/// <summary>
/// Check if the client is open and then close it.
/// </summary>
/// <param name="client">The client to close</param>
public static void CloseService(DocumentConverterServiceClient client)
{
if (client != null && client.State == CommunicationState.Opened)
{
client.Close();
}
}
/// <summary>
/// Check if the client is open and then close it.
/// </summary>
/// <param name="client">The client to close</param>
public static void CloseService(DocumentConverterServiceClient client)
{
if (client != null && client.State == CommunicationState.Opened)
{
client.CloseAsync().GetAwaiter().GetResult();
}
}
/// <summary>
/// Configure the Bindings, endpoints and open the service using the specified address.
/// </summary>
/// <returns>An instance of the Web Service.</returns>
public static DocumentConverterServiceClient OpenService(string address)
{
DocumentConverterServiceClient client = null;
try
{
BasicHttpBinding binding = new BasicHttpBinding();
// ** Use standard Windows Security.
binding.Security.Mode = BasicHttpSecurityMode.TransportCredentialOnly;
binding.Security.Transport.ClientCredentialType =
HttpClientCredentialType.Windows;
// ** Increase the client Timeout to deal with (very) long running requests.
binding.SendTimeout = TimeSpan.FromMinutes(120);
binding.ReceiveTimeout = TimeSpan.FromMinutes(120);
// ** Set the maximum document size to 50MB
binding.MaxReceivedMessageSize = 50 * 1024 * 1024;
binding.ReaderQuotas.MaxArrayLength = 50 * 1024 * 1024;
binding.ReaderQuotas.MaxStringContentLength = 50 * 1024 * 1024;
// ** Specify an identity (any identity) in order to get it past .net3.5 sp1
EndpointIdentity epi = EndpointIdentity.CreateUpnIdentity("unknown");
EndpointAddress epa = new EndpointAddress(new Uri(address), epi);
client = new DocumentConverterServiceClient(binding, epa);
client.Open();
return(client);
}
catch (Exception)
{
CloseService(client);
throw;
}
}
public static async Task <IActionResult> Run(
[HttpTrigger(AuthorizationLevel.Function, "post", Route = null)] HttpRequest req,
ILogger log)
{
// ** Get request body data.
string requestBody = await new StreamReader(req.Body).ReadToEndAsync();
dynamic data = JsonConvert.DeserializeObject(requestBody);
string FileName = data?.fileName;
string FileContent = data?.fileContent;
byte[] convFile = null;
DocumentConverterServiceClient client = null;
try
{
byte[] sourceFile = Convert.FromBase64String(FileContent);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = FileName;
openOptions.FileExtension = Path.GetExtension(FileName);
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
conversionSettings.Fidelity = ConversionFidelities.Full;
conversionSettings.Quality = ConversionQuality.OptimizeForPrint;
convFile = client.ConvertAsync(sourceFile, openOptions, conversionSettings).GetAwaiter().GetResult();
}
catch (Exception ex)
{
return(new BadRequestObjectResult(new
{
message = ex.ToString()
}));
}
finally
{
CloseService(client);
}
return((ActionResult) new OkObjectResult(new
{
processed_file_content = convFile,
}));
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Delete any processed files from a previous run
foreach (FileInfo f in new DirectoryInfo(".").GetFiles("*_ocr.pdf"))
{
f.Delete();
}
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
// ** If nothing is specified then read the first PDF file from the current folder.
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.pdf");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to OCR.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = Path.GetExtension(sourceFileName);
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
// ** OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR
OCRSettings ocr = new OCRSettings();
ocr.Language = OCRLanguage.English.ToString();
ocr.Performance = OCRPerformance.Slow;
ocr.WhiteList = string.Empty;
ocr.BlackList = string.Empty;
conversionSettings.OCRSettings = ocr;
// ** OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR OCR
// ** Carry out the conversion.
