fix cache invalidation for PythonInfo (#2925)

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Author: esafak

docs/changelog/2467.bugfix.rst

@@ -0,0 +1,2 @@
+Fix cache invalidation for PythonInfo by hashing `py_info.py`.
+Contributed by :user:`esafak`.

src/virtualenv/discovery/cached_py_info.py

@@ -7,6 +7,7 @@
 
 from __future__ import annotations
 
+import hashlib
 import logging
 import os
 import random
@@ -58,14 +59,23 @@ def _get_via_file_cache(cls, app_data, path, exe, env):
         path_modified = path.stat().st_mtime
     except OSError:
         path_modified = -1
+    py_info_script = Path(os.path.abspath(__file__)).parent / "py_info.py"
+    try:
+        py_info_hash = hashlib.sha256(py_info_script.read_bytes()).hexdigest()
+    except OSError:
+        py_info_hash = None
+
     if app_data is None:
         app_data = AppDataDisabled()
     py_info, py_info_store = None, app_data.py_info(path)
     with py_info_store.locked():
         if py_info_store.exists():  # if exists and matches load
             data = py_info_store.read()
-            of_path, of_st_mtime, of_content = data["path"], data["st_mtime"], data["content"]
-            if of_path == path_text and of_st_mtime == path_modified:
+            of_path = data.get("path")
+            of_st_mtime = data.get("st_mtime")
+            of_content = data.get("content")
+            of_hash = data.get("hash")
+            if of_path == path_text and of_st_mtime == path_modified and of_hash == py_info_hash:
                 py_info = cls._from_dict(of_content.copy())
                 sys_exe = py_info.system_executable
                 if sys_exe is not None and not os.path.exists(sys_exe):
@@ -80,6 +90,7 @@ def _get_via_file_cache(cls, app_data, path, exe, env):
                     "st_mtime": path_modified,
                     "path": path_text,
                     "content": py_info._to_dict(),  # noqa: SLF001
+                    "hash": py_info_hash,
                 }
                 py_info_store.write(data)
             else:

tests/unit/discovery/py_info/test_py_info.py

@@ -14,6 +14,7 @@
 
 import pytest
 
+from virtualenv.create.via_global_ref.builtin.cpython.common import is_macos_brew
 from virtualenv.discovery import cached_py_info
 from virtualenv.discovery.py_info import PythonInfo, VersionInfo
 from virtualenv.discovery.py_spec import PythonSpec
@@ -154,6 +155,36 @@ def test_py_info_cache_clear(mocker, session_app_data):
     assert spy.call_count >= 2 * count
 
 
+def test_py_info_cache_invalidation_on_py_info_change(mocker, session_app_data):
+    # 1. Get a PythonInfo object for the current executable, this will cache it.
+    PythonInfo.from_exe(sys.executable, session_app_data)
+
+    # 2. Spy on _run_subprocess
+    spy = mocker.spy(cached_py_info, "_run_subprocess")
+
+    # 3. Modify the content of py_info.py
+    py_info_script = Path(cached_py_info.__file__).parent / "py_info.py"
+    original_content = py_info_script.read_text(encoding="utf-8")
+
+    try:
+        # 4. Clear the in-memory cache
+        mocker.patch.dict(cached_py_info._CACHE, {}, clear=True)  # noqa: SLF001
+        py_info_script.write_text(original_content + "\n# a comment", encoding="utf-8")
+
+        # 5. Get the PythonInfo object again
+        info = PythonInfo.from_exe(sys.executable, session_app_data)
+
+        # 6. Assert that _run_subprocess was called again
+        if is_macos_brew(info):
+            assert spy.call_count in {2, 3}
+        else:
+            assert spy.call_count == 2
+
+    finally:
+        # Restore the original content
+        py_info_script.write_text(original_content, encoding="utf-8")
+
+
 @pytest.mark.skipif(not fs_supports_symlink(), reason="symlink is not supported")
 @pytest.mark.xfail(
     # https://doc.pypy.org/en/latest/install.html?highlight=symlink#download-a-pre-built-pypy

tests/unit/discovery/test_discovery.py

@@ -257,6 +257,7 @@ def test_absolute_path_does_not_exist(tmp_path):
         capture_output=True,
         text=True,
         check=False,
+        encoding="utf-8",
     )
 
     # Check that the command was successful
@@ -283,6 +284,7 @@ def test_absolute_path_does_not_exist_fails(tmp_path):
         capture_output=True,
         text=True,
         check=False,
+        encoding="utf-8",
     )
 
     # Check that the command failed