Intention/api/standard_test.py

import logging

from logger_util import setup_logger
from globalData import GlobalData
from utils import standardize_name, clean_useless_team_leader_name, standardize_sub_company, standardize_project_name, \
    standardize_projectDepartment, standardize_team_name, check_standard_name_slot_probability, \
    clean_useless_project_name
import time

from apscheduler.schedulers.blocking import BlockingScheduler
from globalData import GlobalData

# def job():
#     print("[Info] Executing update_from_redis...")
#     GlobalData.update_from_redis()
#
#
logger = setup_logger("utils", level=logging.DEBUG)
GlobalData.update_from_redis()

def check_standard_name_slot_probability_test():
    slot_list = [{"constructionUnit": "合肥供电公司"},
                 {
                     "date": "今天",
                     "constructionUnit": "芜湖供电公司"
                 },
                 {
                     "date": "今天",
                     "implementationOrganization": "送电一分公司"
                 },
                 {
                     "date": "今天",
                     "subcontractor": "百瑞建设发展有限公司"
                 },
                 {
                     "date": "今天",
                     "subcontractor": "安徽宝德电力建设工程有限"
                 },
                 {
                     "date": "今天",
                     "teamName": "徐局班组"
                 }
                 ]
    for slot in slot_list:
            match_results = check_standard_name_slot_probability(12, slot)
            logger.info(f"加权混合策略 项目部名称 输入: 原始槽位：{slot}，输出: {match_results}")


def standardize_team_leader_test():
    team_leader_list = [
        "李东班组",
        "磐基班组",
        "章永班组",
        "张勇班组",
        "王治国班组",
        "代贵华班组",
        "黄安印班组",
        "刘闩班组",
        "王虎班组",
        "周勇勇班组",
        "魏在华班组",
        "王礼良班组",
        "林学刚班组",
        "崔新荣班组",
        "江军班组",
        "笪淦班组",
        "杨海平班组",
        "蔡来云班组",
        "贺中林班组",
        "何勇班组",
        "韦幸朝班组",
        "刘文虎班组",
        "金生班组",
        "段宝强班组",
        "何计划班组",
        "刘兆班组",
        "徐南班组",
        "贺广飞班组",
        "孙泽栋班组",
        "钱小林班组",
        "朱锋东班组",
    ]
    for item in team_leader_list:
        match_results = standardize_team_name(item, GlobalData.simply_to_standard_team_leader_name_map,
                                              GlobalData.pinyin_simply_to_standard_team_leader_name_map, lower_score=70, high_score=90)
        # match_results = standardize_name(item, clean_useless_team_leader_name, GlobalData.simply_to_standard_team_leader_name_map,
        #                                  GlobalData.pinyin_simply_to_standard_team_leader_name_map, lower_score=70, high_score=90)
        logger.info(f"班组长名匹配 输入: {item}-> 输出: {match_results}")


def standardize_company_test():
    test_cases = [
        ("送一分公司"),
        ("送二分公司"),
        ("变电分公司"),
        ("建筑分公司"),
        ("检修试验分公司"),
        ("宏源电力公司"),
        ("宏源电力限公司"),
        ("宏源电力限公司线路"),
        ("宏源电力限公司变电"),
        ("送一分"),
        ("送二分"),
        ("变电分"),
        ("建筑分"),
        ("检修试验分"),
        ("宏源电力"),
        ("红源电力"),
        ("宏源电力有限"),
        ("宏源电力限线路"),
        ("宏源电力限变电"),
    ]

    logger.info(f"加权混合策略 分公司名匹配**********************")
    start = time.perf_counter()
    for item in test_cases:
        match_results = standardize_sub_company(item,GlobalData.simply_to_standard_company_name_map, GlobalData.pinyin_simply_to_standard_company_name_map,70,90)
        logger.info(f"加权混合策略 分公司名匹配 输入: {item}-> 输出: {match_results}")
    end = time.perf_counter()
    logger.info(f"加权混合策略 耗时: {end - start:.4f} 秒")


