bug: fix handling of xml elements with attributes (#26)

Author: matixlol

next-env.d.ts

@@ -1,6 +1,5 @@
 /// <reference types="next" />
 /// <reference types="next/image-types/global" />
-import "./.next/types/routes.d.ts";
 
 // NOTE: This file should not be edited
 // see https://nextjs.org/docs/app/api-reference/config/typescript for more information.

src/lib/rss.test.ts

@@ -162,6 +162,50 @@ describe("rss - XML to final output", () => {
     expect(normalizedRss).toMatchSnapshot();
   });
 
+  it("should handle guid with isPermaLink attribute (object instead of string)", async () => {
+    // Some feeds have <guid isPermaLink="false">...</guid> which rss-parser
+    // returns as an object like { $: { isPermaLink: "false" }, _: "actual-guid" }
+    // or just { $: { isPermaLink: "false" } } if malformed
+    const feedXml = `<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+  <channel>
+    <title>Test Feed</title>
+    <link>http://example.com</link>
+    <item>
+      <title>Article with guid attribute</title>
+      <link>http://example.com/article1</link>
+      <guid isPermaLink="false">https://example.com/?p=12345</guid>
+      <pubDate>Mon, 28 Oct 2025 10:00:00 GMT</pubDate>
+    </item>
+    <item>
+      <title>Article with normal guid</title>
+      <link>http://example.com/article2</link>
+      <guid>http://example.com/article2</guid>
+      <pubDate>Sun, 27 Oct 2025 10:00:00 GMT</pubDate>
+    </item>
+  </channel>
+</rss>`;
+
+    const result = await parseFeedFromXml(feedXml, "http://example.com/feed");
+    expect(result.error).toBeNull();
+
+    const mergedFeed = mergeFeeds(
+      [{ ...result, url: "http://example.com/feed" }],
+      "http://example.com/merged",
+    );
+
+    // This should not throw - the bug was that escapeXml received an object
+    const rssOutput = generateRSS(mergedFeed, "http://example.com/merged");
+
+    // Verify the guid is properly extracted
+    expect(rssOutput).toContain("<guid>https://example.com/?p=12345</guid>");
+    expect(rssOutput).toContain("<guid>http://example.com/article2</guid>");
+
+    // Also verify JSON Feed output works
+    const jsonOutput = generateJSONFeed(mergedFeed, "http://example.com/merged");
+    expect(jsonOutput).toContain("https://example.com/?p=12345");
+  });
+
   it("should parse Aditya Athalye's Eval/Apply Blog feed", async () => {
     const feedXml = `<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
 <channel>

src/lib/rss.ts

@@ -385,19 +385,42 @@ export function mergeFeeds(
 }
 
 // Helper functions for XML generation
-function escapeXml(unsafe: string): string {
-  if (!unsafe) return "";
+// Helper to safely coerce a value to a string.
+// Handles cases where rss-parser returns an object (e.g., { $: { isPermaLink: "false" }, _: "actual-guid" })
+// when XML elements have attributes.
+function safeString(value: unknown): string {
+  if (value == null) return "";
+  if (typeof value === "string") return value;
+  if (typeof value === "number" || typeof value === "boolean")
+    return String(value);
+
+  if (typeof value === "object") {
+    // rss-parser stores the text content in _ and attributes in $
+    const v = value as Record<string, unknown>;
+    if (typeof v._ === "string") return v._;
+    if (v._ != null) return String(v._);
+    // If there's no _ property, the element might be attribute-only (malformed)
+    return "";
+  }
+
+  return String(value);
+}
+
+function escapeXml(unsafe: unknown): string {
+  const str = safeString(unsafe);
+  if (!str) return "";
 
-  return unsafe
+  return str
     .replace(/&/g, "&amp;")
     .replace(/</g, "&lt;")
     .replace(/>/g, "&gt;")
     .replace(/"/g, "&quot;")
     .replace(/'/g, "&apos;");
 }
 
-function wrapCDATA(content: string): string {
-  return `<![CDATA[${content}]]>`;
+function wrapCDATA(content: unknown): string {
+  const str = safeString(content);
+  return `<![CDATA[${str}]]>`;
 }
 
 /**
@@ -458,12 +481,7 @@ export function generateRSS(
       // Categories
       if (item.categories && item.categories.length > 0) {
         item.categories.forEach((category: Category) => {
-          // Handle categories that may be objects with _ property (from rss-parser when they have attributes)
-          const categoryValue =
-            typeof category === "string"
-              ? category
-              : category._ || String(category);
-          itemXml += `      <category>${escapeXml(categoryValue)}</category>\n`;
+          itemXml += `      <category>${escapeXml(category)}</category>\n`;
         });
       }
 
@@ -507,17 +525,15 @@ export function generateJSONFeed(
     home_page_url: mergedFeed.link,
     feed_url: requestUrl,
     items: mergedFeed.items.map((item) => ({
-      id: item.guid || item.link || crypto.randomUUID(),
+      id: safeString(item.guid) || safeString(item.link) || crypto.randomUUID(),
       url: item.link,
       title: item.title,
       content_html: item.content,
       content_text: item.contentSnippet,
       date_published: item.isoDate || item.pubDate,
       author: item.creator ? { name: item.creator } : undefined,
       tags: item.categories
-        ? item.categories.map((cat: any) =>
-            typeof cat === "string" ? cat : cat._ || String(cat),
-          )
+        ? item.categories.map((cat) => safeString(cat))
         : undefined,
     })),
   };

tsconfig.json

@@ -15,7 +15,7 @@
     "moduleResolution": "bundler",
     "resolveJsonModule": true,
     "isolatedModules": true,
-    "jsx": "react-jsx",
+    "jsx": "preserve",
     "incremental": true,
     "plugins": [
       {