@siteed/expo-audio-stream 1.1.5 → 1.1.6

package/android/build/kotlin/compileDebugKotlin/cacheable/caches-jvm/lookups/counters.tab

@@ -0,0 +1,2 @@
+26
+0

package/android/build/kotlin/compileDebugKotlin/cacheable/caches-jvm/lookups/lookups.tab.values.s

@@ -0,0 +1 @@
+�
�
��
�d�
�=Ŭ
���
���
��
�

package/android/build/outputs/logs/manifest-merger-debug-report.txt

@@ -0,0 +1,24 @@
+-- Merging decision tree log ---
+manifest
+ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:1:1-4:12
+INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:1:1-4:12
+	package
+		INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml
+	xmlns:android
+		ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:1:11-69
+uses-permission#android.permission.RECORD_AUDIO
+ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:2:5-70
+	android:name
+		ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:2:22-68
+uses-permission#android.permission.INTERNET
+ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:3:5-66
+	android:name
+		ADDED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml:3:22-64
+uses-sdk
+INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml reason: use-sdk injection requested
+INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml
+INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml
+	android:targetSdkVersion
+		INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml
+	android:minSdkVersion
+		INJECTED from /Volumes/FD/Projects/expo-audio-stream/packages/expo-audio-stream/android/src/main/AndroidManifest.xml

package/app.plugin.js

@@ -0,0 +1 @@
+module.exports = require('./plugin/build')

package/expo-module.config.json

@@ -0,0 +1,9 @@
+{
+    "platforms": ["ios", "tvos", "android", "web"],
+    "ios": {
+        "modules": ["ExpoAudioStreamModule"]
+    },
+    "android": {
+        "modules": ["net.siteed.audiostream.ExpoAudioStreamModule"]
+    }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@siteed/expo-audio-stream",
-  "version": "1.1.5",
+  "version": "1.1.6",
   "description": "stream audio crossplatform",
   "license": "MIT",
   "main": "build/index.js",
@@ -21,26 +21,6 @@
     "expo-audio-stream",
     "ExpoAudioStream"
   ],
-  "files": [
-    "android",
-    "ios",
-    "cpp",
-    "build",
-    "generated",
-    "README.md",
-    "package.json",
-    "*.podspec",
-    "!ios/build",
-    "!android/build",
-    "!android/gradle",
-    "!android/gradlew",
-    "!android/gradlew.bat",
-    "!android/local.properties",
-    "!**/__tests__",
-    "!**/__fixtures__",
-    "!**/__mocks__",
-    "!**/.*"
-  ],
   "scripts": {
     "build": "expo-module build",
     "clean": "expo-module clean",

package/plugin/build/index.d.ts

@@ -0,0 +1,5 @@
+import { ConfigPlugin } from '@expo/config-plugins';
+declare const withRecordingPermission: ConfigPlugin<{
+    microphonePermission: string;
+}>;
+export default withRecordingPermission;

package/plugin/build/index.js

@@ -0,0 +1,28 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const config_plugins_1 = require("@expo/config-plugins");
+const MICROPHONE_USAGE = 'Allow $(PRODUCT_NAME) to access your microphone';
+const withRecordingPermission = (config, existingPerms) => {
+    if (!existingPerms) {
+        console.warn('No previous permissions provided');
+    }
+    config = (0, config_plugins_1.withInfoPlist)(config, (config) => {
+        config.modResults['NSMicrophoneUsageDescription'] = MICROPHONE_USAGE;
+        // Add audio to UIBackgroundModes to allow background audio recording
+        const existingBackgroundModes = config.modResults.UIBackgroundModes || [];
+        if (!existingBackgroundModes.includes('audio')) {
+            existingBackgroundModes.push('audio');
+        }
+        config.modResults.UIBackgroundModes = existingBackgroundModes;
+        return config;
+    });
+    config = (0, config_plugins_1.withAndroidManifest)(config, (config) => {
+        const mainApplication = config_plugins_1.AndroidConfig.Manifest.getMainApplicationOrThrow(config.modResults);
+        config_plugins_1.AndroidConfig.Manifest.addMetaDataItemToMainApplication(mainApplication, 'android.permission.RECORD_AUDIO', MICROPHONE_USAGE);
+        // Add FOREGROUND_SERVICE permission for handling background recording
+        config_plugins_1.AndroidConfig.Manifest.addMetaDataItemToMainApplication(mainApplication, 'android.permission.FOREGROUND_SERVICE', 'This apps needs access to the foreground service to record audio in the background');
+        return config;
+    });
+    return config;
+};
+exports.default = withRecordingPermission;

