private static String GetPdfContent(string path)
{
var text = new StringBuilder();
using (var pdfReader = new PdfReader(path))
{
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy(); // LocationTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(
pdfReader,
page,
strategy);
currentText =
Encoding.UTF8.GetString(Encoding.Convert(
Encoding.Default,
Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
}
return text.ToString();
}
public static string ExtractTextFromPdf(string path)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
using (PdfReader reader = new PdfReader(path))
{
StringBuilder text = new StringBuilder();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(reader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
System.IO.StreamWriter file = new System.IO.StreamWriter("c:\\test.txt");
file.WriteLine(text);
file.Close();
return text.ToString();
}
}
//[Dependency]
//public IF0413Repository F0413Repository { get; set; }
//[Dependency]
//public IF0413Business F0413Business { get; set; }
//[Dependency]
//public IF0414Business F0414Business { get; set; }
public String BuscarDatosPdf(string nombreArchivo)
{
/*path = path + “/ extjs.pdf”;
* string salida = ReadPdfFile(path);
*
* y luego defino el método*/
try
{
PdfReader reader2 = new PdfReader(nombreArchivo);
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader(nombreArchivo);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
reader2.Close();
return(strText);
}
catch (IOException ex)
{
throw new ExportException("Error: No se encuentra el archivo o recurso: " + nombreArchivo + ". --> Traza Original: " + ex.StackTrace);
}
}
private int searchThroughFile(string path)
{
int count = 0;
string[] temp = null;
using (PdfReader reader = new PdfReader(path))
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
string text = null;
try
{
text = (PdfTextExtractor.GetTextFromPage(reader, i, its));
}
catch (Exception e)
{
}
if (text != null && text.Contains(word))
{
count++;
text = null;
}
}
}
return(count);
}
//Este metodo lee el PDF
public string ReadPdfFile(object Filename)
{
string strText = string.Empty;
//try para obtener el error en caso de que ocurra
try
{
PdfReader readerPdf = new PdfReader((string)Filename);
for (int page = 1; page <= readerPdf.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader((string)Filename);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
}
//Manejo de errores
catch (Exception ex)
{
//Muestro el error en caso de que ocurra
lblMsjs.ForeColor = Color.Crimson;
lblMsjs.Text = ex.Message.ToString();
}
//retorno el texto
return(strText);
}
private List <InvoiceItem> GetFaturaItems(string fileName)
{
var result = new List <InvoiceItem>();
try
{
PdfReader reader = new PdfReader(fileName);
var its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String rawTextV = PdfTextExtractor.GetTextFromPage(reader, 1, its);
var pageVencimento = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(rawTextV)));
var vencimento = GetVencimento(pageVencimento);
for (int pageNumber = 1; pageNumber < reader.NumberOfPages + 1; pageNumber++)
{
its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String rawText = PdfTextExtractor.GetTextFromPage(reader, pageNumber, its);
var page = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(rawText)));
result.AddRange(ParsePage(page, vencimento));
}
reader.Close();
}
catch (Exception)
{
//TODO: Bug Hidden
}
return(result);
}
public string ReadTextPDF(string path)
{
try
{
PdfReader reader = new PdfReader(path);
int numberPage = reader.NumberOfPages;
StringBuilder textPages = new StringBuilder();
for (int i = 0; i < numberPage; i++)
{
ITextExtractionStrategy textExtractionStrategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
string textPage = PdfTextExtractor.GetTextFromPage(reader, i + 1, textExtractionStrategy);
textPage = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(textPage)));
textPages.Append(textPage);
}
reader.Close();
string txt = textPages.ToString();
return(txt);
}
catch (Exception ex)
{
throw new Exception(ex.Message);
}
}
public String readTextData(String readText)
{
String str = null;
if (readText.Substring(readText.Length - 3, 3).Equals("pdf"))
{
PdfReader reader = new PdfReader((string)readText);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
str = str + s;
}
reader.Close();
}
else
{
str = System.IO.File.ReadAllText(@readText);
}
str.Replace("\n", " ");
return(str);
}
protected void Page_Load(object sender, EventArgs e)
{
string firstLine = null;
string strText = null;
String str = Request.QueryString["file"];
PdfReader reader = new PdfReader(Server.MapPath("Uploads\\Documents") + "\\" + str);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String s = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, page, its);
strText = strText + s;
//string firstLine = string.Empty;
if (s.Contains("\n"))
{
firstLine += s.Split('\n')[1] + "<br>";
}
else
{
firstLine += s;
}
continue;
}
divMainContent.InnerHtml = firstLine;
reader.Close();
}
public static void ExtractText(string sourceFilePath, string destinationPath)
{
var text = new StringBuilder();
var pdfReader = new PdfReader(sourceFilePath);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(
Encoding.Convert(
Encoding.Default,
Encoding.UTF8,
Encoding.Default.GetBytes(currentText))
);
text.Append(currentText);
}
pdfReader.Close();
var temp = text.ToString();
var regexp = new Regex(@"[ ]{2,}", RegexOptions.None);
temp = regexp.Replace(temp, @" ");
temp = Regex.Replace(temp, @"^\s+$[\r\n]*", "", RegexOptions.Multiline);
File.WriteAllText(destinationPath, temp);
}
public IDictionary <int, string> LeerPdf()
//Metodo que lee y devuelve el contenido de un archivo Pdf
{
Dictionary <int, string> datosPdf = new Dictionary <int, string>();
PdfReader archivo = new PdfReader(this.rutaArchivo);
string strText = string.Empty;
for (int pagina = 1; pagina <= archivo.NumberOfPages; pagina++)
{
ITextExtractionStrategy conte = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader lectura = new PdfReader(this.rutaArchivo);
string s = PdfTextExtractor.GetTextFromPage(lectura, pagina, conte);
s = System.Text.Encoding.UTF8.GetString(ASCIIEncoding.Convert(System.Text.Encoding.Default, System.Text.Encoding.UTF8,
System.Text.Encoding.Default.GetBytes(s)));
strText = strText + s;
datosPdf.Add(pagina, strText);
lectura.Close();
}
return(datosPdf);
}
/************************** FINAL *****************************/
public string pdf2Text(string pdfFile)
{
PdfReader reader = new PdfReader(pdfFile);
//ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
string txt = "";
int pages = reader.NumberOfPages;
for (int page = 1; page <= reader.NumberOfPages; page++)
{
txt = PdfTextExtractor.GetTextFromPage(reader, page, its);
txt = txt.Replace("\n", " ");
// Replace multi spaces with single
RegexOptions options = RegexOptions.None;
Regex regex = new Regex("[ ]{2,}", options);
txt = regex.Replace(txt, " ");
Console.WriteLine("Slide #" + page + "\n-----------------------\n" + txt + "\n-----------------------\n");
}
// txt = txt.Replace("\n", " ").Replace(" ", " "); ;
return(txt);
}
private static IEnumerable<string> GetLinesFrom(PdfReader pdfReader)
{
var strategy = new SimpleTextExtractionStrategy();
return Enumerable
.Range(1, pdfReader.NumberOfPages)
.Select(p => PdfTextExtractor.GetTextFromPage(pdfReader, p, strategy));
}
public static String Extract(String url, String saveTo = null)
{
try
{
WebClient wc = new WebClient();
byte[] data = wc.DownloadData(url);
// 如果设置了保存到文件，则写入文件
if (!String.IsNullOrWhiteSpace(saveTo) && data != null && data.Length > 0)
{
if (!Directory.Exists(saveTo))
{
Directory.CreateDirectory(saveTo);
}
String file = GeneratePath(saveTo, url);
try
{
using (FileStream fs = new FileStream(file, FileMode.CreateNew))
{
fs.Write(data, 0, data.Length);
}
}
catch (IOException ioe)
{
}
}
using (PdfReader reader = new PdfReader(data))
{
try
{
StringBuilder sb = new StringBuilder();
ITextExtractionStrategy extract = new SimpleTextExtractionStrategy();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
sb.Append(PdfTextExtractor.GetTextFromPage(reader, i, extract));
reader.ReleasePage(i);
}
return sb.ToString();
}
finally
{
if (reader != null)
{
reader.Close();
}
}
}
}
catch (Exception e)
{
return String.Empty;
}
}
/**
* Parses the PDF using PRTokeniser
* @param src the path to the original PDF file
* @param dest the path to the resulting text file
*/
public string[] parsePdfToHtml(string src)
{
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(src);
//StreamWriter output = new StreamWriter();
SimpleTextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
List<string> text = new List<string>(); ;
int pageCount = reader.NumberOfPages;
for (int pg = 1; pg <= pageCount; pg++)
{
text.Add(PdfTextExtractor.GetTextFromPage(reader, pg, strategy));
}
return text.ToArray();
}
/// <summary>
/// function to read and process pdf file
/// </summary>
/// <param name="pdf_file">name of the pdf file to be processed</param>
public static void ReadPDF(string pdf_file, BasePDFExtractor pdf_extractor)
{
/*
* Console.Write() - display extended ascii chars?
