Extract text and text rectangle coordinates from a Pdf file using itextsharp

Question

I\'m trying to get all words and their location coordinates from a PDF file. I\'ve succeeded using the Acrobat API on .NET. Now, I\'m trying to get the same res

Answer 1

My account is too new reply to Mark Storer's answer.

I wasn't able to directly use the LocationTextExtracationStrategy (I think I must be doing something wrong). When I used the LocationTextExtracationStrategy I was able to get the text but I couldn't figure out how to get the coords for each string (or line of strings).

I ended up subclassing the LocationTextExtracationStrategy and exposing the data I wanted because it does have it internally.

I also wanted it in .net... so here is a sloppy C# version of what I put together.

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;

using iTextSharp.text.pdf.parser;

namespace PdfHelper
{
    /// 

    /// Taken from http://www.java-frameworks.com/java/itext/com/itextpdf/text/pdf/parser/LocationTextExtractionStrategy.java.html
    /// 
    class LocationTextExtractionStrategyEx : LocationTextExtractionStrategy
    {
        private List m_locationResult = new List();
        private List m_TextLocationInfo = new List();
        public List LocationResult 
        {
            get { return m_locationResult; }
        }
        public List TextLocationInfo
        {
            get { return m_TextLocationInfo; }
        }

        /// 

        /// Creates a new LocationTextExtracationStrategyEx
        /// 
        public LocationTextExtractionStrategyEx()
        {
        }

        /// 

        /// Returns the result so far
        /// 
        /// a String with the resulting text
        public override String GetResultantText()
        {
            m_locationResult.Sort();

            StringBuilder sb = new StringBuilder();
            TextChunk lastChunk = null;
            TextInfo lastTextInfo = null;
            foreach (TextChunk chunk in m_locationResult)
            {
                if (lastChunk == null)
                {
                    sb.Append(chunk.Text);
                    lastTextInfo = new TextInfo(chunk);
                    m_TextLocationInfo.Add(lastTextInfo);
                }
                else
                {
                    if (chunk.sameLine(lastChunk))
                    {
                        float dist = chunk.distanceFromEndOf(lastChunk);

                        if (dist < -chunk.CharSpaceWidth)
                        {
                            sb.Append(' ');
                            lastTextInfo.addSpace();
                        }
                        //append a space if the trailing char of the prev string wasn't a space && the 1st char of the current string isn't a space
                        else if (dist > chunk.CharSpaceWidth / 2.0f && chunk.Text[0] != ' ' && lastChunk.Text[lastChunk.Text.Length - 1] != ' ')
                        {
                            sb.Append(' ');
                            lastTextInfo.addSpace();
                        }
                        sb.Append(chunk.Text);
                        lastTextInfo.appendText(chunk);
                    }
                    else
                    {
                        sb.Append('\n');
                        sb.Append(chunk.Text);
                        lastTextInfo = new TextInfo(chunk);
                        m_TextLocationInfo.Add(lastTextInfo);
                    }
                }
                lastChunk = chunk;
            }
            return sb.ToString();
        }

        /// 

        /// 
        /// 
        /// 
        public override void RenderText(TextRenderInfo renderInfo)
        {
            LineSegment segment = renderInfo.GetBaseline();
            TextChunk location = new TextChunk(renderInfo.GetText(), segment.GetStartPoint(), segment.GetEndPoint(), renderInfo.GetSingleSpaceWidth(), renderInfo.GetAscentLine(), renderInfo.GetDescentLine());
            m_locationResult.Add(location);
        }

        public class TextChunk : IComparable, ICloneable
        {
            string m_text;
            Vector m_startLocation;
            Vector m_endLocation;
            Vector m_orientationVector;
            int m_orientationMagnitude;
            int m_distPerpendicular;
            float m_distParallelStart;
            float m_distParallelEnd;
            float m_charSpaceWidth;

            public LineSegment AscentLine;
            public LineSegment DecentLine;

            public object Clone()
            {
                TextChunk copy = new TextChunk(m_text, m_startLocation, m_endLocation, m_charSpaceWidth, AscentLine, DecentLine);
                return copy;
            }

            public string Text
            {
                get { return m_text; }
                set { m_text = value; }
            }
            public float CharSpaceWidth
            {
                get { return m_charSpaceWidth; }
                set { m_charSpaceWidth = value; }
            }
            public Vector StartLocation
            {
                get { return m_startLocation; }
                set { m_startLocation = value; }
            }
            public Vector EndLocation
            {
                get { return m_endLocation; }
                set { m_endLocation = value; }
            }

