3

我有一种情况，我正在生成要提交给 web 服务的 XML 文件，有时是由于它超过 30mb 或 50mb 的数据量。

我需要使用 c#、.net framework 4.0 压缩文件，而不是拥有大部分数据的节点之一。我不知道我将如何去做。如果有人可以给我一个请举例说明我如何完成这项工作。

xml 文件看起来像这样

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<HeaderTalk xmlns="http://www.w3schools.com/xml">
<EnvelopeVersion>2.0</EnvelopeVersion>
<Header>
<MessageDetails>
  <Class>CHAR-CLM</Class>      
</MessageDetails>
<SenderDetails>
  <IDAuthentication>
    <SenderID>aaaaaa</SenderID>
    <Authentication>
      <Method>MD5</Method>
      <Role>principal</Role>
      <Value>a3MweCsv60kkAgzEpXeCqQ==</Value>
    </Authentication>
  </IDAuthentication>
  <EmailAddress>Someone@somewhere.com</EmailAddress>
</SenderDetails>
</Header>
<TalkDetails>
  <ChannelRouting>
   <Channel>
     <URI>1953</URI>
     <Product>My product</Product>
     <Version>2.0</Version>
    </Channel>
</ChannelRouting>
</TalkDetails>
<Body>
   <envelope xmlns="http://www.w3schools.com/xml/">       
     <PeriodEnd>2013-08-13</PeriodEnd>
     <IRmark Type="generic">zZrxvJ7JmMNaOyrMs9ZOaRuihkg=</IRmark>
     <Sender>Individual</Sender>
     <Report>
       <AuthOfficial>
          <OffName>
            <Fore>B</Fore>
            <Sur>M</Sur>
          </OffName>
          <Phone>0123412345</Phone>
        </AuthOfficial>
    <DefaultCurrency>GBP</DefaultCurrency>
    <Claim>
      <OrgName>B</OrgName>
      <ref>AB12345</ref>
      <Repayment>
        <Account>
          <Donor>
            <Fore>Barry</Fore>
           </Donor>
            <Total>7.00</Total>              
        </Account>           
        <Account>
          <Donor>
            <Fore>Anthony</Fore>               
          </Donor>             
          <Total>20.00</Total>
        </Account>                  
      </Repayment>
      </Claim>
      </Report>
   </envelope>
 </Body>
</HeaderTalk>

CLAIM 节点是我想要压缩的，因为它可以是包含在 XML 中的数百万条记录。

我是编码新手，我花了很长时间才生成这个 XML，并且一直在寻找一种压缩节点的方法，但我无法让它工作.. 结果需要完全相同，直到DefaultCurrency 节点.. 然后

 </AuthOfficial>
 <DefaultCurrency>GBP</DefaultCurrency>
 <CompressedPart Type="zip">UEsDBBQAAAAIAFt690K1</CompressedPart>
 </Report>
 </envelope>
 </Body>
 </HeaderTalk>

或者

 </AuthOfficial>
 <DefaultCurrency>GBP</DefaultCurrency>
 <CompressedPart Type="gzip">UEsDBBQAAAAIAFt690K1</CompressedPart>
 </Report>
 </envelope>
 </Body>
 </HeaderTalk>

请提前谢谢大家。或者，如果有人可以建议我可以在哪里查看并获得一些想法，我想做什么。

要创建文件，我很简单地遍历数据集并使用 XmlElements 编写节点并将内部文本设置为我的值..