* https://stackoverflow.com/questions/3948089/console-write-display-extended-ascii-chars
*/
Console.OutputEncoding = Encoding.UTF8;
/*
* How to extract text line by line when using iTextSharp
* https://stackoverflow.com/questions/15748800/extract-text-by-line-from-pdf-using-itextsharp-c-sharp
*/
// ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
/*
* https://stackoverflow.com/questions/83152/reading-pdf-documents-in-net
* ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
*/
using (PdfReader reader = new PdfReader(pdf_file))
{
//Schedule3Extractor page_reader = new Schedule3Extractor();
// break the whole pdf into pages and then process page by page
string page_content;
for (int page_count = 0; page_count < reader.NumberOfPages;)
{
page_count++;
/* Why are GetTextFromPage from iTextSharp returning longer and longer strings?
* https://stackoverflow.com/questions/35911062/why-are-gettextfrompage-from-itextsharp-returning-longer-and-longer-strings
*/
//ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
// get the whole page content
page_content = PdfTextExtractor.GetTextFromPage(reader, page_count, Strategy);
pdf_extractor.ProcessPage(page_content);
// Debug :
//if (page_count == 1) break;
}
}
}
public string ReadPdfFile(object Filename)
{
PdfReader reader2 = new PdfReader((string)Filename);
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader((string)Filename);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
return(strText);
}
/// <summary>
/// Not really useful since wkhtmltopdf build an image pdf...
/// </summary>
/// <param name="text"></param>
/// <returns></returns>
public bool PdfContains(string text)
{
//var textbuilder = new StringBuilder();
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
var strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
//textbuilder.Append(currentText);
if (currentText.Contains(text))
return true;
pdfReader.Close();
}
return false;
}
public string Go(string url)
{
var text = new StringBuilder();
try
{
using (var pdfReader = new PdfReader(url))
{
// Loop through each page of the document
for (var page = 1; page <= 10; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
try
{
var currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText =
Encoding.UTF8.GetString(
Encoding.Convert(
Encoding.Default,
Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
catch (ArgumentException)
{
Logger.Log.Error(string.Format("Can't parse PDF {0}, only images and no text.", url));
}
}
}
}
catch (Exception ex)
{
throw new BookieException(ex.Message, ex);
}
var rFileIsbn = Regex.Match(text.ToString(), @"ISBN.*?([X\d\-_ .]{10,20})");
if (!rFileIsbn.Success)
{
return null;
}
_isbn = rFileIsbn.Groups[1].ToString();
_isbn = _isbn.Replace(".", string.Empty);
_isbn = _isbn.Replace(" ", string.Empty);
_isbn = _isbn.Replace("-", string.Empty);
_isbn = _isbn.Replace("_", string.Empty);
return _isbn;
}
static string SearchText()
{
string name = @"C:\Users\DELL\Documents\Proyectopdfing\BIO-Alan-Munoz.pdf";
PdfReader reader2 = new PdfReader(name);
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader(name);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
return(strText);
}
static void Main(string[] args)
{
if (args.Length != 2)
{
Console.WriteLine("Usa: pdf2text [nomre pdf] [nombre txt]");
return;
}
else
{
foreach (string s in args){
System.Console.WriteLine(s);
}
String ficheroEntrada = args[0];
String ficheroSalida = args[1];
StringBuilder text = new StringBuilder();
if (File.Exists(ficheroEntrada))
{
PdfReader pdfReader = new PdfReader(ficheroEntrada);
int paginaInicio = 1;
int numberOfPages = pdfReader.NumberOfPages;
for (int page = paginaInicio; page <= numberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
try
{
File.WriteAllText(ficheroSalida, text.ToString(), Encoding.UTF8);
}
catch (Exception ex)
{
Console.WriteLine("error escribiendo fichero de salida" + ex.Message);
}
}
}
public string ReadPdfFile()
{
PdfReader reader2 = new PdfReader("c:\\prueba.pdf");
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader("c:\\prueba.pdf");
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
return strText;
}
private string GetPDFContents(PdfReader reader)
{
string strText = string.Empty;
int intNumPages = reader.NumberOfPages;
for (int page = 1; page <= intNumPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
using (PdfReader pReader = new PdfReader(reader))
{
String pageContents = PdfTextExtractor.GetTextFromPage(pReader, page, its);
pageContents = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(pageContents)));
strText += pageContents;
}
}
return(strText);
}
public void TestUnicodeEmptyString() {
StringBuilder sb = new StringBuilder();
String inFile = "japanese_text.pdf";
PdfReader p = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, inFile);
ITextExtractionStrategy strat = new SimpleTextExtractionStrategy();
sb.Append(PdfTextExtractor.GetTextFromPage(p, FIRST_PAGE, strat));
String result = sb.ToString(0, sb.ToString().IndexOf('\n'));
String origText =
"\u76f4\u8fd1\u306e\u0053\uff06\u0050\u0035\u0030\u0030"
+ "\u914d\u5f53\u8cb4\u65cf\u6307\u6570\u306e\u30d1\u30d5"
+ "\u30a9\u30fc\u30de\u30f3\u30b9\u306f\u0053\uff06\u0050"
+ "\u0035\u0030\u0030\u6307\u6570\u3092\u4e0a\u56de\u308b";
Assert.AreEqual(result, origText);
}
public string Text()
{
if (_pageText != null)
return _pageText;
using (var pdfReader = new PdfReader(_content.Buffer))
{
var strategy = new SimpleTextExtractionStrategy();
var pageText = PdfTextExtractor.GetTextFromPage(pdfReader, _number, strategy);
pageText =
Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(pageText)));
_pageText = pageText;
}
return _pageText;
}
static void Main(string[] args)
{
string ReadPdfFile(object Filename)
{
PdfReader reader2 = new PdfReader((string)Filename);
string strText = string.Empty;
//for (int page = 1; page <= reader2.NumberOfPages; page++)
for (int page = 1; page <= 1; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader((string)Filename);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
return(strText.Substring(84, 61).Replace(" ", "_").Replace(":", "").Trim());
}
DirectoryInfo di = new DirectoryInfo(@"C:\\temp\\pdfs");
foreach (var fi in di.GetFiles())
{
Console.WriteLine(di + "\\\\" + fi);
Console.WriteLine("Pdf: " + ReadPdfFile(di + "\\\\" + fi));
string oldfile = di + "\\\\" + fi;
string text_pdf = ReadPdfFile(di + "\\\\" + fi).ToString();
string nwfile = di + "\\\\" + text_pdf.ToString() + ".pdf";
Console.WriteLine("old: " + oldfile);
Console.WriteLine("new: " + nwfile);
//Console.ReadKey();
// Poner un try para ver donde da error
File.Copy(oldfile, nwfile, true);
}
Console.ReadKey();
/*
* string path = "C:\\temp\\ver.pdf";
* Console.WriteLine("Pdf: " + ReadPdfFile(path));
* Console.ReadKey();
*/
}
private void button1_Click(object sender, EventArgs e)
{
// Start Reading eBook //
if (textBox1.Text == "")
{
MessageBox.Show(" Please Enter a location","PDF to TEXT Converter");
}
else if (File.Exists(filename))
{
try
{
StringBuilder text = new StringBuilder();
PdfReader pdfReader = new PdfReader(filename);
progressBar1.Maximum = pdfReader.NumberOfPages;
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
text.Append(System.Environment.NewLine);
text.Append("\n Page Number:" + page);
text.Append(System.Environment.NewLine);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
pdfReader.Close();
progressBar1.Value++;
}
pdftext.Text += text.ToString();
progressBar1.Value = 0;
}
catch (Exception ex)
{
MessageBox.Show("Error: "+ ex.Message, "Error");
}
}
else
{
pdftext.Text = "Error: eBook does not exist at the specified location";
}
// End Reading eBook //
}
/// <summary>
/// Use the official test extraction interface.