Console.WriteLine("Processing file " + sourceFileName + ".");
byte[] convFile = client.ProcessChanges(sourceFile, openOptions, conversionSettings);
// ** Write the processed file back to the file system with a PDF extension.
string destinationFileName = Path.GetFileNameWithoutExtension(sourceFileName) + "_ocr.pdf";
using (FileStream fs = File.Create(destinationFileName))
{
fs.Write(convFile, 0, convFile.Length);
fs.Close();
}
Console.WriteLine("File written to " + destinationFileName);
// ** Open the generated PDF file in a PDF Reader
Console.WriteLine("Launching file in PDF Reader");
Process.Start(destinationFileName);
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
Console.ReadKey();
}
private void CloseService(DocumentConverterServiceClient client)
{
if (client != null && client.State == CommunicationState.Opened)
client.Close();
}
//private void InsertSeedRecords(bool associated, bool primaryDoc, int consentTypeId, string fName, string lName, int pcid)
//{
// System.Configuration.Configuration config = WebConfigurationManager.OpenWebConfiguration(HttpContext.Current.Request.ApplicationPath);
// var conStr = config.AppSettings.Settings["DBConnection"].Value;
// using (var sqlConnection = new SqlConnection(conStr))
// {
// sqlConnection.Open();
// var cmdTreatment = new SqlCommand("insert into Physican(Associated,Primary_Doctor,ConsentTypeID,Fname,Lname,PCID) values('" + (associated == true ? 1 : 0) + ",'" + (primaryDoc == true ? 1 : 0) + ",'" + consentTypeId + ",'" + fName + ",'" + lName + "'," + pcid + "," + "')", sqlConnection);
// cmdTreatment.ExecuteNonQuery();
// }
//}
private DocumentConverterServiceClient OpenService(string address)
{
DocumentConverterServiceClient client = null;
try
{
var binding = new BasicHttpBinding();
// ** Use standard Windows Authentication
binding.Security.Mode = BasicHttpSecurityMode.TransportCredentialOnly;
binding.Security.Transport.ClientCredentialType = HttpClientCredentialType.Windows;
// ** Allow long running conversions
binding.SendTimeout = TimeSpan.FromMinutes(30);
binding.ReceiveTimeout = TimeSpan.FromMinutes(30);
// ** Allow file sizes of 50MB
binding.MaxReceivedMessageSize = 50 * 1024 * 1024;
binding.ReaderQuotas.MaxArrayLength = 50 * 1024 * 1024;
binding.ReaderQuotas.MaxStringContentLength = 50 * 1024 * 1024;
// ** We need to specify an identity (any identity) in order to get it past .net3.5 sp1
EndpointIdentity epi = EndpointIdentity.CreateUpnIdentity("unknown");
var epa = new EndpointAddress(new Uri(address), epi);
client = new DocumentConverterServiceClient(binding, epa);
client.Open();
return client;
}
catch (Exception)
{
CloseService(client);
throw;
}
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
//** Delete any split files from a previous test run.
foreach (string file in Directory.GetFiles(Directory.GetCurrentDirectory(), "spf-*.pdf"))
{
File.Delete(file);
}
// ** If nothing is specified then read the first PDF file from the current folder.
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.pdf");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to split.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = "pdf";
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
// ** Create the ProcessingOptions for the splitting task.
ProcessingOptions processingOptions = new ProcessingOptions()
{
MergeSettings = null,
SplitOptions = new FileSplitOptions()
{
FileNameTemplate = "spf-{0:D3}",
FileSplitType = FileSplitType.ByNumberOfPages,
BatchSize = 5,
BookmarkLevel = 0
},
SourceFiles = new SourceFile[1]
{
new SourceFile()
{
MergeSettings = null,
OpenOptions = openOptions,
ConversionSettings = conversionSettings,
File = sourceFile
}
}
};
// ** Carry out the splittng.
Console.WriteLine("Splitting file " + sourceFileName);
BatchResults batchResults = client.ProcessBatch(processingOptions);
// ** Process the returned files
foreach (BatchResult result in batchResults.Results)
{
Console.WriteLine("Writing split file " + result.FileName);
File.WriteAllBytes(result.FileName, result.File);
}
Console.WriteLine("Finished.");
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
Console.ReadKey();
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
// ** Only .docx, .xlsx or .pptx filea are accepted
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.docx");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to convert and watermark.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = Path.GetExtension(sourceFileName);
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
// ** Format must be the same as the input format.
// ** Resolve by parsing the extension into OtputFormat enum.
// ** Leading dot (.) must be removed to make the parsing work.
string format = Path.GetExtension(sourceFileName).TrimStart(new char[] { '.' });
conversionSettings.Format = (OutputFormat)Enum.Parse(typeof(OutputFormat), format, true);
conversionSettings.Fidelity = ConversionFidelities.Full;
conversionSettings.Quality = ConversionQuality.OptimizeForPrint;
// ** Get the list of watermarks to apply.
conversionSettings.Watermarks = CreateWatermarks();
// ** Carry out the watermarking.