我以前写的代码是.. //claim

XmlElement GovtSenderClaim = xmldoc.CreateElement("Claim");
XmlElement GovtSenderOrgname = xmldoc.CreateElement("OrgName");
GovtSenderOrgname.InnerText = Charity_name;
GovtSenderClaim.AppendChild(GovtSenderOrgname);

 XmlElement GovtSenderHMRCref = xmldoc.CreateElement("ref");
 GovtSenderHMRCref.InnerText = strref ;
 GovtSenderClaim.AppendChild(GovtSenderref);

 XmlElement GovtSenderRepayments = xmldoc.CreateElement("Repayment");
 while (reader.Read())
 {
  XmlElement GovtSenderAccount = xmldoc.CreateElement("Account");
  XmlElement GovtSenderDonor = xmldoc.CreateElement("Donor");

   XmlElement GovtSenderfore = xmldoc.CreateElement("Fore");
   GovtSenderfore.InnerText = reader["EmployeeName_first_name"].ToString();
   GovtSenderDonor.AppendChild(GovtSenderfore);

   GovtSenderAccount .AppendChild(GovtSenderDonor);

   XmlElement GovtSenderTotal = xmldoc.CreateElement("Total");
   GovtSenderTotal.InnerText = reader["Total"].ToString();

   GovtSenderAccount .AppendChild(GovtSenderTotal);

   GovtSenderRepayments.AppendChild(GovtSenderAccount );
 }
  GovtSenderClaim.AppendChild(GovtSenderRepayments);


   GovtSenderReport.AppendChild(GovtSenderClaim);

其余节点关闭..

4

4 回答 4

2

你可以试试这个：它只会压缩你选择的节点。这与您所要求的略有不同，因为它将替换元素的内容，使元素及其属性保持原样。

{
    // You are using a namespace! 
    XNamespace ns = "http://www.w3schools.com/xml/";

    var xml2 = XDocument.Parse(xml);

    // Compress
    {
        // Will compress all the XElement that are called Claim
        // You should probably select the XElement in a better way
        var nodes = from p in xml2.Descendants(ns + "Claim") select p;

        foreach (XElement el in nodes)
        {
            CompressElementContent(el);
        }
    }

    // Decompress
    {
        // Will decompress all the XElement that are called Claim
        // You should probably select the XElement in a better way
        var nodes = from p in xml2.Descendants(ns + "Claim") select p;

        foreach (XElement el in nodes)
        {
            DecompressElementContent(el);
        }
    }
}

public static void CompressElementContent(XElement el)
{
    string content;

    using (var reader = el.CreateReader())
    {
        reader.MoveToContent();
        content = reader.ReadInnerXml();
    }

    using (var ms = new MemoryStream())
    {
        using (DeflateStream defl = new DeflateStream(ms, CompressionMode.Compress))
        {
            // So that the BOM isn't written we use build manually the encoder.
            // See for example http://stackoverflow.com/a/2437780/613130
            // But note that false is implicit in the parameterless constructor
            using (StreamWriter sw = new StreamWriter(defl, new UTF8Encoding()))
            {
                sw.Write(content);
            }
        }

        string base64 = Convert.ToBase64String(ms.ToArray());

        el.ReplaceAll(new XText(base64));
    }
}

public static void DecompressElementContent(XElement el)
{
    var reader = el.CreateReader();
    reader.MoveToContent();
    var content = reader.ReadInnerXml();

    var bytes = Convert.FromBase64String(content);

    using (var ms = new MemoryStream(bytes))
    {
        using (DeflateStream defl = new DeflateStream(ms, CompressionMode.Decompress))
        {
            using (StreamReader sr = new StreamReader(defl, Encoding.UTF8))
            {
                el.ReplaceAll(ParseXmlFragment(sr));
            }
        }
    }
}

public static IEnumerable<XNode> ParseXmlFragment(StreamReader sr)
{
    var settings = new XmlReaderSettings
    {
        ConformanceLevel = ConformanceLevel.Fragment
    };

    using (var xmlReader = XmlReader.Create(sr, settings))
    {
        xmlReader.MoveToContent();

        while (xmlReader.ReadState != ReadState.EndOfFile)
        {
            yield return XNode.ReadFrom(xmlReader);
        }
    }
}

解压非常复杂，因为很难替换 Xml 的内容。最后，我将内容拆分XNode为XnodeinParseXmlFragment和ReplaceAllin DecompressElementContent。