def  standardize_construction_test():
    test_cases = [
        ("合肥供电公司"),
        ("淮北供电公司"),
        ("六安市城郊供电公司"),
    ]
    logger.info(f"加权混合策略 建管单位名匹配**********************")
    start = time.perf_counter()
    for item in test_cases:
        match_results = standardize_sub_company(item,GlobalData.simply_to_standard_construct_name_map, GlobalData.pinyin_simply_to_standard_construct_name_map,70,90)
        logger.info(f"加权混合策略 建管单位名匹配 输入: {item}-> 输出: {match_results}")

def standardize_project_test():
    test_cases = [
        ("众兴500kV变电站220kV杜岗Ⅱ间隔改造工程(PROJ-2023-0435)"),
        ("众兴500kv变电站220kv杜岗ⅱ间隔改造工程(proj-2023-0435)")
        # ("合肥卫田变电站工程").
        # ("金牛变电站新建建筑"),
        # ("金牛变电站建筑工程"),
        # ("金牛新建工程"),
        # ("金牛新建工程调试"),
        # ("金牛新建调试工程"),
        # ("金牛变电站工程"),
        # ("芦集"),
        # ("芦集变电站"),
        # ("安庆四变电站"),
        # ("锦绣变电站"),
        # ("滁州护桥变电站"),
        # ("合州换流站"),
        # ("陕北合州换流站"),
        # ("陕北安徽合州换流站"),
        # ("金牛变电站"),
        # ("香涧鹭岛工程"),
        # ("延庆换流站"),
        # ("国网延庆换流站"),
        # ("国网北京延庆换流站"),
        # ("陶楼广银线路工程"),
        # ("紫蓬变电站"),
        # ("宿州萧砀变电站"),
        # ("冯井变电站"),
        # ("富邦秋浦变电站"),
        # ("包河玉龙变电站"),
        # ("绿雪莲塘工程"),
        # ("合肥循环园工程"),
        # ("合肥长临河工程"),
        # ("合肥中心变"),
        # ("锁库变电站工程"),
        # ("槽坊工程"),
        # ("富东2798线"),
        # ("安庆四500kV变电站新建工程(PROJ-2024-0862)"),
        # ("锦绣-常青π入中心变电站220kV架空线路工程(PROJ-2024-1206)"),
        # ("渝北±800千伏换流站电气安装A包(调试部分)(PROJ-2024-1192)"),
        # ("先锋-泉河π入安庆四变电站220kV线路工程(PROJ-2024-0834)"),
        # ("安徽滁州护桥220kV变电站2号主变扩建工程(PROJ-2024-0821)"),
        # ("合州士800千伏换流站电气安装A包(PROJ-2025-0056)"),
        # ("卫田-陶楼T接首业变电站110kV电缆线路工程(PROJ-2024-1236)"),
        # ("谯城（亳三）-希夷220kV线路工程(PROJ-2024-1205)"),
    ]
    logger.info(f"去不重要词汇 工程名匹配******************************************")
    start = time.perf_counter()
    for item in test_cases:
        match_results = standardize_project_name(item, GlobalData.simply_to_standard_project_name_map,
                                                 GlobalData.pinyin_simply_to_standard_project_name_map, 70, 90)
        logger.info(f"***************工程名匹配 输入: {item}-> 输出: {match_results}")
    end = time.perf_counter()
    logger.info(f"词集匹配 耗时: {end - start:.4f} 秒")