Console.WriteLine("Watermarking file " + sourceFileName);
byte[] watermarkedFile = client.ApplyWatermark(sourceFile, openOptions, conversionSettings);
// ** Write the watermarked file back to the file system with.
string destinationFileName = Path.GetDirectoryName(sourceFileName) + @"\" +
Path.GetFileNameWithoutExtension(sourceFileName) +
"_Watermarked." + conversionSettings.Format;
using (FileStream fs = File.Create(destinationFileName))
{
fs.Write(watermarkedFile, 0, watermarkedFile.Length);
fs.Close();
}
Console.WriteLine("File watermarked to " + destinationFileName);
// ** Open the generated file
Console.WriteLine("Opening result document.");
Process.Start(destinationFileName);
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
Console.ReadKey();
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
// ** If nothing is specified then read the first PDF file from the current folder.
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.pdf");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to convert to PDF/A.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = "pdf";
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
// ** Set output to PDF/A
conversionSettings.PDFProfile = PDFProfile.PDF_A2B;
// ** Specify output settings as we want to force post processing of files.
OutputFormatSpecificSettings_PDF osf = new OutputFormatSpecificSettings_PDF();
osf.PostProcessFile = true;
// ** We need to specify ALL values of an object, so use these for PDF/A
osf.FastWebView = false;
osf.EmbedAllFonts = true;
osf.SubsetFonts = false;
conversionSettings.OutputFormatSpecificSettings = osf;
// ** Carry out the conversion.
Console.WriteLine("Converting file " + sourceFileName + " to PDF/A.");
byte[] convFile = client.ProcessChangesAsync(sourceFile, openOptions, conversionSettings).GetAwaiter().GetResult();
// ** Write the converted file back to the file system with a PDF extension.
string destinationFileName = Path.GetFileNameWithoutExtension(sourceFileName) + "_PDFA.pdf";
using (FileStream fs = File.Create(destinationFileName))
{
fs.Write(convFile, 0, convFile.Length);
fs.Close();
}
Console.WriteLine("File converted to " + destinationFileName);
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.doc*");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to convert and watermark.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = Path.GetExtension(sourceFileName);
// ** Set the absolute minimum conversion settings.
ConversionSettings conversionSettings = new ConversionSettings();
conversionSettings.Fidelity = ConversionFidelities.Full;
conversionSettings.Quality = ConversionQuality.OptimizeForPrint;
// ** Get the list of watermarks to apply.
conversionSettings.Watermarks = CreateWatermarks();
// ** Carry out the conversion.
Console.WriteLine("Converting file " + sourceFileName);
byte[] convFile = client.ConvertAsync(sourceFile, openOptions, conversionSettings).GetAwaiter().GetResult();
// ** Write the converted file back to the file system with a PDF extension.
string destinationFileName = Path.Combine(Path.GetDirectoryName(sourceFileName),
Path.GetFileNameWithoutExtension(sourceFileName) + "." + conversionSettings.Format);
using (FileStream fs = File.Create(destinationFileName))
{
fs.Write(convFile, 0, convFile.Length);
fs.Close();
}
Console.WriteLine("File converted to " + destinationFileName);
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
// ** If nothing is specified then read the first PDF file from the current folder.
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.pdf");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to extract data from.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
byte[] sourceFile = File.ReadAllBytes(sourceFileName);
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
//** Set the absolute minimum open options
OpenOptions openOptions = new OpenOptions();
openOptions.OriginalFileName = Path.GetFileName(sourceFileName);
openOptions.FileExtension = "pdf";
// ** Set the absolute minimum conversion settings
// ** and set output format to XFDF
ConversionSettings conversionSettings = new ConversionSettings();
conversionSettings.Fidelity = ConversionFidelities.Full;
conversionSettings.Format = OutputFormat.XFDF;
// ** Carry out the conversion.
Console.WriteLine("Exporting data from file " + sourceFileName + " to XFDF.");
byte[] convFile = client.ConvertAsync(sourceFile, openOptions, conversionSettings).GetAwaiter().GetResult();
// ** Write the converted file back to the file system with a PDF extension.
string destinationFileName = Path.GetFileNameWithoutExtension(sourceFileName) + ".xfdf";
using (FileStream fs = File.Create(destinationFileName))
{
fs.Write(convFile, 0, convFile.Length);
fs.Close();
}
Console.WriteLine("Data exported to " + destinationFileName);
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
}
static void Main(string[] args)
{
DocumentConverterServiceClient client = null;
try
{
// ** Delete any processed files from a previous run
foreach (FileInfo f in new DirectoryInfo(".").GetFiles("*_ocr.pdf"))
{
f.Delete();
}
// ** Determine the source file and read it into a byte array.
