public DocumentLogEvent(TextArtifact artifact) : base(artifact)
{
PotentialSensitiveData = artifact.HasSensitiveData ? artifact.SensitiveData.Values.Aggregate((p, n) => p + "," + n) : "";
CompetitorsNamePresent = artifact.CompetitorNamesPresent.Count > 0 ? artifact.CompetitorNamesPresent.Aggregate((p, n) => p + "," + n) : "";
KeyWords = string.Join(",", artifact.KeyWords.ToArray());
Entities = string.Join(",", artifact.Entities.ToArray());
UserOp = artifact.HasFileSource ? (artifact.Source as FileArtifact).UserOp.ToString() : string.Empty;
Global.Logger.Debug("Created Azure Log Analytics log event {0} for text artifact {1} from user op {2} at {3}.", Name, artifact.Id, UserOp, DateTime.Now);
}
protected override ApiResult ProcessClientQueueMessage(ImageArtifact message)
{
BitmapData bData = message.Image.LockBits(
new Rectangle(0, 0, message.Image.Width, message.Image.Height), ImageLockMode.ReadOnly, message.Image.PixelFormat);
int w = bData.Width, h = bData.Height, bpp = Image.GetPixelFormatSize(bData.PixelFormat) / 8;
unsafe
{
TesseractImage.SetImage(new UIntPtr(bData.Scan0.ToPointer()), w, h, bpp, bData.Stride);
}
Pix = TesseractImage.GetInputImage();
Debug("Pix has width: {0} height: {1} depth: {2} xres: {3} yres: {4}.", Pix.Width, Pix.Height, Pix.Depth,
Pix.XRes, Pix.YRes);
List <string> text;
using (var op = Begin("Tesseract OCR (fast)"))
{
TesseractImage.Recognize();
ResultIterator resultIterator = TesseractImage.GetIterator();
text = new List <string>();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
string r = resultIterator.GetUTF8Text(pageIteratorLevel);
if (r.IsEmpty())
{
continue;
}
text.Add(r.Trim());
}while (resultIterator.Next(pageIteratorLevel));
if (text.Count > 0)
{
string alltext = text.Aggregate((s1, s2) => s1 + " " + s2).Trim();
if (text.Count < 7)
{
Info("Artifact id {0} is likely a photo or non-text image.", message.Id);
}
else
{
message.OCRText = text;
Info("OCR Text: {0}", alltext);
}
}
else
{
Info("No text recognized in artifact id {0}.", message.Id);
}
op.Complete();
}
message.Image.UnlockBits(bData);
if (text.Count >= 7)
{
TextArtifact artifact = new TextArtifact(message.Name + ".txt", text);
EnqueueMessage(artifact);
Info("{0} added artifact id {1} of type {2} from artifact {3}.", Name, artifact.Id, artifact.GetType(),
message.Id);
}
return(ApiResult.Success);
}
protected override ApiResult ProcessClientQueueMessage(ImageArtifact message)
{
BitmapData bData = message.Image.LockBits(
new Rectangle(0, 0, message.Image.Width, message.Image.Height), ImageLockMode.ReadOnly, message.Image.PixelFormat);
int w = bData.Width, h = bData.Height, bpp = Image.GetPixelFormatSize(bData.PixelFormat) / 8;
unsafe
{
TesseractImage.SetImage(new UIntPtr(bData.Scan0.ToPointer()), w, h, bpp, bData.Stride);
}
Pix = TesseractImage.GetInputImage();
Debug("Pix has width: {0} height: {1} depth: {2} xres: {3} yres: {4}.", Pix.Width, Pix.Height, Pix.Depth,
Pix.XRes, Pix.YRes);
List <string> text;
using (var op = Begin("Tesseract OCR (fast)"))
{
TesseractImage.Recognize();
ResultIterator resultIterator = TesseractImage.GetIterator();
text = new List <string>();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
string ant = TextArtifact.GetAlphaNumericString(resultIterator.GetUTF8Text(pageIteratorLevel));
ant = string.Join(" ",
ant.Split(new[] { ' ', '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries)
.Where(word => TextArtifact.IsNumber(word) || word.Length > 3 || Pipeline.Dictionaries["common_words_en_3grams"].Contains(word)))
.Trim();
if (ant.IsEmpty())
{
continue;
}
else
{
text.Add(ant);
}
}while (resultIterator.Next(pageIteratorLevel));
if (text.Count > 0)
{
string alltext = text.Aggregate((s1, s2) => s1 + " " + s2).Trim();
if (text.Count < 7)
{
Info("Artifact id {0} is likely a photo or non-text image.", message.Id);
}
else
{
message.OCRText = text;
Info("OCR Text: {0}", alltext);
}
}
else
{
Info("No text recognized in artifact id {0}.", message.Id);
}
op.Complete();
}
message.Image.UnlockBits(bData);
if (text.Count >= 7)
{
TextArtifact artifact = new TextArtifact(message.Name + ".txt", string.Join(Environment.NewLine, text.ToArray()));
artifact.Source = message.Source;
artifact.CurrentProcess = message.CurrentProcess;
artifact.CurrentWindowTitle = message.CurrentWindowTitle;
artifact.Image = message;
message.TextArtifact = artifact;
EnqueueMessage(artifact);
Info("{0} added artifact id {1} of type {2} from artifact {3}.", Name, artifact.Id, artifact.GetType(),
message.Id);
}
return(ApiResult.Success);
}
