iTextSharp System.OutOfMemoryException
iTextSharp System.OutOfMemoryException
我在尝试创建大型 PDF 文件时遇到问题。基本上我有一个字节数组列表,每个数组都包含一个字节数组形式的 PDF。我想将字节数组合并成一个 PDF。这适用于较小的文件(2000 页以下),但当我尝试创建一个 12,00 页的文件时,它被轰炸了)。最初我使用的是 MemoryStream,但经过一些研究,一个常见的解决方案是改用 FileStream。所以我尝试了一种文件流方法,但得到了类似的结果。该列表包含 3,800 条记录,每条包含 4 页。 MemoryStream 在大约 570 条记录后爆炸。FileStream 在大约 680 条记录后。代码崩溃后的当前文件大小为 60MB。我究竟做错了什么?这是我的代码,代码在 "for(" 循环内的 "copy.AddPage(curPg);" 指令上崩溃。
private byte[] MergePDFs(List<byte[]> PDFs)
{
iTextSharp.text.Document doc = new iTextSharp.text.Document();
byte[] completePDF;
Guid uniqueId = Guid.NewGuid();
string tempFileName = Server.MapPath("~/" + uniqueId.ToString() + ".pdf");
//using (MemoryStream ms = new MemoryStream())
using(FileStream ms = new FileStream(tempFileName, FileMode.Create, FileAccess.Write, FileShare.Read))
{
iTextSharp.text.pdf.PdfCopy copy = new iTextSharp.text.pdf.PdfCopy(doc, ms);
doc.Open();
int i = 0;
foreach (byte[] PDF in PDFs)
{
i++;
// Create a reader
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(PDF);
// Cycle through all the pages
for (int currentPageNumber = 1; currentPageNumber <= reader.NumberOfPages; ++currentPageNumber)
{
// Read a page
iTextSharp.text.pdf.PdfImportedPage curPg = copy.GetImportedPage(reader, currentPageNumber);
// Add the page over to the rest of them
copy.AddPage(curPg);
}
// Close the reader
reader.Close();
}
// Close the document
doc.Close();
// Close the copier
copy.Close();
// Convert the memorystream to a byte array
//completePDF = ms.ToArray();
}
//return completePDF;
return GetPDFsByteArray(tempFileName);
}
所以经过一番折腾后,我意识到这是没有办法解决的。但是,我确实设法找到了解决方法。我 return 一个临时文件路径,而不是 returning 字节数组,然后我将其传输并删除。
private string MergeLotsOfPDFs(List<byte[]> PDFs)
{
Document doc = new Document();
Guid uniqueId = Guid.NewGuid();
string tempFileName = Server.MapPath("~/__" + uniqueId.ToString() + ".pdf");
using (FileStream ms = new FileStream(tempFileName, FileMode.Create, FileAccess.Write, FileShare.Read))
{
PdfCopy copy = new PdfCopy(doc, ms);
doc.Open();
int i = 0;
foreach (byte[] PDF in PDFs)
{
i++;
// Create a reader
PdfReader reader = new PdfReader(new RandomAccessFileOrArray(PDF), null);
// Cycle through all the pages
for (int currentPageNumber = 1; currentPageNumber <= reader.NumberOfPages; ++currentPageNumber)
{
// Read a page
PdfImportedPage curPg = copy.GetImportedPage(reader, currentPageNumber);
// Add the page over to the rest of them
copy.AddPage(curPg);
// This is a lie, it still costs money, hue hue hue :)~
copy.FreeReader(reader);
}
reader.Close();
}
// Close the document
doc.Close();
// Close the document
copy.Close();
}
// Return temp file path
return tempFileName;
}
下面是我将数据发送给客户端的方式。
// Send the merged PDF file to the user.
System.Web.HttpResponse response = System.Web.HttpContext.Current.Response;
response.ClearContent();
Response.ClearHeaders();
response.ContentType = "application/pdf";
response.AddHeader("Content-Disposition", "attachment; filename=1094C.pdf;");
response.WriteFile(tempFileName);
HttpContext.Current.Response.Flush(); // Sends all currently buffered output to the client.
DeleteFile(tempFileName); // Call right after flush but before close
HttpContext.Current.Response.SuppressContent = true; // Gets or sets a value indicating whether to send HTTP content to the client.
HttpContext.Current.ApplicationInstance.CompleteRequest(); // Causes ASP.NET to bypass all events and filtering in the HTTP pipeline chain of execution and directly execute the EndRequest event.
