skipping spellcheck for tool directives in comments

3 files changed, 103 insertions, 14 deletions

diff --git a/pylint/checkers/spelling.py b/pylint/checkers/spelling.py
index 95b46cda2..dca7da3b5 100644
--- a/pylint/checkers/spelling.py
+++ b/pylint/checkers/spelling.py
@@ -17,6 +17,7 @@
 # Copyright (c) 2020 Ganden Schaffner <gschaffner@pm.me>
 # Copyright (c) 2020 hippo91 <guillaume.peillex@gmail.com>
 # Copyright (c) 2020 Damien Baty <damien.baty@polyconseil.fr>
+# Copyright (c) 2021 Eli Fine <ejfine@gmail.com>
 
 # Licensed under the GPL: https://www.gnu.org/licenses/old-licenses/gpl-2.0.html
 # For details: https://github.com/PyCQA/pylint/blob/master/COPYING
@@ -26,6 +27,7 @@
 import os
 import re
 import tokenize
+from typing import Pattern
 
 from pylint.checkers import BaseTokenChecker
 from pylint.checkers.utils import check_messages
@@ -79,7 +81,7 @@ else:
     instr = " To make it work, install the 'python-enchant' package."
 
 
-class WordsWithDigigtsFilter(Filter):
+class WordsWithDigitsFilter(Filter):
     """Skips words with digits."""
 
     def _skip(self, word):
@@ -99,7 +101,18 @@ class WordsWithUnderscores(Filter):
         return "_" in word
 
 
-class CamelCasedWord(Filter):
+class RegExFilter(Filter):
+    r"""Parent class for filters using regular expressions.
+    This filter skips any words the match the expression assigned to the class attribute `_pattern`
+
+    """
+    _pattern: Pattern[str]
+
+    def _skip(self, word) -> bool:
+        return bool(self._pattern.match(word))
+
+
+class CamelCasedWord(RegExFilter):
     r"""Filter skipping over camelCasedWords.
     This filter skips any words matching the following regular expression:
 
@@ -109,11 +122,8 @@ class CamelCasedWord(Filter):
     """
     _pattern = re.compile(r"^([a-z]+([\d]|[A-Z])(?:\w+)?)")
 
-    def _skip(self, word):
-        return bool(self._pattern.match(word))
-
 
-class SphinxDirectives(Filter):
+class SphinxDirectives(RegExFilter):
     r"""Filter skipping over Sphinx Directives.
     This filter skips any words matching the following regular expression:
 
@@ -124,11 +134,8 @@ class SphinxDirectives(Filter):
     # The final ` in the pattern is optional because enchant strips it out
     _pattern = re.compile(r"^(:([a-z]+)){1,2}:`([^`]+)(`)?")
 
-    def _skip(self, word):
-        return bool(self._pattern.match(word))
-
 
-class ForwardSlashChunkder(Chunker):
+class ForwardSlashChunker(Chunker):
     """
     This chunker allows splitting words like 'before/after' into 'before' and 'after'
     """
@@ -283,15 +290,16 @@ class SpellingChecker(BaseTokenChecker):
 
         self.tokenizer = get_tokenizer(
             dict_name,
-            chunkers=[ForwardSlashChunkder],
+            chunkers=[ForwardSlashChunker],
             filters=[
                 EmailFilter,
                 URLFilter,
                 WikiWordFilter,
-                WordsWithDigigtsFilter,
+                WordsWithDigitsFilter,
                 WordsWithUnderscores,
                 CamelCasedWord,
                 SphinxDirectives,
+                # BlackDirectives
             ],
         )
         self.initialized = True
@@ -308,6 +316,17 @@ class SpellingChecker(BaseTokenChecker):
             initial_space = 0
         if line.strip().startswith("#") and "docstring" not in msgid:
             line = line.strip()[1:]
+            for iter_directive in (
+                "fmt: on",
+                "fmt: off",
+                "noqa:",
+                "noqa",
+                "nosec",
+                "isort:skip",
+            ):
+                if line.startswith(" " + iter_directive):
+                    line = line[(len(iter_directive) + 1) :]
+                    break
             starts_with_comment = True
         else:
             starts_with_comment = False
diff --git a/pylint/testutils/decorator.py b/pylint/testutils/decorator.py
index 3b70867cb..3fb5f190a 100644
--- a/pylint/testutils/decorator.py
+++ b/pylint/testutils/decorator.py
@@ -11,13 +11,15 @@ def set_config(**kwargs):
 
