Question

我正在提取文档并以txt文件格式存储所有数据。对于提取我正在使用http://www.codeproject.com/Articles/31944/Implementing-a-TextReader-to-extract-various-files此库。对于文档提取，我使用下面的代码：

public static  void ExtractDocument()
    {
        List<string>  lstFiles= new List<string>();
        lstFiles.Add("123.txt");
        lstFiles.Add("123.doc");
        lstFiles.Add("123.docx");
        foreach (var fileName in lstFiles)
        {
            string newFileName = Path.Combine("D://extractFiles//downloadPath", fileName);
            string outputFilefiname = "D://extractFiles//vij.txt";
            using (var target = new FilterReader(newFileName, 0x1000))
            {
                target.Init();
                const int blockSize = 1024;
                var buffer = new Char[blockSize];
                var readblockBufferSize = target.ReadBlock(buffer, 0, blockSize);
                while (readblockBufferSize > 0)
                {
                    if (buffer[0] != '\0')
                    {
                        using (var writer = new StreamWriter(outputFilefiname, true))
                        {
                            writer.Write(buffer, 0, readblockBufferSize);
                        }
                        readblockBufferSize = target.ReadBlock(buffer, 0, blockSize);
                    }
                    else
                    {
                        readblockBufferSize = readblockBufferSize - 1; --"may be due to this Line I have lost data"
                    }
                }
            }
            // Write Delimete.  
            using (StreamWriter sWriter = new StreamWriter(outputFilefiname, true))
            {
                sWriter.WriteLine(string.Format("{0} 1111111111--2222222222-333333333-444444444-555555555 {0}", Environment.NewLine));
            }
        }
    }

在此方法中，提取工作正常但我在提取期间丢失了一些数据

else { readblockBufferSize = readblockBufferSize - 1; --"may be due to this Line I have lost data" }

但是当我使用下面的提取代码时：

public static void ExtractDocument()
    {
        List<string> lstFiles = new List<string>();
        lstFiles.Add("123.txt");
        lstFiles.Add("123.doc");
        lstFiles.Add("123.docx");
        foreach (var fileName in lstFiles)
        {
            string newFileName = Path.Combine("D://extractFiles//downloadPath", fileName);
            string outputFilefiname = "D://extractFiles//vij.txt";
            using (var target = new FilterReader(newFileName, 0x1000))
            {
                target.Init();
                const int blockSize = 1024;
                var buffer = new Char[blockSize];
                var readblockBufferSize = target.ReadBlock(buffer, 0, blockSize);
                while (target.ReadBlock(buffer, 0, blockSize) > 0)
                {
                    if (buffer[0] != '\0')
                    {
                        using (var writer = new StreamWriter(outputFilefiname, true))
                        {
                            writer.Write(buffer, 0, readblockBufferSize);
                        }
                    }
                }
            }
            // Write Delimete.  
            using (StreamWriter sWriter = new StreamWriter(outputFilefiname, true))
            {
                sWriter.WriteLine(string.Format("{0} 1111111111--2222222222-333333333-444444444-555555555 {0}", Environment.NewLine));
            }
        }
    }

在这种情况下，While循环永远不会结束（无限循环）。我无法分析我在做错误的地方。

更新方法

 public ResponseOutput ExtractFile(string outputFilefiname,string downloadedFileLocation,List<string> lstfiles)
    {
       var responseOutput = new ResponseOutput();
       responseOutput.IsSuccessful = false;
       int filescount = 0;
       if (!Directory.Exists(downloadedFileLocation) || string.IsNullOrWhiteSpace(downloadedFileLocation))
       {
           return responseOutput;
       }
       try
       {
           foreach (var fileName in lstfiles)
           {
               responseOutput = new ResponseOutput();
               responseOutput.IsSuccessful = false;
               string finalExtractedFile = Path.Combine(downloadedFileLocation, fileName);
               using (var target = new FilterReader(finalExtractedFile, 0x1000))
               {
                   target.Init();
                   var buffer = new Char[1024];
                   int blockSize = buffer.Length;
                   int readBlockBufferSize = 0;
                   while ((readBlockBufferSize = target.ReadBlock(buffer, 0, blockSize)) > 0)
                   {
                       if (buffer[0] != '\0')
                       {
                           using (var writer = new StreamWriter(outputFilefiname, true))
                           {
                               writer.Write(buffer, 0, readBlockBufferSize);
                           }
                       }
                   }
                   filescount = filescount + 1;
                   if (filescount != lstfiles.Count)
                   {
                       using (StreamWriter sWriter = new StreamWriter(outputFilefiname, true))
                       {
                           sWriter.WriteLine(string.Format("{0} {1} {0}", Environment.NewLine, FileSepratorDelimiter));
                       }
                   }
               }
               if(File.Exists(finalExtractedFile))
               {
                   //File.Delete(finalExtractedFile);
               }
           }
       }
       catch (Exception ex)
       {
         //
       }
        return responseOutput;
    }

请建议我在哪里犯错，或者我需要做些什么来解决这个问题。

Answer 1

问题在于此代码：

var readblockBufferSize = target.ReadBlock(buffer, 0, blockSize);
while (target.ReadBlock(buffer, 0, blockSize) > 0)
{
    ....
}

在第一行中，您正在读取一个块并将大小存储在readBlockBufferSize中。然后你再次阅读（它会丢弃第一次读取的缓冲区内容），但你不更新readBlockBuffersize。

代码应如下所示：

int readBlockBufferSize = 0;
while ((readBlockBufferSize = target.ReadBlock(buffer, 0, blockSize)) > 0)
{
   if (buffer[0] != '\0')
   {
       using (var writer = new StreamWriter(outputFilefiname, true))
       {
           writer.Write(buffer, 0, readblockBufferSize);
       }
   }
}

在文件提取期间，循环永远不会结束

1 个答案: