how can i get text formatting with iTextSharp

Question

I am using iTextSharp to read text contents from PDF. I am able to read that also. But I am loosing text formatting like the font, color etc. Is there any way to get that formatting as well.

Below is the code segment i am using to exact text -

PdfReader reader = new PdfReader("F:\EBooks\AspectsOfAjax.pdf");
textBox1.Text = ExtractTextFromPDFBytes(reader.GetPageContent(1));

private string ExtractTextFromPDFBytes(byte[] input)
{
    if (input == null || input.Length == 0) return "";
    try
    {
        string resultString = "";
        // Flag showing if we are we currently inside a text object
        bool inTextObject = false;
        // Flag showing if the next character is literal  e.g. '\' to get a '\' character or '\(' to get '('
        bool nextLiteral = false;
        // () Bracket nesting level. Text appears inside ()
        int bracketDepth = 0;
        // Keep previous chars to get extract numbers etc.:
        char[] previousCharacters = new char[_numberOfCharsToKeep];
        for (int j = 0; j < _numberOfCharsToKeep; j++) previousCharacters[j] = ' ';
        for (int i = 0; i < input.Length; i++)
        {
            char c = (char)input[i];
            if (inTextObject)
            {
                // Position the text
                if (bracketDepth == 0)
                {
                    if (CheckToken(new string[] { "TD", "Td" }, previousCharacters))
                    {
                        resultString += "\n\r";
                    }
                    else
                    {
                        if (CheckToken(new string[] {"'", "T*", """}, previousCharacters))
                        {
                            resultString += "\n";
                        }
                        else
                        {
                            if (CheckToken(new string[] { "Tj" }, previousCharacters))
                            {
                                resultString += " ";
                            }
                        }
                    }
                }
                // End of a text object, also go to a new line.
                if (bracketDepth == 0 && CheckToken( new string[]{"ET"}, previousCharacters))
                {
                    inTextObject = false;
                    resultString += " ";
                }
                else
                {
                    // Start outputting text
                    if ((c == '(') && (bracketDepth == 0) && (!nextLiteral))
                    {
                        bracketDepth = 1;
                    }
                    else
                    {
                        // Stop outputting text
                        if ((c == ')') && (bracketDepth == 1) && (!nextLiteral))
                        {
                            bracketDepth = 0;
                        }
                        else
                        {
                            // Just a normal text character:
                            if (bracketDepth == 1)
                            {
                                // Only print out next character no matter what. 
                                // Do not interpret.
                                if (c == '\' && !nextLiteral)
                                {
                                    nextLiteral = true;
                                }
                                else
                                {
                                    if (((c >= ' ') && (c <= '~')) || ((c >= 128) && (c < 255)))
                                    {
                                        resultString += c.ToString();
                                    }
                                    nextLiteral = false;
                                }
                            }
                        }
                    }
                }
            }
            // Store the recent characters for when we have to go back for a checking
            for (int j = 0; j < _numberOfCharsToKeep - 1; j++)
            {
                previousCharacters[j] = previousCharacters[j + 1];
            }
            previousCharacters[_numberOfCharsToKeep - 1] = c;

            // Start of a text object
            if (!inTextObject && CheckToken(new string[]{"BT"}, previousCharacters))
            {
                inTextObject = true;
            }
        }
        return resultString;
    }
    catch
    {
        return "";
    }
}

private bool CheckToken(string[] tokens, char[] recent)
{
    foreach(string token in tokens)
    {
        if ((recent[_numberOfCharsToKeep - 3] == token[0]) &&
            (recent[_numberOfCharsToKeep - 2] == token[1]) &&
            ((recent[_numberOfCharsToKeep - 1] == ' ') ||
            (recent[_numberOfCharsToKeep - 1] == 0x0d) ||
            (recent[_numberOfCharsToKeep - 1] == 0x0a)) &&
            ((recent[_numberOfCharsToKeep - 4] == ' ') ||
            (recent[_numberOfCharsToKeep - 4] == 0x0d) ||
            (recent[_numberOfCharsToKeep - 4] == 0x0a))
            )
        {
            return true;
        }
    }
    return false;
}

user_2206871 · Answer

I converted @Chris code to Java if anyone is looking for it

import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.parser.ImageRenderInfo;
import com.itextpdf.text.pdf.parser.TextExtractionStrategy;
import com.itextpdf.text.pdf.parser.TextRenderInfo;
import com.itextpdf.text.pdf.parser.Vector;

public class TextWithFontExtractionStategy implements TextExtractionStrategy {
//HTML buffer
private StringBuilder result = new StringBuilder();

//Store last used properties
private Vector lastBaseLine;
private String lastFont;
private float lastFontSize;

//http://api.itextpdf.com/itext/com/itextpdf/text/pdf/parser/TextRenderInfo.html
private enum TextRenderMode
{
    FillText(0),
    StrokeText(1),
    FillThenStrokeText(2),
    Invisible(3),
    FillTextAndAddToPathForClipping(4),
    StrokeTextAndAddToPathForClipping(5),
    FillThenStrokeTextAndAddToPathForClipping(6),
    AddTextToPaddForClipping(7);

    private int value;

    TextRenderMode(int value) {
        this.value = value;
    }

    public int getValue() {
        return value;
    }
}

    public void renderText(TextRenderInfo renderInfo)
    {
        String curFont = renderInfo.getFont().getPostscriptFontName();
        //Check if faux bold is used
        if ((renderInfo.getTextRenderMode() == TextRenderMode.FillThenStrokeText.getValue()))
        {
            curFont += "-Bold";
        }

        //This code assumes that if the baseline changes then we're on a newline
        Vector curBaseline = renderInfo.getBaseline().getStartPoint();
        Vector topRight = renderInfo.getAscentLine().getEndPoint();
        Rectangle rect = new Rectangle(curBaseline.get(Vector.I1), curBaseline.get(Vector.I2), topRight.get(Vector.I1), topRight.get(Vector.I2));
        float curFontSize = rect.getHeight();

        //See if something has changed, either the baseline, the font or the font size
        if ((this.lastBaseLine == null) || (curBaseline.get(Vector.I2) != lastBaseLine.get(Vector.I2)) || (curFontSize != lastFontSize) || (curFont != lastFont))
        {
            //if we've put down at least one span tag close it
            if ((this.lastBaseLine != null))
            {
                this.result.append("").append("
");
            }
            //If the baseline has changed then insert a line break
            if ((this.lastBaseLine != null) && curBaseline.get(Vector.I2) != lastBaseLine.get(Vector.I2))
            {
                this.result.append("
").append("
");
            }
            //Create an HTML tag with appropriate styles
            this.result.append(String.format("", curFont, curFontSize));
        }

        //Append the current text
        this.result.append(renderInfo.getText() + " ");

        //Set currently used properties
        this.lastBaseLine = curBaseline;
        this.lastFontSize = curFontSize;
        this.lastFont = curFont;
    }

    public String getResultantText()
    {
        //If we wrote anything then we'll always have a missing closing tag so close it here
        if (result.length() > 0)
        {
            result.append("");
        }
        return result.toString();
    }

    //Not needed
    public void beginTextBlock() { }
    public void endTextBlock() { }
    public void renderImage(ImageRenderInfo renderInfo) { }

}

how can i get text formatting with iTextSharp

2 Answers