/// THIS IS THE BEST METHOD
/// </summary>
/// <param name="Filename"></param>
public string GetPdfFileText(string SrcFilename)
{
StringBuilder builder = new StringBuilder();
PdfReader reader = new PdfReader(SrcFilename);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
//ITextExtractionStrategy its = new CSVTextExtractionStrategy();
string PageText = PdfTextExtractor.GetTextFromPage(reader, page, its);
//PageCSVText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(PageCSVText)));
//Byte[] b = Encoding.UTF8.GetBytes(PageCSVText);
//PageCSVText = Encoding.UTF8.GetString(Encoding.ASCII.GetBytes(PageCSVText));
//System.Diagnostics.Debug.WriteLine(PageText);
builder.AppendLine(PageText);
}
reader.Close();
return(builder.ToString());
}
public static string ReadPdfFile(Stream fileContent)
{
StringBuilder text = new StringBuilder();
//if (File.Exists(fileName))
{
var pdfReader = new PdfReader(fileContent);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
return text.ToString();
}
/**
* Searches for a tag in a page.
*
* @param tag
* the name of the tag
* @param obj
* an identifier to find the marked content
* @param page
* a page dictionary
* @throws IOException
*/
public void ParseTag(String tag, PdfObject obj, PdfDictionary page)
{
PRStream stream = (PRStream)page.GetAsStream(PdfName.CONTENTS);
// if the identifier is a number, we can extract the content right away
if (obj is PdfNumber)
{
PdfNumber mcid = (PdfNumber)obj;
RenderFilter filter = new MarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(strategy, new RenderFilter[] { filter });
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetStreamBytes(stream), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(SimpleXMLParser.EscapeXML(listener.GetResultantText(), true));
}
// if the identifier is an array, we call the parseTag method
// recursively
else if (obj is PdfArray)
{
PdfArray arr = (PdfArray)obj;
int n = arr.Size;
for (int i = 0; i < n; i++)
{
ParseTag(tag, arr[i], page);
if (i < n - 1)
{
outp.WriteLine();
}
}
}
// if the identifier is a dictionary, we get the resources from the
// dictionary
else if (obj is PdfDictionary)
{
PdfDictionary mcr = (PdfDictionary)obj;
ParseTag(tag, mcr.GetDirectObject(PdfName.MCID), mcr
.GetAsDict(PdfName.PG));
}
}
public static String ParsePDFtoString(String path)
{
StringBuilder text = new StringBuilder();
try
{
PdfReader pdfReader = new PdfReader(path);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
pdfReader.Close();
}
}
catch (Exception) { }
return text.ToString();
}
public static string ReadText(string filename)
{
string strText = string.Empty;
using (PdfReader documentReader = new PdfReader(filename))
{
for (int page = 1; page <= documentReader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
using (PdfReader pageReader = new PdfReader(filename))
{
String s = PdfTextExtractor.GetTextFromPage(pageReader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
pageReader.Close();
}
}
}
return(strText);
}
private List <string> ExtractTextFromPdf(string path)
{
List <string> text = new List <string>();
if (!File.Exists(path))
{
MessageBox.Show("Please give the valid path of the PDF file.");
}
PdfReader reader2 = new PdfReader(path);
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader(path);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
text.Add(s);
reader.Close();
}
return(text);
}
public void Process(Crawler crawler, PropertyBag propertyBag)
{
AspectF.Define.
NotNull(crawler, "crawler").
NotNull(propertyBag, "propertyBag");
if (propertyBag.StatusCode != HttpStatusCode.OK)
{
return;
}
if (!IsPdfContent(propertyBag.ContentType))
{
return;
}
using (Stream input = propertyBag.GetResponse())
{
PdfReader pdfReader = new PdfReader(input);
try
{
string title;
if (pdfReader.Info.TryGetValue("Title", out title))
{
propertyBag.Title = Convert.ToString(title, CultureInfo.InvariantCulture).Trim();
}
SimpleTextExtractionStrategy textExtractionStrategy = new SimpleTextExtractionStrategy();
propertyBag.Text = Enumerable.Range(1, pdfReader.NumberOfPages).
Select(pageNumber => PdfTextExtractor.GetTextFromPage(pdfReader, pageNumber, textExtractionStrategy)).
Join(Environment.NewLine);
}
finally
{
pdfReader.Close();
}
}
}
void doSomething(PdfReader reader)
{
//pdfReader.Close();
string tmp;
PP.SimpleTextExtractionStrategy blah;
tester atester = null;
blah = new PP.SimpleTextExtractionStrategy();
//Debug.WriteLine("here");
for (int page = 1; page <= reader.NumberOfPages; page++)
{
//Debug.WriteLine("here");
var avar = reader.GetLinks(page);
//Debug.WriteLine("here");
var v1 = reader.GetNamedDestinationFromNames();
var v2 = reader.GetNamedDestinationFromStrings();
var v3 = reader.GetPageContent(page);
var v4 = reader.GetPageN(page);
//var v5=reader.get
//PP.SimpleTextExtractionStrategy blah = new PP.SimpleTextExtractionStrategy();
tmp = blah.GetResultantText();
if (atester == null)
{
atester = new tester();
}
tmp = PP.PdfTextExtractor.GetTextFromPage(reader, page);
tmp = PP.PdfTextExtractor.GetTextFromPage(reader, page, blah);
tmp = PP.PdfTextExtractor.GetTextFromPage(reader, page, atester);
PP.PdfContentReaderTool.ListContentStreamForPage(reader, page, Console.Out);
//PdfReaderContentParser
this.showPage(reader, page);
//((PP.ITextExtractionStrategy) new tester()).
