anhuiqiang
/
KnowledgeBase


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498
							const fs = require('fs');
const { execSync } = require('child_process');
const path = require('path');
const puppeteer = require('puppeteer');

console.log('=== MD to PDF Converter Starting ===');
console.log('Node.js version:', process.version);
console.log('Working directory:', process.cwd());
console.log('Input path:', process.argv[2]);
console.log('Output path:', process.argv[3]);

// Arguments: node md_to_pdf.js <input_md_path> <output_pdf_path>
const inputPath = process.argv[2];
const outputPath = process.argv[3];

if (!inputPath || !outputPath) {
    console.error('Usage: node md_to_pdf.js <input_md_path> <output_pdf_path>');
    process.exit(1);
}

console.log(`Processing Markdown: ${inputPath}`);

(async () => {
    try {
        console.log('Reading input file...');
        let mdContent = fs.readFileSync(inputPath, 'utf8');
        console.log(`File read successfully, length: ${mdContent.length} characters`);

        // 1. Protect Math Blocks
        const mathBlocks = [];
        const placeholderPrefix = 'MATHBLOCK_PLACEHOLDER_';

        mdContent = mdContent.replace(/\$\$([\s\S]*?)\$\$/g, (match, p1) => {
            const id = mathBlocks.length;
            mathBlocks.push(`$$${p1}$$`);
            return `${placeholderPrefix}${id}`;
        });

        mdContent = mdContent.replace(/\$([^\$\n]+?)\$/g, (match, p1) => {
            const id = mathBlocks.length;
            mathBlocks.push(`$${p1}$`);
            return `${placeholderPrefix}${id}`;
        });
        console.log(`Protected ${mathBlocks.length} math blocks`);

        // 2. Convert to HTML using marked (CLI via npx or library?)
        // Since we are in a container, we should use the library directly if possible,
        // but the reference uses npx. To avoid npx/network dependency at runtime,
        // we will require 'marked' from node_modules (assuming we verify it's installed).
        const marked = require('marked');
        console.log('Parsing markdown content...');
        let finalHtml = marked.parse(mdContent);
        console.log('Markdown parsed successfully');

        // 3. Restore Math Blocks
        mathBlocks.forEach((block, index) => {
            finalHtml = finalHtml.replace(`${placeholderPrefix}${index}`, block);
        });

        // 4. Fix Mermaid syntax
        finalHtml = finalHtml.replace(
            /<pre><code class="language-mermaid">([\s\S]*?)<\/code><\/pre>/g,
            (match, content) => {
                content = content.replace(/&quot;/g, '"')
                    .replace(/&#39;/g, "'")
                    .replace(/&gt;/g, '>')
                    .replace(/&lt;/g, '<')
                    .replace(/&amp;/g, '&');
                return `<div class="mermaid">${content}</div>`;
            }
        );

        // 5. Wrap in Template
        const template = `
<!DOCTYPE html>
<html lang="zh-CN">
<head>
    <meta charset="UTF-8">
    <title>Document</title>
    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/github-markdown-css/5.2.0/github-markdown-light.min.css">

    <!-- Mermaid -->
    <script src="https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js"></script>

    <!-- MathJax -->
    <script>
    window.MathJax = {
      tex: {
        inlineMath: [['$', '$'], ['\\\\(', '\\\\)']],
        displayMath: [['$$', '$$'], ['\\\\[', '\\\\]']],
        processEscapes: false
      },
      startup: {
        pageReady: () => {
            return MathJax.startup.defaultPageReady().then(() => {
                const div = document.createElement('div');
                div.id = 'mathjax-finished';
                div.style.display = 'none';
                document.body.appendChild(div);
            });
        }
      }
    };
    </script>
    <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>

    <style>
        body {
            box-sizing: border-box;
            margin: 0 auto;
            padding: 20px;
        }
        .mermaid {
            display: flex;
            justify-content: center;
            margin: 20px 0;
        }
        table {
            width: 100% !important;
            display: table !important;
        }
    </style>

    <!-- Embedded Mermaid Library -->
    <script>
        // This is a minimal stub to prevent errors when mermaid is referenced but not available
        if (typeof window.mermaid === 'undefined') {
            window.mermaid = {
                initialize: function() {},
                init: function() {},
                render: function() {}
            };
        }
    </script>

