Deprecate MapReduceMixin and implements its methods in BaseChecker

ChangeLog

@@ -63,6 +63,12 @@ Release date: TBA
 
   Ref #5392
 
+* ``MapReduceMixin`` has been deprecated. ``BaseChecker`` now implements ``get_map_data`` and
+  ``reduce_map_data``. If a checker actually needs to reduce data it should define ``get_map_data``
+  as returning something different than ``None`` and let its ``reduce_map_data`` handle a list
+  of the types returned by ``get_map_data``.
+  An example can be seen by looking at ``pylint/checkers/similar.py``.
+
 * ``UnsupportedAction`` has been deprecated.
 
   Ref #5392

doc/how_tos/custom_checkers.rst

@@ -243,6 +243,17 @@ Now we can debug our checker!
     environment variable or by adding the ``my_plugin.py``
     file to the ``pylint/checkers`` directory if running from source.
 
+Parallelize a Checker
+---------------------
+
+``BaseChecker`` has two methods ``get_map_data`` and ``reduce_map_data`` that
+permit to parallelize the checks when used with the ``-j`` option. If a checker
+actually needs to reduce data it should define ``get_map_data`` as returning
+something different than ``None`` and let its ``reduce_map_data`` handle a list
+of the types returned by ``get_map_data``.
+
+An example can be seen by looking at ``pylint/checkers/similar.py``.
+
 Testing a Checker
 -----------------
 Pylint is very well suited to test driven development.

doc/whatsnew/2.14.rst

@@ -25,6 +25,12 @@ New checkers
 
   Closes #5895
 
+* ``MapReduceMixin`` has been deprecated. ``BaseChecker`` now implements ``get_map_data`` and
+  ``reduce_map_data``. If a checker actually needs to reduce data it should define ``get_map_data``
+  as returning something different than ``None`` and let its ``reduce_map_data`` handle a list
+  of the types returned by ``get_map_data``.
+  An example can be seen by looking at ``pylint/checkers/similar.py``.
+
 * Add new check ``unnecessary-dunder-call`` for unnecessary dunder method calls.
 
   Closes #5936

pylint/checkers/base_checker.py

@@ -206,6 +206,14 @@ def open(self):
     def close(self):
         """Called after visiting project (i.e set of modules)."""
 
+    # pylint: disable-next=no-self-use
+    def get_map_data(self) -> Any:
+        return None
+
+    # pylint: disable-next=no-self-use, unused-argument
+    def reduce_map_data(self, linter: PyLinter, data: list[Any]) -> None:
+        return None
+
 
 class BaseTokenChecker(BaseChecker):
     """Base class for checkers that want to have access to the token stream."""

pylint/checkers/mapreduce_checker.py

@@ -2,16 +2,30 @@
 # For details: https://github.com/PyCQA/pylint/blob/main/LICENSE
 # Copyright (c) https://github.com/PyCQA/pylint/blob/main/CONTRIBUTORS.txt
 
+from __future__ import annotations
+
 import abc
+import warnings
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from pylint.lint import PyLinter
 
 
 class MapReduceMixin(metaclass=abc.ABCMeta):
     """A mixin design to allow multiprocess/threaded runs of a Checker."""
 
+    def __init__(self) -> None:
+        warnings.warn(
+            "MapReduceMixin has been deprecated and will be removed in pylint 3.0. "
+            "To make a checker reduce map data simply implement get_map_data and reduce_map_data.",
+            DeprecationWarning,
+        )
+
     @abc.abstractmethod
-    def get_map_data(self):
+    def get_map_data(self) -> Any:
         """Returns mergeable/reducible data that will be examined."""
 
     @abc.abstractmethod
-    def reduce_map_data(self, linter, data):
+    def reduce_map_data(self, linter: PyLinter, data: list[Any]) -> None:
         """For a given Checker, receives data for all mapped runs."""

pylint/checkers/similar.py

@@ -47,7 +47,7 @@
 import astroid
 from astroid import nodes
 
-from pylint.checkers import BaseChecker, MapReduceMixin, table_lines_from_stats
+from pylint.checkers import BaseChecker, table_lines_from_stats
 from pylint.interfaces import IRawChecker
 from pylint.reporters.ureports.nodes import Table
 from pylint.typing import Options
@@ -727,7 +727,7 @@ def report_similarities(
 
 
 # wrapper to get a pylint checker from the similar class
-class SimilarChecker(BaseChecker, Similar, MapReduceMixin):
+class SimilarChecker(BaseChecker, Similar):
     """Checks for similarities and duplicated code.
 
