@tyroneross/blog-scraper 0.1.0 → 0.3.0

package/dist/lib/circuit-breaker.js

@@ -0,0 +1,89 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.circuitBreakers = exports.CircuitBreaker = void 0;
+class CircuitBreaker {
+    constructor(options) {
+        this.failures = 0;
+        this.lastFailureTime = 0;
+        this.state = 'CLOSED';
+        this.options = options;
+    }
+    async execute(operation) {
+        if (this.state === 'OPEN') {
+            if (Date.now() - this.lastFailureTime < this.options.resetTimeout) {
+                throw new Error(`[CircuitBreaker:${this.options.name}] Circuit is OPEN - preventing request`);
+            }
+            else {
+                this.state = 'HALF_OPEN';
+                console.log(`🔄 [CircuitBreaker:${this.options.name}] Circuit moving to HALF_OPEN state`);
+            }
+        }
+        try {
+            const result = await this.executeWithTimeout(operation);
+            this.onSuccess();
+            return result;
+        }
+        catch (error) {
+            this.onFailure();
+            throw error;
+        }
+    }
+    async executeWithTimeout(operation) {
+        return new Promise((resolve, reject) => {
+            const timer = setTimeout(() => {
+                reject(new Error(`[CircuitBreaker:${this.options.name}] Operation timeout after ${this.options.timeout}ms`));
+            }, this.options.timeout);
+            operation()
+                .then(result => {
+                clearTimeout(timer);
+                resolve(result);
+            })
+                .catch(error => {
+                clearTimeout(timer);
+                reject(error);
+            });
+        });
+    }
+    onSuccess() {
+        this.failures = 0;
+        this.state = 'CLOSED';
+    }
+    onFailure() {
+        this.failures++;
+        this.lastFailureTime = Date.now();
+        if (this.failures >= this.options.failureThreshold) {
+            this.state = 'OPEN';
+            console.error(`❌ [CircuitBreaker:${this.options.name}] Circuit opened after ${this.failures} failures`);
+        }
+    }
+    getState() {
+        return {
+            state: this.state,
+            failures: this.failures,
+            lastFailureTime: this.lastFailureTime
+        };
+    }
+}
+exports.CircuitBreaker = CircuitBreaker;
+// Pre-configured circuit breakers for common services
+exports.circuitBreakers = {
+    rss: new CircuitBreaker({
+        name: 'RSS',
+        failureThreshold: 3,
+        timeout: 15000, // 15 seconds
+        resetTimeout: 30000 // 30 seconds
+    }),
+    scraping: new CircuitBreaker({
+        name: 'Scraping',
+        failureThreshold: 5,
+        timeout: 10000, // 10 seconds
+        resetTimeout: 30000 // 30 seconds
+    }),
+    scrapingTest: new CircuitBreaker({
+        name: 'ScrapingTest',
+        failureThreshold: 3,
+        timeout: 120000, // 120 seconds to accommodate large sites with many sitemaps
+        resetTimeout: 60000 // 1 minute
+    })
+};
+//# sourceMappingURL=circuit-breaker.js.map

