基本满足双边合并功能
This commit is contained in:
711
页面.py
711
页面.py
@ -4,6 +4,7 @@ from tkinter import ttk, filedialog, messagebox, simpledialog
|
|||||||
import os
|
import os
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import re
|
import re
|
||||||
|
from datetime import datetime
|
||||||
|
|
||||||
|
|
||||||
# ==========================================
|
# ==========================================
|
||||||
@ -12,58 +13,113 @@ import re
|
|||||||
|
|
||||||
class DataProcessor:
|
class DataProcessor:
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
# 1. 总表表头 (保持不变，严格去空格)
|
# ==================== 1. 外贸总表表头 ====================
|
||||||
self.columns_general = [
|
self.cols_asd_foreign_general = [
|
||||||
"合同编号", "签署公司", "外贸合同号", "收款情况", "合同签订日期",
|
"合同编号", "签署公司", "外贸合同号", "收款情况", "合同签订日期", "销售员",
|
||||||
"销售员", "最终用户单位", "最终用户信息联系人、电话、邮箱", "最终用户所在地",
|
"最终用户单位", "最终用户信息\n联系人、电话、邮箱", "最终用户所在地",
|
||||||
"厂家", "型号/货号", "合同标的", "数量", "单位", "币种", "折扣率",
|
"厂家", "型号/货号", "合同标的", "数量", "单位", "币种", "折扣率",
|
||||||
"合同", "总合同额", "外购", "已收款", "未收款", "收款日期",
|
"合同额", "总合同额", "外购", "已收款", "未收款", "收款日期",
|
||||||
"最晚发货期", "付款方式", "发货港", "目的港", "发货日期",
|
"最晚发货期", "付款方式", "发货港", "目的港", "发货日期",
|
||||||
"买方单位", "买方信息联系人、电话、邮箱", "收货人信息"
|
"买方单位", "买方信息\n联系人、电话、邮箱", "收货人信息",
|
||||||
|
"转为美元净合同额", "转为美元总合同额"
|
||||||
]
|
]
|
||||||
|
|
||||||
# 内贸总表表头
|
self.cols_nonasd_foreign_general = [
|
||||||
self.columns_domestic_general = [c if c != "外贸合同号" else "内贸合同号" for c in self.columns_general]
|
"合同编号", "签署公司", "外贸合同号", "收款情况", "合同签订日期", "销售员",
|
||||||
|
"最终用户单位", "最终用户信息\n联系人、电话、邮箱", "最终用户所在地",
|
||||||
# 2. [关键修改] 明细表表头 (完全按照你的截图顺序和名称定义)
|
"厂家", "型号/货号", "合同标的", "数量", "单位", "币种", "折扣率",
|
||||||
self.columns_detail = [
|
"合同额", "总合同额", "外购", "已收款", "未收款", "收款日期",
|
||||||
"合同编号", "销售员", "合同标的", "厂家", "货号", "产品描述",
|
"最晚发货期", "付款方式", "发货港", "目的港", "发货日期",
|
||||||
"净合同额美元", "外购", "计算汇率", "外购转美元", "报价总价美元",
|
"买方单位", "买方信息\n联系人、电话、邮箱", "收货人信息",
|
||||||
"数量", "单位", "外币币种", "外币报价单价",
|
"合同币种/美元", "转为美元净合同额", "转为美元总合同额"
|
||||||
"报价RMB单价", "报价RMB总价", "售价RMB单价", "售价RMB总价", "折扣率（％）"
|
|
||||||
]
|
]
|
||||||
|
|
||||||
# OM合同表头 (保持不变)
|
# ==================== 2. 内贸总表表头 ====================
|
||||||
self.columns_om = [
|
self.cols_domestic_general = [
|
||||||
"合同编号", "签署公司", "内贸合同号", "收款情况", "签订日期",
|
"合同编号", "签署公司", "内贸合同号", "收款情况", "签订日期", "销售员",
|
||||||
"销售员", "最终用户单位", "最终用户信息联系人、电话、邮箱", "最终用户所在地",
|
"最终用户单位", "最终用户信息\n联系人、电话、邮箱", "最终用户所在地",
|
||||||
"买方单位", "买方信息联系人、电话、邮箱", "合同标的", "合同总额",
|
"买方单位", "买方信息\n联系人、电话、邮箱",
|
||||||
"已收款", "未收款", "收款日期"
|
"厂家", "型号", "合同标的", "数量", "单位", "折扣率（％）",
|
||||||
|
"合同额", "合同总额", "外购", "付款方式", "最晚发货期",
|
||||||
|
"已收款", "未收款", "收款日期",
|
||||||
|
"转为美元净合同额", "转为美元总合同额"
|
||||||
]
|
]
|
||||||
|
|
||||||
# [修改] 定义需要保留两位小数的金额列 (根据新表头更新)
|
# ==================== 3. 外贸明细表头 ====================
|
||||||
self.money_cols = set([
|
self.cols_foreign_detail = [
|
||||||
"合同", "总合同额", "外购", "已收款", "未收款",
|
"合同编号", "销售员", "合同标的", "厂家", "货号", "产品描述", "数量", "单位",
|
||||||
"净合同额美元", "外购转美元", "报价总价美元",
|
"币种", "报价单价", "报价总价", "销售单价", "销售总价", "折扣率",
|
||||||
"外币报价单价", "报价RMB单价", "报价RMB总价",
|
"外购", "合同币种/美元", "外购转美元", "报价总价美元", "净合同额美元"
|
||||||
"售价RMB单价", "售价RMB总价", "外购产品金额"
|
]
|
||||||
|
|
||||||
|
# ==================== 4. 内贸明细表头 ====================
|
||||||
|
self.cols_domestic_detail = [
|
||||||
|
"合同编号", "销售员", "合同标的", "厂家", "货号", "产品描述", "数量", "单位",
|
||||||
|
"外币币种", "外币报价单价", "报价RMB单价", "报价RMB总价",
|
||||||
|
"售价RMB单价", "售价RMB总价", "折扣率（％）", "外购",
|
||||||
|
"计算汇率", "外购转美元", "报价总价美元", "净合同额美元"
|
||||||
|
]
|
||||||
|
|
||||||
|
# ==================== 5. OM合同表头 ====================
|
||||||
|
self.cols_om = [
|
||||||
|
"合同编号", "签署公司", "内贸合同号", "收款情况", "签订日期", "销售员",
|
||||||
|
"最终用户单位", "最终用户信息\n联系人、电话、邮箱", "最终用户所在地",
|
||||||
|
"买方单位", "买方信息\n联系人、电话、邮箱", "合同标的",
|
||||||
|
"合同总额", "已收款", "未收款", "收款日期"
|
||||||
|
]
|
||||||
|
|
||||||
|
# [逻辑] 只写在“第一行”（单价最高行）的列
|
||||||
|
self.header_only_cols = set([
|
||||||
|
"总合同额", "合同总额", "外购", "付款方式", "最晚发货期",
|
||||||
|
"已收款", "未收款", "收款日期", "收款情况",
|
||||||
|
"转为美元净合同额", "转为美元总合同额"
|
||||||
])
|
])
|
||||||
|
|
||||||
# [修改] 定义需要百分比展示的列 (根据新表头更新)
|
# [逻辑] 金额列 (保留两位小数)
|
||||||
|
self.money_cols = set([
|
||||||
|
"合同额", "总合同额", "合同总额", "外购", "已收款", "未收款",
|
||||||
|
"净合同额美元", "外购转美元", "报价总价美元",
|
||||||
|
"外币报价单价", "报价RMB单价", "报价RMB总价",
|
||||||
|
"售价RMB单价", "售价RMB总价", "外购产品金额",
|
||||||
|
"转为美元净合同额", "转为美元总合同额", "报价单价", "报价总价", "销售单价", "销售总价"
|
||||||
|
])
|
||||||
|
|
||||||
|
# [逻辑] 比率列 (百分比展示)
|
||||||
self.percent_cols = set([
|
self.percent_cols = set([
|
||||||
"折扣率", "折扣率（％）", "计算汇率", "合同币种/美元"
|
"折扣率", "折扣率（％）", "计算汇率", "合同币种/美元"
|
||||||
])
|
])
|
||||||
|
|
||||||
# 旧表头映射字典 (现在代码标准已更新为Excel标准，这个字典主要用于兼容总表的旧名称)
|
# [新增逻辑] 日期列 (需要去除时分秒)
|
||||||
# 注意：明细表现在不需要映射了，因为 self.columns_detail 已经和 Excel 一样了
|
self.date_cols = set([
|
||||||
|
