Create setup.py and add bot apis

.gitignore

@@ -3,4 +3,9 @@ outputs/*
 dataset/*
 *.pyc
 .idea
-venv
+venv
+
+# package build
+build/*
+dist/*
+group_purchase.egg-info/*

MANIFEST.in

@@ -0,0 +1,2 @@
+include README.md
+include group_purchase\assets\html_format.css

README.md

@@ -1,18 +1,45 @@
 # JuWeiHui
-Currently a very ugly but usable script to covert group purchase results to printable sheets for delivery during the pandemic in Shanghai
+
+Currently a very ugly but usable script to covert group purchase results to printable sheets for delivery during the
+pandemic in Shanghai
 
 ## How to use
-1. Define your own personal community logic in the community_hardcode folder. Import this class in main.py and change the class name.
+
+1. Define your own personal community logic in the community_hardcode folder. Import this class in main.py and change
+   the class name.
 2. Create 2 folders files and outputfiles.
-3. Put all the files you what to generate in files folder. 
+3. Put all the files you what to generate in files folder.
 4. Run main.py
 5. If your file has some missind data, an error will be thrown. Ask the one with missing data to fill the data here.
 6. The latex pdf file will be generated in outputfiles folder
 
 ## Other points
 
-This repo is more like a hardcode repo to solve temporary problems of the JuWeiHui package delivery. We might have more types of excel templates, more communities involved. So it will be appreciate if you can help me to make it less hardcode, and more applicable for more situations.
+This repo is more like a hardcode repo to solve temporary problems of the JuWeiHui package delivery. We might have more
+types of excel templates, more communities involved. So it will be appreciate if you can help me to make it less
+hardcode, and more applicable for more situations.
+
+Users of this form might touch personal data of the purchaser. For me I will delete all those data when the pandemic is
+done, and won't send any such data to anyone else. Please make similar declairation if you need to use this script.
+
+I would like to add some algorithm-based features to even improve the delivery logic. If you are a specialist in
+optimization, please contact me. Wechat id:wgzjack0305
+
+---
+
+# 订单excel处理方法
+
+1. 先指定小区和excel模板，小区用对象（以后这个对象是全局的，生命周期很长），模板用类（模板对象生命周期很短，处理完就销毁了）
+2. 指定输入和输出文件名。输入和输出文件名应和需求名有关，输入模板和输出模板会依赖这个。
+3. 调用接口处理excel
+    1. 创建parser实例，一个parser对应一个excel文件
+    2. 调用parser解析接口，返回订单集合对象和出错单元格坐标
+    3. 按需生成pdf或提示用户检查原表格数据
 
-Users of this form might touch personal data of the purchaser. For me I will delete all those data when the pandemic is done, and won't send any such data to anyone else. Please make similar declairation if you need to use this script.
+获取excel模板接口：`get_excel_parser(name: str) -> Optional[Type[ExcelParserBase]]`
 
-I would like to add some algorithm-based features to even improve the delivery logic. If you are a specialist in optimization, please contact me. Wechat id:wgzjack0305
+- 输入：`name`模板的中文名。
+- 输出：模板的Parser类。找不到该名称对应的模板时返回None。
+- 当前支持模板：
+    - 群接龙
+    - 快团团

REFACTORING_PLANS.md

@@ -5,13 +5,15 @@
 1. ~~解耦小区信息和团购信息~~
  - 1.1 ~~创建excel模板机制的抽象。输出不应依赖输入的表格本身，而是依赖表格解析出的数据抽象类。~~
  - 1.2 ~~优化小区类，小区类只应承担小区的独有属性。这也方便之后的架构演进。~~
-2. 入口脚本优化
- - 2.1 预留支持小区定制，预留支持excel模板定制
-3. 美化目录结构和代码格式，提升可维护性。
+2. ~~入口脚本优化~~
+ - 2.1 ~~预留支持小区定制，预留支持excel模板定制~~
+3. ~~美化目录结构和代码格式，提升可维护性。~~
 4. 新增单元测试
 5. 记录适配定制开发者手册
 ## 阶段二 居委会仓和微信bot仓链接
 居委会仓和微信bot仓现在依然是两个独立工作的仓。如果有需要，居委会仓的功能可以接入bot。最终架构中，小区数据和小区定制信息由居委会仓管理，微信bot可以通过统一的接口向居委会仓请求数据或触发动作，这可以降低技术人员维护的成本，因为脚本处理动作将由非技术人员从微信上触发。
+1. 居委会仓支持pip安装，以module的形式接入bot。涉及的配置的需要支持动态配置。
+2. ~~excel模板搞一个管理器，支持通过字符串查找模板~~
 ## 阶段三 居委会仓和bot归一
 架构的最终形态居委会仓演进成数据处理模块，bot仓演进成用户交互模块。是所有数据均由数据处理模块处理，而对用户的输入输出则由用户交互接管。本开源社区持续维护数据模块，不断降低使用成本和部署成本，并对转发模块选型，使用成本最低、效果最好的用户交互方案。
 