    <!-- MathJax configuration and library -->
    <script>
        window.MathJax = {
          tex: {
            inlineMath: [['$', '$'], ['\\\\(', '\\\\)']],
            displayMath: [['$$', '$$'], ['\\\\[', '\\\\]']],
            processEscapes: false
          },
          startup: {
            pageReady: () => {
                return MathJax.startup.defaultPageReady().then(() => {
                    const div = document.createElement('div');
                    div.id = 'mathjax-finished';
                    div.style.display = 'none';
                    document.body.appendChild(div);
                });
            }
          }
        };
    </script>
    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
</head>
<body class="markdown-body">
${finalHtml}
<script>
    // Initialize mermaid if it's available
    if (typeof mermaid !== 'undefined') {
        mermaid.initialize({ startOnLoad: true, theme: 'default', securityLevel: 'loose' });
    } else {
        console.log('Mermaid library not loaded, skipping initialization');
    }
</script>
</body>
</html>`;

        console.log('Template prepared, starting PDF generation...');

        // 6. Generate PDF with Puppeteer
        console.log('Starting Puppeteer browser launch...');
        const browser = await puppeteer.launch({
            executablePath: '/usr/bin/chromium-browser', // Alpine location
            args: [
                '--no-sandbox',
                '--disable-setuid-sandbox',
                '--disable-dev-shm-usage',
                '--disable-background-timer-throttling',
                '--disable-renderer-backgrounding',
                '--disable-backgrounding-occluded-windows',
                '--memory-pressure-off',
                '--js-flags=--max-old-space-size=4096',  // 增加内存限制
                '--enable-features=NetworkService',
                '--disable-features=VizDisplayCompositor',
                '--disable-gpu',
                '--disable-web-security',
                '--disable-features=VizDisplayCompositor'
            ],
            headless: 'new',
            timeout: 120000  // Increased timeout for containerized environment
        });
        console.log('Browser launched successfully');

        const page = await browser.newPage();
        console.log('Page created successfully');

        // ページのビューポートとユーザーエージェントを設定
        await page.setViewport({ width: 1200, height: 800 });
        await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
        console.log('Viewport and user agent set');

        // さまざまなタイムアウトを設定 - 長時間の待機を避けるためにデフォルト値を低下
        await page.setDefaultNavigationTimeout(30000); // 30秒
        await page.setDefaultTimeout(30000); // 30秒
        console.log('Timeouts configured');

        // すべての外部リソースの読み込みをブロックするリクエストをインターセプト
        await page.setRequestInterception(true);
        page.on('request', (req) => {
            // すべての外部リソース要求を完全にブロック（CDNリソースを含む）してネットワークタイムアウトを回避
            const url = req.url();

            if (url.startsWith('http') || url.startsWith('https') || url.startsWith('ftp')) {
                // すべての外部リクエストに空白のレスポンスを返して、ネットワークタイムアウトエラーを回避
                req.respond({
                    status: 200,
                    contentType: 'text/plain',
                    body: ''
                }).catch(() => {});
            } else {
                // ローカルおよびdata URLリソースを許可
                req.continue().catch(() => {});
            }
        });
        console.log('Request interception configured to block all external resources');

        // エラーイベントを監視
        page.on('error', (error) => {
            console.error('Page error:', error);
        });

        page.on('pageerror', (error) => {
            console.error('Page error event:', error);
        });

        page.on('console', (msg) => {
            console.log('Browser console:', msg.text());
        });

        console.log('Error listeners attached');

        // 再試行メカニズム
        let success = false;
        let attempts = 0;
        const maxAttempts = 3;

        while (!success && attempts < maxAttempts) {
            attempts++;
            console.log(`Attempt ${attempts} of ${maxAttempts} for PDF generation...`);
            console.log(`HTML template length: ${template.length} characters`);

            try {
                console.log('About to navigate to data URL...');
                // 外部リソースを待たずに高速なナビゲーションオプションを使用
                await page.goto(`data:text/html;charset=UTF-8,${encodeURIComponent(template)}`, {
                    waitUntil: 'domcontentloaded',  // 等待DOM加载完成，但不等待资源
                    timeout: 30000  // Reduced timeout for faster failure
                });
                console.log('Page loaded successfully');

