
||||
file_path: ProductionID.txt 文件路径
|
||||
input_str: 输入字符串
|
||||
|
||||
Returns:
|
||||
总排号列表
|
||||
"production_id": 总排号格式 (2位数字 + 1位字母 + 流水号)
|
||||
"order_number": 生产订单号格式 (SC + 14位数字)
|
||||
"unknown": 无法识别
|
||||
"""
|
||||
input_str = input_str.strip()
|
||||
|
||||
# 生产订单号: SC + 14位数字
|
||||
if re.match(r"^SC\d{14}$", input_str):
|
||||
return "order_number"
|
||||
|
||||
# 总排号: 2位数字 + 1位字母 + 流水号(1-6位数字)
|
||||
if re.match(r"^\d{2}[A-Za-z]\d{1,6}$", input_str):
|
||||
return "production_id"
|
||||
|
||||
return "unknown"
|
||||
|
||||
|
||||
def read_production_ids(file_path):
|
||||
"""
|
||||
读取输入文件,获取输入项列表
|
||||
|
||||
Args:
|
||||
file_path: 输入文件路径
|
||||
|
||||
Returns:
|
||||
输入项列表(可能是总排号或生产订单号)
|
||||
"""
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
# 去除空白行和空格
|
||||
production_ids = [line.strip() for line in f if line.strip()]
|
||||
return production_ids
|
||||
items = [line.strip() for line in f if line.strip()]
|
||||
return items
|
||||
|
||||
|
||||
def query_production_order_numbers(production_ids):
|
||||
def _query_order_numbers_from_db(production_ids, db_type):
|
||||
"""
|
||||
根据总排号列表,从数据库查询生产订单号
|
||||
根据总排号列表从数据库查询生产订单号(内部函数)
|
||||
|
||||
Args:
|
||||
production_ids: 总排号列表
|
||||
db_type: 数据库类型
|
||||
|
||||
Returns:
|
||||
生产订单号列表
|
||||
@@ -37,10 +64,6 @@ def query_production_order_numbers(production_ids):
|
||||
if not production_ids:
|
||||
return []
|
||||
|
||||
# 获取当前数据库类型
|
||||
app_config = ConfigLoader.load()
|
||||
db_type = app_config.database.db_type
|
||||
|
||||
# SQL Server 限制每个查询最多 2100 个参数
|
||||
BATCH_SIZE = 2000
|
||||
all_results = []
|
||||
@@ -48,7 +71,7 @@ def query_production_order_numbers(production_ids):
|
||||
# 分批查询
|
||||
for i in range(0, len(production_ids), BATCH_SIZE):
|
||||
batch = production_ids[i : i + BATCH_SIZE]
|
||||
|
||||
|
||||
with get_connection() as conn:
|
||||
# 获取正确的占位符
|
||||
placeholder = conn.get_placeholder()
|
||||
@@ -76,3 +99,41 @@ def query_production_order_numbers(production_ids):
|
||||
all_results.extend(batch_numbers)
|
||||
|
||||
return all_results
|
||||
|
||||
|
||||
def query_production_order_numbers(inputs):
|
||||
"""
|
||||
根据输入列表,智能处理并返回生产订单号列表
|
||||
|
||||
对于 productionID(总排号):查询数据库获取生产订单号
|
||||
对于生产订单号:直接使用
|
||||
|
||||
Args:
|
||||
inputs: 输入项列表(可能是总排号或生产订单号)
|
||||
|
||||
Returns:
|
||||
生产订单号列表
|
||||
"""
|
||||
if not inputs:
|
||||
return []
|
||||
|
||||
production_ids = [] # 需要查询数据库的
|
||||
order_numbers = [] # 直接使用的
|
||||
|
||||
for item in inputs:
|
||||
input_type = identify_input_type(item)
|
||||
if input_type == "order_number":
|
||||
order_numbers.append(item)
|
||||
elif input_type == "production_id":
|
||||
production_ids.append(item)
|
||||
