public static bool UpdateOcrRendition(Record record)
{
bool success = false;
string extractedFilePath = string.Empty;
string ocrFilePath = string.Empty;
try
{
// get a temp working location on disk
var rootDirectory = Path.Combine(Path.GetTempPath(), "cmramble_ocr");
if (!Directory.Exists(rootDirectory))
{
Directory.CreateDirectory(rootDirectory);
}
// formulate file name to extract, delete if exists for some reason
extractedFilePath = Path.Combine(rootDirectory, $"{record.Uri}.{record.Extension}");
ocrFilePath = Path.Combine(rootDirectory, $"{record.Uri}.txt");
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
// fetch document
Log.Debug($"Extracting Record {record.Number}: {extractedFilePath}");
record.GetDocument(extractedFilePath, false, "OCR", string.Empty);
// get the OCR text
Log.Debug($"Tesseract Ocr Record {record.Number}: {extractedFilePath}");
ocrFilePath = TesseractOcr.ExtractFromFile(extractedFilePath);
// use record extension method that removes existing OCR rendition (if exists)
record.AddOcrRendition(ocrFilePath);
Log.Debug($"Saving Record {record.Number}");
record.Save();
Log.Debug($"Saved Record {record.Number}");
success = true;
}
catch (Exception ex)
{
Log.Error(ex);
}
finally
{
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
}
return(success);
}
public static bool GenerateOcrRendition(Record record, RecordRendition sourceRendition)
{
bool success = false;
string extractedFilePath = string.Empty;
string ocrFilePath = string.Empty;
try
{
// get a temp working location on disk
var rootDirectory = Path.Combine(Path.GetTempPath(), "cmramble_ocr");
if (!Directory.Exists(rootDirectory))
{
Directory.CreateDirectory(rootDirectory);
}
// formulate file name to extract, delete if exists for some reason
extractedFilePath = Path.Combine(rootDirectory, $"{sourceRendition.Uri}.{sourceRendition.Extension}");
ocrFilePath = Path.Combine(rootDirectory, $"{sourceRendition.Uri}.txt");
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
// fetch document
var extract = sourceRendition.GetExtractDocument();
extract.FileName = Path.GetFileName(extractedFilePath);
extract.DoExtract(Path.GetDirectoryName(extractedFilePath), true, false, "");
if (!String.IsNullOrWhiteSpace(extract.FileName) && File.Exists(extractedFilePath))
{
ocrFilePath = TesseractOcr.ExtractFromFile(extractedFilePath);
// use record extension method that removes existing OCR rendition (if exists)
record.AddOcrRendition(ocrFilePath);
record.Save();
success = true;
}
}
catch (Exception ex)
{
}
finally
{
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
}
return(success);
}
