From ac172d91001e258beb8258a470c31de4f6ccd1db Mon Sep 17 00:00:00 2001
From: M Bussonnier <bussonniermatthias@gmail.com>
Date: Mon, 21 Oct 2024 15:23:26 +0200
Subject: [PATCH] Add implied assertion in WheelInfo

Some simple indexes (anaconda), only list the full-pathname of download
URL (assuming same domain, which make sens).

WheelInfo.download does not work on this case at it tries to make the
requests on the current page domain.

Thus we implicitely assume that URL start with http (well https:// would
be better, but when you prototype local index could be http.)

The error can be weird if we let it propagate (bad ziplife as you try to
decode often a 404 html page as ZIP).

This thus just add an assert at construction time to catch the error
early and that we start with actual protocol.

It should in the end be pushed earler in the code (likely at parsing
time), where we are likely to know the index URL and be able to resolve
URLs at that time.

I think there was also a missing comma in test parametrisations, and I
added a !r in a few places as I had some error with empty filenames,
without quotes, so hard to see.

The conftest was also update to explicitely pass a fake URL instead of
just a filename.

I'm not entirely sure we should allow constructing URLs with things that
don't have a protocol though, as this can be confusing.
---
 micropip/_utils.py        |  4 ++--
 micropip/wheelinfo.py     |  6 ++++++
 tests/conftest.py         |  2 +-
 tests/test_install.py     |  2 +-
 tests/test_transaction.py | 10 +++++++---
 5 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/micropip/_utils.py b/micropip/_utils.py
index 9d6bc350..1167a010 100644
--- a/micropip/_utils.py
+++ b/micropip/_utils.py
@@ -142,9 +142,9 @@ def check_compatible(filename: str) -> None:
     try:
         tags = parse_tags(filename)
     except InvalidWheelFilename:
-        raise ValueError(f"Wheel filename is invalid: {filename}") from None
+        raise ValueError(f"Wheel filename is invalid: {filename!r}") from None
     except InvalidVersion:
-        raise ValueError(f"Wheel version is invalid: {filename}") from None
+        raise ValueError(f"Wheel version is invalid: {filename!r}") from None
 
     tag: Tag = next(iter(tags))
     if "emscripten" not in tag.platform:
diff --git a/micropip/wheelinfo.py b/micropip/wheelinfo.py
index c6d255fa..197ea4cb 100644
--- a/micropip/wheelinfo.py
+++ b/micropip/wheelinfo.py
@@ -54,6 +54,9 @@ class WheelInfo:
     _dist_info: Path | None = None
 
     def __post_init__(self):
+        assert (
+            self.url.startwith(p) for p in ("http:", "https:", "emfs:", "file:")
+        ), self.url
         self._project_name = safe_name(self.name)
 
     @classmethod
@@ -63,7 +66,10 @@ def from_url(cls, url: str) -> "WheelInfo":
         See https://www.python.org/dev/peps/pep-0427/#file-name-convention
         """
         parsed_url = urlparse(url)
+        if parsed_url.scheme == "":
+            url = "file:///" + url
         file_name = Path(parsed_url.path).name
+        assert file_name, (url, file_name, parsed_url)
         name, version, build, tags = parse_wheel_filename(file_name)
         return WheelInfo(
             name=name,
diff --git a/tests/conftest.py b/tests/conftest.py
index af55b88c..c704a572 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -270,7 +270,7 @@ def add_pkg_version(
         releases[version] = [
             {
                 "filename": filename,
-                "url": filename,
+                "url": f"http://fake.domain/f/{filename}",
                 "digests": {
                     "sha256": Wildcard(),
                 },
diff --git a/tests/test_install.py b/tests/test_install.py
index 111926a3..aa89b0e3 100644
--- a/tests/test_install.py
+++ b/tests/test_install.py
@@ -257,7 +257,7 @@ def _mock_fetch_bytes(arg, *args, **kwargs):
 
     msg = "Access-Control-Allow-Origin"
     with pytest.raises(ValueError, match=msg):
-        await micropip.install("htps://x.com/xxx-1.0.0-py3-none-any.whl")
+        await micropip.install("https://x.com/xxx-1.0.0-py3-none-any.whl")
 
 
 @pytest.mark.skip_refcount_check
diff --git a/tests/test_transaction.py b/tests/test_transaction.py
index 326490d3..e3f36189 100644
--- a/tests/test_transaction.py
+++ b/tests/test_transaction.py
@@ -7,17 +7,21 @@
     "path",
     [
         SNOWBALL_WHEEL,
-        f"/{SNOWBALL_WHEEL}" f"a/{SNOWBALL_WHEEL}",
+        f"/{SNOWBALL_WHEEL}",
+        f"a/{SNOWBALL_WHEEL}",
         f"/a/{SNOWBALL_WHEEL}",
         f"//a/{SNOWBALL_WHEEL}",
     ],
 )
-@pytest.mark.parametrize("protocol", ["https:", "file:", "emfs:", ""])
+@pytest.mark.parametrize(
+    "protocol",
+    ["https:", "file:", "emfs:", ""],
+)
 def test_parse_wheel_url1(protocol, path):
     pytest.importorskip("packaging")
     from micropip.transaction import WheelInfo
 
-    url = protocol + path
+    url = protocol + path if protocol else "file:///" + path
     wheel = WheelInfo.from_url(url)
     assert wheel.name == "snowballstemmer"
     assert str(wheel.version) == "2.0.0"