|
||||
# 获取当前数据库类型
|
||||
app_config = ConfigLoader.load()
|
||||
db_type = app_config.database.db_type
|
||||
|
||||
# 查询数据库获取总排号对应的生产订单号
|
||||
if production_ids:
|
||||
db_order_numbers = _query_order_numbers_from_db(production_ids, db_type)
|
||||
order_numbers.extend(db_order_numbers)
|
||||
|
||||
return order_numbers
|
||||
|
||||
@@ -5,9 +5,14 @@
|
||||
支持两种数据源:
|
||||
1. Excel 文件(原有方式)
|
||||
2. 数据库驱动(新增方式)
|
||||
|
||||
支持两种输入格式:
|
||||
1. productionID(总排号): 2位数字 + 1位字母 + 流水号 (如 25A1, 25A12345)
|
||||
2. 生产订单号: SC + 14位数字 (如 SC00000000000001)
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import pandas as pd
|
||||
from typing import List, Dict, Any, Optional, Set
|
||||
from dataclasses import dataclass
|
||||
@@ -221,6 +226,31 @@ class MaterialStatusValidator:
|
||||
|
||||
# ==================== DATABASE-DRIVEN VALIDATION ====================
|
||||
|
||||
@staticmethod
|
||||
def _identify_input_type(input_str: str) -> str:
|
||||
"""
|
||||
识别输入字符串的类型
|
||||
|
||||
Args:
|
||||
input_str: 输入字符串
|
||||
|
||||
Returns:
|
||||
"production_id": 总排号格式 (2位数字 + 1位字母 + 流水号)
|
||||
"order_number": 生产订单号格式 (SC + 14位数字)
|
||||
"unknown": 无法识别
|
||||
"""
|
||||
input_str = input_str.strip()
|
||||
|
||||
# 生产订单号: SC + 14位数字
|
||||
if re.match(r"^SC\d{14}$", input_str):
|
||||
return "order_number"
|
||||
|
||||
# 总排号: 2位数字 + 1位字母 + 流水号(1-6位数字)
|
||||
if re.match(r"^\d{2}[A-Za-z]\d{1,6}$", input_str):
|
||||
return "production_id"
|
||||
|
||||
return "unknown"
|
||||
|
||||
def _read_production_ids(self, production_id_file: str) -> List[str]:
|
||||
"""
|
||||
读取 ProductionID.txt 文件
|
||||
@@ -229,34 +259,57 @@ class MaterialStatusValidator:
|
||||
production_id_file: ProductionID.txt 文件路径
|
||||
|
||||
Returns:
|
||||
List[str]: 总排号列表
|
||||
List[str]: 输入项列表(可能是总排号或生产订单号)
|
||||
"""
|
||||
with open(production_id_file, 'r', encoding='utf-8') as f:
|
||||
production_ids = [line.strip() for line in f if line.strip()]
|
||||
return production_ids
|
||||
items = [line.strip() for line in f if line.strip()]
|
||||
return items
|
||||
|
||||
def _get_source_numbers_from_production_ids(
|
||||
self, production_ids: List[str]
|
||||
def _get_source_numbers_from_inputs(
|
||||
self, inputs: List[str]
|
||||
) -> List[str]:
|
||||
"""
|
||||
通过 ProductionID 查询获取 SourceNumber 列表
|
||||
根据输入列表智能获取 SourceNumber(生产订单号)列表
|
||||
|
||||
查询链路:
|
||||
ProductionID (总排号) -> productionContractData.26年压力表合同数据.生产订单号
|
||||
对于 productionID(总排号):查询数据库获取生产订单号
|
||||
对于生产订单号:直接使用
|
||||
|
||||
Args:
|
||||
production_ids: 总排号列表
|
||||
inputs: 输入项列表(可能是总排号或生产订单号)
|
||||
|
||||
Returns:
|
||||
List[str]: 生产订单号列表
|
||||
"""
|
||||
self._print(f"[INFO] 正在查询 {len(production_ids)} 个总排号对应的生产订单号...")
