pythongh-105017: Fix including additional NL token when using CRLF (p…

…ythonGH-105022)

(cherry picked from commit 86d8f48)

Co-authored-by: Marta Gómez Macías <mgmacias@google.com>
Co-authored-by: Pablo Galindo Salgado <Pablogsal@gmail.com>

Lib/test/test_tokenize.py

@@ -84,6 +84,14 @@ def test_basic(self):
  NEWLINE '\\n' (4, 26) (4, 27)
  DEDENT '' (5, 0) (5, 0)
  """)
+
+ self.check_tokenize("foo='bar'\r\n", """\
+ NAME 'foo' (1, 0) (1, 3)
+ OP '=' (1, 3) (1, 4)
+ STRING "'bar'" (1, 4) (1, 9)
+ NEWLINE '\\n' (1, 9) (1, 10)
+ """)
+
  indent_error_file = b"""\
 def k(x):
  x += 2

Misc/NEWS.d/next/Core and Builtins/2023-05-27-16-23-16.gh-issue-105017.KQrsC0.rst

@@ -0,0 +1 @@
+Do not include an additional final ``NL`` token when parsing files having CRLF lines. Patch by Marta Gómez.

Parser/tokenizer.c

@@ -800,7 +800,7 @@ translate_newlines(const char *s, int exec_input, struct tok_state *tok) {
  }
  /* If this is exec input, add a newline to the end of the string if
  there isn't one already. */
- if (exec_input && c != '\n') {
+ if (exec_input && c != '\n' && c != '\0') {
  *current = '\n';
  current++;
  }