public override void Run(
)
{
// 1. Opening the PDF file...
string filePath = PromptFileChoice("Please select a PDF file");
using(File file = new File(filePath))
{
Document document = file.Document;
// 2. Text extraction from the document pages.
TextExtractor extractor = new TextExtractor();
foreach(Page page in document.Pages)
{
if(!PromptNextPage(page, false))
{
Quit();
break;
}
IList<ITextString> textStrings = extractor.Extract(page)[TextExtractor.DefaultArea];
foreach(ITextString textString in textStrings)
{
RectangleF textStringBox = textString.Box.Value;
Console.WriteLine(
"Text ["
+ "x:" + Math.Round(textStringBox.X) + ","
+ "y:" + Math.Round(textStringBox.Y) + ","
+ "w:" + Math.Round(textStringBox.Width) + ","
+ "h:" + Math.Round(textStringBox.Height)
+ "]: " + textString.Text
);
}
}
}
}
public override void Run(
)
{
// 1. Opening the PDF file...
string filePath = PromptFileChoice("Please select a PDF file");
using(File file = new File(filePath))
{
// Define the text pattern to look for!
string textRegEx = PromptChoice("Please enter the pattern to look for: ");
Regex pattern = new Regex(textRegEx, RegexOptions.IgnoreCase);
// 2. Iterating through the document pages...
TextExtractor textExtractor = new TextExtractor(true, true);
foreach(Page page in file.Document.Pages)
{
Console.WriteLine("\nScanning page " + (page.Index+1) + "...\n");
// 2.1. Extract the page text!
IDictionary<RectangleF?,IList<ITextString>> textStrings = textExtractor.Extract(page);
// 2.2. Find the text pattern matches!
MatchCollection matches = pattern.Matches(TextExtractor.ToString(textStrings));
// 2.3. Highlight the text pattern matches!
textExtractor.Filter(
textStrings,
new TextHighlighter(page, matches)
);
}
// 3. Highlighted file serialization.
Serialize(file);
}
}
public List<CardCriterion> GetAll()
{
var Ds = new DataSet(); //dummy var to not blow the method
DataRowCollection rows = Ds.Tables[0].Rows;
//Map all Database Rows To DataModels. Add each Model to Dict.
List<CardCriterion> cardCriteria = new List<CardCriterion>(rows.Count);
#region Linq
//cardCriteria.AddRange(from DataRow row in Ds.Tables[0].Rows
// select row.ItemArray
// into values
// let textExtractor = new TextExtractor()
// select
// new CardCriterion()
// {
// CardId = Convert.ToInt16(values[0]),
// Territory = Convert.ToString(values[1]),
// CardKind = Convert.ToString(values[2]),
// CardAdoptionKindSubject = Convert.ToString(values[3]),
// CardAdoptionSubject = Convert.ToString(values[4]),
// CardName = Convert.ToString(values[5]),
// CardEdition = textExtractor.Extract((byte[]) values[6]).Text,
// ContentMetadataDict = textExtractor.Extract((byte[]) values[6]).Metadata,
// ContentType = textExtractor.Extract((byte[]) values[6]).ContentType
// });
#endregion
foreach (DataRow row in rows)
{
var criterion = new CardCriterion();
object[] values = row.ItemArray;
var textExtractionResult = new TextExtractor().Extract((byte[]) values[7]);
criterion.EditionId = Convert.ToUInt32(values[0]);
criterion.Territory = Convert.ToString(values[1]);
criterion.CardKind = Convert.ToString(values[2]);
criterion.CardAdoptionKindSubject = Convert.ToString(values[3]);
criterion.CardAdoptionSubject = Convert.ToString(values[4]);
criterion.CardName = Convert.ToString(values[5]);
criterion.CardAdoptionDate = Convert.ToDateTime(values[6]);
criterion.CardEdition = textExtractionResult.Text;
criterion.ContentMetadataDict = textExtractionResult.Metadata;
criterion.CardAdoptionNumber = Convert.ToString(values[8]);
cardCriteria.Add(criterion);
Function(1, rows.Count);
//http://stackoverflow.com/questions/6471378/implementing-a-progress-bar-to-show-work-being-done
}
return cardCriteria;
