Java and GCP Speech AIHolo impl and fixes to Python example

java-ai/auth_and_run.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# token itself expires after 1 hour, but it is automatically refreshed as long as the stored credentials remain valid.
+# provides long-lived authentication (~1 week) via Application Default Credentials (ADC).
+gcloud auth application-default login
+mvn clean package
+java -jar .\target\oracleai-0.0.1-SNAPSHOT.jar

java-ai/pom.xml

@@ -16,8 +16,29 @@
 
 	<properties>
 		<oci.sdk.version>3.52.1</oci.sdk.version>
+		<oracle.jdbc.version>21.7.0.0</oracle.jdbc.version>
 	</properties>
 
+
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>com.google.cloud</groupId>
+        <artifactId>libraries-bom</artifactId>
+        <version>26.32.0</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
+
+
+
+
+
+
+
 	<dependencies>
 		<dependency>
 			<groupId>org.springframework.boot</groupId>
@@ -40,7 +61,7 @@
 		<dependency>
 			<groupId>com.oracle.cloud.spring</groupId>
 			<artifactId>spring-cloud-oci-starter</artifactId>
-			<version>1.3.0</version>
+			<version>1.4.0</version>
 		</dependency>
 		<dependency>
 			<groupId>com.oracle.oci.sdk</groupId>
@@ -99,6 +120,112 @@
 			<artifactId>service</artifactId>
 			<version>0.12.0</version>
 		</dependency>
+
+		<dependency>
+			<groupId>org.springframework.boot</groupId>
+			<artifactId>spring-boot-starter-security</artifactId>
+		</dependency>
+
+
+		<!-- <dependency>
+            <groupId>com.oracle.database.spring</groupId>
+            <artifactId>oracle-spring-boot-starter-ucp</artifactId>
+            <version>23.4.0</version>
+        </dependency> -->
+<!-- <dependency>
+    <groupId>com.oracle.database.spring</groupId>
+    <artifactId>oracle-spring-boot-starter-wallet</artifactId>
+    <version>23.4.0</version>
+</dependency> -->
+
+		<dependency>
+			<groupId>com.oracle.database.jdbc</groupId>
+			<artifactId>ojdbc8</artifactId>
+			<version>${oracle.jdbc.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>com.oracle.database.jdbc</groupId>
+			<artifactId>ucp</artifactId>
+			<version>${oracle.jdbc.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>com.oracle.database.security</groupId>
+			<artifactId>oraclepki</artifactId>
+			<version>${oracle.jdbc.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>com.oracle.database.security</groupId>
+			<artifactId>osdt_core</artifactId>
+			<version>${oracle.jdbc.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>com.oracle.database.security</groupId>
+			<artifactId>osdt_cert</artifactId>
+			<version>${oracle.jdbc.version}</version>
+		</dependency>
+
+    <dependency>
+      <groupId>com.google.cloud</groupId>
+      <artifactId>google-cloud-texttospeech</artifactId>
+    </dependency>
+	   <dependency>
+      <groupId>com.google.cloud</groupId>
+      <artifactId>google-cloud-speech</artifactId>
+    </dependency>
+   <dependency>
+      <groupId>net.sourceforge.argparse4j</groupId>
+      <artifactId>argparse4j</artifactId>
+      <version>0.9.0</version>
+    </dependency>
+
+
+   <dependency>
+        <groupId>org.springframework.boot</groupId>
+        <artifactId>spring-boot-starter-websocket</artifactId>
+    </dependency>
+
+
+    <dependency>
+      <groupId>commons-cli</groupId>
+      <artifactId>commons-cli</artifactId>
+      <version>1.6.0</version>
+    </dependency>
+
+    <dependency>
+        <groupId>com.google.auth</groupId>
+        <artifactId>google-auth-library-oauth2-http</artifactId>
+        <version>1.18.0</version>
+    </dependency>
+
+   <dependency>
+        <groupId>jakarta.websocket</groupId>
+        <artifactId>jakarta.websocket-api</artifactId>
+		  <version>2.2.0</version>
+        <!-- <version>2.1.1</version> -->
+    </dependency>
+
+	<dependency>
+    <groupId>org.apache.tomcat.embed</groupId>
+    <artifactId>tomcat-embed-websocket</artifactId>
+</dependency>
+
+    <!-- <dependency>
+        <groupId>org.apache.tomcat</groupId>
+        <artifactId>tomcat-websocket</artifactId>
+        <version>10.1.14</version>
+    </dependency> -->
+	<dependency>
+    <groupId>org.glassfish.tyrus</groupId>
+    <artifactId>tyrus-server</artifactId>
+    <version>2.1.3</version>
+</dependency>
+
+<dependency>
+    <groupId>org.glassfish.tyrus</groupId>
+    <artifactId>tyrus-container-servlet</artifactId>
+    <version>2.1.3</version>
+</dependency>
+
 	</dependencies>
 	<build>
 		<plugins>

