Question

我正在使用此代码将不同的pdf文件页面导入单个文档。当我导入大文件（200页或以上）时，我收到OutOfMemory例外。我在这里做错了吗？

    private bool SaveToFile(string fileName)
    {
        try
        {
            iTextSharp.text.Document doc;
            iTextSharp.text.pdf.PdfCopy pdfCpy;
            string output = fileName;

            doc = new iTextSharp.text.Document();
            pdfCpy = new iTextSharp.text.pdf.PdfCopy(doc, new System.IO.FileStream(output, System.IO.FileMode.Create));
            doc.Open();

            foreach (DataGridViewRow item in dvSourcePreview.Rows)
            {
                string pdfFileName = item.Cells[COL_FILENAME].Value.ToString();
                int pdfPageIndex = int.Parse(item.Cells[COL_PAGE_NO].Value.ToString());
                pdfPageIndex += 1;

                iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(pdfFileName);
                int pageCount = reader.NumberOfPages;

                // set page size for the documents
                doc.SetPageSize(reader.GetPageSizeWithRotation(1));

                iTextSharp.text.pdf.PdfImportedPage page = pdfCpy.GetImportedPage(reader, pdfPageIndex);
                pdfCpy.AddPage(page);

                reader.Close();
            }

            doc.Close();

            return true;
        }
        catch (Exception ex)
        {
            return false;
        }
    }

Answer 1

我没有遇到过iTextSharp的OOM问题。是用iTextSharp或其他东西创建的PDF吗？您能否将问题隔离到单个PDF或一组可能已损坏的PDF？下面是创建10个PDF的示例代码，每个PDF包含1,000页。然后它再创建一个PDF，并从这些PDF中随机抽取1页500次。在我的机器上运行需要一段时间，但我没有看到任何内存问题或任何事情。（iText 5.1.1.0）

using System;
using System.Windows.Forms;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;

namespace WindowsFormsApplication1
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            //Folder that we will be working in

            string WorkingFolder = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "Big File PDF Test");

            //Base name of PDFs that we will be creating
            string BigFileBase = Path.Combine(WorkingFolder, "BigFile");

            //Final combined PDF name
            string CombinedFile = Path.Combine(WorkingFolder, "Combined.pdf");

            //Number of "large" files to create
            int NumberOfBigFilesToMakes = 10;

            //Number of pages to put in the files
            int NumberOfPagesInBigFile = 1000;

            //Number of pages to insert into combined file
            int NumberOfPagesToInsertIntoCombinedFile = 500;

            //Create our test directory
            if (!Directory.Exists(WorkingFolder)) Directory.CreateDirectory(WorkingFolder);

            //First step, create a bunch of files with a bunch of pages, hopefully code is self-explanatory
            for (int FileCount = 1; FileCount <= NumberOfBigFilesToMakes; FileCount++)
            {
                using (FileStream FS = new FileStream(BigFileBase + FileCount + ".pdf", FileMode.Create, FileAccess.Write, FileShare.Read))
                {
                    using (iTextSharp.text.Document Doc = new iTextSharp.text.Document(PageSize.LETTER))
                    {
                        using (PdfWriter writer = PdfWriter.GetInstance(Doc, FS))
                        {
                            Doc.Open();
                            for (int I = 1; I <= NumberOfPagesInBigFile; I++)
                            {
                                Doc.NewPage();
                                Doc.Add(new Paragraph("This is file " + FileCount));
                                Doc.Add(new Paragraph("This is page " + I));
                            }
                            Doc.Close();
                        }
                    }
                }
            }

            //Second step, loop around pulling random pages from random files

            //Create our output file
            using (FileStream FS = new FileStream(CombinedFile, FileMode.Create, FileAccess.Write, FileShare.Read))
            {
                using (Document Doc = new Document())
                {
                    using (PdfCopy pdfCopy = new PdfCopy(Doc, FS))
                    {
                        Doc.Open();

                        //Setup some variables to use in the loop below
                        PdfReader reader = null;
                        PdfImportedPage page = null;
                        int RanFileNum = 0;
                        int RanPageNum = 0;

                        //Standard random number generator
                        Random R = new Random();

                        for (int I = 1; I <= NumberOfPagesToInsertIntoCombinedFile; I++)
                        {
                            //Just to output our current progress
                            Console.WriteLine(I);

                            //Get a random page and file. Remember iText pages are 1-based.
                            RanFileNum = R.Next(1, NumberOfBigFilesToMakes + 1);
                            RanPageNum = R.Next(1, NumberOfPagesInBigFile + 1);

                            //Open the random file
                            reader = new PdfReader(BigFileBase + RanFileNum + ".pdf");
                            //Set the current page
                            Doc.SetPageSize(reader.GetPageSizeWithRotation(1));

                            //Grab a random page
                            page = pdfCopy.GetImportedPage(reader, RanPageNum);
                            //Add it to the combined file
                            pdfCopy.AddPage(page);

                            //Clean up
                            reader.Close();
                        }

                        //Clean up
                        Doc.Close();
                    }
                }
            }

        }
    }
}

Answer 2

您为每次传递创建了一个新的PdfReader。这非常低效。而且因为每个人都有PdfImportedPage，所有这些（可能是多余的）PdfReader实例都不会被GC控制。

建议：

两次通过。首先建立一个文件列表＆amp;页面。其次依次对每个文件进行操作，因此您一次只能有一个PdfReader“打开”。完成给定的阅读器后，请使用PdfCopy.freeReader()。这几乎肯定会改变页面的添加顺序（可能是非常糟糕的事情）。
一通。根据文件名缓存PdfReader个实例。完成后再次使用FreeReader ......但是在你退出循环之前，你可能无法释放任何一个。仅缓存可能足以防止内存不足。
保持代码不变，但在关闭给定的freeReader()实例后调用PdfReader。

iTextSharp Pdf页面导入内存问题

2 个答案: