automl: explictly update timeoutes due to default library changes (#2719)

* automl: explictly update timeoutes due to library changes in the defaults

* Update ImportDataset.java

* try bumping timeout

AutoML provides no guarantee on how long this could take and normally would send an email followup. Though normally, I see this finish in under 10 mins. Trying to pin down if TASK CANCELLED is actually related to a timeout or not.

* update timeouts for all import methods

* undo changes to TablesImport, add catch for Cancellation Exception

* update to correct CancelledException

* wrong cancellation again

* run tests

* log to error

* test

* reset changes that printed error

* set retry settings

* add timeout check to beta code

Author: nnegrey

automl/beta/pom.xml

@@ -40,7 +40,7 @@
             <dependency>
                 <groupId>com.google.cloud</groupId>
                 <artifactId>libraries-bom</artifactId>
-                <version>4.4.1</version>
+                <version>5.2.0</version>
                 <type>pom</type>
                 <scope>import</scope>
             </dependency>
@@ -60,7 +60,6 @@
         <dependency>
             <groupId>com.google.cloud</groupId>
             <artifactId>google-cloud-storage</artifactId>
-            <version>1.107.0</version>
         </dependency>
         <dependency>
             <groupId>net.sourceforge.argparse4j</groupId>

automl/beta/src/main/java/com/example/automl/ImportDataset.java

@@ -17,19 +17,26 @@
 package com.example.automl;
 
 // [START automl_import_dataset_beta]
+import com.google.api.gax.longrunning.OperationFuture;
+import com.google.api.gax.retrying.RetrySettings;
 import com.google.cloud.automl.v1beta1.AutoMlClient;
+import com.google.cloud.automl.v1beta1.AutoMlSettings;
 import com.google.cloud.automl.v1beta1.DatasetName;
 import com.google.cloud.automl.v1beta1.GcsSource;
 import com.google.cloud.automl.v1beta1.InputConfig;
+import com.google.cloud.automl.v1beta1.OperationMetadata;
 import com.google.protobuf.Empty;
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.concurrent.ExecutionException;
+import java.util.concurrent.TimeUnit;
+import java.util.concurrent.TimeoutException;
+import org.threeten.bp.Duration;
 
 class ImportDataset {
 
   public static void main(String[] args)
-      throws IOException, ExecutionException, InterruptedException {
+      throws IOException, ExecutionException, InterruptedException, TimeoutException {
     // TODO(developer): Replace these variables before running the sample.
     String projectId = "YOUR_PROJECT_ID";
     String datasetId = "YOUR_DATASET_ID";
@@ -39,11 +46,17 @@ public static void main(String[] args)
 
   // Import a dataset
   static void importDataset(String projectId, String datasetId, String path)
-      throws IOException, ExecutionException, InterruptedException {
+      throws IOException, ExecutionException, InterruptedException, TimeoutException {
+    Duration totalTimeout = Duration.ofMinutes(45);
+    RetrySettings retrySettings = RetrySettings.newBuilder().setTotalTimeout(totalTimeout).build();
+    AutoMlSettings.Builder builder = AutoMlSettings.newBuilder();
+    builder.importDataSettings().setRetrySettings(retrySettings).build();
+    AutoMlSettings settings = builder.build();
+
     // Initialize client that will be used to send requests. This client only needs to be created
     // once, and can be reused for multiple requests. After completing all of your requests, call
     // the "close" method on the client to safely clean up any remaining background resources.
-    try (AutoMlClient client = AutoMlClient.create()) {
+    try (AutoMlClient client = AutoMlClient.create(settings)) {
       // Get the complete path of the dataset.
       DatasetName datasetFullId = DatasetName.of(projectId, "us-central1", datasetId);
 
@@ -55,8 +68,22 @@ static void importDataset(String projectId, String datasetId, String path)
       InputConfig inputConfig = InputConfig.newBuilder().setGcsSource(gcsSource).build();
       System.out.println("Processing import...");
 
-      Empty response = client.importDataAsync(datasetFullId, inputConfig).get();
+      // Start the import job
+      OperationFuture<Empty, OperationMetadata> operation = client
+          .importDataAsync(datasetFullId, inputConfig);
+
+      System.out.format("Operation name: %s%n", operation.getName());
+
+      // If you want to wait for the operation to finish, adjust the timeout appropriately. The
+      // operation will still run if you choose not to wait for it to complete. You can check the
+      // status of your operation using the operation's name.
+      Empty response = operation.get(45, TimeUnit.MINUTES);
       System.out.format("Dataset imported. %s%n", response);
+    } catch (TimeoutException e) {
+      System.out.println("The operation's polling period was not long enough.");
+      System.out.println("You can use the Operation's name to get the current status.");
+      System.out.println("The import job is still running and will complete as expected.");
+      throw e;
     }
   }
 }

automl/beta/src/test/java/com/example/automl/ImportDatasetTest.java

@@ -28,6 +28,7 @@
 import java.io.PrintStream;
 import java.util.UUID;
 import java.util.concurrent.ExecutionException;
+import java.util.concurrent.TimeoutException;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.BeforeClass;
@@ -92,7 +93,8 @@ public void tearDown() throws InterruptedException, ExecutionException, IOExcept
   }
 