最后,这是一个奇特的 DeleteFile 方法
private void DeleteFile(string fileName)
{
if (File.Exists(fileName))
{
try
{
File.Delete(fileName);
}
catch (Exception ex)
{
//Could not delete the file, wait and try again
try
{
System.GC.Collect();
System.GC.WaitForPendingFinalizers();
File.Delete(fileName);
}
catch
{
//Could not delete the file still
}
}
}
}
一些注意事项:
PdfCopy
实现了 iDisposable
,因此您应该尝试看看 using
是否有帮助。
PdfCopy.FreeReader()
会有帮助。
无论如何,不确定您使用的是 MVC 还是 WebForms,但这是一个简单的工作 HTTP handler 使用 15 页 125KB 测试文件测试 运行s 在我的工作站上:
<%@ WebHandler Language="C#" Class="MergeFiles" %>
using System;
using System.Collections.Generic;
using System.Web;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;
public class MergeFiles : IHttpHandler
{
public void ProcessRequest(HttpContext context)
{
List<byte[]> pdfs = new List<byte[]>();
var pdf = File.ReadAllBytes(context.Server.MapPath("~/app_data/test.pdf"));
for (int i = 0; i < 4000; ++i) pdfs.Add(pdf);
var Response = context.Response;
Response.ContentType = "application/pdf";
Response.AddHeader(
"content-disposition",
"attachment; filename=MergeLotsOfPdfs.pdf"
);
Response.BinaryWrite(MergeLotsOfPdfs(pdfs));
}
byte[] MergeLotsOfPdfs(List<byte[]> pdfs)
{
using (var ms = new MemoryStream())
{
using (Document document = new Document())
{
using (PdfCopy copy = new PdfCopy(document, ms))
{
document.Open();
for (int i = 0; i < pdfs.Count; ++i)
{
using (PdfReader reader = new PdfReader(
new RandomAccessFileOrArray(pdfs[i]), null))
{
copy.AddDocument(reader);
copy.FreeReader(reader);
}
}
}
}
return ms.ToArray();
}
}
public bool IsReusable { get { return false; } }
}
尝试使输出文件类似于您在问题中描述的内容,但 YMMV,具体取决于您处理的单个 PDF 的大小。这是我的 运行:
的测试输出
我在尝试创建大型 PDF 文件时遇到问题。基本上我有一个字节数组列表,每个数组都包含一个字节数组形式的 PDF。我想将字节数组合并成一个 PDF。这适用于较小的文件(2000 页以下),但当我尝试创建一个 12,00 页的文件时,它被轰炸了)。最初我使用的是 MemoryStream,但经过一些研究,一个常见的解决方案是改用 FileStream。所以我尝试了一种文件流方法,但得到了类似的结果。该列表包含 3,800 条记录,每条包含 4 页。 MemoryStream 在大约 570 条记录后爆炸。FileStream 在大约 680 条记录后。代码崩溃后的当前文件大小为 60MB。我究竟做错了什么?这是我的代码,代码在 "for(" 循环内的 "copy.AddPage(curPg);" 指令上崩溃。
private byte[] MergePDFs(List<byte[]> PDFs)
{
iTextSharp.text.Document doc = new iTextSharp.text.Document();
byte[] completePDF;
Guid uniqueId = Guid.NewGuid();
string tempFileName = Server.MapPath("~/" + uniqueId.ToString() + ".pdf");
//using (MemoryStream ms = new MemoryStream())
using(FileStream ms = new FileStream(tempFileName, FileMode.Create, FileAccess.Write, FileShare.Read))
{
iTextSharp.text.pdf.PdfCopy copy = new iTextSharp.text.pdf.PdfCopy(doc, ms);
doc.Open();
int i = 0;
foreach (byte[] PDF in PDFs)
{
i++;
// Create a reader
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(PDF);
// Cycle through all the pages
for (int currentPageNumber = 1; currentPageNumber <= reader.NumberOfPages; ++currentPageNumber)
{
// Read a page
iTextSharp.text.pdf.PdfImportedPage curPg = copy.GetImportedPage(reader, currentPageNumber);
// Add the page over to the rest of them
copy.AddPage(curPg);
}
// Close the reader
reader.Close();
}
// Close the document
doc.Close();
// Close the copier
copy.Close();
// Convert the memorystream to a byte array
//completePDF = ms.ToArray();
}
//return completePDF;
return GetPDFsByteArray(tempFileName);
}
所以经过一番折腾后,我意识到这是没有办法解决的。但是,我确实设法找到了解决方法。我 return 一个临时文件路径,而不是 returning 字节数组,然后我将其传输并删除。
private string MergeLotsOfPDFs(List<byte[]> PDFs)
{
Document doc = new Document();
Guid uniqueId = Guid.NewGuid();