//http://codereview.stackexchange.com/questions/30714/faster-way-to-convert-datatable-to-list-of-class
}
public ActionResult CountStatistics([FromBody] string fileName)
{
List <string> extractedText = new List <string>();
string filePath = Server.MapPath("../App_Data//Uploads//" + fileName);
try
{
string[] arguments = new string[] { filePath };
int maxWordLength = 0;
for (int i = 0; i < arguments.Length; i++)
{
if (arguments[i].Length == 1 || !int.TryParse(arguments[i], out maxWordLength))
{
maxWordLength = 5;
}
}
ExtractorFactory factory = new ExtractorFactory();
Dictionary <string, int> statistic = new Dictionary <string, int>();
TextExtractor extractor = factory.CreateTextExtractor(filePath);
if (extractor == null)
{
extractedText.Add("The document's format is not supported");
}
try
{
string line = null;
do
{
line = extractor.ExtractLine();
if (line != null)
{
string[] words = line.Split(' ', ',', ';', '.');
foreach (string w in words)
{
string word = w.Trim().ToLower();
if (word.Length > maxWordLength)
{
if (!statistic.ContainsKey(word))
{
statistic[word] = 0;
}
statistic[word]++;
}
}
}
}while (line != null);
}
finally
{
extractor.Dispose();
}
extractedText.Add("Top words:");
for (int i = 0; i < 10; i++)
{
int count = -1;
string maxKey = null;
foreach (string key in statistic.Keys)
{
if (statistic[key] > count)
{
count = statistic[key];
maxKey = key;
}
}
if (maxKey == null)
{
break;
}
extractedText.Add(maxKey + " : " + count);
statistic.Remove(maxKey);
}
}
catch (Exception ex)
{
extractedText.Add(ex.Message);
}
return(Json(extractedText, JsonRequestBehavior.AllowGet));
}
private List<string> ExtractPageList(Document document)
{
// extract page list
List<string> pageList = new List<string>();
TextExtractor textExtractor = new TextExtractor();
try {
foreach (var page in document.Pages)
{
var textStrings = textExtractor.Extract(page);
string pageContent = TextExtractor.ToString(textStrings);
//string[] ssize = content.Split(null); // splits by whitespace
pageList.Add(pageContent);
}
}
catch (Exception e)
{
Utility.Log("Blad");
}
return pageList;
}
private static CardCriterion _extractRowToCriterion(IDataRecord record)
{
CardCriterion criterion = new CardCriterion();
var textExtractionResult = new TextExtractor().Extract((byte[]) record[5]);
criterion.EditionId = Convert.ToUInt32(record[0]);
criterion.CardId = Convert.ToUInt32(record[1]);
criterion.Territory = Convert.ToString(record[2]);
criterion.CardKind = Convert.ToString(record[3]);
criterion.CardName = Convert.ToString(record[4]);
criterion.CardEdition = textExtractionResult.Text;
criterion.ContentMetadataDict = textExtractionResult.Metadata;
criterion.FileExt = Convert.ToString(record[6]);
criterion.CardAdoptionKindSubject = Convert.ToString(record[7]);
criterion.CardAdoptionSubject = Convert.ToString(record[8]);
criterion.CardAdoptionDate = Convert.ToDateTime(record[9]);
criterion.CardAdoptionNumber = Convert.ToString(record[10]);
return criterion;
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
// Automatically deskew skewed scans
//extractor.OCRImagePreprocessingFilters.AddDeskew();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentation errors)
//extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover();
//extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Repair broken letters
//extractor.OCRImagePreprocessingFilters.AddDilate();
// Remove noise
//extractor.OCRImagePreprocessingFilters.AddMedian();
// Apply Gamma Correction
//extractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// Add Contrast
//extractor.OCRImagePreprocessingFilters.AddContrast(20);
// (!) You can use new OCRAnalyser class to find an optimal set of image preprocessing
// filters for your specific document.
// See "OCR Analyser" example.