Debug.WriteLine("here");
}
}
/// <summary>
/// Search specified text into this input file.
/// </summary>
/// <param name="text">Text to search.</param>
/// <returns>
/// A <see cref="PdfText"/> list of matches.
/// </returns>
public IEnumerable <PdfText> SearchText(string text)
{
Logger.Instance.Debug("");
Logger.Instance.Debug(" Assembly: iTin.Utilities.Pdf.Writer, Namespace: iTin.Utilities.Pdf.Writer, Class: PdfInput");
Logger.Instance.Debug(" earch specified text into this input file");
Logger.Instance.Debug($" > Signature: ({typeof(IEnumerable<PdfText>)}) SearchText({typeof(string)})");
Logger.Instance.Debug($" > text: {text}");
List <PdfText> matchs = new List <PdfText>();
try
{
NativePdf.PdfReader pdfReader = new NativePdf.PdfReader(ToStream());
int count = pdfReader.NumberOfPages;
for (int page = 1; page <= count; page++)
{
NativePdfParser.ITextExtractionStrategy strategy = new NativePdfParser.SimpleTextExtractionStrategy();
string currentText = NativePdfParser.PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
var absolutePosition = currentText.IndexOf(text, StringComparison.OrdinalIgnoreCase);
if (absolutePosition != -1)
{
matchs.Add(new PdfText(text, page, absolutePosition));
}
}
pdfReader.Close();
}
catch
{
}
Logger.Instance.Debug($" > Output: {matchs.Count} item(s)");
return(matchs);
}
public void searchWord(string filename) {
string[] words = { "Взлом", "Хакер", "шаг" };
List<int> pages = new List<int>();
//if (File.Exists("C:\\1\\" + filename))
//if (File.Exists("C:\\1\\Instr.pdf"))
if (File.Exists(filename))
{
//PdfReader pdfReader = new PdfReader("C:\\1\\" + filename);
//PdfReader pdfReader = new PdfReader("C:\\1\\Instr.pdf");
PdfReader pdfReader = new PdfReader(filename);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
for (int i = 0; i < words.Length; i++)
{
//bool switch1 = false;
if (currentPageText.Contains(words[i]))
{
pages.Add(page);
textBox1.Text += page.ToString();
textBox1.AppendText(Environment.NewLine);
textBox2.Text += words[i];
textBox2.AppendText(Environment.NewLine);
textBox2.Text += "\n";
}
}
}
pdfReader.Close();
}
}
private void readPdf(string fileToOpen)
{
try
{
PdfReader reader = new PdfReader(fileToOpen);
// total number of pages
int n = reader.NumberOfPages;
// size of the first page
Rectangle psize = reader.GetPageSize(1);
float width = psize.Width;
float height = psize.Height;
string asd = "Size of page 1 of {0} => {1} × {2}"+ n+ width+ height;
RoutesBoxList.Items.Add(asd);
// file properties
Dictionary<string, string> infodict = reader.Info;
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(reader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
RoutesBoxList.Items.Add(currentText);
TestBox.Text = currentText;
}
foreach (KeyValuePair<string, string> kvp in infodict)
RoutesBoxList.Items.Add(kvp.Key + " => " + kvp.Value);
}
catch (Exception e)
{
RoutesBoxList.Items.Add("Cannot deserialize PDF " + fileToOpen);
}
}
//Read stop word list from text file called stopwords.txt
//public string[] StopWords()
//{
// string[] stopText = File.ReadAllLines("stopwords.txt");
// return stopText;
//}
public void ReadPdf(string pdfpath)
{
try
{
PdfReader pdfr = new PdfReader(pdfpath);
StringBuilder pdfText = new StringBuilder();
int tp = DocumentInfo.TotalPages;
//loop to read pdf page by page
for (int page = 1; page <= tp; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfr, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
//currentText = currentText.ToLower();
POSTagger.mModelPath = "Models\\";
string[] tSplittedWords = GetWords(currentText);
string[] sentences = POSTagger.SplitSentences(currentText);
Sentences[] sentencearray = new Sentences[sentences.Count()];
int sc = sentences.Count();
for (int i = 0; i < sc; i++)
{
sentencearray[i] = new Sentences();
sentencearray[i].SentenceNumber = i + 1 + currentcountofsentences;
sentencearray[i].SentenceString = sentences[i].ToLower();
sentenceList.Add(sentencearray[i]);
}
currentcountofsentences += sentences.Count();
string[] POS = POSTagger.PosTagTokens(tSplittedWords);
splittedWords.Clear();
nrSplittedWords.Clear();
countList.Clear();
int poslength = POS.Length;
for (int i = 0; i < poslength; i++)
{
//NN Noun, singular or mass
//NNS Noun, plural
//NNP Proper noun, singular
//NNPS Proper noun, plural
if (POS[i] == "NN" || POS[i] == "NNS" || POS[i] == "NNP" || POS[i] == "NNPS")
{
tSplittedWords[i] = tSplittedWords[i].ToLower();
splittedWords.Add(tSplittedWords[i]);
}
}
//removing stop words from splittedwords list
List<string> t1SplittedWords = new List<string>();
foreach (string sw in splittedWords)
{
if (!Array.Exists(_stopWords, element => element == sw))
{
t1SplittedWords.Add(sw);
}
//this also works
//if (!_stopWords.Contains(sw))
//{
// t1SplittedWords.Add(sw);
//}
}
splittedWords.Clear();
splittedWords = t1SplittedWords.ToList();
nrSplittedWords = splittedWords.Distinct().ToList();
int nrswcount = nrSplittedWords.Count;
_eachPageWordCount.Add(nrswcount);
_tUniqueWordsinPage = nrswcount;
//calculating frequency of words in each page i.e. Term Frequency
for (int i = 0; i < nrswcount; i++)
{
string searchItem = nrSplittedWords[i];
int count = 0;
for (int j = 0; j < splittedWords.Count(); j++)
{
if (searchItem == splittedWords[j])
count++;
}
countList.Add(count);
}
Words[] wordarray = new Words[nrSplittedWords.Count()];
for (int i = 0; i < nrswcount; i++)
{
wordarray[i] = new Words();
wordarray[i].Word = nrSplittedWords[i];
wordarray[i].TermFrequency = countList[i];
wordarray[i].Pageno = page;
wordList.Add(wordarray[i]);
}
//foreach (string s in nrSplittedWords)
//{
// UniqueWordsinCorpus.Add(s);
//}
UniqueWordsinCorpus.AddRange(nrSplittedWords);
pdfText.Append(currentText);
} //end of page loop
pdfr.Close();
//UniqueWordsinCorpus is a list of string of unique words
UniqueWordsinCorpus = UniqueWordsinCorpus.Distinct().ToList();
UniqueWordsinCorpus.Sort();
foreach (Words w in wordList)
{
int corf = 0;
foreach (Words w1 in wordList)
{
if (w.Word == w1.Word)
corf = corf + w1.TermFrequency;
}
w.CorpusFrequency = corf;
}
foreach (Words w in wordList)
{
w.SentencenoWithFrequency = new Dictionary<int, int>();
foreach (Sentences s in sentenceList)
{
int sentfreq = 0;
string[] splittedwordsofsentence = GetWords(s.SentenceString);
int swoscount = splittedwordsofsentence.Count();
for (int i = 0; i < swoscount; i++)
{
if (w.Word == splittedwordsofsentence[i])
sentfreq++;
}
w.SentencenoWithFrequency.Add(s.SentenceNumber, sentfreq);
}
}
//wordList.Sort(delegate(Words w1, Words w2) { return w1.Word.CompareTo(w2.Word); });
wordList.Sort((w1, w2) => w1.Word.CompareTo(w2.Word));
//copying words from wordList of Words to uniquewordlist of uniquewords while removing the redundant entry
UniqueWords[] uniquewordarray = new UniqueWords[UniqueWordsinCorpus.Count];
int uwiccount = UniqueWordsinCorpus.Count;
for (int i = 0; i < uwiccount; i++)
{
uniquewordarray[i] = new UniqueWords();
uniquewordarray[i].SentencenoWithFrequency = new Dictionary<int, int>();