java-ai/src/main/java/oracleai/BinaryServerConfigurator.java

@@ -0,0 +1,11 @@
+package oracleai;
+
+import jakarta.websocket.server.ServerEndpointConfig;
+
+public class BinaryServerConfigurator extends ServerEndpointConfig.Configurator {
+    @Override
+    public boolean checkOrigin(String originHeaderValue) {
+        System.out.println("✅ WebSocket checkOrigin originHeaderValue: " + originHeaderValue);
+        return true; // Allow all origins for WebSocket
+    }
+}

java-ai/src/main/java/oracleai/SpeechWebSocketConfigurator.java

@@ -0,0 +1,12 @@
+package oracleai;
+
+import jakarta.websocket.server.HandshakeRequest;
+import jakarta.websocket.HandshakeResponse;
+import jakarta.websocket.server.ServerEndpointConfig;
+
+public class SpeechWebSocketConfigurator extends ServerEndpointConfig.Configurator {
+    @Override
+    public void modifyHandshake(ServerEndpointConfig sec, HandshakeRequest request, HandshakeResponse response) {
+        sec.getUserProperties().put("org.apache.tomcat.websocket.binaryBufferSize", 1024 * 1024); // Enable binary message support
+    }
+}

java-ai/src/main/java/oracleai/SpeechWebSocketServer.java

@@ -0,0 +1,160 @@
+package oracleai;
+
+import com.google.api.gax.rpc.BidiStreamingCallable;
+import com.google.api.gax.rpc.ApiStreamObserver;
+import com.google.cloud.speech.v1.*;
+import com.google.protobuf.ByteString;
+
+import jakarta.websocket.*;
+import jakarta.websocket.server.ServerEndpoint;
+import java.io.*;
+import java.nio.ByteBuffer;
+import java.util.concurrent.Executors;
+import java.util.concurrent.ScheduledExecutorService;
+import javax.sound.sampled.*;
+
+import org.springframework.stereotype.Component;
+
+@ServerEndpoint(value = "/speech", configurator = SpeechWebSocketConfigurator.class)
+@Component
+public class SpeechWebSocketServer {
+    private static final ScheduledExecutorService executorService = Executors.newSingleThreadScheduledExecutor();
+    private static SpeechClient speechClient;
+    private ApiStreamObserver<StreamingRecognizeRequest> requestObserver;
+
+    static {
+        try {
+            speechClient = SpeechClient.create();
+        } catch (IOException e) {
+            throw new RuntimeException("❌ Failed to initialize SpeechClient", e);
+        }
+    }
+
+    @OnOpen
+    public void onOpen(Session session) {
+        System.out.println("✅ WebSocket Connected: " + session.getId());
+        session.setMaxBinaryMessageBufferSize(1024 * 1024); // Allow large audio messages
+
+        ApiStreamObserver<StreamingRecognizeResponse> responseObserver = new ApiStreamObserver<>() {
+            @Override
+            public void onNext(StreamingRecognizeResponse response) {
+                for (StreamingRecognitionResult result : response.getResultsList()) {
+                    if (result.getAlternativesCount() > 0) {
+                        String transcript = result.getAlternatives(0).getTranscript().trim();
+                        if (!transcript.isEmpty()) {
+                            System.out.println("📝 Transcription: " + transcript);
+                            try {
+                                session.getBasicRemote().sendText(transcript);
+                            } catch (IOException e) {
+                                e.printStackTrace();
+                            }
+                        }
+                    }
+                }
+            }
+
+            @Override
+            public void onError(Throwable t) {
+                System.err.println("❌ Google API Error: " + t.getMessage());
+            }
+
+            @Override
+            public void onCompleted() {
+                System.out.println("✅ Streaming completed.");
+            }
+        };
+
+        // Initialize Streaming to Google Speech API
+        BidiStreamingCallable<StreamingRecognizeRequest, StreamingRecognizeResponse> callable =
+                speechClient.streamingRecognizeCallable();
+        requestObserver = callable.bidiStreamingCall(responseObserver);
+
+        requestObserver.onNext(StreamingRecognizeRequest.newBuilder()
+                .setStreamingConfig(StreamingRecognitionConfig.newBuilder()
+                        .setConfig(RecognitionConfig.newBuilder()
+                                .setEncoding(RecognitionConfig.AudioEncoding.LINEAR16)
+                                .setSampleRateHertz(16000)
+                                .setLanguageCode("en-US")