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
public void TestExtractMethodWithInvalidFile()
{
Assert.ThrowsException <NotSupportedException>(
() => TextExtractor.Extract(@"Documents\Invalid.docx")
);
}
public void TestIsValidFileTypeMethodWithMissingStream()
{
Assert.IsFalse(TextExtractor.IsValidFileType(new MemoryStream()));
}
public void TestIsValidFileTypeMethodWithUndefinedBytes()
{
Assert.ThrowsException <ArgumentNullException>(
() => TextExtractor.IsValidFileType((byte[])null)
);
}
public void TestExtractMethodWithUndefinedFile()
{
Assert.ThrowsException <ArgumentNullException>(
() => TextExtractor.Extract((string)null)
);
}
public override ApiResult Init()
{
Extractor = new TextExtractor();
return(SetInitializedStatusAndReturnSucces());
}
public WordStatistic(string fileName, int maxWordLength)
{
//ExStart:WordStatistic
ExtractorFactory factory = new ExtractorFactory();
Dictionary <string, int> statistic = new Dictionary <string, int>();
TextExtractor extractor = factory.CreateTextExtractor(fileName);
if (extractor == null)
{
Console.WriteLine("The document's format is not supported");
return;
}
try
{
string line = null;
do
{
line = extractor.ExtractLine();
if (line != null)
{
string[] words = line.Split(' ', ',', ';', '.');
foreach (string w in words)
{
string word = w.Trim().ToLower();
if (word.Length > maxWordLength)
{
if (!statistic.ContainsKey(word))
{
statistic[word] = 0;
}
statistic[word]++;
}
}
}
}while (line != null);
}
finally
{
extractor.Dispose();
}
Console.WriteLine("Top words:");
for (int i = 0; i < 10; i++)
{
int count = -1;
string maxKey = null;
foreach (string key in statistic.Keys)
{
if (statistic[key] > count)
{
count = statistic[key];
maxKey = key;
}
}
if (maxKey == null)
{
break;
}
Console.WriteLine("{0}: {1}", maxKey, count);
statistic.Remove(maxKey);
}
//ExEnd:WordStatistic
}
public ActionResult ExtractText([FromBody] string fileName, string password = null)
{
//ExStart:ExtractText
ExtractorFactory factory = new ExtractorFactory();
string path = Server.MapPath("../App_Data//Uploads//" + fileName);
string ext = Path.GetExtension(path);
List <string> extractedText = new List <string>();
try
{
string line = null;
//If file password procted
if (!string.IsNullOrWhiteSpace(password))
{
if (ext == ".one")
{
var loadOptions = new LoadOptions();
loadOptions.Password = password;
using (var extractor = new NoteTextExtractor(path, loadOptions))
{
do
{
int lineNumber = 0;
do
{
line = extractor.ExtractLine();
lineNumber++;
if (line != null)
{
extractedText.Add(line);
}
}while (line != null);
}while (line != null);
}
}
else
{
LoadOptions loadOptions = new LoadOptions();
loadOptions.Password = password;
WordsTextExtractor protectedDocument = new WordsTextExtractor(path, loadOptions);
do
{
int lineNumber = 0;
do
{
line = protectedDocument.ExtractLine();
lineNumber++;
if (line != null)
{
extractedText.Add(line);
}
}while (line != null);
}while (line != null);
}
}
else
{
//if file type is zip
if (ext == ".zip")
{
using (var container = new ZipContainer(path))
{
for (int i = 0; i < container.Entities.Count; i++)
{
using (TextExtractor extractor = factory.CreateTextExtractor(container.Entities[i].OpenStream()))
{
int lineNumber = 0;
do
{
line = extractor.ExtractLine();
lineNumber++;
if (line != null)
{
extractedText.Add(line);
}
}while (line != null);
}
}
}
}
else
{
TextExtractor extractor = factory.CreateTextExtractor(path);
do
{
int lineNumber = 0;
do
{
try
{
line = extractor.ExtractLine();
}
catch (Exception)
{
if (ext == ".one")
{
extractedText.Add("Invalid password");
break;
}
}
lineNumber++;
if (line != null)
{
extractedText.Add(line);
}
}while (line != null);
}while (line != null);
}
}
//extractedText.Add(extractor.ExtractAll());
}
catch (Exception ex)
{
extractedText.Add(ex.Message);
}
return(Json(extractedText, JsonRequestBehavior.AllowGet));
}
public void TestExtractMethodWithMissingBytes()
{
Assert.ThrowsException <NotSupportedException>(
() => TextExtractor.Extract(new byte[] { })
);
}
public void TestIsValidFileTypeMethodWithMissingBytes()
{
Assert.IsFalse(TextExtractor.IsValidFileType(new byte[] { }));
}
public void TestExtractMethodWithMissingFile()
{
Assert.ThrowsException <FileNotFoundException>(
() => TextExtractor.Extract(string.Empty)
);
}
public void TestIsValidFileTypeMethodWithMissingFile()
{
Assert.ThrowsException <FileNotFoundException>(
() => TextExtractor.IsValidFileType(string.Empty)
);
}
public void TestExtractMethodWithValidFileWithWhitespacePreserveFile()
{
var text = TextExtractor.Extract(@"Documents\ValidWithWhitespacePreserve.docx");
Assert.IsTrue(text == "This is a Word document.");
}
public void TestExtractMethodWithUndefinedStream()
{
Assert.ThrowsException <ArgumentNullException>(
() => TextExtractor.Extract((Stream)null)
);
}
static void Main(string[] args)
{
// Create TextExtractor instance
TextExtractor textExtractor = new TextExtractor("demo", "demo");
textExtractor.WordMatchingMode = WordMatchingMode.ExactMatch; // Set exact search (default is SmartSearch that works like in Adobe Reader)
// Create XMLExtractor instance
XMLExtractor xmlExtractor = new XMLExtractor("demo", "demo");
// Load document
textExtractor.LoadDocumentFromFile("Invoice.pdf");
xmlExtractor.LoadDocumentFromFile("Invoice.pdf");
// Results
string invoiceNo = string.Empty;
string invoiceDate = string.Empty;
string total = string.Empty;
string tableData = string.Empty;
// Iterate pages
for (int i = 0; i < textExtractor.GetPageCount(); i++)
{
RectangleF pageRectangle = textExtractor.GetPageRectangle(i);
RectangleF tableRect = new RectangleF(0, 0, pageRectangle.Width, 0);
// Search for "Invoice No."
