minor docs

* issue# 107: on gather timeout, if minDigits are collected, resolve with dtmf-num-digits

* gather timeout: use conditional instead of if/else

Co-authored-by: Prashanth Gujjeti <prashanth@minervacq.com>

README.md

@@ -86,7 +86,5 @@ module.exports = {
 ```
 
 #### Running the test suite
-The test suite currently only consists of JSON-parsing unit tests.  A full end-to-end sip test suite should be added.
-```
-npm test
-```
+
+Please [see this]](./docs/contributing.md#run-the-regression-test-suite).

docs/contributing.md

@@ -89,7 +89,9 @@ f80adda48eb5   jambonz/webhook-test-scaffold:latest            "/entrypoint.sh"
 
 #### Run the regression test suite
 
-At this point you should be able to run the tests:
+The test suite has a dependency that the mysql client is installed on your laptop/machine where the test will be run.  This is needed in order to seed the mysql database that is running in the docker network.
+
+Assuming you have installed the mysql client, and done the above steps, you should now be able to run the tests:
 
 ```bash
 ./run-tests.sh

lib/tasks/dial.js

@@ -606,7 +606,7 @@ class TaskDial extends Task {
     if (this.parentDtmfCollector) this._installDtmfDetection(cs, cs.dlg);
     if (this.childDtmfCollector) this._installDtmfDetection(cs, this.dlg);
 
-    if (this.transcribeTask) this.transcribeTask.exec(cs, this.epOther);
+    if (this.transcribeTask) this.transcribeTask.exec(cs, this.epOther, this.ep);
     if (this.listenTask) this.listenTask.exec(cs, this.epOther);
 
     /* if we can release the media back to the SBC, do so now */

lib/tasks/gather.js

@@ -349,7 +349,9 @@ class TaskGather extends Task {
     }
     assert(!this._timeoutTimer);
     this.logger.debug(`Gather:_startTimer: timeout ${this.timeout}`);
-    this._timeoutTimer = setTimeout(() => this._resolve('timeout'), this.timeout);
+    this._timeoutTimer = setTimeout(() => {
+      this._resolve(this.digitBuffer.length >= this.minDigits ? 'dtmf-num-digits' : 'timeout');
+    }, this.timeout);
   }
 
   _clearTimer() {

lib/tasks/transcribe.js

@@ -58,11 +58,12 @@ class TaskTranscribe extends Task {
 
   get name() { return TaskName.Transcribe; }
 
-  async exec(cs, ep, parentTask) {
+  async exec(cs, ep, ep2) {
     super.exec(cs);
     const {updateSpeechCredentialLastUsed} = require('../utils/db-utils')(this.logger, cs.srf);
 
     this.ep = ep;
+    this.ep2 = ep2;
     if ('default' === this.vendor || !this.vendor) this.vendor = cs.speechRecognizerVendor;
     if ('default' === this.language || !this.language) this.language = cs.speechRecognizerLanguage;
     this.sttCredentials = cs.getSpeechCredentials(this.vendor, 'stt');
@@ -78,7 +79,9 @@ class TaskTranscribe extends Task {
         }).catch((err) => this.logger.info({err}, 'Error generating alert for no stt'));
         throw new Error('no provisioned speech credentials for TTS');
       }
-      await this._startTranscribing(cs, ep);
+      await this._startTranscribing(cs, ep, 1);
+      if (this.separateRecognitionPerChannel && ep2) await this._startTranscribing(cs, ep2, 2);
+
       updateSpeechCredentialLastUsed(this.sttCredentials.speech_credential_sid)
         .catch(() => {/*already logged error */});
 
@@ -106,11 +109,15 @@ class TaskTranscribe extends Task {
       // hangup after 1 sec if we don't get a final transcription
       this._timer = setTimeout(() => this.notifyTaskDone(), 1000);
     }
+    if (this.separateRecognitionPerChannel && this.ep2 && this.ep2.connected) {
+      this.ep2.stopTranscription({vendor: this.vendor})
+        .catch((err) => this.logger.info(err, 'Error TaskTranscribe:kill'));
+    }
     else this.notifyTaskDone();
     await this.awaitTaskDone();
   }
 
-  async _startTranscribing(cs, ep) {
+  async _startTranscribing(cs, ep, channel) {
     const opts = {};
 
     if (this.vad.enable) {
@@ -119,22 +126,24 @@ class TaskTranscribe extends Task {
       if (this.vad.mode >= 0 && this.vad.mode <= 3) opts.RECOGNIZER_VAD_MODE = this.vad.mode;
     }
 
