Fix file:// drive URLs on POSIX and .b2d detection with a query

file://C:/x names the host C:, which only Windows can reach, so POSIX
now raises instead of silently producing a relative path.  And the
suffix check that routes .b2d stores to cache_storage= saw the query
string, not the name; strip it (and any fragment) before comparing.

Author: FrancescAlted

src/blosc2/core.py

@@ -629,6 +629,10 @@ def normalize_urlpath(urlpath: object) -> object:
         parsed = urllib.parse.urlparse(urlpath)
         netloc = "" if parsed.netloc.lower() in ("", "localhost") else parsed.netloc
         if re.fullmatch("[A-Za-z]:", netloc):
+            if os.name != "nt":
+                raise ValueError(
+                    f"{urlpath} names the host {netloc!r}; only Windows can reach one, as a drive"
+                )
             # A Windows drive lands in netloc for the two-slash form, `file://C:/x`
             prefix = netloc
         elif not netloc:

src/blosc2/schunk.py

@@ -2019,7 +2019,7 @@ def _open_fsspec_url(urlpath: str, mode: str, offset: int, kwargs: dict):
     requested = [k for k, v in kwargs.items() if v is not None]
     if requested:
         raise NotImplementedError(f"{', '.join(requested)} on an fsspec URL requires passing cache_storage=")
-    if urlpath.endswith(".b2d"):
+    if urlpath.split("?", 1)[0].split("#", 1)[0].endswith(".b2d"):
         raise NotImplementedError(
             "directory containers (.b2d, sparse frames) on an fsspec URL require "
             "passing cache_storage= to fetch them locally first"

tests/test_fsspec.py

@@ -136,6 +136,11 @@ def test_dir_container_needs_cache():
         blosc2.open("memory://store.b2d")
 
 
+def test_dir_container_with_query_needs_cache():
+    with pytest.raises(NotImplementedError, match="cache_storage"):
+        blosc2.open("memory://store.b2d?version=1")
+
+
 def test_cached_open(tmp_path):
     a = blosc2.arange(10, dtype="i4")
     with fsspec.open("memory://c.b2nd", "wb") as f:
@@ -554,15 +559,23 @@ def test_zip_store_needs_cache(tmp_path):
     [
         ("file:///tmp/a.b2nd", "/tmp/a.b2nd"),
         ("file://localhost/tmp/a.b2nd", "/tmp/a.b2nd"),
-        # A Windows drive lands in the netloc for the two-slash form
-        ("file://C:/data/a.b2nd", "C:"),
     ],
 )
 def test_normalize_file_url(url, expected):
     # as_posix() because the separator is the platform's, the layout is not
     assert expected in pathlib.PurePath(blosc2.core.normalize_urlpath(url)).as_posix()
 
 
+def test_normalize_windows_drive_url():
+    # file://C:/x names the host C:, which only Windows can reach, as a drive
+    url = "file://C:/data/a.b2nd"
+    if os.name == "nt":
+        assert pathlib.PurePath(blosc2.core.normalize_urlpath(url)).as_posix() == "C:/data/a.b2nd"
+    else:
+        with pytest.raises(ValueError, match="C:"):
+            blosc2.core.normalize_urlpath(url)
+
+
 def test_normalize_file_url_with_a_host():
     # A host authority is a UNC path, which only Windows can reach; concatenating
     # it without its two slashes would silently make it a relative path instead