Issue #2382: SyntaxError cursor "^" now is written at correct position in most

cases when multibyte characters are in line (before "^").  This still not
works correctly with wide East Asian characters.

2 files changed, 22 insertions, 0 deletions

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index f0851bdbe2..4770dfd43e 100644
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -148,6 +148,19 @@ class ExceptionTests(unittest.TestCase):
         ckmsg(s, "'continue' not properly in loop")
         ckmsg("continue\n", "'continue' not properly in loop")
 
+    def testSyntaxErrorOffset(self):
+        def check(src, lineno, offset):
+            with self.assertRaises(SyntaxError) as cm:
+                compile(src, '<fragment>', 'exec')
+            self.assertEqual(cm.exception.lineno, lineno)
+            self.assertEqual(cm.exception.offset, offset)
+
+        check('def fact(x):\n\treturn x!\n', 2, 10)
+        check('1 +\n', 1, 4)
+        check('def spam():\n  print(1)\n print(2)', 3, 10)
+        check('Python = "Python" +', 1, 20)
+        check('Python = "\u1e54\xfd\u0163\u0125\xf2\xf1" +', 1, 20)
+
     @cpython_only
     def testSettingException(self):
         # test that setting an exception at the C level works even if the
diff --git a/Lib/test/test_traceback.py b/Lib/test/test_traceback.py
index 172f5b5368..a6ae1e5ef2 100644
--- a/Lib/test/test_traceback.py
+++ b/Lib/test/test_traceback.py
@@ -32,6 +32,9 @@ class SyntaxTracebackCases(unittest.TestCase):
     def syntax_error_bad_indentation(self):
         compile("def spam():\n  print(1)\n print(2)", "?", "exec")
 
+    def syntax_error_with_caret_non_ascii(self):
+        compile('Python = "\u1e54\xfd\u0163\u0125\xf2\xf1" +', "?", "exec")
+
     def test_caret(self):
         err = self.get_exception_format(self.syntax_error_with_caret,
                                         SyntaxError)
@@ -46,6 +49,12 @@ class SyntaxTracebackCases(unittest.TestCase):
         self.assertTrue(err[2].count('\n') == 1) # and no additional newline
         self.assertTrue(err[1].find("+") == err[2].find("^")) # in the right place
 
+        err = self.get_exception_format(self.syntax_error_with_caret_non_ascii,
+                                        SyntaxError)
+        self.assertIn("^", err[2]) # third line has caret
+        self.assertTrue(err[2].count('\n') == 1) # and no additional newline
+        self.assertTrue(err[1].find("+") == err[2].find("^")) # in the right place
+
     def test_nocaret(self):
         exc = SyntaxError("error", ("x.py", 23, None, "bad syntax"))
         err = traceback.format_exception_only(SyntaxError, exc)