package/dist/lib/circuit-breaker.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"circuit-breaker.js","sourceRoot":"","sources":["../../lib/circuit-breaker.ts"],"names":[],"mappings":";;;AAOA,MAAa,cAAc;IAMzB,YAAY,OAA8B;QALlC,aAAQ,GAAG,CAAC,CAAC;QACb,oBAAe,GAAG,CAAC,CAAC;QACpB,UAAK,GAAoC,QAAQ,CAAC;QAIxD,IAAI,CAAC,OAAO,GAAG,OAAO,CAAC;IACzB,CAAC;IAED,KAAK,CAAC,OAAO,CAAI,SAA2B;QAC1C,IAAI,IAAI,CAAC,KAAK,KAAK,MAAM,EAAE,CAAC;YAC1B,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,eAAe,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC;gBAClE,MAAM,IAAI,KAAK,CAAC,mBAAmB,IAAI,CAAC,OAAO,CAAC,IAAI,wCAAwC,CAAC,CAAC;YAChG,CAAC;iBAAM,CAAC;gBACN,IAAI,CAAC,KAAK,GAAG,WAAW,CAAC;gBACzB,OAAO,CAAC,GAAG,CAAC,sBAAsB,IAAI,CAAC,OAAO,CAAC,IAAI,qCAAqC,CAAC,CAAC;YAC5F,CAAC;QACH,CAAC;QAED,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,kBAAkB,CAAC,SAAS,CAAC,CAAC;YACxD,IAAI,CAAC,SAAS,EAAE,CAAC;YACjB,OAAO,MAAM,CAAC;QAChB,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,IAAI,CAAC,SAAS,EAAE,CAAC;YACjB,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;IAEO,KAAK,CAAC,kBAAkB,CAAI,SAA2B;QAC7D,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;YACrC,MAAM,KAAK,GAAG,UAAU,CAAC,GAAG,EAAE;gBAC5B,MAAM,CAAC,IAAI,KAAK,CAAC,mBAAmB,IAAI,CAAC,OAAO,CAAC,IAAI,6BAA6B,IAAI,CAAC,OAAO,CAAC,OAAO,IAAI,CAAC,CAAC,CAAC;YAC/G,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;YAEzB,SAAS,EAAE;iBACR,IAAI,CAAC,MAAM,CAAC,EAAE;gBACb,YAAY,CAAC,KAAK,CAAC,CAAC;gBACpB,OAAO,CAAC,MAAM,CAAC,CAAC;YAClB,CAAC,CAAC;iBACD,KAAK,CAAC,KAAK,CAAC,EAAE;gBACb,YAAY,CAAC,KAAK,CAAC,CAAC;gBACpB,MAAM,CAAC,KAAK,CAAC,CAAC;YAChB,CAAC,CAAC,CAAC;QACP,CAAC,CAAC,CAAC;IACL,CAAC;IAEO,SAAS;QACf,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC;QAClB,IAAI,CAAC,KAAK,GAAG,QAAQ,CAAC;IACxB,CAAC;IAEO,SAAS;QACf,IAAI,CAAC,QAAQ,EAAE,CAAC;QAChB,IAAI,CAAC,eAAe,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QAElC,IAAI,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAC,OAAO,CAAC,gBAAgB,EAAE,CAAC;YACnD,IAAI,CAAC,KAAK,GAAG,MAAM,CAAC;YACpB,OAAO,CAAC,KAAK,CAAC,qBAAqB,IAAI,CAAC,OAAO,CAAC,IAAI,0BAA0B,IAAI,CAAC,QAAQ,WAAW,CAAC,CAAC;QAC1G,CAAC;IACH,CAAC;IAED,QAAQ;QACN,OAAO;YACL,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,QAAQ,EAAE,IAAI,CAAC,QAAQ;YACvB,eAAe,EAAE,IAAI,CAAC,eAAe;SACtC,CAAC;IACJ,CAAC;CACF;AAtED,wCAsEC;AAED,sDAAsD;AACzC,QAAA,eAAe,GAAG;IAC7B,GAAG,EAAE,IAAI,cAAc,CAAC;QACtB,IAAI,EAAE,KAAK;QACX,gBAAgB,EAAE,CAAC;QACnB,OAAO,EAAE,KAAK,EAAE,aAAa;QAC7B,YAAY,EAAE,KAAK,CAAC,aAAa;KAClC,CAAC;IAEF,QAAQ,EAAE,IAAI,cAAc,CAAC;QAC3B,IAAI,EAAE,UAAU;QAChB,gBAAgB,EAAE,CAAC;QACnB,OAAO,EAAE,KAAK,EAAE,aAAa;QAC7B,YAAY,EAAE,KAAK,CAAC,aAAa;KAClC,CAAC;IAEF,YAAY,EAAE,IAAI,cAAc,CAAC;QAC/B,IAAI,EAAE,cAAc;QACpB,gBAAgB,EAAE,CAAC;QACnB,OAAO,EAAE,MAAM,EAAE,4DAA4D;QAC7E,YAAY,EAAE,KAAK,CAAC,WAAW;KAChC,CAAC;CACH,CAAC"}

package/dist/lib/content-extractor.d.ts

@@ -0,0 +1,13 @@
+/**
+ * Simplified content extractor for standalone app
+ * Uses Mozilla Readability for article extraction
+ */
+import { ExtractedContent } from './types';
+export declare class ContentExtractor {
+    extractContent(url: string): Promise<ExtractedContent | null>;
+    /**
+     * Extract published time from document metadata
+     */
+    private extractPublishedTime;
+}
+//# sourceMappingURL=content-extractor.d.ts.map

package/dist/lib/content-extractor.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"content-extractor.d.ts","sourceRoot":"","sources":["../../lib/content-extractor.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAIH,OAAO,EAAE,gBAAgB,EAAE,MAAM,SAAS,CAAC;AAE3C,qBAAa,gBAAgB;IACrB,cAAc,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,GAAG,IAAI,CAAC;IA6CnE;;OAEG;IACH,OAAO,CAAC,oBAAoB;CAqB7B"}

