Beta feature : Vision : PDF/TIFF/GIF document feature detection

vision/beta/cloud-client/pom.xml

@@ -26,7 +26,7 @@
   <parent>
     <groupId>com.google.cloud.samples</groupId>
     <artifactId>shared-configuration</artifactId>
-    <version>1.0.9</version>
+    <version>1.0.10</version>
   </parent>
 
   <properties>
@@ -40,7 +40,7 @@
     <dependency>
       <groupId>com.google.cloud</groupId>
       <artifactId>google-cloud-vision</artifactId>
-      <version>1.62.0</version>
+      <version>1.64.0</version>
     </dependency>
     <dependency>
       <groupId>com.google.cloud</groupId>

vision/beta/cloud-client/src/main/java/com/example/vision/AsyncBatchAnnotateImagesGcs.java

@@ -0,0 +1,161 @@
+/*
+ * Copyright 2019 Google LLC
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package com.example.vision;
+
+// [START vision_detect_async_batch_annotate_images_beta]
+
+import com.google.api.core.ApiFuture;
+import com.google.api.gax.paging.Page;
+import com.google.cloud.storage.Blob;
+import com.google.cloud.storage.Bucket;
+import com.google.cloud.storage.Storage;
+import com.google.cloud.storage.Storage.BlobListOption;
+import com.google.cloud.storage.StorageOptions;
+import com.google.cloud.vision.v1p4beta1.AnnotateImageRequest;
+import com.google.cloud.vision.v1p4beta1.AsyncBatchAnnotateImagesRequest;
+import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse.Builder;
+import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse;
+import com.google.cloud.vision.v1p4beta1.Feature;
+import com.google.cloud.vision.v1p4beta1.Feature.Type;
+import com.google.cloud.vision.v1p4beta1.GcsDestination;
+import com.google.cloud.vision.v1p4beta1.Image;
+import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient;
+import com.google.cloud.vision.v1p4beta1.ImageSource;
+import com.google.cloud.vision.v1p4beta1.OutputConfig;
+
+import com.google.longrunning.Operation;
+import com.google.protobuf.util.JsonFormat;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.concurrent.TimeUnit;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+public class AsyncBatchAnnotateImagesGcs {
+
+  /**
+   * Performs asynchronous batch annotation of images on Google Cloud Storage
+   * @param gcsSourcePath The path to the remote file on Google Cloud Storage
+   * @param gcsDestinationPath The path to the annotated image file
+   * @throws Exception on errors
+   */
+
+  public static void asyncBatchAnnotateImagesGcs(String gcsSourcePath, String gcsDestinationPath)
+      throws Exception {
+
+    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
+      List<AnnotateImageRequest> requests = new ArrayList<>();
+      System.out.println("source: " + gcsSourcePath);
+
+      ImageSource imgSource = ImageSource.newBuilder().setImageUri(gcsSourcePath).build();
+
+      Image image = Image.newBuilder().setSource(imgSource).build();
+
+      // Set the GCS destination path for where to save the results.
+      GcsDestination gcsDestination =
+          GcsDestination.newBuilder().setUri(gcsDestinationPath).build();
+
+      // Create the configuration for the output with the batch size.
+      // The batch size sets how many pages should be grouped into each json output file.
+      OutputConfig outputConfig =
+          OutputConfig.newBuilder().setGcsDestination(gcsDestination).setBatchSize(2).build();
+
+      // Select the Features required by the vision API
+      Feature features =
+          Feature.newBuilder()
+              .setType(Type.LABEL_DETECTION)
+              .setType(Type.TEXT_DETECTION)
+              .setType(Type.IMAGE_PROPERTIES)
+              .build();
+
+      // Build the request
+      AnnotateImageRequest annotateImageRequest =
+          AnnotateImageRequest.newBuilder().setImage(image).addFeatures(features).build();
+
+      requests.add(annotateImageRequest);
+      AsyncBatchAnnotateImagesRequest request =
+          AsyncBatchAnnotateImagesRequest.newBuilder()
+              .addAllRequests(requests)
+              .setOutputConfig(outputConfig)
+              .build();
+
+      ApiFuture<Operation> future = client.asyncBatchAnnotateImagesCallable().futureCall(request);
+      // Wait for the request to finish. (The result is not used, since the API saves the result to
+      // the specified location on GCS.)
+      Operation response = future.get(180, TimeUnit.SECONDS);
+
+      System.out.println("Waiting for the operation to finish.");
+
+      // Once the request has completed and the output has been
+      // written to GCS, we can list all the output files.
+      Storage storage = StorageOptions.getDefaultInstance().getService();
+
+      // Get the destination location from the gcsDestinationPath
+      Pattern pattern = Pattern.compile("gs://([^/]+)/(.+)");
+      Matcher matcher = pattern.matcher(gcsDestinationPath);
+
+      if (matcher.find()) {
+        String bucketName = matcher.group(1);
+        String prefix = matcher.group(2);
+
+        // Get the list of objects with the given prefix from the GCS bucket
+        Bucket bucket = storage.get(bucketName);
+        Page<Blob> pageList = bucket.list(BlobListOption.prefix(prefix));
+
+        Blob firstOutputFile = null;
+
+        // List objects with the given prefix.
+        System.out.println("Output files:");
+        for (Blob blob : pageList.iterateAll()) {
+          System.out.println(blob.getName());
+
+          // Process the first output file from GCS.
+          // Since we specified batch size = 2, the first response contains
+          // the first two image requests
+          if (firstOutputFile == null) {
+            firstOutputFile = blob;
+          }
+        }
+
+        // Get the contents of the file and convert the JSON contents to an
+        // BatchAnnotateImagesResponse
+        // object. If the Blob is small read all its content in one request
+        // (Note: the file is a .json file)
+        // Storage guide: https://cloud.google.com/storage/docs/downloading-objects
+        String jsonContents = new String(firstOutputFile.getContent());
+        Builder builder = BatchAnnotateImagesResponse.newBuilder();
+        JsonFormat.parser().merge(jsonContents, builder);
+
+        // Build the AnnotateFileResponse object
+        BatchAnnotateImagesResponse batchAnnotateImagesResponse = builder.build();
+
+        // Here we print the response for the first image
+        // The response contains more information:
+        // annotation/pages/blocks/paragraphs/words/symbols/colors
+        // including confidence score and bounding boxes
+        System.out.format("\nResponse: %s\n", batchAnnotateImagesResponse.getResponses(0));
+
+      } else {
+        System.out.println("No MATCH");
+      }
+    } catch (Exception e) {
+      System.out.println("Error during asyncBatchAnnotateImagesGcs: \n" + e.toString());
+    }
+  }
+}
+
+// [END vision_detect_async_batch_annotate_images_beta]

