如何在.net中读取具有不同层次结构的xml文件 [英] How to read xml file having different hierarchy in .net
问题描述
我有一个7GB的xml大文件,我在这里粘贴了一小部分
I have big 7GB xml file ,and i am pasting small portion here
<?xml version="1.0" encoding="UTF-8"?>
<bulkFile xmlns:un="utranNrm.xsd"
xmlns:es="Attributes.15.25.xsd"
xmlns:xn="generic.xsd" xmlns:gn="geran.xsd" xmlns="configData.xsd">
<fileHeader fileFormatVersion="32.615 V4.5" Name="Wmart"/>
<configData dnPrefix="Undefined">
<xn:SubNetwork id="M_ROOT">
<xn:VsDataContainer id="1">
<xn:attributes>
<xn:vsDataType>vsDataAreas</xn:vsDataType>
<xn:vsDataFormatVersion>SpecificAttributes</xn:vsDataFormatVersion>
<es:vsDataAreas/>
</xn:attributes>
<xn:VsDataContainer id="424_2_2">
<xn:attributes>
<xn:vsDataType>vsDataPlmn</xn:vsDataType>
<xn:vsDataFormatVersion>SpecificAttributes</xn:vsDataFormatVersion>
<es:vsDataPlmn>
<es:userLabel></es:userLabel>
<es:mcc>424</es:mcc>
<es:mnc>2</es:mnc>
<es:mncLength>2</es:mncLength>
<es:aliasPlmnIdentities>
<es:mcc>424</es:mcc>
<es:mnc>2</es:mnc>
<es:mncLength>2</es:mncLength>
</es:aliasPlmnIdentities>
</es:vsDataPlmn>
</xn:attributes>
<xn:VsDataContainer id="10">
<xn:attributes>
<xn:vsDataType>vsDataLocationArea</xn:vsDataType>
<xn:vsDataFormatVersion>SpecificAttributes</xn:vsDataFormatVersion>
<es:vsDataLocationArea>
<es:userLabel></es:userLabel>
<es:lac>10</es:lac>
<es:t3212>10</es:t3212>
<es:att>1</es:att>
</es:vsDataLocationArea>
</xn:attributes>
</xn:VsDataContainer>
</xn:VsDataContainer>
</xn:VsDataContainer>
<xn:SubNetwork id="G-Mum">
<xn:attributes>
<xn:userDefinedNetworkType>SiteSolutions</xn:userDefinedNetworkType>
<xn:userLabel>G-Mum</xn:userLabel>
</xn:attributes>
<xn:MeContext id="32509_I_East">
<xn:VsDataContainer id="23502_I_AAN_UAEU_Crescent_East">
<xn:attributes>
<xn:vsDataType>vsDataMeContext</xn:vsDataType>
<xn:vsDataFormatVersion>EricssonSpecificAttributes.15.25</xn:vsDataFormatVersion>
<es:vsDataMeContext>
<es:userLabel>23502_I_AAN_UAEU_Crescent_East</es:userLabel>
<es:ipAddress>10.235.20.10</es:ipAddress>
<es:neMIMversion>vF.1.108</es:neMIMversion>
<es:lostSynchronisation>SYNCHRONISED</es:lostSynchronisation>
<es:bcrLastChange>1474785017888</es:bcrLastChange>
<es:bctLastChange>1470699087457</es:bctLastChange>
<es:multiStandardRbs6k>false</es:multiStandardRbs6k>
<es:mixedModeRadio>false</es:mixedModeRadio>
<es:mirrorMIBversion>F.1.100.S.1.6</es:mirrorMIBversion>
<es:stnNodes></es:stnNodes>
</es:vsDataMeContext>
</xn:attributes>
</xn:VsDataContainer>
<xn:ManagedElement id="1">
<xn:attributes>
</xn:attributes>
<xn:VsDataContainer id="1">
<xn:attributes>
<xn:vsDataType>vsDataManagedElement</xn:vsDataType>
<xn:vsDataFormatVersion>Attributes.15.25.xsd</xn:vsDataFormatVersion>
<es:vsDataManagedElement>
<es:siteRef>SubNetwork=M_ROOT,Site=32509_I_East</es:siteRef>
<es:productType>Node</es:productType>
<es:productName>RBS6601L</es:productName>
<es:productNumber></es:productNumber>
<es:productRevision></es:productRevision>
<es:prodDesignation>0</es:prodDesignation>
</es:vsDataManagedElement>
</xn:attributes>
</xn:VsDataContainer>
.
.
<xn:VsDataContainer id="1">
<xn:attributes>
<xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
<xn:vsDataFormatVersion>Attributes.15.25.xsd</xn:vsDataFormatVersion>
<es:vsDataENodeBFunction>
<es:userLabel></es:userLabel>
<es:dscpLabel>24</es:dscpLabel>
<es:dnsLookupOnTai>1</es:dnsLookupOnTai>
<es:eNBId>32509</es:eNBId>
</es:vsDataENodeBFunction>
</xn:attributes>
<xn:VsDataContainer id="BC_3250_32509_L1_B">
<xn:attributes>
<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
<es:earfcndl>1651</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
..
<xn:VsDataContainer id="BD_4250_32509_L1_B">
<xn:attributes>
<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
<es:earfcndl>1651</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
<xn:VsDataContainer id="CC_3250_32509_L1_C">
<xn:attributes>
<xn:vsDataType>testranCellFDD</xn:vsDataType>
<es:earfcndl>165</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
</xn:VsDataContainer>
..
