fix: preserve charset detection and block CGNAT range in parse-url SSRF fix

Follow-up to the multi-reviewer review of the SSRF fix:

- Restore charset handling lost when switching from extract() to
  response.text(): non-UTF-8 pages (Shift_JIS/GBK/EUC/Big5, common on CJK
  sites this project targets) decoded as mojibake. Now read the body as
  bytes, detect charset from Content-Type / <meta charset>, and decode
  with TextDecoder before extractFromHtml.
- Wrap extractFromHtml in try/catch: it throws (not returns null) on
  empty/non-HTML bodies, which previously surfaced as a 500 instead of the
  intended 400.
- Add 100.64.0.0/10 (RFC 6598 CGNAT) to isPrivateIp; it is routable inside
  some cloud internal networks and was a residual SSRF target.
- Add tests for CGNAT, its boundaries, 0.0.0.0, and DNS-resolved IPv6.

app/api/parse-url/route.ts

@@ -7,6 +7,31 @@ const MAX_CONTENT_LENGTH = 150000 // Match PDF limit
 const EXTRACT_TIMEOUT_MS = 15000
 const USER_AGENT = "Mozilla/5.0 (compatible; NextAIDrawio/1.0)"
 
+// Detect the page's charset so non-UTF-8 pages (Shift_JIS/GBK/EUC/Big5, common
+// on CJK sites) are decoded correctly. Response.text() always assumes UTF-8 and
+// would produce mojibake; the article-extractor library does the same detection
+// when it fetches the page itself, which we no longer rely on.
+function detectCharset(
+    contentType: string | null,
+    buffer: ArrayBuffer,
+): string {
+    // 1. HTTP Content-Type header charset (most authoritative).
+    const headerCharset = contentType?.match(/charset=([^;]+)/i)?.[1]?.trim()
+    // 2. <meta charset> / <meta http-equiv> in the first bytes of the document.
+    const head = new TextDecoder("utf-8").decode(buffer.slice(0, 4096))
+    const metaCharset =
+        head.match(/<meta[^>]+charset=["']?\s*([\w-]+)/i)?.[1] ||
+        head.match(/<meta[^>]+content=["'][^"']*charset=([\w-]+)/i)?.[1]
+    const charset = (headerCharset || metaCharset || "utf-8").toLowerCase()
+    // TextDecoder throws on unknown encoding labels; fall back to UTF-8.
+    try {
+        new TextDecoder(charset)
+        return charset
+    } catch {
+        return "utf-8"
+    }
+}
+
 export async function POST(req: Request) {
     try {
         const { url } = await req.json()
@@ -72,7 +97,9 @@ export async function POST(req: Request) {
                 )
             }
 
-            html = await response.text()
+            const buffer = await response.arrayBuffer()
+            const charset = detectCharset(contentType, buffer)
+            html = new TextDecoder(charset).decode(buffer)
         } catch (err: any) {
             if (err?.name === "AbortError") {
                 return NextResponse.json(
@@ -90,7 +117,14 @@ export async function POST(req: Request) {
             clearTimeout(timeoutId)
         }
 
-        const article = await extractFromHtml(html, url)
+        // extractFromHtml throws (not returns null) on empty/non-HTML bodies,
+        // so map any parse error to the same 400 as the no-content case.
+        let article: Awaited<ReturnType<typeof extractFromHtml>>
+        try {
+            article = await extractFromHtml(html, url)
+        } catch {
+            article = null
+        }
 
         if (!article || !article.content) {
             return NextResponse.json(

lib/ssrf-protection.ts

@@ -41,6 +41,7 @@ function isPrivateIp(ip: string): boolean {
         if (a === 169 && b === 254) return true // 169.254.0.0/16 (link-local)
         if (a === 127) return true // 127.0.0.0/8 (loopback)
         if (a === 0) return true // 0.0.0.0/8
+        if (a === 100 && b >= 64 && b <= 127) return true // 100.64.0.0/10 (CGNAT, used by some cloud internal networks)
     }
 
     return false

tests/unit/ssrf-protection.test.ts

@@ -31,9 +31,26 @@ describe("isPrivateUrl", () => {
         expect(await isPrivateUrl("http://10.0.0.5/")).toBe(true)
         expect(await isPrivateUrl("http://192.168.1.1/")).toBe(true)
         expect(await isPrivateUrl("http://169.254.169.254/")).toBe(true)
+        expect(await isPrivateUrl("http://0.0.0.0/")).toBe(true)
+        // 100.64.0.0/10 CGNAT (RFC 6598), routable in some cloud internal nets
+        expect(await isPrivateUrl("http://100.64.0.1/")).toBe(true)
+        expect(await isPrivateUrl("http://100.127.255.255/")).toBe(true)
         expect(lookupMock).not.toHaveBeenCalled()
     })
 
+    it("treats CGNAT boundaries correctly", async () => {
+        // 100.63.x and 100.128.x are outside 100.64.0.0/10 → public
+        lookupMock.mockResolvedValue([{ address: "100.63.255.255", family: 4 }])
+        expect(await isPrivateUrl("http://just-below.example/")).toBe(false)
+        lookupMock.mockResolvedValue([{ address: "100.128.0.1", family: 4 }])
+        expect(await isPrivateUrl("http://just-above.example/")).toBe(false)
+    })
+
+    it("blocks a hostname that resolves to a private IPv6 address", async () => {
+        lookupMock.mockResolvedValue([{ address: "fd00::1", family: 6 }])
+        expect(await isPrivateUrl("http://v6.example.com/")).toBe(true)
+    })
+
     it("allows public URLs that resolve to public IPs", async () => {
         lookupMock.mockResolvedValue([{ address: "93.184.216.34", family: 4 }])
         expect(await isPrivateUrl("https://example.com/article")).toBe(false)