create consume_modules() to properly load annotations in get_overrides()

Author: BurnzZ

docs/intro/overrides.rst

@@ -161,6 +161,31 @@ to see the other functionalities.
     using only the ``default_registry``. There's no need to declare multiple
     :class:`~.PageObjectRegistry` instances and use multiple annotations.
 
+.. warning::
+
+    :meth:`~.PageObjectRegistry.get_overrides` relies on the fact that all essential
+    packages/modules which contains the :meth:`~.PageObjectRegistry.handle_urls`
+    annotations are properly loaded.
+
+    Thus, for cases like importing Page Objects from another external package, you'd
+    need to properly load all :meth:`~.PageObjectRegistry.handle_urls` annotations
+    from the external module. This ensures that the external Page Objects' have
+    their annotations properly loaded.
+
+    This can be done via the function named :func:`~.web_poet.overrides.consume_modules`.
+    Here's an example:
+
+    .. code-block:: python
+
+        from web_poet import default_registry, consume_modules
+
+        consume_modules("external_package_A.po", "another_ext_package.lib")
+        rules = default_registry.get_overrides()
+
+    **NOTE**: :func:`~.web_poet.overrides.consume_modules` must be called before
+    :meth:`~.PageObjectRegistry.get_overrides` for the imports to properly load.
+
+
 A handy CLI tool is also available at your disposal to quickly see the available
 Override rules in a given module in your project. For example, invoking something
 like ``web_poet my_project.page_objects`` would produce the following:
@@ -226,7 +251,7 @@ Then we could easily retrieve all Page Objects per subpackage or module like thi
 
 .. code-block:: python
 
-    from web_poet import default_registry
+    from web_poet import default_registry, consume_modules
 
     # We can do it per website.
     rules = default_registry.get_overrides_from("my_page_obj_project.cool_gadget_site")
@@ -236,11 +261,16 @@ Then we could easily retrieve all Page Objects per subpackage or module like thi
     rules = default_registry.get_overrides_from("my_page_obj_project.cool_gadget_site.us")
     rules = default_registry.get_overrides_from("my_page_obj_project.cool_gadget_site.fr")
 
-    # or even drill down further to the specific module.
+    # Or even drill down further to the specific module.
     rules = default_registry.get_overrides_from("my_page_obj_project.cool_gadget_site.us.products")
     rules = default_registry.get_overrides_from("my_page_obj_project.cool_gadget_site.us.product_listings")
 
-    # Or simply all of Override rules ever declared.
+    # Or simply all of the Override rules ever declared.
+    rules = default_registry.get_overrides()
+
+    # Lastly, you'd need to properly load external packages/modules for the
+    # @handle_urls annotation to be correctly read.
+    consume_modules("external_package_A.po", "another_ext_package.lib")
     rules = default_registry.get_overrides()
 
 Multiple Registry Approach

tests/test_overrides.py

@@ -9,6 +9,7 @@
     PONestedModule,
     PONestedModuleOverridenSecondary,
 )
+from web_poet import consume_modules
 from web_poet.overrides import PageObjectRegistry, default_registry
 
 
@@ -17,9 +18,19 @@
 
 def test_list_page_objects_all():
     rules = default_registry.get_overrides()
-
     page_objects = {po.use for po in rules}
 
+    # Note that the 'tests_extra.po_lib_sub_not_imported.POLibSubNotImported'
+    # Page Object is not included here since it was never imported anywhere in
+    # our test package. It would only be included if we run any of the following
+    # below. (Note that they should run before `get_overrides` is called.)
+    #   - from tests_extra import po_lib_sub_not_imported
+    #   - import tests_extra.po_lib_sub_not_imported
+    #   - web_poet.consume_modules("tests_extra")
+    # Merely having `import tests_extra` won't work since the subpackages and
+    # modules needs to be traversed and imported as well.
+    assert all(["po_lib_sub_not_imported" not in po.__module__ for po in page_objects])
+
     # Ensure that ALL Override Rules are returned as long as the given
     # registry's @handle_urls annotation was used.
     assert page_objects == POS.union({POLibSub})
@@ -29,6 +40,16 @@ def test_list_page_objects_all():
         assert rule.meta == rule.use.expected_meta, rule.use
 
