Meta Validation

docs/advanced/meta.rst

@@ -129,3 +129,26 @@ From the example above, we can see how :class:`~.Meta` is able to arbitrarily
 limit the pagination behavior by passing an optional **max_pages** info. Take
 note that a ``default_max_pages`` value is also present in the Page Object in
 case the :class:`~.Meta` instance did not provide it.
+
+Value Restrictions
+------------------
+
+From the examples above, you may notice that we can access :class:`~.Meta` with
+a ``dict`` interface since it's simply a subclass of it. However, :class:`~.Meta`
+posses some extendable features on top of being a ``dict``.
+
+Specifically, :class:`~.Meta` is able to restrict any value passed based on its
+type. For example, if any of these values are passed, then a ``ValueError`` is
+raised:
+
+    * module
+    * class
+    * method or function
+    * generator
+    * coroutine or awaitable
+    * traceback
+    * frame
+
+This is to ensure that frameworks using **web-poet** are able safely use values
+passed into :class:`~.Meta` as they could be passed via CLI, web forms, HTTP API
+calls, etc.

tests/test_page_inputs.py

@@ -1,4 +1,7 @@
-from web_poet.page_inputs import ResponseData
+import pytest
+import asyncio
+
+from web_poet.page_inputs import ResponseData, Meta
 
 
 def test_html_response():
@@ -11,3 +14,19 @@ def test_html_response():
     response = ResponseData("url", "content", 200, {"User-Agent": "test agent"})
     assert response.status == 200
     assert response.headers["User-Agent"] == "test agent"
+
+
+def test_meta_restriction():
+    # Any value that conforms with `Meta.restrictions` raises an error
+    with pytest.raises(ValueError) as err:
+        Meta(func=lambda x: x + 1)
+
+    with pytest.raises(ValueError) as err:
+        Meta(class_=ResponseData)
+
+    # These are allowed though
+    m = Meta(x="hi", y=2.2, z={"k": "v"})
+    m["allowed"] = [1, 2, 3]
+
+    with pytest.raises(ValueError) as err:
+        m["not_allowed"] = asyncio.sleep(1)

web_poet/page_inputs.py

@@ -1,4 +1,6 @@
-from typing import Optional, Dict, Any, ByteString, Union
+import inspect
+from typing import Optional, Dict, Any, ByteString, Union, Set
+from contextlib import suppress
 
 import attr
 
@@ -34,6 +36,50 @@ class ResponseData:
 class Meta(dict):
     """Container class that could contain any arbitrary data to be passed into
     a Page Object.
+
+    This is basically a subclass of a ``dict`` that adds the ability to check
+    if any of the assigned values are not allowed. This ensures that some input
+    parameters with data types that are difficult to provide or pass via CLI
+    like ``lambdas`` are checked. Otherwise, a ``ValueError`` is raised.
     """
 
-    pass
+    # Any "value" that returns True for the functions here are not allowed.
+    restrictions: Dict = {
+        inspect.ismodule: "module",
+        inspect.isclass: "class",
+        inspect.ismethod: "method",
+        inspect.isfunction: "function",
+        inspect.isgenerator: "generator",
+        inspect.isgeneratorfunction: "generator",
+        inspect.iscoroutine: "coroutine",
+        inspect.isawaitable: "awaitable",
+        inspect.istraceback: "traceback",
+        inspect.isframe: "frame",
+    }
+
+    def __init__(self, *args, **kwargs) -> None:
+        for val in kwargs.values():
+            self.enforce_value_restriction(val)
+        super().__init__(*args, **kwargs)
+
+    def __setitem__(self, key: Any, value: Any) -> None:
+        self.enforce_value_restriction(value)
+        super().__setattr__(key, value)
+
+    def enforce_value_restriction(self, value: Any) -> None:
+        """Raises a ``ValueError`` if a given value isn't allowed inside the meta.
+
+        This method is called during :class:`~.Meta` instantiation and setting
+        new values in an existing instance.
+
+        This behavior can be controlled by tweaking the class variable named
+        ``restrictions``.
+        """
+        violations = []
+
+        for restrictor, err in self.restrictions.items():
+            if restrictor(value):
+                violations.append(f"{err} is not allowed: {value}")
+
+        if violations:
+            raise ValueError(f"Found these issues: {', '.join(violations)}")