private static void ExtractLines(PdfReader reader, StringBuilder sb, PdfObject content)
{
var ir = (PRIndirectReference)content;
var value = reader.GetPdfObject(ir.Number);
if (value.IsStream())
{
PRStream stream = (PRStream)value;
var streamBytes = PdfReader.GetStreamBytes(stream);
var tokenizer = new PRTokeniser(new RandomAccessFileOrArray(streamBytes));
try
{
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TK_STRING)
{
string str = tokenizer.StringValue;
sb.Append(str);
}
}
}
finally
{
tokenizer.Close();
}
}
}
private string ReadPDF(string filePath)
{
var builder = new StringBuilder();
PdfReader document = null;
try
{
document = new PdfReader(filePath);
for (int i = 1; i <= document.NumberOfPages; i++)
{
byte[] stream = document.GetPageContent(i);
var tokenizer = new PRTokeniser(new RandomAccessFileOrArray(stream));
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TokType.STRING)
{
builder.Append(tokenizer.StringValue);
}
}
}
}
catch (Exception e)
{
builder.Append(e.Message);
}
finally
{
document?.Close();
}
return(builder.ToString());
}
private static void ParsePdf(byte[] pdf, IPdfParsingStrategy strategy)
{
PdfReader reader = new PdfReader(pdf);
for (int i = 1; i <= reader.NumberOfPages; i++)
{
byte[] page = reader.GetPageContent(i);
if (page != null)
{
PRTokeniser tokenizer = new PRTokeniser(page);
List <PdfToken> parameters = new List <PdfToken>();
while (tokenizer.NextToken())
{
var token = PdfToken.Create(tokenizer);
if (token.IsOperand)
{
strategy.Execute(new PdfOperation(token, parameters));
parameters.Clear();
}
else
{
parameters.Add(token);
}
}
}
}
}
IDictionary <string, IList <object> > ParseDAParam(PdfString DA)
{
IDictionary <string, IList <object> > commandArguments = new Dictionary <string, IList <object> >();
PRTokeniser tokeniser = new PRTokeniser(new RandomAccessFileOrArray(new RandomAccessSourceFactory().CreateSource(DA.GetBytes())));
IList <object> currentArguments = new List <object>();
while (tokeniser.NextToken())
{
if (tokeniser.TokenType == PRTokeniser.TokType.OTHER)
{
String key = tokeniser.StringValue;
if (key == "RG" || key == "G" || key == "K")
{
key = STROKE_COLOR;
}
else if (key == "rg" || key == "g" || key == "k")
{
key = FILL_COLOR;
}
if (commandArguments.ContainsKey(key))
{
commandArguments[key] = currentArguments;
}
else
{
commandArguments.Add(key, currentArguments);
}
currentArguments = new List <object>();
}
else
{
switch (tokeniser.TokenType)
{
case PRTokeniser.TokType.NUMBER:
currentArguments.Add(new PdfNumber(tokeniser.StringValue));
break;
case PRTokeniser.TokType.NAME:
currentArguments.Add(new PdfName(tokeniser.StringValue));
break;
default:
currentArguments.Add(tokeniser.StringValue);
break;
}
}
}
return(commandArguments);
}
virtual public bool CompareInnerText(String path1, String path2)
{
PdfReader reader1 = new PdfReader(path1);
byte[] streamBytes1 = reader1.GetPageContent(1);
PRTokeniser tokenizer1 =
new PRTokeniser(new RandomAccessFileOrArray(new RandomAccessSourceFactory().CreateSource(streamBytes1)));
