MARKUS

using iTextSharp.text.pdf;

using iTextSharp.text.pdf.parser;

using System;

using System.Collections.Generic;

using System.IO;

using System.IO.Compression;

using System.Linq;

using System.Text;

namespace TEST

{

    public class RectAndText

    {

        public iTextSharp.text.Rectangle Rect;

        public String Text;

        public RectAndText(iTextSharp.text.Rectangle rect, String text)

        {

            this.Rect = rect;

            this.Text = text;

        }

    }

    //public class MyLocationTextExtractionStrategy : LocationTextExtractionStrategy

    //{

    //    //Hold each coordinate

    //    public List<RectAndText> myPoints = new List<RectAndText>();

    //    //Automatically called for each chunk of text in the PDF

    //    public override void RenderText(TextRenderInfo renderInfo)

    //    {

    //        base.RenderText(renderInfo);

    //        //Get the bounding box for the chunk of text

    //        var bottomLeft = renderInfo.GetDescentLine().GetStartPoint();

    //        var topRight = renderInfo.GetAscentLine().GetEndPoint();

    //        //Create a rectangle from it

    //        var rect = new iTextSharp.text.Rectangle(

    //                                                bottomLeft[Vector.I1],

    //                                                bottomLeft[Vector.I2],

    //                                                topRight[Vector.I1],

    //                                                topRight[Vector.I2]

    //                                                );

    //        //Add this to our main collection

    //        this.myPoints.Add(new RectAndText(rect, renderInfo.GetText()));

    //    }

    //}

    public class TopToBottomTextExtractionStrategy : ITextExtractionStrategy //라인에 텍스트 찾는

    {

        private Vector lastStart;

        private Vector lastEnd;

        //Store each line individually. A SortedDictionary will automatically shuffle things around based on the key

        public SortedDictionary<int, StringBuilder> results = new SortedDictionary<int, StringBuilder>();

        //Constructor and some methods that aren't used

        public TopToBottomTextExtractionStrategy() { }

        public virtual void BeginTextBlock() { }

        public virtual void EndTextBlock() { }

        public virtual void RenderImage(ImageRenderInfo renderInfo) { }

        //Convert our lines into a giant block of text

        public virtual String GetResultantText()

        {

            //Buffer

            StringBuilder buf = new StringBuilder();

            //Loop through each line (which is already sorted top to bottom)

            foreach (var s in results)

            {

                //Append to the buffer

                buf.AppendLine(s.Value.ToString());

            }

            return buf.ToString();

        }

        public virtual void RenderText(TextRenderInfo renderInfo)

        {

            bool firstRender = results.Count == 0;

            LineSegment segment = renderInfo.GetBaseline();

            Vector start = segment.GetStartPoint();

            Vector end = segment.GetEndPoint();

            //Use the Y value of the bottom left corner of the text for the key

            int currentLineKey = (int)start[1];

            if (!firstRender)

            {

                Vector x0 = start;

                Vector x1 = lastStart;

                Vector x2 = lastEnd;

                float dist = (x2.Subtract(x1)).Cross((x1.Subtract(x0))).LengthSquared / x2.Subtract(x1).LengthSquared;

                float sameLineThreshold = 1f;

                //If we've detected that we're still on the same

                if (dist <= sameLineThreshold)

                {

                    //Use the previous Y coordinate

                    currentLineKey = (int)lastStart[1];

                }

            }

            //Hack: PDFs start with zero at the bottom so our keys will be upside down. Using negative keys cheats this.

            currentLineKey = currentLineKey * -1;

            //If this line hasn't been used before add a new line to our collection

            if (!results.ContainsKey(currentLineKey))

            {

                results.Add(currentLineKey, new StringBuilder());

            }

            //Insert a space between blocks of text if it appears there should be

            if (!firstRender &&                                       //First pass never needs a leading space

                results[currentLineKey].Length != 0 &&                 //Don't append a space to the begining of a line

