audiohook.c: Substitute silence for unavailable audio frames

There are 4 scenarios to consider when capturing audio from a channel
with an audiohook:

 1. There is no rx and no tx audio, so return nothing.
 2. There is rx but no tx audio, so return rx.
 3. There is tx but no rx audio, so return tx.
 4. There is rx and tx audio, so mix them and return.

The file passed as the primary argument to MixMonitor will be written to
in scenarios 2, 3, and 4. However, if you pass the r() and t() options
to MixMonitor, a frame will only be written to the r() file if there was
rx audio and a frame will only be written to the t() file if there was
tx audio.

If you subsequently take the r() and t() files and try to mix them, the
sides of the conversation will 'drift' and be non-representative of the
user experience.

This patch adds a new 'S' option to MixMonitor that injects a frame of
silence on either the r() side or the t() side of the channel so that
when later mixed, there is no such drift.

Change-Id: Ibf5ed73a811087727bd561a89a59f4447b4ee20e

apps/app_mixmonitor.c

@@ -115,6 +115,11 @@
 						Like with the basic filename argument, if an absolute path isn't given, it will create
 						the file in the configured monitoring directory.</para>
 					</option>
+					<option name="S">
+						<para>When combined with the <replaceable>r</replaceable> or <replaceable>t</replaceable>
+						option, inserts silence when necessary to maintain synchronization between the receive
+						and transmit audio streams.</para>
+					</option>
 					<option name="i">
 						<argument name="chanvar" required="true" />
 						<para>Stores the MixMonitor's ID on this channel variable.</para>
@@ -347,7 +352,8 @@ enum mixmonitor_flags {
 	MUXFLAG_VMRECIPIENTS = (1 << 10),
 	MUXFLAG_BEEP = (1 << 11),
 	MUXFLAG_BEEP_START = (1 << 12),
-	MUXFLAG_BEEP_STOP = (1 << 13)
+	MUXFLAG_BEEP_STOP = (1 << 13),
+	MUXFLAG_RWSYNC = (1 << 14),
 };
 
 enum mixmonitor_args {
@@ -359,6 +365,7 @@ enum mixmonitor_args {
 	OPT_ARG_UID,
 	OPT_ARG_VMRECIPIENTS,
 	OPT_ARG_BEEP_INTERVAL,
+	OPT_ARG_RWSYNC,
 	OPT_ARG_ARRAY_SIZE,	/* Always last element of the enum */
 };
 
@@ -375,6 +382,7 @@ AST_APP_OPTIONS(mixmonitor_opts, {
 	AST_APP_OPTION_ARG('t', MUXFLAG_WRITE, OPT_ARG_WRITENAME),
 	AST_APP_OPTION_ARG('i', MUXFLAG_UID, OPT_ARG_UID),
 	AST_APP_OPTION_ARG('m', MUXFLAG_VMRECIPIENTS, OPT_ARG_VMRECIPIENTS),
+	AST_APP_OPTION_ARG('S', MUXFLAG_RWSYNC, OPT_ARG_RWSYNC),
 });
 
 struct mixmonitor_ds {
@@ -962,6 +970,9 @@ static int launch_monitor_thread(struct ast_channel *chan, const char *filename,
 	}
 
 	ast_set_flag(&mixmonitor->audiohook, AST_AUDIOHOOK_TRIGGER_SYNC);
+	if ((ast_test_flag(mixmonitor, MUXFLAG_RWSYNC))) {
+		ast_set_flag(&mixmonitor->audiohook, AST_AUDIOHOOK_SUBSTITUTE_SILENCE);
+	}
 
 	if (readvol)
 		mixmonitor->audiohook.options.read_volume = readvol;

doc/CHANGES-staging/mixmonitor-s-option.txt

@@ -0,0 +1,7 @@
+Subject: app_mixmonitor
+
+An option 'S' has been added to MixMonitor. If used in combination with
+the r() and/or t() options, if a frame is available to write to one of
+those files but not the other, a frame of silence if written to the file
+that does not have an audio frame. This should prevent the two files
+from "drifting" when mixed after the fact.

include/asterisk/audiohook.h

@@ -64,6 +64,8 @@ enum ast_audiohook_flags {
 	AST_AUDIOHOOK_MUTE_READ     = (1 << 5), /*!< audiohook should be mute frames read */
 	AST_AUDIOHOOK_MUTE_WRITE    = (1 << 6), /*!< audiohook should be mute frames written */
 	AST_AUDIOHOOK_COMPATIBLE    = (1 << 7), /*!< is the audiohook native slin compatible */
+
+	AST_AUDIOHOOK_SUBSTITUTE_SILENCE = (1 << 8), /*!< Substitute silence for missing audio */
 };
 
 enum ast_audiohook_init_flags {

main/audiohook.c

@@ -338,6 +338,17 @@ static struct ast_frame *audiohook_read_frame_both(struct ast_audiohook *audioho
 
 	frame.subclass.format = ast_format_cache_get_slin_by_rate(audiohook->hook_internal_samp_rate);
 
+	/* Should we substitute silence if one side lacks audio? */
+	if ((ast_test_flag(audiohook, AST_AUDIOHOOK_SUBSTITUTE_SILENCE))) {
+		if (read_reference && !read_buf && write_buf) {
+			read_buf = buf1;
+			memset(buf1, 0, sizeof(buf1));
+		} else if (write_reference && read_buf && !write_buf) {
+			write_buf = buf2;
+			memset(buf2, 0, sizeof(buf2));
+		}
+	}
+
 	/* Basically we figure out which buffer to use... and if mixing can be done here */
 	if (read_buf && read_reference) {
 		frame.data.ptr = read_buf;