|
||||
production_ids = [] # 需要查询数据库的
|
||||
order_numbers = [] # 直接使用的
|
||||
|
||||
contract_dao = ProductionContractDataDAO()
|
||||
source_numbers = contract_dao.get_source_numbers_by_总排号(production_ids)
|
||||
for item in inputs:
|
||||
input_type = self._identify_input_type(item)
|
||||
if input_type == "order_number":
|
||||
order_numbers.append(item)
|
||||
elif input_type == "production_id":
|
||||
production_ids.append(item)
|
||||
|
||||
self._print(f"[INFO] 找到 {len(source_numbers)} 个唯一的生产订单号")
|
||||
return source_numbers
|
||||
# 统计输入类型
|
||||
if production_ids:
|
||||
self._print(f"[INFO] 识别到 {len(production_ids)} 个总排号")
|
||||
if order_numbers:
|
||||
self._print(f"[INFO] 识别到 {len(order_numbers)} 个生产订单号")
|
||||
|
||||
# 查询数据库获取总排号对应的生产订单号
|
||||
if production_ids:
|
||||
self._print(f"[INFO] 正在查询 {len(production_ids)} 个总排号对应的生产订单号...")
|
||||
contract_dao = ProductionContractDataDAO()
|
||||
db_order_numbers = contract_dao.get_source_numbers_by_总排号(production_ids)
|
||||
self._print(f"[INFO] 从数据库获取到 {len(db_order_numbers)} 个生产订单号")
|
||||
order_numbers.extend(db_order_numbers)
|
||||
|
||||
# 去重
|
||||
unique_order_numbers = list(dict.fromkeys(order_numbers))
|
||||
if len(unique_order_numbers) != len(order_numbers):
|
||||
self._print(f"[INFO] 去重后得到 {len(unique_order_numbers)} 个唯一生产订单号")
|
||||
|
||||
return unique_order_numbers
|
||||
|
||||
def _get_material_names_from_db(
|
||||
self, source_numbers: List[str] = None
|
||||
@@ -292,17 +345,21 @@ class MaterialStatusValidator:
|
||||
|
||||
支持两种模式:
|
||||
1. 全表校验 (full_table=True): 查询整个 DiscreteMaterialPlanData 表
|
||||
2. ProductionID 过滤校验 (production_id_file 指定): 基于 ProductionID.txt 文件过滤
|
||||
2. 输入过滤校验 (production_id_file 指定): 基于输入文件过滤
|
||||
- 支持总排号格式 (如 25A1, 25A12345)
|
||||
- 支持生产订单号格式 (如 SC00000000000001)
|
||||
- 支持混合输入
|
||||
|
||||
查询链路(模式2):
|
||||
ProductionID.txt (总排号)
|
||||
-> productionContractData.26年压力表合同数据.生产订单号 (SourceNumber)
|
||||
输入文件 (总排号或生产订单号)
|
||||
-> 总排号需查询: productionContractData.26年压力表合同数据.生产订单号 (SourceNumber)
|
||||
-> 生产订单号直接使用
|
||||
-> DiscreteMaterialPlanData.SourceNumber
|
||||
-> DiscreteMaterialPlanData.MaterialName
|
||||
-> 对比 MaterialsTypeToBeDeleted.MaterialName
|
||||
|
||||
Args:
|
||||
production_id_file: ProductionID.txt 路径(模式2)
|
||||
production_id_file: 输入文件路径(模式2)
|
||||
full_table: 是否全表校验(模式1)
|
||||
output_file: 输出文件路径
|
||||
|
||||
@@ -322,15 +379,15 @@ class MaterialStatusValidator:
|
||||
self._print("[INFO] 查询 DiscreteMaterialPlanData 表中的所有材料...")
|
||||
material_names = self._get_material_names_from_db(None)
|
||||
elif production_id_file:
|
||||
self._print("\n模式: ProductionID 过滤校验")
|
||||
self._print(f"[INFO] 读取 ProductionID 文件: {production_id_file}")
|
||||
self._print("\n模式: 输入过滤校验")
|
||||
self._print(f"[INFO] 读取输入文件: {production_id_file}")
|
||||
|
||||
# 1. 读取 ProductionID.txt
|
||||
production_ids = self._read_production_ids(production_id_file)
|
||||
self._print(f"[INFO] 读取到 {len(production_ids)} 个总排号")
|
||||
# 1. 读取输入文件
|
||||
inputs = self._read_production_ids(production_id_file)
|
||||
self._print(f"[INFO] 读取到 {len(inputs)} 个输入项")
|
||||
|
||||
# 2. 查询获取 SourceNumbers
|
||||
source_numbers = self._get_source_numbers_from_production_ids(production_ids)
|
||||
# 2. 智能识别并获取 SourceNumbers
|
||||
source_numbers = self._get_source_numbers_from_inputs(inputs)
|
||||
|
||||
# 3. 获取材料名称
|
||||
material_names = self._get_material_names_from_db(source_numbers)
|
||||
@@ -428,10 +485,17 @@ class MaterialStatusValidator:
|
||||
"""
|
||||
Enhanced database validation with complete record information.