"合同签订日期", "签订日期", "收款日期", "最晚发货期", "发货日期"
|
||||||
|
])
|
||||||
|
|
||||||
|
# [逻辑] 旧表头映射 (用于读取旧Excel时兼容)
|
||||||
self.legacy_map = {
|
self.legacy_map = {
|
||||||
"外币币种": "币种", # 仅用于总表可能的兼容
|
"外币币种": "币种",
|
||||||
"汇率": "计算汇率",
|
"汇率": "计算汇率",
|
||||||
# 如果旧Excel里的总表还在用"折扣率(%)"，映射回总表的"折扣率"
|
"折扣率(%)": "折扣率",
|
||||||
"折扣率(%)": "折扣率"
|
"折扣率（%）": "折扣率（％）",
|
||||||
|
"合同": "合同额"
|
||||||
}
|
}
|
||||||
|
|
||||||
self.source_cols_processed = []
|
# [核心] 构建所有标准列名的快速查找字典 (清洗后的key -> 标准带换行的key)
|
||||||
|
# 目的：无论Excel里是 "最终用户信息联系人..." 还是 "最终用户信息\n联系人...", 都能映射回标准
|
||||||
|
self.standard_col_map = {}
|
||||||
|
all_lists = [
|
||||||
|
self.cols_asd_foreign_general, self.cols_nonasd_foreign_general,
|
||||||
|
self.cols_domestic_general, self.cols_foreign_detail,
|
||||||
|
self.cols_domestic_detail, self.cols_om
|
||||||
|
]
|
||||||
|
for lst in all_lists:
|
||||||
|
for col in lst:
|
||||||
|
clean_key = self.clean_header_key(col)
|
||||||
|
self.standard_col_map[clean_key] = col
|
||||||
|
|
||||||
|
def clean_header_key(self, text):
|
||||||
|
"""清洗表头：去除换行、空格、制表符，只保留纯文本"""
|
||||||
|
if not isinstance(text, str): return str(text)
|
||||||
|
return re.sub(r'[\s\n\r]+', '', text)
|
||||||
|
|
||||||
def safe_float(self, val):
|
def safe_float(self, val):
|
||||||
try:
|
try:
|
||||||
@ -93,6 +149,20 @@ class DataProcessor:
|
|||||||
except:
|
except:
|
||||||
return str(val)
|
return str(val)
|
||||||
|
|
||||||
|
def format_date_str(self, val):
|
||||||
|
"""格式化日期：去除时分秒，统一为 YYYY-MM-DD"""
|
||||||
|
if pd.isna(val) or str(val).strip() == "": return ""
|
||||||
|
try:
|
||||||
|
# 如果已经是短日期字符串，直接返回
|
||||||
|
s_val = str(val).strip()
|
||||||
|
# 尝试解析
|
||||||
|
dt = pd.to_datetime(val, errors='coerce')
|
||||||
|
if pd.isnull(dt):
|
||||||
|
return s_val # 解析失败返回原样
|
||||||
|
return dt.strftime('%Y-%m-%d')
|
||||||
|
except:
|
||||||
|
return str(val)
|
||||||
|
|
||||||
def normalize_for_compare(self, val):
|
def normalize_for_compare(self, val):
|
||||||
if pd.isna(val) or val is None: return ""
|
if pd.isna(val) or val is None: return ""
|
||||||
s_val = str(val).strip()
|
s_val = str(val).strip()
|
||||||
@ -127,64 +197,6 @@ class DataProcessor:
|
|||||||
|
|
||||||
return df, (col_factory_general, col_factory_detail)
|
return df, (col_factory_general, col_factory_detail)
|
||||||
|
|
||||||
def parse_complex_subject(self, text):
|
|
||||||
res = {'name': '', 'model': '', 'qty': '', 'unit': '', 'price': ''}
|
|
||||||
if not isinstance(text, str) or not text.strip(): return res
|
|
||||||
text = text.strip()
|
|
||||||
|
|
||||||
name_patterns = [r'(?:中文品名|中文名称|名称|Name)[:：]\s*(.*?)(?:\n|$)', r'(?:英文名称)[:：]\s*(.*?)(?:\n|$)']
|
|
||||||
for p in name_patterns:
|
|
||||||
m = re.search(p, text, re.IGNORECASE)
|
|
||||||
if m and not res['name']: res['name'] = m.group(1).strip()
|
|
||||||
|
|
||||||
model_patterns = [r'(?:型号|Model)[:：]\s*(.*?)(?:\n|$)']
|
|
||||||
for p in model_patterns:
|
|
||||||
m = re.search(p, text, re.IGNORECASE)
|
|
||||||
if m: res['model'] = m.group(1).strip()
|
|
||||||
|
|
||||||
brand_match = re.search(r'(?:品牌|Brand)[:：]\s*(.*?)(?:\n|$)', text, re.IGNORECASE)
|
|
||||||
if brand_match:
|
|
||||||
brand_str = brand_match.group(1).strip()
|
|
||||||
if res['model']:
|
|
||||||
res['model'] = f"{brand_str} {res['model']}"
|
|
||||||
else:
|
|
||||||
res['model'] = brand_str
|
|
||||||
|
|
||||||
clean_text = text
|
|
||||||
for k in ['中文品名', '中文名称', '英文名称', '名称', '型号', 'Model', '品牌', 'Brand']:
|
|
||||||
clean_text = re.sub(f'{k}.*?(?:\n|$)', '', clean_text, flags=re.IGNORECASE)
|
|
||||||
|
|
||||||
if not res['name'] and '/' in text:
|
|
||||||
parts = text.split('/')
|
|
||||||
if len(parts) > 0: res['name'] = parts[0].strip()
|
|
||||||
|
|
||||||
if not res['qty']:
|
|
||||||
qty_slash = re.search(r'/(\d+(\.\d+)?)/', text)
|
|
||||||
if qty_slash:
|
|
||||||
res['qty'] = qty_slash.group(1)
|
|
||||||
else:
|
|
||||||
qty_unit_match = re.search(r'(\d+)\s*([台个套件支箱组setpc]+)|([setpc]+)\s*(\d+)', text, re.IGNORECASE)
|
|
||||||
if qty_unit_match:
|
|
||||||
if qty_unit_match.group(1):
|
|
||||||
res['qty'] = qty_unit_match.group(1)
|
|
||||||
res['unit'] = qty_unit_match.group(2)
|
|
||||||
else:
|
|
||||||
res['qty'] = qty_unit_match.group(4)
|
|
||||||
res['unit'] = qty_unit_match.group(3)
|
|
||||||
|
|
||||||
nums = re.findall(r'\d+(?:\.\d+)?', text.replace(',', '').replace('，', ''))
|
|
||||||
if nums:
|
|
||||||
candidate = nums[-1]
|
|
||||||
if candidate != res['qty']: res['price'] = candidate
|
|
||||||
|
|
||||||
if not res['name'] and not res['model'] and '/' in text:
|
|
||||||
parts = text.split('/')
|
|
||||||
if len(parts) >= 1: res['name'] = parts[0]
|
|
||||||
if len(parts) >= 2: res['model'] = parts[1]
|
|
||||||
if len(parts) >= 3: res['qty'] = parts[2]
|
|
||||||
if len(parts) >= 4: res['price'] = parts[3]
|
|
||||||
return res
|
|
||||||
|
|
||||||