uniquewordarray[i].PagenoWithFrequency = new Dictionary<int, int>();
foreach (Words w in wordList)
{
if (UniqueWordsinCorpus[i] == w.Word)
{
if (uniquewordarray[i].Term == null)
uniquewordarray[i].Term = w.Word;
uniquewordarray[i].CorpusFrequency = w.CorpusFrequency;
uniquewordarray[i].SentencenoWithFrequency = w.SentencenoWithFrequency;
uniquewordarray[i].PagenoWithFrequency.Add(w.Pageno, w.TermFrequency);
}
}
UniqueWordList.Add(uniquewordarray[i]);
}
//computing document frequency of unique words
foreach (UniqueWords uw in UniqueWordList)
{
uw.DocFrequency = uw.PagenoWithFrequency.Count;
}
//Displaying uniquewords with their attribute values
//foreach (UniqueWords uw in UniqueWordList)
//{
// DocText.AppendText(uw.Term + "........");
// DocText.AppendText(uw.CorpusFrequency.ToString() + "\n");
// DocText.AppendText("Sentence no with frequency \n");
// List<KeyValuePair<int, int>> list = uw.SentencenoWithFrequency.ToList();
// foreach (KeyValuePair<int, int> pair in list)
// {
// if (pair.Value > 0)
// {
// DocText.AppendText(pair.Key.ToString() + ".......");
// DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
// }
// }
// DocText.AppendText("Page no with freqency \n");
// List<KeyValuePair<int, int>> list1 = uw.PagenoWithFrequency.ToList();
// foreach (KeyValuePair<int, int> pair in list1)
// {
// if (pair.Value > 0)
// {
// DocText.AppendText(pair.Key.ToString() + ".......");
// DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
// }
// }
//}
//foreach (Words w in wordList)
//{
// DocText.AppendText(w.Word + Environment.NewLine);
// List<KeyValuePair<int, int>> list = w.SentencenoWithFrequency.ToList();
// foreach (KeyValuePair<int, int> pair in list)
// {
// if (pair.Value > 0)
// {
// DocText.AppendText(pair.Key.ToString() + ".......");
// DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
// }
// }
//}
// matrixpro.GenerateMatrix(UniqueWordList);
//UserWordsEditor uwe=new UserWordsEditor(UniqueWordList);
//uwe.Show();
}
catch (Exception se)
{
MessageBox.Show(se.Message);
}
}
public void ReadPdf(string path)
{
try
{
PdfReader pdfr = new PdfReader(path);
StringBuilder pdfText = new StringBuilder();
//loop to read pdf page by page
for (int page = 1; page <= pdfr.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfr, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
POSTagger.mModelPath = "Models\\";
string[] tSplittedWords = GetWords(currentText);
string[] sentences = POSTagger.SplitSentences(currentText);
sentencearray=new Sentences[sentences.Count()];
for (int i = 0; i < sentences.Count(); i++)
{
sentencearray[i]=new Sentences();
sentencearray[i].SentenceNumber = i+1+currentcountofsentences;
sentencearray[i].SentenceString = sentences[i];
sentenceList.Add(sentencearray[i]);
}
currentcountofsentences += sentences.Count();
string[] POS = POSTagger.PosTagTokens(tSplittedWords);
splittedWords.Clear();
nrSplittedWords.Clear();
countList.Clear();
for (int i = 0; i < POS.Length; i++)
{
//NN Noun, singular or mass
//NNS Noun, plural
//NNP Proper noun, singular
//NNPS Proper noun, plural
if (POS[i] == "NN" || POS[i] == "NNS" || POS[i] == "NNP" || POS[i] == "NNPS")
splittedWords.Add(tSplittedWords[i]);
}
nrSplittedWords = splittedWords.Distinct().ToList();
_tUniqueWordsinPage = nrSplittedWords.Count();
//calculating frequency of words in each page
for (int i = 0; i < nrSplittedWords.Count();i++ )
{
string searchItem = nrSplittedWords[i];
int count=0;
for (int j = 0; j < splittedWords.Count();j++ )
{
if (searchItem == splittedWords[j])
count++;
}
countList.Add(count);
}
wordarray=new Words[nrSplittedWords.Count()];
for (int i = 0; i < nrSplittedWords.Count(); i++)
{
wordarray[i] = new Words();
wordarray[i].Word = nrSplittedWords[i];
wordarray[i].DocFrequency = countList[i];
wordarray[i].Pageno=page;
wordList.Add(wordarray[i]);
}
foreach (string s in nrSplittedWords)
{
UniqueWordsinCorpus.Add(s);
}
pdfText.Append(currentText);
} //end of page loop
pdfr.Close();
UniqueWordsinCorpus = UniqueWordsinCorpus.Distinct().ToList();
UniqueWordsinCorpus.Sort();
foreach (Words w in wordList)
{
int corf = 0;
foreach (Words w1 in wordList)
{
if (w.Word == w1.Word)
corf = corf + w1.DocFrequency;
}
w.CorpusFrequency = corf;
}
foreach(Words w in wordList)
{
w.SentencenoWithFrequency=new Dictionary<int, int>();
foreach(Sentences s in sentenceList)
{
int sentfreq = 0;
string[] splittedwordsofsentence = GetWords(s.SentenceString);
for(int i=0;i<splittedwordsofsentence.Count();i++)
{
if (w.Word == splittedwordsofsentence[i])
sentfreq++;
}
w.SentencenoWithFrequency.Add(s.SentenceNumber,sentfreq);
}
}
//wordList.Sort(delegate(Words w1, Words w2) { return w1.Word.CompareTo(w2.Word); });
wordList.Sort((w1,w2) => w1.Word.CompareTo(w2.Word));
//copying words from wordList of Words to uniquewordlist of uniquewords while removing the redundant entry
uniquewordarray=new UniqueWords[UniqueWordsinCorpus.Count];
for (int i = 0; i < UniqueWordsinCorpus.Count; i++)
{
uniquewordarray[i] = new UniqueWords();
uniquewordarray[i].SentencenoWithFrequency = new Dictionary<int, int>();
uniquewordarray[i].PagenoWithFrequency = new Dictionary<int, int>();
foreach (Words w in wordList)
{
if (UniqueWordsinCorpus[i] == w.Word)
{
if(uniquewordarray[i].Term==null)
uniquewordarray[i].Term = w.Word;
uniquewordarray[i].CorpusFrequency = w.CorpusFrequency;
uniquewordarray[i].SentencenoWithFrequency = w.SentencenoWithFrequency;
uniquewordarray[i].PagenoWithFrequency.Add(w.Pageno,w.DocFrequency);
}
}
UniqueWordList.Add(uniquewordarray[i]);
}
//Displaying uniquewords with their attribute values
foreach (UniqueWords uw in UniqueWordList)
{
DocText.AppendText(uw.Term + "........");
DocText.AppendText(uw.CorpusFrequency.ToString() + "\n");
DocText.AppendText("Sentence no with frequency \n");
List<KeyValuePair<int, int>> list = uw.SentencenoWithFrequency.ToList();
foreach (KeyValuePair<int, int> pair in list)
{
if (pair.Value > 0)
{
DocText.AppendText(pair.Key.ToString() + ".......");
DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
}
}
DocText.AppendText("Page no with freqency \n");
List<KeyValuePair<int, int>> list1 = uw.PagenoWithFrequency.ToList();
foreach (KeyValuePair<int, int> pair in list1)
{
if (pair.Value > 0)
{
DocText.AppendText(pair.Key.ToString() + ".......");
DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
}
}
}
foreach (Words w in wordList)
{
DocText.AppendText(w.Word + Environment.NewLine);
List<KeyValuePair<int, int>> list = w.SentencenoWithFrequency.ToList();
foreach (KeyValuePair<int, int> pair in list)
{
if (pair.Value > 0)
{
DocText.AppendText(pair.Key.ToString() + ".......");
DocText.AppendText(pair.Value.ToString() + Environment.NewLine);
}
}
}
//Diplaying words with their page no and Docfrequency using objects
foreach (Words w in wordList)
{
WordnFrequencyTxtBox.AppendText(w.Pageno + "---------" + w.Word + " -----------" + w.DocFrequency +"-----------"+w.CorpusFrequency+ System.Environment.NewLine);
}
}
catch (Exception se)
{
MessageBox.Show(se.Message);
}
}
/**
* Searches for a tag in a page.