作为旁注，您的 XML 中有两个相似但不同的命名空间：http://www.w3schools.com/xml和http://www.w3schools.com/xml/

这个其他变体将完全按照您的要求执行（因此它将创建一个 CompressedPart 节点）减去具有压缩类型的属性。

{
    XNamespace ns = "http://www.w3schools.com/xml/";

    var xml2 = XDocument.Parse(xml);

    // Compress
    {
        // Here the ToList() is necessary, because we will replace the selected elements
        var nodes = (from p in xml2.Descendants(ns + "Claim") select p).ToList();

        foreach (XElement el in nodes)
        {
            CompressElementContent(el);
        }
    }

    // Decompress
    {
        // Here the ToList() is necessary, because we will replace the selected elements
        var nodes = (from p in xml2.Descendants("CompressedPart") select p).ToList();

        foreach (XElement el in nodes)
        {
            DecompressElementContent(el);
        }
    }
}

public static void CompressElementContent(XElement el)
{
    string content = el.ToString();

    using (var ms = new MemoryStream())
    {
        using (DeflateStream defl = new DeflateStream(ms, CompressionMode.Compress))
        {
            // So that the BOM isn't written we use build manually the encoder.
            using (StreamWriter sw = new StreamWriter(defl, new UTF8Encoding()))
            {
                sw.Write(content);
            }
        }

        string base64 = Convert.ToBase64String(ms.ToArray());

        var newEl = new XElement("CompressedPart", new XText(base64));
        el.ReplaceWith(newEl);
    }
}

public static void DecompressElementContent(XElement el)
{
    var reader = el.CreateReader();
    reader.MoveToContent();
    var content = reader.ReadInnerXml();

    var bytes = Convert.FromBase64String(content);

    using (var ms = new MemoryStream(bytes))
    {
        using (DeflateStream defl = new DeflateStream(ms, CompressionMode.Decompress))
        {
            using (StreamReader sr = new StreamReader(defl, Encoding.UTF8))
            {
                var newEl = XElement.Parse(sr.ReadToEnd());
                el.ReplaceWith(newEl);
            }
        }
    }
}
于 2013-08-13T15:34:30.597 回答
2

我需要使用 c#、.net framework 4.0 压缩文件，而不是其中一个节点

您可以使用GZip 压缩。就像是

public static void Compress(FileInfo fileToCompress)
        {
            using (FileStream originalFileStream = fileToCompress.OpenRead())
            {
                if ((File.GetAttributes(fileToCompress.FullName) & FileAttributes.Hidden) != FileAttributes.Hidden & fileToCompress.Extension != ".gz")
                {
                    using (FileStream compressedFileStream = File.Create(fileToCompress.FullName + ".gz"))
                    {
                        using (GZipStream compressionStream = new GZipStream(compressedFileStream, CompressionMode.Compress))
                        {
                            originalFileStream.CopyTo(compressionStream);
                            Console.WriteLine("Compressed {0} from {1} to {2} bytes.",
                                fileToCompress.Name, fileToCompress.Length.ToString(), compressedFileStream.Length.ToString());
                        }
                    }
                }
            }
        }

        public static void Decompress(FileInfo fileToDecompress)
        {
            using (FileStream originalFileStream = fileToDecompress.OpenRead())
            {
                string currentFileName = fileToDecompress.FullName;
                string newFileName = currentFileName.Remove(currentFileName.Length - fileToDecompress.Extension.Length);

                using (FileStream decompressedFileStream = File.Create(newFileName))
                {
                    using (GZipStream decompressionStream = new GZipStream(originalFileStream, CompressionMode.Decompress))
                    {
                        decompressionStream.CopyTo(decompressedFileStream);
                        Console.WriteLine("Decompressed: {0}", fileToDecompress.Name);
                    }
                }
            }
        }