def parse_buyer_info(self, text):
|
def parse_buyer_info(self, text):
|
||||||
info = {'name': '', 'contact_full': ''}
|
info = {'name': '', 'contact_full': ''}
|
||||||
if not isinstance(text, str) or not text.strip(): return info
|
if not isinstance(text, str) or not text.strip(): return info
|
||||||
@ -194,25 +206,63 @@ class DataProcessor:
|
|||||||
info['contact_full'] = " ".join(lines[1:])
|
info['contact_full'] = " ".join(lines[1:])
|
||||||
return info
|
return info
|
||||||
|
|
||||||
def process_row_general(self, row, trade_type, col_factory):
|
def parse_single_line_subject(self, text):
|
||||||
target_cols = self.columns_general if trade_type == '外贸' else self.columns_domestic_general
|
res = {'name': '', 'model': '', 'qty': '', 'unit': '', 'price': '', 'sort_price': 0.0}
|
||||||
new_row = {col: "" for col in target_cols}
|
if not isinstance(text, str) or not text.strip(): return res
|
||||||
|
text = text.strip()
|
||||||
|
|
||||||
|
if '/' in text:
|
||||||
|
parts = [p.strip() for p in text.split('/')]
|
||||||
|
if len(parts) >= 1: res['name'] = parts[0]
|
||||||
|
if len(parts) >= 2: res['model'] = parts[1]
|
||||||
|
if len(parts) >= 3:
|
||||||
|
m_qty = re.match(r'^(\d+(\.\d+)?)\s*([\u4e00-\u9fa5a-zA-Z]+)?$', parts[2])
|
||||||
|
if m_qty:
|
||||||
|
res['qty'] = m_qty.group(1)
|
||||||
|
res['unit'] = m_qty.group(3) if m_qty.group(3) else ""
|
||||||
|
else:
|
||||||
|
res['qty'] = parts[2]
|
||||||
|
|
||||||
|
if len(parts) >= 4:
|
||||||
|
res['price'] = parts[3]
|
||||||
|
res['sort_price'] = self.safe_float(parts[3])
|
||||||
|
return res
|
||||||
|
|
||||||
|
name_match = re.search(r'(?:中文品名|中文名称|名称|Name)[:：]\s*(.*?)(?:\n|$)', text, re.IGNORECASE)
|
||||||
|
if name_match:
|
||||||
|
res['name'] = name_match.group(1).strip()
|
||||||
|
else:
|
||||||
|
res['name'] = text.split('\n')[0]
|
||||||
|
|
||||||
|
nums = re.findall(r'\d+(?:\.\d+)?', text.replace(',', ''))
|
||||||
|
if nums:
|
||||||
|
res['sort_price'] = self.safe_float(nums[-1])
|
||||||
|
res['price'] = nums[-1]
|
||||||
|
|
||||||
|
return res
|
||||||
|
|
||||||
|
# === [核心] 总表处理逻辑 ===
|
||||||
|
def process_row_general_expanded(self, row, trade_type, trade_cols, col_factory):
|
||||||
|
# 使用传入的 trade_cols (已是根据ASD/NonASD选择好的标准表头)
|
||||||
|
target_cols = trade_cols
|
||||||
|
|
||||||
|
base_data = {}
|
||||||
order_no_raw = str(row.get('合同订单编号', '')).strip()
|
order_no_raw = str(row.get('合同订单编号', '')).strip()
|
||||||
parts_no = order_no_raw.split()
|
parts_no = order_no_raw.split()
|
||||||
new_row['合同编号'] = parts_no[0] if len(parts_no) > 0 else order_no_raw
|
base_data['合同编号'] = parts_no[0] if len(parts_no) > 0 else order_no_raw
|
||||||
contract_no_col = '外贸合同号' if trade_type == '外贸' else '内贸合同号'
|
contract_no_col = '外贸合同号' if trade_type == '外贸' else '内贸合同号'
|
||||||
new_row[contract_no_col] = " ".join(parts_no[1:]) if len(parts_no) > 1 else ""
|
base_data[contract_no_col] = " ".join(parts_no[1:]) if len(parts_no) > 1 else ""
|
||||||
|
|
||||||
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
# 财务数据
|
||||||
parsed_target = self.parse_complex_subject(target_raw)
|
total_amount = self.format_money_str(row.get('合同总额', ''))
|
||||||
|
status = str(row.get('收款状态', '')).strip()
|
||||||
new_row['合同标的'] = parsed_target['name']
|
received = ""
|
||||||
new_row['型号/货号'] = parsed_target['model']
|
unreceived = ""
|
||||||
new_row['数量'] = parsed_target['qty']
|
if '已收' in status:
|
||||||
new_row['单位'] = parsed_target['unit']
|
received = total_amount
|
||||||
new_row['合同'] = parsed_target['price']
|
unreceived = self.format_money_str(0)
|
||||||
|
|
||||||
|
# 买方信息
|
||||||
if trade_type == '内贸':
|
if trade_type == '内贸':
|
||||||
buyer_raw = str(row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
buyer_raw = str(row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
||||||
else:
|
else:
|
||||||
@ -220,41 +270,133 @@ class DataProcessor:
|
|||||||
if buyer_raw == '' or buyer_raw == 'nan':
|
if buyer_raw == '' or buyer_raw == 'nan':
|
||||||
buyer_raw = str(row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
buyer_raw = str(row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
||||||
parsed_buyer = self.parse_buyer_info(buyer_raw)
|
parsed_buyer = self.parse_buyer_info(buyer_raw)
|
||||||
new_row['买方单位'] = parsed_buyer['name']
|
|
||||||
new_row['买方信息联系人、电话、邮箱'] = parsed_buyer['contact_full']
|
|
||||||
new_row['收货人信息'] = parsed_buyer['name']
|
|
||||||
|
|
||||||
total_amount = row.get('合同总额', '')
|
# 解析标的
|
||||||
status = str(row.get('收款状态', '')).strip()
|
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
||||||
new_row['总合同额'] = total_amount
|
lines = [line.strip() for line in target_raw.split('\n') if line.strip()]
|
||||||
new_row['收款情况'] = status
|
|
||||||
if '已收' in status:
|
parsed_items = []
|
||||||
new_row['已收款'] = total_amount
|
if not lines:
|
||||||
new_row['未收款'] = 0
|