def standardize_program_test():
    logger.info(f"项目名匹配******************************************")
    oral_program_name_list = [
        ("金上第一项目部"),
        ("第一项目部金上"),
        # ("第1项目部"),  # 期望返回所有"第三项目管理部"
        # ("第2项目部"),
        # ("第3项目部"),
        # ("第4项目部"),
        # ("第5项目部"),
        # ("第6项目部"),
        # ("第7项目部"),
        # ("第8项目部"),
        # ("第9项目部"),
        # ("第10项目部"),
        # ("第11项目部"),
        # ("第12项目部"),
        # ("第13项目部"),
        # ("电缆班"),
        # ("调试1队"),
        # ("调试2队"),
        # ("调试3队"),
        # ("调试4队"),
        # ("调试5队"),
        # ("第一项目管理部"),
        # ("第二项目管理部"),
        # ("第五项目管理部"),
        # ("第十一项目管理部（萧砀线路）"),
        # ("第三项目管理部（张店线路）"),
        # ("第三项目管理部(岳西线路)"),
        # ("第五项目管理部（蚌埠）"),
        # ("第三项目管理部（六安线路）"),
        # ("第十一项目管理部（宿州线路）"),
        # ("调试一队"),
        # ("调试二队"),
        # ("调试三队"),
        # ("电缆班"),
    ]

    for company in GlobalData.standard_company_name_list:
        for program in oral_program_name_list:
            match_results = standardize_projectDepartment(company, program, GlobalData.standard_company_program, high_score=90)
            logger.info(f"加权混合策略 项目部名称 输入: 公司：{company}，项目部：{program}-> 输出: {match_results}")



def  standardize_sub_constractor_test():
    test_cases = [
        ("怀电能源科技"),
        ("泰央建设有限责任公司"),
        ("泓源电力建设有限公司"),
        ("怀电能源科技公司"),
        ("宝德电力公司"),
        ("亿甲建筑公司"),
    ]
    logger.info(f"加权混合策略 分包单位名匹配**********************")
    start = time.perf_counter()
    for item in test_cases:
        match_results = standardize_sub_company(item,GlobalData.simply_to_standard_constractor_name_map, GlobalData.pinyin_simply_to_standard_constractor_name_map,70,90)
        logger.info(f"分包单位名匹配 输入: {item}-> 输出: {match_results}")


def get_file_name():
    import os
    # 你想要遍历的目录路径
    target_dir = '/Users/wangvivi/Desktop/Work/2025项目材料/送变电大模型/知识库文档/送变电文档合并V5'  # ← 请替换为你的目标目录路径

    # 存储文件名的列表
    all_file_names = []

    # 遍历目录及其子目录
    for root, dirs, files in os.walk(target_dir):
        for file in files:
            all_file_names.append(file)

    # 写入 name.txt 文件
    output_path = 'name.txt'  # 会生成在当前运行目录下
    with open(output_path, 'w', encoding='utf-8') as f:
        for name in all_file_names:
            f.write(name + '\n')

    logger.info(f"共收集了 {len(all_file_names)} 个文件名，已写入 {output_path}")


class Message:
    def __init__(self, role, content):
        self.role = role
        self.content = content

class Message:
    def __init__(self, role, content):
        self.role = role
        self.content = content

def history_message():
    from collections import namedtuple
    Message = namedtuple("Message", ["role", "content"])

    messages = [
        # Message("user", "延庆换流站今天有多少作业计划"),
        # Message("assistant", "2025-04-23 ±500KV延庆换流站备用换流变安装(PROJ-2025-0162)风险等级为2级的有0项，3级的有0项，4级的有1项，5级的有0项，一共有1项作业计划"),
        # Message("user", "河州换流站今天有多少作业计划"),
        # Message("assistant", "您说的工程名可能是： 第1个：合州±800千伏换流站电气安装A包(PROJ-2025-0056) 第2个：合州换流站-文都500千伏线路工程(PROJ-2024-1089) 第3个：陕北-安徽直流工程合州±800千伏换流站土建A包(PROJ-2024-0312) 第4个：文都-官山改接入合州换流站500千伏线路工程(PROJ-2024-1090) 请确认您要选择哪一个"),
        Message("user", "第一个")
    ]

    latest_message = messages[-1]
    latest_user_question = latest_message.content if latest_message.role == "user" else ""