vision/beta/cloud-client/src/main/java/com/example/vision/DetectBatchAnnotateFiles.java

@@ -0,0 +1,118 @@
+/*
+ * Copyright 2019 Google LLC
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package com.example.vision;
+
+// [START vision_detect_batch_annotate_files_beta]
+
+import com.google.api.core.ApiFuture;
+import com.google.cloud.vision.v1p4beta1.AnnotateFileRequest;
+import com.google.cloud.vision.v1p4beta1.AnnotateFileResponse;
+import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesRequest;
+import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesResponse;
+import com.google.cloud.vision.v1p4beta1.Block;
+import com.google.cloud.vision.v1p4beta1.Feature;
+import com.google.cloud.vision.v1p4beta1.Feature.Type;
+import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient;
+import com.google.cloud.vision.v1p4beta1.InputConfig;
+import com.google.cloud.vision.v1p4beta1.Page;
+import com.google.cloud.vision.v1p4beta1.Paragraph;
+import com.google.cloud.vision.v1p4beta1.Symbol;
+import com.google.cloud.vision.v1p4beta1.TextAnnotation;
+import com.google.cloud.vision.v1p4beta1.Word;
+import com.google.protobuf.ByteString;
+
+import java.io.FileInputStream;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+
+public class DetectBatchAnnotateFiles {
+
+  /**
+   * Performs document feature detection on a local PDF/TIFF/GIF file.
+   * While your PDF file may have several pages, this API can process up to 5 pages only.
+   * @param filePath The local file path e.g. "path/to/file.pdf"
+   * @throws Exception on errors
+   */
+  public static void detectBatchAnnotateFiles(String filePath) {
+
+    // Initialize the 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 (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
+      //Annotate the first two pages and the last one (max 5 pages)
+      //First page starts at 1, and not 0. Last page is -1.
+      List<Integer> pages = Arrays.asList(1,2,-1);
+      ByteString pdfBytes = ByteString.readFrom(new FileInputStream(filePath));
+      Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
+      //Other supported mime types : 'image/tiff' or 'image/gif'
+      InputConfig inputConfig =
+          InputConfig.newBuilder().setMimeType("application/pdf").setContent(pdfBytes).build();
+      AnnotateFileRequest request =
+          AnnotateFileRequest.newBuilder()
+              .addFeatures(feat)
+              .setInputConfig(inputConfig)
+              .addAllPages(pages)
+              .build();
+      List<AnnotateFileRequest> requests = new ArrayList<>();
+      requests.add(request);
+      BatchAnnotateFilesRequest batchAnnotateFilesRequest =
+          BatchAnnotateFilesRequest.newBuilder().addAllRequests(requests).build();
+      ApiFuture<BatchAnnotateFilesResponse> future =
+          client.batchAnnotateFilesCallable().futureCall(batchAnnotateFilesRequest);
+      BatchAnnotateFilesResponse response = future.get();
+      client.close();
+      //Getting the first response
+      AnnotateFileResponse annotateFileResponse = response.getResponses(0);
+      // For full list of available annotations, see http://g.co/cloud/vision/docs
+      TextAnnotation textAnnotation = annotateFileResponse.getResponses(0).getFullTextAnnotation();
+      for (Page page : textAnnotation.getPagesList()) {
+        String pageText = "";
+        for (Block block : page.getBlocksList()) {
+          String blockText = "";
+          for (Paragraph para : block.getParagraphsList()) {
+            String paraText = "";
+            for (Word word : para.getWordsList()) {
+              String wordText = "";
+              for (Symbol symbol : word.getSymbolsList()) {
+                wordText = wordText + symbol.getText();
+                System.out.format(
+                    "Symbol text: %s (Confidence: %f)\n", symbol.getText(), symbol.getConfidence());
+              }
+              System.out.format(
+                  "Word text: %s (Confidence: %f)\n\n", wordText, word.getConfidence());
+              paraText = String.format("%s %s", paraText, wordText);
+            }
+            // Output Example using Paragraph:
+            System.out.println("\nParagraph: \n" + paraText);
+            System.out.format("Paragraph Confidence: %f\n", para.getConfidence());
+            blockText = blockText + paraText;
+          }
+          pageText = pageText + blockText;
+        }
+      }
+      System.out.println("\nComplete annotation:");
+      System.out.println(textAnnotation.getText());
+
+    } catch (Exception e) {
+      System.out.println("Error during detectPdfText: \n" + e.toString());
+    }
+  }
+}
+// [END vision_detect_batch_annotate_files_beta]