parsed_items.append({'name': '', 'model': '', 'qty': '', 'unit': '', 'price': '', 'sort_price': 0})
|
||||||
else:
|
else:
|
||||||
new_row['已收款'] = ""
|
for line in lines:
|
||||||
new_row['未收款'] = ""
|
parsed_items.append(self.parse_single_line_subject(line))
|
||||||
|
|
||||||
|
# 排序并只取第一行
|
||||||
|
parsed_items.sort(key=lambda x: x['sort_price'], reverse=True)
|
||||||
|
best_item = parsed_items[0]
|
||||||
|
|
||||||
|
new_row = {col: "" for col in target_cols}
|
||||||
|
|
||||||
|
new_row['合同编号'] = base_data['合同编号']
|
||||||
|
new_row[contract_no_col] = base_data[contract_no_col]
|
||||||
new_row['签署公司'] = row.get('收款账户', '')
|
new_row['签署公司'] = row.get('收款账户', '')
|
||||||
new_row['合同签订日期'] = row.get('签约日期', '')
|
|
||||||
|
# 日期 (使用新格式化函数)
|
||||||
|
date_raw = row.get('签约日期', '')
|
||||||
|
if '合同签订日期' in new_row: new_row['合同签订日期'] = self.format_date_str(date_raw)
|
||||||
|
if '签订日期' in new_row: new_row['签订日期'] = self.format_date_str(date_raw)
|
||||||
|
|
||||||
new_row['销售员'] = row.get('负责人', '')
|
new_row['销售员'] = row.get('负责人', '')
|
||||||
new_row['最终用户单位'] = row.get('客户名称', '')
|
new_row['最终用户单位'] = row.get('客户名称', '')
|
||||||
new_row['最终用户信息联系人、电话、邮箱'] = row.get('联系人姓名', '')
|
|
||||||
|
# 处理带换行符的列名映射
|
||||||
|
# 通过遍历 target_cols 找到匹配的列
|
||||||
|
for col in target_cols:
|
||||||
|
if "最终用户信息" in col: new_row[col] = row.get('联系人姓名', '')
|
||||||
|
if "买方信息" in col: new_row[col] = parsed_buyer['contact_full']
|
||||||
|
|
||||||
new_row['厂家'] = row.get(col_factory, '')
|
new_row['厂家'] = row.get(col_factory, '')
|
||||||
new_row['币种'] = row.get('货币(选完产品再改)', '')
|
|
||||||
new_row['外购'] = row.get('外购产品金额', '')
|
|
||||||
new_row['收款日期'] = row.get('最新收款日期', '')
|
|
||||||
new_row['最晚发货期'] = row.get('最晚发货期', '')
|
|
||||||
new_row['付款方式'] = row.get('付款比例及期限', '')
|
|
||||||
new_row['发货港'] = row.get('发货地', '')
|
|
||||||
new_row['目的港'] = row.get('目的港', '')
|
|
||||||
new_row['折扣率'] = row.get('折扣率', '')
|
|
||||||
|
|
||||||
return pd.Series(new_row)
|
if '币种' in new_row: new_row['币种'] = row.get('货币(选完产品再改)', '')
|
||||||
|
if '发货港' in new_row: new_row['发货港'] = row.get('发货地', '')
|
||||||
|
if '目的港' in new_row: new_row['目的港'] = row.get('目的港', '')
|
||||||
|
|
||||||
# [关键修改] 明细表处理逻辑更新，匹配新表头
|
new_row['买方单位'] = parsed_buyer['name']
|
||||||
def process_row_detail(self, row, col_factory):
|
if '收货人信息' in new_row: new_row['收货人信息'] = parsed_buyer['name']
|
||||||
new_row = {col: "" for col in self.columns_detail}
|
|
||||||
|
discount_col = '折扣率' if '折扣率' in new_row else '折扣率（％）'
|
||||||
|
if discount_col in new_row: new_row[discount_col] = self.format_percent_str(row.get('折扣率', ''))
|
||||||
|
|
||||||
|
new_row['合同标的'] = best_item['name']
|
||||||
|
if '型号/货号' in new_row: new_row['型号/货号'] = best_item['model']
|
||||||
|
if '型号' in new_row: new_row['型号'] = best_item['model']
|
||||||
|
new_row['数量'] = best_item['qty']
|
||||||
|
new_row['单位'] = best_item['unit']
|
||||||
|
# 合同额 (单行价格)
|
||||||
|
if '合同额' in new_row: new_row['合同额'] = self.format_money_str(best_item['price'])
|
||||||
|
|
||||||
|
# 财务总额 (整单)
|
||||||
|
total_col_name = '总合同额' if '总合同额' in new_row else '合同总额'
|
||||||
|
new_row[total_col_name] = total_amount
|
||||||
|
|
||||||
|
new_row['收款情况'] = status
|
||||||
|
new_row['外购'] = self.format_money_str(row.get('外购产品金额', ''))
|
||||||
|
new_row['已收款'] = received
|
||||||
|
new_row['未收款'] = unreceived
|
||||||
|
new_row['收款日期'] = self.format_date_str(row.get('最新收款日期', ''))
|
||||||
|
|
||||||
|
if '最晚发货期' in new_row: new_row['最晚发货期'] = self.format_date_str(row.get('最晚发货期', ''))
|
||||||
|
if '付款方式' in new_row: new_row['付款方式'] = row.get('付款比例及期限', '')
|
||||||
|
if '发货日期' in new_row: new_row['发货日期'] = "" # 初始为空
|
||||||
|
|
||||||
|
if '合同币种/美元' in new_row:
|
||||||
|
new_row['合同币种/美元'] = row.get('合同币种/美元', '')
|
||||||
|
|
||||||
|
new_row['_sort_price'] = best_item['sort_price']
|
||||||
|
|
||||||
|
return [new_row]
|
||||||
|
|
||||||
|
# === [核心] 通用总表聚合行生成逻辑 (用于处理多行CSV聚合) ===
|
||||||
|
def generate_general_row_aggregated(self, contract_id, group_df, target_cols, trade_type, is_asd, col_factory):
|
||||||
|
first_row = group_df.iloc[0]
|
||||||
|
# 直接复用单行处理逻辑，因为核心差异在标的聚合，我们在这里做聚合解析
|
||||||
|
# 实际上 process_row_general_expanded 已经包含了标的解析和 Top 1 选取
|
||||||
|
# 但如果是多行CSV记录（例如3行CSV对应同一个合同号），我们需要把所有标的收集起来排序
|
||||||
|
|
||||||
|
all_items = []
|
||||||
|
for _, row in group_df.iterrows():
|
||||||
|
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
||||||
|
lines = [line.strip() for line in target_raw.split('\n') if line.strip()]
|
||||||
|
if lines:
|
||||||
|
for line in lines:
|
||||||
|
all_items.append(self.parse_single_line_subject(line))
|
||||||
|
|
||||||
|
if not all_items:
|
||||||
|
all_items.append({'name': '', 'model': '', 'qty': '', 'unit': '', 'price': '', 'sort_price': 0})
|
||||||
|
|
||||||
|
all_items.sort(key=lambda x: x['sort_price'], reverse=True)
|
||||||
|
best_item = all_items[0]