if (textExtractor.Find(i, "Invoice No.", false))
{
// Get the found text rectangle
RectangleF textRect = textExtractor.FoundText.Bounds;
// Assume the text at right is the invoice number.
// Shift the rectangle to the right:
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
// Set the extraction region and extract the text
textExtractor.SetExtractionArea(textRect);
invoiceNo = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Invoice Date" and extract text at right
if (textExtractor.Find(i, "Invoice Date", false))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
invoiceDate = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Quantity" keyword to detect the top of the tabular data rectangle
if (textExtractor.Find(i, "Quantity", false))
{
// Keep the top table coordinate
tableRect.Y = textExtractor.FoundText.Bounds.Top; // use textRect.Bottom if you want to skip column headers
}
// Search for "TOTAL" (it will be also the bottom of tabular data rectangle)
if (textExtractor.Find(i, "TOTAL", true /* case sensitive! */))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
total = textExtractor.GetTextFromPage(i).Trim();
// Calculate the table height
tableRect.Height = textRect.Top - tableRect.Top;
}
// Extract tabular data using XMLExtractor
if (tableRect.Height > 0)
{
xmlExtractor.SetExtractionArea(tableRect);
tableData = xmlExtractor.GetXMLFromPage(i);
}
}
// Display extracted data
Console.WriteLine("Invoice No.: " + invoiceNo);
Console.WriteLine("Invoice Date: " + invoiceDate);
Console.WriteLine("TOTAL: " + total);
Console.WriteLine("Table Data: ");
Console.WriteLine(tableData);
Console.WriteLine("Press any key...");
Console.ReadKey();
}
public void TestIsValidFileTypeMethodWithInvalidFile()
{
Assert.IsFalse(TextExtractor.IsValidFileType(@"Documents\Invalid.docx"));
}
public override void Run(
)
{
// 1. Opening the PDF file...
string filePath = PromptFileChoice("Please select a PDF file");
using(files::File file = new files::File(filePath))
{
Document document = file.Document;
// 2. Link extraction from the document pages.
TextExtractor extractor = new TextExtractor();
extractor.AreaTolerance = 2; // 2 pt tolerance on area boundary detection.
bool linkFound = false;
foreach(Page page in document.Pages)
{
if(!PromptNextPage(page, !linkFound))
{
Quit();
break;
}
IDictionary<RectangleF?,IList<ITextString>> textStrings = null;
linkFound = false;
// Get the page annotations!
PageAnnotations annotations = page.Annotations;
if(!annotations.Exists())
{
Console.WriteLine("No annotations here.");
continue;
}
// Iterating through the page annotations looking for links...
foreach(Annotation annotation in annotations)
{
if(annotation is Link)
{
linkFound = true;
if(textStrings == null)
{textStrings = extractor.Extract(page);}
Link link = (Link)annotation;
RectangleF linkBox = link.Box;
// Text.
/*
Extracting text superimposed by the link...
NOTE: As links have no strong relation to page text but a weak location correspondence,
we have to filter extracted text by link area.
*/
StringBuilder linkTextBuilder = new StringBuilder();
foreach(ITextString linkTextString in extractor.Filter(textStrings,linkBox))
{linkTextBuilder.Append(linkTextString.Text);}
Console.WriteLine("Link '" + linkTextBuilder + "' ");
// Position.
