'''' This code is part of Document Solutions for PDF .NET demos.'' Copyright (c) MESCIUS inc. All rights reserved.''Imports System.IOImports System.DrawingImports System.LinqImports System.Collections.GenericImports GrapeCity.Documents.PdfImports GrapeCity.Documents.Pdf.RecognitionImports GrapeCity.Documents.TextImports GCTEXT = GrapeCity.Documents.Text
Public Class GetTablePages    Public Function CreatePDF(ByVal stream As Stream) As Integer        Const DPI As Single = 72        Const margin As Single = 36        Dim doc = New GcPdfDocument()
        Dim tf = New TextFormat() With {            .Font = GCTEXT.Font.FromFile(Path.Combine("Resources", "Fonts", "NotoSans-Regular.ttf")),            .FontSize = 9,            .ForeColor = Color.Black        }        Dim tfHdr = New TextFormat(tf) With {            .Font = GCTEXT.Font.FromFile(Path.Combine("Resources", "Fonts", "NotoSans-Bold.ttf")),            .FontSize = 11,            .ForeColor = Color.DarkBlue        }        Dim tfRed = New TextFormat(tf) With {.ForeColor = Color.Red}
        Using fs = File.OpenRead(Path.Combine("Resources", "PDFs", "product-list.pdf"))            Dim page = doc.NewPage()            page.Landscape = True            Dim g = page.Graphics
            Dim rc = Util.AddNote(                "This sample loads a PDF that contains a table split between several pages (a product price list), " &                "and extracts the tables on all pages using the Page.GetTable() method. " &                "The extracted data is printed as a list of rows and cells. " &                "The source product list PDF is appended to the generated document for reference.",                page,                New RectangleF(margin, margin, page.Bounds.Width - margin * 2, page.Bounds.Height - margin * 2))
            Dim tl = g.CreateTextLayout()            tl.MaxWidth = page.Bounds.Width            tl.MaxHeight = page.Bounds.Height            tl.MarginAll = margin            tl.MarginTop = rc.Bottom            tl.DefaultTabStops = 165
            Dim docSrc = New GcPdfDocument()            docSrc.Load(fs)
            For i = 0 To docSrc.Pages.Count - 1                ' TableExtractOptions allow you to fine-tune table recognition accounting for                ' specifics of the table formatting:                Dim teo = New TableExtractOptions()                Dim GetMinimumDistanceBetweenRows = teo.GetMinimumDistanceBetweenRows                ' In this particular case, we slightly increase the minimum distance between rows                ' to make sure cells with wrapped text are not mistaken for two cells:                teo.GetMinimumDistanceBetweenRows = Function(list)                                                        Dim res = GetMinimumDistanceBetweenRows(list)                                                        Return res * 1.2F                                                    End Function                Dim top = If(i = 0, DPI * 2, DPI)                ' Get the table at the specified bounds:                Dim itable = docSrc.Pages(i).GetTable(New RectangleF(DPI * 0.25F, top, DPI * 8, DPI * 10.5F - top), teo)
                ' Add table data to the text layout:                tl.Append($"{vbLf}Table on page {i + 1} of the source document has {itable.Cols.Count} column(s) and {itable.Rows.Count} row(s), table data is:", tfHdr)                tl.AppendParagraphBreak()                For row = 0 To itable.Rows.Count - 1                    Dim tfmt = If(row = 0, tfHdr, tf)                    For col = 0 To itable.Cols.Count - 1                        Dim cell = itable.GetCell(row, col)                        If col > 0 Then                            tl.Append(vbTab, tfmt)                        End If                        If cell Is Nothing Then                            tl.Append("<no cell>", tfRed)                        Else                            tl.Append(cell.Text, tfmt)                        End If                    Next                    tl.AppendLine()                Next            Next
            ' Print the extracted data:            Dim to_ = New TextSplitOptions(tl) With {.RestMarginTop = margin, .MinLinesInFirstParagraph = 2, .MinLinesInLastParagraph = 2}            tl.PerformLayout(True)            While True                Dim rest As TextLayout = Nothing                Dim splitResult = tl.Split(to_, rest)                doc.Pages.Last.Graphics.DrawTextLayout(tl, PointF.Empty)                If splitResult <> SplitResult.Split Then                    Exit While                End If                tl = rest                doc.NewPage().Landscape = True            End While
            ' Append the original document for reference:            doc.MergeWithDocument(docSrc)
            doc.Save(stream)            Return doc.Pages.Count        End Using    End FunctionEnd Class