Fix: Content-disposition filename matcher - improve regexp to work wi…

…th white space + non latin filename in utf8
Touffy · Nov 13, 2024 · bda1d4e · bda1d4e
1 parent 6b86177
commit bda1d4e
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/src/metadata.ts b/src/metadata.ts
@@ -21,7 +21,7 @@ export function normalizeMetadata(input?: File | Response | BufferLike | StreamL
   }
   if (input instanceof Response) {
     const contentDisposition = input.headers.get("content-disposition")
-    const filename = contentDisposition && contentDisposition.match(/filename=['"]?([^'";]+)['"]?(?:;|$)/i)   
+    const filename = contentDisposition && contentDisposition.match(/;\s*filename\*?\s*=\s*(?:UTF-\d+''|)["']?([^;"'\r\n]*)["']?(?:;|$)/i);   
     const urlName = filename && filename[1] || input.url && new URL(input.url).pathname.split("/").findLast(Boolean)
     const decoded = urlName && decodeURIComponent(urlName)
     // @ts-ignore allow coercion from null to zero

diff --git a/test/metadata.test.ts b/test/metadata.test.ts
@@ -19,6 +19,14 @@ Deno.test("normalizeMetadata guesses filename from Content-Disposition", () => {
   assertEquals(metadata, { uncompressedSize: 0n, encodedName, nameIsBuffer: false })
 })
 
+Deno.test("normalizeMetadata guesses filename from non latin Content-Disposition", () => {
+  const metadata = normalizeMetadata(new Response("four", {
+    headers: { "content-disposition": "attachment; filename* = UTF-8''%CF%8C%CE%BD%CE%BF%CE%BC%CE%B1%20%CE%B1%CF%81%CF%87%CE%B5%CE%AF%CE%BF%CF%85.txt" }
+  }))
+  assertEquals(metadata, { uncompressedSize: 0n,encodedName: new TextEncoder().encode("όνομα αρχείου.txt"), nameIsBuffer: false })
+})
+
+
 Deno.test("normalizeMetadata guesses filename from a Response URL", () => {
   const response = Object.create(Response.prototype, {
     url: { get() { return "https://example.com/path/test.txt" } },