|
||||||
|
|
||||||
|
# 构造一个合成的 row，大部分信息取 first_row，标的信息替换为 best_item
|
||||||
|
# 为了复用 process_row_general_expanded 的大量字段映射逻辑，我们构造一个 Series
|
||||||
|
# 但 process_row_general_expanded 内部又会解析一次标的...
|
||||||
|
# 简便做法：修改 process_row_general_expanded 让它接受 item 参数
|
||||||
|
# 或者我们在这里手动构造
|
||||||
|
|
||||||
|
# 重新利用 process_row_general_expanded 生成骨架，然后修正标的数据
|
||||||
|
rows = self.process_row_general_expanded(first_row, trade_type, target_cols, col_factory)
|
||||||
|
final_row = rows[0]
|
||||||
|
|
||||||
|
# 修正标的字段为全局最优
|
||||||
|
final_row['合同标的'] = best_item['name']
|
||||||
|
if '型号/货号' in final_row: final_row['型号/货号'] = best_item['model']
|
||||||
|
if '型号' in final_row: final_row['型号'] = best_item['model']
|
||||||
|
final_row['数量'] = best_item['qty']
|
||||||
|
final_row['单位'] = best_item['unit']
|
||||||
|
if '合同额' in final_row: final_row['合同额'] = self.format_money_str(best_item['price'])
|
||||||
|
final_row['_sort_price'] = best_item['sort_price']
|
||||||
|
|
||||||
|
return final_row
|
||||||
|
|
||||||
|
# === 明细表处理逻辑 ===
|
||||||
|
def process_row_detail(self, row, col_factory, trade_type):
|
||||||
|
if trade_type == '外贸':
|
||||||
|
target_cols = self.cols_foreign_detail
|
||||||
|
else:
|
||||||
|
target_cols = self.cols_domestic_detail
|
||||||
|
|
||||||
|
new_row = {col: "" for col in target_cols}
|
||||||
detail_manuf_val = str(row.get(col_factory, ''))
|
detail_manuf_val = str(row.get(col_factory, ''))
|
||||||
|
|
||||||
order_no_raw = str(row.get('合同订单编号', '')).strip()
|
order_no_raw = str(row.get('合同订单编号', '')).strip()
|
||||||
@ -264,87 +406,115 @@ class DataProcessor:
|
|||||||
new_row['厂家'] = detail_manuf_val
|
new_row['厂家'] = detail_manuf_val
|
||||||
new_row['货号'] = row.get('产品编码', '')
|
new_row['货号'] = row.get('产品编码', '')
|
||||||
|
|
||||||
# 币种 -> 外币币种
|
if trade_type == '外贸':
|
||||||
|
new_row['币种'] = row.get('原币种', '')
|
||||||
|
else:
|
||||||
new_row['外币币种'] = row.get('原币种', '')
|
new_row['外币币种'] = row.get('原币种', '')
|
||||||
|
|
||||||
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
||||||
parsed_target = self.parse_complex_subject(target_raw)
|
if '/' in target_raw:
|
||||||
new_row['合同标的'] = parsed_target['name']
|
new_row['合同标的'] = target_raw.split('/')[0].strip()
|
||||||
|
else:
|
||||||
|
new_row['合同标的'] = target_raw.split('\n')[0].strip()
|
||||||
|
|
||||||
csv_qty = str(row.get('数量', '')).strip()
|
csv_qty = str(row.get('数量', '')).strip()
|
||||||
if csv_qty and csv_qty.lower() != 'nan':
|
if csv_qty and csv_qty.lower() != 'nan':
|
||||||
new_row['数量'] = csv_qty
|
new_row['数量'] = csv_qty
|
||||||
else:
|
|
||||||
new_row['数量'] = parsed_target['qty']
|
|
||||||
new_row['单位'] = parsed_target['unit']
|
|
||||||
|
|
||||||
val_product_subtotal = self.safe_float(row.get('产品小计', 0))
|
val_product_subtotal = self.safe_float(row.get('产品小计', 0))
|
||||||
|
|
||||||
if '外购' in detail_manuf_val:
|
if '外购' in detail_manuf_val:
|
||||||
new_row['外购'] = val_product_subtotal
|
new_row['外购'] = self.format_money_str(val_product_subtotal)
|
||||||
remark = str(row.get('备注', '')).strip()
|
remark = str(row.get('备注', '')).strip()
|
||||||
if not remark or remark.lower() == 'nan':
|
if not remark or remark.lower() == 'nan':
|
||||||
outsourced_detail = str(row.get('外购产品明细', '')).strip()
|
outsourced = str(row.get('外购产品明细', '')).strip()
|
||||||
if outsourced_detail and outsourced_detail.lower() != 'nan':
|
new_row['产品描述'] = outsourced if outsourced.lower() != 'nan' else ""
|
||||||
new_row['产品描述'] = outsourced_detail
|
|
||||||
else:
|
|
||||||
new_row['产品描述'] = ""
|
|
||||||
else:
|
else:
|
||||||
new_row['产品描述'] = remark
|
new_row['产品描述'] = remark
|
||||||
else:
|
else:
|
||||||
new_row['外购'] = ""
|
new_row['外购'] = ""
|
||||||
new_row['产品描述'] = row.get('产品名称', '')
|
new_row['产品描述'] = row.get('产品名称', '')
|
||||||
# 美元报价 -> 外币报价单价
|
if '外币报价单价' in new_row: new_row['外币报价单价'] = self.format_money_str(row.get('美元报价', ''))
|
||||||
new_row['外币报价单价'] = row.get('美元报价', '')
|
if '报价单价' in new_row: new_row['报价单价'] = self.format_money_str(row.get('美元报价', ''))
|
||||||
# 产品小计 -> 报价RMB总价 (假设逻辑)
|
|
||||||
new_row['报价RMB总价'] = row.get('产品小计', '')
|
|
||||||
|
|
||||||
new_row['计算汇率'] = row.get('汇率', '')
|
if '报价RMB总价' in new_row: new_row['报价RMB总价'] = self.format_money_str(row.get('产品小计', ''))
|
||||||
new_row['折扣率（％）'] = row.get('折扣率', '')
|
if '报价总价' in new_row: new_row['报价总价'] = self.format_money_str(row.get('产品小计', ''))
|
||||||
new_row['售价RMB单价'] = row.get('销售单价', '')
|
|
||||||
new_row['售价RMB总价'] = row.get('销售总价', '')
|
if '计算汇率' in new_row: new_row['计算汇率'] = self.format_percent_str(row.get('汇率', ''))
|
||||||
new_row['外购转美元'] = row.get('外购转美元', '')
|
if '合同币种/美元' in new_row: new_row['合同币种/美元'] = self.format_percent_str(row.get('汇率', ''))
|
||||||
new_row['报价总价美元'] = row.get('报价总价美元', '')
|
|
||||||
new_row['净合同额美元'] = row.get('净合同额美元', '')
|
discount_col = '折扣率' if '折扣率' in new_row else '折扣率（％）'
|
||||||
new_row['报价RMB单价'] = row.get('报价RMB单价', '') # 如果CSV有这一列，如果没有则为空
|
if discount_col in new_row: new_row[discount_col] = self.format_percent_str(row.get('折扣率', ''))
|
||||||
|
|
||||||
|
if '售价RMB单价' in new_row: new_row['售价RMB单价'] = self.format_money_str(row.get('销售单价', ''))
|
||||||
|
if '销售单价' in new_row: new_row['销售单价'] = self.format_money_str(row.get('销售单价', ''))
|
||||||
|
|
||||||
|
if '售价RMB总价' in new_row: new_row['售价RMB总价'] = self.format_money_str(row.get('销售总价', ''))
|
||||||
|
if '销售总价' in new_row: new_row['销售总价'] = self.format_money_str(row.get('销售总价', ''))
|
||||||
|
|
||||||
|
new_row['外购转美元'] = self.format_money_str(row.get('外购转美元', ''))
|
||||||
|
new_row['报价总价美元'] = self.format_money_str(row.get('报价总价美元', ''))
|
||||||
|
new_row['净合同额美元'] = self.format_money_str(row.get('净合同额美元', ''))
|
||||||
|
|
||||||
|
if '报价RMB单价' in new_row: new_row['报价RMB单价'] = self.format_money_str(row.get('报价RMB单价', ''))
|
||||||
|
|
||||||
return pd.Series(new_row)
|
return pd.Series(new_row)
|
||||||
|
|
||||||
def process_row_om(self, row):
|
# OM表处理 (使用聚合)
|
||||||
new_row = {col: "" for col in self.columns_om}
|
def generate_om_row_aggregated(self, contract_id, group_df, target_cols):
|
||||||
order_no_raw = str(row.get('合同订单编号', '')).strip()
|
first_row = group_df.iloc[0]
|
||||||
|
|
||||||
|
all_items = []
|
||||||
|
for _, row in group_df.iterrows():
