bpo-44409: Fix error location in tokenizer errors that happen during initialization...

(cherry picked from commit 507ed6fa1d6661e0f8e6d3282764aa9625a99594)

Co-authored-by: Pablo Galindo <Pablogsal@gmail.com>

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index 9cb5466a674d1364c279883a4503dbdb2cb0abe7..d444a122af9be7bc36df1e5fb759ed0811e4e779 100644 (file)
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -246,6 +246,7 @@ class ExceptionTests(unittest.TestCase):
         check("pass\npass\npass\n(1+)\npass\npass\npass", 4, 4)
         check("(1+)", 1, 4)
         check("[interesting\nfoo()\n", 1, 1)
+        check(b"\xef\xbb\xbf#coding: utf8\nprint('\xe6\x88\x91')\n", 0, -1)
 
         # Errors thrown by symtable.c
         check('x = [(yield i) for i in range(3)]', 1, 5)

diff --git a/Misc/NEWS.d/next/Core and Builtins/2021-06-13-23-12-18.bpo-44409.eW4LS-.rst b/Misc/NEWS.d/next/Core and Builtins/2021-06-13-23-12-18.bpo-44409.eW4LS-.rst
new file mode 100644 (file)
index 0000000..0f204ed
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2021-06-13-23-12-18.bpo-44409.eW4LS-.rst
@@ -0,0 +1,2 @@
+Fix error location information for tokenizer errors raised on initialization
+of the tokenizer. Patch by Pablo Galindo.

diff --git a/Parser/pegen.c b/Parser/pegen.c
index 19412446b118abd4b1ab00a2641fed220f3689fd..615047c1b6a00731b756d0b5bbc49d9efad0e2a6 100644 (file)
--- a/Parser/pegen.c
+++ b/Parser/pegen.c
@@ -283,6 +283,7 @@ static void
 raise_tokenizer_init_error(PyObject *filename)
 {
     if (!(PyErr_ExceptionMatches(PyExc_LookupError)
+          || PyErr_ExceptionMatches(PyExc_SyntaxError)
           || PyErr_ExceptionMatches(PyExc_ValueError)
           || PyErr_ExceptionMatches(PyExc_UnicodeDecodeError))) {
         return;