package/dist/lib/content-extractor.js

@@ -0,0 +1,75 @@
+"use strict";
+/**
+ * Simplified content extractor for standalone app
+ * Uses Mozilla Readability for article extraction
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.ContentExtractor = void 0;
+const readability_1 = require("@mozilla/readability");
+const jsdom_1 = require("jsdom");
+class ContentExtractor {
+    async extractContent(url) {
+        try {
+            const response = await fetch(url, {
+                headers: {
+                    'User-Agent': 'Mozilla/5.0 (compatible; ScraperApp/1.0)',
+                },
+            });
+            if (!response.ok) {
+                throw new Error(`HTTP ${response.status}: ${response.statusText}`);
+            }
+            const html = await response.text();
+            const dom = new jsdom_1.JSDOM(html, { url });
+            const reader = new readability_1.Readability(dom.window.document);
+            const article = reader.parse();
+            if (!article) {
+                return null;
+            }
+            // Calculate reading time (200 words per minute)
+            const wordCount = article.textContent?.split(/\s+/).length || 0;
+            const readingTime = Math.ceil(wordCount / 200);
+            // Extract publish time from metadata
+            const publishedTime = this.extractPublishedTime(dom.window.document);
+            return {
+                title: article.title ?? undefined,
+                byline: article.byline ?? undefined,
+                content: article.content ?? undefined,
+                textContent: article.textContent ?? undefined,
+                length: article.length ?? undefined,
+                excerpt: article.excerpt ?? undefined,
+                siteName: article.siteName ?? undefined,
+                publishedTime,
+                readingTime,
+            };
+        }
+        catch (error) {
+            console.error(`[ContentExtractor] Failed to extract from ${url}:`, error);
+            return null;
+        }
+    }
+    /**
+     * Extract published time from document metadata
+     */
+    extractPublishedTime(doc) {
+        // Try various metadata sources
+        const selectors = [
+            'meta[property="article:published_time"]',
+            'meta[name="article:published_time"]',
+            'meta[property="og:published_time"]',
+            'meta[name="published_time"]',
+            'meta[name="date"]',
+            'time[datetime]',
+        ];
+        for (const selector of selectors) {
+            const element = doc.querySelector(selector);
+            if (element) {
+                const content = element.getAttribute('content') || element.getAttribute('datetime');
+                if (content)
+                    return content;
+            }
+        }
+        return undefined;
+    }
+}
+exports.ContentExtractor = ContentExtractor;
+//# sourceMappingURL=content-extractor.js.map

package/dist/lib/content-extractor.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"content-extractor.js","sourceRoot":"","sources":["../../lib/content-extractor.ts"],"names":[],"mappings":";AAAA;;;GAGG;;;AAEH,sDAAmD;AACnD,iCAA8B;AAG9B,MAAa,gBAAgB;IAC3B,KAAK,CAAC,cAAc,CAAC,GAAW;QAC9B,IAAI,CAAC;YACH,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;gBAChC,OAAO,EAAE;oBACP,YAAY,EAAE,0CAA0C;iBACzD;aACF,CAAC,CAAC;YAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;gBACjB,MAAM,IAAI,KAAK,CAAC,QAAQ,QAAQ,CAAC,MAAM,KAAK,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;YACrE,CAAC;YAED,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YACnC,MAAM,GAAG,GAAG,IAAI,aAAK,CAAC,IAAI,EAAE,EAAE,GAAG,EAAE,CAAC,CAAC;YACrC,MAAM,MAAM,GAAG,IAAI,yBAAW,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YACpD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,EAAE,CAAC;YAE/B,IAAI,CAAC,OAAO,EAAE,CAAC;gBACb,OAAO,IAAI,CAAC;YACd,CAAC;YAED,gDAAgD;YAChD,MAAM,SAAS,GAAG,OAAO,CAAC,WAAW,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC;YAChE,MAAM,WAAW,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,GAAG,GAAG,CAAC,CAAC;YAE/C,qCAAqC;YACrC,MAAM,aAAa,GAAG,IAAI,CAAC,oBAAoB,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAErE,OAAO;gBACL,KAAK,EAAE,OAAO,CAAC,KAAK,IAAI,SAAS;gBACjC,MAAM,EAAE,OAAO,CAAC,MAAM,IAAI,SAAS;gBACnC,OAAO,EAAE,OAAO,CAAC,OAAO,IAAI,SAAS;gBACrC,WAAW,EAAE,OAAO,CAAC,WAAW,IAAI,SAAS;gBAC7C,MAAM,EAAE,OAAO,CAAC,MAAM,IAAI,SAAS;gBACnC,OAAO,EAAE,OAAO,CAAC,OAAO,IAAI,SAAS;gBACrC,QAAQ,EAAE,OAAO,CAAC,QAAQ,IAAI,SAAS;gBACvC,aAAa;gBACb,WAAW;aACZ,CAAC;QACJ,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO,CAAC,KAAK,CAAC,6CAA6C,GAAG,GAAG,EAAE,KAAK,CAAC,CAAC;YAC1E,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IAED;;OAEG;IACK,oBAAoB,CAAC,GAAa;QACxC,+BAA+B;QAC/B,MAAM,SAAS,GAAG;YAChB,yCAAyC;YACzC,qCAAqC;YACrC,oCAAoC;YACpC,6BAA6B;YAC7B,mBAAmB;YACnB,gBAAgB;SACjB,CAAC;QAEF,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;YACjC,MAAM,OAAO,GAAG,GAAG,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC;YAC5C,IAAI,OAAO,EAAE,CAAC;gBACZ,MAAM,OAAO,GAAG,OAAO,CAAC,YAAY,CAAC,SAAS,CAAC,IAAI,OAAO,CAAC,YAAY,CAAC,UAAU,CAAC,CAAC;gBACpF,IAAI,OAAO;oBAAE,OAAO,OAAO,CAAC;YAC9B,CAAC;QACH,CAAC;QAED,OAAO,SAAS,CAAC;IACnB,CAAC;CACF;AAtED,4CAsEC"}