                // 画像の読み込みを待機（タイムアウトあり、読み込み失敗の画像は素早くスキップ）
                try {
                    console.log('Checking for images to load...');
                    await page.evaluate(async () => {
                        const images = Array.from(document.querySelectorAll('img'));
                        console.log(`Found ${images.length} images on the page`);
                        if (images.length > 0) {
                            // すべての画像の読み込みを待つのではなく、短時間だけ待って次に進む
                            await new Promise((resolve) => {
                                setTimeout(() => {
                                    console.log(`Continuing after attempting to load ${images.length} images`);
                                    resolve();
                                }, 500); // 只等待500ms，不管图像是否加载完成
                            });
                        }
                    });
                } catch (e) {
                    console.warn('Error checking images:', e.message);
                }

                // MathJaxのレンダリングを待機（タイムアウトあり）
                console.log('Checking for MathJax...');
                let mathjaxFinished = false;
                let mermaidProcessed = false;  // 移动变量声明到这里
                try {
                    // ページに数式が含まれているか確認（MathJaxは通常、$...$または$$...$$形式の数式を処理します）
                    const hasMathContent = await page.evaluate(() => {
                        const html = document.documentElement.innerHTML;
                        // 数学記号のタグを確認
                        return html.includes('$') || html.includes('\\(') || html.includes('\\[') ||
                               html.includes('\\begin{') || html.includes('math-tex') ||
                               document.querySelectorAll('mjx-container').length > 0 ||
                               document.querySelectorAll('[class*="math"]').length > 0;
                    });

                    console.log(`Math content found: ${hasMathContent}`);

                    if (hasMathContent) {
                        console.log('Math content detected, waiting for MathJax...');

                        // 特定のセレクタを無限に待つのではなく、MathJaxの初期化に合理的な時間を待機
                        await new Promise(r => setTimeout(r, 1000)); // 短暂等待1秒

                        // MathJaxが存在するか再度確認
                        const mathjaxExists = await page.evaluate(() => typeof window.MathJax !== 'undefined');

                        if (mathjaxExists) {
                            // MathJaxが存在する場合、レンダリング完了を待機
                            await page.evaluate(async () => {
                                if (window.MathJax && window.MathJax.Hub) {
                                    await window.MathJax.Hub.Queue(['Typeset', window.MathJax.Hub]);
                                } else if (window.MathJax && window.MathJax.typesetPromise) {
                                    await window.MathJax.typesetPromise();
                                }
                            });

                            console.log('MathJax typesetting completed');
                            mathjaxFinished = true;
                        } else {
                            console.log('MathJax not found after content check');
                        }
                    } else {
                        console.log('No math content found, skipping MathJax wait');
                    }
                } catch (e) {
                    console.warn('Error checking MathJax:', e.message);
                }

                // MathJaxが完了していない場合、追加の時間を待機
                if (!mathjaxFinished) {
                    console.log('Waiting 1 second before generating PDF...');
                    await new Promise(r => setTimeout(r, 1000));
                }

                // Mermaidが完了していない場合、追加の時間を待機
                if (!mermaidProcessed) {
                    console.log('Waiting 1 second before generating PDF...');
                    await new Promise(r => setTimeout(r, 1000));
                }

                // 等待 Mermaid 图表渲染
                console.log('Checking for Mermaid diagrams...');
                try {
                    // ページにMermaidチャートコンテナがあるか確認
                    const mermaidElementsCount = await page.evaluate(() => document.querySelectorAll('.mermaid').length);
                    console.log(`Mermaid diagrams found: ${mermaidElementsCount > 0}`);

                    if (mermaidElementsCount > 0) {
                        console.log(`Processing ${mermaidElementsCount} Mermaid diagrams...`);

                        // Mermaidライブラリが存在するか確認し、初期化を試みる
                        const mermaidExists = await page.evaluate(() => typeof mermaid !== 'undefined');

                        if (mermaidExists) {
                            console.log('Mermaid library found, attempting to initialize...');

                            await page.evaluate(async () => {
                                // mermaidオブジェクトが存在するか確認
                                if (typeof mermaid !== 'undefined' && mermaid.init) {
                                    try {
                                        // Mermaidチャートの初期化を試みる
                                        mermaid.init(undefined, '.mermaid');
                                    } catch (e) {
                                        console.log('Mermaid init error:', e.message);
                                    }
                                } else {
                                    console.log('Mermaid library not fully loaded, skipping initialization');
                                }

