limit the maximum number of multipart form parts

Add a limit to the number of multipart form data parts the parser will
attempt to parse. If the limit is exceeded, it raises
`RequestEntityTooLargeError`.

A default of 1000 seems large enough to allow legitimate use cases while
preventing the previous unlimited parsing. This differs from similar
settings that are unset by default, as I think safe defaults are better
practice.

The limit can be adjusted per request by changing it on the request
object before parsing. For example, it can be set based on what you
expect a given endpoint to handle.

```python
req.max_form_parts = 20
form = req.form
```

CHANGES.rst

@@ -21,6 +21,10 @@ Unreleased
     the requested size in one ``read`` call. :issue:`2558`
 -   A cookie header that starts with ``=`` is treated as an empty key and discarded,
     rather than stripping the leading ``==``.
+-   Specify a maximum number of multipart parts, default 100, after
+    which a RequestEntityTooLarge exception is raised on parsing. The
+    mitigates a DOS attack whereby a larger number file/form parts are
+    sent resulting in a heavy parsing cost.
 
 
 Version 2.2.2

src/werkzeug/formparser.py

@@ -179,6 +179,10 @@ class FormDataParser:
     :param cls: an optional dict class to use.  If this is not specified
                        or `None` the default :class:`MultiDict` is used.
     :param silent: If set to False parsing errors will not be caught.
+    :param max_form_parts: the maximum number of parts to be accepted for the
+                           multipart data sent. If this is exceeded an
+                           :exc:`~exceptions.RequestEntityTooLarge` exception
+                           is raised.
     """
 
     def __init__(
@@ -190,6 +194,7 @@ def __init__(
         max_content_length: t.Optional[int] = None,
         cls: t.Optional[t.Type[MultiDict]] = None,
         silent: bool = True,
+        max_form_parts: t.Optional[int] = None,
     ) -> None:
         if stream_factory is None:
             stream_factory = default_stream_factory
@@ -205,6 +210,7 @@ def __init__(
 
         self.cls = cls
         self.silent = silent
+        self.max_form_parts = max_form_parts
 
     def get_parse_func(
         self, mimetype: str, options: t.Dict[str, str]
@@ -281,6 +287,7 @@ def _parse_multipart(
             self.errors,
             max_form_memory_size=self.max_form_memory_size,
             cls=self.cls,
+            max_form_parts=self.max_form_parts,
         )
         boundary = options.get("boundary", "").encode("ascii")
 
@@ -346,10 +353,12 @@ def __init__(
         max_form_memory_size: t.Optional[int] = None,
         cls: t.Optional[t.Type[MultiDict]] = None,
         buffer_size: int = 64 * 1024,
+        max_form_parts: t.Optional[int] = None,
     ) -> None:
         self.charset = charset
         self.errors = errors
         self.max_form_memory_size = max_form_memory_size
+        self.max_form_parts = max_form_parts
 
         if stream_factory is None:
             stream_factory = default_stream_factory
@@ -409,7 +418,9 @@ def parse(
             [None],
         )
 
-        parser = MultipartDecoder(boundary, self.max_form_memory_size)
+        parser = MultipartDecoder(
+            boundary, self.max_form_memory_size, self.max_form_parts
+        )
 
         fields = []
         files = []

src/werkzeug/sansio/multipart.py

@@ -87,10 +87,12 @@ def __init__(
         self,
         boundary: bytes,
         max_form_memory_size: Optional[int] = None,
+        max_parts: Optional[int] = None,
     ) -> None:
         self.buffer = bytearray()
         self.complete = False
         self.max_form_memory_size = max_form_memory_size
+        self.max_parts = max_parts
         self.state = State.PREAMBLE
         self.boundary = boundary
 
@@ -118,6 +120,7 @@ def __init__(
             re.MULTILINE,
         )
         self._search_position = 0
+        self._parts_decoded = 0
 
     def last_newline(self) -> int:
         try:
@@ -191,6 +194,10 @@ def next_event(self) -> Event:
                     )
                 self.state = State.DATA
                 self._search_position = 0
+                self._parts_decoded += 1
+
+                if self.max_parts is not None and self._parts_decoded > self.max_parts:
+                    raise RequestEntityTooLarge()
             else:
                 # Update the search start position to be equal to the
                 # current buffer length (already searched) minus a

src/werkzeug/wrappers/request.py

@@ -83,6 +83,16 @@ class Request(_SansIORequest):
     #: .. versionadded:: 0.5
     max_form_memory_size: t.Optional[int] = None
 
+    #: the maximum number of multipart parts. This is forwarded to teh
+    #: form data parsing function (:func:`parse_form_data`).  When the
+    #: :attr:`form` or :attr:`files` attribute is accessed and the
+    #: parsing fails because more parts than the specified value is
+    #: transmitted a :exc:`~werkzeug.exceptions.RequestEntityTooLarge`
+    #: exception is raised.
+    #:
+    #: .. versionadded:: 2.2.3
+    max_form_parts = 1000
+
     #: The form data parser that should be used.  Can be replaced to customize
     #: the form date parsing.
     form_data_parser_class: t.Type[FormDataParser] = FormDataParser
@@ -246,6 +256,7 @@ def make_form_data_parser(self) -> FormDataParser:
             self.max_form_memory_size,
             self.max_content_length,
             self.parameter_storage_class,
+            max_form_parts=self.max_form_parts,
         )
 
     def _load_form_data(self) -> None:

tests/test_formparser.py

@@ -127,6 +127,15 @@ def test_limiting(self):
         req.max_form_memory_size = 400
         assert req.form["foo"] == "Hello World"
 
+        req = Request.from_values(
+            input_stream=io.BytesIO(data),
+            content_length=len(data),
+            content_type="multipart/form-data; boundary=foo",
+            method="POST",
+        )
+        req.max_form_parts = 1
+        pytest.raises(RequestEntityTooLarge, lambda: req.form["foo"])
+
     def test_missing_multipart_boundary(self):
         data = (
             b"--foo\r\nContent-Disposition: form-field; name=foo\r\n\r\n"