bpo-34454: Clean up datetime.fromisoformat surrogate handling (GH-8959)

* Use _PyUnicode_Copy in sanitize_isoformat_str

* Use repr in fromisoformat error message

This reverses commit 67b74a98b2 per Serhiy Storchaka's suggestion:

     I suggested to use %R in the error message because including the raw
     string can be confusing in the case of empty string, or string
     containing trailing whitespaces, invisible or unprintable characters.

We agree that it is better to change both the C and pure Python versions
to use repr.

* Retain non-sanitized dtstr for error printing

This does not create an extra string, it just holds on to a reference to
the original input string for purposes of creating the error message.

* PEP 7 fixes to from_isoformat

* Separate handling of Unicode and other errors

In the initial implementation, errors other than encoding errors would
both raise an error indicating an invalid format, which would not be
true for errors like MemoryError.

* Drop needs_decref from _sanitize_isoformat_str

Instead _sanitize_isoformat_str returns a new reference, even to the
original string.
(cherry picked from commit 3df8540)

Co-authored-by: Paul Ganssle <[email protected]>

Author: miss-islington

Lib/datetime.py

@@ -857,7 +857,7 @@ def fromisoformat(cls, date_string):
             assert len(date_string) == 10
             return cls(*_parse_isoformat_date(date_string))
         except Exception:
-            raise ValueError('Invalid isoformat string: %s' % date_string)
+            raise ValueError(f'Invalid isoformat string: {date_string!r}')
 
 
     # Conversions to string
@@ -1369,7 +1369,7 @@ def fromisoformat(cls, time_string):
         try:
             return cls(*_parse_isoformat_time(time_string))
         except Exception:
-            raise ValueError('Invalid isoformat string: %s' % time_string)
+            raise ValueError(f'Invalid isoformat string: {time_string!r}')
 
 
     def strftime(self, fmt):
@@ -1646,13 +1646,13 @@ def fromisoformat(cls, date_string):
         try:
             date_components = _parse_isoformat_date(dstr)
         except ValueError:
-            raise ValueError('Invalid isoformat string: %s' % date_string)
+            raise ValueError(f'Invalid isoformat string: {date_string!r}')
 
         if tstr:
             try:
                 time_components = _parse_isoformat_time(tstr)
             except ValueError:
-                raise ValueError('Invalid isoformat string: %s' % date_string)
+                raise ValueError(f'Invalid isoformat string: {date_string!r}')
         else:
             time_components = [0, 0, 0, 0, None]
 

Lib/test/datetimetester.py

@@ -13,6 +13,7 @@
 import os
 import pickle
 import random
+import re
 import struct
 import unittest
 
@@ -2676,6 +2677,14 @@ def test_fromisoformat_fails_datetime(self):
                 with self.assertRaises(ValueError):
                     self.theclass.fromisoformat(bad_str)
 
+    def test_fromisoformat_fails_surrogate(self):
+        # Test that when fromisoformat() fails with a surrogate character as
+        # the separator, the error message contains the original string
+        dtstr = "2018-01-03\ud80001:0113"
+
+        with self.assertRaisesRegex(ValueError, re.escape(repr(dtstr))):
+            self.theclass.fromisoformat(dtstr)
+
     def test_fromisoformat_utc(self):
         dt_str = '2014-04-19T13:21:13+00:00'
         dt = self.theclass.fromisoformat(dt_str)