/// <summary>Snippet for AsyncBatchAnnotateFilesAsync</summary>
public async Task AsyncBatchAnnotateFilesAsync()
{
// Snippet: AsyncBatchAnnotateFilesAsync(IEnumerable<AsyncAnnotateFileRequest>, CallSettings)
// Additional: AsyncBatchAnnotateFilesAsync(IEnumerable<AsyncAnnotateFileRequest>, CancellationToken)
// Create client
ImageAnnotatorClient imageAnnotatorClient = await ImageAnnotatorClient.CreateAsync();
// Initialize request argument(s)
IEnumerable <AsyncAnnotateFileRequest> requests = new AsyncAnnotateFileRequest[]
{
new AsyncAnnotateFileRequest(),
};
// Make the request
Operation <AsyncBatchAnnotateFilesResponse, OperationMetadata> response = await imageAnnotatorClient.AsyncBatchAnnotateFilesAsync(requests);
// Poll until the returned long-running operation is complete
Operation <AsyncBatchAnnotateFilesResponse, OperationMetadata> completedResponse = await response.PollUntilCompletedAsync();
// Retrieve the operation result
AsyncBatchAnnotateFilesResponse result = completedResponse.Result;
// Or get the name of the operation
string operationName = response.Name;
// This name can be stored, then the long-running operation retrieved later by name
Operation <AsyncBatchAnnotateFilesResponse, OperationMetadata> retrievedResponse = await imageAnnotatorClient.PollOnceAsyncBatchAnnotateFilesAsync(operationName);
// Check if the retrieved long-running operation has completed
if (retrievedResponse.IsCompleted)
{
// If it has completed, then access the result
AsyncBatchAnnotateFilesResponse retrievedResult = retrievedResponse.Result;
}
// End snippet
}
private static async Task GetDataAsync(string path, GoogleCredential credential)
{
try
{
int pos = path.LastIndexOf("\\");
string strFileName = path.Substring(pos + 1, path.Length - pos - 1);
StorageClient storageClient = await StorageClient.CreateAsync(credential);
storageClient.Service.HttpClient.Timeout = new TimeSpan(0, 10, 0);
var bucket = await storageClient.GetBucketAsync("bucket ocr");
FileStream fs = new FileStream(path, FileMode.Open, FileAccess.ReadWrite);
using (MemoryStream memStream = new MemoryStream())
{
await fs.CopyToAsync(memStream);
Google.Apis.Storage.v1.Data.Object googleDataObject;
googleDataObject = await storageClient.UploadObjectAsync(bucket.Name, "sinProcesar/" + strFileName, "application/pdf", memStream);
}
var asyncRequest = new AsyncAnnotateFileRequest
{
InputConfig = new InputConfig
{
GcsSource = new GcsSource
{
Uri = $"gs://{bucket.Name}/sinProcesar/{strFileName}"
},
MimeType = "application/pdf"
},
OutputConfig = new OutputConfig
{
BatchSize = 2,
GcsDestination = new GcsDestination
{
Uri = $"gs://{bucket.Name}/procesados/{strFileName.Split('.')[0]}"
}
}
};
asyncRequest.Features.Add(new Feature
{
Type = Feature.Types.Type.DocumentTextDetection
});
List <AsyncAnnotateFileRequest> requests = new List <AsyncAnnotateFileRequest>();
requests.Add(asyncRequest);
var client = new ImageAnnotatorClientBuilder
{
CredentialsPath = @"D:\Google_API_key_TFM.json"
}.Build();
var operation = client.AsyncBatchAnnotateFiles(requests);
operation.PollUntilCompleted();
}
catch (Exception e) { }
}
// [START vision_text_detection_pdf_gcs]
private static object DetectDocument(string gcsSourceUri,
string gcsDestinationBucketName, string gcsDestinationPrefixName)
{
var client = ImageAnnotatorClient.Create();
var asyncRequest = new AsyncAnnotateFileRequest
{
InputConfig = new InputConfig
{
GcsSource = new GcsSource
{
Uri = gcsSourceUri
},
// Supported mime_types are: 'application/pdf' and 'image/tiff'
MimeType = "application/pdf"
},
OutputConfig = new OutputConfig
{
// How many pages should be grouped into each json output file.
