Switch to more recent 'files' API from importlib.resources from Pytho…

…n 3.9 and importlib_metadata 1.1. Add explicit temporary file cleanup behavior using atexit. Fixes certifi#131.

certifi/compat.py

@@ -0,0 +1,17 @@
+"""
+Fallback for Python prior to 3.9 where importlib_resources
+is not available.
+Does not support modules where __file__ is not defined on
+the module.
+"""
+
+import os
+
+
+def read_text(_module, _path):
+    with open(where(), "r", encoding="ascii") as data:
+        return data.read()
+
+
+def where():
+    return os.path.join(os.path.dirname(__file__), "cacert.pem")

certifi/core.py

@@ -6,55 +6,13 @@
 
 This module returns the installation location of cacert.pem or its contents.
 """
-import os
 
-try:
-    from importlib.resources import path as get_path, read_text
-
-    _CACERT_CTX = None
-    _CACERT_PATH = None
-
-    def where():
-        # This is slightly terrible, but we want to delay extracting the file
-        # in cases where we're inside of a zipimport situation until someone
-        # actually calls where(), but we don't want to re-extract the file
-        # on every call of where(), so we'll do it once then store it in a
-        # global variable.
-        global _CACERT_CTX
-        global _CACERT_PATH
-        if _CACERT_PATH is None:
-            # This is slightly janky, the importlib.resources API wants you to
-            # manage the cleanup of this file, so it doesn't actually return a
-            # path, it returns a context manager that will give you the path
-            # when you enter it and will do any cleanup when you leave it. In
-            # the common case of not needing a temporary file, it will just
-            # return the file system location and the __exit__() is a no-op.
-            #
-            # We also have to hold onto the actual context manager, because
-            # it will do the cleanup whenever it gets garbage collected, so
-            # we will also store that at the global level as well.
-            _CACERT_CTX = get_path("certifi", "cacert.pem")
-            _CACERT_PATH = str(_CACERT_CTX.__enter__())
-
-        return _CACERT_PATH
 
-
-except ImportError:
-    # This fallback will work for Python versions prior to 3.7 that lack the
-    # importlib.resources module but relies on the existing `where` function
-    # so won't address issues with environments like PyOxidizer that don't set
-    # __file__ on modules.
-    def read_text(_module, _path, encoding="ascii"):
-        with open(where(), "r", encoding=encoding) as data:
-            return data.read()
-
-    # If we don't have importlib.resources, then we will just do the old logic
-    # of assuming we're on the filesystem and munge the path directly.
-    def where():
-        f = os.path.dirname(__file__)
-
-        return os.path.join(f, "cacert.pem")
+try:
+    from .resources import where, read_text
+except Exception:
+    from .compat import where, read_text  # noqa: F401
 
 
 def contents():
-    return read_text("certifi", "cacert.pem", encoding="ascii")
+    return read_text("certifi", "cacert.pem")

certifi/resources.py

@@ -0,0 +1,28 @@
+import atexit
+import functools
+
+try:
+    from importlib import resources
+except ImportError:
+    import importlib_resources as resources
+
+
+# ensure 'files' API is present
+resources.files
+read_text = resources.read_text
+
+
+def as_file(path):
+    """
+    Ensure the path is a file on the file system for the duration
+    of the interpreter run.
+    """
+    ctx = resources.as_file(path)
+    tmp_copy = ctx.__enter__()
+    atexit.register(tmp_copy.__exit__, None, None, None)
+    return tmp_copy
+
+
+@functools.lru_cache()
+def where():
+    return as_file(resources.files('certifi') / 'cacert.pem')