feat: update python-cachecontrol to 0.14.3-1

Makefile

@@ -5,19 +5,17 @@
 VENV=.venv
 VENV_CMD=python3 -m venv
 ACTIVATE = $(VENV)/bin/activate
-CHEESE=https://pypi.python.org/pypi
-BUMPTYPE=patch
-BUMPPRE=0
 
-
-$(VENV)/bin/pip3:
+$(VENV)/bin/pip:
 	$(VENV_CMD) $(VENV)
 
-bootstrap: $(VENV)/bin/pip3
-	$(VENV)/bin/pip3 install -e .[dev]
+bootstrap: $(VENV)/bin/pip
+	$(VENV)/bin/pip install -e .[dev]
 
 format:
-	$(VENV)/bin/black .
+	$(VENV)/bin/codespell
+	$(VENV)/bin/ruff check --fix
+	$(VENV)/bin/ruff format
 
 doc: $(VENV)/bin/sphinx-build
 	. $(ACTIVATE);

README.rst

@@ -35,7 +35,7 @@ Quickstart
   sess = requests.session()
   cached_sess = CacheControl(sess)
 
-  response = cached_sess.get('http://google.com')
+  response = cached_sess.get('https://google.com')
 
 If the URL contains any caching based headers, it will cache the
 result in a simple dictionary.

cachecontrol/__init__.py

@@ -6,9 +6,10 @@
 
 Make it easy to import from cachecontrol without long namespaces.
 """
+
 __author__ = "Eric Larson"
 __email__ = "[email protected]"
-__version__ = "0.13.1"
+__version__ = "0.14.3"
 
 from cachecontrol.adapter import CacheControlAdapter
 from cachecontrol.controller import CacheController

cachecontrol/adapter.py

@@ -5,6 +5,7 @@
 
 import functools
 import types
+import weakref
 import zlib
 from typing import TYPE_CHECKING, Any, Collection, Mapping
 
@@ -77,7 +78,7 @@ def send(
 
         return resp
 
-    def build_response(
+    def build_response(  # type: ignore[override]
         self,
         request: PreparedRequest,
         response: HTTPResponse,
@@ -125,25 +126,31 @@ def build_response(
             else:
                 # Wrap the response file with a wrapper that will cache the
                 #   response when the stream has been consumed.
-                response._fp = CallbackFileWrapper(  # type: ignore[attr-defined]
-                    response._fp,  # type: ignore[attr-defined]
+                response._fp = CallbackFileWrapper(  # type: ignore[assignment]
+                    response._fp,  # type: ignore[arg-type]
                     functools.partial(
-                        self.controller.cache_response, request, response
+                        self.controller.cache_response, request, weakref.ref(response)
                     ),
                 )
                 if response.chunked:
-                    super_update_chunk_length = response._update_chunk_length  # type: ignore[attr-defined]
+                    super_update_chunk_length = response.__class__._update_chunk_length
 
-                    def _update_chunk_length(self: HTTPResponse) -> None:
-                        super_update_chunk_length()
+                    def _update_chunk_length(
+                        weak_self: weakref.ReferenceType[HTTPResponse],
+                    ) -> None:
+                        self = weak_self()
+                        if self is None:
+                            return
+
+                        super_update_chunk_length(self)
                         if self.chunk_left == 0:
-                            self._fp._close()  # type: ignore[attr-defined]
+                            self._fp._close()  # type: ignore[union-attr]
 
-                    response._update_chunk_length = types.MethodType(  # type: ignore[attr-defined]
-                        _update_chunk_length, response
+                    response._update_chunk_length = functools.partial(  # type: ignore[method-assign]
+                        _update_chunk_length, weakref.ref(response)
                     )
 
-        resp: Response = super().build_response(request, response)  # type: ignore[no-untyped-call]
+        resp: Response = super().build_response(request, response)
 
         # See if we should invalidate the cache.
         if request.method in self.invalidating_methods and resp.ok:

cachecontrol/cache.py

@@ -6,6 +6,7 @@
 The cache object API for implementing caches. The default is a thread
 safe in-memory dictionary.
 """
+
 from __future__ import annotations
 
 from threading import Lock

cachecontrol/caches/file_cache.py

@@ -5,8 +5,10 @@
 
 import hashlib
 import os
+import tempfile
 from textwrap import dedent
 from typing import IO, TYPE_CHECKING
+from pathlib import Path
 
 from cachecontrol.cache import BaseCache, SeparateBodyBaseCache
 from cachecontrol.controller import CacheController
@@ -17,53 +19,12 @@
     from filelock import BaseFileLock
 
 
-def _secure_open_write(filename: str, fmode: int) -> IO[bytes]:
-    # We only want to write to this file, so open it in write only mode
-    flags = os.O_WRONLY
-
-    # os.O_CREAT | os.O_EXCL will fail if the file already exists, so we only
-    #  will open *new* files.
-    # We specify this because we want to ensure that the mode we pass is the
-    # mode of the file.
-    flags |= os.O_CREAT | os.O_EXCL
-
-    # Do not follow symlinks to prevent someone from making a symlink that
-    # we follow and insecurely open a cache file.
-    if hasattr(os, "O_NOFOLLOW"):
-        flags |= os.O_NOFOLLOW
-
-    # On Windows we'll mark this file as binary
-    if hasattr(os, "O_BINARY"):
-        flags |= os.O_BINARY
-
-    # Before we open our file, we want to delete any existing file that is
-    # there
-    try:
-        os.remove(filename)
-    except OSError:
-        # The file must not exist already, so we can just skip ahead to opening
-        pass
-
-    # Open our file, the use of os.O_CREAT | os.O_EXCL will ensure that if a
-    # race condition happens between the os.remove and this line, that an
-    # error will be raised. Because we utilize a lockfile this should only
-    # happen if someone is attempting to attack us.
-    fd = os.open(filename, flags, fmode)
-    try:
-        return os.fdopen(fd, "wb")
-
-    except:
-        # An error occurred wrapping our FD in a file object
-        os.close(fd)
-        raise
-
-
 class _FileCacheMixin:
     """Shared implementation for both FileCache variants."""
 
     def __init__(
         self,
-        directory: str,
+        directory: str | Path,
         forever: bool = False,
         filemode: int = 0o0600,
         dirmode: int = 0o0700,
@@ -79,7 +40,7 @@ def __init__(
                 """
             NOTE: In order to use the FileCache you must have
             filelock installed. You can install it via pip:
-              pip install filelock
+              pip install cachecontrol[filecache]
             """
             )
             raise ImportError(notice)
@@ -121,15 +82,18 @@ def _write(self, path: str, data: bytes) -> None:
         Safely write the data to the given path.
         """
         # Make sure the directory exists
-        try:
-            os.makedirs(os.path.dirname(path), self.dirmode)
-        except OSError:
-            pass
+        dirname = os.path.dirname(path)
+        os.makedirs(dirname, self.dirmode, exist_ok=True)
 
         with self.lock_class(path + ".lock"):
             # Write our actual file
-            with _secure_open_write(path, self.filemode) as fh:
-                fh.write(data)
+            (fd, name) = tempfile.mkstemp(dir=dirname)
+            try:
+                os.write(fd, data)
+            finally:
+                os.close(fd)
+            os.chmod(name, self.filemode)
+            os.replace(name, path)
 
     def _delete(self, key: str, suffix: str) -> None:
         name = self._fn(key) + suffix

cachecontrol/controller.py

@@ -5,12 +5,14 @@
 """
 The httplib2 algorithms ported for use with requests.
 """
+
 from __future__ import annotations
 
 import calendar
 import logging
 import re
 import time
+import weakref
 from email.utils import parsedate_tz
 from typing import TYPE_CHECKING, Collection, Mapping
 
@@ -142,6 +144,11 @@ def _load_from_cache(self, request: PreparedRequest) -> HTTPResponse | None:
         """
         Load a cached response, or return None if it's not available.
         """
+        # We do not support caching of partial content: so if the request contains a
+        # Range header then we don't want to load anything from the cache.
+        if "Range" in request.headers:
+            return None
+
         cache_url = request.url
         assert cache_url is not None
         cache_data = self.cache.get(cache_url)
@@ -317,7 +324,7 @@ def _cache_set(
     def cache_response(
         self,
         request: PreparedRequest,
-        response: HTTPResponse,
+        response_or_ref: HTTPResponse | weakref.ReferenceType[HTTPResponse],
         body: bytes | None = None,
         status_codes: Collection[int] | None = None,
     ) -> None:
@@ -326,6 +333,16 @@ def cache_response(
 
         This assumes a requests Response object.
         """
+        if isinstance(response_or_ref, weakref.ReferenceType):
+            response = response_or_ref()
+            if response is None:
+                # The weakref can be None only in case the user used streamed request
+                # and did not consume or close it, and holds no reference to requests.Response.
+                # In such case, we don't want to cache the response.
+                return
+        else:
+            response = response_or_ref
+
         # From httplib2: Don't cache 206's since we aren't going to
         #                handle byte range requests
         cacheable_status_codes = status_codes or self.cacheable_status_codes
@@ -480,7 +497,7 @@ def update_cached_response(
         cached_response.headers.update(
             {
                 k: v
-                for k, v in response.headers.items()  # type: ignore[no-untyped-call]
+                for k, v in response.headers.items()
                 if k.lower() not in excluded_headers
             }
         )

cachecontrol/filewrapper.py

@@ -38,10 +38,10 @@ def __init__(
         self.__callback = callback
 
     def __getattr__(self, name: str) -> Any:
-        # The vaguaries of garbage collection means that self.__fp is
+        # The vagaries of garbage collection means that self.__fp is
         # not always set.  By using __getattribute__ and the private
         # name[0] allows looking up the attribute value and raising an
-        # AttributeError when it doesn't exist. This stop thigns from
+        # AttributeError when it doesn't exist. This stop things from
         # infinitely recursing calls to getattr in the case where
         # self.__fp hasn't been set.
         #

cachecontrol/heuristics.py

@@ -68,7 +68,10 @@ def update_headers(self, response: HTTPResponse) -> dict[str, str]:
 
         if "expires" not in response.headers:
             date = parsedate(response.headers["date"])
-            expires = expire_after(timedelta(days=1), date=datetime(*date[:6], tzinfo=timezone.utc))  # type: ignore[misc]
+            expires = expire_after(
+                timedelta(days=1),
+                date=datetime(*date[:6], tzinfo=timezone.utc),  # type: ignore[index,misc]
+            )
             headers["expires"] = datetime_to_header(expires)
             headers["cache-control"] = "public"
         return headers