Issue #18609: Add a fast-path for "iso8859-1" encoding

vstinner · vstinner · commit fa3ba4c3bc31 · 2013-10-29T11:34:05.000+01:00
On AIX, the locale encoding may be "iso8859-1", which was not a known syntax of
the legacy ISO 8859-1 encoding.

Using a C codec instead of a Python codec is faster but also avoids tricky
issues during Python startup or complex code.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
@@ -3021,7 +3021,8 @@ PyUnicode_Decode(const char *s,
             return PyUnicode_DecodeUTF8Stateful(s, size, errors, NULL);
         else if ((strcmp(lower, "latin-1") == 0) ||
                  (strcmp(lower, "latin1") == 0) ||
-                 (strcmp(lower, "iso-8859-1") == 0))
+                 (strcmp(lower, "iso-8859-1") == 0) ||
+                 (strcmp(lower, "iso8859-1") == 0))
             return PyUnicode_DecodeLatin1(s, size, errors);
 #ifdef HAVE_MBCS
         else if (strcmp(lower, "mbcs") == 0)
@@ -3392,7 +3393,8 @@ PyUnicode_AsEncodedString(PyObject *unicode,
         }
         else if ((strcmp(lower, "latin-1") == 0) ||
                  (strcmp(lower, "latin1") == 0) ||
-                 (strcmp(lower, "iso-8859-1") == 0))
+                 (strcmp(lower, "iso-8859-1") == 0) ||
+                 (strcmp(lower, "iso8859-1") == 0))
             return _PyUnicode_AsLatin1String(unicode, errors);
 #ifdef HAVE_MBCS
         else if (strcmp(lower, "mbcs") == 0)
