# 安裝必要的Python庫
pip install python-docx openpyxl smtplib

import os
import re
from docx import Document
from pathlib import Path

def create_output_directory(base_dir="切分文件"):
    """創(chuàng)建輸出目錄，如果不存在則自動(dòng)創(chuàng)建"""
    if not os.path.exists(base_dir):
        os.makedirs(base_dir)
        print(f"創(chuàng)建目錄: {base_dir}")
    return base_dir

def count_english_words(text):
    """精確計(jì)算英文單詞數(shù)量（專業(yè)級處理）"""
    # 專業(yè)思考：翻譯行業(yè)的單詞計(jì)數(shù)需要包含連字符單詞
    # 如"state-of-the-art"計(jì)為1個(gè)單詞，而非4個(gè)
    words = re.findall(r'\b[a-zA-Z\']+(?:-[a-zA-Z]+)*\b', text)
    return len(words)

def split_docx_by_word_count(input_file, words_per_file=10000):
    """
    智能切分Word文檔，自動(dòng)創(chuàng)建目錄并按規(guī)則命名
    
    參數(shù):
        input_file: 輸入文件路徑
        words_per_file: 每個(gè)文件的單詞數(shù)目標(biāo)
    
    返回:
        生成的文件列表
    """
    # 創(chuàng)建輸出目錄
    output_dir = create_output_directory("切分文件")
    
    # 獲取原文件名（不含擴(kuò)展名）
    original_name = Path(input_file).stem
    
    try:
        doc = Document(input_file)
        file_count = 1
        current_word_count = 0
        current_doc = Document()
        output_files = []
        
        print(f"開始處理文檔: {input_file}")
        print(f"目標(biāo)字?jǐn)?shù): {words_per_file}詞/文件")
        
        for i, paragraph in enumerate(doc.paragraphs):
            if not paragraph.text.strip():
                continue
                
            paragraph_word_count = count_english_words(paragraph.text)
            
            # 專業(yè)思考：保持段落完整性，避免在段落中間切分
            if current_word_count + paragraph_word_count > words_per_file and current_word_count > 0:
                # 保存當(dāng)前文件
                output_filename = f"{original_name}{file_count}.docx"
                output_path = os.path.join(output_dir, output_filename)
                current_doc.save(output_path)
                output_files.append(output_path)
                print(f"生成文件: {output_filename} (字?jǐn)?shù): {current_word_count})")
                
                # 創(chuàng)建新文件
                file_count += 1
                current_doc = Document()
                current_word_count = 0
            
            # 添加段落到當(dāng)前文檔
            current_doc.add_paragraph(paragraph.text)
            current_word_count += paragraph_word_count
        
        # 保存最后一個(gè)文件
        if current_word_count > 0:
            output_filename = f"{original_name}{file_count}.docx"
            output_path = os.path.join(output_dir, output_filename)
            current_doc.save(output_path)
            output_files.append(output_path)
            print(f"生成文件: {output_filename} (字?jǐn)?shù): {current_word_count})")
        
        print(f"切分完成！共生成 {len(output_files)} 個(gè)文件")
        return output_files
        
    except Exception as e:
        print(f"文檔處理出錯(cuò): {str(e)}")
        return []

import openpyxl

def read_translator_list(excel_file):
    """
    讀取譯員名單Excel文件
    格式要求：第一列姓名，第二列郵箱
    """
    try:
        workbook = openpyxl.load_workbook(excel_file)
        sheet = workbook.active
        
        translators = []
        for row_num, row in enumerate(sheet.iter_rows(min_row=2, values_only=True), start=2):
            if row[0] and row[1]:  # 確保姓名和郵箱都不為空
                translators.append({
                    'name': str(row[0]).strip(),
                    'email': str(row[1]).strip(),
                    'row': row_num  # 記錄行號(hào)便于排查問題
                })
            elif row[0] or row[1]:  # 只有一個(gè)字段有內(nèi)容
                print(f"警告: 第{row_num}行信息不完整")
        