group_purchase/__init__.py

@@ -0,0 +1 @@
+name = "group_purchase"

group_purchase/bot/__init__.py

@@ -0,0 +1,6 @@
+from .bot import on_file, update_file
+
+__all__ = [
+    'on_file',
+    'update_file'
+]

group_purchase/bot/bot.py

@@ -0,0 +1,32 @@
+
+from group_purchase.community.parser_mng import get_community_parser
+from group_purchase.purchase_deliver.parser_mng import get_excel_parser
+
+import openpyxl
+
+def on_file(input_file_path, output_file_path, community, excel):
+    excel_parser = get_excel_parser(excel)
+    community_parser = get_community_parser(community)
+
+    parser = excel_parser(open(input_file_path, 'rb'))
+    result, errors = parser.parse_for_community(community_parser())
+    if errors:
+        return f"以下单元格数据无法识别，请检查:\n{errors}"
+    else:
+        pass
+
+    result.print_to_pdf(output_file_path)
+    return output_file_path
+
+
+def update_file(input_file_path, updated_data, coordinate):
+    try:
+        workbook = openpyxl.load_workbook(open(input_file_path, 'rb'))
+        sheet = workbook.active
+        sheet[coordinate].value = updated_data
+        workbook.save(input_file_path)
+        return True
+    except Exception as error:
+        print(f"Cannot modify file {input_file_path}, error:\n {error}")
+        return False
+

group_purchase/community/__init__.py

@@ -0,0 +1,5 @@
+from .jia_yi_shui_an import JiaYiShuiAn
+
+__all__ = [
+    'JiaYiShuiAn'
+]

src/Communitiy/CommunityBase.py → group_purchase/community/community_base.py

@@ -3,9 +3,10 @@ class CommunityAddress:
     小区地址类，building表示楼栋，供表格分组用；full_addr是地址全写，用来输出
     """
 
-    def __init__(self, full_addr, building=''):
+    def __init__(self, full_addr, building='', room=0):
         self.full_addr = full_addr
         self.building = building
+        self.room = room
 
     def __str__(self):
         return str(self.full_addr)

src/Communitiy/JiaYiShuiAn.py → group_purchase/community/jia_yi_shui_an.py

@@ -1,16 +1,12 @@
-from .CommunityBase import CommunityBase, CommunityAddress
-from utils.chinese import replace_location
+from .community_base import CommunityBase, CommunityAddress
+from group_purchase.utils.chinese import replace_location
 
 
 class JiaYiShuiAn(CommunityBase):
     def __init__(self):
         super().__init__('嘉怡水岸')
         self.keywords = ['上海市', '上海', '闵行区', '闵行', '紫龙路', '500号', '五百号', '500']
 