PdfReader reader2 = new PdfReader(path2);
byte[] streamBytes2 = reader2.GetPageContent(1);
PRTokeniser tokenizer2 =
new PRTokeniser(new RandomAccessFileOrArray(new RandomAccessSourceFactory().CreateSource(streamBytes2)));
try {
while (tokenizer1.NextToken())
{
if (!tokenizer2.NextToken())
{
return(false);
}
else
{
if (tokenizer1.TokenType != tokenizer2.TokenType)
{
return(false);
}
else
{
if (tokenizer1.TokenType == tokenizer2.TokenType && tokenizer2.TokenType == PRTokeniser.TokType.NUMBER)
{
if (Math.Abs(float.Parse(tokenizer1.StringValue, CultureInfo.InvariantCulture)
- float.Parse(tokenizer2.StringValue, CultureInfo.InvariantCulture)) > 0.001)
{
return(false);
}
}
else if (!tokenizer1.StringValue.Equals(tokenizer2.StringValue))
{
return(false);
}
}
}
}
return(true);
}
finally {
reader1.Close();
reader2.Close();
}
}
public string ParsePdf(string filePath)
{
string text = string.Empty;
PdfReader reader = new iTextSharp.text.pdf.PdfReader(filePath);
byte[] streamBytes = reader.GetPageContent(1);
FileStream fStream = File.OpenRead(filePath);
byte[] contents = new byte[fStream.Length];
fStream.Read(contents, 0, (int)fStream.Length);
fStream.Close();
string s = Encoding.UTF8.GetString(contents, 0, contents.Length);
var table = (Encoding.Default.GetString(streamBytes, 0, streamBytes.Length - 1)).Split(new string[] { "\r\n", "\r", "\n" }, StringSplitOptions.None);
byte[] buf = Encoding.Convert(Encoding.GetEncoding("iso-8859-1"), Encoding.UTF8, streamBytes);
string tempString = Encoding.UTF8.GetString(buf, 0, buf.Count());
PRTokeniser tokenizer = new PRTokeniser(streamBytes);
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TK_STRING)
{
text += tokenizer.StringValue;
}
}
// create a reader (constructor overloaded for path to local file or URL)
//PdfReader reader
// = new PdfReader("http://www.chinehamchat.com/Chineham_Chat_Advertisements.pdf");
// 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;
//Console.WriteLine("Size of page 1 of {0} => {1} × {2}", n, width, height);
// file properties
Hashtable infoHash = reader.Info;
ICollection keys = infoHash.Keys;
// Dictionary<string, string> infodict = (Dictionary<string,string>)reader.Info;
foreach (string key in keys)
{
text += key + " => " + infoHash[key];
}
// Console.WriteLine(key+ " => " + infoHash[key]);
return(text);
}
// ---------------------------------------------------------------------------
/**
* Parses the PDF using PRTokeniser
* @param src the ]original PDF file
* ] */
public string ParsePdf(byte[] src)
{
PdfReader reader = new PdfReader(src);
// we can inspect the syntax of the imported page
byte[] streamBytes = reader.GetPageContent(1);
StringBuilder sb = new StringBuilder();
PRTokeniser tokenizer = new PRTokeniser(streamBytes);
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TokType.STRING)
{
sb.AppendLine(tokenizer.StringValue);
}
}
return(sb.ToString());
}
/// <summary>
/// Old algorithm designed to work with iTextSharp 4.1.6. Use iTextSharp version >= 5 if possible (license changes were made).