package/dist/lib/formatters/html-to-markdown.d.ts

@@ -0,0 +1,21 @@
+/**
+ * Convert HTML to clean Markdown
+ * - Preserves headings, bold, lists, links, code blocks
+ * - Strips navigation, forms, UI elements
+ * - Smart paragraph detection
+ */
+export declare function htmlToMarkdown(html: string): string;
+/**
+ * Strip non-article content from HTML before conversion
+ * Removes navigation, forms, UI elements
+ */
+export declare function stripNonArticleContent(html: string): string;
+/**
+ * Convert HTML to Markdown with full cleaning
+ * This is the main function developers should use
+ */
+export declare function convertToMarkdown(html: string, options?: {
+    cleanNonArticle?: boolean;
+    smartParagraphs?: boolean;
+}): string;
+//# sourceMappingURL=html-to-markdown.d.ts.map

package/dist/lib/formatters/html-to-markdown.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"html-to-markdown.d.ts","sourceRoot":"","sources":["../../../lib/formatters/html-to-markdown.ts"],"names":[],"mappings":"AAEA;;;;;GAKG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAgDnD;AA0DD;;;GAGG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAyB3D;AAED;;;GAGG;AACH,wBAAgB,iBAAiB,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,GAAE;IACvD,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B,eAAe,CAAC,EAAE,OAAO,CAAC;CACtB,GAAG,MAAM,CAiBd"}

package/dist/lib/formatters/html-to-markdown.js

@@ -0,0 +1,146 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.htmlToMarkdown = htmlToMarkdown;
+exports.stripNonArticleContent = stripNonArticleContent;
+exports.convertToMarkdown = convertToMarkdown;
+const turndown_1 = __importDefault(require("turndown"));
+/**
+ * Convert HTML to clean Markdown
+ * - Preserves headings, bold, lists, links, code blocks
+ * - Strips navigation, forms, UI elements
+ * - Smart paragraph detection
+ */
+function htmlToMarkdown(html) {
+    if (!html)
+        return '';
+    // Create Turndown service with custom rules
+    const turndownService = new turndown_1.default({
+        headingStyle: 'atx', // Use # for headings
+        codeBlockStyle: 'fenced', // Use ``` for code blocks
+        bulletListMarker: '-', // Use - for lists
+        emDelimiter: '*', // Use * for emphasis
+        strongDelimiter: '**', // Use ** for strong
+    });
+    // Remove unwanted elements before conversion
+    turndownService.remove([
+        'script',
+        'style',
+        'nav',
+        'header',
+        'footer',
+        'aside',
+        'form',
+        'button',
+        'input',
+        'select',
+        'textarea',
+        'iframe',
+        'noscript',
+    ]);
+    // Custom rule: Clean up attributes from elements
+    turndownService.addRule('cleanAttributes', {
+        filter: ['div', 'span', 'p', 'section', 'article'],
+        replacement: (content) => {
+            // Just return content, stripping the wrapper
+            return content;
+        },
+    });
+    // Convert HTML to Markdown
+    let markdown = turndownService.turndown(html);
+    // Post-processing: Smart paragraph detection
+    markdown = smartParagraphDetection(markdown);
+    // Clean up excessive whitespace
+    markdown = normalizeWhitespace(markdown);
+    return markdown;
+}
+/**
+ * Smart paragraph detection
+ * Adds proper spacing between sections
+ */
+function smartParagraphDetection(markdown) {
+    // Split into lines
+    const lines = markdown.split('\n');
+    const result = [];
+    for (let i = 0; i < lines.length; i++) {
+        const line = lines[i];
+        const prevLine = i > 0 ? lines[i - 1] : '';
+        const nextLine = i < lines.length - 1 ? lines[i + 1] : '';
+        result.push(line);
+        // Add extra line break after headings
+        if (line.match(/^#{1,6}\s/) && nextLine && !nextLine.match(/^#{1,6}\s/)) {
+            result.push('');
+        }
+        // Add extra line break before headings
+        if (nextLine.match(/^#{1,6}\s/) && line && !line.match(/^#{1,6}\s/) && !prevLine.match(/^$/)) {
+            result.push('');
+        }
+        // Add line break after lists
+        if (line.match(/^[-*+]\s/) && nextLine && !nextLine.match(/^[-*+]\s/) && !nextLine.match(/^$/)) {
+            result.push('');
+        }
+    }
+    return result.join('\n');
+}
+/**
+ * Normalize whitespace
+ * - Remove excessive line breaks (more than 2)
+ * - Trim lines
+ */
+function normalizeWhitespace(markdown) {
+    // Replace 3+ consecutive line breaks with just 2
+    markdown = markdown.replace(/\n{3,}/g, '\n\n');
+    // Trim each line
+    markdown = markdown
+        .split('\n')
+        .map(line => line.trim())
+        .join('\n');
+    // Remove leading/trailing whitespace
+    markdown = markdown.trim();
+    return markdown;
+}
+/**
+ * Strip non-article content from HTML before conversion
+ * Removes navigation, forms, UI elements
+ */
+function stripNonArticleContent(html) {
+    if (!html)
+        return '';
+    // Remove elements with specific classes/IDs that indicate non-article content
+    const nonArticlePatterns = [
+        /<nav\b[^>]*>.*?<\/nav>/gi,
+        /<header\b[^>]*>.*?<\/header>/gi,
+        /<footer\b[^>]*>.*?<\/footer>/gi,
+        /<aside\b[^>]*>.*?<\/aside>/gi,
+        /<form\b[^>]*>.*?<\/form>/gi,
+        /<div[^>]*class="[^"]*(?:nav|menu|sidebar|advertisement|ads|social|share|comment|popup|modal)[^"]*"[^>]*>.*?<\/div>/gi,
+        /<div[^>]*id="[^"]*(?:nav|menu|sidebar|advertisement|ads|social|share|comment|popup|modal)[^"]*"[^>]*>.*?<\/div>/gi,
+    ];
+    let cleaned = html;
+    for (const pattern of nonArticlePatterns) {
+        cleaned = cleaned.replace(pattern, '');
+    }
+    // Remove all class, id, and data attributes
+    cleaned = cleaned.replace(/\s*class="[^"]*"/gi, '');
+    cleaned = cleaned.replace(/\s*id="[^"]*"/gi, '');
+    cleaned = cleaned.replace(/\s*data-[^=]*="[^"]*"/gi, '');
+    return cleaned;
+}
+/**
+ * Convert HTML to Markdown with full cleaning
+ * This is the main function developers should use
+ */
+function convertToMarkdown(html, options = {}) {
+    const { cleanNonArticle = true, smartParagraphs = true, } = options;
+    let processedHtml = html;
+    // Step 1: Strip non-article content if requested
+    if (cleanNonArticle) {
+        processedHtml = stripNonArticleContent(processedHtml);
+    }
+    // Step 2: Convert to Markdown
+    const markdown = htmlToMarkdown(processedHtml);
+    return markdown;
+}
+//# sourceMappingURL=html-to-markdown.js.map