*
* @param tag
* the name of the tag
* @param obj
* an identifier to find the marked content
* @param page
* a page dictionary
* @throws IOException
*/
public void ParseTag(String tag, PdfObject obj, PdfDictionary page) {
PRStream stream = (PRStream) page.GetAsStream(PdfName.CONTENTS);
// if the identifier is a number, we can extract the content right away
if (obj is PdfNumber) {
PdfNumber mcid = (PdfNumber) obj;
RenderFilter filter = new MarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(strategy, new RenderFilter[]{filter});
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetStreamBytes(stream), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(SimpleXMLParser.EscapeXML(listener.GetResultantText(), true));
}
// if the identifier is an array, we call the parseTag method
// recursively
else if (obj is PdfArray) {
PdfArray arr = (PdfArray) obj;
int n = arr.Size;
for (int i = 0; i < n; i++) {
ParseTag(tag, arr[i], page);
if (i < n - 1)
outp.WriteLine();
}
}
// if the identifier is a dictionary, we get the resources from the
// dictionary
else if (obj is PdfDictionary) {
PdfDictionary mcr = (PdfDictionary) obj;
ParseTag(tag, mcr.GetDirectObject(PdfName.MCID), mcr
.GetAsDict(PdfName.PG));
}
}
public string runCheckPatientFolder(Hashtable checkChartNumbers)
{
DateTime startDateVal = DateTime.Now, endDateVal = DateTime.Now;
string []chartNumbers;
//get directories under the encounter folder
string []paths = Directory.GetDirectories(data["ENCOUNTER_FOLDER"], "*", SearchOption.TopDirectoryOnly);
Array.Sort(paths);
FileInfo tempFile ;
int endIndex = paths.Length;
string[] encounterFiles, searchFiles;
string textToAnalyze, currentText, currentEncounter;
Regex rgx;
StringBuilder text;
PdfReader pdfReader;
//this is function of check pt folder//
//john is this where the method is for checking pt folder?
//this is the text that is searched for in the pdf
string[] octFolder = data["OCT_TEXT_SEARCH"].Split(','), photosFAFolder = data["PHOTOFA_TEXT_SEARCH"].Split(',');
string[] ultrasound = data["ULTRASOUND_TEXT_SEARCH"].Split(',');
string[] vf = data["VF_TEXT_SEARCH"].Split(',');
bool hasOctFolder = false, hasPhotosFolder = false, hasUltrasoundFolder = false, hasVFFolder = false;
//string runLog = data["CKPTFOLDERS"] + startDateVal.ToString("yyyy-MM-dd");
string runLog = data["CKPTFOLDERS"];
Directory.CreateDirectory(runLog);
runLog = runLog + "\\" + DateTime.Now.ToString("yyyyMMddHHmmss") + "-CKPTFOLDERS-" + startDateVal.ToString("yyyy-MM-dd") + ".txt";
StreamWriter sw = new StreamWriter(runLog, true);
MemoryStream stream = new MemoryStream();
DateTime theDate;
StringWriter tw = new StringWriter();
foreach (DictionaryEntry entry in checkChartNumbers)
{
theDate = (DateTime)entry.Key;
paths = Directory.GetDirectories(data["ENCOUNTER_FOLDER"] + Path.DirectorySeparatorChar +
theDate.ToString("yyyy-MM-dd"), "*", SearchOption.TopDirectoryOnly);
chartNumbers = (string[]) entry.Value;
for(int j = 0; j < chartNumbers.Length; j++)
{
encounterFiles = Directory.GetFiles(data["ENCOUNTER_FOLDER"] + Path.DirectorySeparatorChar +
theDate.ToString("yyyy-MM-dd"), "*" + chartNumbers[j] + "*", SearchOption.AllDirectories);
//reset the flags that indicate whether or not the text was found
hasVFFolder = hasOctFolder = hasPhotosFolder = hasUltrasoundFolder = false;
if (encounterFiles != null && encounterFiles.Length > 0)
{//if there are some encounter files
sw.WriteLine("{0}:", chartNumbers[j]);
tw.WriteLine("{0}:", chartNumbers[j]);
}
else
{//if there are no encounter files for the patient
// sw.WriteLine("{0}: no tests", chartNumbers[j]);
// tw.WriteLine("{0}: no tests", chartNumbers[j]);
}
for (int k = 0; k < encounterFiles.Length; k++)
{
pdfReader = new PdfReader(encounterFiles[k]);
tempFile = new FileInfo(encounterFiles[k]);
currentEncounter = tempFile.Name.Substring(0, 8);
text = new StringBuilder();
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
//grab the text from the pdf pages
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText );
}
text = text.Replace("\n", " ");
textToAnalyze = text.ToString();
if (!hasOctFolder)
{//if the OCT folder flag hasn't been set to true
for (int u = 0; u < octFolder.Length; u++)
{//loop through all the text items we should search for
rgx = new Regex(".*" + octFolder[u] + ":[\\s*]\\w+");//build the regular expression pattern that will be used to search the text
if (rgx.IsMatch(textToAnalyze))//search teh text
{//there we have a match. make sure there is a file in the 5OCT folder with the same encounter date prefix (currentEncounter)
if (Directory.Exists(data["ROUTING_BASE"] + chartNumbers[j] + "\\5OCT\\"))
{
searchFiles = Directory.GetFiles(data["ROUTING_BASE"] + chartNumbers[j] + "\\5OCT\\", currentEncounter + "*.*", SearchOption.AllDirectories);
if (searchFiles.Length > 0)
{//we have files
hasOctFolder = true;
sw.WriteLine("\t{0}: OK", octFolder[u]);
tw.WriteLine(" {0}: OK", octFolder[u]);
}
else
{//we don't have the files we should have
sw.WriteLine("\t{0}: missing files", octFolder[u]);
tw.WriteLine(" {0}: missing files", octFolder[u]);
}
}
else
{
sw.WriteLine("\t{0}: missing files and 5OCT folder", octFolder[u]);
tw.WriteLine(" {0}: missing files and 5OCT folder", octFolder[u]);
}
}
}
}
if (!hasVFFolder)
{//if the OCT folder flag hasn't been set to true
for (int u = 0; u < vf.Length; u++)
{//loop through all the text items we should search for
rgx = new Regex(".*" + vf[u] + ":[\\s*]\\w+");//build the regular expression pattern that will be used to search the text
if (rgx.IsMatch(textToAnalyze))//search teh text
{//there we have a match. make sure there is a file in the 5OCT folder with the same encounter date prefix (currentEncounter)
if (Directory.Exists(data["ROUTING_BASE"] + chartNumbers[j] + "\\6VF\\"))
{
searchFiles = Directory.GetFiles(data["ROUTING_BASE"] + chartNumbers[j] + "\\6VF\\", currentEncounter + "*.*", SearchOption.AllDirectories);
if (searchFiles.Length > 0)
{//we have files
hasOctFolder = true;
sw.WriteLine("\t{0}: OK", vf[u]);
tw.WriteLine(" {0}: OK", vf[u]);
}
else
{//we don't have the files we should have
sw.WriteLine("\t{0}: missing files", vf[u]);
tw.WriteLine(" {0}: missing files", vf[u]);
}
}
else
{
sw.WriteLine("\t{0}: missing files and 6VF folder", vf[u]);