|
||||||
|
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
||||||
|
lines = [line.strip() for line in target_raw.split('\n') if line.strip()]
|
||||||
|
if lines:
|
||||||
|
for line in lines:
|
||||||
|
all_items.append(self.parse_single_line_subject(line))
|
||||||
|
|
||||||
|
if not all_items: all_items.append({'name': '', 'price': '', 'sort_price': 0})
|
||||||
|
all_items.sort(key=lambda x: x['sort_price'], reverse=True)
|
||||||
|
best_item = all_items[0]
|
||||||
|
|
||||||
|
new_row = {col: "" for col in target_cols}
|
||||||
|
|
||||||
|
order_no_raw = str(first_row.get('合同订单编号', '')).strip()
|
||||||
parts_no = order_no_raw.split()
|
parts_no = order_no_raw.split()
|
||||||
new_row['合同编号'] = parts_no[0] if len(parts_no) > 0 else order_no_raw
|
new_row['合同编号'] = parts_no[0] if len(parts_no) > 0 else order_no_raw
|
||||||
if len(parts_no) > 1: new_row['内贸合同号'] = " ".join(parts_no[1:])
|
new_row['内贸合同号'] = " ".join(parts_no[1:]) if len(parts_no) > 1 else ""
|
||||||
|
|
||||||
target_raw = str(row.get('合同标的（品名/型号/数量/单价/总价）', ''))
|
total_amount = self.format_money_str(first_row.get('合同总额', ''))
|
||||||
parsed_target = self.parse_complex_subject(target_raw)
|
status = str(first_row.get('收款状态', '')).strip()
|
||||||
new_row['合同标的'] = parsed_target['name']
|
received = ""
|
||||||
|
unreceived = ""
|
||||||
total_amount = row.get('合同总额', '')
|
|
||||||
status = str(row.get('收款状态', '')).strip()
|
|
||||||
new_row['合同总额'] = total_amount
|
|
||||||
new_row['收款情况'] = status
|
|
||||||
if '已收' in status:
|
if '已收' in status:
|
||||||
new_row['已收款'] = total_amount
|
received = total_amount
|
||||||
new_row['未收款'] = 0
|
unreceived = self.format_money_str(0)
|
||||||
else:
|
|
||||||
new_row['已收款'] = ""
|
|
||||||
new_row['未收款'] = ""
|
|
||||||
|
|
||||||
new_row['签署公司'] = row.get('收款账户', '')
|
new_row['签署公司'] = first_row.get('收款账户', '')
|
||||||
new_row['签订日期'] = row.get('签约日期', '')
|
new_row['签订日期'] = self.format_date_str(first_row.get('签约日期', ''))
|
||||||
new_row['销售员'] = row.get('负责人', '')
|
new_row['销售员'] = first_row.get('负责人', '')
|
||||||
new_row['最终用户单位'] = row.get('客户名称', '')
|
new_row['最终用户单位'] = first_row.get('客户名称', '')
|
||||||
new_row['最终用户信息联系人、电话、邮箱'] = row.get('联系人姓名', '')
|
|
||||||
|
|
||||||
buyer_raw = str(row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
contact_col = '最终用户信息\n联系人、电话、邮箱'
|
||||||
|
if contact_col in new_row: new_row[contact_col] = first_row.get('联系人姓名', '')
|
||||||
|
|
||||||
|
buyer_raw = str(first_row.get('合同买方（名称/联系人/电话/邮箱）', ''))
|
||||||
parsed_buyer = self.parse_buyer_info(buyer_raw)
|
parsed_buyer = self.parse_buyer_info(buyer_raw)
|
||||||
new_row['买方单位'] = parsed_buyer['name']
|
new_row['买方单位'] = parsed_buyer['name']
|
||||||
new_row['买方信息联系人、电话、邮箱'] = parsed_buyer['contact_full']
|
|
||||||
new_row['收款日期'] = row.get('最新收款日期', '')
|
|
||||||
|
|
||||||
return pd.Series(new_row)
|
buyer_info_col = '买方信息\n联系人、电话、邮箱'
|
||||||
|
if buyer_info_col in new_row: new_row[buyer_info_col] = parsed_buyer['contact_full']
|
||||||
|
|
||||||
|
new_row['收款日期'] = self.format_date_str(first_row.get('最新收款日期', ''))
|
||||||
|
new_row['合同标的'] = best_item['name']
|
||||||
|
new_row['_sort_price'] = best_item['sort_price']
|
||||||
|
|
||||||
|
new_row['合同总额'] = total_amount
|
||||||
|
new_row['收款情况'] = status
|
||||||
|
new_row['已收款'] = received
|
||||||
|
new_row['未收款'] = unreceived
|
||||||
|
|
||||||
|
return new_row
|
||||||
|
|
||||||
def merge_datasets(self, old_dfs, csv_df, is_asd):
|
def merge_datasets(self, old_dfs, csv_df, is_asd):
|
||||||
col_gen = '厂家'
|
col_gen = '厂家'
|
||||||
@ -361,31 +531,28 @@ class DataProcessor:
|
|||||||
|
|
||||||
result_dfs = {}
|
result_dfs = {}
|
||||||
|
|
||||||
def merge_logic(old_df, new_rows_df, unique_col, target_columns):
|
def merge_logic_expanded(old_df, new_rows_list, unique_col, target_columns):
|
||||||
if old_df is None or old_df.empty:
|
if old_df is None or old_df.empty:
|
||||||
if new_rows_df.empty: return pd.DataFrame(columns=target_columns + ['_status'])
|
if not new_rows_list: return pd.DataFrame(columns=target_columns + ['_status'])
|
||||||
combined = new_rows_df.copy()
|
combined = pd.DataFrame(new_rows_list)
|
||||||
combined['_status'] = 'new'
|
combined['_status'] = 'new'
|
||||||
return combined
|
return combined
|
||||||
|
|
||||||
combined = old_df.copy()
|
combined = old_df.copy()
|
||||||
|
|
||||||
# 确保旧数据列名存在
|
|
||||||
for col in target_columns:
|
for col in target_columns:
|
||||||
if col not in combined.columns:
|
if col not in combined.columns: combined[col] = ""
|
||||||
combined[col] = ""
|
if '_sort_price' not in combined.columns: combined['_sort_price'] = 0.0
|
||||||
|
|
||||||
if unique_col in combined.columns:
|
if unique_col in combined.columns:
|
||||||
combined[unique_col] = combined[unique_col].astype(str)
|
combined[unique_col] = combined[unique_col].astype(str)
|
||||||
|
if '_status' not in combined.columns: combined['_status'] = ''
|
||||||
|
|
||||||
|
if not new_rows_list: return combined
|
||||||
|
|
||||||
|
new_rows_df = pd.DataFrame(new_rows_list)
|
||||||
if unique_col in new_rows_df.columns:
|
if unique_col in new_rows_df.columns:
|
||||||
new_rows_df[unique_col] = new_rows_df[unique_col].astype(str)
|
new_rows_df[unique_col] = new_rows_df[unique_col].astype(str)
|
||||||
|
|
||||||
if '_status' not in combined.columns:
|
|
||||||
combined['_status'] = ''
|
|
||||||
|
|
||||||
if new_rows_df.empty:
|
|
||||||
return combined
|
|
||||||
|
|
||||||
new_contract_ids = new_rows_df[unique_col].unique()
|
new_contract_ids = new_rows_df[unique_col].unique()
|
||||||
rows_to_append = []
|
rows_to_append = []
|
||||||
|
|
||||||
@ -394,24 +561,25 @@ class DataProcessor:
|
|||||||
old_indices = combined[combined[unique_col] == cid].index
|
old_indices = combined[combined[unique_col] == cid].index
|
||||||
|
|
||||||
if len(old_indices) > 0:
|
if len(old_indices) > 0:
|
||||||
idx = old_indices[0]
|
first_old_idx = old_indices[0]
|
||||||
|
new_first_row = new_subset.iloc[0]
|
||||||
|
|
||||||
has_changed = False
|
has_changed = False
|
||||||
new_row_series = new_subset.iloc[0]
|
|
||||||
|
|
||||||
for col in target_columns:
|
for col in target_columns:
|
||||||
if col in new_row_series:
|
if col in new_first_row:
|
||||||