Console.WriteLine(
" Position: "
+ "x:" + Math.Round(linkBox.X) + ","
+ "y:" + Math.Round(linkBox.Y) + ","
+ "w:" + Math.Round(linkBox.Width) + ","
+ "h:" + Math.Round(linkBox.Height)
);
// Target.
Console.Write(" Target: ");
PdfObjectWrapper target = link.Target;
if(target is Destination)
{PrintDestination((Destination)target);}
else if(target is actions::Action)
{PrintAction((actions::Action)target);}
else if(target == null)
{Console.WriteLine("[not available]");}
else
{Console.WriteLine("[unknown type: " + target.GetType().Name + "]");}
}
}
if(!linkFound)
{
Console.WriteLine("No links here.");
continue;
}
}
}
}
public void TestIsValidFileTypeMethodWithValidFile()
{
Assert.IsTrue(TextExtractor.IsValidFileType(@"Documents\Valid.docx"));
}
private void btInput_Click(object sender, EventArgs e)
{
if (rbFromFile.Checked)
{
openFileDialog.Filter = "IFO Files (*.ifo)|*.ifo|MPLS Files (*.mpls)|*.mpls|Text Files (*.txt)|*.txt|All Files supported (*.ifo,*.mpls,*.txt)|*.ifo;*.mpls;*.txt";
openFileDialog.FilterIndex = 4;
if (this.openFileDialog.ShowDialog() == DialogResult.OK)
{
input.Text = openFileDialog.FileName;
if (input.Text.ToLower().EndsWith("ifo"))
{
ChapterExtractor ex = new IfoExtractor();
pgc = ex.GetStreams(input.Text)[0];
FreshChapterView();
updateTimeLine();
}
else if (input.Text.ToLower().EndsWith("mpls"))
{
ChapterExtractor ex = new MplsExtractor();
pgc = ex.GetStreams(input.Text)[0];
FreshChapterView();
updateTimeLine();
}
else
{
ChapterExtractor ex = new TextExtractor();
pgc = ex.GetStreams(input.Text)[0];
FreshChapterView();
updateTimeLine();
}
}
}
else
{
using (FolderBrowserDialog d = new FolderBrowserDialog())
{
d.ShowNewFolderButton = false;
d.Description = "Select DVD, BluRay disc, or folder.";
if (d.ShowDialog() == DialogResult.OK)
{
input.Text = d.SelectedPath;
try
{
ChapterExtractor ex =
Directory.Exists(Path.Combine(input.Text, "VIDEO_TS")) ?
new DvdExtractor() as ChapterExtractor :
Directory.Exists(Path.Combine(Path.Combine(input.Text, "BDMV"), "PLAYLIST")) ?
new BlurayExtractor() as ChapterExtractor :
null;
if (ex == null)
throw new Exception("The location was not detected as DVD, or Blu-Ray.");
using (frmStreamSelect frm = new frmStreamSelect(ex))
{
if (ex is DvdExtractor)
frm.Text = "Select your PGC";
else
frm.Text = "Select your Playlist";
ex.GetStreams(input.Text);
if (frm.ShowDialog(this) == DialogResult.OK)
{
pgc = frm.ProgramChain;
if (pgc.FramesPerSecond == 0) pgc.FramesPerSecond = 25.0;
if (pgc.LangCode == null) pgc.LangCode = "und";
}
}
FreshChapterView();
updateTimeLine();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
}
}
if (chapterListView.Items.Count != 0)
chapterListView.Items[0].Selected = true;
}
public void TestExtractMethodWithUndefinedBytes()
{
Assert.ThrowsException <ArgumentNullException>(
() => TextExtractor.Extract((byte[])null)
);
}
public virtual void SetUp()
{
_cut = new TextExtractor();
}
public void TestExtractMethodWithMissingStream()
{
Assert.ThrowsException <NotSupportedException>(
() => TextExtractor.Extract(new MemoryStream())
);
}
private void button3_Click(object sender, EventArgs e)
{
timer1.Stop();
button5.Text = "P L A Y";
OpenFileDialog dlg = new OpenFileDialog();
string filepath;
dlg.Filter = "Text files(*.txt)|*.txt|Doc files(*.doc)|*.doc|Docx files(*.docx)|*.docx|All files(*.*)|*.*";
if (dlg.ShowDialog() == DialogResult.OK)
{
filepath = dlg.FileName.ToString();
string strText = string.Empty;
try
{
string ext = System.IO.Path.GetExtension(dlg.FileName);
if (ext == ".doc" || ext == ".docx")
{
Code7248.word_reader.TextExtractor extractor = new TextExtractor(dlg.FileName);
string contents = extractor.ExtractText();
MyText.Text = contents;
}
else
{
MyText.Text = File.ReadAllText(dlg.FileName);
}
MyText.Text = MyText.Text.Replace("\t", " ");
MyText.Text = MyText.Text.Replace(Environment.NewLine, "\n");