package/plugin/src/index.ts

@@ -0,0 +1,53 @@
+import {
+    AndroidConfig,
+    ConfigPlugin,
+    withAndroidManifest,
+    withInfoPlist,
+} from '@expo/config-plugins'
+
+const MICROPHONE_USAGE = 'Allow $(PRODUCT_NAME) to access your microphone'
+
+const withRecordingPermission: ConfigPlugin<{
+    microphonePermission: string
+}> = (config, existingPerms) => {
+    if (!existingPerms) {
+        console.warn('No previous permissions provided')
+    }
+    config = withInfoPlist(config, (config) => {
+        config.modResults['NSMicrophoneUsageDescription'] = MICROPHONE_USAGE
+
+        // Add audio to UIBackgroundModes to allow background audio recording
+        const existingBackgroundModes =
+            config.modResults.UIBackgroundModes || []
+        if (!existingBackgroundModes.includes('audio')) {
+            existingBackgroundModes.push('audio')
+        }
+        config.modResults.UIBackgroundModes = existingBackgroundModes
+
+        return config
+    })
+
+    config = withAndroidManifest(config, (config) => {
+        const mainApplication =
+            AndroidConfig.Manifest.getMainApplicationOrThrow(config.modResults)
+
+        AndroidConfig.Manifest.addMetaDataItemToMainApplication(
+            mainApplication,
+            'android.permission.RECORD_AUDIO',
+            MICROPHONE_USAGE
+        )
+
+        // Add FOREGROUND_SERVICE permission for handling background recording
+        AndroidConfig.Manifest.addMetaDataItemToMainApplication(
+            mainApplication,
+            'android.permission.FOREGROUND_SERVICE',
+            'This apps needs access to the foreground service to record audio in the background'
+        )
+
+        return config
+    })
+
+    return config
+}
+
+export default withRecordingPermission

package/plugin/tsconfig.json

@@ -0,0 +1,9 @@
+{
+    "extends": "expo-module-scripts/tsconfig.plugin",
+    "compilerOptions": {
+        "outDir": "build",
+        "rootDir": "src"
+    },
+    "include": ["./src"],
+    "exclude": ["**/__mocks__/*", "**/__tests__/*"]
+}

package/publish.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -e
+# Bump version
+yarn version patch
+version=$(node -p "require('./package.json').version")
+git add .
+git commit -m "feat: bump version to $version"
+yarn clean && yarn prepare && yarn npm publish

