ExtractParagraphs.cs
//
// This code is part of Document Solutions for PDF demos.
// Copyright (c) MESCIUS inc. All rights reserved.
//
using System;
using System.IO;
using System.Drawing;
using System.Numerics;
using System.Collections.Generic;
using System.Linq;
using GrapeCity.Documents.Text;
using GrapeCity.Documents.Drawing;
using GrapeCity.Documents.Pdf;
using GrapeCity.Documents.Pdf.Annotations;
using GrapeCity.Documents.Pdf.Graphics;
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 ExtractParagraphs
    {
        public int CreatePDF(Stream stream)
        {
            const int margin = 36;
            var c1 = Color.PaleGreen;
            var c2 = Color.PaleGoldenrod;

            var doc = new GcPdfDocument();
            var page = doc.NewPage();

            var rc = Common.Util.AddNote(
                "Here we load an existing PDF (Wetlands) into a temporary GcPdfDocument, " +
                "and iterate over the pages of that document, printing all paragraphs found on the page. " +
                "We alternate the background color for the paragraphs so that the bounds between paragraphs are more clear. " +
                "The original PDF is appended to the generated document for reference.",
                page,
                new RectangleF(margin, margin, page.Size.Width - margin * 2, 0));

            // Text format for captions:
            var tf = new TextFormat()
            {
                Font = GCTEXT.Font.FromFile(Path.Combine("Resources", "Fonts", "yumin.ttf")),
                FontSize = 14,
                ForeColor = Color.Blue
            };
            // Text format for the paragraphs:
            var tfpar = new TextFormat()
            {
                Font = StandardFonts.Times,
                FontSize = 12,
                BackColor = c1,
            };
            // Text layout to render the text:
            var tl = page.Graphics.CreateTextLayout();
            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);

            for (int i = 0; i < doc1.Pages.Count; ++i)
            {
                tl.AppendLine(string.Format("Paragraphs from page {0} of the original PDF:", i + 1), tf);

                var pg = doc1.Pages[i];
                var pars = pg.GetTextMap().Paragraphs;
                foreach (var par in pars)
                {
                    tl.AppendLine(par.GetText(), tfpar);
                    tfpar.BackColor = tfpar.BackColor == c1 ? c2 : c1;
                }
            }

            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();
            }
            // Append the original document for reference:
            doc.MergeWithDocument(doc1, new MergeDocumentOptions());
            // Done:
            doc.Save(stream);
            return doc.Pages.Count;
        }
    }
}