if (mychar == '\n')
{
MyText.Text = MyText.Text.Replace("\n", " ");
}
string nolstrTextine = MyText.Text.Replace("\n", System.Convert.ToString(mychar));
i = 0;
if (mychar == '\n')
{
nolstrTextine = nolstrTextine.Replace(".", ". " + mychar);
}
words = nolstrTextine.Split(new char[] { mychar }, StringSplitOptions.RemoveEmptyEntries); ;
progressBar1.Maximum = words.Length;
timer1.Stop();
button5.Text = "P L A Y";
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
}
static void Main(string[] args)
{
try
{
// Files
string fileName = "hindi_text_with_image.pdf";
string destFileName = "output_hindi_text_with_image.pdf";
string destFileName_serachable = "output_hindi_text_with_image_searchable.pdf";
// Read all text from pdf file
string allTextExtracted = "";
using (TextExtractor extractor = new TextExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile(fileName);
// Read all text directly
allTextExtracted = extractor.GetText();
}
// Get image from pdf file
MemoryStream memoryStream = new MemoryStream();
using (ImageExtractor extractor = new ImageExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile(fileName);
if (extractor.GetFirstImage())
{
extractor.SaveCurrentImageToStream(memoryStream, ImageFormat.Png);
}
}
// Load image from file to System.Drawing.Image object (we need it to get the image resolution)
using (System.Drawing.Image sysImage = System.Drawing.Image.FromStream(memoryStream))
{
// Compute image size in PDF units (Points)
float widthInPoints = sysImage.Width / sysImage.HorizontalResolution * 72f;
float heightInPoints = sysImage.Height / sysImage.VerticalResolution * 72f;
// Create new PDF document
using (Document outPdfDocument = new Document())
{
outPdfDocument.RegistrationName = "demo";
outPdfDocument.RegistrationKey = "demo";
// Create page of computed size
Page page = new Page(widthInPoints, heightInPoints);
// Add page to the document
outPdfDocument.Pages.Add(page);
Canvas canvas = page.Canvas;
// Create Bytescout.PDF.Image object from loaded image
Image pdfImage = new Image(sysImage);
// Draw the image
canvas.DrawImage(pdfImage, 0, 0, widthInPoints, heightInPoints);
// Dispose the System.Drawing.Image object to free resources
sysImage.Dispose();
// Create brush
SolidBrush transparentBrush = new SolidBrush(new ColorGray(0));
// ... and make it transparent
transparentBrush.Opacity = 0;
// Draw text with transparent brush
// Need to set Font which supports hindi characters.
Font font16 = new Font("Arial Unicode MS", 16);
canvas.DrawString(allTextExtracted, font16, transparentBrush, 40, 40);
// Save document to file
outPdfDocument.Save(destFileName);
}
}
// Make PDF file with hindi text searchable to OCR.
using (SearchablePDFMaker searchablePDFMaker = new SearchablePDFMaker())
{
//Load PDF document
searchablePDFMaker.LoadDocumentFromFile(destFileName);
// Set the location of "tessdata" folder containing language data files
/*
* It used following files for hindi language support. Need to put these files into "testdata" folder. Below location contains these files.
* https://github.com/tesseract-ocr/tessdata/tree/3.04.00
* hin.traineddata
* hin.cube.bigrams
* hin.cube.lm
* hin.cube.nn
* hin.cube.params
* hin.cube.word-freq
* hin.tesseract_cube.nn
*/
searchablePDFMaker.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\Redistributable\net2.00\tessdata\";
// Set OCR language
searchablePDFMaker.OCRLanguage = "hin";
// Need to set Font which supports hindi characters
searchablePDFMaker.LabelingFont = "Arial Unicode MS";
// Set PDF document rendering resolution
searchablePDFMaker.OCRResolution = 300;
searchablePDFMaker.MakePDFSearchable(destFileName_serachable);
}
// Open document in default PDF viewer app
Process.Start(destFileName_serachable);
}
catch (Exception ex)
{
Console.WriteLine("ERROR:" + ex.Message);
}
Console.ReadLine();
}
