gh-94808: Improve coverage of `unicode_find` and `unicode_rfind` (GH-98648)

(cherry picked from commit b1783bc124712fa03fea9621a0eb4119d29b14fe)

Co-authored-by: Nikita Sobolev <mail@sobolevn.me>

diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index f5ce095d1c12d6a8917a10d3183826316035eb62..0feb61629174e40f8fabd2e3701d39560b49147d 100644 (file)
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -221,6 +221,20 @@ class UnicodeTest(string_tests.CommonTest,
         self.checkequalnofix(9,  'abcdefghiabc', 'find', 'abc', 1)
         self.checkequalnofix(-1, 'abcdefghiabc', 'find', 'def', 4)
 
+        # test utf-8 non-ascii char
+        self.checkequal(0, 'тест', 'find', 'т')
+        self.checkequal(3, 'тест', 'find', 'т', 1)
+        self.checkequal(-1, 'тест', 'find', 'т', 1, 3)
+        self.checkequal(-1, 'тест', 'find', 'e')  # english `e`
+        # test utf-8 non-ascii slice
+        self.checkequal(1, 'тест тест', 'find', 'ес')
+        self.checkequal(1, 'тест тест', 'find', 'ес', 1)
+        self.checkequal(1, 'тест тест', 'find', 'ес', 1, 3)
+        self.checkequal(6, 'тест тест', 'find', 'ес', 2)
+        self.checkequal(-1, 'тест тест', 'find', 'ес', 6, 7)
+        self.checkequal(-1, 'тест тест', 'find', 'ес', 7)
+        self.checkequal(-1, 'тест тест', 'find', 'ec')  # english `ec`
+
         self.assertRaises(TypeError, 'hello'.find)
         self.assertRaises(TypeError, 'hello'.find, 42)
         # test mixed kinds
@@ -251,6 +265,19 @@ class UnicodeTest(string_tests.CommonTest,
         self.checkequalnofix(9,   'abcdefghiabc', 'rfind', 'abc')
         self.checkequalnofix(12,  'abcdefghiabc', 'rfind', '')
         self.checkequalnofix(12, 'abcdefghiabc', 'rfind',  '')
+        # test utf-8 non-ascii char
+        self.checkequal(1, 'тест', 'rfind', 'е')
+        self.checkequal(1, 'тест', 'rfind', 'е', 1)
+        self.checkequal(-1, 'тест', 'rfind', 'е', 2)
+        self.checkequal(-1, 'тест', 'rfind', 'e')  # english `e`
+        # test utf-8 non-ascii slice
+        self.checkequal(6, 'тест тест', 'rfind', 'ес')
+        self.checkequal(6, 'тест тест', 'rfind', 'ес', 1)
+        self.checkequal(1, 'тест тест', 'rfind', 'ес', 1, 3)
+        self.checkequal(6, 'тест тест', 'rfind', 'ес', 2)
+        self.checkequal(-1, 'тест тест', 'rfind', 'ес', 6, 7)
+        self.checkequal(-1, 'тест тест', 'rfind', 'ес', 7)
+        self.checkequal(-1, 'тест тест', 'rfind', 'ec')  # english `ec`
         # test mixed kinds
         self.checkequal(0, 'a' + '\u0102' * 100, 'rfind', 'a')
         self.checkequal(0, 'a' + '\U00100304' * 100, 'rfind', 'a')