Properly parse the content disposition filename (#46)

If the content disposition header filename uses quotes, `pyodide-build`
includes the quotes in the literal filename, which e.g. confuses
`shutil.unpack_archive` in determining the file type.

This PR includes a simple fix to check and strip the quotes using the
`email.message.Message` parser to properly extract the filename (see
https://stackoverflow.com/a/78073510).

pyodide_build/buildpkg.py

@@ -7,13 +7,13 @@
 import fnmatch
 import http.client
 import os
-import re
 import shutil
 import subprocess
 import sys
 import warnings
 from collections.abc import Iterator
 from datetime import datetime
+from email.message import Message
 from pathlib import Path
 from typing import Any, cast
 
@@ -59,6 +59,20 @@ def _make_whlfile(
 )
 
 
+def _extract_tarballname(url: str, headers: dict) -> str:
+    tarballname = url.split("/")[-1]
+
+    if "Content-Disposition" in headers:
+        msg = Message()
+        msg["Content-Disposition"] = headers["Content-Disposition"]
+
+        filename = msg.get_filename()
+        if filename is not None:
+            tarballname = filename
+
+    return tarballname
+
+
 class RecipeBuilder:
     """
     A class to build a Pyodide meta.yaml recipe.
@@ -323,14 +337,7 @@ def _download_and_extract(self) -> None:
 
         self.build_dir.mkdir(parents=True, exist_ok=True)
 
-        tarballname = url.split("/")[-1]
-        if "Content-Disposition" in response.headers:
-            filenames = re.findall(
-                "filename=(.+)", response.headers["Content-Disposition"]
-            )
-            if filenames:
-                tarballname = filenames[0]
-
+        tarballname = _extract_tarballname(url, response.headers)
         tarballpath = self.build_dir / tarballname
         tarballpath.write_bytes(response.content)
 

pyodide_build/tests/test_buildpkg.py

@@ -260,3 +260,24 @@ def test_copy_sharedlib(tmp_path):
     deps = ("sharedlib-test.so", "sharedlib-test-dep.so", "sharedlib-test-dep2.so")
     for dep in deps:
         assert dep in dep_map
+
+
+def test_extract_tarballname():
+    url = "https://www.test.com/ball.tar.gz"
+    headers = [
+        {},
+        {"Content-Disposition": "inline"},
+        {"Content-Disposition": "attachment"},
+        {"Content-Disposition": 'attachment; filename="ball 2.tar.gz"'},
+        {"Content-Disposition": "attachment; filename*=UTF-8''ball%203.tar.gz"},
+    ]
+    tarballnames = [
+        "ball.tar.gz",
+        "ball.tar.gz",
+        "ball.tar.gz",
+        "ball 2.tar.gz",
+        "ball 3.tar.gz",
+    ]
+
+    for header, tarballname in zip(headers, tarballnames, strict=True):
+        assert buildpkg._extract_tarballname(url, header) == tarballname