                                // レンダリング完了を待機（最大5秒）
                                const startTime = Date.now();
                                while (Date.now() - startTime < 5000) {
                                    // 未完成のMermaidチャートがあるか確認
                                    const incompleteCharts = document.querySelectorAll('.mermaid:not(.mermaid-loaded)');
                                    if (incompleteCharts.length === 0) {
                                        break;
                                    }
                                    // 等待一小段时间后重试
                                    await new Promise(r => setTimeout(r, 100));
                                }
                            });
                        } else {
                            console.log('Mermaid library not found in document, skipping processing');
                        }

                        console.log('Mermaid diagrams processed');
                        mermaidProcessed = true;
                    } else {
                        console.log('No Mermaid diagrams found, skipping wait');
                    }
                } catch (e) {
                    console.warn('Error processing Mermaid:', e.message);
                }

                // 等待页面基本渲染完成（不等待所有外部资源）
                console.log('Waiting for basic page content to be loaded...');
                try {
                    // complete状態ではなくDOMContentLoadedイベントを待機
                    await page.waitForFunction(() => document.readyState !== 'loading', { timeout: 10000 });  // Reduced timeout
                    console.log('Page DOM loaded, readyState is not loading');
                } catch (e) {
                    console.warn('DOM did not finish loading, continuing...', e.message);
                }

                // 确保所有异步操作完成后再生成PDF
                console.log('Waiting 2 seconds before generating PDF...');
                await new Promise(r => setTimeout(r, 2000));

                console.log('Generating PDF file...');
                await page.pdf({
                    path: outputPath,
                    format: 'A4',
                    printBackground: true,
                    scale: 0.75, // Scale down to fit more content
                    margin: { top: '10mm', right: '10mm', bottom: '10mm', left: '10mm' },
                    timeout: 120000
                });
                console.log('PDF generated successfully');

                success = true;
                console.log(`PDF successfully generated at ${outputPath}`);

            } catch (error) {
                console.error(`Attempt ${attempts} failed:`, error.message);
                console.error(`Error stack:`, error.stack);

                // 致命的なエラーの場合は再試行不要
                if (error.message.includes('Protocol error') ||
                    error.message.includes('Target closed') ||
                    error.message.includes('Browser closed') ||
                    error.message.includes('Connection closed') ||
                    error.message.includes('Navigation failed') ||
                    error.message.includes('net::ERR_CONNECTION_CLOSED')) {
                    console.error('Fatal browser error occurred, aborting retries');
                    throw error;
                }

                if (attempts >= maxAttempts) {
                    // すべての再試行が失敗した場合、最も簡略化された方法を試す
                    console.log('All attempts failed, trying most basic PDF generation...');
                    console.log('Creating a new page for basic method...');

                    // 重新创建页面以确保干净的状态
                    const basicPage = await browser.newPage();
                    await basicPage.setViewport({ width: 1200, height: 800 });
                    await basicPage.setDefaultNavigationTimeout(60000);

                    await basicPage.goto(`data:text/html;charset=UTF-8,${encodeURIComponent(template)}`, {
                        waitUntil: 'domcontentloaded',
                        timeout: 120000  // Increased timeout for containerized environment
                    });

                    // 等待一段较短的时间
                    console.log('Waiting 2 seconds in basic method...');
                    await new Promise(r => setTimeout(r, 2000));

                    try {
                        console.log('Generating PDF with basic method...');
                        await basicPage.pdf({
                            path: outputPath,
                            format: 'A4',
                            printBackground: true,
                            scale: 0.75,
                            margin: { top: '10mm', right: '10mm', bottom: '10mm', left: '10mm' },
                            timeout: 300000  // Increased timeout for containerized environment
                        });
                        success = true;
                        console.log(`PDF generated using basic method at ${outputPath}`);
                        await basicPage.close();
                    } catch (basicError) {
                        console.error('Basic PDF generation also failed:', basicError.message);
                        console.error('Basic error stack:', basicError.stack);
                        await basicPage.close();
                        throw basicError;
                    }
                } else {
                    // 一定時間待機してから再試行（システムが復旧する時間を与える）
                    const delay = 10000 * attempts; // 逐次的に遅延時間を増加
                    console.log(`Waiting ${delay}ms before retry...`);
                    await new Promise(r => setTimeout(r, delay));
                }
            }
        }

        console.log('Closing browser...');
        await browser.close();
        console.log('Browser closed');
        console.log('=== MD to PDF Conversion Completed Successfully ===');

    } catch (err) {
        console.error('Error during conversion:', err);
        console.error('Error stack:', err.stack);
        process.exit(1);
    }
})();