Add redundant-u-string-prefix checker (#4804)

* Add ``redundant-u-string-prefix`` checker
This adds a checker for u-prefixes for strings, as used in Python 2. It only work in python 3.8 and above.
Closes #4102

ChangeLog

@@ -89,10 +89,14 @@ Release date: TBA
 
   Closes #626
 
-* Add ``disable-next`` option: allows using `# pylint: disable-next=msgid` to disable a message for the following line
+* Added ``disable-next`` option: allows using `# pylint: disable-next=msgid` to disable a message for the following line
 
   Closes #1682
 
+* Added ``redundant-u-string-prefix`` checker: Emitted when the u prefix is added to a string
+
+  Closes #4102
+
 
 What's New in Pylint 2.9.6?
 ===========================

doc/whatsnew/2.10.rst

@@ -71,10 +71,14 @@ Other Changes
 
   Closes #626
 
-* Add ``disable-next`` option: allows using `# pylint: disable-next=msgid` to disable a message for the following line
+* Added ``disable-next`` option: allows using `# pylint: disable-next=msgid` to disable a message for the following line
 
   Closes #1682
 
 * Added ``format-string-without-interpolation`` checker: Emitted when formatting is applied to a string without any variables to be replaced
 
   Closes #4042
+
+* Added ``redundant-u-string-prefix`` checker: Emitted when the u prefix is added to a string
+
+  Closes #4102

pylint/checkers/strings.py

@@ -669,6 +669,13 @@ class StringConstantChecker(BaseTokenChecker):
             "Quote delimiters are not used consistently throughout a module "
             "(with allowances made for avoiding unnecessary escaping).",
         ),
+        "W1406": (
+            "The u prefix for strings is no longer necessary in Python >=3.0",
+            "redundant-u-string-prefix",
+            "Used when we detect a string with a u prefix. These prefixes were necessary "
+            "in Python 2 to indicate a string was Unicode, but since Python 3.0 strings "
+            "are Unicode by default.",
+        ),
     }
     options = (
         (
@@ -905,6 +912,22 @@ def process_non_raw_string_token(
             # character can never be the start of a new backslash escape.
             index += 2
 
+    @check_messages("redundant-u-string-prefix")
+    def visit_const(self, node: astroid.Const):
+        if node.pytype() == "builtins.str" and not isinstance(
+            node.parent, astroid.JoinedStr
+        ):
+            self._detect_u_string_prefix(node)
+
+    def _detect_u_string_prefix(self, node: astroid.Const):
+        """Check whether strings include a 'u' prefix like u'String'"""
+        if node.kind == "u":
+            self.add_message(
+                "redundant-u-string-prefix",
+                line=node.lineno,
+                col_offset=node.col_offset,
+            )
+
 
 def register(linter):
     """required method to auto register this checker"""

tests/functional/a/anomalous_unicode_escape_py3.py

@@ -1,4 +1,4 @@
-# pylint:disable=pointless-string-statement
+# pylint:disable=pointless-string-statement, redundant-u-string-prefix
 """Test for backslash escapes in byte vs unicode strings"""
 
 # Would be valid in Unicode, but probably not what you want otherwise

tests/functional/a/assign/assigning_non_slot.py

@@ -1,7 +1,7 @@
 """ Checks assigning attributes not found in class slots
 will trigger assigning-non-slot warning.
 """
-# pylint: disable=too-few-public-methods, no-init, missing-docstring, no-absolute-import, import-error, useless-object-inheritance
+# pylint: disable=too-few-public-methods, no-init, missing-docstring, no-absolute-import, import-error, useless-object-inheritance, redundant-u-string-prefix
 from collections import deque
 
 from missing import Unknown

tests/functional/d/duplicate_dict_literal_key.py

@@ -1,5 +1,5 @@
 """Check multiple key definition"""
-# pylint: disable=pointless-statement
+# pylint: disable=pointless-statement, redundant-u-string-prefix
 
 correct_dict = {
     'tea': 'for two',

tests/functional/e/excess_escapes.py

@@ -1,5 +1,6 @@
 # pylint:disable=pointless-string-statement, fixme, misplaced-comparison-constant, comparison-with-itself
 """Stray backslash escapes may be missing a raw-string prefix."""
+# pylint: disable=redundant-u-string-prefix
 
