Add new message called duplicate-value for sets (#5928)

Adds some new functionality which checks for duplicate values
inside sets. For that reason, we create a new message called duplicate-value.

Co-authored-by: Daniël van Noord <13665637+DanielNoord@users.noreply.github.com>
Co-authored-by: Pierre Sassoulas <pierre.sassoulas@gmail.com>

ChangeLog

@@ -40,6 +40,10 @@ Release date: TBA
 
 * Fix bug where specifically enabling just ``await-outside-async`` was not possible.
 
+* Added new message called ``duplicate-value`` which identifies duplicate values inside sets.
+
+  Closes #5880
+
 ..
   Insert your changelog randomly, it will reduce merge conflicts
   (Ie. not necessarily at the end)

doc/data/messages/d/duplicate-value/bad.py

@@ -0,0 +1 @@
+incorrect_set = {'value1', 23, 5, 'value1'} # [duplicate-value]

doc/data/messages/d/duplicate-value/good.py

@@ -0,0 +1 @@
+correct_set = {'value1', 23, 5}

doc/whatsnew/2.14.rst

@@ -27,6 +27,10 @@ New checkers
 
   Closes #4525
 
+* Added new message called ``duplicate-value`` which identifies duplicate values inside sets.
+
+  Closes #5880
+
 Removed checkers
 ================
 

pylint/checkers/base/basic_checker.py

@@ -15,7 +15,7 @@
 from pylint import interfaces
 from pylint import utils as lint_utils
 from pylint.checkers import BaseChecker, utils
-from pylint.interfaces import IAstroidChecker
+from pylint.interfaces import HIGH, IAstroidChecker
 from pylint.reporters.ureports import nodes as reporter_nodes
 from pylint.utils import LinterStats
 from pylint.utils.utils import get_global_option
@@ -246,6 +246,11 @@ class BasicChecker(_BasicChecker):
             "Used when an assert statement has a string literal as its first argument, which will "
             "cause the assert to always pass.",
         ),
+        "W0130": (
+            "Duplicate value %r in set",
+            "duplicate-value",
+            "This message is emitted when a set contains the same value two or more times.",
+        ),
     }
 
     reports = (("RP0101", "Statistics by type", report_by_type_stats),)
@@ -637,6 +642,21 @@ def visit_dict(self, node: nodes.Dict) -> None:
                 self.add_message("duplicate-key", node=node, args=key)
             keys.add(key)
 
+    @utils.check_messages("duplicate-value")
+    def visit_set(self, node: nodes.Set) -> None:
+        """Check duplicate value in set."""
+        values = set()
+        for v in node.elts:
+            if isinstance(v, nodes.Const):
+                value = v.value
+            else:
+                continue
+            if value in values:
+                self.add_message(
+                    "duplicate-value", node=node, args=value, confidence=HIGH
+                )
+            values.add(value)
+
     def visit_tryfinally(self, node: nodes.TryFinally) -> None:
         """Update try...finally flag."""
         self._tryfinallys.append(node)

pylint/checkers/format.py

@@ -673,10 +673,8 @@ def is_line_length_check_activated(pylint_pattern_match_object) -> bool:
     def specific_splitlines(lines: str) -> List[str]:
         """Split lines according to universal newlines except those in a specific sets."""
         unsplit_ends = {
-            "\v",
-            "\x0b",
-            "\f",
-            "\x0c",
+            "\x0b",  # synonym of \v
+            "\x0c",  # synonym of \f
             "\x1c",
             "\x1d",
             "\x1e",

tests/functional/d/duplicate_value.py

@@ -0,0 +1,18 @@
+# pylint: disable = invalid-name, line-too-long
+"""Simple test sets for checking duplicate values"""
+
+set1 = {1, 2, 3, 4}
+set2 = {1, 1, 2} # [duplicate-value]
+set3 = {1, 2, 2} # [duplicate-value]
+
+set4 = {'one', 'two', 'three'}
+set5 = {'one', 'two', 'one'} # [duplicate-value]
+set6 = {'one', 'two', 'two'} # [duplicate-value]
+
+wrong_set = {12, 23, True, 6, True, 0, 12} # [duplicate-value, duplicate-value]
+correct_set = {12, 13, 23, 24, 89}
+
+wrong_set_mixed = {1, 2, 'value', 1} # [duplicate-value]
+wrong_set = {'arg1', 'arg2', False, 'arg1', True} # [duplicate-value]
+
+another_wrong_set = {2, 3, 'arg1', True, 'arg1', False, True} # [duplicate-value, duplicate-value]

tests/functional/d/duplicate_value.txt

@@ -0,0 +1,10 @@
+duplicate-value:5:7:5:16::Duplicate value 1 in set:HIGH
+duplicate-value:6:7:6:16::Duplicate value 2 in set:HIGH
+duplicate-value:9:7:9:28::Duplicate value 'one' in set:HIGH
+duplicate-value:10:7:10:28::Duplicate value 'two' in set:HIGH
+duplicate-value:12:12:12:42::Duplicate value 12 in set:HIGH
+duplicate-value:12:12:12:42::Duplicate value True in set:HIGH
+duplicate-value:15:18:15:36::Duplicate value 1 in set:HIGH
+duplicate-value:16:12:16:49::Duplicate value 'arg1' in set:HIGH
+duplicate-value:18:20:18:61::Duplicate value 'arg1' in set:HIGH
+duplicate-value:18:20:18:61::Duplicate value True in set:HIGH