bpo-42065: Fix incorrectly formatted _codecs.charmap_decode error message (GH-19940)

(cherry picked from commit 3635388f52b42e5280229104747962117104c453)

Co-authored-by: Max Bernstein <tekknolagi@users.noreply.github.com>

diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index 54a3520802a4f317ccdb792765c4427689710d9a..8d112a171d7c4ef5f2138ff398d2b5270b3cccee 100644 (file)
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -2183,6 +2183,18 @@ class CharmapTest(unittest.TestCase):
             ("", len(allbytes))
         )
 
+        self.assertRaisesRegex(TypeError,
+            "character mapping must be in range\\(0x110000\\)",
+            codecs.charmap_decode,
+            b"\x00\x01\x02", "strict", {0: "A", 1: 'Bb', 2: -2}
+        )
+
+        self.assertRaisesRegex(TypeError,
+            "character mapping must be in range\\(0x110000\\)",
+            codecs.charmap_decode,
+            b"\x00\x01\x02", "strict", {0: "A", 1: 'Bb', 2: 999999999}
+        )
+
     def test_decode_with_int2int_map(self):
         a = ord('a')
         b = ord('b')

diff --git a/Misc/NEWS.d/next/Library/2020-10-17-23-17-18.bpo-42065.85BsRA.rst b/Misc/NEWS.d/next/Library/2020-10-17-23-17-18.bpo-42065.85BsRA.rst
new file mode 100644 (file)
index 0000000..83c86c0
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2020-10-17-23-17-18.bpo-42065.85BsRA.rst
@@ -0,0 +1,3 @@
+Fix an incorrectly formatted error from :meth:`_codecs.charmap_decode` when
+called with a mapped value outside the range of valid Unicode code points.
+PR by Max Bernstein.

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 3c2383d57c863e0b79e81e4757be03feb8414f97..d5fbf158d50b429e97919135490632380e9091f1 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -8160,7 +8160,7 @@ charmap_decode_mapping(const char *s,
                 goto Undefined;
             if (value < 0 || value > MAX_UNICODE) {
                 PyErr_Format(PyExc_TypeError,
-                             "character mapping must be in range(0x%lx)",
+                             "character mapping must be in range(0x%x)",
                              (unsigned long)MAX_UNICODE + 1);
                 goto onError;
             }