gst/subparse/: Fix parsing of tmplayer subtitle variant where every single line contains text and there isn't an empt...

Original commit message from CVS:
* gst/subparse/gstsubparse.c: (handle_buffer),
(gst_sub_parse_sink_event):
* gst/subparse/tmplayerparse.c: (tmplayer_process_buffer),
(tmplayer_parse_line):
Fix parsing of tmplayer subtitle variant where every single line contains
text and there isn't an empty line after each line to determine the
duration (#530962). Improve EOS handling for tmplayer subtitles a bit by
making sure that we push out the last line of text without a duration if
there's still text left in the buffer at the end.

ChangeLog

@@ -1,3 +1,15 @@
+2008-05-03  Tim-Philipp Müller  <tim.muller at collabora co uk>
+
+	* gst/subparse/gstsubparse.c: (handle_buffer),
+	  (gst_sub_parse_sink_event):
+	* gst/subparse/tmplayerparse.c: (tmplayer_process_buffer),
+	  (tmplayer_parse_line):
+	  Fix parsing of tmplayer subtitle variant where every single line contains
+	  text and there isn't an empty line after each line to determine the
+	  duration (#530962). Improve EOS handling for tmplayer subtitles a bit by
+	  making sure that we push out the last line of text without a duration if
+	  there's still text left in the buffer at the end.
+
 2008-05-03  Tim-Philipp Müller  <tim.muller at collabora co uk>
 
 	* gst/subparse/gstsubparse.c: (feed_textbuf):

gst/subparse/gstsubparse.c

@@ -1093,6 +1093,10 @@ handle_buffer (GstSubParse * self, GstBuffer * buf)
         ret = gst_pad_push (self->srcpad, buf);
       }
 
+      /* move this forward (the tmplayer parser needs this) */
+      if (self->state.duration != GST_CLOCK_TIME_NONE)
+        self->state.start_time += self->state.duration;
+
       g_free (subtitle);
       subtitle = NULL;
 
@@ -1143,13 +1147,15 @@ gst_sub_parse_sink_event (GstPad * pad, GstEvent * event)
       /* Make sure the last subrip chunk is pushed out even
        * if the file does not have an empty line at the end */
       if (self->parser_type == GST_SUB_PARSE_FORMAT_SUBRIP ||
+          self->parser_type == GST_SUB_PARSE_FORMAT_TMPLAYER ||
           self->parser_type == GST_SUB_PARSE_FORMAT_MPL2) {
-        GstBuffer *buf = gst_buffer_new_and_alloc (1 + 1);
+        GstBuffer *buf = gst_buffer_new_and_alloc (2 + 1);
 
         GST_DEBUG ("EOS. Pushing remaining text (if any)");
         GST_BUFFER_DATA (buf)[0] = '\n';
-        GST_BUFFER_DATA (buf)[1] = '\0';        /* play it safe */
+        GST_BUFFER_DATA (buf)[1] = '\n';
-        GST_BUFFER_SIZE (buf) = 1;
+        GST_BUFFER_DATA (buf)[2] = '\0';        /* play it safe */
+        GST_BUFFER_SIZE (buf) = 2;
         GST_BUFFER_OFFSET (buf) = self->offset;
         gst_sub_parse_chain (pad, buf);
       }

gst/subparse/tmplayerparse.c

@@ -1,5 +1,5 @@
 /* GStreamer tmplayer format subtitle parser
- * Copyright (C) 2006 Tim-Philipp Müller <tim centricular net>
+ * Copyright (C) 2006-2008 Tim-Philipp Müller <tim centricular net>
  *
  * This library is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Library General Public
@@ -55,8 +55,29 @@
  * 00:00:53,1=
  * 00:00:54,1=a lush and fertile planet.
  * 00:00:56,1=
+ *
+ * --------------------------------------------------------------------------
+ *
+ * And another variety (which is 'time-base 0:00:00:' but without empty lines):
+ *
+ * 00:00:01:This is the Earth at a time|when the dinosaurs roamed...
+ * 00:00:03:a lush and fertile planet.
+ * 00:00:06:More text here
+ * 00:00:12:Yet another line
+ *
  */
 
+static gchar *
+tmplayer_process_buffer (ParserState * state)
+{
+  gchar *ret;
+
+  ret = g_strndup (state->buf->str, state->buf->len);
+  g_strdelimit (ret, "|", '\n');
+  g_string_truncate (state->buf, 0);
+  return ret;
+}
+
 static gchar *
 tmplayer_parse_line (ParserState * state, const gchar * line, guint line_num)
 {
@@ -78,19 +99,34 @@ tmplayer_parse_line (ParserState * state, const gchar * line, guint line_num)
     GST_LOG ("single line format %u %u %u %u %c", h, m, s, l, divc);
     ts = GST_SECOND * ((((h * 60) + m) * 60) + s);
     text_start = strchr (line + 6, divc);
+  } else if (line[0] == '\0' && state->buf->len > 0 &&
+      GST_CLOCK_TIME_IS_VALID (state->start_time)) {
+    /* if we get an empty line (could be the end of the file, but doesn't have
+     * to be), just push whatever is still in the buffer without a duration */
+    GST_LOG ("empty line, and there's still text in the buffer");
+    ret = tmplayer_process_buffer (state);
+    state->duration = GST_CLOCK_TIME_NONE;
+    return ret;
   } else {
     GST_WARNING ("failed to parse line: '%s'", line);
     return NULL;
   }
 
+  /* if this is a line without text, or the first line in a multiline file,
+   * process and return the data in the buffer, which is the previous line(s) */
   if (text_start == NULL || text_start[1] == '\0' ||
       (l == 1 && state->buf->len > 0)) {
+
     if (GST_CLOCK_TIME_IS_VALID (state->start_time) &&
         state->start_time < ts && line_num > 0) {
-      ret = g_strndup (state->buf->str, state->buf->len);
+      ret = tmplayer_process_buffer (state);
-      g_strdelimit (ret, "|", '\n');
-      g_string_truncate (state->buf, 0);
       state->duration = ts - state->start_time;
+      /* ..and append current line's text (if there is any) for the next round.
+       * We don't have to store ts as pending_start_time, since we deduce the
+       * durations from the start times anyway, so as long as the parser just
+       * forwards state->start_time by duration after it pushes the line we
+       * are about to return it will all be good. */
+      g_string_append (state->buf, text_start + 1);
     } else if (line_num > 0) {
       GST_WARNING ("end of subtitle unit but no valid start time?!");
     }
@@ -101,6 +137,7 @@ tmplayer_parse_line (ParserState * state, const gchar * line, guint line_num)
     state->start_time = ts;
   }
 
+  GST_LOG ("returning: '%s'", GST_STR_NULL (ret));
   return ret;
 }