gh-81005: Refactor str tests to reflect that str and unicode are merged in Python 3 (#13172)

Co-authored-by: Hugo van Kemenade <[email protected]>

Author: asqui

Lib/test/string_tests.py

@@ -8,26 +8,20 @@
 from collections import UserList
 import random
 
+
 class Sequence:
     def __init__(self, seq='wxyz'): self.seq = seq
     def __len__(self): return len(self.seq)
     def __getitem__(self, i): return self.seq[i]
 
-class BadSeq1(Sequence):
-    def __init__(self): self.seq = [7, 'hello', 123]
-    def __str__(self): return '{0} {1} {2}'.format(*self.seq)
-
-class BadSeq2(Sequence):
-    def __init__(self): self.seq = ['a', 'b', 'c']
-    def __len__(self): return 8
 
 class BaseTest:
     # These tests are for buffers of values (bytes) and not
     # specific to character interpretation, used for bytes objects
     # and various string implementations
 
     # The type to be tested
-    # Change in subclasses to change the behaviour of fixtesttype()
+    # Change in subclasses to change the behaviour of fixtype()
     type2test = None
 
     # Whether the "contained items" of the container are integers in
@@ -36,7 +30,7 @@ class BaseTest:
     contains_bytes = False
 
     # All tests pass their arguments to the testing methods
-    # as str objects. fixtesttype() can be used to propagate
+    # as str objects. fixtype() can be used to propagate
     # these arguments to the appropriate type
     def fixtype(self, obj):
         if isinstance(obj, str):
@@ -1096,7 +1090,7 @@ def test_splitlines(self):
         self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)
 
 
-class CommonTest(BaseTest):
+class StringLikeTest(BaseTest):
     # This testcase contains tests that can be used in all
     # stringlike classes. Currently this is str and UserString.
 
@@ -1127,11 +1121,6 @@ def test_capitalize_nonascii(self):
         self.checkequal('\u019b\u1d00\u1d86\u0221\u1fb7',
                         '\u019b\u1d00\u1d86\u0221\u1fb7', 'capitalize')
 
-
-class MixinStrUnicodeUserStringTest:
-    # additional tests that only work for
-    # stringlike objects, i.e. str, UserString
-
     def test_startswith(self):
         self.checkequal(True, 'hello', 'startswith', 'he')
         self.checkequal(True, 'hello', 'startswith', 'hello')
@@ -1313,8 +1302,11 @@ def test_join(self):
             self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
                  ('a' * i,) * i)
 
-        #self.checkequal(str(BadSeq1()), ' ', 'join', BadSeq1())
-        self.checkequal('a b c', ' ', 'join', BadSeq2())
+        class LiesAboutLengthSeq(Sequence):
+            def __init__(self): self.seq = ['a', 'b', 'c']
+            def __len__(self): return 8
+
+        self.checkequal('a b c', ' ', 'join', LiesAboutLengthSeq())
 
         self.checkraises(TypeError, ' ', 'join')
         self.checkraises(TypeError, ' ', 'join', None)

Lib/test/test_builtin.py

@@ -1614,7 +1614,7 @@ def test_setattr(self):
         msg = r"^attribute name must be string, not 'int'$"
         self.assertRaisesRegex(TypeError, msg, setattr, sys, 1, 'spam')
 
-    # test_str(): see test_unicode.py and test_bytes.py for str() tests.
+    # test_str(): see test_str.py and test_bytes.py for str() tests.
 
     def test_sum(self):
         self.assertEqual(sum([]), 0)

Lib/test/test_unicode.py renamed to Lib/test/test_str.py

@@ -55,8 +55,7 @@ def duplicate_string(text):
 class StrSubclass(str):
     pass
 
-class UnicodeTest(string_tests.CommonTest,
-        string_tests.MixinStrUnicodeUserStringTest,
+class StrTest(string_tests.StringLikeTest,
         string_tests.MixinStrUnicodeTest,
         unittest.TestCase):
 