package/dist/lib/formatters/html-to-markdown.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"html-to-markdown.js","sourceRoot":"","sources":["../../../lib/formatters/html-to-markdown.ts"],"names":[],"mappings":";;;;;AAQA,wCAgDC;AA8DD,wDAyBC;AAMD,8CAoBC;AAzKD,wDAAuC;AAEvC;;;;;GAKG;AACH,SAAgB,cAAc,CAAC,IAAY;IACzC,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IAErB,4CAA4C;IAC5C,MAAM,eAAe,GAAG,IAAI,kBAAe,CAAC;QAC1C,YAAY,EAAE,KAAK,EAAE,qBAAqB;QAC1C,cAAc,EAAE,QAAQ,EAAE,0BAA0B;QACpD,gBAAgB,EAAE,GAAG,EAAE,kBAAkB;QACzC,WAAW,EAAE,GAAG,EAAE,qBAAqB;QACvC,eAAe,EAAE,IAAI,EAAE,oBAAoB;KAC5C,CAAC,CAAC;IAEH,6CAA6C;IAC7C,eAAe,CAAC,MAAM,CAAC;QACrB,QAAQ;QACR,OAAO;QACP,KAAK;QACL,QAAQ;QACR,QAAQ;QACR,OAAO;QACP,MAAM;QACN,QAAQ;QACR,OAAO;QACP,QAAQ;QACR,UAAU;QACV,QAAQ;QACR,UAAU;KACX,CAAC,CAAC;IAEH,iDAAiD;IACjD,eAAe,CAAC,OAAO,CAAC,iBAAiB,EAAE;QACzC,MAAM,EAAE,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC;QAClD,WAAW,EAAE,CAAC,OAAO,EAAE,EAAE;YACvB,6CAA6C;YAC7C,OAAO,OAAO,CAAC;QACjB,CAAC;KACF,CAAC,CAAC;IAEH,2BAA2B;IAC3B,IAAI,QAAQ,GAAG,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IAE9C,6CAA6C;IAC7C,QAAQ,GAAG,uBAAuB,CAAC,QAAQ,CAAC,CAAC;IAE7C,gCAAgC;IAChC,QAAQ,GAAG,mBAAmB,CAAC,QAAQ,CAAC,CAAC;IAEzC,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;GAGG;AACH,SAAS,uBAAuB,CAAC,QAAgB;IAC/C,mBAAmB;IACnB,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACnC,MAAM,MAAM,GAAa,EAAE,CAAC;IAE5B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QAC3C,MAAM,QAAQ,GAAG,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QAE1D,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAElB,sCAAsC;QACtC,IAAI,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,IAAI,QAAQ,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,WAAW,CAAC,EAAE,CAAC;YACxE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAClB,CAAC;QAED,uCAAuC;QACvC,IAAI,QAAQ,CAAC,KAAK,CAAC,WAAW,CAAC,IAAI,IAAI,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;YAC7F,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAClB,CAAC;QAED,6BAA6B;QAC7B,IAAI,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,IAAI,QAAQ,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;YAC/F,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAClB,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC3B,CAAC;AAED;;;;GAIG;AACH,SAAS,mBAAmB,CAAC,QAAgB;IAC3C,iDAAiD;IACjD,QAAQ,GAAG,QAAQ,CAAC,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC;IAE/C,iBAAiB;IACjB,QAAQ,GAAG,QAAQ;SAChB,KAAK,CAAC,IAAI,CAAC;SACX,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;SACxB,IAAI,CAAC,IAAI,CAAC,CAAC;IAEd,qCAAqC;IACrC,QAAQ,GAAG,QAAQ,CAAC,IAAI,EAAE,CAAC;IAE3B,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;GAGG;AACH,SAAgB,sBAAsB,CAAC,IAAY;IACjD,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IAErB,8EAA8E;IAC9E,MAAM,kBAAkB,GAAG;QACzB,0BAA0B;QAC1B,gCAAgC;QAChC,gCAAgC;QAChC,8BAA8B;QAC9B,4BAA4B;QAC5B,sHAAsH;QACtH,mHAAmH;KACpH,CAAC;IAEF,IAAI,OAAO,GAAG,IAAI,CAAC;IACnB,KAAK,MAAM,OAAO,IAAI,kBAAkB,EAAE,CAAC;QACzC,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;IACzC,CAAC;IAED,4CAA4C;IAC5C,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,oBAAoB,EAAE,EAAE,CAAC,CAAC;IACpD,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,iBAAiB,EAAE,EAAE,CAAC,CAAC;IACjD,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,yBAAyB,EAAE,EAAE,CAAC,CAAC;IAEzD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;;GAGG;AACH,SAAgB,iBAAiB,CAAC,IAAY,EAAE,UAG5C,EAAE;IACJ,MAAM,EACJ,eAAe,GAAG,IAAI,EACtB,eAAe,GAAG,IAAI,GACvB,GAAG,OAAO,CAAC;IAEZ,IAAI,aAAa,GAAG,IAAI,CAAC;IAEzB,iDAAiD;IACjD,IAAI,eAAe,EAAE,CAAC;QACpB,aAAa,GAAG,sBAAsB,CAAC,aAAa,CAAC,CAAC;IACxD,CAAC;IAED,8BAA8B;IAC9B,MAAM,QAAQ,GAAG,cAAc,CAAC,aAAa,CAAC,CAAC;IAE/C,OAAO,QAAQ,CAAC;AAClB,CAAC"}