-        self.SPECIAL_NUMBERS_BUILDING = {
-            9999: '居委会'
-        }
-
         # In JiaYiShuiAn, number 7 -36 are houses, with no room number
         self.SPECIAL_NUMBERS_HOUSE = {
             5899: '商务楼'
@@ -26,16 +22,21 @@ def parse_address(self, address):
             raise ValueError
 
         if len(locations) == 2:
-            return CommunityAddress(f'{locations[0]}号楼{locations[1]}号', f'{locations[0]}号楼')
+            if address.__contains__('5899'):
+                locations.remove(5899)
+                return CommunityAddress(f'商务楼{locations[0]}',
+                                        '商务楼',
+                                        int(locations[0]))
+            return CommunityAddress(f'{locations[0]}号楼{locations[1]}号', f'{locations[0]}号楼', int(locations[1]))
         if len(locations) == 1:
-            if self.SPECIAL_NUMBERS_BUILDING.__contains__(locations[0]):
-                return CommunityAddress(f'{self.SPECIAL_NUMBERS_BUILDING[locations[0]]}{locations[0]}号',
-                                        self.SPECIAL_NUMBERS_BUILDING[locations[0]])
             if self.SPECIAL_NUMBERS_HOUSE.__contains__(locations[0]):
                 return CommunityAddress(f'{self.SPECIAL_NUMBERS_HOUSE[locations[0]]}{locations[0]}号',
-                                        self.SPECIAL_NUMBERS_HOUSE[locations[0]])
+                                        self.SPECIAL_NUMBERS_HOUSE[locations[0]],
+                                        int(locations[0]))
             if address.__contains__('商务楼'):
-                return CommunityAddress(f'商务楼{locations[0]}', '商务楼')
+                return CommunityAddress(f'商务楼{locations[0]}',
+                                        '商务楼',
+                                        int(locations[0]))
             if address.__contains__('居委会'):
                 return CommunityAddress('居委会', '居委会')
         raise ValueError

group_purchase/community/parser_mng.py

@@ -0,0 +1,12 @@
+from typing import *
+
+from .community_base import CommunityBase
+from .jia_yi_shui_an import JiaYiShuiAn
+
+parser_map: Mapping[str, Type[CommunityBase]] = {
+    '嘉怡水岸': JiaYiShuiAn,
+}
+
+
+def get_community_parser(name: str) -> Optional[Type[CommunityBase]]:
+    return parser_map.get(name, None)

group_purchase/purchase_deliver/__init__.py

@@ -0,0 +1,5 @@
+from .parser_mng import get_excel_parser
+
+__all__ = [
+    'get_excel_parser'
+]

src/PurchaseDeliver/ExcelParser.py → group_purchase/purchase_deliver/excel_parser/excel_parser.py

@@ -1,9 +1,9 @@
 import openpyxl
 
-from .OrderSet import OrderSet
+from group_purchase.purchase_deliver.order_set import OrderSet
 
 
-class ExcelParser:
+class ExcelParserBase:
     """
     Excel模板Base类。
     """

src/PurchaseDeliver/ExcelParser1.py → group_purchase/purchase_deliver/excel_parser/jielong_parser.py

@@ -1,10 +1,11 @@
 from pathlib import Path
 
-from .Order import Order
-from .ExcelParser import ExcelParser
+from group_purchase.purchase_deliver.order import Order
+from .excel_parser import ExcelParserBase
+
 
 # 群接龙
-class ExcelParser1(ExcelParser):
+class JieLongParser(ExcelParserBase):
     """
     Excel模板，第一行：收货人 联系电话 订单总金额 支付状态 收货地址 订购数量
     后起每行一条记录，最后一行是合计

src/PurchaseDeliver/ExcelParser2.py → group_purchase/purchase_deliver/excel_parser/kuaituantuan_parser.py

@@ -1,11 +1,12 @@
 from audioop import add
 from pathlib import Path
 
-from .Order import Order
-from .ExcelParser import ExcelParser
+from group_purchase.purchase_deliver.order import Order
+from .excel_parser import ExcelParserBase
+
 
 # 快团团
-class ExcelParser2(ExcelParser):
+class KuaiTuanTuanParser(ExcelParserBase):
     """
     Excel模板，第一行：
     下单人 团员备注 团长备注 跟团号 商品 规格 数量 商品金额 
@@ -15,11 +16,16 @@ class ExcelParser2(ExcelParser):
     商品名和excel文件名保持一致
     """
 