tw.WriteLine(" {0}: missing files and 6VF folder", vf[u]);
}
}
}
}
if (!hasPhotosFolder)
{
for (int u = 0; u < photosFAFolder.Length; u++)
{
rgx = new Regex(".*" + photosFAFolder[u] + ":[\\s*]\\w+");
if (rgx.IsMatch(textToAnalyze))
{//there we have a match. make sure there is a file in the 5OCT folder with the same encounter date prefix
if (Directory.Exists(data["ROUTING_BASE"] + chartNumbers[j] + "\\4photosFA\\"))
{
searchFiles = Directory.GetFiles(data["ROUTING_BASE"] + chartNumbers[j] + "\\4photosFA\\", currentEncounter + "*.*", SearchOption.AllDirectories);
if (searchFiles.Length > 0)
{//we have files
hasPhotosFolder = true;
sw.WriteLine("\t{0}: OK", photosFAFolder[u]);
tw.WriteLine(" {0}: OK", photosFAFolder[u]);
}
else
{
sw.WriteLine("\t{0}: missing files", photosFAFolder[u]);
tw.WriteLine(" {0}: missing files", photosFAFolder[u]);
}
}
else
{
sw.WriteLine("\t{0}: missing files and 4photosFA folder", photosFAFolder[u]);
tw.WriteLine(" {0}: missing files and 4photosFA folder", photosFAFolder[u]);
}
}
}
}
if (!hasUltrasoundFolder)
{
for (int u = 0; u < ultrasound.Length; u++)
{
rgx = new Regex(".*" + ultrasound[u] + ":[\\s*]\\w+");
if (rgx.IsMatch(textToAnalyze))
{//there we have a match. make sure there is a file in the 5OCT folder with the same encounter date prefix
if (Directory.Exists(data["ROUTING_BASE"] + chartNumbers[j] + "\\7Ultrasound\\"))
{
searchFiles = Directory.GetFiles(data["ROUTING_BASE"] + chartNumbers[j] + "\\7Ultrasound\\", currentEncounter + "*.*", SearchOption.AllDirectories);
if (searchFiles.Length > 0)
{//we have files
hasUltrasoundFolder = true;
sw.WriteLine("\t{0}: OK", ultrasound[u]);
tw.WriteLine(" {0}: OK", ultrasound[u]);
}
else
{
sw.WriteLine("\t{0}: missing files", ultrasound[u]);
tw.WriteLine(" {0}: missing files", ultrasound[u]);
}
}
else
{
sw.WriteLine("\t{0}: missing files and 7Ultrasound folder", photosFAFolder[u]);
tw.WriteLine(" {0}: missing files and 7Ultrasound folder", photosFAFolder[u]);
}
}
}
}
}
/*if (matchedOct && !hasOctFolder)
{
sw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedOct ? "Should have OCT" : "Should not have OCT", hasOctFolder ? "Has files in OCT folder" : "Does not have OCT");
tw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedOct ? "Should have OCT" : "Should not have OCT", hasOctFolder ? "Has files in OCT folder" : "Does not have OCT");
}
if (matchedPhotos && !hasPhotosFolder)
{
sw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedPhotos ? "Should have PhotosFA" : "Should not have PhotosFA", hasPhotosFolder ? "Has files in PhotosFA folder" : "Does not have PhotosFA");
tw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedPhotos ? "Should have PhotosFA" : "Should not have PhotosFA", hasPhotosFolder ? "Has file in PhotosFA folder" : "Does not have PhotosFA");
}
if(matchedUltrasound && !hasUltrasoundFolder){
sw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedUltrasound ? "Should have Ultrasound" : "Should not have Ultrasound", hasUltrasoundFolder ? "Has files in Ultrasound folder" : "Does not have Ultrasound");
tw.WriteLine("{0} {1} {2} {3}", DateTime.Now, chartNumbers[j], matchedUltrasound ? "Should have Ultrasound" : "Should not have Ultrasound", hasUltrasoundFolder ? "Has files in Ultrasound folder" : "Does not have Ultrasound");
}*/
}
}
if (tw.ToString().Length == 0)
{
/*for (int j = 0; j < chartNumbers.Length; j++)
{
sw.WriteLine("{0}: no tests", chartNumbers[j]);
tw.WriteLine("{0}: no tests", chartNumbers[j]);
}*/
}
sw.Close();
return tw.ToString();
}
private static IEnumerable<String> GetPdfPagesContent(string path)
{
var pagesList = new List<String>();
using (var pdfReader = new PdfReader(path))
{
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy(); // LocationTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(
pdfReader,
page,
strategy);
currentText =
Encoding.UTF8.GetString(Encoding.Convert(
Encoding.Default,
Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
pagesList.Add(currentText);
}
}
return pagesList;
}
public List<int> ReadPdfFile(string fileName, string searthText)
{
List<int> pages = new List<int>();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
if (currentPageText.Contains(searthText))
{
pages.Add(page);
}
}
pdfReader.Close();
}
return pages;
}
public static string getPDFText(string fileName)
{
PdfReader pdfReader = new PdfReader(fileName);
StringBuilder text = new StringBuilder();
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText + "\r\n");
}
pdfReader.Close();
return text.ToString();
}
private static List<Entry> ReadCembraPdf(string file)
{
List<Entry> entries = new List<Entry>();
PdfReader pdfReader = new PdfReader(file);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText =
Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.GetEncoding("ISO-8859-1"), Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
string[] lines = currentText.Split('\n');
bool startEntries = false;
foreach (string line in lines)
{
if (startEntries)
{
if (line.StartsWith("Kontonummer") || line.StartsWith("Diverses"))
{
break;
}
string normalizedline = line.Replace(" ", "");
DateTime date;
if (DateTime.TryParse(normalizedline.Substring(0, 10), out date))
{
string currency = "CHE";
if (normalizedline.Contains("DEU"))
{
currency = "DEU";
}
else if (normalizedline.Contains("GBR"))
{
currency = "GBR";
}
else if (normalizedline.Contains("LUX"))
{
currency = "LUX";
}
else if (normalizedline.Contains("FRA"))
{
currency = "FRA";
}
int currencyPos = normalizedline.IndexOf(currency, StringComparison.InvariantCulture);
if (currencyPos <= 0)
{
continue;
}
string text = normalizedline.Substring(20, currencyPos - 20);
double amount = Double.Parse(normalizedline.Substring(currencyPos + 3));
entries.Add(new Entry
{
Amount = -1*amount,
Date = date,
Text = text
});
}
}
if (line.StartsWith("Einkaufs-Datum"))
{
startEntries = true;
}
}
}
pdfReader.Close();
return entries;
}
// Es wird der gesuchte Ausdruck aus der PDF-Fatei ausgelesen.
public List<string> ReadPdfFile(string fileName, string RegexPattern, string begrenzer1, string begrenzer2, int pComboBoxIndex)
{
StringBuilder text = new StringBuilder();
PdfReader pdfReader = new PdfReader(fileName);
// Jede einzelne Seite wird ausgelesen.
