c0cecd0e60
1. Gnumeric has unbalanced XML tags in its doc translations. 2. itstool's XML error handler tries to print this error with context. 3. libxml2's context snipper treats the data as bytes, not UTF-8. 4. python3Packages.libxml2 casts the context to a UTF-8 Python string. 5. itstool dereferences a null pointer. This patch intervenes at #4. In https://bugzilla.gnome.org/show_bug.cgi?id=789714#c4 , upstream suggests that intervening at #3 would be better -- that each of the four copies of xmlParserPrintFileContextInternal() have four additional UTF-8 problems, one of which is that the caret indicator ought to count "unicode characters" not bytes. But to position a caret correctly, a character count is not sufficient -- this would need to use icu's BiDi logic (with fallback to doing something wrong when libxml2 is configured not to use icu) -- which makes a 'correct' fix a much larger project than this simple band-aid.
30 lines
1.1 KiB
Diff
30 lines
1.1 KiB
Diff
Index: libxml2-2.9.5/python/libxml.c
|
|
===================================================================
|
|
--- libxml2-2.9.5.orig/python/libxml.c
|
|
+++ libxml2-2.9.5/python/libxml.c
|
|
@@ -1620,6 +1620,7 @@ libxml_xmlErrorFuncHandler(ATTRIBUTE_UNU
|
|
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);
|
|
@@ -1636,10 +1637,16 @@ libxml_xmlErrorFuncHandler(ATTRIBUTE_UNU
|
|
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);
|
|
Py_XDECREF(list);
|