package/dist/lib/formatters/text-cleaner.d.ts

@@ -0,0 +1,44 @@
+/**
+ * Text cleanup utilities
+ * Normalize whitespace, remove excessive line breaks, clean HTML entities
+ */
+/**
+ * Clean text content
+ * - Normalize whitespace between paragraphs
+ * - Remove excessive line breaks
+ * - Decode HTML entities
+ * - Trim redundant spaces
+ */
+export declare function cleanText(text: string): string;
+/**
+ * Decode HTML entities ( , &, etc.)
+ */
+export declare function decodeHTMLEntities(text: string): string;
+/**
+ * Normalize whitespace
+ * - Replace multiple spaces with single space
+ * - Replace tabs with spaces
+ * - Remove trailing/leading whitespace from lines
+ */
+export declare function normalizeWhitespace(text: string): string;
+/**
+ * Detect paragraph boundaries and add proper spacing
+ * Looks for sentence endings followed by capital letters
+ */
+export declare function detectParagraphs(text: string): string;
+/**
+ * Remove URLs from text
+ * Useful for cleaning up citations or references
+ */
+export declare function removeUrls(text: string): string;
+/**
+ * Truncate text to a maximum length
+ * Breaks at word boundaries and adds ellipsis
+ */
+export declare function truncateText(text: string, maxLength: number): string;
+/**
+ * Extract plain text from HTML
+ * Quick and dirty HTML stripping
+ */
+export declare function stripHTML(html: string): string;
+//# sourceMappingURL=text-cleaner.d.ts.map

package/dist/lib/formatters/text-cleaner.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"text-cleaner.d.ts","sourceRoot":"","sources":["../../../lib/formatters/text-cleaner.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;;;;;GAMG;AACH,wBAAgB,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAkB9C;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAgCvD;AAED;;;;;GAKG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAiBxD;AAED;;;GAGG;AACH,wBAAgB,gBAAgB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CA2BrD;AAED;;;GAGG;AACH,wBAAgB,UAAU,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAE/C;AAED;;;GAGG;AACH,wBAAgB,YAAY,CAAC,IAAI,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,GAAG,MAAM,CAYpE;AAED;;;GAGG;AACH,wBAAgB,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAO9C"}