     This computation may be memory / CPU intensive, so you

pylint/lint/parallel.py

@@ -71,11 +71,9 @@ def _worker_check_single_file(
     _worker_linter.check_single_file_item(file_item)
     mapreduce_data = defaultdict(list)
     for checker in _worker_linter.get_checkers():
-        try:
-            data = checker.get_map_data()  # type: ignore[attr-defined]
-        except AttributeError:
-            continue
-        mapreduce_data[checker.name].append(data)
+        data = checker.get_map_data()
+        if data is not None:
+            mapreduce_data[checker.name].append(data)
     msgs = _worker_linter.reporter.messages
     assert isinstance(_worker_linter.reporter, reporters.CollectingReporter)
     _worker_linter.reporter.reset()
@@ -108,7 +106,7 @@ def _merge_mapreduce_data(
     # validation. The intent here is to collect all the mapreduce data for all checker-
     # runs across processes - that will then be passed to a static method on the
     # checkers to be reduced and further processed.
-    collated_map_reduce_data = defaultdict(list)
+    collated_map_reduce_data: defaultdict[str, list[Any]] = defaultdict(list)
     for linter_data in all_mapreduce_data.values():
         for run_data in linter_data:
             for checker_name, data in run_data.items():
@@ -120,7 +118,7 @@ def _merge_mapreduce_data(
         if checker.name in collated_map_reduce_data:
             # Assume that if the check has returned map/reduce data that it has the
             # reducer function
-            checker.reduce_map_data(linter, collated_map_reduce_data[checker.name])  # type: ignore[attr-defined]
+            checker.reduce_map_data(linter, collated_map_reduce_data[checker.name])
 
 
 def check_parallel(
@@ -132,8 +130,7 @@ def check_parallel(
     """Use the given linter to lint the files with given amount of workers (jobs).
 
     This splits the work filestream-by-filestream. If you need to do work across
-    multiple files, as in the similarity-checker, then inherit from MapReduceMixin and
-    implement the map/reduce mixin functionality.
+    multiple files, as in the similarity-checker, then implement the map/reduce mixin functionality.
     """
     # The linter is inherited by all the pool's workers, i.e. the linter
     # is identical to the linter object here. This is required so that

tests/checkers/unittest_similar.py

@@ -376,7 +376,7 @@ def test_no_args() -> None:
 
 
 def test_get_map_data() -> None:
-    """Tests that a SimilarChecker respects the MapReduceMixin interface."""
+    """Tests that a SimilarChecker can return and reduce mapped data."""
     linter = PyLinter(reporter=Reporter())
     # Add a parallel checker to ensure it can map and reduce
     linter.register_checker(similar.SimilarChecker(linter))

tests/test_check_parallel.py

@@ -19,7 +19,6 @@
 import pylint.interfaces
 import pylint.lint.parallel
 from pylint.checkers.base_checker import BaseChecker
-from pylint.checkers.mapreduce_checker import MapReduceMixin
 from pylint.lint import PyLinter
 from pylint.lint.parallel import _worker_check_single_file as worker_check_single_file
 from pylint.lint.parallel import _worker_initialize as worker_initialize
@@ -73,7 +72,7 @@ def process_module(self, _node: nodes.Module) -> None:
         self.data.append(record)
 
 
-class ParallelTestChecker(BaseChecker, MapReduceMixin):
+class ParallelTestChecker(BaseChecker):
     """A checker that does need to consolidate data.
 
     To simulate the need to consolidate data, this checker only

tests/test_deprecation.py

@@ -0,0 +1,28 @@
+# Licensed under the GPL: https://www.gnu.org/licenses/old-licenses/gpl-2.0.html
+# For details: https://github.com/PyCQA/pylint/blob/main/LICENSE
+# Copyright (c) https://github.com/PyCQA/pylint/blob/main/CONTRIBUTORS.txt
+
+"""Check deprecation across the codebase."""
+
+from __future__ import annotations
+
+from typing import Any
+
+import pytest
+
+from pylint.checkers.mapreduce_checker import MapReduceMixin
+from pylint.lint import PyLinter
+
+
+def test_mapreducemixin() -> None:
+    """Test that MapReduceMixin has been deprecated correctly."""
+
+    class MyChecker(MapReduceMixin):
+        def get_map_data(self) -> Any:
+            ...
+
+        def reduce_map_data(self, linter: PyLinter, data: list[Any]) -> None:
+            ...
+
+    with pytest.warns(DeprecationWarning):
+        MyChecker()