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
internal static string ExtractTextFromPdfBytes(byte[] input)
{
if (input == null || input.Length == 0)
{
return("");
}
var result = new StringBuilder();
var tokeniser = new PRTokeniser(input);
try
{
while (tokeniser.NextToken())
{
var tknType = tokeniser.TokenType;
var tknValue = tokeniser.StringValue.Replace('\0', ' ');
if (tknType == PRTokeniser.TK_STRING)
{
result.Append(tknValue);
}
else
{
switch (tknValue)
{
case "-600":
result.Append(" ");
break;
case "TJ":
result.Append(" ");
break;
}
}
}
}
finally
{
tokeniser.Close();
}
return(result.ToString());
}
public List <DataTable> Load(MemoryStream stream)
{
var tables = new List <DataTable>();
var sb = new StringBuilder();
var reader = new PdfReader(stream);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
var cpage = reader.GetPageN(page);
var content = cpage.Get(PdfName.CONTENTS);
var ir = (PRIndirectReference)content;
var value = reader.GetPdfObject(ir.Number);
if (value.IsStream())
{
PRStream prstream = (PRStream)value;
var streamBytes = PdfReader.GetStreamBytes(prstream);
var tokenizer = new PRTokeniser(new RandomAccessFileOrArray(streamBytes));
try
{
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TK_STRING)
{
string str = tokenizer.StringValue;
sb.AppendLine(str);
}
}
}
finally
{
tokenizer.Close();
}
}
}
Console.WriteLine(sb.ToString());
return(tables);
}
static void Main(string[] args)
{
string pdfPath = "C:\\mypdf.pdf";
PdfReader reader = new PdfReader(pdfPath);
StringBuilder sb = new StringBuilder();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
var cpage = reader.GetPageN(page);
var content = cpage.Get(PdfName.CONTENTS);
var ir = (PRIndirectReference)content;
var value = reader.GetPdfObject(ir.Number);
if (value.IsStream())
{
PRStream stream = (PRStream)value;
var streamBytes = PdfReader.GetStreamBytes(stream);
var tokenizer = new PRTokeniser(new RandomAccessFileOrArray(streamBytes));
try
{
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PRTokeniser.TK_STRING)
{
string str = tokenizer.StringValue;
sb.Append(str);
}
}
}
finally
{
tokenizer.Close();
}
}
}
Console.Write("PDF Content:" + Environment.NewLine);
Console.Write(sb.ToString());
Console.Write(Environment.NewLine + "--EOF--");
}
private static List <Line> FindRectangles(string sourceFile, int pageNumber)
{
//Source file to read from
var listOfLines = new List <Line>();
//Bind a reader to our PDF
using (PdfReader reader = new PdfReader(sourceFile))
{
//Create our buffer for previous token values. For Java users, List<string> is a generic list, probably most similar to an ArrayList
List <string> buf = new List <string>();
//Get the raw bytes for the page
byte[] pageBytes = reader.GetPageContent(pageNumber);
//Get the raw tokens from the bytes
PRTokeniser tokeniser = new PRTokeniser(new RandomAccessFileOrArray(pageBytes));
//Create some variables to set later
PRTokeniser.TokType tokenType;
string tokenValue;
int countOfLines = 0;
var AllowDecimalPoint = System.Globalization.NumberStyles.AllowDecimalPoint;
//Loop through each token
while (tokeniser.NextToken())
{
//Get the types and value
tokenType = tokeniser.TokenType;
tokenValue = tokeniser.StringValue;
//If the type is a numeric type
if (tokenType == PRTokeniser.TokType.NUMBER)
{
//Store it in our buffer for later user
buf.Add(tokenValue);
//Otherwise we only care about raw commands which are categorized as "OTHER"
}
else if (tokenType == PRTokeniser.TokType.OTHER)
{
//Look for a rectangle token
//if (tokenValue == "re")
if (tokenValue == "l")
{
//Sanity check, make sure we have enough items in the buffer
if (buf.Count < 2)
{
throw new Exception("Not enough elements in buffer for a rectangle");
}
countOfLines += 1;
//Read and convert the values
float x2 = float.Parse(buf[buf.Count - 2], AllowDecimalPoint);
float y2 = float.Parse(buf[buf.Count - 1], AllowDecimalPoint);
float x1 = float.Parse(buf[buf.Count - 4], AllowDecimalPoint);
float y1 = float.Parse(buf[buf.Count - 3], AllowDecimalPoint);