@@ -213,7 +212,7 @@ def test_pickle_iterator(self):
                         self.assertEqual(case, pickled)
 
     def test_count(self):
-        string_tests.CommonTest.test_count(self)
+        string_tests.StringLikeTest.test_count(self)
         # check mixed argument types
         self.checkequalnofix(3,  'aaa', 'count', 'a')
         self.checkequalnofix(0,  'aaa', 'count', 'b')
@@ -243,7 +242,7 @@ class MyStr(str):
         self.checkequal(3, MyStr('aaa'), 'count', 'a')
 
     def test_find(self):
-        string_tests.CommonTest.test_find(self)
+        string_tests.StringLikeTest.test_find(self)
         # test implementation details of the memchr fast path
         self.checkequal(100, 'a' * 100 + '\u0102', 'find', '\u0102')
         self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0201')
@@ -288,7 +287,7 @@ def test_find(self):
         self.checkequal(-1, '\u0102' * 100, 'find', '\u0102\U00100304')
 
     def test_rfind(self):
-        string_tests.CommonTest.test_rfind(self)
+        string_tests.StringLikeTest.test_rfind(self)
         # test implementation details of the memrchr fast path
         self.checkequal(0, '\u0102' + 'a' * 100 , 'rfind', '\u0102')
         self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0201')
@@ -329,7 +328,7 @@ def test_rfind(self):
         self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304\u0102')
 
     def test_index(self):
-        string_tests.CommonTest.test_index(self)
+        string_tests.StringLikeTest.test_index(self)
         self.checkequalnofix(0, 'abcdefghiabc', 'index',  '')
         self.checkequalnofix(3, 'abcdefghiabc', 'index',  'def')
         self.checkequalnofix(0, 'abcdefghiabc', 'index',  'abc')
@@ -353,7 +352,7 @@ def test_index(self):
         self.assertRaises(ValueError, ('\u0102' * 100).index, '\u0102\U00100304')
 
     def test_rindex(self):
-        string_tests.CommonTest.test_rindex(self)
+        string_tests.StringLikeTest.test_rindex(self)
         self.checkequalnofix(12, 'abcdefghiabc', 'rindex',  '')
         self.checkequalnofix(3,  'abcdefghiabc', 'rindex',  'def')
         self.checkequalnofix(9,  'abcdefghiabc', 'rindex',  'abc')
@@ -449,7 +448,7 @@ def test_maketrans_translate(self):
         self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz')
 
     def test_split(self):
-        string_tests.CommonTest.test_split(self)
+        string_tests.StringLikeTest.test_split(self)
 
         # test mixed kinds
         for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
@@ -466,7 +465,7 @@ def test_split(self):
                                 left + delim * 2 + right, 'split', delim *2)
 
     def test_rsplit(self):
-        string_tests.CommonTest.test_rsplit(self)
+        string_tests.StringLikeTest.test_rsplit(self)
         # test mixed kinds
         for left, right in ('ba', 'юё', '\u0101\u0100', '\U00010301\U00010300'):
             left *= 9
@@ -486,7 +485,7 @@ def test_rsplit(self):
                              left + right, 'rsplit', None)
 
     def test_partition(self):
-        string_tests.MixinStrUnicodeUserStringTest.test_partition(self)
+        string_tests.StringLikeTest.test_partition(self)
         # test mixed kinds
         self.checkequal(('ABCDEFGH', '', ''), 'ABCDEFGH', 'partition', '\u4200')
         for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
@@ -503,7 +502,7 @@ def test_partition(self):
                                 left + delim * 2 + right, 'partition', delim * 2)
 
     def test_rpartition(self):
-        string_tests.MixinStrUnicodeUserStringTest.test_rpartition(self)
+        string_tests.StringLikeTest.test_rpartition(self)
         # test mixed kinds
         self.checkequal(('', '', 'ABCDEFGH'), 'ABCDEFGH', 'rpartition', '\u4200')
         for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
@@ -520,7 +519,7 @@ def test_rpartition(self):
                                 left + delim * 2 + right, 'rpartition', delim * 2)
 
     def test_join(self):
-        string_tests.MixinStrUnicodeUserStringTest.test_join(self)
+        string_tests.StringLikeTest.test_join(self)
 
         class MyWrapper:
             def __init__(self, sval): self.sval = sval
@@ -547,7 +546,7 @@ def test_join_overflow(self):
         self.assertRaises(OverflowError, ''.join, seq)
 
     def test_replace(self):
-        string_tests.CommonTest.test_replace(self)
+        string_tests.StringLikeTest.test_replace(self)
 