|
||||
|
||||
支持两种模式:
|
||||
1. 全表校验 (full_table=True): 查询整个 DiscreteMaterialPlanData 表
|
||||
2. 输入过滤校验 (production_id_file 指定): 基于输入文件过滤
|
||||
- 支持总排号格式 (如 25A1, 25A12345)
|
||||
- 支持生产订单号格式 (如 SC00000000000001)
|
||||
- 支持混合输入
|
||||
|
||||
Args:
|
||||
production_id_file: ProductionID.txt path (for filtered mode)
|
||||
full_table: Whether to query full table (for full table mode)
|
||||
output_file: Output Excel file path
|
||||
production_id_file: 输入文件路径(模式2)
|
||||
full_table: 是否全表校验(模式1)
|
||||
output_file: 输出 Excel 文件路径
|
||||
|
||||
Returns:
|
||||
Tuple of (output_file_path, List[MaterialValidationResult])
|
||||
@@ -459,15 +523,23 @@ class MaterialStatusValidator:
|
||||
if dedup_count > 0:
|
||||
self._print(f"[INFO] 基于 MaterialCode 去重:移除了 {dedup_count} 条重复记录")
|
||||
elif production_id_file:
|
||||
self._print("\n模式: ProductionID 过滤校验")
|
||||
self._print(f"[INFO] 读取 ProductionID 文件: {production_id_file}")
|
||||
self._print("\n模式: 输入过滤校验")
|
||||
self._print(f"[INFO] 读取输入文件: {production_id_file}")
|
||||
|
||||
# 1. Read ProductionID.txt
|
||||
production_ids = self._read_production_ids(production_id_file)
|
||||
self._print(f"[INFO] 读取到 {len(production_ids)} 个总排号")
|
||||
# 1. Read input file
|
||||
inputs = self._read_production_ids(production_id_file)
|
||||
self._print(f"[INFO] 读取到 {len(inputs)} 个输入项")
|
||||
|
||||
# 2. Query SourceNumbers
|
||||
source_numbers = self._get_source_numbers_from_production_ids(production_ids)
|
||||
# 2. Smart identify and get SourceNumbers
|
||||
source_numbers = self._get_source_numbers_from_inputs(inputs)
|
||||
|
||||
if not source_numbers:
|
||||
self._print("\n[ERROR] 校验失败:未找到有效的生产订单号")
|
||||
self._print("[ERROR] 可能原因:")
|
||||
self._print("[ERROR] 1. 总排号在数据库中不存在对应的生产订单号")
|
||||
self._print("[ERROR] 2. 输入的生产订单号格式不正确")
|
||||
self._print("[ERROR] 3. 请检查输入文件内容")
|
||||
return output_file, []
|
||||
|
||||
# 3. Get complete material records with deduplication
|
||||
self._print(f"[INFO] 查询 {len(source_numbers)} 个生产订单对应的完整物料记录(启用 MaterialCode 去重)...")
|
||||
@@ -491,7 +563,7 @@ class MaterialStatusValidator:
|
||||
self._print("[ERROR] 1. 这些生产订单的物料数据还没有提取到数据库")
|
||||
self._print("[ERROR] 2. 请先运行【正式备料计划数据提取】工具")
|
||||
self._print("[ERROR] 3. 提取时勾选【持久化到数据库】选项")
|
||||
self._print("[ERROR] 4. 将这 10 个 ProductionID 的物料数据保存到 DiscreteMaterialPlanData 表")
|
||||
self._print(f"[ERROR] 4. 将这些输入项的物料数据保存到 DiscreteMaterialPlanData 表")
|
||||
else:
|
||||
raise ValueError("必须指定 full_table=True 或提供 production_id_file 参数")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user