 
+def test_list_page_objects_all_consume_modules():
+    """A test similar to the one above but calls ``consume_modules()`` to properly
+    load the @handle_urls annotations from other modules/packages.
+    """
+    consume_modules("tests_extra")
+    rules = default_registry.get_overrides()
+    page_objects = {po.use for po in rules}
+    assert any(["po_lib_sub_not_imported" in po.__module__ for po in page_objects])
+
+
 def test_list_page_objects_from_pkg():
     """Tests that metadata is extracted properly from the po_lib package"""
     rules = default_registry.get_overrides_from("tests.po_lib")

tests_extra/__init__.py

@@ -0,0 +1,5 @@
+"""
+This test package was created separately to see the behavior of retrieving the
+Override rules declared on a registry where @handle_urls is defined on another
+package.
+"""

tests_extra/po_lib_sub_not_imported/__init__.py

@@ -0,0 +1,28 @@
+"""
+This package quite is similar to tests/po_lib_sub in terms of code contents.
+
+What we're ultimately trying to test here is to see if the `default_registry`
+captures the rules annotated in this module if it was not imported.
+"""
+from typing import Dict, Any, Callable
+
+from url_matcher import Patterns
+
+from web_poet import handle_urls
+
+
+class POBase:
+    expected_overrides: Callable
+    expected_patterns: Patterns
+    expected_meta: Dict[str, Any]
+
+
+class POLibSubOverridenNotImported:
+    ...
+
+
+@handle_urls("sub_example_not_imported.com", POLibSubOverridenNotImported)
+class POLibSubNotImported(POBase):
+    expected_overrides = POLibSubOverridenNotImported
+    expected_patterns = Patterns(["sub_example_not_imported.com"])
+    expected_meta = {}  # type: ignore

web_poet/__init__.py

@@ -1,3 +1,3 @@
 from .pages import WebPage, ItemPage, ItemWebPage, Injectable
 from .page_inputs import ResponseData
-from .overrides import handle_urls, PageObjectRegistry, default_registry
+from .overrides import handle_urls, PageObjectRegistry, default_registry, consume_modules

web_poet/overrides.py

@@ -2,7 +2,9 @@
 import importlib.util
 import warnings
 import pkgutil
+from collections import deque
 from dataclasses import dataclass, field
+from types import ModuleType
 from typing import Iterable, Union, List, Callable, Dict, Any
 
 from url_matcher import Patterns
@@ -164,7 +166,7 @@ def get_overrides_from(self, module: str) -> List[OverrideRule]:
         """
         rules: Dict[Callable, OverrideRule] = {}
 
-        for mod in walk_modules(module):
+        for mod in walk_module(module):
             # Dict ensures that no duplicates are collected and returned.
             rules.update(self._filter_from_module(mod.__name__))
 
@@ -191,7 +193,7 @@ def _filter_from_module(self, module: str) -> Dict[Callable, OverrideRule]:
 handle_urls = default_registry.handle_urls
 
 
-def walk_modules(module: str) -> Iterable:
+def walk_module(module: str) -> Iterable:
     """Return all modules from a module recursively.
 
     Note that this will import all the modules and submodules. It returns the
@@ -212,3 +214,41 @@ def onerror(err):
         ):
             mod = importlib.import_module(info.name)
             yield mod
+
+
+def consume_modules(*modules: str) -> None:
+    """A quick wrapper for :func:`~.walk_module` to efficiently consume the
+    generator and recursively load all packages/modules.
+
+    This function is essential to be run before calling :meth:`~.PageObjectRegistry.get_overrides`
+    from the :class:`~.PageObjectRegistry`. It essentially ensures that the
+    ``@handle_urls`` are properly acknowledged for modules/packages that are not
+    imported.
+
+    Let's take a look at an example:
+
+    .. code-block:: python
+
+        # my_page_obj_project/load_rules.py
+
+        from web_poet import default_registry, consume_modules
+
+        consume_modules("other_external_pkg.po", "another_pkg.lib")
+        rules = default_registry.get_overrides()
+
+    For this case, the Override rules are coming from:
+
+        - ``my_page_obj_project`` `(since it's the same module as the file above)`
+        - ``other_external_pkg.po``
+        - ``another_pkg.lib``
+
+    So if the ``default_registry`` had other ``@handle_urls`` annotations outside
+    of the packages/modules list above, then the Override rules won't be returned.
+    """
+
+    for module in modules:
+        gen = walk_module(module)
+
+        # Inspired by itertools recipe: https://docs.python.org/3/library/itertools.html
+        # Using a deque() results in a tiny bit performance improvement that list().
+        deque(gen, maxlen=0)