     def _wrapper(fun):
         @functools.wraps(fun)
-        def _forward(self):
+        def _forward(self, *args, **test_function_kwargs):
             for key, value in kwargs.items():
                 setattr(self.checker.config, key, value)
             if isinstance(self, CheckerTestCase):
                 # reopen checker in case, it may be interested in configuration change
                 self.checker.open()
-            fun(self)
+            fun(
+                self, *args, **test_function_kwargs
+            )  # Passing the args and kwargs back to the test function itself allows this decorator to be used on parametrized test cases
 
         return _forward
 
diff --git a/tests/checkers/unittest_spelling.py b/tests/checkers/unittest_spelling.py
index c14062d2d..dec6b19ee 100644
--- a/tests/checkers/unittest_spelling.py
+++ b/tests/checkers/unittest_spelling.py
@@ -303,6 +303,74 @@ class TestSpellingChecker(CheckerTestCase):
         ):
             self.checker.visit_classdef(stmt)
 
+    # @skip_on_missing_package_or_dict
+    # # @set_config(spelling_dict=spell_dict)
+    # @pytest.mark.parametrize(
+    #     "num_files,num_jobs,num_checkers",
+    #     [
+    #         (1, 2, 1),
+    #         (1, 2, 2),
+    #         (1, 2, 3),
+    #         (2, 2, 1),
+    #         (2, 2, 2),
+    #         (2, 2, 3),
+    #         (3, 2, 1),
+    #         (3, 2, 2),
+    #         (3, 2, 3),
+    #         (3, 1, 1),
+    #         (3, 1, 2),
+    #         (3, 1, 3),
+    #         (3, 5, 1),
+    #         (3, 5, 2),
+    #         (3, 5, 3),
+    #         (10, 2, 1),
+    #         (10, 2, 2),
+    #         (10, 2, 3),
+    #         (2, 10, 1),
+    #         (2, 10, 2),
+    #         (2, 10, 3),
+    #     ],
+    # )
+    # def test_compare_workers_to_single_proc(self, num_files, num_jobs, num_checkers):
+    #     assert True
+
+    @skip_on_missing_package_or_dict
+    @set_config(spelling_dict=spell_dict)
+    @pytest.mark.parametrize(
+        ",".join(
+            (
+                "misspelled_portion_of_directive",
+                "second_portion_of_directive",
+                "description",
+            )
+        ),
+        (
+            ("fmt", ": on", "black directive to turn on formatting"),
+            ("fmt", ": off", "black directive to turn off formatting"),
+            ("noqa", "", "pycharm directive"),
+            ("noqa", ":", "flake8 / zimports directive"),
+            ("nosec", "", "bandit directive"),
+            ("isort", ":skip", "isort directive"),
+        ),
+    )
+    def test_skip_tool_directives_at_beginning_of_comments_but_still_raise_error_if_directive_appears_later_in_comment(  # pylint:disable=unused-argument # Having the extra description parameter allows the description to show up in the pytest output as part of the test name when running parametrized tests
+        self, misspelled_portion_of_directive, second_portion_of_directive, description
+    ):
+        full_comment = f"# {misspelled_portion_of_directive}{second_portion_of_directive} {misspelled_portion_of_directive}"
+        with self.assertAddsMessages(
+            Message(
+                "wrong-spelling-in-comment",
+                line=1,
+                args=(
+                    misspelled_portion_of_directive,
+                    full_comment,
+                    f"  {'^'*len(misspelled_portion_of_directive)}",
+                    self._get_msg_suggestions(misspelled_portion_of_directive),
+                ),
+            )
+        ):
+            self.checker.process_tokens(_tokenize_str(full_comment))
+
     @skip_on_missing_package_or_dict
     @set_config(spelling_dict=spell_dict)
     def test_handle_words_joined_by_forward_slash(self):