                !results[currentLineKey].ToString().EndsWith(" ") &&  //Don't append if the current buffer ends in a space already

                renderInfo.GetText().Length > 0 &&                    //Don't append if the new next is empty

                !renderInfo.GetText().StartsWith(" "))

            {              //Don't append if the new text starts with a space

                           //Calculate the distance between the two blocks

                float spacing = lastEnd.Subtract(start).Length;

                //If it "looks" like it should be a space

                if (spacing > renderInfo.GetSingleSpaceWidth() / 2f)

                {

                    //Add a space

                    results[currentLineKey].Append(" ");

                }

            }

            //Add the text to the line in our collection

            results[currentLineKey].Append(renderInfo.GetText());

            lastStart = start;

            lastEnd = end;

        }

    }

    public class MyLocationTextExtractionStrategy : LocationTextExtractionStrategy

    {

        //Hold each coordinate

        public List<RectAndText> myPoints = new List<RectAndText>();

        //The string that we're searching for

        public String TextToSearchFor { get; set; }

        //How to compare strings

        public System.Globalization.CompareOptions CompareOptions { get; set; }

        public MyLocationTextExtractionStrategy(String textToSearchFor, System.Globalization.CompareOptions compareOptions = System.Globalization.CompareOptions.None)

        {

            this.TextToSearchFor = textToSearchFor;

            this.CompareOptions = compareOptions;

        }

        //Automatically called for each chunk of text in the PDF

        public override void RenderText(TextRenderInfo renderInfo)

        {

            base.RenderText(renderInfo);

            //if (renderInfo.GetText().Contains("기술들을"))

            //{

            //}

            //See if the current chunk contains the text

            var startPosition = System.Globalization.CultureInfo.CurrentCulture.CompareInfo.IndexOf(renderInfo.GetText(), this.TextToSearchFor, this.CompareOptions);

            //If not found bail

            if (startPosition < 0)

            {

                return;

            }

            //Grab the individual characters

            var chars = renderInfo.GetCharacterRenderInfos().Skip(startPosition).Take(this.TextToSearchFor.Length).ToList();

            //Grab the first and last character

            var firstChar = chars.First();

            var lastChar = chars.Last();

            //Get the bounding box for the chunk of text

            var bottomLeft = firstChar.GetDescentLine().GetStartPoint();

            var topRight = lastChar.GetAscentLine().GetEndPoint();

            //Create a rectangle from it

            var rect = new iTextSharp.text.Rectangle(

                                                    bottomLeft[Vector.I1],

                                                    bottomLeft[Vector.I2],

                                                    topRight[Vector.I1],

                                                    topRight[Vector.I2]

                                                    );

            //Add this to our main collection

            this.myPoints.Add(new RectAndText(rect, this.TextToSearchFor));

        }

    }

    class Program

    {

        public static string Zip(string value)

        {

            //Transform string into byte[]  

            byte[] byteArray = new byte[value.Length];

            int indexBA = 0;

            foreach (char item in value.ToCharArray())

            {

                byteArray[indexBA++] = (byte)item;

            }

            //Prepare for compress

            System.IO.MemoryStream ms = new System.IO.MemoryStream();

            System.IO.Compression.GZipStream sw = new System.IO.Compression.GZipStream(ms, System.IO.Compression.CompressionMode.Compress);

            //Compress

            sw.Write(byteArray, 0, byteArray.Length);

            //Close, DO NOT FLUSH cause bytes will go missing...

            sw.Close();

            //Transform byte[] zip data to string

            byteArray = ms.ToArray();

            System.Text.StringBuilder sB = new System.Text.StringBuilder(byteArray.Length);

            foreach (byte item in byteArray)

            {

                sB.Append((char)item);

            }

            ms.Close();

            sw.Dispose();

            ms.Dispose();

            return sB.ToString();

