MARKUS

using iTextSharp.text.pdf.parser;

using System;

using System.Collections.Generic;

using System.Linq;

using System.Text;

using System.Threading.Tasks;

using static iTextSharp.text.pdf.parser.LocationTextExtractionStrategy;

namespace MarkupToPDF.Common

{

    public class LocationTextExtractionStrategyWithPosition : LocationTextExtractionStrategy

    {

        private readonly List<TextChunk> locationalResult = new List<TextChunk>();

        private readonly ITextChunkLocationStrategy tclStrat;

        public LocationTextExtractionStrategyWithPosition() : this(new TextChunkLocationStrategyDefaultImp())

        {

        }

        /**

         * Creates a new text extraction renderer, with a custom strategy for

         * creating new TextChunkLocation objects based on the input of the

         * TextRenderInfo.

         * @param strat the custom strategy

         */

        public LocationTextExtractionStrategyWithPosition(ITextChunkLocationStrategy strat)

        {

            tclStrat = strat;

        }

        private bool StartsWithSpace(string str)

        {

            if (str.Length == 0) return false;

            return str[0] == ' ';

        }

        private bool EndsWithSpace(string str)

        {

            if (str.Length == 0) return false;

            return str[str.Length - 1] == ' ';

        }

        /**

         * Filters the provided list with the provided filter

         * @param textChunks a list of all TextChunks that this strategy found during processing

         * @param filter the filter to apply.  If null, filtering will be skipped.

         * @return the filtered list

         * @since 5.3.3

         */

        private List<TextChunk> filterTextChunks(List<TextChunk> textChunks, ITextChunkFilter filter)

        {

            if (filter == null)

            {

                return textChunks;

            }

            var filtered = new List<TextChunk>();

            foreach (var textChunk in textChunks)

            {

                if (filter.Accept(textChunk))

                {

                    filtered.Add(textChunk);

                }

            }

            return filtered;

        }

        public override void RenderText(TextRenderInfo renderInfo)

        {

            LineSegment segment = renderInfo.GetBaseline();

            if (renderInfo.GetRise() != 0)

            { // remove the rise from the baseline - we do this because the text from a super/subscript render operations should probably be considered as part of the baseline of the text the super/sub is relative to 

                Matrix riseOffsetTransform = new Matrix(0, -renderInfo.GetRise());

                segment = segment.TransformBy(riseOffsetTransform);

            }

            TextChunk tc = new TextChunk(renderInfo.GetText(), tclStrat.CreateLocation(renderInfo, segment));

            locationalResult.Add(tc);

        }

        public IList<TextLocation> GetLocations()

        {

            var filteredTextChunks = filterTextChunks(locationalResult, null);

            filteredTextChunks.Sort();

            TextChunk lastChunk = null;

            var textLocations = new List<TextLocation>();

            foreach (var chunk in filteredTextChunks)

            {

                if (lastChunk == null)

                {

                    //initial

                    textLocations.Add(new TextLocation

                    {

                        Text = chunk.Text,

                        X = iTextSharp.text.Utilities.PointsToMillimeters(chunk.Location.StartLocation[0]),

                        Y = iTextSharp.text.Utilities.PointsToMillimeters(chunk.Location.StartLocation[1])

                    });

                }

                else

                {

                    if (chunk.SameLine(lastChunk))

                    {

                        var text = "";

                        // we only insert a blank space if the trailing character of the previous string wasn't a space, and the leading character of the current string isn't a space

                        if (IsChunkAtWordBoundary(chunk, lastChunk) && !StartsWithSpace(chunk.Text) && !EndsWithSpace(lastChunk.Text))

                            text += ' ';

                        text += chunk.Text;

                        textLocations[textLocations.Count - 1].Text += text;

                    }

                    else

                    {

                        textLocations.Add(new TextLocation

                        {

                            Text = chunk.Text,

                            X = iTextSharp.text.Utilities.PointsToMillimeters(chunk.Location.StartLocation[0]),

                            Y = iTextSharp.text.Utilities.PointsToMillimeters(chunk.Location.StartLocation[1])

                        });

                    }

                }

                lastChunk = chunk;

            }

            //now find the location(s) with the given texts

            return textLocations;

        }

    }

    public class TextLocation

    {

        public float X { get; set; }

        public float Y { get; set; }

        public string Text { get; set; }

    }

    public class LocationTextExtractionStrategyEx : LocationTextExtractionStrategy

    {

        private List<TextChunk> m_locationResult = new List<TextChunk>();

        private List<TextInfo> m_TextLocationInfo = new List<TextInfo>();

        public List<TextChunk> LocationResult

        {

            get { return m_locationResult; }

        }

        public List<TextInfo> TextLocationInfo

        {

            get { return m_TextLocationInfo; }

        }

        /// <summary>

        /// Creates a new LocationTextExtracationStrategyEx

        /// </summary>

        public LocationTextExtractionStrategyEx()

        {

        }

        /// <summary>

        /// Returns the result so far

        /// </summary>

        /// <returns>a String with the resulting text</returns>

        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();

        }

        /// <summary>

        /// 

        /// </summary>

        /// <param name="renderInfo"></param>

        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; }

            }

            /// <summary>

            /// Represents a chunk of text, it's orientation, and location relative to the orientation vector

            /// </summary>

            /// <param name="txt"></param>

            /// <param name="startLoc"></param>

            /// <param name="endLoc"></param>

            /// <param name="charSpaceWidth"></param>

            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);

            }

            /// <summary>

            /// true if this location is on the the same line as the other text chunk

            /// </summary>

            /// <param name="textChunkToCompare">the location to compare to</param>

            /// <returns>true if this location is on the the same line as the other</returns>

            public bool sameLine(TextChunk textChunkToCompare)

            {

                if (m_orientationMagnitude != textChunkToCompare.m_orientationMagnitude) return false;

                if (m_distPerpendicular != textChunkToCompare.m_distPerpendicular) return false;

                return true;

            }

            /// <summary>

            /// 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.