package/src/AudioAnalysis/AudioAnalysis.types.ts

@@ -0,0 +1,84 @@
+// packages/expo-audio-stream/src/AudioAnalysis/AudioAnalysis.types.ts
+
+/**
+ * Represents various audio features extracted from an audio signal.
+ */
+export interface AudioFeatures {
+    energy: number // The infinite integral of the squared signal, representing the overall energy of the audio.
+    mfcc: number[] // Mel-frequency cepstral coefficients, describing the short-term power spectrum of a sound.
+    rms: number // Root mean square value, indicating the amplitude of the audio signal.
+    minAmplitude: number // Minimum amplitude value in the audio signal.
+    maxAmplitude: number // Maximum amplitude value in the audio signal.
+    zcr: number // Zero-crossing rate, indicating the rate at which the signal changes sign.
+    spectralCentroid: number // The center of mass of the spectrum, indicating the brightness of the sound.
+    spectralFlatness: number // Measure of the flatness of the spectrum, indicating how noise-like the signal is.
+    spectralRolloff: number // The frequency below which a specified percentage (usually 85%) of the total spectral energy lies.
+    spectralBandwidth: number // The width of the spectrum, indicating the range of frequencies present.
+    chromagram: number[] // Chromagram, representing the 12 different pitch classes of the audio.
+    tempo: number // Estimated tempo of the audio signal, measured in beats per minute (BPM).
+    hnr: number // Harmonics-to-noise ratio, indicating the proportion of harmonics to noise in the audio signal.
+}
+
+/**
+ * Options to specify which audio features to extract.
+ */
+export interface AudioFeaturesOptions {
+    energy?: boolean
+    mfcc?: boolean
+    rms?: boolean
+    zcr?: boolean
+    spectralCentroid?: boolean
+    spectralFlatness?: boolean
+    spectralRolloff?: boolean
+    spectralBandwidth?: boolean
+    chromagram?: boolean
+    tempo?: boolean
+    hnr?: boolean
+}
+
+/**
+ * Represents a single data point in the audio analysis.
+ */
+export interface DataPoint {
+    id: number
+    amplitude: number
+    activeSpeech?: boolean
+    dB?: number
+    silent?: boolean
+    features?: AudioFeatures
+    startTime?: number
+    endTime?: number
+    // start / end position in bytes
+    startPosition?: number
+    endPosition?: number
+    // number of audio samples for this point (samples size depends on bit depth)
+    samples?: number
+    // TODO: speaker detection
+    speaker?: number
+}
+
+export type AmplitudeAlgorithm = 'peak' | 'rms'
+
+/**
+ * Represents the complete data from the audio analysis.
+ */
+export interface AudioAnalysis {
+    pointsPerSecond: number // How many consolidated value per second
+    durationMs: number // Duration of the audio in milliseconds
+    bitDepth: number // Bit depth of the audio
+    samples: number // Size of the audio in bytes
+    numberOfChannels: number // Number of audio channels
+    sampleRate: number // Sample rate of the audio
+    dataPoints: DataPoint[] // Array of data points from the analysis.
+    amplitudeAlgorithm: AmplitudeAlgorithm // Algorithm used to calculate amplitude values.
+    amplitudeRange: {
+        min: number
+        max: number
+    }
+    // TODO: speaker detection
+    speakerChanges?: {
+        timestamp: number // Timestamp of the speaker change in milliseconds.
+        speaker: number // Speaker identifier.
+    }[]
+}
+

