gst-libs/gst/tag/tags.c: Don't pass trailing zeroes in fixed-size string arrays in...

Original commit message from CVS:
* gst-libs/gst/tag/tags.c: (gst_tag_freeform_string_to_utf8):
Don't pass trailing zeroes in fixed-size string arrays in ID3v1 tags
to utf8-validate; fixes recognition of ID3v1 tags in UTF-8 encoding
(#451707); also, output some debugging info when dealing with
freeform strings.
* tests/check/libs/tag.c: (GST_START_TEST), (tag_suite):
Add unit test for the above.

diff --git a/ChangeLog b/ChangeLog
index 7132d8b..6160f9d 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,16 @@
 2007-06-27  Tim-Philipp Müller  <tim at centricular dot net>
 
+       * gst-libs/gst/tag/tags.c: (gst_tag_freeform_string_to_utf8):
+         Don't pass trailing zeroes in fixed-size string arrays in ID3v1 tags
+         to utf8-validate; fixes recognition of ID3v1 tags in UTF-8 encoding
+         (#451707); also, output some debugging info when dealing with
+         freeform strings.
+
+       * tests/check/libs/tag.c: (GST_START_TEST), (tag_suite):
+         Add unit test for the above.
+
+2007-06-27  Tim-Philipp Müller  <tim at centricular dot net>
+
        * gst-libs/gst/pbutils/descriptions.c: (caps_are_rtp_caps):
          Add description for Windows Media RTP caps.
 

diff --git a/gst-libs/gst/tag/tags.c b/gst-libs/gst/tag/tags.c
index 706ab96..19ebb58 100644 (file)
--- a/gst-libs/gst/tag/tags.c
+++ b/gst-libs/gst/tag/tags.c
@@ -255,10 +255,18 @@ gst_tag_freeform_string_to_utf8 (const gchar * data, gint size,
   if (size < 0)
     size = strlen (data);
 
+  /* chop off trailing string terminators to make sure utf8_validate doesn't
+   * get to see them (since that would make the utf8 check fail) */
+  while (size > 0 && data[size - 1] == '\0')
+    --size;
+
   /* Should we try the charsets specified
    * via environment variables FIRST ? */
-  if (g_utf8_validate (data, size, NULL))
-    return g_strndup (data, size);
+  if (g_utf8_validate (data, size, NULL)) {
+    utf8 = g_strndup (data, size);
+    GST_LOG ("String '%s' is valid UTF-8 already", utf8);
+    goto beach;
+  }
 
   while (env_vars && *env_vars != NULL) {
     const gchar *env = NULL;
@@ -271,6 +279,7 @@ gst_tag_freeform_string_to_utf8 (const gchar * data, gint size,
       csets = g_strsplit (env, G_SEARCHPATH_SEPARATOR_S, -1);
 
       for (c = csets; c && *c; ++c) {
+        GST_LOG ("Trying to convert freeform string to UTF-8 from '%s'", *c);
         if ((utf8 =
                 g_convert (data, size, "UTF-8", *c, &bytes_read, NULL, NULL))) {
           if (bytes_read == size) {
@@ -289,6 +298,7 @@ gst_tag_freeform_string_to_utf8 (const gchar * data, gint size,
 
   /* Try current locale (if not UTF-8) */
   if (!g_get_charset (&cur_loc)) {
+    GST_LOG ("Trying to convert freeform string using locale ('%s')", cur_loc);
     if ((utf8 = g_locale_to_utf8 (data, size, &bytes_read, NULL, NULL))) {
       if (bytes_read == size) {
         goto beach;
@@ -299,6 +309,7 @@ gst_tag_freeform_string_to_utf8 (const gchar * data, gint size,
   }
 
   /* Try ISO-8859-1 */
+  GST_LOG ("Trying to convert freeform string using ISO-8859-1 fallback");
   utf8 = g_convert (data, size, "UTF-8", "ISO-8859-1", &bytes_read, NULL, NULL);
   if (utf8 != NULL && bytes_read == size) {
     goto beach;
@@ -310,8 +321,10 @@ gst_tag_freeform_string_to_utf8 (const gchar * data, gint size,
 beach:
 
   g_strchomp (utf8);
-  if (utf8 && utf8[0] != '\0')
+  if (utf8 && utf8[0] != '\0') {
+    GST_LOG ("Returning '%s'", utf8);
     return utf8;
+  }
 
   g_free (utf8);
   return NULL;

diff --git a/tests/check/libs/tag.c b/tests/check/libs/tag.c
index 2f3c5c8..1cfd422 100644 (file)
--- a/tests/check/libs/tag.c
+++ b/tests/check/libs/tag.c
@@ -600,6 +600,80 @@ GST_START_TEST (test_id3_tags)
 
