From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: "Jan Alexander Steffens (heftig)" <heftig@archlinux.org>
Date: Tue, 11 Apr 2023 21:55:36 +0000
Subject: [PATCH] Fix python3 unicode errors

Patch taken from Fedora at
https://src.fedoraproject.org/rpms/libxml2/raw/c1fa5c85e9d3a0b7340aaf34d2e5134cf47f5d66/f/libxml2-2.9.8-python3-unicode-errors.patch

Works around https://bugzilla.gnome.org/show_bug.cgi?id=789714
and https://gitlab.gnome.org/GNOME/libxml2/-/issues/64
---
 python/libxml.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/python/libxml.c b/python/libxml.c
index e071e824ca39..9d476f4fcd92 100644
--- a/python/libxml.c
+++ b/python/libxml.c
@@ -1621,28 +1621,37 @@ libxml_xmlErrorFuncHandler(ATTRIBUTE_UNUSED void *ctx, const char *msg,
     PyObject *message;
     PyObject *result;
     char str[1000];
+    unsigned char *ptr = (unsigned char *)str;
 
 #ifdef DEBUG_ERROR
     printf("libxml_xmlErrorFuncHandler(%p, %s, ...) called\n", ctx, msg);
 #endif
 
 
     if (libxml_xmlPythonErrorFuncHandler == NULL) {
         va_start(ap, msg);
         vfprintf(stderr, msg, ap);
         va_end(ap);
     } else {
         va_start(ap, msg);
         if (vsnprintf(str, 999, msg, ap) >= 998)
 	    str[999] = 0;
         va_end(ap);
 
+#if PY_MAJOR_VERSION >= 3
+        /* Ensure the error string doesn't start at UTF8 continuation. */
+        while (*ptr && (*ptr & 0xc0) == 0x80)
+            ptr++;
+#endif
+
         list = PyTuple_New(2);
         PyTuple_SetItem(list, 0, libxml_xmlPythonErrorFuncCtxt);
         Py_XINCREF(libxml_xmlPythonErrorFuncCtxt);
-        message = libxml_charPtrConstWrap(str);
+        message = libxml_charPtrConstWrap(ptr);
         PyTuple_SetItem(list, 1, message);
         result = PyEval_CallObject(libxml_xmlPythonErrorFuncHandler, list);
+        /* Forget any errors caused in the error handler. */
+        PyErr_Clear();
         Py_XDECREF(list);
         Py_XDECREF(result);
     }