另一种可能的做法是通过 Deflate。见这里。GZipStream 和 Deflate 流之间的主要区别在于 GZipStream 将添加 CRC 以确保数据没有错误。

于 2013-08-13T14:51:06.663 回答
1

您要问的是可能的，但有些涉及。您需要在内存中创建压缩节点，然后将其写入。我不知道你是如何编写 XML 的，所以我假设你有类似的东西：

open xml writer
write <MessageDetails>
write <SenderDetails>
write other nodes
write Claim node
write other stuff
close file

要编写声明节点，您需要写入内存流，然后对其进行 base64 编码。结果字符串是您写入文件的<CompressedPart>.

string compressedData;
using (MemoryStream ms = new MemoryStream())
{
    using (GZipStream gz = new GZipStream(CompressionMode.Compress, true))
    {
        using (XmlWriter writer = XmlWriter.Create(gz))
        {
            writer.WriteStartElement("Claim");
            // write claim stuff here
            writer.WriteEndElement();
        }
    }
    // now base64 encode the memory stream buffer
    byte[] buff = ms.GetBuffer();
    compressedData = Convert.ToBase64String(buff, 0, buff.Length);
}

然后，您的数据位于compressedData字符串中，您可以将其写为元素数据。

正如我在评论中所说，GZip 通常会减少原始 XML 大小的 80%，因此 50 MB 变为 10 MB。但是 base64 编码会增加 33% 的压缩大小。我预计结果约为 13.5 MB。

更新

根据您的附加代码，您尝试做的事情看起来并不太难。我想你想做的是：

// do a bunch of stuff
GovtSenderClaim.AppendChild(GovtSenderRepayments);

// start of added code

// compress the GovtSenderClaim element
// This code writes the GovtSenderClaim element to a compressed MemoryStream.
// We then read the MemoryStream and create a base64 encoded representation.
string compressedData;
using (MemoryStream ms = new MemoryStream())
{
    using (GZipStream gz = new GZipStream(CompressionMode.Compress, true))
    {
        using (StreamWriter writer = StreamWriter(gz))
        {
            GovtSenderClaim.Save(writer);
        }
    }
    // now base64 encode the memory stream buffer
    byte[] buff = ms.ToArray();
    compressedData = Convert.ToBase64String(buff, 0, buff.Length);
}

// compressedData now contains the compressed Claim node, encoded in base64.

// create the CompressedPart element
XElement CompressedPart = xmldoc.CreateElement("CompressedPart");
CompressedPart.SetAttributeValue("Type", "gzip");
CompressedPart.SetValue(compressedData);

GovtSenderReport.AppendChild(CompressedPart);
// GovtSenderReport.AppendChild(GovtSenderClaim);
于 2013-08-13T15:22:05.687 回答
0

这就是我为使其工作所做的工作..

public void compressTheData(string xml)
{
  XNamespace ns =  "http://www.w3schools.com/xml/";
  var xml2 = XDocument.Load(xml);   

  // Compress
  {
   var nodes = (from p in xml2.Descendants(ns + "Claim") select p).ToList();
    foreach (XElement el in nodes)
    {      
        CompressElementContent(el);           
    }
}
xml2.Save(xml);   
}


public static void CompressElementContent(XElement el)
{
  string content = el.ToString();    

  using (var ms = new MemoryStream())
  {
    using (GZipStream defl = new GZipStream(ms, CompressionMode.Compress))
    {           
        using (StreamWriter sw = new StreamWriter(defl))
        {
            sw.Write(content); 
        }
    }
    string base64 = Convert.ToBase64String(ms.ToArray());  
    XElement newEl = new XElement("CompressedPart", new XText(base64));
    XAttribute attrib = new XAttribute("Type", "gzip");
    newEl.Add(attrib);
    el.ReplaceWith(newEl);
  }
 }

谢谢大家的意见。

于 2013-08-15T14:43:50.120 回答