new_val = new_row_series[col]
|
new_val = new_first_row[col]
|
||||||
old_val = combined.at[idx, col]
|
old_val = combined.at[first_old_idx, col]
|
||||||
|
|
||||||
# 保护逻辑：新值非空才覆盖
|
|
||||||
if str(new_val).strip() != "":
|
if str(new_val).strip() != "":
|
||||||
if self.normalize_for_compare(old_val) != self.normalize_for_compare(new_val):
|
if self.normalize_for_compare(old_val) != self.normalize_for_compare(new_val):
|
||||||
combined.at[idx, col] = new_val
|
combined.at[first_old_idx, col] = new_val
|
||||||
has_changed = True
|
has_changed = True
|
||||||
|
|
||||||
if has_changed:
|
if '_sort_price' in new_first_row:
|
||||||
combined.at[idx, '_status'] = 'modified'
|
combined.at[first_old_idx, '_sort_price'] = new_first_row['_sort_price']
|
||||||
|
|
||||||
|
if has_changed:
|
||||||
|
combined.at[first_old_idx, '_status'] = 'modified'
|
||||||
else:
|
else:
|
||||||
new_subset_copy = new_subset.copy()
|
new_subset_copy = new_subset.copy()
|
||||||
new_subset_copy['_status'] = 'new'
|
new_subset_copy['_status'] = 'new'
|
||||||
@ -422,44 +590,57 @@ class DataProcessor:
|
|||||||
|
|
||||||
return combined
|
return combined
|
||||||
|
|
||||||
# --- 合并执行 ---
|
# --- 1. 外贸总表 (聚合) ---
|
||||||
|
new_gen_rows = []
|
||||||
|
target_cols_foreign = self.cols_asd_foreign_general if is_asd else self.cols_nonasd_foreign_general
|
||||||
if not csv_foreign.empty:
|
if not csv_foreign.empty:
|
||||||
new_gen = csv_foreign.apply(lambda r: self.process_row_general(r, '外贸', col_gen), axis=1)
|
grouped = csv_foreign.groupby('合同订单编号')
|
||||||
new_gen = new_gen.drop_duplicates(subset=['合同编号'], keep='first')
|
for contract_id, group in grouped:
|
||||||
else:
|
row_data = self.generate_general_row_aggregated(contract_id, group, target_cols_foreign, '外贸', is_asd,
|
||||||
new_gen = pd.DataFrame(columns=self.columns_general)
|
col_gen)
|
||||||
old_gen = old_dfs.get('外贸', old_dfs.get('外贸总表', pd.DataFrame(columns=self.columns_general)))
|
new_gen_rows.append(row_data)
|
||||||
result_dfs['外贸'] = merge_logic(old_gen, new_gen, '合同编号', self.columns_general)
|
|
||||||
|
|
||||||
|
old_gen = old_dfs.get('外贸', old_dfs.get('外贸总表', pd.DataFrame(columns=target_cols_foreign)))
|
||||||
|
result_dfs['外贸'] = merge_logic_expanded(old_gen, new_gen_rows, '合同编号', target_cols_foreign)
|
||||||
|
|
||||||
|
# --- 2. 外贸明细 ---
|
||||||
if not csv_foreign.empty:
|
if not csv_foreign.empty:
|
||||||
new_det = csv_foreign.apply(lambda r: self.process_row_detail(r, col_det), axis=1)
|
new_det = csv_foreign.apply(lambda r: self.process_row_detail(r, col_det, '外贸'), axis=1)
|
||||||
else:
|
else:
|
||||||
new_det = pd.DataFrame(columns=self.columns_detail)
|
new_det = pd.DataFrame(columns=self.cols_foreign_detail)
|
||||||
old_det = old_dfs.get('外贸明细', pd.DataFrame(columns=self.columns_detail))
|
old_det = old_dfs.get('外贸明细', pd.DataFrame(columns=self.cols_foreign_detail))
|
||||||
result_dfs['外贸明细'] = merge_logic(old_det, new_det, '合同编号', self.columns_detail)
|
result_dfs['外贸明细'] = merge_logic_expanded(old_det, new_det.to_dict('records'), '合同编号',
|
||||||
|
self.cols_foreign_detail)
|
||||||
|
|
||||||
|
# --- 3. 内贸总表 (聚合) ---
|
||||||
|
new_dom_rows = []
|
||||||
if not csv_domestic.empty:
|
if not csv_domestic.empty:
|
||||||
new_dom_gen = csv_domestic.apply(lambda r: self.process_row_general(r, '内贸', col_gen), axis=1)
|
grouped = csv_domestic.groupby('合同订单编号')
|
||||||
new_dom_gen = new_dom_gen.drop_duplicates(subset=['合同编号'], keep='first')
|
for contract_id, group in grouped:
|
||||||
else:
|
row_data = self.generate_general_row_aggregated(contract_id, group, self.cols_domestic_general, '内贸',
|
||||||
new_dom_gen = pd.DataFrame(columns=self.columns_domestic_general)
|
is_asd, col_gen)
|
||||||
old_dom_gen = old_dfs.get('内贸', old_dfs.get('内贸总表', pd.DataFrame(columns=self.columns_domestic_general)))
|
new_dom_rows.append(row_data)
|
||||||
result_dfs['内贸'] = merge_logic(old_dom_gen, new_dom_gen, '合同编号', self.columns_domestic_general)
|
old_dom_gen = old_dfs.get('内贸', old_dfs.get('内贸总表', pd.DataFrame(columns=self.cols_domestic_general)))
|
||||||
|
result_dfs['内贸'] = merge_logic_expanded(old_dom_gen, new_dom_rows, '合同编号', self.cols_domestic_general)
|
||||||
|
|
||||||
|
# --- 4. 内贸明细 ---
|
||||||
if not csv_domestic.empty:
|
if not csv_domestic.empty:
|
||||||
new_dom_det = csv_domestic.apply(lambda r: self.process_row_detail(r, col_det), axis=1)
|
new_dom_det = csv_domestic.apply(lambda r: self.process_row_detail(r, col_det, '内贸'), axis=1)
|
||||||
else:
|
else:
|
||||||
new_dom_det = pd.DataFrame(columns=self.columns_detail)
|
new_dom_det = pd.DataFrame(columns=self.cols_domestic_detail)
|
||||||
old_dom_det = old_dfs.get('内贸明细', pd.DataFrame(columns=self.columns_detail))
|
old_dom_det = old_dfs.get('内贸明细', pd.DataFrame(columns=self.cols_domestic_detail))
|
||||||
result_dfs['内贸明细'] = merge_logic(old_dom_det, new_dom_det, '合同编号', self.columns_detail)
|
result_dfs['内贸明细'] = merge_logic_expanded(old_dom_det, new_dom_det.to_dict('records'), '合同编号',
|
||||||
|
self.cols_domestic_detail)
|
||||||
|
|
||||||
|
# --- 5. OM (聚合) ---
|
||||||
|
new_om_rows = []
|
||||||
if not csv_om.empty:
|
if not csv_om.empty:
|
||||||
new_om = csv_om.apply(lambda r: self.process_row_om(r), axis=1)
|
grouped = csv_om.groupby('合同订单编号')
|
||||||
new_om = new_om.drop_duplicates(subset=['合同编号'], keep='first')
|
for contract_id, group in grouped:
|
||||||
else:
|
row_data = self.generate_om_row_aggregated(contract_id, group, self.cols_om)
|
||||||
new_om = pd.DataFrame(columns=self.columns_om)
|
new_om_rows.append(row_data)
|
||||||
old_om = old_dfs.get('OM合同', old_dfs.get('其他', pd.DataFrame(columns=self.columns_om)))
|
old_om = old_dfs.get('OM合同', old_dfs.get('其他', pd.DataFrame(columns=self.cols_om)))
|
||||||
result_dfs['OM合同'] = merge_logic(old_om, new_om, '合同编号', self.columns_om)
|
result_dfs['OM合同'] = merge_logic_expanded(old_om, new_om_rows, '合同编号', self.cols_om)
|
||||||
|
|
||||||
return result_dfs
|
return result_dfs
|
||||||
|
|
||||||
@ -472,6 +653,9 @@ class DataProcessor:
|
|||||||
for col in self.percent_cols:
|
for col in self.percent_cols:
|
||||||
if col in df.columns:
|
if col in df.columns:
|
||||||
df[col] = df[col].apply(self.format_percent_str)
|
df[col] = df[col].apply(self.format_percent_str)
|
||||||
|
