From d5296f28959c0cd0a6960ef36a8db840ba93aba2 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Tim-Philipp=20M=C3=BCller?= <tim@centricular.net>
Date: Fri, 28 Apr 2006 11:37:22 +0000
Subject: [PATCH] gst/id3demux/id3v2frames.c: Recognise and skip any byte order
 marker (BOM) in

Original commit message from CVS:
* gst/id3demux/id3v2frames.c: (has_utf16_bom),
(parse_split_strings):
Recognise and skip any byte order marker (BOM) in
UTF-16 strings.
---
 ChangeLog                  |  7 +++++++
 gst/id3demux/id3v2frames.c | 24 ++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/ChangeLog b/ChangeLog
index d04066a..54bc8f0 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2006-04-28  Tim-Philipp Müller  <tim at centricular dot net>
+
+	* gst/id3demux/id3v2frames.c: (has_utf16_bom),
+	(parse_split_strings):
+	  Recognise and skip any byte order marker (BOM) in
+	  UTF-16 strings.
+
 2006-04-27  Tim-Philipp Müller  <tim at centricular dot net>
 
 	* docs/plugins/Makefile.am:
diff --git a/gst/id3demux/id3v2frames.c b/gst/id3demux/id3v2frames.c
index cf56f8b..b97e4d0 100644
--- a/gst/id3demux/id3v2frames.c
+++ b/gst/id3demux/id3v2frames.c
@@ -668,6 +668,24 @@ parse_insert_string_field (const gchar * encoding, gchar * data, gint data_size,
     g_array_append_val (fields, field);
 }
 
+static gboolean
+has_utf16_bom (gchar * data, const gchar ** p_in_encoding)
+{
+  guint16 marker = (GST_READ_UINT8 (data) << 8) | GST_READ_UINT8 (data + 1);
+
+  switch (marker) {
+    case 0xFFFE:
+      *p_in_encoding = "UTF16LE";
+      return TRUE;
+    case 0xFEFF:
+      *p_in_encoding = "UTF16BE";
+      return TRUE;
+    default:
+      break;
+  }
+  return FALSE;
+}
+
 static void
 parse_split_strings (guint8 encoding, gchar * data, gint data_size,
     GArray ** out_fields)
@@ -719,6 +737,9 @@ parse_split_strings (guint8 encoding, gchar * data, gint data_size,
       /* Find '\0\0' terminator */
       for (text_pos = 0; text_pos < data_size - 1; text_pos += 2) {
         if (data[text_pos] == '\0' && data[text_pos + 1] == '\0') {
+          if (has_utf16_bom (data + prev, &in_encode)) {
+            prev += 2;          /* skip BOM */
+          }
           /* found a delimiter */
           parse_insert_string_field (in_encode, data + prev,
               text_pos - prev + 2, fields);
@@ -729,6 +750,9 @@ parse_split_strings (guint8 encoding, gchar * data, gint data_size,
       }
       if (data_size - prev > 1 &&
           (data[prev] != 0x00 || data[prev + 1] != 0x00)) {
+        if (has_utf16_bom (data + prev, &in_encode)) {
+          prev += 2;            /* skip BOM */
+        }
         /* There were 2 or more non-null chars left, convert those too */
         parse_insert_string_field (in_encode, data + prev,
             data_size - prev, fields);
-- 
2.7.4