[pull] master from aio-libs:master

CHANGES/13099.bugfix.rst

@@ -0,0 +1 @@
+Fixed ``BaseRequest.text()`` and ``application/x-www-form-urlencoded`` request parsing to return HTTP 415 when body bytes fail to decode with the default charset -- by :user:`cyphercodes`.

README.rst

@@ -59,7 +59,7 @@ To get something from the web:
   async def main():
 
       async with aiohttp.ClientSession() as session:
-          async with session.get('http://python.org') as response:
+          async with session.get('https://python.org') as response:
 
               print("Status:", response.status)
               print("Content-type:", response.headers['content-type'])
@@ -134,11 +134,11 @@ External links
 ==============
 
 * `Third party libraries
-  <http://aiohttp.readthedocs.io/en/latest/third_party.html>`_
+  <https://aiohttp.readthedocs.io/en/latest/third_party.html>`_
 * `Built with aiohttp
-  <http://aiohttp.readthedocs.io/en/latest/built_with.html>`_
+  <https://aiohttp.readthedocs.io/en/latest/built_with.html>`_
 * `Powered by aiohttp
-  <http://aiohttp.readthedocs.io/en/latest/powered_by.html>`_
+  <https://aiohttp.readthedocs.io/en/latest/powered_by.html>`_
 
 Feel free to make a Pull Request for adding your link to these pages!
 

aiohttp/web_request.py

@@ -665,7 +665,7 @@ async def text(self) -> str:
         encoding = self.charset or "utf-8"
         try:
             return bytes_body.decode(encoding)
-        except LookupError:
+        except (LookupError, UnicodeDecodeError):
             raise HTTPUnsupportedMediaType()
 
     async def json(
@@ -790,7 +790,7 @@ async def post(self) -> "MultiDictProxy[str | bytes | FileField]":
                 bytes_query = data.rstrip()
                 try:
                     query = bytes_query.decode(charset)
-                except LookupError:
+                except (LookupError, UnicodeDecodeError):
                     raise HTTPUnsupportedMediaType()
                 out.extend(
                     parse_qsl(qs=query, keep_blank_values=True, encoding=charset)

tests/test_web_request.py

@@ -930,6 +930,22 @@ async def test_request_with_wrong_content_type_encoding(protocol: BaseProtocol)
     assert err.value.status_code == 415
 
 
+async def test_request_text_with_invalid_default_encoding(
+    protocol: BaseProtocol,
+) -> None:
+    payload = StreamReader(
+        protocol, DEFAULT_CHUNK_SIZE, loop=asyncio.get_running_loop()
+    )
+    payload.feed_data(b"\xff")
+    payload.feed_eof()
+    headers = {"Content-Type": "text/html"}
+    req = make_mocked_request("POST", "/", payload=payload, headers=headers)
+
+    with pytest.raises(web.HTTPUnsupportedMediaType) as err:
+        await req.text()
+    assert err.value.status_code == 415
+
+
 async def test_make_too_big_request_same_size_to_max(protocol: BaseProtocol) -> None:
     payload = StreamReader(protocol, 2**16, loop=asyncio.get_running_loop())
     large_file = 1024**2 * b"x"
@@ -977,6 +993,24 @@ async def test_multipart_formdata(protocol: BaseProtocol) -> None:
     assert dict(result) == {"a": "b", "c": "d"}
 
 
+async def test_urlencoded_form_with_invalid_default_encoding(
+    protocol: BaseProtocol,
+) -> None:
+    payload = StreamReader(
+        protocol, DEFAULT_CHUNK_SIZE, loop=asyncio.get_running_loop()
+    )
+    payload.feed_data(b"a=1&b=\xff")
+    payload.feed_eof()
+    headers = {
+        "Content-Type": "application/x-www-form-urlencoded",
+    }
+    req = make_mocked_request("POST", "/", payload=payload, headers=headers)
+
+    with pytest.raises(web.HTTPUnsupportedMediaType) as err:
+        await req.post()
+    assert err.value.status_code == 415
+
+
 async def test_multipart_formdata_field_missing_name(protocol: BaseProtocol) -> None:
     # Ensure ValueError is raised when Content-Disposition has no name
     payload = StreamReader(