-    ep.addCustomEventListener(GoogleTranscriptionEvents.Transcription, this._onTranscription.bind(this, cs, ep));
-    ep.addCustomEventListener(GoogleTranscriptionEvents.NoAudioDetected, this._onNoAudio.bind(this, cs, ep));
+    ep.addCustomEventListener(GoogleTranscriptionEvents.Transcription,
+      this._onTranscription.bind(this, cs, ep, channel));
+    ep.addCustomEventListener(GoogleTranscriptionEvents.NoAudioDetected, this._onNoAudio.bind(this, cs, ep, channel));
     ep.addCustomEventListener(GoogleTranscriptionEvents.MaxDurationExceeded,
-      this._onMaxDurationExceeded.bind(this, cs, ep));
-    ep.addCustomEventListener(AwsTranscriptionEvents.Transcription, this._onTranscription.bind(this, cs, ep));
-    ep.addCustomEventListener(AwsTranscriptionEvents.NoAudioDetected, this._onNoAudio.bind(this, cs, ep));
+      this._onMaxDurationExceeded.bind(this, cs, ep, channel));
+    ep.addCustomEventListener(AwsTranscriptionEvents.Transcription, this._onTranscription.bind(this, cs, ep, channel));
+    ep.addCustomEventListener(AwsTranscriptionEvents.NoAudioDetected, this._onNoAudio.bind(this, cs, ep, channel));
     ep.addCustomEventListener(AwsTranscriptionEvents.MaxDurationExceeded,
-      this._onMaxDurationExceeded.bind(this, cs, ep));
-    ep.addCustomEventListener(AzureTranscriptionEvents.Transcription, this._onTranscription.bind(this, cs, ep));
-    ep.addCustomEventListener(AzureTranscriptionEvents.NoSpeechDetected, this._onNoAudio.bind(this, cs, ep));
+      this._onMaxDurationExceeded.bind(this, cs, ep, channel));
+    ep.addCustomEventListener(AzureTranscriptionEvents.Transcription,
+      this._onTranscription.bind(this, cs, ep, channel));
+    ep.addCustomEventListener(AzureTranscriptionEvents.NoSpeechDetected, this._onNoAudio.bind(this, cs, ep, channel));
 
     if (this.vendor === 'google') {
       if (this.sttCredentials) opts.GOOGLE_APPLICATION_CREDENTIALS = JSON.stringify(this.sttCredentials.credentials);
       [
         ['enhancedModel', 'GOOGLE_SPEECH_USE_ENHANCED'],
-        ['separateRecognitionPerChannel', 'GOOGLE_SPEECH_SEPARATE_RECOGNITION_PER_CHANNEL'],
+        //['separateRecognitionPerChannel', 'GOOGLE_SPEECH_SEPARATE_RECOGNITION_PER_CHANNEL'],
         ['profanityFilter', 'GOOGLE_SPEECH_PROFANITY_FILTER'],
         ['punctuation', 'GOOGLE_SPEECH_ENABLE_AUTOMATIC_PUNCTUATION'],
         ['words', 'GOOGLE_SPEECH_ENABLE_WORD_TIME_OFFSETS'],
@@ -222,12 +231,12 @@ class TaskTranscribe extends Task {
       vendor: this.vendor,
       interim: this.interim ? true : false,
       locale: this.language,
-      channels: this.separateRecognitionPerChannel ? 2 : 1
+      channels: /*this.separateRecognitionPerChannel ? 2 : */ 1
     });
   }
 
-  _onTranscription(cs, ep, evt) {
-    this.logger.debug({evt}, 'TaskTranscribe:_onTranscription');
+  _onTranscription(cs, ep, channel, evt) {
+    this.logger.debug({evt, channel}, 'TaskTranscribe:_onTranscription');
     if ('aws' === this.vendor && Array.isArray(evt) && evt.length > 0) evt = evt[0];
     if ('microsoft' === this.vendor) {
       const nbest = evt.NBest;
@@ -240,12 +249,13 @@ class TaskTranscribe extends Task {
       }) :
         [
           {
-            transcript: evt.Text
+            transcript: evt.DisplayText
           }
         ];
 
       const newEvent = {
         is_final: evt.RecognitionStatus === 'Success',
+        channel,
         language_code,
         alternatives
       };
@@ -257,6 +267,8 @@ class TaskTranscribe extends Task {
       return this._transcribe(ep);
     }
 
+    evt.channel_tag = channel;
+
     if (this.transcriptionHook) {
       const b3 = this.getTracingPropagation();
       const httpHeaders = b3 && {b3};
@@ -274,13 +286,13 @@ class TaskTranscribe extends Task {
     }
   }
 
-  _onNoAudio(cs, ep) {
-    this.logger.debug('TaskTranscribe:_onNoAudio restarting transcription');
+  _onNoAudio(cs, ep, channel) {
+    this.logger.debug(`TaskTranscribe:_onNoAudio restarting transcription on channel ${channel}`);
     this._transcribe(ep);
   }
 
-  _onMaxDurationExceeded(cs, ep) {
-    this.logger.debug('TaskTranscribe:_onMaxDurationExceeded restarting transcription');
+  _onMaxDurationExceeded(cs, ep, channel) {
+    this.logger.debug(`TaskTranscribe:_onMaxDurationExceeded restarting transcription on channel ${channel}`);
     this._transcribe(ep);
   }