gh-88535: Improve syntax error for wrongly closed strings (#26633)

Author: pablogsal

Doc/whatsnew/3.14.rst

@@ -165,7 +165,7 @@ Improved error messages
   error message prints the received number of values in more cases than before.
   (Contributed by Tushar Sadhwani in :gh:`122239`.)
 
-  .. code-block:: pycon
+  .. code-block:: python
 
      >>> x, y, z = 1, 2, 3, 4
      Traceback (most recent call last):
@@ -175,6 +175,17 @@ Improved error messages
      ValueError: too many values to unpack (expected 3, got 4)
 
 
+* When incorrectly closed strings are detected, the error message suggests
+  that the string may be intended to be part of the string. (Contributed by
+  Pablo Galindo in :gh:`88535`.)
+
+  .. code-block:: python
+
+    >>> "The interesting object "The important object" is very important"
+    Traceback (most recent call last):
+    SyntaxError: invalid syntax. Is this intended to be part of the string?
+
+
 .. _whatsnew314-pep741:
 
 PEP 741: Python Configuration C API

Grammar/python.gram

@@ -1178,6 +1178,9 @@ invalid_type_param:
         }
 
 invalid_expression:
+   |  STRING a=(!STRING expression_without_invalid)+ STRING {
+        RAISE_SYNTAX_ERROR_KNOWN_RANGE( PyPegen_first_item(a, expr_ty), PyPegen_last_item(a, expr_ty),
+        "invalid syntax. Is this intended to be part of the string?") }
     # !(NAME STRING) is not matched so we don't show this error with some invalid string prefixes like: kf"dsfsdf"
     # Soft keywords need to also be ignored because they can be parsed as NAME NAME
    | !(NAME STRING | SOFT_KEYWORD) a=disjunction b=expression_without_invalid {

Lib/test/test_exceptions.py

@@ -2303,7 +2303,7 @@ def test_encodings(self):
         )
         err = run_script(source.encode('cp437'))
         self.assertEqual(err[-3], '    "¢¢¢¢¢¢" + f(4, x for x in range(1))')
-        self.assertEqual(err[-2], '                          ^^^^^^^^^^^^^^^^^^^')
+        self.assertEqual(err[-2], '                            ^^^')
 
         # Check backwards tokenizer errors
         source = '# -*- coding: ascii -*-\n\n(\n'

Lib/test/test_syntax.py

@@ -312,6 +312,12 @@
 Traceback (most recent call last):
 SyntaxError: did you forget parentheses around the comprehension target?
 
+# Incorrectly closed strings
+
+>>> "The interesting object "The important object" is very important"
+Traceback (most recent call last):
+SyntaxError: invalid syntax. Is this intended to be part of the string?
+
 # Missing commas in literals collections should not
 # produce special error messages regarding missing
 # parentheses, but about missing commas instead

Misc/NEWS.d/next/Core_and_Builtins/2021-06-09-23-04-58.bpo-44369.R7QkFv.rst

@@ -0,0 +1 @@
+Improve syntax errors for incorrectly closed strings. Patch by Pablo Galindo