package/dist/lib/formatters/text-cleaner.js

@@ -0,0 +1,143 @@
+"use strict";
+/**
+ * Text cleanup utilities
+ * Normalize whitespace, remove excessive line breaks, clean HTML entities
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.cleanText = cleanText;
+exports.decodeHTMLEntities = decodeHTMLEntities;
+exports.normalizeWhitespace = normalizeWhitespace;
+exports.detectParagraphs = detectParagraphs;
+exports.removeUrls = removeUrls;
+exports.truncateText = truncateText;
+exports.stripHTML = stripHTML;
+/**
+ * Clean text content
+ * - Normalize whitespace between paragraphs
+ * - Remove excessive line breaks
+ * - Decode HTML entities
+ * - Trim redundant spaces
+ */
+function cleanText(text) {
+    if (!text)
+        return '';
+    let cleaned = text;
+    // Step 1: Decode HTML entities
+    cleaned = decodeHTMLEntities(cleaned);
+    // Step 2: Normalize whitespace
+    cleaned = normalizeWhitespace(cleaned);
+    // Step 3: Smart paragraph detection
+    cleaned = detectParagraphs(cleaned);
+    // Step 4: Trim
+    cleaned = cleaned.trim();
+    return cleaned;
+}
+/**
+ * Decode HTML entities ( , &, etc.)
+ */
+function decodeHTMLEntities(text) {
+    const entities = {
+        ' ': ' ',
+        '&': '&',
+        '&lt;': '<',
+        '&gt;': '>',
+        '&quot;': '"',
+        '&#039;': "'",
+        '&apos;': "'",
+        '&ndash;': '–',
+        '&mdash;': '—',
+        '&hellip;': '…',
+        '&ldquo;': '"',
+        '&rdquo;': '"',
+        '&lsquo;': '\u2018',
+        '&rsquo;': '\u2019',
+    };
+    let decoded = text;
+    for (const [entity, char] of Object.entries(entities)) {
+        decoded = decoded.replace(new RegExp(entity, 'g'), char);
+    }
+    // Handle numeric entities (&#123;, &#x1a2b;)
+    decoded = decoded.replace(/&#(\d+);/g, (_, code) => String.fromCharCode(parseInt(code, 10)));
+    decoded = decoded.replace(/&#x([0-9a-f]+);/gi, (_, code) => String.fromCharCode(parseInt(code, 16)));
+    return decoded;
+}
+/**
+ * Normalize whitespace
+ * - Replace multiple spaces with single space
+ * - Replace tabs with spaces
+ * - Remove trailing/leading whitespace from lines
+ */
+function normalizeWhitespace(text) {
+    // Replace tabs with spaces
+    let normalized = text.replace(/\t/g, ' ');
+    // Replace multiple spaces with single space (but preserve line breaks)
+    normalized = normalized.replace(/ {2,}/g, ' ');
+    // Trim each line
+    normalized = normalized
+        .split('\n')
+        .map(line => line.trim())
+        .join('\n');
+    // Replace 3+ consecutive line breaks with just 2
+    normalized = normalized.replace(/\n{3,}/g, '\n\n');
+    return normalized;
+}
+/**
+ * Detect paragraph boundaries and add proper spacing
+ * Looks for sentence endings followed by capital letters
+ */
+function detectParagraphs(text) {
+    // Split by existing line breaks
+    const lines = text.split('\n').filter(line => line.trim().length > 0);
+    const result = [];
+    for (let i = 0; i < lines.length; i++) {
+        const line = lines[i];
+        const nextLine = i < lines.length - 1 ? lines[i + 1] : '';
+        result.push(line);
+        // Add paragraph break if:
+        // 1. Current line ends with sentence-ending punctuation (. ! ?)
+        // 2. Next line starts with capital letter or number
+        // 3. Lines are not too short (likely not a title)
+        if (line.match(/[.!?]$/) &&
+            nextLine.match(/^[A-Z0-9]/) &&
+            line.length > 40 && // Avoid breaking after short lines
+            nextLine.length > 20) {
+            result.push(''); // Add empty line for paragraph break
+        }
+    }
+    return result.join('\n');
+}
+/**
+ * Remove URLs from text
+ * Useful for cleaning up citations or references
+ */
+function removeUrls(text) {
+    return text.replace(/https?:\/\/[^\s]+/g, '');
+}
+/**
+ * Truncate text to a maximum length
+ * Breaks at word boundaries and adds ellipsis
+ */
+function truncateText(text, maxLength) {
+    if (text.length <= maxLength)
+        return text;
+    // Find the last space before maxLength
+    const truncated = text.substring(0, maxLength);
+    const lastSpace = truncated.lastIndexOf(' ');
+    if (lastSpace > 0) {
+        return truncated.substring(0, lastSpace) + '…';
+    }
+    return truncated + '…';
+}
+/**
+ * Extract plain text from HTML
+ * Quick and dirty HTML stripping
+ */
+function stripHTML(html) {
+    return html
+        .replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, '')
+        .replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, '')
+        .replace(/<[^>]+>/g, '')
+        .replace(/\s+/g, ' ')
+        .trim();
+}
+//# sourceMappingURL=text-cleaner.js.map