+                                .setAudioChannelCount(1)
+                                .setEnableAutomaticPunctuation(true)
+                                .build())
+                        .setInterimResults(true)
+                        .setSingleUtterance(false)
+                        .build())
+                .build());
+    }
+
+    /**
+     * 🔹 **Handles Incoming Binary Audio Data (From WebSocket)**
+     * This method now **reads a WAV file** instead of processing real-time audio streaming.
+     */
+    @OnMessage
+    public void onMessage(Session session) {
+        String filePath = "C:/Users/opc/Downloads/audio_logs/sample.wav"; // Change to your WAV file path
+        byte[] audioBytes;
+
+        try {
+            audioBytes = readWavFile(filePath);
+            if (audioBytes == null || audioBytes.length == 0) {
+                System.out.println("⚠️ WAV file is empty or could not be read.");
+                return;
+            }
+        } catch (IOException | UnsupportedAudioFileException e) {
+            System.err.println("❌ Error reading WAV file: " + e.getMessage());
+            return;
+        }
+
+        System.out.println("✅ Sending Audio Data from WAV file: " + audioBytes.length + " bytes");
+
+        if (requestObserver != null) {
+            requestObserver.onNext(StreamingRecognizeRequest.newBuilder()
+                    .setAudioContent(ByteString.copyFrom(audioBytes))
+                    .build());
+        }
+    }
+
+    @OnClose
+    public void onClose(Session session) {
+        System.out.println("🔴 WebSocket Closed: " + session.getId());
+        if (requestObserver != null) {
+            requestObserver.onCompleted();
+        }
+    }
+
+    @OnError
+    public void onError(Session session, Throwable throwable) {
+        System.err.println("⚠️ WebSocket error: " + throwable.getMessage());
+    }
+
+    /**
+     * **🔹 Reads WAV File and Extracts PCM Data**
+     * - Converts **WAV file** to **raw PCM data**.
+     * - Ensures it is in the **correct format** (16-bit mono PCM).
+     */
+    private byte[] readWavFile(String filePath) throws IOException, UnsupportedAudioFileException {
+        File file = new File(filePath);
+        AudioInputStream audioInputStream = AudioSystem.getAudioInputStream(file);
+        AudioFormat format = audioInputStream.getFormat();
+
+        System.out.println("🎵 WAV File Format: " + format);
+
+        // Convert to PCM Signed if necessary
+        if (format.getEncoding() != AudioFormat.Encoding.PCM_SIGNED) {
+            AudioFormat pcmFormat = new AudioFormat(
+                    AudioFormat.Encoding.PCM_SIGNED,
+                    format.getSampleRate(),
+                    16, // Force 16-bit audio
+                    format.getChannels(),
+                    format.getChannels() * 2,
+                    format.getSampleRate(),
+                    false // Little-endian
+            );
+            audioInputStream = AudioSystem.getAudioInputStream(pcmFormat, audioInputStream);
+        }
+
+        // Read raw audio data
+        byte[] audioBytes = audioInputStream.readAllBytes();
+        audioInputStream.close();
+        return audioBytes;
+    }
+}

java-ai/src/main/java/oracleai/WebConfig.java

@@ -6,13 +6,18 @@
 import org.springframework.web.servlet.config.annotation.WebMvcConfigurer;
 
 @Configuration
-public class WebConfig implements WebMvcConfigurer {
-    @Override
-    public void addCorsMappings(CorsRegistry registry) {
-        registry.addMapping("/**") // This will apply to all routes
-                .allowedOrigins("https://130.61.51.75:4884") // Allow this origin
-                .allowedMethods("GET", "POST", "PUT", "DELETE") // Allowed methods
-                .allowedHeaders("*") // Allowed headers
-                .allowCredentials(true); // Allow credentials
+public class WebConfig {
+    @Bean
+    public WebMvcConfigurer corsConfigurer() {
+        return new WebMvcConfigurer() {
+            @Override
+            public void addCorsMappings(CorsRegistry registry) {
+                registry.addMapping("/**")  // Apply to all endpoints
+                        .allowedOriginPatterns("*")  // ✅ Use allowedOriginPatterns instead of "*"
+                        .allowedMethods("GET", "POST", "PUT", "DELETE", "OPTIONS")
+                        .allowedHeaders("*")
+                        .allowCredentials(true);  // ✅ Keep credentials enabled
+            }
+        };
     }
 }