 __revision__ = '$Id$'
 

tests/functional/e/excess_escapes.txt

@@ -1,9 +1,9 @@
-anomalous-backslash-in-string:7:5::"Anomalous backslash in string: '\['. String constant might be missing an r prefix."
-anomalous-backslash-in-string:7:7::"Anomalous backslash in string: '\]'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:8:8::"Anomalous backslash in string: '\/'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:9:20::"Anomalous backslash in string: '\`'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:16:15::"Anomalous backslash in string: '\o'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:16:20::"Anomalous backslash in string: '\o'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:18:13::"Anomalous backslash in string: '\8'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:18:17::"Anomalous backslash in string: '\9'. String constant might be missing an r prefix."
-anomalous-backslash-in-string:31:42::"Anomalous backslash in string: '\P'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:8:5::"Anomalous backslash in string: '\['. String constant might be missing an r prefix."
+anomalous-backslash-in-string:8:7::"Anomalous backslash in string: '\]'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:9:8::"Anomalous backslash in string: '\/'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:10:20::"Anomalous backslash in string: '\`'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:17:15::"Anomalous backslash in string: '\o'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:17:20::"Anomalous backslash in string: '\o'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:19:13::"Anomalous backslash in string: '\8'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:19:17::"Anomalous backslash in string: '\9'. String constant might be missing an r prefix."
+anomalous-backslash-in-string:32:42::"Anomalous backslash in string: '\P'. String constant might be missing an r prefix."

tests/functional/i/implicit/implicit_str_concat.py

@@ -1,4 +1,4 @@
-#pylint: disable=invalid-name,missing-docstring
+#pylint: disable=invalid-name,missing-docstring,redundant-u-string-prefix
 
 # Basic test with a list
 TEST_LIST1 = ['a' 'b']  # [implicit-str-concat]

tests/functional/i/iterable_context.py

@@ -2,7 +2,7 @@
 Checks that primitive values are not used in an
 iterating/mapping context.
 """
-# pylint: disable=missing-docstring,invalid-name,too-few-public-methods,no-init,no-self-use,import-error,unused-argument,bad-mcs-method-argument,wrong-import-position,no-else-return, useless-object-inheritance, unnecessary-comprehension
+# pylint: disable=missing-docstring,invalid-name,too-few-public-methods,no-init,no-self-use,import-error,unused-argument,bad-mcs-method-argument,wrong-import-position,no-else-return, useless-object-inheritance, unnecessary-comprehension,redundant-u-string-prefix
 from __future__ import print_function
 
 # primitives

tests/functional/m/member/membership_protocol.py

@@ -1,4 +1,4 @@
-# pylint: disable=missing-docstring,pointless-statement,expression-not-assigned,too-few-public-methods,import-error,no-init,wrong-import-position,no-else-return, comparison-with-itself, useless-object-inheritance
+# pylint: disable=missing-docstring,pointless-statement,expression-not-assigned,too-few-public-methods,import-error,no-init,wrong-import-position,no-else-return, comparison-with-itself, useless-object-inheritance, redundant-u-string-prefix
 
