feat(cloner): add cloner-library and finalize pdf-library rename

packages/cloner-library/src/AssetManager.ts

@@ -0,0 +1,93 @@
+import axios from "axios";
+import fs from "node:fs";
+import path from "node:path";
+
+export interface AssetMap {
+    [originalUrl: string]: string;
+}
+
+export class AssetManager {
+    private userAgent: string;
+
+    constructor(userAgent: string = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36") {
+        this.userAgent = userAgent;
+    }
+
+    public sanitizePath(rawPath: string): string {
+        return rawPath
+            .split("/")
+            .map((p) => p.replace(/[^a-z0-9._-]/gi, "_"))
+            .join("/");
+    }
+
+    public async downloadFile(url: string, assetsDir: string): Promise<string | null> {
+        if (url.startsWith("//")) url = `https:${url}`;
+        if (!url.startsWith("http")) return null;
+
+        try {
+            const u = new URL(url);
+            const relPath = this.sanitizePath(u.hostname + u.pathname);
+            const dest = path.join(assetsDir, relPath);
+
+            if (fs.existsSync(dest)) return `./assets/${relPath}`;
+
+            const res = await axios.get(url, {
+                responseType: "arraybuffer",
+                headers: { "User-Agent": this.userAgent },
+                timeout: 15000,
+                validateStatus: () => true,
+            });
+
+            if (res.status !== 200) return null;
+
+            if (!fs.existsSync(path.dirname(dest)))
+                fs.mkdirSync(path.dirname(dest), { recursive: true });
+            fs.writeFileSync(dest, Buffer.from(res.data));
+            return `./assets/${relPath}`;
+        } catch {
+            return null;
+        }
+    }
+
+    public async processCssRecursively(
+        cssContent: string,
+        cssUrl: string,
+        assetsDir: string,
+        urlMap: AssetMap,
+        depth = 0,
+    ): Promise<string> {
+        if (depth > 5) return cssContent;
+
+        const urlRegex = /(?:url\(["']?|@import\s+["'])([^"'\)]+)["']?\)?/gi;
+        let match;
+        let newContent = cssContent;
+
+        while ((match = urlRegex.exec(cssContent)) !== null) {
+            const originalUrl = match[1];
+            if (originalUrl.startsWith("data:") || originalUrl.startsWith("blob:"))
+                continue;
+
+            try {
+                const absUrl = new URL(originalUrl, cssUrl).href;
+                const local = await this.downloadFile(absUrl, assetsDir);
+
+                if (local) {
+                    const u = new URL(cssUrl);
+                    const cssPath = u.hostname + u.pathname;
+                    const assetPath = new URL(absUrl).hostname + new URL(absUrl).pathname;
+
+                    const rel = path.relative(
+                        path.dirname(this.sanitizePath(cssPath)),
+                        this.sanitizePath(assetPath),
+                    );
+
+                    newContent = newContent.split(originalUrl).join(rel);
+                    urlMap[absUrl] = local;
+                }
+            } catch {
+                // Ignore
+            }
+        }
+        return newContent;
+    }
+}