+    def __init__(self, file):
+        super().__init__(file)
+        self.amount_col = None
+        self.full_address_col = None
+
     def get_header(self):
         for i in range(self.sheet.max_column):
-            if self.sheet.cell(1, i+1).value == "详细地址":
+            if self.sheet.cell(1, i + 1).value == "详细地址":
                 self.full_address_col = i
-            if self.sheet.cell(1, i+1).value == "数量":
+            if self.sheet.cell(1, i + 1).value == "数量":
                 self.amount_col = i
 
     def loop_record(self):

group_purchase/purchase_deliver/order.py

@@ -0,0 +1,22 @@
+from typing import *
+from collections import defaultdict
+from group_purchase.community.community_base import CommunityAddress
+
+
+class Order:
+    def __init__(self):
+        self.buyer_name: str = ''
+        self.address: Optional[CommunityAddress] = None
+        self.items: defaultdict[str, int] = defaultdict(int)
+
+    def set_buyer(self, buyer: str) -> 'Order':
+        self.buyer_name = buyer
+        return self
+
+    def set_address(self, address: CommunityAddress) -> 'Order':
+        self.address = address
+        return self
+
+    def set_item(self, item_name: str, amount: int) -> 'Order':
+        self.items[item_name] = amount
+        return self

src/PurchaseDeliver/OrderSet.py → group_purchase/purchase_deliver/order_set.py

@@ -1,7 +1,7 @@
 from collections import defaultdict
 from pathlib import Path
 
-from utils.PdfGen import html_string_to_pdf
+from group_purchase.utils.pdf_gen import html_string_to_pdf
 
 
 def group_orders_by_address(orders):
@@ -14,17 +14,19 @@ def group_orders_by_address(orders):
 def order_set_to_html(orders, title):
     ret = ''
     groups = group_orders_by_address(orders)
+    orders = 0
     for group in sorted(groups):  # TODO: 改进排序算法，支持数字和非数字混合排序，不要用字典序
+        orders += int(sum(sum(i.items.values()) for i in groups[group]))
         ret += f'''<div class='no-break'>
-        <h1>{group}, 共{int(sum(sum(i.items.values()) for i in groups[group]))}单  {title}</h1>
+        <h2>{group}, 共{int(sum(sum(i.items.values()) for i in groups[group]))}单  {title}</h2>
         <table>
         <tr>
-        <th>需求概述</th><th>地址</th><th>购买物品</th><th>配送完成</th>
+        <th>需求概述</th><th>楼栋号</th><th>房间号</th><th>购买物品</th><th>配送完成</th>
         </tr>
         {''.join(
-            f'<tr><td>{order.address}: {title}</td><td>{order.address}</td>'
+            f'<tr><td>{order.address}: {title}</td><td>{order.address.building}</td><td>{order.address.room}</td>'
             f'<td>{"<br>".join(f"{item} ×{int(amount)}" for item, amount in order.items.items())}</td><td>&nbsp;</td></tr>'
-            for order in groups[group])}
+            for order in sorted(groups[group], key=lambda x: x.address.room))}
         </table>
         </div>'''
     return ret

group_purchase/purchase_deliver/parser_mng.py

@@ -0,0 +1,14 @@
+from typing import *
+
+from .excel_parser.excel_parser import ExcelParserBase
+from .excel_parser.jielong_parser import JieLongParser
+from .excel_parser.kuaituantuan_parser import KuaiTuanTuanParser
+
+parser_map: Mapping[str, Type[ExcelParserBase]] = {
+    '群接龙': JieLongParser,
+    '快团团': KuaiTuanTuanParser
+}
+
+
+def get_excel_parser(name: str) -> Optional[Type[ExcelParserBase]]:
+    return parser_map.get(name, None)

group_purchase/utils/__init__.py

@@ -0,0 +1 @@
+__all__ = []

src/utils/PdfGen.py → group_purchase/utils/pdf_gen.py

@@ -1,11 +1,11 @@
 import pdfkit
 
-
 # TODO: 写的有点草率，之后再斟酌下。。。
 def html_string_to_pdf(html, filename):
+
     pdfkit.from_string(html, filename, configuration=pdfkit.configuration(
         wkhtmltopdf=r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe'), options={
         'encoding': 'utf-8',
-        'user-style-sheet': 'assets/html_format.css',
+        'user-style-sheet': 'group_purchase/assets/html_format.css',
         'footer-center': '第[page]页  共[topage]页'
     })