Examples with InputConfig com.google.cloud.documentai.v1beta2.InputConfig used on opensource projects

Example 21 with InputConfig

use of com.google.cloud.documentai.v1beta2.InputConfig in project java-vision by googleapis.

the class DetectBatchAnnotateFilesGcs method detectBatchAnnotateFilesGcs.

// Performs document feature detection on a remote PDF/TIFF/GIF file on Google Cloud Storage.
public static void detectBatchAnnotateFilesGcs(String gcsPath) {
    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);
        GcsSource gcsSource = GcsSource.newBuilder().setUri(gcsPath).build();
        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").setGcsSource(gcsSource).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();
        // 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());
    }
}

Example 22 with InputConfig

use of com.google.cloud.documentai.v1beta2.InputConfig in project java-vision by googleapis.

the class DetectBatchAnnotateFiles method detectBatchAnnotateFiles.

// Performs document feature detection on a local PDF/TIFF/GIF file.
public static void detectBatchAnnotateFiles(String filePath) {
    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();
        // 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());
    }
}

Example 23 with InputConfig

use of com.google.cloud.documentai.v1beta2.InputConfig in project java-vision by googleapis.

the class BatchAnnotateFiles method batchAnnotateFiles.

public static void batchAnnotateFiles(String filePath) throws IOException {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (ImageAnnotatorClient imageAnnotatorClient = ImageAnnotatorClient.create()) {
        // You can send multiple files to be annotated, this sample demonstrates how to do this with
        // one file. If you want to use multiple files, you have to create a `AnnotateImageRequest`
        // object for each file that you want annotated.
        // First read the files contents
        Path path = Paths.get(filePath);
        byte[] data = Files.readAllBytes(path);
        ByteString content = ByteString.copyFrom(data);
        // Specify the input config with the file's contents and its type.
        // Supported mime_type: application/pdf, image/tiff, image/gif
        // https://cloud.google.com/vision/docs/reference/rpc/google.cloud.vision.v1#inputconfig
        InputConfig inputConfig = InputConfig.newBuilder().setMimeType("application/pdf").setContent(content).build();
        // Set the type of annotation you want to perform on the file
        // https://cloud.google.com/vision/docs/reference/rpc/google.cloud.vision.v1#google.cloud.vision.v1.Feature.Type
        Feature feature = Feature.newBuilder().setType(Feature.Type.DOCUMENT_TEXT_DETECTION).build();
        // Build the request object for that one file. Note: for additional file you have to create
        // additional `AnnotateFileRequest` objects and store them in a list to be used below.
        // Since we are sending a file of type `application/pdf`, we can use the `pages` field to
        // specify which pages to process. The service can process up to 5 pages per document file.
        // https://cloud.google.com/vision/docs/reference/rpc/google.cloud.vision.v1#google.cloud.vision.v1.AnnotateFileRequest
        AnnotateFileRequest fileRequest = AnnotateFileRequest.newBuilder().setInputConfig(inputConfig).addFeatures(feature).addPages(// Process the first page
        1).addPages(// Process the second page
        2).addPages(// Process the last page
        -1).build();
        // Add each `AnnotateFileRequest` object to the batch request.
        BatchAnnotateFilesRequest request = BatchAnnotateFilesRequest.newBuilder().addRequests(fileRequest).build();
        // Make the synchronous batch request.
        BatchAnnotateFilesResponse response = imageAnnotatorClient.batchAnnotateFiles(request);
        // sample.
        for (AnnotateImageResponse imageResponse : response.getResponsesList().get(0).getResponsesList()) {
            System.out.format("Full text: %s%n", imageResponse.getFullTextAnnotation().getText());
            for (Page page : imageResponse.getFullTextAnnotation().getPagesList()) {
                for (Block block : page.getBlocksList()) {
                    System.out.format("%nBlock confidence: %s%n", block.getConfidence());
                    for (Paragraph par : block.getParagraphsList()) {
                        System.out.format("\tParagraph confidence: %s%n", par.getConfidence());
                        for (Word word : par.getWordsList()) {
                            System.out.format("\t\tWord confidence: %s%n", word.getConfidence());
                            for (Symbol symbol : word.getSymbolsList()) {
                                System.out.format("\t\t\tSymbol: %s, (confidence: %s)%n", symbol.getText(), symbol.getConfidence());
                            }
                        }
                    }
                }
            }
        }
    }
}