package/src/AudioAnalysis/extractAudioAnalysis.ts

@@ -0,0 +1,147 @@
+// packages/expo-audio-stream/src/AudioAnalysis/extractAudioAnalysis.ts
+import {
+    AmplitudeAlgorithm,
+    AudioAnalysis,
+    AudioFeaturesOptions,
+} from './AudioAnalysis.types'
+import ExpoAudioStreamModule from '../ExpoAudioStreamModule'
+import { isWeb } from '../constants'
+import { getLogger } from '../logger'
+import { convertPCMToFloat32 } from '../utils/convertPCMToFloat32'
+import { getWavFileInfo, WavFileInfo } from '../utils/getWavFileInfo'
+import { InlineFeaturesExtractor } from '../workers/InlineFeaturesExtractor.web'
+
+const logger = getLogger('extractAudioAnalysis')
+
+export interface ExtractAudioAnalysisProps {
+    fileUri?: string // should provide either fileUri or arrayBuffer
+    wavMetadata?: WavFileInfo
+    arrayBuffer?: ArrayBuffer
+    bitDepth?: number
+    skipWavHeader?: boolean
+    durationMs?: number
+    sampleRate?: number
+    numberOfChannels?: number
+    algorithm?: AmplitudeAlgorithm
+    position?: number // Optional number of bytes to skip. Default is 0
+    length?: number // Optional number of bytes to read.
+    pointsPerSecond?: number // Optional number of points per second. Use to reduce the number of points and compute the number of datapoints to return.
+    features?: AudioFeaturesOptions
+    featuresExtratorUrl?: string
+}
+
+export const extractAudioAnalysis = async ({
+    fileUri,
+    pointsPerSecond = 20,
+    arrayBuffer,
+    bitDepth,
+    skipWavHeader = true,
+    durationMs,
+    sampleRate,
+    numberOfChannels,
+    algorithm = 'rms',
+    features,
+    featuresExtratorUrl,
+}: ExtractAudioAnalysisProps): Promise<AudioAnalysis> => {
+    if (isWeb) {
+        if (!arrayBuffer && !fileUri) {
+            throw new Error('Either arrayBuffer or fileUri must be provided')
+        }
+
+        if (!arrayBuffer) {
+            logger.log(`fetching fileUri`, fileUri)
+            const response = await fetch(fileUri!)
+
+            if (!response.ok) {
+                throw new Error(
+                    `Failed to fetch fileUri: ${response.statusText}`
+                )
+            }
+
+            arrayBuffer = await response.arrayBuffer()
+            logger.log(`fetched fileUri`, arrayBuffer.byteLength, arrayBuffer)
+        }
+
+        // Create a new copy of the ArrayBuffer to avoid detachment issues
+        const bufferCopy = arrayBuffer.slice(0)
+        logger.log(
+            `extractAudioAnalysis skipWavHeader=${skipWavHeader} bitDepth=${bitDepth} len=${bufferCopy.byteLength}`,
+            bufferCopy.slice(0, 100)
+        )
+
+        let actualBitDepth = bitDepth
+        if (!actualBitDepth) {
+            logger.log(
+                `extractAudioAnalysis bitDepth not provided -- getting wav file info`
+            )
+            const fileInfo = await getWavFileInfo(bufferCopy)
+            actualBitDepth = fileInfo.bitDepth
+        }
+        logger.log(`extractAudioAnalysis actualBitDepth=${actualBitDepth}`)
+
+        const {
+            pcmValues: channelData,
+            min,
+            max,
+        } = await convertPCMToFloat32({
+            buffer: arrayBuffer,
+            bitDepth: actualBitDepth,
+            skipWavHeader,
+        })
+        logger.log(
+            `extractAudioAnalysis skipWaveHeader=${skipWavHeader} convertPCMToFloat32 length=${channelData.length} range: [ ${min} :: ${max} ]`
+        )
+
+        return new Promise((resolve, reject) => {
+            let worker: Worker
+            if (featuresExtratorUrl) {
+                worker = new Worker(
+                    new URL(featuresExtratorUrl, window.location.href)
+                )
+            } else {
+                const blob = new Blob([InlineFeaturesExtractor], {
+                    type: 'application/javascript',
+                })
+                const url = URL.createObjectURL(blob)
+                worker = new Worker(url)
+            }
+
+            worker.onmessage = (event) => {
+                resolve(event.data.result)
+            }
+
+            worker.onerror = (error) => {
+                reject(error)
+            }
+
+            worker.postMessage({
+                command: 'process',
+                channelData,
+                sampleRate,
+                pointsPerSecond,
+                algorithm,
+                bitDepth,
+                fullAudioDurationMs: durationMs,
+                numberOfChannels,
+            })
+        })
+    } else {
+        if (!fileUri) {
+            throw new Error('fileUri is required')
+        }
+        logger.log(`extractAudioAnalysis`, {
+            fileUri,
+            pointsPerSecond,
+            algorithm,
+        })
+        const res = await ExpoAudioStreamModule.extractAudioAnalysis({
+            fileUri,
+            pointsPerSecond,
+            skipWavHeader,
+            algorithm,
+            features,
+        })
+        logger.log(`extractAudioAnalysis`, res)
+        return res
+    }
+}