bpo-46503: Prevent an assert from firing when parsing some invalid \N sequences in f-strings. (GH-30865) (30867)

* bpo-46503: Prevent an assert from firing.  Also fix one nearby tiny PEP-7 nit.

* Added blurb.
(cherry picked from commit 0daf72194bd4e31de7f12020685bb39a14d6f45e)

Co-authored-by: Eric V. Smith <ericvsmith@users.noreply.github.com>

Co-authored-by: Eric V. Smith <ericvsmith@users.noreply.github.com>

1 files changed, 14 insertions, 2 deletions

diff --git a/Parser/pegen/parse_string.c b/Parser/pegen/parse_string.c
index f1df2c4..af350b3 100644
--- a/Parser/pegen/parse_string.c
+++ b/Parser/pegen/parse_string.c
@@ -444,12 +444,23 @@ fstring_find_literal(Parser *p, const char **str, const char *end, int raw,
         if (!raw && ch == '\\' && s < end) {
             ch = *s++;
             if (ch == 'N') {
+                /* We need to look at and skip matching braces for "\N{name}"
+                   sequences because otherwise we'll think the opening '{'
+                   starts an expression, which is not the case with "\N".
+                   Keep looking for either a matched '{' '}' pair, or the end
+                   of the string. */
+
                 if (s < end && *s++ == '{') {
                     while (s < end && *s++ != '}') {
                     }
                     continue;
                 }
-                break;
+
+                /* This is an invalid "\N" sequence, since it's a "\N" not
+                   followed by a "{".  Just keep parsing this literal.  This
+                   error will be caught later by
+                   decode_unicode_with_escapes(). */
+                continue;
             }
             if (ch == '{' && warn_invalid_escape_sequence(p, ch, t) < 0) {
                 return -1;
@@ -493,7 +504,8 @@ done:
             *literal = PyUnicode_DecodeUTF8Stateful(literal_start,
                                                     s - literal_start,
                                                     NULL, NULL);
-        } else {
+        }
+        else {
             *literal = decode_unicode_with_escapes(p, literal_start,
                                                    s - literal_start, t);
         }