//// This code is part of Document Solutions for PDF .NET demos.// Copyright (c) MESCIUS inc. All rights reserved.//using System.IO;using System.Drawing;using System.Collections.Generic;using System.Linq;using GrapeCity.Documents.Text;using GrapeCity.Documents.Pdf;using GCTEXT = GrapeCity.Documents.Text;using GCDRAW = GrapeCity.Documents.Drawing;
namespace DsPdfWeb.Demos{    // This sample demonstrates how to extract text from an existing PDF.    // It loads an arbitrary PDF into a temporary GcPdfDocument, then    // retrieves text from each page of that document using the Page.GetText() method,    // adds all those texts to a TextLayout and renders it into the current document.    // An alternative to Page.GetText() is the method GcPdfDocument.GetText()    // which retrieves the text from the whole document at once.    public class ExtractText    {        public int CreatePDF(Stream stream)        {            var doc = new GcPdfDocument();            var page = doc.NewPage();
            var rc = Common.Util.AddNote(                "This sample loads an arbitrary PDF into a temporary GcPdfDocument, " +                "then retrieves text from each page of the loaded document using the Page.GetText() method, " +                "adds all those texts to a TextLayout and renders it into the current document. " +                "An alternative to Page.GetText() is the method GcPdfDocument.GetText() " +                "which retrieves the text from the whole document at once.",                page);
            // Text format for captions:            var tf = new TextFormat()            {                Font = GCTEXT.Font.FromFile(Path.Combine("Resources", "Fonts", "NotoSerif-Regular.ttf")),                FontSize = 14,                ForeColor = Color.Blue            };            // Text layout to render the text:            var tl = page.Graphics.CreateTextLayout();            tl.DefaultFormat.Font = StandardFonts.Times;            tl.DefaultFormat.FontSize = 12;            tl.MaxWidth = doc.PageSize.Width;            tl.MaxHeight = doc.PageSize.Height;            tl.MarginAll = rc.Left;            tl.MarginTop = rc.Bottom + 36;
            // Text split options for widow/orphan control:            var to = new TextSplitOptions(tl)            {                MinLinesInFirstParagraph = 2,                MinLinesInLastParagraph = 2,                RestMarginTop = rc.Left,            };
            // Open an arbitrary PDF, load it into a temp document and get all page texts:            using var fs = File.OpenRead(Path.Combine("Resources", "PDFs", "Wetlands.pdf"));
            var doc1 = new GcPdfDocument();            doc1.Load(fs);
            // Get the texts of the loaded document's pages:            var texts = new List<string>();            doc1.Pages.ToList().ForEach(p_ => texts.Add(p_.GetText()));
            // Add texts and captions to the text layout:            for (int i = 0; i < texts.Count; ++i)            {                tl.AppendLine(string.Format("Text from page {0} of the loaded document:", i + 1), tf);                tl.AppendLine(texts[i]);            }            tl.PerformLayout(true);            while (true)            {                // 'rest' will accept the text that did not fit:                var splitResult = tl.Split(to, out TextLayout rest);                doc.Pages.Last.Graphics.DrawTextLayout(tl, PointF.Empty);                if (splitResult != SplitResult.Split)                    break;                tl = rest;                doc.NewPage();            }
            // Done:            doc.Save(stream);            return doc.Pages.Count;        }    }}