string tempFileName = Server.MapPath("~/__" + uniqueId.ToString() + ".pdf");
using (FileStream ms = new FileStream(tempFileName, FileMode.Create, FileAccess.Write, FileShare.Read))
{
PdfCopy copy = new PdfCopy(doc, ms);
doc.Open();
int i = 0;
foreach (byte[] PDF in PDFs)
{
i++;
// Create a reader
PdfReader reader = new PdfReader(new RandomAccessFileOrArray(PDF), null);
// Cycle through all the pages
for (int currentPageNumber = 1; currentPageNumber <= reader.NumberOfPages; ++currentPageNumber)
{
// Read a page
PdfImportedPage curPg = copy.GetImportedPage(reader, currentPageNumber);
// Add the page over to the rest of them
copy.AddPage(curPg);
// This is a lie, it still costs money, hue hue hue :)~
copy.FreeReader(reader);
}
reader.Close();
}
// Close the document
doc.Close();
// Close the document
copy.Close();
}
// Return temp file path
return tempFileName;
}
下面是我将数据发送给客户端的方式。
// Send the merged PDF file to the user.
System.Web.HttpResponse response = System.Web.HttpContext.Current.Response;
response.ClearContent();
Response.ClearHeaders();
response.ContentType = "application/pdf";
response.AddHeader("Content-Disposition", "attachment; filename=1094C.pdf;");
response.WriteFile(tempFileName);
HttpContext.Current.Response.Flush(); // Sends all currently buffered output to the client.
DeleteFile(tempFileName); // Call right after flush but before close
HttpContext.Current.Response.SuppressContent = true; // Gets or sets a value indicating whether to send HTTP content to the client.
HttpContext.Current.ApplicationInstance.CompleteRequest(); // Causes ASP.NET to bypass all events and filtering in the HTTP pipeline chain of execution and directly execute the EndRequest event.
最后,这是一个奇特的 DeleteFile 方法
private void DeleteFile(string fileName)
{
if (File.Exists(fileName))
{
try
{
File.Delete(fileName);
}
catch (Exception ex)
{
//Could not delete the file, wait and try again
try
{
System.GC.Collect();
System.GC.WaitForPendingFinalizers();
File.Delete(fileName);
}
catch
{
//Could not delete the file still
}
}
}
}
一些注意事项:
PdfCopy
实现了iDisposable
,因此您应该尝试看看using
是否有帮助。PdfCopy.FreeReader()
会有帮助。
无论如何,不确定您使用的是 MVC 还是 WebForms,但这是一个简单的工作 HTTP handler 使用 15 页 125KB 测试文件测试 运行s 在我的工作站上:
<%@ WebHandler Language="C#" Class="MergeFiles" %>
using System;
using System.Collections.Generic;
using System.Web;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;
public class MergeFiles : IHttpHandler
{
public void ProcessRequest(HttpContext context)
{
List<byte[]> pdfs = new List<byte[]>();
var pdf = File.ReadAllBytes(context.Server.MapPath("~/app_data/test.pdf"));
for (int i = 0; i < 4000; ++i) pdfs.Add(pdf);
var Response = context.Response;
Response.ContentType = "application/pdf";
Response.AddHeader(
"content-disposition",
"attachment; filename=MergeLotsOfPdfs.pdf"
);
Response.BinaryWrite(MergeLotsOfPdfs(pdfs));
}
byte[] MergeLotsOfPdfs(List<byte[]> pdfs)
{
using (var ms = new MemoryStream())
{
using (Document document = new Document())
{
using (PdfCopy copy = new PdfCopy(document, ms))
{
document.Open();
for (int i = 0; i < pdfs.Count; ++i)
{
using (PdfReader reader = new PdfReader(
new RandomAccessFileOrArray(pdfs[i]), null))
{
copy.AddDocument(reader);
copy.FreeReader(reader);
}
}
}
}
return ms.ToArray();
}
}
public bool IsReusable { get { return false; } }
}
尝试使输出文件类似于您在问题中描述的内容,但 YMMV,具体取决于您处理的单个 PDF 的大小。这是我的 运行:
的测试输出