Restore pre 22.3 wheel cache pathing

Prior to bad03ef wheel cache paths
incorporated source material hashes in their paths. This commit which
ended up in 22.3 stopped including that information. This is problematic
for two reasons. First our cache is no longer encoding data integrity
information that was previously intentionally included. Second it means
anyone upgrading from < 22.3 to 22.3 will have orphaned wheel cache
entries.

The fix here is to update the Link object to set Link.link_hash in the
Link.from_json method. Otherwise the hash information is simply missing.

This will cause anyone upgrading from 22.3 to newer to have orphaned
wheels, but that seems worthwile considering 22.3 hasn't been around as
long as the previous implementation and we get stronger data integrity
controls out of it.

This fixes pypa#11527

Author: cboylan

news/11527.bugfix.rst

@@ -0,0 +1,2 @@
+This change restores 22.2.x wheel cache behavior to pip allowing the
+cache to find existing entries.

src/pip/_internal/models/link.py

@@ -248,6 +248,11 @@ def from_json(
         yanked_reason = file_data.get("yanked")
         dist_info_metadata = file_data.get("dist-info-metadata")
         hashes = file_data.get("hashes", {})
+        link_hash = None
+        if hashes:
+            for hash_name in _SUPPORTED_HASHES:
+                if hash_name in hashes:
+                    link_hash = LinkHash(name=hash_name, value=hashes[hash_name])
 
         # The Link.yanked_reason expects an empty string instead of a boolean.
         if yanked_reason and not isinstance(yanked_reason, str):
@@ -262,6 +267,7 @@ def from_json(
             requires_python=pyrequire,
             yanked_reason=yanked_reason,
             hashes=hashes,
+            link_hash=link_hash,
             dist_info_metadata=dist_info_metadata,
         )
 

tests/unit/test_cache.py

@@ -1,7 +1,7 @@
 import os
 from pathlib import Path
 
-from pip._vendor.packaging.tags import Tag
+from pip._vendor.packaging.tags import Tag, interpreter_name, interpreter_version
 
 from pip._internal.cache import WheelCache, _hash_dict
 from pip._internal.models.format_control import FormatControl
@@ -52,6 +52,48 @@ def test_cache_hash() -> None:
     assert h == "f83b32dfa27a426dec08c21bf006065dd003d0aac78e7fc493d9014d"
 
 
+def test_link_to_cache(tmpdir: Path) -> None:
+    """
+    Test that Link.from_json() produces Links with consistent cache
+    locations
+    """
+    wc = WheelCache(os.fspath(tmpdir), FormatControl())
+    # Define our expectations for stable cache path.
+    i_name = interpreter_name()
+    i_version = interpreter_version()
+    key_parts = {
+        "url": "https://files.pythonhosted.org/packages/a6/91/"
+        "86a6eac449ddfae239e93ffc1918cf33fd9bab35c04d1e963b311e347a73/"
+        "netifaces-0.11.0.tar.gz",
+        "sha256": "043a79146eb2907edf439899f262b3dfe41717d34124298ed281139a8b93ca32",
+        "interpreter_name": i_name,
+        "interpreter_version": i_version,
+    }
+    expected_hash = _hash_dict(key_parts)
+    parts = [
+        expected_hash[:2],
+        expected_hash[2:4],
+        expected_hash[4:6],
+        expected_hash[6:],
+    ]
+    pathed_hash = os.path.join(*parts)
+    # Check working from a Link produces the same result.
+    file_data = {
+        "filename": "netifaces-0.11.0.tar.gz",
+        "hashes": {
+            "sha256": key_parts["sha256"],
+        },
+        "requires-python": "",
+        "url": key_parts["url"],
+        "yanked": False,
+    }
+    page_url = "https://pypi.org/simple/netifaces/"
+    link = Link.from_json(file_data=file_data, page_url=page_url)
+    assert link
+    path = wc.get_path_for_link(link)
+    assert pathed_hash in path
+
+
 def test_get_cache_entry(tmpdir: Path) -> None:
     wc = WheelCache(os.fspath(tmpdir), FormatControl())
     persi_link = Link("https://g.c/o/r/persi")