Commit 53072a43 authored by Tim-Philipp Müller's avatar Tim-Philipp Müller 🐠

ssaparse: ignore invalid UTF-8 in init section

The codec data blob we get from matroskademux with the SSA/ASS
init section is supposed to be valid UTF-8. If it's not, just
continue with the bits that are valid UTF-8 instead of erroring
out. We don't actually parse the init section yet anyway..
parent 6549db36
......@@ -150,10 +150,11 @@ gst_ssa_parse_setcaps (GstPad * sinkpad, GstCaps * caps)
const GValue *val;
GstStructure *s;
const guchar bom_utf8[] = { 0xEF, 0xBB, 0xBF };
const gchar *end;
GstBuffer *priv;
GstMapInfo map;
gchar *ptr;
gsize left;
gsize left, bad_offset;
gboolean ret;
s = gst_caps_get_structure (caps, 0);
......@@ -172,7 +173,10 @@ gst_ssa_parse_setcaps (GstPad * sinkpad, GstCaps * caps)
gst_buffer_ref (priv);
gst_buffer_map (priv, &map, GST_MAP_READ);
if (!gst_buffer_map (priv, &map, GST_MAP_READ))
return FALSE;
GST_MEMDUMP_OBJECT (parse, "init section",, map.size);
ptr = (gchar *);
left = map.size;
......@@ -186,8 +190,13 @@ gst_ssa_parse_setcaps (GstPad * sinkpad, GstCaps * caps)
if (!strstr (ptr, "[Script Info]"))
goto invalid_init;
if (!g_utf8_validate (ptr, left, NULL))
goto invalid_utf8;
if (!g_utf8_validate (ptr, left, &end)) {
bad_offset = (gsize) (end - ptr);
GST_WARNING_OBJECT (parse, "Init section is not valid UTF-8. Problem at "
"byte offset %" G_GSIZE_FORMAT, bad_offset);
/* continue with valid UTF-8 data */
left = bad_offset;
/* FIXME: parse initial section */
parse->ini = g_strndup (ptr, left);
......@@ -212,13 +221,6 @@ invalid_init:
gst_buffer_unref (priv);
return FALSE;
GST_WARNING_OBJECT (parse, "Init section is not valid UTF-8");
gst_buffer_unmap (priv, &map);
gst_buffer_unref (priv);
return FALSE;
static gboolean
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment