From: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>
Date: Sun, 23 Apr 2023 23:21:27 +0000 (-0700)
Subject: [3.11] gh-102310: Change error range for invalid bytes literals (GH-103663) (#103703)
X-Git-Tag: v3.11.4~182
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=7b2ac6cf3dd33d591d0e14a020c84aa331d29932;p=thirdparty%2FPython%2Fcpython.git

[3.11] gh-102310: Change error range for invalid bytes literals (GH-103663) (#103703)
---

diff --git a/Lib/test/test_syntax.py b/Lib/test/test_syntax.py
index 50168d9200a2..81456d62a37c 100644
--- a/Lib/test/test_syntax.py
+++ b/Lib/test/test_syntax.py
@@ -1803,6 +1803,30 @@ x: *b
     Traceback (most recent call last):
         ...
     SyntaxError: invalid syntax
+
+Invalid bytes literals:
+
+   >>> b"Ā"
+   Traceback (most recent call last):
+      ...
+       b"Ā"
+        ^^^
+   SyntaxError: bytes can only contain ASCII literal characters
+
+   >>> b"абвгде"
+   Traceback (most recent call last):
+      ...
+       b"абвгде"
+        ^^^^^^^^
+   SyntaxError: bytes can only contain ASCII literal characters
+
+   >>> b"abc ъющый"  # first 3 letters are ascii
+   Traceback (most recent call last):
+      ...
+       b"abc ъющый"
+        ^^^^^^^^^^^
+   SyntaxError: bytes can only contain ASCII literal characters
+
 """
 
 import re
diff --git a/Misc/NEWS.d/next/Core and Builtins/2023-04-21-17-03-14.gh-issue-102310.anLjDx.rst b/Misc/NEWS.d/next/Core and Builtins/2023-04-21-17-03-14.gh-issue-102310.anLjDx.rst
new file mode 100644
index 000000000000..15cb6c64adba
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2023-04-21-17-03-14.gh-issue-102310.anLjDx.rst	
@@ -0,0 +1 @@
+Change the error range for invalid bytes literals.
diff --git a/Parser/string_parser.c b/Parser/string_parser.c
index 4f3f046673cb..fb2b9808af15 100644
--- a/Parser/string_parser.c
+++ b/Parser/string_parser.c
@@ -259,7 +259,8 @@ _PyPegen_parsestr(Parser *p, int *bytesmode, int *rawmode, PyObject **result,
         const char *ch;
         for (ch = s; *ch; ch++) {
             if (Py_CHARMASK(*ch) >= 0x80) {
-                RAISE_SYNTAX_ERROR(
+                RAISE_SYNTAX_ERROR_KNOWN_LOCATION(
+                                   t,
                                    "bytes can only contain ASCII "
                                    "literal characters");
                 return -1;