        print(f"從Excel讀取到 {len(translators)} 位譯員")
        return translators
        
    except Exception as e:
        print(f"讀取Excel文件失敗: {str(e)}")
        return []

def validate_assignment(translators, output_files):
    """
    驗(yàn)證譯員數(shù)量與文件數(shù)量是否匹配
    """
    translator_count = len(translators)
    file_count = len(output_files)
    
    print("\n" + "="*50)
    print("分配驗(yàn)證檢查")
    print("="*50)
    print(f"譯員數(shù)量: {translator_count}")
    print(f"文件數(shù)量: {file_count}")
    
    if translator_count == file_count:
        print("? 驗(yàn)證通過：譯員數(shù)量與文件數(shù)量匹配")
        return True
    elif translator_count > file_count:
        print(f"? 驗(yàn)證失?。鹤g員數(shù)量({translator_count})多于文件數(shù)量({file_count})")
        print(f"   請?jiān)黾?{translator_count - file_count} 個(gè)文件或減少譯員")
    else:
        print(f"? 驗(yàn)證失?。何募?shù)量({file_count})多于譯員數(shù)量({translator_count})")
        print(f"   請減少 {file_count - translator_count} 個(gè)文件或增加譯員")
    
    return False

from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.mime.application import MIMEApplication
from email.header import Header
import traceback
import time

def send_translation_assignments(smtp_config, translators, output_files):
    """
    批量發(fā)送翻譯任務(wù)郵件（增強(qiáng)版）
    """
    success_count = 0
    failed_emails = []
    
    print(f"\n開始發(fā)送任務(wù)郵件...")
    
    # 任務(wù)信息配置
    task_info = {
        'deadline': 7,
        'style': '技術(shù)文檔的嚴(yán)謹(jǐn)性',
        'project_name': '翻譯項(xiàng)目',
        'word_count': 12000,
        'manager_name': smtp_config.get('sender_name', '項(xiàng)目經(jīng)理')
    }
    
    for i, translator in enumerate(translators):
        if i < len(output_files):  # 安全邊界檢查
            attachment_file = output_files[i]
            translator_name = translator['name']
            translator_email = translator['email']
            
            print(f"正在發(fā)送給: {translator_name} ({translator_email})")
            
            if send_single_email(smtp_config, translator_name, translator_email, attachment_file, task_info):
                success_count += 1
                # 添加延遲，避免發(fā)送頻率過高被限制
                if i < len(translators) - 1:  # 最后一個(gè)不需要延遲
                    time.sleep(2)
            else:
                failed_emails.append(f"{translator_name}({translator_email})")
    
    # 發(fā)送結(jié)果匯總
    print(f"\n" + "="*50)
    print("郵件發(fā)送完成！")
    print("="*50)
    print(f"成功: {success_count}/{len(translators)}")
    if failed_emails:
        print(f"失敗的收件人:")
        for failed in failed_emails:
            print(f"  ? {failed}")
    else:
        print("? 所有郵件發(fā)送成功！")
    
    return success_count

def send_single_email(smtp_config, name, email, attachment_file, task_info):
    """發(fā)送單個(gè)郵件（增強(qiáng)版）"""
    try:
        # 創(chuàng)建多部分郵件對象
        msg = MIMEMultipart()
        
        # 設(shè)置郵件頭（符合企業(yè)郵箱規(guī)范）
        display_name = smtp_config.get('display_name', '翻譯項(xiàng)目管理中心')
        msg['From'] = f"{Header(display_name, 'utf-8').encode()} <{smtp_config['sender_email']}>"
        msg['To'] = email
        msg['Subject'] = Header(f"翻譯任務(wù)分配 - {name}", 'utf-8')

        # 郵件正文
        email_content = f"""
尊敬的{name}：

您好！

您分配到的翻譯任務(wù)文件請見附件。

任務(wù)要求：
1. 請?jiān)趝task_info['deadline']}個(gè)工作日內(nèi)完成翻譯
2. 保持術(shù)語一致性，請參考術(shù)語表
3. 翻譯風(fēng)格請保持{task_info['style']}
4. 如有問題請及時(shí)與我溝通

