Add regexs for bad- and good-names to enable better white- or blacklisting (#3186)

To enable better handling of whitelisting/blacklisting names, we added two new
config options: `good-names-rgxs` and `bad-names-rgxs`. They both
are a comma-separated list of regexes, where the former is used for exempting
names from name checking while the latter is used for always marking a name
as blacklisted.

Author: Germandrummer92

CONTRIBUTORS.txt

@@ -334,6 +334,8 @@ contributors:
 
 * Rémi Cardona: contributor
 
+* Daniel Draper: contributor
+
 * Gabriel R. Sezefredo: contributor
     - Fixed "exception-escape" false positive with generators
 

doc/whatsnew/2.5.rst

@@ -31,4 +31,10 @@ Other Changes
   for example ``[tool.pylint.'MESSAGES CONTROL']``.
   These files can also be passed in on the command line.
 
+* Add new good-names-rgx and bad-names-rgx to enable white-/blacklisting of regular expressions
+
+To enable better handling of whitelisting/blacklisting names, we added two new config options: good-names-rgxs: a comma-
+separated list of regexes, that if a name matches will be exempt of naming-checking. bad-names-rgxs: a comma-
+separated list of regexes, that if a name matches will be always marked as a blacklisted name.
+
 * Mutable ``collections.*`` are now flagged as dangerous defaults.

pylint/checkers/base.py

@@ -1680,6 +1680,16 @@ class NameChecker(_BasicChecker):
                 " separated by a comma.",
             },
         ),
+        (
+            "good-names-rgxs",
+            {
+                "default": "",
+                "type": "regexp_csv",
+                "metavar": "<names>",
+                "help": "Good variable names regexes, separated by a comma. If names match any regex,"
+                " they will always be accepted",
+            },
+        ),
         (
             "bad-names",
             {
@@ -1690,6 +1700,16 @@ class NameChecker(_BasicChecker):
                 "separated by a comma.",
             },
         ),
+        (
+            "bad-names-rgxs",
+            {
+                "default": "",
+                "type": "regexp_csv",
+                "metavar": "<names>",
+                "help": "Bad variable names regexes, separated by a comma. If names match any regex,"
+                " they will always be refused",
+            },
+        ),
         (
             "name-group",
             {
@@ -1735,6 +1755,8 @@ def __init__(self, linter):
         self._bad_names = {}
         self._name_regexps = {}
         self._name_hints = {}
+        self._good_names_rgxs_compiled = []
+        self._bad_names_rgxs_compiled = []
 
     def open(self):
         self.stats = self.linter.add_stats(
@@ -1756,6 +1778,12 @@ def open(self):
         regexps, hints = self._create_naming_rules()
         self._name_regexps = regexps
         self._name_hints = hints
+        self._good_names_rgxs_compiled = [
+            re.compile(rgxp) for rgxp in self.config.good_names_rgxs
+        ]
+        self._bad_names_rgxs_compiled = [
+            re.compile(rgxp) for rgxp in self.config.bad_names_rgxs
+        ]
 
     def _create_naming_rules(self):
         regexps = {}
@@ -1894,6 +1922,16 @@ def _raise_name_warning(self, node, node_type, name, confidence):
         self.add_message("invalid-name", node=node, args=args, confidence=confidence)
         self.stats["badname_" + node_type] += 1
 
+    def _name_valid_due_to_whitelist(self, name: str) -> bool:
+        return name in self.config.good_names or any(
+            pattern.match(name) for pattern in self._good_names_rgxs_compiled
+        )
+
+    def _name_invalid_due_to_blacklist(self, name: str) -> bool:
+        return name in self.config.bad_names or any(
+            pattern.match(name) for pattern in self._bad_names_rgxs_compiled
+        )
+
     def _check_name(self, node_type, name, node, confidence=interfaces.HIGH):
         """check for a name using the type's regexp"""
 
@@ -1908,9 +1946,9 @@ def _should_exempt_from_invalid_name(node):
             clobbering, _ = utils.clobber_in_except(node)
             if clobbering:
                 return
-        if name in self.config.good_names:
+        if self._name_valid_due_to_whitelist(name=name):
             return
-        if name in self.config.bad_names:
+        if self._name_invalid_due_to_blacklist(name=name):
             self.stats["badname_" + node_type] += 1
             self.add_message("blacklisted-name", node=node, args=name)
             return

tests/functional/n/name_good_bad_names_regex.py

@@ -0,0 +1,20 @@
+# pylint: disable=missing-docstring,too-few-public-methods
+__version__ = "1.0"
+ignored_SOME_CONSTANT = 42
+
+explicit_bad_some_constant = 42  # [blacklisted-name]
+
+snake_case_bad_SOME_CONSTANT = 42  # [invalid-name]
+
+
+class my_class:
+    def __init__(self, arg_x):
+        self._my_secret_x = arg_x
+
+    @property
+    def my_public_x(self):
+        return self._my_secret_x * 2
+
+
+def blacklisted_2_snake_case():  # [blacklisted-name]
+    pass

tests/functional/n/name_good_bad_names_regex.rc

@@ -0,0 +1,15 @@
+[BASIC]
+function-naming-style=snake_case
+const-naming-style=snake_case
+attr-naming-style=snake_case
+argument-naming-style=snake_case
+module-naming-style=snake_case
+method-naming-style=snake_case
+variable-naming-style=snake_case
+class-attribute-naming-style=snake_case
+inlinevar-naming-style=snake_case
+class-naming-style=snake_case
+
+good-names-rgxs=ignored.*
+bad-names-rgxs=explicit.*,blacklisted.*
+include-naming-hint=yes

tests/functional/n/name_good_bad_names_regex.txt

@@ -0,0 +1,3 @@
+blacklisted-name:5::"Black listed name ""explicit_bad_some_constant"""
+invalid-name:7::"Constant name ""snake_case_bad_SOME_CONSTANT"" doesn't conform to snake_case naming style ('(([a-z_][a-z0-9_]*)|(__.*__))$' pattern)"
+blacklisted-name:19:blacklisted_2_snake_case:"Black listed name ""blacklisted_2_snake_case"""