feat: add smart URL parser for bulk import

apps/web/src/lib/url-parser.ts

@@ -0,0 +1,43 @@
+function isValidHttpUrl(str: string): boolean {
+  try {
+    const url = new URL(str);
+    return url.protocol === "http:" || url.protocol === "https:";
+  } catch {
+    return false;
+  }
+}
+
+export function extractUrls(input: string): string[] {
+  const urls: string[] = [];
+
+  for (const rawLine of input.split("\n")) {
+    let line = rawLine.trim();
+    if (!line) continue;
+
+    // Strip numbered list prefixes: "1. ", "2) ", "3 "
+    line = line.replace(/^\d+[.)]?\s+/, "");
+    // Strip bullet prefixes: "- ", "* ", "+ "
+    line = line.replace(/^[-*+]\s+/, "");
+
+    // Extract from markdown links: [text](url)
+    const mdMatch = line.match(/\[.*?]\((https?:\/\/[^)]+)\)/);
+    if (mdMatch) {
+      urls.push(mdMatch[1]);
+      continue;
+    }
+
+    // Extract from HTML img tags: <img src="url">
+    const imgMatch = line.match(/<img[^>]+src=["'](https?:\/\/[^"']+)["']/i);
+    if (imgMatch) {
+      urls.push(imgMatch[1]);
+      continue;
+    }
+
+    line = line.trim();
+    if (isValidHttpUrl(line)) {
+      urls.push(line);
+    }
+  }
+
+  return [...new Set(urls)];
+}

tests/unit/web/url-parser.test.ts

@@ -0,0 +1,72 @@
+import { describe, expect, it } from "vitest";
+import { extractUrls } from "../../../apps/web/src/lib/url-parser.js";
+
+describe("extractUrls", () => {
+  it("extracts plain URLs one per line", () => {
+    const input = "https://example.com/a.jpg\nhttps://example.com/b.png";
+    expect(extractUrls(input)).toEqual(["https://example.com/a.jpg", "https://example.com/b.png"]);
+  });
+
+  it("strips numbered list prefixes", () => {
+    const input =
+      "1. https://example.com/a.jpg\n2) https://example.com/b.png\n3 https://example.com/c.webp";
+    expect(extractUrls(input)).toEqual([
+      "https://example.com/a.jpg",
+      "https://example.com/b.png",
+      "https://example.com/c.webp",
+    ]);
+  });
+
+  it("strips bullet prefixes", () => {
+    const input =
+      "- https://example.com/a.jpg\n* https://example.com/b.png\n+ https://example.com/c.webp";
+    expect(extractUrls(input)).toEqual([
+      "https://example.com/a.jpg",
+      "https://example.com/b.png",
+      "https://example.com/c.webp",
+    ]);
+  });
+
+  it("extracts URLs from markdown links", () => {
+    const input = "[Photo 1](https://example.com/a.jpg)\n[Photo 2](https://example.com/b.png)";
+    expect(extractUrls(input)).toEqual(["https://example.com/a.jpg", "https://example.com/b.png"]);
+  });
+
+  it("extracts URLs from HTML img tags", () => {
+    const input = '<img src="https://example.com/a.jpg">\n<img src="https://example.com/b.png" />';
+    expect(extractUrls(input)).toEqual(["https://example.com/a.jpg", "https://example.com/b.png"]);
+  });
+
+  it("handles mixed formats", () => {
+    const input = `1. https://example.com/a.jpg
+- [Photo](https://example.com/b.png)
+<img src="https://example.com/c.webp">
+https://example.com/d.avif`;
+    expect(extractUrls(input)).toEqual([
+      "https://example.com/a.jpg",
+      "https://example.com/b.png",
+      "https://example.com/c.webp",
+      "https://example.com/d.avif",
+    ]);
+  });
+
+  it("deduplicates URLs", () => {
+    const input = "https://example.com/a.jpg\nhttps://example.com/a.jpg";
+    expect(extractUrls(input)).toEqual(["https://example.com/a.jpg"]);
+  });
+
+  it("filters out non-HTTP URLs", () => {
+    const input = "ftp://example.com/a.jpg\nhttps://example.com/b.png\nnot-a-url";
+    expect(extractUrls(input)).toEqual(["https://example.com/b.png"]);
+  });
+
+  it("returns empty array for empty input", () => {
+    expect(extractUrls("")).toEqual([]);
+    expect(extractUrls("  \n  \n  ")).toEqual([]);
+  });
+
+  it("preserves URLs with query parameters", () => {
+    const input = "https://example.com/photo?id=123&size=large";
+    expect(extractUrls(input)).toEqual(["https://example.com/photo?id=123&size=large"]);
+  });
+});