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string derGesamteAusgeleseneTextInEinemString = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
if (begrenzer1 != "")
{
// Überflüssiges vorne abschneiden
Regex regex = new Regex(begrenzer1);
string[] substrings = regex.Split(derGesamteAusgeleseneTextInEinemString);
derGesamteAusgeleseneTextInEinemString = substrings[1];
}
if (begrenzer2 != "")
{
// Überflüssiges hinten abschneiden
Regex hinten = new Regex(begrenzer2);
string[] substrings = hinten.Split(derGesamteAusgeleseneTextInEinemString);
derGesamteAusgeleseneTextInEinemString = substrings[0];
}
derGesamteAusgeleseneTextInEinemString = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(derGesamteAusgeleseneTextInEinemString)));
text.Append(derGesamteAusgeleseneTextInEinemString);
pdfReader.Close();
//MessageBox.Show(derGesamteAusgeleseneTextInEinemString);
}
// Auf jeder Seite können auch mehr als eine gefundene Adresse verarbeitet werden.
System.Text.RegularExpressions.MatchCollection matches;
// Bei der E-Mail-Adresse wird Groß-/Kleinschreibung nicht unterschieden. Beim Kürzel, Namen etc. schon.
if (pComboBoxIndex == 0)
{
matches = System.Text.RegularExpressions.Regex.Matches(text.ToString(), RegexPattern, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
}
else
{
matches = System.Text.RegularExpressions.Regex.Matches(text.ToString(), RegexPattern);
}
List<string> gefundeneReguläreAusdrücke = new List<string>();
int zaehler = 0;
string ausgabe = "";
foreach (Match match in matches)
{
// Wenn in den Einstellungen festgelegt ist, dass eine bestimmte Domain ignoriert wird, wird ggfs. nichts zurückgegeben.
if ((Properties.Settings.Default.DieseDomainIgnorieren != "" && match.Value.EndsWith(Properties.Settings.Default.DieseDomainIgnorieren)) || (Properties.Settings.Default.DieseMailIgnorieren != "" && match.Value == Properties.Settings.Default.DieseMailIgnorieren))
{
gefundeneReguläreAusdrücke.Add("Die gefundene E-Mail-Adresse wird aufgrund Ihrer Einstellungen ignoriert.");
ausgabe = "\n" + ausgabe + "\n" + "Die gefundene E-Mail-Adresse wird aufgrund Ihrer Einstellungen ignoriert.";
}
else
{
gefundeneReguläreAusdrücke.Add(match.Value.ToString());
ausgabe = "\n" + ausgabe + "\n" + match.Value.ToString();
}
zaehler++;
}
return gefundeneReguläreAusdrücke;
}
public override void ParseTag(String tag, PdfObject obj, PdfDictionary page) {
if (obj is PdfNumber) {
PdfNumber mcid = (PdfNumber) obj;
RenderFilter filter = new MyMarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(
strategy, filter);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetPageContent(page), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(XMLUtil.EscapeXML(listener.GetResultantText(), true));
}
else {
base.ParseTag(tag, obj, page);
}
}
private void button1_Click(object sender, EventArgs e)
{
iTextSharp.text.FontFactory.RegisterDirectories();
timer1.Stop();
button5.Text = "P L A Y";
OpenFileDialog dlg = new OpenFileDialog();
string filepath;
dlg.Filter = "PDF files(*.PDF)|*.PDF|All files(*.*)|*.*";
// axFoxitCtl1.OpenFile("");
if (dlg.ShowDialog() == DialogResult.OK)
{
filepath = dlg.FileName.ToString();
string strText = string.Empty;
try
{
PdfReader reader = new PdfReader(filepath);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its ;//= new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy(); //LocationTextExtractionStrategy
if (radioButton3.Checked)
{
its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy(); //LocationTextExtractionStrategy
}
else {
its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy(); //LocationTextExtractionStrategy
}
String s;
s = PdfTextExtractor.GetTextFromPage(reader, page, its);
if (false)
{
var fTahoma = FontFactory.GetFont("Tahoma", BaseFont.IDENTITY_H);
var pi = new Phrase(s, fTahoma);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Unicode, Encoding.UTF8, Encoding.Unicode.GetBytes(pi.Content)));
char[] charArray = s.ToCharArray();
Array.Reverse(charArray);
s = new string(charArray);
}
var ss = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
//s = s.ToString;
strText = strText + " " +ss;
MyText.Text = strText;
//MyText.RightToLeft = MyText.Fon
}
reader.Close();
i = 0;
strText = strText.Replace("\t", " ");
strText = strText.Replace(" ", " ");
strText = strText.Replace("\u2000", " ");
strText = strText.Replace(Environment.NewLine, "\n");
if (mychar == '\n')
{
strText = strText.Replace("\n", " ");
strText = strText.Replace(".", ". " + mychar);
}
words = strText.Split(new char[] { mychar}, StringSplitOptions.RemoveEmptyEntries);
progressBar1.Maximum = words.Length;
timer1.Stop();
button5.Text = "P L A Y";
System.Diagnostics.Process.Start(filepath);
//axFoxitCtl1.OpenFile();
//axAcroPDF2.LoadFile(filepath);
//axAcroPDF2.src = filepath;
//axAcroPDF2.Show();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
}
public static void SetProperties(string filename)
{
Filename = filename;
FileInfo fi = new FileInfo(Filename);
Size = Math.Round(Convert.ToDouble(fi.Length)/(1048576), 2); //1048576=1024*1024
Extension = fi.Extension;
if (Extension == ".pdf")
{
DocumentType = "Portable Document Format(.pdf)";
PdfReader pdfr = new PdfReader(Filename);
StringBuilder pdfText = new StringBuilder();
TotalPages = pdfr.NumberOfPages;
//loop to read pdf page by page
for (int page = 1; page <= pdfr.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfr, page, strategy);
currentText =
Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
pdfText.Append(currentText);
}
pdfr.Close();
string completetext=pdfText.ToString();
// NoOfWords=completetext.Split(' ').Length;
NoOfWords=Regex.Matches(completetext, @"[A-Za-z0-9]+").Count;
}
else if (Extension == ".odt")
{
DocumentType = "Open Document Format(.odt)";
ComputeStatistics();
}
else if (Extension == ".docx")
{
DocumentType = "Microsoft Word Document(.docx)";
ComputeStatistics();
}
else
{
DocumentType = "Word 97-2003 document(.doc)";
ComputeStatistics();
}
}