            /// 

            /// Represents a chunk of text, it's orientation, and location relative to the orientation vector
            /// 
            /// 
            /// 
            /// 
            /// 
            public TextChunk(string txt, Vector startLoc, Vector endLoc, float charSpaceWidth, LineSegment ascentLine, LineSegment decentLine)
            {
                m_text = txt;
                m_startLocation = startLoc;
                m_endLocation = endLoc;
                m_charSpaceWidth = charSpaceWidth;
                AscentLine = ascentLine;
                DecentLine = decentLine;

                m_orientationVector = m_endLocation.Subtract(m_startLocation).Normalize();
                m_orientationMagnitude = (int)(Math.Atan2(m_orientationVector[Vector.I2], m_orientationVector[Vector.I1]) * 1000);

                // see http://mathworld.wolfram.com/Point-LineDistance2-Dimensional.html
                // the two vectors we are crossing are in the same plane, so the result will be purely
                // in the z-axis (out of plane) direction, so we just take the I3 component of the result
                Vector origin = new Vector(0, 0, 1);
                m_distPerpendicular = (int)(m_startLocation.Subtract(origin)).Cross(m_orientationVector)[Vector.I3];

                m_distParallelStart = m_orientationVector.Dot(m_startLocation);
                m_distParallelEnd = m_orientationVector.Dot(m_endLocation);
            }

            /// 

            /// true if this location is on the the same line as the other text chunk
            /// 
            /// the location to compare to
            /// true if this location is on the the same line as the other
            public bool sameLine(TextChunk textChunkToCompare)
            {
                if (m_orientationMagnitude != textChunkToCompare.m_orientationMagnitude) return false;
                if (m_distPerpendicular != textChunkToCompare.m_distPerpendicular) return false;
                return true;
            }

            /// 

            /// Computes the distance between the end of 'other' and the beginning of this chunk
            /// in the direction of this chunk's orientation vector.  Note that it's a bad idea
            /// to call this for chunks that aren't on the same line and orientation, but we don't
            /// explicitly check for that condition for performance reasons.
            /// 
            /// 
            /// the number of spaces between the end of 'other' and the beginning of this chunk
            public float distanceFromEndOf(TextChunk other)
            {
                float distance = m_distParallelStart - other.m_distParallelEnd;
                return distance;
            }

            /// 

            /// Compares based on orientation, perpendicular distance, then parallel distance
            /// 
            /// 
            /// 
            public int CompareTo(object obj)
            {
                if (obj == null) throw new ArgumentException("Object is now a TextChunk");

                TextChunk rhs = obj as TextChunk;
                if (rhs != null)
                {
                    if (this == rhs) return 0;

                    int rslt;
                    rslt = m_orientationMagnitude - rhs.m_orientationMagnitude;
                    if (rslt != 0) return rslt;

                    rslt = m_distPerpendicular - rhs.m_distPerpendicular;
                    if (rslt != 0) return rslt;

                    // note: it's never safe to check floating point numbers for equality, and if two chunks
                    // are truly right on top of each other, which one comes first or second just doesn't matter
                    // so we arbitrarily choose this way.
                    rslt = m_distParallelStart < rhs.m_distParallelStart ? -1 : 1;

                    return rslt;
                }
                else
                {
                    throw new ArgumentException("Object is now a TextChunk");
                }
            }
        }

        public class TextInfo
        {
            public Vector TopLeft;
            public Vector BottomRight;
            private string m_Text;

            public string Text
            {
                get { return m_Text; }
            }

            /// 

            /// Create a TextInfo.
            /// 
            /// 
            public TextInfo(TextChunk initialTextChunk)
            {
                TopLeft = initialTextChunk.AscentLine.GetStartPoint();
                BottomRight = initialTextChunk.DecentLine.GetEndPoint();
                m_Text = initialTextChunk.Text;
            }

            /// 

            /// Add more text to this TextInfo.
            /// 
            /// 
            public void appendText(TextChunk additionalTextChunk)
            {
                BottomRight = additionalTextChunk.DecentLine.GetEndPoint();
                m_Text += additionalTextChunk.Text;
            }

            /// 

            /// Add a space to the TextInfo.  This will leave the endpoint out of sync with the text.
            /// The assumtion is that you will add more text after the space which will correct the endpoint.
            /// 
            public void addSpace()
            {
                m_Text += ' ';
            }


        }
    }
}

I added a TextLocationInfo property which hands back a List of lines of text + the coords for those lines (upper left and lower right) which can be used to give you a bounding box.

I also saw something odd with my initial playing around. It looked like I got the same coords if I pulled the startPoint & endPoint from the baseline (I think the right thing to do, and the thing I did, was to pull those points from ascentLine and DecentLine). My initial pass I just used the baseline. Odd that I didn't see a difference in the resulting coords. So word to the wary... I'm not sure if the coords I'm providing are right... I just think they are/should be.