            /// </summary>

            /// <param name="other"></param>

            /// <returns>the number of spaces between the end of 'other' and the beginning of this chunk</returns>

            public float distanceFromEndOf(TextChunk other)

            {

                float distance = m_distParallelStart - other.m_distParallelEnd;

                return distance;

            }

            /// <summary>

            /// Compares based on orientation, perpendicular distance, then parallel distance

            /// </summary>

            /// <param name="obj"></param>

            /// <returns></returns>

            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; }

            }

            /// <summary>

            /// Create a TextInfo.

            /// </summary>

            /// <param name="initialTextChunk"></param>

            public TextInfo(TextChunk initialTextChunk)

            {

                TopLeft = initialTextChunk.AscentLine.GetStartPoint();

                BottomRight = initialTextChunk.DecentLine.GetEndPoint();

                m_Text = initialTextChunk.Text;

            }

            /// <summary>

            /// Add more text to this TextInfo.

            /// </summary>

            /// <param name="additionalTextChunk"></param>

            public void appendText(TextChunk additionalTextChunk)

            {

                BottomRight = additionalTextChunk.DecentLine.GetEndPoint();

                m_Text += additionalTextChunk.Text;

            }

            /// <summary>

            /// 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.

            /// </summary>

            public void addSpace()

            {

                m_Text += ' ';

            }

        }

    }

    public class HoneyheadTEXT

    {

        public int PageNo { get; set; }

        public string Text { get; set; }

        public pdftron.PDF.Rect Bounds { get; set; }

    }

    public class PDFSearchText

    {

        public PDFSearchText()

        {

            pdftron.PDFNet.Initialize("daelim.co.kr(Doftech Corp):CPU:2::W:AMC(20120315):EF6E886F25A414FFB5F8C1F2999CF2DA33DC6C5164315BAF7011B87AF0FA");

        }

        public List<HoneyheadTEXT> GetPageText(string inputPdf, int pageNumber, bool IsSearchAllPage)

        {

            IList<TextLocation> res = null;

            List<HoneyheadTEXT> txtSet = new List<HoneyheadTEXT>();

            using (pdftron.PDF.PDFDoc doc = new pdftron.PDF.PDFDoc(inputPdf))

            {

                doc.InitSecurityHandler();

                if (IsSearchAllPage)

                {

                    for (int i = 1; i <= doc.GetPageCount(); i++)

                    {

                        pdftron.PDF.Page page = doc.GetPage(i);

                        using (pdftron.PDF.TextExtractor txt = new pdftron.PDF.TextExtractor())

                        {

                            txt.Begin(page);  // Read the page.

                                              //pdftron.PDF.Rect bbox;

                                              //int cur_flow_id = -1, cur_para_id = -1;

                            //TextExtractor.Line line;

                            //TextExtractor.Word word;

                            //TextExtractor.Style s, line_style;

                            //// For each line on the page...

                            //for (line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())

                            //{

                            //}

                            //String text = txt.GetAsXML(TextExtractor.XMLOutputFlags.e_output_bbox);

                            pdftron.PDF.TextExtractor.Word word;

                            for (pdftron.PDF.TextExtractor.Line line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())

                            {

                                for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())

                                {

                                    string text = word.GetString();

                                    var data = word.GetBBox();

                                    //wordString += word.GetString() + " ";

                                    txtSet.Add(new HoneyheadTEXT { Text = text, Bounds = data, PageNo = i });

                                }

                            }

                        }

                    }

                }

                else

                {

                    pdftron.PDF.Page page = doc.GetPage(pageNumber);

                    if (page == null)

                    {

                        return txtSet;

                    }

                    using (pdftron.PDF.TextExtractor txt = new pdftron.PDF.TextExtractor())

                    {

                        txt.Begin(page);  // Read the page.

                                          //pdftron.PDF.Rect bbox;

                                          //int cur_flow_id = -1, cur_para_id = -1;

                        //TextExtractor.Line line;

                        //TextExtractor.Word word;

                        //TextExtractor.Style s, line_style;

                        //// For each line on the page...

                        //for (line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())

                        //{

                        //}

                        //String text = txt.GetAsXML(TextExtractor.XMLOutputFlags.e_output_bbox);

                        pdftron.PDF.TextExtractor.Word word;

                        for (pdftron.PDF.TextExtractor.Line line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())

                        {

                            for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())

                            {

                                string text = word.GetString();

                                var data = word.GetBBox();

                                //wordString += word.GetString() + " ";

                                txtSet.Add(new HoneyheadTEXT { Text = text, Bounds = data, PageNo = pageNumber });

                            }

                        }

                    }

                }

                return txtSet;

            }

        }

    }

}

    <Reference Include="PDFNet, Version=5.8.0.0, Culture=neutral, PublicKeyToken=36167be3f67ac39c, processorArchitecture=x86">

      <SpecificVersion>False</SpecificVersion>

      <HintPath>..\packages\PDFNet.dll</HintPath>

    </Reference>

    <Compile Include="Common\LocationTextExtractionStrategyWithPosition.cs" />