//Console.WriteLine($"{countOfLines} : ({x1}, {y1}) - ({x2}, {y2})");
listOfLines.Add(new Line()
{
BeginX = x1, BeginY = y1, EndX = x2, EndY = y2
});
//..do something with them here
}
}
}
}
listOfLines.Sort();
//foreach (Line line in listOfLines)
//{
// countOfLines += 1;
// Console.WriteLine($"{countOfLines}: {line}");
//}
return(listOfLines);
}
public void ExtractTextTest1()
{
PDFManager pdfManager = new PDFManager(); // TODO: Initialize to an appropriate value
//byte[] input = File.ReadAllBytes(DiscoveryManager.GetDiscoveryPath("M:\\DFD", "http://unicode.org/charts/PDF/U0590.pdf", ".pdf"));
byte[] input = File.ReadAllBytes(@"");
string path = @"M:\COL\hebrew.pdf";
string destinationFileName = @"M:\COL\hebrew1.pdf";
PdfReader reader = new PdfReader(path);
int n = reader.NumberOfPages;
Document document = new Document(PageSize.A4);
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(destinationFileName, FileMode.Create));
int i = 0;
document.Open();
PdfContentByte cb = writer.DirectContent;
PdfTemplate template = cb.CreateTemplate(0, 0);
while (i < n)
{
document.NewPage();
i++;
PdfImportedPage importedPage = writer.GetImportedPage(reader, i);
Image img = Image.GetInstance(importedPage);
img.ScalePercent(100);
document.Add(img);
cb.AddTemplate(importedPage, 0, 100);
}
document.Close();
writer.Close();
PdfReader pdfReader = new PdfReader(input);
StringBuilder stringBuilder = new StringBuilder();
string dingle = string.Empty;
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
stringBuilder.Append(pdfManager.ExtractText(pdfReader.GetPageContent(page)) + " ");
PRTokeniser prTokeniser = new PRTokeniser(pdfReader.GetPageContent(page));
PdfDictionary pdfDictionary = pdfReader.GetPageN(page);
byte[] dinas = pdfReader.GetPageContent(page);
string winsdgf = Encoding.GetEncoding(1255).GetString(dinas);
try
{
while (prTokeniser.NextToken())
{
if (prTokeniser.TokenType == PRTokeniser.TokType.STRING)
{
dingle += prTokeniser.StringValue;
try
{
//dingle += (char)(int.Parse(prTokeniser.StringValue));
//dingle += iTextSharp.text.Utilities.ConvertFromUtf32(prTokeniser.FilePointer);
//dingle += ((char)prTokeniser.Read()).ToString();
dingle += prTokeniser.ReadString(2);
Chunk chunk = new Chunk(prTokeniser.StringValue);
//string wangle = PRTokeniser.GetHex(prTokeniser.IntValue).ToString();
}
catch (Exception)
{
}
}
}
}
catch (Exception)
{
{
}
//throw;
}
//int ij = 0;
// #
//If Not IsNothing(pageBytes) Then
//#
// token = New PRTokeniser(pageBytes)
//#
// While token.NextToken()
//#
// tknType = token.TokenType()
//#
// tknValue = token.StringValue
//#
// If tknType = PRTokeniser.TK_STRING Then
//#
// sb.Append(token.StringValue)
//#
// 'I need to add these additional tests to properly add whitespace to the output string
//#
// ElseIf tknType = 1 AndAlso tknValue = "-600" Then
//#
// sb.Append(" ")
//#
// ElseIf tknType = 10 AndAlso tknValue = "TJ" Then
//#
// sb.Append(" ")
//#
// End If
//#
// End While
}
string actual = pdfManager.ExtractText(input);
}
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;
}
PdfReader pdfReader = new PdfReader(propertyBag.Response);
try
{
object title = pdfReader.Info["Title"];
if (!title.IsNull())
{
string pdfTitle = Convert.ToString(title, CultureInfo.InvariantCulture).Trim();
if (!pdfTitle.IsNullOrEmpty())
{
propertyBag.Title = pdfTitle;
}
}
StringBuilder sb = new StringBuilder();
// Following code from:
// http://www.vbforums.com/showthread.php?t=475759
for (int p = 1; p <= pdfReader.NumberOfPages; p++)
{
byte[] pageBytes = pdfReader.GetPageContent(p);
if (pageBytes.IsNull())
{
continue;
}
PRTokeniser token = new PRTokeniser(pageBytes);
while (token.NextToken())
{
int tknType = token.TokenType;
string tknValue = token.StringValue;
if (tknType == PRTokeniser.TK_STRING)
{
sb.Append(token.StringValue);
sb.Append(" ");
}
else if (tknType == 1 && tknValue == "-600")
{
sb.Append(" ");
}
else if (tknType == 10 && tknValue == "TJ")
{
sb.Append(" ");
}
}
}
propertyBag.Text = sb.ToString();
}
finally
{
pdfReader.Close();
}
}