for col in self.date_cols:
|
||||||
|
if col in df.columns:
|
||||||
|
df[col] = df[col].apply(self.format_date_str)
|
||||||
return data_dict
|
return data_dict
|
||||||
|
|
||||||
|
|
||||||
@ -482,7 +666,7 @@ class DataProcessor:
|
|||||||
class ContractApp:
|
class ContractApp:
|
||||||
def __init__(self, root):
|
def __init__(self, root):
|
||||||
self.root = root
|
self.root = root
|
||||||
self.root.title("合同数据处理系统 V3.2 (表头修正版)")
|
self.root.title("合同数据处理系统 V3.8 (换行符修复版)")
|
||||||
self.root.geometry("1300x850")
|
self.root.geometry("1300x850")
|
||||||
|
|
||||||
self.style = ttk.Style()
|
self.style = ttk.Style()
|
||||||
@ -573,15 +757,25 @@ class ContractApp:
|
|||||||
dfs = pd.read_excel(path, sheet_name=None)
|
dfs = pd.read_excel(path, sheet_name=None)
|
||||||
clean_dfs = {}
|
clean_dfs = {}
|
||||||
for k, v in dfs.items():
|
for k, v in dfs.items():
|
||||||
v.columns = v.columns.astype(str).str.replace(r'\s+', '', regex=True)
|
# [关键修复] 智能表头匹配：重命名表头为标准格式
|
||||||
|
new_columns = []
|
||||||
|
for col in v.columns:
|
||||||
|
clean_col = self.processor.clean_header_key(str(col))
|
||||||
|
# 尝试在标准映射里找
|
||||||
|
if clean_col in self.processor.standard_col_map:
|
||||||
|
new_columns.append(self.processor.standard_col_map[clean_col])
|
||||||
|
# 尝试在旧映射里找
|
||||||
|
elif col in self.processor.legacy_map:
|
||||||
|
new_columns.append(self.processor.legacy_map[col])
|
||||||
|
else:
|
||||||
|
new_columns.append(col) # 找不到就保留原样
|
||||||
|
v.columns = new_columns
|
||||||
|
|
||||||
# 总表仍可能需要 legacy_map，但明细表不需要了因为我们已经在代码里统一了列名
|
# 去重
|
||||||
v.rename(columns=self.processor.legacy_map, inplace=True)
|
|
||||||
v = v.loc[:, ~v.columns.duplicated()]
|
v = v.loc[:, ~v.columns.duplicated()]
|
||||||
|
|
||||||
if '合同编号' in v.columns:
|
if '合同编号' in v.columns:
|
||||||
v['合同编号'] = v['合同编号'].astype(str)
|
v['合同编号'] = v['合同编号'].astype(str)
|
||||||
|
|
||||||
clean_dfs[k.strip()] = v
|
clean_dfs[k.strip()] = v
|
||||||
return clean_dfs
|
return clean_dfs
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
@ -632,20 +826,31 @@ class ContractApp:
|
|||||||
if not df.empty:
|
if not df.empty:
|
||||||
if '合同编号' in df.columns:
|
if '合同编号' in df.columns:
|
||||||
df['合同编号'] = df['合同编号'].astype(str)
|
df['合同编号'] = df['合同编号'].astype(str)
|
||||||
df = df.sort_values(by='合同编号', ascending=True)
|
|
||||||
|
sort_cols = ['合同编号']
|
||||||
|
asc_order = [True]
|
||||||
|
if '_sort_price' in df.columns:
|
||||||
|
sort_cols.append('_sort_price')
|
||||||
|
asc_order.append(False)
|
||||||
|
df = df.sort_values(by=sort_cols, ascending=asc_order)
|
||||||
|
|
||||||
if '明细' in sheet_name:
|
if '明细' in sheet_name:
|
||||||
mask = df.duplicated(subset=['合同编号'], keep='first')
|
mask = df.duplicated(subset=['合同编号'], keep='first')
|
||||||
df.loc[mask, '合同标的'] = ""
|
df.loc[mask, '合同标的'] = ""
|
||||||
|
|
||||||
standard_cols = []
|
standard_cols = []
|
||||||
|
is_asd = (file_type == 'ASD')
|
||||||
|
|
||||||
if sheet_name == '外贸':
|
if sheet_name == '外贸':
|
||||||
standard_cols = self.processor.columns_general
|
standard_cols = self.processor.cols_asd_foreign_general if is_asd else self.processor.cols_nonasd_foreign_general
|
||||||
elif sheet_name == '内贸':
|
elif sheet_name == '内贸':
|
||||||
standard_cols = self.processor.columns_domestic_general
|
standard_cols = self.processor.cols_domestic_general
|
||||||
elif sheet_name == 'OM合同':
|
elif sheet_name == 'OM合同':
|
||||||
standard_cols = self.processor.columns_om
|
standard_cols = self.processor.cols_om
|
||||||
elif '明细' in sheet_name:
|
elif sheet_name == '外贸明细':
|
||||||
standard_cols = self.processor.columns_detail
|
standard_cols = self.processor.cols_foreign_detail
|
||||||
|
elif sheet_name == '内贸明细':
|
||||||
|
standard_cols = self.processor.cols_domestic_detail
|
||||||
|
|
||||||
self.create_treeview(inner_notebook, df, sheet_name, standard_cols)
|
self.create_treeview(inner_notebook, df, sheet_name, standard_cols)
|
||||||
|
|
||||||
@ -656,6 +861,7 @@ class ContractApp:
|
|||||||
scroll_y = ttk.Scrollbar(frame, orient="vertical")
|
scroll_y = ttk.Scrollbar(frame, orient="vertical")
|
||||||
scroll_x = ttk.Scrollbar(frame, orient="horizontal")
|
scroll_x = ttk.Scrollbar(frame, orient="horizontal")
|
||||||
|
|
||||||
|
# 仅显示标准列
|
||||||
display_cols = target_cols
|
display_cols = target_cols
|
||||||
|
|
||||||
tree = ttk.Treeview(frame, columns=display_cols, show='headings',
|
tree = ttk.Treeview(frame, columns=display_cols, show='headings',
|
||||||
@ -668,7 +874,9 @@ class ContractApp:
|
|||||||
tree.pack(fill="both", expand=True)
|
tree.pack(fill="both", expand=True)
|
||||||
|
|
||||||
for col in display_cols:
|
for col in display_cols:
|
||||||
tree.heading(col, text=col)
|
# 清洗显示名称（换行变空格，防止表头太高）
|
||||||
|
clean_header = col.replace('\n', ' ')
|
||||||
|
tree.heading(col, text=clean_header)
|
||||||
tree.column(col, width=120, anchor="center")
|
tree.column(col, width=120, anchor="center")
|
||||||
|
|
||||||
tree.tag_configure('new', background='#FFFFCC')
|
tree.tag_configure('new', background='#FFFFCC')
|
||||||
@ -728,11 +936,18 @@ class ContractApp:
|
|||||||
for sheet_name in valid_sheets:
|
for sheet_name in valid_sheets:
|
||||||
if sheet_name in sheets:
|
if sheet_name in sheets:
|
||||||
df = sheets[sheet_name]
|
df = sheets[sheet_name]
|
||||||
save_df = df.drop(columns=['_status'], errors='ignore')
|
|
||||||
|
if '合同编号' in df.columns:
|
||||||
|
sort_cols = ['合同编号']
|
||||||
|
asc_order = [True]
|
||||||
|
if '_sort_price' in df.columns:
|
||||||
|
sort_cols.append('_sort_price')
|
||||||
|
asc_order.append(False)
|
||||||
|
df = df.sort_values(by=sort_cols, ascending=asc_order)
|
||||||
|
|
||||||
|
save_df = df.drop(columns=['_status', '_sort_price'], errors='ignore')
|
||||||
|
|
||||||
if not save_df.empty:
|
if not save_df.empty:
|
||||||
if '合同编号' in save_df.columns:
|
|
||||||
save_df['合同编号'] = save_df['合同编号'].astype(str)
|
|
||||||
save_df = save_df.sort_values(by='合同编号', ascending=True)
|
|
||||||
if '明细' in sheet_name:
|
if '明细' in sheet_name:
|
||||||
mask = save_df.duplicated(subset=['合同编号'], keep='first')
|
mask = save_df.duplicated(subset=['合同编号'], keep='first')
|
||||||
save_df.loc[mask, '合同标的'] = ""
|
save_df.loc[mask, '合同标的'] = ""
|
||||||
|
|||||||
Reference in New Issue
Block a user