miaoguo_system_server/src/api/yjbdc/readerController.js

import moment from 'moment';
import fs from 'fs';
import { promises as fsPromises } from 'fs';
import commonModel from '../../model/commonModel.js';
import config from '../../config/index.js';
import _ from 'lodash';
import axios from 'axios';
import { stringUtils } from '../../util/stringClass.js';
import { globalCache } from '../../util/GlobalCache.js';
import machineTranslationAPI from './machineTranslation.js';
import path from 'path';
import { fileURLToPath } from 'url';


const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);

export async function GetReaderBooks(ctx) {
    let result = [
        {
            Title: "Strange-Life-of-a-Cat",
        },{
            Title: "Throne-of-Magical-Arcana",
        },{
            Title: "Zhui-Xu",
        },{
            Title: "Hidden-Assassin",
        },{
            Title: "Release-that-Witch",
        },{
            Title: "The-Legendary-Mechanic",
        },
    ];

    ctx.body = { "errcode": 10000, result };
}

export async function GetReaderBooksChapter(ctx) {
    const param = {
        Title: ctx.query.Title || "",
    };

    let result = [];

    const { readdir, readFile, writeFile } = fs.promises;
    let sourceDir = path.join(__dirname, '../../web_crawler/'+ param.Title + '/' + param.Title + '_contents');
    const files = (await readdir(sourceDir))
            .filter(file => file.endsWith('.html'))
            .sort((a, b) => parseInt(a.split('_')[0]) - parseInt(b.split('_')[0]));
    
    for (const file of files) {
        // 提取章节标题
        const titleMatch = file.match(/_([^\.]+)\.html$/);
        const title = titleMatch ? titleMatch[1] : file;
        result.push(title);
    }

    ctx.body = { "errcode": 10000, result: result };
}

export async function GetReaderBooksChapterContent(ctx) {
    const param = {
        Title: ctx.query.Title || "",
        Chapter: ctx.query.Chapter || "0",
    };

    let result = [];

    const {readFile} = fs.promises;
    // 读取文本文件
    let filePath = path.join(__dirname, '../../web_crawler/'+ param.Title + '/' + param.Title + '.html');
    
    const content = await fs.promises.readFile(filePath, 'utf-8');
    console.log(`已读取文件: ${filePath}`);
    
    const chapters = content.split('\n');
    let b=false;
    // 处理每个章节
    for (const chapter of chapters) {
        if (b && chapter && chapter.indexOf("<h2>Chapter")>=0) {
            break; // 找到下一个章节标题，停止处理
        }
        
        if (chapter === "<h2>Chapter "+ param.Chapter+"</h2>") {
            b=true;
        }
        if (b) {
            let chapter2=chapter.replace(/<br\s*\/?>/gi, '\n').replace(/&nbsp;/g, ' ').replace(/<h2>/g, '\n\n').replace(/<\/h2>/g, '\n\n').replace(/<p>/g, '\n').replace(/<\/p>/g, '\n').replace(/<[^>]+>/g, '').trim();
            
            // 确保每个句子标点符号（句号、问号、感叹号）后面有一个空格
            chapter2 = chapter2.replace(/([.!?])(?=\S)/g, '$1 ');
            
            // 按句子分割文本，形成段落内的句子数组
            if (chapter2) {
                // 创建当前段落的句子数组
                let paragraphSentences = [];
                
                // 先将文本按句子分割
                // 使用正则表达式匹配句子结束标志：句号、问号、感叹号后跟空格或结束
                const sentenceParts = chapter2.split(/(?<=[.!?])\s+/);
                //console.log('初始分割的句子:', sentenceParts);
                
                // 对每个句子部分处理引号
                for (const part of sentenceParts) {
                    if (!part.trim()) continue;
                    
                    let currentText = '';
                    for (let i = 0; i < part.length; i++) {
                        if (part[i] === '"') {
                            // 如果是引号，先添加之前的文本（如果有）
                            if (currentText.trim()) {
                                paragraphSentences.push(currentText.trim());
                            }
                            // 添加引号作为单独元素
                            paragraphSentences.push('"');
                            currentText = '';
                        } else {
                            currentText += part[i];
                        }
                    }
                    
                    // 添加剩余文本（如果有）
                    if (currentText.trim()) {
                        // 确保非引号文本末尾有空格
                        let trimmedText = currentText.trim();
                        if (!trimmedText.endsWith('"') && !trimmedText.endsWith(' ')) {
                            trimmedText += ' ';
                        }
                        paragraphSentences.push(trimmedText);
                    }
                }
                
                // 只有当段落中有句子时，才将该段落添加到结果中
                if (paragraphSentences.length > 0) {
                    result.push(paragraphSentences);
                }
            }
        }
    }

    
    result=result.slice(1);

    ctx.body = { "errcode": 10000, result: result };
}