    time_prefixes = ["今天", "昨天", "本周", "下周", "明天", "今日"]
    history_messages = [] if any(prefix in latest_user_question for prefix in time_prefixes) else messages[:-1]

    logger.info("len(history_messages):\n", len(history_messages))
    oldest_chat_history = "\n".join([f"{msg.role}: {msg.content}" for msg in history_messages[:2]])
    last_chat_history = "\n".join([f"{msg.role}: {msg.content}" for msg in history_messages[-2:]])

    logger.info("oldest_chat_history:\n", oldest_chat_history)
    logger.info("last_chat_history:\n", last_chat_history)
    logger.info("latest_user_question:\n", latest_user_question)


def standardize_program():
    from rapidfuzz import process, fuzz
    # query = "金上第一项目"
    # choices = [
    #     "第五项目管理部（阜阳）",
    #     "第一项目管理部（金上）",
    #     "第二项目管理部（香鹭西段）",
    #     "第十一项目管理部（宣城）",
    #     "第八项目管理部（芜湖）",
    #     "第十三项目管理部（黄山）",
    #     "第六项目管理部（滁州）",
    #     "第四项目管理部（甘浙）",
    #     "第九项目管理部（马鞍山）",
    #     "第三项目管理部（香鹭东段）",
    #     "第一项目管理部（天津）"
    # ]

    query = "第一金上"
    choices = [
        "第五阜阳",
        "第一金上",
        "第二香鹭西段",
        "第十一宣城",
        "第八芜湖",
        "第十三黄山",
        "第六滁州",
        "第四甘浙",
        "第九马鞍山）",
        "第三香鹭东段",
        "第一天津"
    ]

    match = process.extractOne(query, choices, scorer=fuzz.WRatio)
    logger.info(match)
def get_size():
    import sys
    total_size = sys.getsizeof(GlobalData.standard_company_program) + sys.getsizeof(GlobalData.standard_company_name_list) + sys.getsizeof(GlobalData.simply_to_standard_company_name_map)+ sys.getsizeof(GlobalData.pinyin_simply_to_standard_company_name_map)
    logger.info(f"standard_company size: {total_size} bytes")
    total_size = sys.getsizeof(GlobalData.standard_project_name_list) + sys.getsizeof(GlobalData.simply_to_standard_project_name_map) + sys.getsizeof(GlobalData.pinyin_simply_to_standard_project_name_map)
    logger.info(f"standard_project size: {total_size} bytes")
    total_size = sys.getsizeof(GlobalData.standard_construct_name_list) + sys.getsizeof(GlobalData.simply_to_standard_construct_name_map) + sys.getsizeof(GlobalData.pinyin_simply_to_standard_construct_name_map)
    logger.info(f"standard_construct size: {total_size} bytes")
    total_size = sys.getsizeof(GlobalData.standard_constractor_name_list) + sys.getsizeof(GlobalData.simply_to_standard_constractor_name_map) + sys.getsizeof(GlobalData.pinyin_simply_to_standard_constractor_name_map)
    logger.info(f"standard_constractor size: {total_size} bytes")
    total_size = sys.getsizeof(GlobalData.standard_team_leader_name_list) + sys.getsizeof(GlobalData.simply_to_standard_team_leader_name_map) + sys.getsizeof(GlobalData.pinyin_simply_to_standard_constractor_name_map)
    logger.info(f"standard_team size: {total_size} bytes")

    standardize_project_test()


unuselessStr = clean_useless_project_name("众兴杜岗ⅱ间隔改造")
print(f"众兴杜岗ⅱ间隔改造:{unuselessStr}")
unuselessStr = clean_useless_project_name("众兴杜岗Ⅱ间隔改造")
print(f"众兴杜岗Ⅱ间隔改造:{unuselessStr}")
print("今天的长度：",len("今天"))
# standardize_program()
# history_message()

# standardize_team_leader_test()
#
# standardize_sub_constractor_test()
#
# check_standard_name_slot_probability_test()
#
# standardize_construction_test()
# standardize_program_test()