 # standard types
 1 in [1, 2, 3]

tests/functional/r/raise/raising_format_tuple.py

@@ -4,6 +4,7 @@
 instead.  The same holds for a string containing {...} suggesting str.format()
 was intended.
 '''
+# pylint: disable=redundant-u-string-prefix
 
 def bad_percent(arg):
     '''Raising a percent-formatted string and an argument'''

tests/functional/r/raise/raising_format_tuple.txt

@@ -1,7 +1,7 @@
-raising-format-tuple:10:4:bad_percent:Exception arguments suggest string formatting might be intended
-raising-format-tuple:18:4:bad_multiarg:Exception arguments suggest string formatting might be intended
-raising-format-tuple:26:4:bad_braces:Exception arguments suggest string formatting might be intended
-raising-format-tuple:34:4:bad_multistring:Exception arguments suggest string formatting might be intended
-raising-format-tuple:40:4:bad_triplequote:Exception arguments suggest string formatting might be intended
-raising-format-tuple:46:4:bad_unicode:Exception arguments suggest string formatting might be intended
-raising-format-tuple:51:4:raise_something_without_name:Exception arguments suggest string formatting might be intended
+raising-format-tuple:11:4:bad_percent:Exception arguments suggest string formatting might be intended
+raising-format-tuple:19:4:bad_multiarg:Exception arguments suggest string formatting might be intended
+raising-format-tuple:27:4:bad_braces:Exception arguments suggest string formatting might be intended
+raising-format-tuple:35:4:bad_multistring:Exception arguments suggest string formatting might be intended
+raising-format-tuple:41:4:bad_triplequote:Exception arguments suggest string formatting might be intended
+raising-format-tuple:47:4:bad_unicode:Exception arguments suggest string formatting might be intended
+raising-format-tuple:52:4:raise_something_without_name:Exception arguments suggest string formatting might be intended

tests/functional/r/redundant_u_string_prefix.py

@@ -0,0 +1,14 @@
+""""Checks for redundant u-prefixes for strings"""
+# pylint: disable=missing-function-docstring
+
+def print_good():
+    print("String")
+    print(f"String{1 + 1}")
+
+
+def print_bad():
+    print(u"String")  # [redundant-u-string-prefix]
+    print(u'String')  # [redundant-u-string-prefix]
+    print([u"String", u"String2"])  # [redundant-u-string-prefix, redundant-u-string-prefix]
+    print((u"String", u"String2"))  # [redundant-u-string-prefix, redundant-u-string-prefix]
+    print({1: u"String"})  # [redundant-u-string-prefix]

tests/functional/r/redundant_u_string_prefix.rc

@@ -0,0 +1,2 @@
+[testoptions]
+min_pyver=3.8

tests/functional/r/redundant_u_string_prefix.txt

@@ -0,0 +1,7 @@
+redundant-u-string-prefix:10:10::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:11:10::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:12:11::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:12:22::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:13:11::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:13:22::The u prefix for strings is no longer necessary in Python >=3.0:HIGH
+redundant-u-string-prefix:14:14::The u prefix for strings is no longer necessary in Python >=3.0:HIGH

tests/functional/s/suspicious_str_strip_call_py3.py

@@ -1,4 +1,5 @@
 """Suspicious str.strip calls."""
+# pylint: disable=redundant-u-string-prefix
 __revision__ = 1
 
 ''.strip('yo')

tests/functional/s/suspicious_str_strip_call_py3.txt

@@ -1,3 +1,3 @@
-bad-str-strip-call:7:0::Suspicious argument in str.strip call
-bad-str-strip-call:8:0::Suspicious argument in str.lstrip call
-bad-str-strip-call:9:0::Suspicious argument in bytes.rstrip call
+bad-str-strip-call:8:0::Suspicious argument in str.strip call
+bad-str-strip-call:9:0::Suspicious argument in str.lstrip call
+bad-str-strip-call:10:0::Suspicious argument in bytes.rstrip call

tests/functional/u/unsubscriptable_value.py

@@ -3,7 +3,7 @@
 (i.e. defines __getitem__ method).
 """
 # pylint: disable=missing-docstring,pointless-statement,expression-not-assigned,wrong-import-position, unnecessary-comprehension
-# pylint: disable=too-few-public-methods,import-error,invalid-name,wrong-import-order, useless-object-inheritance
+# pylint: disable=too-few-public-methods,import-error,invalid-name,wrong-import-order, useless-object-inheritance, redundant-u-string-prefix
 import six
 
 # primitives