package/dist/lib/formatters/text-cleaner.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"text-cleaner.js","sourceRoot":"","sources":["../../../lib/formatters/text-cleaner.ts"],"names":[],"mappings":";AAAA;;;GAGG;;AASH,8BAkBC;AAKD,gDAgCC;AAQD,kDAiBC;AAMD,4CA2BC;AAMD,gCAEC;AAMD,oCAYC;AAMD,8BAOC;AA/JD;;;;;;GAMG;AACH,SAAgB,SAAS,CAAC,IAAY;IACpC,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IAErB,IAAI,OAAO,GAAG,IAAI,CAAC;IAEnB,+BAA+B;IAC/B,OAAO,GAAG,kBAAkB,CAAC,OAAO,CAAC,CAAC;IAEtC,+BAA+B;IAC/B,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,CAAC;IAEvC,oCAAoC;IACpC,OAAO,GAAG,gBAAgB,CAAC,OAAO,CAAC,CAAC;IAEpC,eAAe;IACf,OAAO,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;IAEzB,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;GAEG;AACH,SAAgB,kBAAkB,CAAC,IAAY;IAC7C,MAAM,QAAQ,GAA2B;QACvC,QAAQ,EAAE,GAAG;QACb,OAAO,EAAE,GAAG;QACZ,MAAM,EAAE,GAAG;QACX,MAAM,EAAE,GAAG;QACX,QAAQ,EAAE,GAAG;QACb,QAAQ,EAAE,GAAG;QACb,QAAQ,EAAE,GAAG;QACb,SAAS,EAAE,GAAG;QACd,SAAS,EAAE,GAAG;QACd,UAAU,EAAE,GAAG;QACf,SAAS,EAAE,GAAG;QACd,SAAS,EAAE,GAAG;QACd,SAAS,EAAE,QAAQ;QACnB,SAAS,EAAE,QAAQ;KACpB,CAAC;IAEF,IAAI,OAAO,GAAG,IAAI,CAAC;IACnB,KAAK,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAC;QACtD,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3D,CAAC;IAED,6CAA6C;IAC7C,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,EAAE,CACjD,MAAM,CAAC,YAAY,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,CACxC,CAAC;IACF,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,mBAAmB,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,EAAE,CACzD,MAAM,CAAC,YAAY,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,CACxC,CAAC;IAEF,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;;;;GAKG;AACH,SAAgB,mBAAmB,CAAC,IAAY;IAC9C,2BAA2B;IAC3B,IAAI,UAAU,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC;IAE1C,uEAAuE;IACvE,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IAE/C,iBAAiB;IACjB,UAAU,GAAG,UAAU;SACpB,KAAK,CAAC,IAAI,CAAC;SACX,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;SACxB,IAAI,CAAC,IAAI,CAAC,CAAC;IAEd,iDAAiD;IACjD,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC;IAEnD,OAAO,UAAU,CAAC;AACpB,CAAC;AAED;;;GAGG;AACH,SAAgB,gBAAgB,CAAC,IAAY;IAC3C,gCAAgC;IAChC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAEtE,MAAM,MAAM,GAAa,EAAE,CAAC;IAE5B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,QAAQ,GAAG,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QAE1D,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAElB,0BAA0B;QAC1B,gEAAgE;QAChE,oDAAoD;QACpD,kDAAkD;QAClD,IACE,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC;YACpB,QAAQ,CAAC,KAAK,CAAC,WAAW,CAAC;YAC3B,IAAI,CAAC,MAAM,GAAG,EAAE,IAAI,mCAAmC;YACvD,QAAQ,CAAC,MAAM,GAAG,EAAE,EACpB,CAAC;YACD,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,qCAAqC;QACxD,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC3B,CAAC;AAED;;;GAGG;AACH,SAAgB,UAAU,CAAC,IAAY;IACrC,OAAO,IAAI,CAAC,OAAO,CAAC,oBAAoB,EAAE,EAAE,CAAC,CAAC;AAChD,CAAC;AAED;;;GAGG;AACH,SAAgB,YAAY,CAAC,IAAY,EAAE,SAAiB;IAC1D,IAAI,IAAI,CAAC,MAAM,IAAI,SAAS;QAAE,OAAO,IAAI,CAAC;IAE1C,uCAAuC;IACvC,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC;IAC/C,MAAM,SAAS,GAAG,SAAS,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;IAE7C,IAAI,SAAS,GAAG,CAAC,EAAE,CAAC;QAClB,OAAO,SAAS,CAAC,SAAS,CAAC,CAAC,EAAE,SAAS,CAAC,GAAG,GAAG,CAAC;IACjD,CAAC;IAED,OAAO,SAAS,GAAG,GAAG,CAAC;AACzB,CAAC;AAED;;;GAGG;AACH,SAAgB,SAAS,CAAC,IAAY;IACpC,OAAO,IAAI;SACR,OAAO,CAAC,qDAAqD,EAAE,EAAE,CAAC;SAClE,OAAO,CAAC,kDAAkD,EAAE,EAAE,CAAC;SAC/D,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC;SACvB,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC;SACpB,IAAI,EAAE,CAAC;AACZ,CAAC"}