   @Test
-  public void testImportDataset() throws IOException, ExecutionException, InterruptedException {
+  public void testImportDataset()
+      throws InterruptedException, ExecutionException, TimeoutException, IOException {
     ImportDataset.importDataset(PROJECT_ID, datasetId, BUCKET + "/entity-extraction/dataset.csv");
     String got = bout.toString();
     assertThat(got).contains("Dataset imported.");

automl/beta/src/test/java/com/example/automl/TablesImportDatasetTest.java

@@ -65,7 +65,7 @@ public void tearDown() {
   @Test
   public void testTablesImportDataset() {
     try {
-      ImportDataset.importDataset(
+      TablesImportDataset.importDataset(
           PROJECT_ID, "TEN0000000000000000000", "gs://cloud-ml-tables-data/bank-marketing.csv");
       String got = bout.toString();
       assertThat(got).contains("The Dataset doesn't exist or is inaccessible for use with AutoMl.");

automl/cloud-client/pom.xml

@@ -32,18 +32,30 @@
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
   </properties>
 
+  <!-- [START automl_java_dependencies] -->
+  <!--  Using libraries-bom to manage versions.
+  See https://github.com/GoogleCloudPlatform/cloud-opensource-java/wiki/The-Google-Cloud-Platform-Libraries-BOM -->
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>com.google.cloud</groupId>
+        <artifactId>libraries-bom</artifactId>
+        <version>5.2.0</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
   <dependencies>
-    <!-- [START automl_java_dependencies] -->
     <dependency>
       <groupId>com.google.cloud</groupId>
       <artifactId>google-cloud-automl</artifactId>
-      <version>1.1.1</version>
     </dependency>
     <!-- [END automl_java_dependencies] -->
     <dependency>
       <groupId>com.google.cloud</groupId>
       <artifactId>google-cloud-storage</artifactId>
-      <version>1.107.0</version>
     </dependency>
     <dependency>
       <groupId>net.sourceforge.argparse4j</groupId>
@@ -64,5 +76,7 @@
       <version>1.0.1</version>
       <scope>test</scope>
     </dependency>
+    <!-- [START automl_java_dependencies] -->
   </dependencies>
+  <!-- [END automl_java_dependencies] -->
 </project>

automl/cloud-client/src/main/java/com/example/automl/ImportDataset.java

@@ -17,19 +17,23 @@
 package com.example.automl;
 
 // [START automl_import_dataset]
+import com.google.api.gax.longrunning.OperationFuture;
 import com.google.cloud.automl.v1.AutoMlClient;
 import com.google.cloud.automl.v1.DatasetName;
 import com.google.cloud.automl.v1.GcsSource;
 import com.google.cloud.automl.v1.InputConfig;
+import com.google.cloud.automl.v1.OperationMetadata;
 import com.google.protobuf.Empty;
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.concurrent.ExecutionException;
+import java.util.concurrent.TimeUnit;
+import java.util.concurrent.TimeoutException;
 
 class ImportDataset {
 
   public static void main(String[] args)
-      throws IOException, ExecutionException, InterruptedException {
+      throws IOException, ExecutionException, InterruptedException, TimeoutException {
     // TODO(developer): Replace these variables before running the sample.
     String projectId = "YOUR_PROJECT_ID";
     String datasetId = "YOUR_DATASET_ID";
@@ -39,7 +43,7 @@ public static void main(String[] args)
 
   // Import a dataset
   static void importDataset(String projectId, String datasetId, String path)
-      throws IOException, ExecutionException, InterruptedException {
+      throws IOException, ExecutionException, InterruptedException, TimeoutException {
     // Initialize client that will be used to send requests. This client only needs to be created
     // once, and can be reused for multiple requests. After completing all of your requests, call
     // the "close" method on the client to safely clean up any remaining background resources.
@@ -55,8 +59,22 @@ static void importDataset(String projectId, String datasetId, String path)
       InputConfig inputConfig = InputConfig.newBuilder().setGcsSource(gcsSource).build();
       System.out.println("Processing import...");
 
-      Empty response = client.importDataAsync(datasetFullId, inputConfig).get();
-      System.out.format("Dataset imported. %s\n", response);
+      // Start the import job
+      OperationFuture<Empty, OperationMetadata> operation =
+          client.importDataAsync(datasetFullId, inputConfig);
+
+      System.out.format("Operation name: %s%n", operation.getName());
+
+      // If you want to wait for the operation to finish, adjust the timeout appropriately. The
+      // operation will still run if you choose not to wait for it to complete. You can check the
+      // status of your operation using the operation's name.
+      Empty response = operation.get(45, TimeUnit.MINUTES);
+      System.out.format("Dataset imported. %s%n", response);
+    } catch (TimeoutException e) {
+      System.out.println("The operation's polling period was not long enough.");
+      System.out.println("You can use the Operation's name to get the current status.");
+      System.out.println("The import job is still running and will complete as expected.");
+      throw e;
     }
   }
 }

automl/cloud-client/src/test/java/com/example/automl/ImportDatasetTest.java

@@ -24,6 +24,7 @@
 import java.io.PrintStream;
 import java.util.UUID;
 import java.util.concurrent.ExecutionException;
+import java.util.concurrent.TimeoutException;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.BeforeClass;
@@ -83,7 +84,8 @@ public void tearDown() throws InterruptedException, ExecutionException, IOExcept
   }
 
   @Test
-  public void testImportDataset() throws IOException, ExecutionException, InterruptedException {
+  public void testImportDataset()
+      throws IOException, ExecutionException, InterruptedException, TimeoutException {
     ImportDataset.importDataset(PROJECT_ID, datasetId, BUCKET + "/entity-extraction/dataset.csv");
     String got = bout.toString();
     assertThat(got).contains("Dataset imported.");