BatchSize = 2,
GcsDestination = new GcsDestination
{
Uri = $"gs://{gcsDestinationBucketName}/{gcsDestinationPrefixName}"
}
}
};
asyncRequest.Features.Add(new Feature
{
Type = Feature.Types.Type.DocumentTextDetection
});
List <AsyncAnnotateFileRequest> requests =
new List <AsyncAnnotateFileRequest>();
requests.Add(asyncRequest);
var operation = client.AsyncBatchAnnotateFiles(requests);
Console.WriteLine("Waiting for the operation to finish");
operation.PollUntilCompleted();
// Once the rquest has completed and the output has been
// written to GCS, we can list all the output files.
var storageClient = StorageClient.Create();
// List objects with the given prefix.
var blobList = storageClient.ListObjects(gcsDestinationBucketName,
gcsDestinationPrefixName);
Console.WriteLine("Output files:");
foreach (var blob in blobList)
{
Console.WriteLine(blob.Name);
}
// Process the first output file from GCS.
// Select the first JSON file from the objects in the list.
var output = blobList.Where(x => x.Name.Contains(".json")).First();
var jsonString = "";
using (var stream = new MemoryStream())
{
storageClient.DownloadObject(output, stream);
jsonString = System.Text.Encoding.UTF8.GetString(stream.ToArray());
}
var response = JsonParser.Default
.Parse <AnnotateFileResponse>(jsonString);
// The actual response for the first page of the input file.
var firstPageResponses = response.Responses[0];
var annotation = firstPageResponses.FullTextAnnotation;
// Here we print the full text from the first page.
// The response contains more information:
// annotation/pages/blocks/paragraphs/words/symbols
// including confidence scores and bounding boxes
Console.WriteLine($"Full text: \n {annotation.Text}");
return(0);
}
public int Executar(string nomeDoArquivo, MemoryStream arquivo)
{
var bucketName = BucketName.RandomName();
var outputPrefix = "";
var gcsSourceURI = $"gs://{bucketName}/{nomeDoArquivo}";
SortedDictionary <string, SortedSet <string> > _garbage = new SortedDictionary <string, SortedSet <string> >();
StorageClient _storage = StorageClient.Create();
_storage.CreateBucket(_projectId, bucketName);
_storage.UploadObject(bucketName, nomeDoArquivo, "application/pdf", arquivo);
SortedSet <string> objectNames;
if (!_garbage.TryGetValue(bucketName, out objectNames))
{
objectNames = _garbage[bucketName] = new SortedSet <string>();
}
objectNames.Add(nomeDoArquivo);
var client = ImageAnnotatorClient.Create();
var asyncRequest = new AsyncAnnotateFileRequest
{
InputConfig = new InputConfig
{
GcsSource = new GcsSource
{
Uri = gcsSourceURI
},
MimeType = "application/pdf"
},
OutputConfig = new OutputConfig
{
// How many pages should be grouped into each json output file.
BatchSize = 100,
GcsDestination = new GcsDestination
{
Uri = $"gs://{bucketName}/{outputPrefix}"
}
}
};
asyncRequest.Features.Add(new Feature
{
Type = Feature.Types.Type.DocumentTextDetection
});
List <AsyncAnnotateFileRequest> requests = new List <AsyncAnnotateFileRequest>
{
asyncRequest
};
var operation = client.AsyncBatchAnnotateFiles(requests);
operation.PollUntilCompleted();
var blobList = _storage.ListObjects(bucketName, outputPrefix);
var output = blobList.Where(x => x.Name.Contains(".json")).First();
var jsonString = "";
using (var stream = new MemoryStream())
{
_storage.DownloadObject(output, stream);
jsonString = System.Text.Encoding.UTF8.GetString(stream.ToArray());
}
var response = JsonParser.Default.Parse <AnnotateFileResponse>(jsonString);
int total = 0;
for (int i = 0; i < response.Responses.Count; i++)
{
var pageResponses = response.Responses[i];
if (pageResponses != null)
{
var annotation = pageResponses.FullTextAnnotation;
var conteudo = annotation.Text.Replace("\n", " ");
var remocaoDosEspacos = conteudo.Split(' ');
foreach (var item in remocaoDosEspacos)
{
total += item.Length;
}
}
}
RemoverArquivos(bucketName);
return(total);
}