文件信息：{os.path.basename(attachment_file)}
項(xiàng)目名稱：{task_info['project_name']}
單詞數(shù)量：約{task_info['word_count']}詞

請確認(rèn)收到本郵件及附件，謝謝！

祝工作順利！

{task_info['manager_name']}
"""
        msg.attach(MIMEText(email_content, 'plain', 'utf-8'))

        # 添加附件
        if not os.path.isfile(attachment_file):
            print(f"  ? 附件不存在: {attachment_file}")
            return False
            
        try:
            with open(attachment_file, "rb") as f:
                filename = os.path.basename(attachment_file)
                part = MIMEApplication(f.read())
                part.add_header('Content-Disposition', 'attachment',
                               filename=('utf-8', '', filename))
                msg.attach(part)
                print(f"  ? 已添加附件: {filename}")
        except Exception as e:
            print(f"  ? 添加附件失敗: {attachment_file} | 錯(cuò)誤: {str(e)}")
            return False

        # 建立加密連接并發(fā)送
        try:
            with smtplib.SMTP_SSL(smtp_config['server'], smtp_config['port']) as server:
                server.login(smtp_config['sender_email'], smtp_config['password'])
                server.sendmail(smtp_config['sender_email'], [email], msg.as_string())
            
            print(f"  ? 發(fā)送成功")
            return True

        except smtplib.SMTPAuthenticationError:
            print(f"  ? 郵箱認(rèn)證失敗，請檢查賬號(hào)密碼")
        except smtplib.SMTPRecipientsRefused:
            print(f"  ? 收件人被拒絕，可能郵箱不存在")
        except smtplib.SMTPException as e:
            print(f"  ? SMTP錯(cuò)誤: {str(e)}")
        except Exception as e:
            print(f"  ? 連接錯(cuò)誤: {str(e)}")

    except Exception as e:
        print(f"  ? 郵件構(gòu)造錯(cuò)誤: {str(e)}")
        traceback.print_exc()
    
    return False    

def main():
    """主程序 - 項(xiàng)目管理自動(dòng)化入口"""
    print("=" * 60)
    print("       翻譯項(xiàng)目智能分派系統(tǒng)")
    print("=" * 60)
    
    # 配置參數(shù)
    config = {
        'input_file': 'project.docx',           # 原始項(xiàng)目文件
        'excel_file': 'translators.xlsx',       # 譯員名單
        'words_per_file': 10000,                # 每個(gè)文件1萬詞
        
        # 郵箱配置（根據(jù)實(shí)際情況修改）
        'smtp': {
            'server': 'smtp.163.com',
            'port': 587,
            'sender_email': 'your_email@163.com',
            'sender_name': '張項(xiàng)目經(jīng)理',
            'password': 'your_password'
        }
    }
    
    # 執(zhí)行流程
    print("步驟1: 文件切分...")
    output_files = split_docx_by_word_count(config['input_file'], config['words_per_file'])
    
    if not output_files:
        print("文件切分失敗，程序退出")
        return
    
    print("\n步驟2: 讀取譯員名單...")
    translators = read_translator_list(config['excel_file'])
    
    if not translators:
        print("讀取譯員名單失敗，程序退出")
        return
    
    print("\n步驟3: 分配驗(yàn)證...")
    if validate_assignment(translators, output_files):
        print("\n步驟4: 發(fā)送任務(wù)郵件...")
        send_translation_assignments(config['smtp'], translators, output_files)
    else:
        print("\n??  分配驗(yàn)證未通過，請調(diào)整后重新運(yùn)行程序")
        print("建議:")
        if len(translators) > len(output_files):
            print("  - 增加輸入文檔內(nèi)容")
            print("  - 或從Excel中移除部分譯員")
        else:
            print("  - 減少每個(gè)文件的字?jǐn)?shù)目標(biāo)")
            print("  - 或在Excel中添加更多譯員")

if __name__ == "__main__":
    main()