        }

        public static string UnZip(string value)

        {

            //Transform string into byte[]

            byte[] byteArray = new byte[value.Length];

            int indexBA = 0;

            foreach (char item in value.ToCharArray())

            {

                byteArray[indexBA++] = (byte)item;

            }

            //Prepare for decompress

            System.IO.MemoryStream ms = new System.IO.MemoryStream(byteArray);

            System.IO.Compression.GZipStream sr = new System.IO.Compression.GZipStream(ms,

                System.IO.Compression.CompressionMode.Decompress);

            //Reset variable to collect uncompressed result

            byteArray = new byte[byteArray.Length];

            //Decompress

            int rByte = sr.Read(byteArray, 0, byteArray.Length);

            //Transform byte[] unzip data to string

            System.Text.StringBuilder sB = new System.Text.StringBuilder(rByte);

            //Read the number of bytes GZipStream red and do not a for each bytes in

            //resultByteArray;

            for (int i = 0; i < rByte; i++)

            {

                sB.Append((char)byteArray[i]);

            }

            sr.Close();

            ms.Close();

            sr.Dispose();

            ms.Dispose();

            return sB.ToString();

        }

        static void Main(string[] args)

        {

            //string rr= @"data:image/gif;base64,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";

            //var ra = Zip(rr);

            //var rb = UnZip(ra);

            //string filePath = @"E:\sample2.pdf";

            //Console.WriteLine("입력 : ");

            //string embro = Console.ReadLine();

            //while(embro!="종료")

            //{

            //    var result = ReadPdfFile(filePath, embro);

            //    embro = Console.ReadLine();

            //}

            iTextSharp.text.Document doc = new iTextSharp.text.Document(iTextSharp.text.PageSize.A4, 50, 50, 50, 50);

            PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream(@"E:\test.pdf", FileMode.OpenOrCreate));

            doc.Open();

            iTextSharp.text.Font link = iTextSharp.text.FontFactory.GetFont("Arial", 12, iTextSharp.text.Font.UNDERLINE, new iTextSharp.text.BaseColor(0, 0, 255));

            iTextSharp.text.Anchor anchor = new iTextSharp.text.Anchor("www.mikesdotnetting.com", link);

            anchor.Reference = "http://www.mikesdotnetting.com";

            doc.Add(anchor);

            doc.Close();

            Console.WriteLine("Finished...");

            Console.ReadKey();

        }

        public static List<int> ReadPdfFile(string fileName, string searchText)

        {

            string currentText = string.Empty;

            System.Text.StringBuilder pdfText = new System.Text.StringBuilder();

            List<int> pages = new List<int>();

            if (File.Exists(fileName))

            {

                PdfReader pdfReader = new PdfReader(fileName);

                for (int page = 1; page <= pdfReader.NumberOfPages; page++)

                {

                    var t = new MyLocationTextExtractionStrategy(searchText, System.Globalization.CompareOptions.None);

                    //var t = new TopToBottomTextExtractionStrategy();

                    var ex = PdfTextExtractor.GetTextFromPage(pdfReader, page, t);

                    //if (ex.Contains(searchText) && searchText.Contains(" "))

                    //{

                    //}

                    //foreach (var p in t.myPoints)

                    //{

                    //    Console.WriteLine(string.Format("Found text {0} at {1}x{2}", p.Text, p.Rect.Left, p.Rect.Bottom));

                    //}

                }

                //pdfReader.Close();

                //List<string> lines = new List<string>();

                //lines = pdfText.ToString().Trim().Split(' ').ToList();

                //List<string> matchedWord = new List<string>();

                //foreach (string item in lines)

                //{

                //    if (!string.IsNullOrEmpty(item))

                //    {

                //        if (item.ToUpper().Contains(searthText.ToUpper()))

                //        {

                //            matchedWord.Add(item);

                //        }

                //    }

                //}

            }

            return pages;

        }

    }

}