         # method call forwarded from str implementation because of unicode argument
         self.checkequalnofix('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
@@ -866,7 +865,7 @@ def test_surrogates(self):
 
 
     def test_lower(self):
-        string_tests.CommonTest.test_lower(self)
+        string_tests.StringLikeTest.test_lower(self)
         self.assertEqual('\U00010427'.lower(), '\U0001044F')
         self.assertEqual('\U00010427\U00010427'.lower(),
                          '\U0001044F\U0001044F')
@@ -897,7 +896,7 @@ def test_casefold(self):
         self.assertEqual('\u00b5'.casefold(), '\u03bc')
 
     def test_upper(self):
-        string_tests.CommonTest.test_upper(self)
+        string_tests.StringLikeTest.test_upper(self)
         self.assertEqual('\U0001044F'.upper(), '\U00010427')
         self.assertEqual('\U0001044F\U0001044F'.upper(),
                          '\U00010427\U00010427')
@@ -914,7 +913,7 @@ def test_upper(self):
         self.assertEqual('\u2177'.upper(), '\u2167')
 
     def test_capitalize(self):
-        string_tests.CommonTest.test_capitalize(self)
+        string_tests.StringLikeTest.test_capitalize(self)
         self.assertEqual('\U0001044F'.capitalize(), '\U00010427')
         self.assertEqual('\U0001044F\U0001044F'.capitalize(),
                          '\U00010427\U0001044F')
@@ -948,7 +947,7 @@ def test_title(self):
         self.assertEqual('A\u03a3A'.title(), 'A\u03c3a')
 
     def test_swapcase(self):
-        string_tests.CommonTest.test_swapcase(self)
+        string_tests.StringLikeTest.test_swapcase(self)
         self.assertEqual('\U0001044F'.swapcase(), '\U00010427')
         self.assertEqual('\U00010427'.swapcase(), '\U0001044F')
         self.assertEqual('\U0001044F\U0001044F'.swapcase(),
@@ -974,7 +973,7 @@ def test_swapcase(self):
         self.assertEqual('\u1fd2'.swapcase(), '\u0399\u0308\u0300')
 
     def test_center(self):
-        string_tests.CommonTest.test_center(self)
+        string_tests.StringLikeTest.test_center(self)
         self.assertEqual('x'.center(2, '\U0010FFFF'),
                          'x\U0010FFFF')
         self.assertEqual('x'.center(3, '\U0010FFFF'),
@@ -1475,7 +1474,7 @@ def __format__(self, spec):
         self.assertEqual('{f:{}}{}{g}'.format(2, 4, f=1, g='g'), ' 14g')
 
     def test_formatting(self):
-        string_tests.MixinStrUnicodeUserStringTest.test_formatting(self)
+        string_tests.StringLikeTest.test_formatting(self)
         # Testing Unicode formatting strings...
         self.assertEqual("%s, %s" % ("abc", "abc"), 'abc, abc')
         self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", 1, 2, 3), 'abc, abc, 1, 2.000000,  3.00')

Lib/test/test_userstring.py

@@ -7,8 +7,7 @@
 from collections import UserString
 
 class UserStringTest(
-    string_tests.CommonTest,
-    string_tests.MixinStrUnicodeUserStringTest,
+    string_tests.StringLikeTest,
     unittest.TestCase
     ):
 

Misc/NEWS.d/next/Tests/2023-05-19-08-06-06.gh-issue-81005.-q7m9W.rst

@@ -0,0 +1,2 @@
+String tests are modified to reflect that ``str`` and ``unicode`` are merged
+in Python 3. Patch by Daniel Fortunov.