import os
import re
from docx import Document
from pathlib import Path
import openpyxl
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.mime.application import MIMEApplication
from email.header import Header
import traceback
import time

def create_output_directory(base_dir="切分文件"):
    """創(chuàng)建輸出目錄，如果不存在則自動(dòng)創(chuàng)建"""
    if not os.path.exists(base_dir):
        os.makedirs(base_dir)
        print(f"創(chuàng)建目錄: {base_dir}")
    return base_dir

def count_english_words(text):
    """精確計(jì)算英文單詞數(shù)量（專業(yè)級處理）"""
    # 專業(yè)思考：翻譯行業(yè)的單詞計(jì)數(shù)需要包含連字符單詞
    # 如"state-of-the-art"計(jì)為1個(gè)單詞，而非4個(gè)
    words = re.findall(r'\b[a-zA-Z\']+(?:-[a-zA-Z]+)*\b', text)
    return len(words)

def split_docx_by_word_count(input_file, words_per_file=10000):
    """
    智能切分Word文檔，自動(dòng)創(chuàng)建目錄并按規(guī)則命名
    
    參數(shù):
        input_file: 輸入文件路徑
        words_per_file: 每個(gè)文件的單詞數(shù)目標(biāo)
    
    返回:
        生成的文件列表
    """
    # 創(chuàng)建輸出目錄
    output_dir = create_output_directory("切分文件")
    
    # 獲取原文件名（不含擴(kuò)展名）
    original_name = Path(input_file).stem
    
    try:
        doc = Document(input_file)
        file_count = 1
        current_word_count = 0
        current_doc = Document()
        output_files = []
        
        print(f"開始處理文檔: {input_file}")
        print(f"目標(biāo)字?jǐn)?shù): {words_per_file}詞/文件")
        
        for i, paragraph in enumerate(doc.paragraphs):
            if not paragraph.text.strip():
                continue
                
            paragraph_word_count = count_english_words(paragraph.text)
            
            # 專業(yè)思考：保持段落完整性，避免在段落中間切分
            if current_word_count + paragraph_word_count > words_per_file and current_word_count > 0:
                # 保存當(dāng)前文件
                output_filename = f"{original_name}{file_count}.docx"
                output_path = os.path.join(output_dir, output_filename)
                current_doc.save(output_path)
                output_files.append(output_path)
                print(f"生成文件: {output_filename} (字?jǐn)?shù): {current_word_count})")
                
                # 創(chuàng)建新文件
                file_count += 1
                current_doc = Document()
                current_word_count = 0
            
            # 添加段落到當(dāng)前文檔
            current_doc.add_paragraph(paragraph.text)
            current_word_count += paragraph_word_count
        
        # 保存最后一個(gè)文件
        if current_word_count > 0:
            output_filename = f"{original_name}{file_count}.docx"
            output_path = os.path.join(output_dir, output_filename)
            current_doc.save(output_path)
            output_files.append(output_path)
            print(f"生成文件: {output_filename} (字?jǐn)?shù): {current_word_count})")
        
        print(f"切分完成！共生成 {len(output_files)} 個(gè)文件")
        return output_files
        
    except Exception as e:
        print(f"文檔處理出錯(cuò): {str(e)}")
        return []


def read_translator_list(excel_file):
    """
    讀取譯員名單Excel文件
    格式要求：第一列姓名，第二列郵箱
    """
    try:
        workbook = openpyxl.load_workbook(excel_file)
        sheet = workbook.active
        
        translators = []
        for row_num, row in enumerate(sheet.iter_rows(min_row=2, values_only=True), start=2):
            if row[0] and row[1]:  # 確保姓名和郵箱都不為空
                translators.append({
                    'name': str(row[0]).strip(),
                    'email': str(row[1]).strip(),
                    'row': row_num  # 記錄行號(hào)便于排查問題
                })
            elif row[0] or row[1]:  # 只有一個(gè)字段有內(nèi)容
                print(f"警告: 第{row_num}行信息不完整")
        
