@siteed/expo-audio-stream 1.0.0 → 1.0.2

package/README.md

@@ -1,6 +1,6 @@
 # @siteed/expo-audio-stream
 
-`@siteed/expo-audio-stream` is a comprehensive library designed to facilitate real-time audio processing and streaming across iOS, Android, and web platforms. This library leverages Expo's robust ecosystem to simplify the implementation of audio recording and streaming functionalities within React Native applications. Key features include audio streaming with configurable buffer intervals and automatic handling of microphone permissions in managed Expo projects.
+`@siteed/expo-audio-stream` is a comprehensive library designed to facilitate real-time audio processing and streaming across iOS, Android, and web platforms.
 
 ## Features
 
@@ -11,7 +11,7 @@
 - Listeners for audio data events with detailed event payloads.
 - Utility functions for recording control and file management.
 
-## Example Application
+## Playground Example Application
 
 The project comes with a fully functional example application that demonstrates how to use the library in a real-world scenario.
 
@@ -23,9 +23,9 @@ To try it:
 git clone https://github.com/deeeed/expo-audio-stream.git
 cd expo-audio-stream
 yarn
-yarn example ios
-yarn example android
-yarn example web
+yarn playground ios
+yarn playground android
+yarn playground web
 ```
 
 ## Installation
@@ -38,13 +38,10 @@ npm install @siteed/expo-audio-stream
 yarn add @siteed/expo-audio-stream
 ```
 
-Make sure that you have Expo set up in your project. For details on setting up Expo, refer to the Expo documentation.
 
 ### Configuring with app.json
 
-To ensure expo-audio-stream works correctly with Expo, you must add it as a plugin in your app.json configuration file. This step is crucial as it allows Expo to load any necessary configurations or permissions required by the library.
-
-Add the plugin to your app.json like so:
+To ensure expo-audio-stream works correctly with Expo, you must add it as a plugin in your app.json configuration file.
 
 ```json
 {
@@ -63,7 +60,7 @@ This library provides two hooks: `useAudioRecorder` for standalone use and `useS
 
 ### Standalone Recording
 
-The `example/` folder contains a fully functional React Native application demonstrating how to integrate and use `useAudioRecorder` from `@siteed/expo-audio-stream`. This includes starting and stopping recordings, handling permissions, and processing live audio data.
+The `playground/` folder contains a fully functional React Native application demonstrating how to integrate and use `useAudioRecorder` from `@siteed/expo-audio-stream`. This includes starting and stopping recordings, handling permissions, and processing live audio data.
 
 
 #### Standalone Usage
@@ -187,11 +184,3 @@ function App() {
 - on web, it usually records in opus  but it depends on the browser configuration.
 
 If you want to process the audio livestream directly, I recommend having another encoding step to align the audio format across platforms.
-
-## TODO
-this package is still in development, and there are a few things that need to be done:
-- Add resume (vs currently use start) support and implement pause on iOS.
-- Multi format support: Extend support to other audio formats beyond WAV, such as MP3 or AAC
-- Integrate an audio processing library for optional audio analysis, such as equalization, noise reduction, or volume normalization.
-- Implement a more robust error handling system to provide detailed error messages and recovery options.
-

package/android/build.gradle

@@ -89,4 +89,9 @@ repositories {
 dependencies {
   implementation project(':expo-modules-core')
   implementation "org.jetbrains.kotlin:kotlin-stdlib-jdk7:${getKotlinVersion()}"
+
+  // Add testing dependencies
+  testImplementation 'junit:junit:4.13.2'
+  testImplementation 'org.jetbrains.kotlin:kotlin-test:1.8.10'
+  testImplementation 'org.jetbrains.kotlin:kotlin-test-junit:1.8.10'
 }

package/android/src/main/java/net/siteed/audiostream/AudioAnalysisData.kt

@@ -0,0 +1,120 @@
+// net/siteed/audiostream/AudioAnalysisData.kt
+package net.siteed.audiostream
+
+import android.os.Bundle
+import androidx.core.os.bundleOf
+
+data class DataPoint(
+    val id: Long,
+    val amplitude: Float,
+    val activeSpeech: Boolean? = null,
+    val dB: Float? = null,
+    val silent: Boolean? = null,
+    val features: Features? = null,
+    val startTime: Float? = null,
+    val endTime: Float? = null,
+    val startPosition: Int? = null,
+    val endPosition: Int? = null,
+    val samples: Int = 0,
+    val speaker: Int? = null
+) {
+    fun toDictionary(): Map<String, Any?> {
+        return mapOf(
+            "id" to id,
+            "amplitude" to amplitude,
+            "activeSpeech" to activeSpeech,
+            "dB" to dB,
+            "silent" to silent,
+            "features" to features?.toDictionary(),
+            "startTime" to startTime,
+            "endTime" to endTime,
+            "startPosition" to startPosition,
+            "endPosition" to endPosition,
+            "samples" to samples,
+            "speaker" to speaker
+        )
+    }
+
+    fun toBundle(): Bundle {
+        return bundleOf(
+            "id" to id,
+            "amplitude" to amplitude,
+            "activeSpeech" to activeSpeech,
+            "dB" to dB,
+            "silent" to silent,
+            "features" to features?.toBundle(),
+            "startTime" to startTime,
+            "endTime" to endTime,
+            "startPosition" to startPosition,
+            "endPosition" to endPosition,
+            "samples" to samples,
+            "speaker" to speaker
+        )
+    }
+}
+
+data class AudioAnalysisData(
+    val pointsPerSecond: Double,
+    val durationMs: Int,
+    val bitDepth: Int,
+    val numberOfChannels: Int,
+    val sampleRate: Int,
+    val samples: Int,
+    val dataPoints: List<DataPoint>,
+    val amplitudeRange: AmplitudeRange,
+    val speakerChanges: List<SpeakerChange>,
+    val extractionTimeMs: Float
+) {
+    data class AmplitudeRange(val min: Float, val max: Float) {
+        fun toDictionary(): Map<String, Float> {
+            return mapOf("min" to min, "max" to max)
+        }
+
+        fun toBundle(): Bundle {
+            return bundleOf("min" to min, "max" to max)
+        }
+    }
+
+    data class SpeakerChange(val timestamp: Float, val speaker: Int) {
+        fun toDictionary(): Map<String, Any> {
+            return mapOf("timestamp" to timestamp, "speaker" to speaker)
+        }
+
+        fun toBundle(): Bundle {
+            return bundleOf("timestamp" to timestamp, "speaker" to speaker)
+        }
+    }
+
+    fun toDictionary(): Map<String, Any> {
+        return mapOf(
+            "pointsPerSecond" to pointsPerSecond,
+            "durationMs" to durationMs,
+            "bitDepth" to bitDepth,
+            "numberOfChannels" to numberOfChannels,
+            "sampleRate" to sampleRate,
+            "samples" to samples,
+            "dataPoints" to dataPoints.map { it.toDictionary() },
+            "amplitudeRange" to amplitudeRange.toDictionary(),
+            "speakerChanges" to speakerChanges.map { it.toDictionary() },
+            "extractionTimeMs" to extractionTimeMs
+        )
+    }
+
+    fun toBundle(): Bundle {
+        val dataPointsBundleArray = dataPoints.map { it.toBundle() }.toTypedArray()
+        val speakerChangesBundleArray = speakerChanges.map { it.toBundle() }.toTypedArray()
+
+        return bundleOf(
+            "pointsPerSecond" to pointsPerSecond,
+            "durationMs" to durationMs,
+            "bitDepth" to bitDepth,
+            "numberOfChannels" to numberOfChannels,
+            "sampleRate" to sampleRate,
+            "samples" to samples,
+            "dataPoints" to dataPointsBundleArray,
+            "amplitudeRange" to amplitudeRange.toBundle(),
+            "speakerChanges" to speakerChangesBundleArray,
+            "extractionTimeMs" to extractionTimeMs
+        )
+    }
+}

package/android/src/main/java/net/siteed/audiostream/AudioFileHandler.kt

@@ -14,25 +14,55 @@ class AudioFileHandler(private val filesDir: File) {
 
         // RIFF/WAVE header
         "RIFF".toByteArray().copyInto(header, 0)
-        header[4] = 0 // Size will be updated later
+        // (file size - 8) to be updated later
+        header[4] = 0 // Placeholder
+        header[5] = 0 // Placeholder
+        header[6] = 0 // Placeholder
+        header[7] = 0 // Placeholder
         "WAVE".toByteArray().copyInto(header, 8)
         "fmt ".toByteArray().copyInto(header, 12)
 
         // 16 for PCM
         header[16] = 16
+        header[17] = 0
+        header[18] = 0
+        header[19] = 0
+
+        // PCM format ID
         header[20] = 1 // Audio format 1 for PCM (not compressed)
-        header[22] = channels.toByte()
+        header[21] = 0
+
+        // Number of channels
+        header[22] = (channels and 0xff).toByte()
+        header[23] = (channels shr 8 and 0xff).toByte()
+
+        // Sample rate
         header[24] = (sampleRateInHz and 0xff).toByte()
         header[25] = (sampleRateInHz shr 8 and 0xff).toByte()
         header[26] = (sampleRateInHz shr 16 and 0xff).toByte()
         header[27] = (sampleRateInHz shr 24 and 0xff).toByte()
+
+        // Byte rate
         header[28] = (byteRate and 0xff).toByte()
         header[29] = (byteRate shr 8 and 0xff).toByte()
         header[30] = (byteRate shr 16 and 0xff).toByte()
         header[31] = (byteRate shr 24 and 0xff).toByte()
-        header[32] = blockAlign.toByte()
-        header[34] = bitDepth.toByte()
+
+        // Block align
+        header[32] = (blockAlign and 0xff).toByte()
+        header[33] = (blockAlign shr 8 and 0xff).toByte()
+
+        // Bits per sample
+        header[34] = (bitDepth and 0xff).toByte()
+        header[35] = (bitDepth shr 8 and 0xff).toByte()
+
+        // Data chunk
         "data".toByteArray().copyInto(header, 36)
+        // Data size to be updated later
+        header[40] = 0 // Placeholder
+        header[41] = 0 // Placeholder
+        header[42] = 0 // Placeholder
+        header[43] = 0 // Placeholder
 
         out.write(header, 0, 44)
     }