 GST_END_TEST;
 
+
+GST_START_TEST (test_id3v1_utf8_tag)
+{
+  const guint8 id3v1[128] = {
+    /* marker */
+    'T', 'A', 'G',
+    /* title (30 bytes) */
+    'D', 0xc3, 0xad, 'v', 'k', 'a', ' ', 's',
+    ' ', 'p', 'e', 'r', 'l', 'a', 'm', 'i',
+    ' ', 'v', 'e', ' ', 'v', 'l', 'a', 's',
+    'e', 'c', 'h', 0, 0, 0,
+    /* artist (30 bytes) */
+    'A', 'l', 'e', 0xc5, 0xa1, ' ', 'B', 'r', 'i', 'c', 'h', 't', 'a',
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* album (30 bytes) */
+    'B', 'e', 's', 't', ' ', 'o', 'f', ' ', '(', 'P', 'r', 'o', 's', 't',
+    0xc4, 0x9b, ' ', 0xc3, 0xba, 0xc5, 0xbe, 'a', 's', 'n', 0xc3, 0xbd, ')',
+    0, 0, 0,
+    /* year (4 bytes) */
+    '2', '0', '0', '0',
+    /* comment (28 bytes) */
+    '-', '-', '-', ' ', 0xc4, 0x8d, 'e', 's', 'k', 0xc3, 0xa9, ' ', 'p',
+    0xc3, 0xad, 's', 'n', 'i', 0xc4, 0x8d, 'k', 'y', ' ', '-', '-', '-',
+    0, 0,
+    /* track number */
+    0, 0,
+    /* genre */
+    0x11
+  };
+  GstTagList *tags;
+  GDate *d;
+  gchar *s;
+
+  /* set this, to make sure UTF-8 strings are really interpreted properly
+   * as UTF-8, regardless of the locale set */
+  g_setenv ("GST_ID3V1_TAG_ENCODING", "WINDOWS-1250", TRUE);
+
+  tags = gst_tag_list_new_from_id3v1 (id3v1);
+  fail_unless (tags != NULL);
+
+  GST_LOG ("Got tags: %" GST_PTR_FORMAT, tags);
+
+  s = NULL;
+  fail_unless (gst_tag_list_get_string (tags, GST_TAG_TITLE, &s));
+  fail_unless (s != NULL);
+  fail_unless_equals_string (s, "Dívka s perlami ve vlasech");
+  g_free (s);
+
+  s = NULL;
+  fail_unless (gst_tag_list_get_string (tags, GST_TAG_ARTIST, &s));
+  fail_unless (s != NULL);
+  fail_unless_equals_string (s, "Aleš Brichta");
+  g_free (s);
+
+  s = NULL;
+  fail_unless (gst_tag_list_get_string (tags, GST_TAG_ALBUM, &s));
+  fail_unless (s != NULL);
+  fail_unless_equals_string (s, "Best of (Prostě úžasný)");
+  g_free (s);
+
+  d = NULL;
+  fail_unless (gst_tag_list_get_date (tags, GST_TAG_DATE, &d));
+  fail_unless (d != NULL);
+  fail_unless_equals_int (g_date_get_year (d), 2000);
+  g_date_free (d);
+  d = NULL;
+
+  gst_tag_list_free (tags);
+
+  g_unsetenv ("GST_ID3V1_TAG_ENCODING");
+}
+
+GST_END_TEST;
+
 static Suite *
 tag_suite (void)
 {
@@ -611,6 +685,7 @@ tag_suite (void)
   tcase_add_test (tc_chain, test_parse_extended_comment);
   tcase_add_test (tc_chain, test_vorbis_tags);
   tcase_add_test (tc_chain, test_id3_tags);
+  tcase_add_test (tc_chain, test_id3v1_utf8_tag);
   return s;
 }