        print(f"從Excel讀取到 {len(translators)} 位譯員")
        return translators
        
    except Exception as e:
        print(f"讀取Excel文件失敗: {str(e)}")
        return []

def validate_assignment(translators, output_files):
    """
    驗(yàn)證譯員數(shù)量與文件數(shù)量是否匹配
    """
    translator_count = len(translators)
    file_count = len(output_files)
    
    print("\n" + "="*50)
    print("分配驗(yàn)證檢查")
    print("="*50)
    print(f"譯員數(shù)量: {translator_count}")
    print(f"文件數(shù)量: {file_count}")
    
    if translator_count == file_count:
        print("? 驗(yàn)證通過：譯員數(shù)量與文件數(shù)量匹配")
        return True
    elif translator_count > file_count:
        print(f"? 驗(yàn)證失?。鹤g員數(shù)量({translator_count})多于文件數(shù)量({file_count})")
        print(f"   請?jiān)黾?{translator_count - file_count} 個(gè)文件或減少譯員")
    else:
        print(f"? 驗(yàn)證失敗：文件數(shù)量({file_count})多于譯員數(shù)量({translator_count})")
        print(f"   請減少 {file_count - translator_count} 個(gè)文件或增加譯員")
    
    return False

def send_translation_assignments(smtp_config, translators, output_files):
    """
    批量發(fā)送翻譯任務(wù)郵件（增強(qiáng)版）
    """
    success_count = 0
    failed_emails = []
    
    print(f"\n開始發(fā)送任務(wù)郵件...")
    
    # 任務(wù)信息配置
    task_info = {
        'deadline': 7,
        'style': '技術(shù)文檔的嚴(yán)謹(jǐn)性',
        'project_name': '翻譯項(xiàng)目',
        'word_count': 12000,
        'manager_name': smtp_config.get('sender_name', '項(xiàng)目經(jīng)理')
    }
    
    for i, translator in enumerate(translators):
        if i < len(output_files):  # 安全邊界檢查
            attachment_file = output_files[i]
            translator_name = translator['name']
            translator_email = translator['email']
            
            print(f"正在發(fā)送給: {translator_name} ({translator_email})")
            
            if send_single_email(smtp_config, translator_name, translator_email, attachment_file, task_info):
                success_count += 1
                # 添加延遲，避免發(fā)送頻率過高被限制
                if i < len(translators) - 1:  # 最后一個(gè)不需要延遲
                    time.sleep(2)
            else:
                failed_emails.append(f"{translator_name}({translator_email})")
    
    # 發(fā)送結(jié)果匯總
    print(f"\n" + "="*50)
    print("郵件發(fā)送完成！")
    print("="*50)
    print(f"成功: {success_count}/{len(translators)}")
    if failed_emails:
        print(f"失敗的收件人:")
        for failed in failed_emails:
            print(f"  ? {failed}")
    else:
        print("? 所有郵件發(fā)送成功！")
    
    return success_count

def send_single_email(smtp_config, name, email, attachment_file, task_info):
    """發(fā)送單個(gè)郵件（增強(qiáng)版）"""
    try:
        # 創(chuàng)建多部分郵件對象
        msg = MIMEMultipart()
        
        # 設(shè)置郵件頭（符合企業(yè)郵箱規(guī)范）
        display_name = smtp_config.get('display_name', '翻譯項(xiàng)目管理中心')
        msg['From'] = f"{Header(display_name, 'utf-8').encode()} <{smtp_config['sender_email']}>"
        msg['To'] = email
        msg['Subject'] = Header(f"翻譯任務(wù)分配 - {name}", 'utf-8')

        # 郵件正文
        email_content = f"""
尊敬的{name}：

您好！

您分配到的翻譯任務(wù)文件請見附件。

任務(wù)要求：
1. 請?jiān)趝task_info['deadline']}個(gè)工作日內(nèi)完成翻譯
2. 保持術(shù)語一致性，請參考術(shù)語表
3. 翻譯風(fēng)格請保持{task_info['style']}
4. 如有問題請及時(shí)與我溝通

文件信息：{os.path.basename(attachment_file)}
項(xiàng)目名稱：{task_info['project_name']}
單詞數(shù)量：約{task_info['word_count']}詞

請確認(rèn)收到本郵件及附件，謝謝！

祝工作順利！

{task_info['manager_name']}
"""
        msg.attach(MIMEText(email_content, 'plain', 'utf-8'))

        # 添加附件
        if not os.path.isfile(attachment_file):
            print(f"  ? 附件不存在: {attachment_file}")
            return False
            
        try:
            with open(attachment_file, "rb") as f:
                filename = os.path.basename(attachment_file)
                part = MIMEApplication(f.read())
                part.add_header('Content-Disposition', 'attachment',
                               filename=('utf-8', '', filename))
                msg.attach(part)
                print(f"  ? 已添加附件: {filename}")
        except Exception as e:
            print(f"  ? 添加附件失敗: {attachment_file} | 錯(cuò)誤: {str(e)}")
            return False

        # 建立加密連接并發(fā)送
        try:
            with smtplib.SMTP_SSL(smtp_config['server'], smtp_config['port']) as server:
                server.login(smtp_config['sender_email'], smtp_config['password'])
                server.sendmail(smtp_config['sender_email'], [email], msg.as_string())
            
            print(f"  ? 發(fā)送成功")
            return True

        except smtplib.SMTPAuthenticationError:
            print(f"  ? 郵箱認(rèn)證失敗，請檢查賬號(hào)密碼")
        except smtplib.SMTPRecipientsRefused:
            print(f"  ? 收件人被拒絕，可能郵箱不存在")
        except smtplib.SMTPException as e:
            print(f"  ? SMTP錯(cuò)誤: {str(e)}")
        except Exception as e:
            print(f"  ? 連接錯(cuò)誤: {str(e)}")

    except Exception as e:
        print(f"  ? 郵件構(gòu)造錯(cuò)誤: {str(e)}")
        traceback.print_exc()
    
    return False    
def main():
    """主程序 - 項(xiàng)目管理自動(dòng)化入口"""
    print("=" * 60)
    print("       翻譯項(xiàng)目智能分派系統(tǒng)")
    print("=" * 60)
    
    # 配置參數(shù)
    config = {
        'input_file': 'input.docx',           # 原始項(xiàng)目文件
        'excel_file': 'email.xlsx',           # 譯員名單
        'words_per_file': 10000,              # 每個(gè)文件1萬詞
        
        # 郵箱配置（根據(jù)實(shí)際情況修改）
        'smtp': {
            'server': 'smtpdm.aliyun.com',
            'port': 465,
            'sender_email': 'Your Email Address',
            'sender_name': '李項(xiàng)目經(jīng)理',
            'display_name': '翻譯項(xiàng)目管理中心',  # 新增：發(fā)件人顯示名稱
            'password': 'Your Password'
        }
    }
    
    # 執(zhí)行流程
    print("步驟1: 文件切分...")
    output_files = split_docx_by_word_count(config['input_file'], config['words_per_file'])
    
    if not output_files:
        print("文件切分失敗，程序退出")
        return
    
    print("\n步驟2: 讀取譯員名單...")
    translators = read_translator_list(config['excel_file'])
    
    if not translators:
        print("讀取譯員名單失敗，程序退出")
        return
    
    print("\n步驟3: 分配驗(yàn)證...")
    if validate_assignment(translators, output_files):
        print("\n步驟4: 發(fā)送任務(wù)郵件...")
        send_translation_assignments(config['smtp'], translators, output_files)
    else:
        print("\n??  分配驗(yàn)證未通過，請調(diào)整后重新運(yùn)行程序")
        print("建議:")
        if len(translators) > len(output_files):
            print("  - 增加輸入文檔內(nèi)容")
            print("  - 或從Excel中移除部分譯員")
        else:
            print("  - 減少每個(gè)文件的字?jǐn)?shù)目標(biāo)")
            print("  - 或在Excel中添加更多譯員")

if __name__ == "__main__":
    main()