string sourceFileName = null;
if (args.Length == 0)
{
// ** If nothing is specified then read the first PDF file from the current folder.
string[] sourceFiles = Directory.GetFiles(Directory.GetCurrentDirectory(), "*.pdf");
if (sourceFiles.Length > 0)
{
sourceFileName = sourceFiles[0];
}
else
{
Console.WriteLine("Please specify a document to OCR.");
Console.ReadKey();
return;
}
}
else
{
sourceFileName = args[0];
}
// ** Open the service and configure the bindings
client = OpenService(SERVICE_URL);
// ** Specify the various OCR related settings.
ProcessingOptions processingOptions = new ProcessingOptions()
{
// ** Set up array of source files. For OCR we can pass in only a single file at a time.
SourceFiles = new SourceFile[]
{
new SourceFile()
{
// ** Set the binary content
File = File.ReadAllBytes(sourceFileName),
// ** Create absolute minimum OpenOptions
OpenOptions = new OpenOptions()
{
OriginalFileName = Path.GetFileName(sourceFileName),
FileExtension = Path.GetExtension(sourceFileName),
}
}
},
// ** Define OCR settings
OCRSettings = new OCRSettings()
{
// ** Select OCR engine, change this to 'Muhimbi' to use the default Muhimbi OCR engine.
OCREngine = "PrimeOCR",
// ** Set language, keep in mind that different OCR engines support different languages (e.g. in the Muhimbi OCR engine, use 'English', not 'English_UK' / 'English_US'
Language = OCRLanguage.English_UK.ToString(),
// ** Set the desired output, in this case we want the OCRed PDF and OCRed text to be returned separately.
OutputType = OCROutputType.Text | OCROutputType.PDF,
// ** Include PrimeOCR specific properties. These settings cannot be passed into the Muhimbi default OCR engine.
OCREngineSpecificSettings = new OCREngineSpecificSettings_PrimeOCR()
{
// ** Predefined accuracy levels can be used as well as manually defined integer values.
AccuracyLevel = (int)PrimeOCR_AccuracyLevel.Level6,
// ** Set various other parameters
AutoZone = PrimeOCR_AutoZone.NoAutoZone,
Deskew = PrimeOCR_Deskew.On,
ImageProcessingOptions = PrimeOCR_ImageProcessingOptions.Autorotate |
PrimeOCR_ImageProcessingOptions.Deshade |
PrimeOCR_ImageProcessingOptions.Despeck |
PrimeOCR_ImageProcessingOptions.Smooth,
LexicalChecking = PrimeOCR_LexicalChecking.Lexical,
PageQuality = PrimeOCR_PageQuality.NormalQuality,
PrintType = PrimeOCR_PrintType.Machine,
ZoneContent = PrimeOCR_ZoneContent.NoRestrictions
},
}
};
// ** Carry out the operation.
Console.WriteLine("Processing file " + sourceFileName + ".");
BatchResults results = client.ProcessBatch(processingOptions);
// ** Get results. Both textual and PDF
OCRResult ocredText = results.Results[0].OCRResult;
byte[] ocredPdfFile = results.Results[0].File;
// ** Process textual output
if (ocredText != null)
{
// ** Write the text into a txt file
string destFileName = Path.GetFileNameWithoutExtension(sourceFileName) + "_ocr.txt";
File.WriteAllText(destFileName, ocredText.Text);
Console.WriteLine("Text file written to " + destFileName);
// ** Show the file
Console.WriteLine("Launching text file in reader");
Process.Start(destFileName);
}
else
{
Console.WriteLine("No text file was produced.");
}
// ** Process the resulting PDF
if (ocredPdfFile != null)
{
// ** Write the processed file back to the file system with a PDF extension.
string destFileName = Path.GetFileNameWithoutExtension(sourceFileName) + "_ocr.pdf";
File.WriteAllBytes(destFileName, ocredPdfFile);
Console.WriteLine("PDF file written to " + destFileName);
// ** Open the generated PDF file in a PDF Reader
Console.WriteLine("Launching file in PDF Reader");
Process.Start(destFileName);
}
else
{
Console.WriteLine("No PDF file was generated.");
}
}
catch (FaultException <WebServiceFaultException> ex)
{
Console.WriteLine("FaultException occurred: ExceptionType: " +
ex.Detail.ExceptionType.ToString());
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
CloseService(client);
}
Console.ReadKey();
}