</xn:ManagedElement>
</xn:MeContext>
<xn:MeContext id="32509_I_west">
<xn:VsDataContainer id="32509_I_AAN_UAEU_Crescent_East">
<xn:attributes>
<xn:vsDataType>vsDataMeContext</xn:vsDataType>
<xn:vsDataFormatVersion>Attributes.15.25</xn:vsDataFormatVersion>
<es:vsDataMeContext>
<es:userLabel>32509_I_AAN_UAEU_Crescent_East</es:userLabel>
<es:ipAddress>10.235.20.10</es:ipAddress>
<es:neMIMversion>vF.1.108</es:neMIMversion>
<es:lostSynchronisation>SYNCHRONISED</es:lostSynchronisation>
<es:bcrLastChange>1474785017888</es:bcrLastChange>
<es:bctLastChange>1470699087457</es:bctLastChange>
<es:multiStandardRbs6k>false</es:multiStandardRbs6k>
<es:mixedModeRadio>false</es:mixedModeRadio>
<es:mirrorMIBversion>F.1.100.S.1.6</es:mirrorMIBversion>
<es:stnNodes></es:stnNodes>
</es:vsDataMeContext>
</xn:attributes>
</xn:VsDataContainer>
<xn:ManagedElement id="1">
<xn:attributes>
</xn:attributes>
<xn:VsDataContainer id="1">
<xn:attributes>
<xn:vsDataType>vsDataManagedElement</xn:vsDataType>
<xn:vsDataFormatVersion>Attributes.15.25.xsd</xn:vsDataFormatVersion>
<es:vsDataManagedElement>
<es:siteRef>SubNetwork=M_ROOT,Site=32509_I_East</es:siteRef>
<es:productType>Node</es:productType>
<es:productName>RBS6601L</es:productName>
<es:productNumber></es:productNumber>
<es:productRevision></es:productRevision>
<es:prodDesignation>0</es:prodDesignation>
</es:vsDataManagedElement>
</xn:attributes>
</xn:VsDataContainer>
.
.
<xn:VsDataContainer id="1">
<xn:attributes>
<xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
<xn:vsDataFormatVersion>Attributes.15.25.xsd</xn:vsDataFormatVersion>
<es:vsDataENodeBFunction>
<es:userLabel></es:userLabel>
<es:dscpLabel>24</es:dscpLabel>
<es:dnsLookupOnTai>1</es:dnsLookupOnTai>
<es:eNBId>32509</es:eNBId>
</es:vsDataENodeBFunction>
</xn:attributes>
<xn:VsDataContainer id="CC_3250_32509_L1_B">
<xn:attributes>
<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
<es:earfcndl>1651</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
..
<xn:VsDataContainer id="CD_4250_32509_L1_B">
<xn:attributes>
<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
<es:earfcndl>1651</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
<xn:VsDataContainer id="DC_3250_32509_L1_C">
<xn:attributes>
<xn:vsDataType>testranCellFDD</xn:vsDataType>
<es:earfcndl>165</es:earfcndl>
<es:earfcnul>19651</es:earfcnul>
</xn:attributes>
</xn:VsDataContainer>
</xn:VsDataContainer>
..
</xn:ManagedElement>
</xn:MeContext>
</xn:SubNetwork>
</xn:SubNetwork>
</configData>
</bulkFile>
在这里,我想获取声明的c#变量的值,这些值类似于subnetwork
,sitename
,eNBId
,cellname
,earfcndl
和earfcnul
所有信息都驻留在根标记<xn:SubNetwork id="M_ROOT">
标记下,其余所有归根目录下的所有站点所有,这里我仅粘贴一个站点详细信息.逻辑为
Here i want to get values for c# variables i declared which are like subnetwork
,sitename
,eNBId
,cellname
,earfcndl
and earfcnul
all the information's resides under root tag <xn:SubNetwork id="M_ROOT">
tag,rest all for all sites coming under the root and here i am pasting only one site details.The logic is
subnetwork = <xn:SubNetwork id > attribute value
sitename = <xn:MeContext id> attribute value
eNBId = <es:eNBId> value, here the important thing is, there will be huge number of `<xn:VsDataContainer id="1">` parent tag,but the filtration is based on `<xn:vsDataType>` inner tag which is of `vsDataENodeBFunction`.
cellname = `<xn:VsDataContainer id>` attribute value and
`earfcndl` and `earfcnul` is values for `<es:earfcndl> and <es:earfcnul>` tag .Here also filtration is based on <xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
所以我想得到subnetwork = G-Mum,,sitename = 32509_I_East,,eNBId=32509,,cellname=BC_3250_32509_L1_B,,earfcndl=1651,,earfcnul=19651
.
我在这里执行了以下代码,但是卡住了,不知道该怎么办.但是我可以保证这是唯一的方法(xmlreader
和(XElement)XNode.ReadFrom
方法),我们可以读取7Gb Xml文件,其余全部将抛出内存不足异常"
Here i did following code, but got stuck and don't know what to do.But i can guarantee that this is the only way(xmlreader
and (XElement)XNode.ReadFrom
method) we can read 7Gb Xml file,rest all will throw "Out of memory exceptions"
using (XmlReader xr = XmlReader.Create(path))
{
xr.MoveToContent();
XNamespace un = xr.LookupNamespace("un");
while (xr.Read())
{
while (xr.NodeType == XmlNodeType.Element && xr.NamespaceURI == un && xr.LocalName == "M_ROOT")
{
XElement pin = (XElement)XNode.ReadFrom(xr);
var data = from atts in pin.Elements(un + "attributes")
select new
{
eNBId= (string)atts.Element(es + "eNBId"),
}
}
}
编辑 层次结构只是一个xn:SubNetwork id ="M_ROOT"标签,其中包含所有区域,例如再次包含所有站点信息的under标签,而该标签又包含所有vsinfoEUtranCellFDD类型的单元格信息
EDIT Hierarchy is only one xn:SubNetwork id="M_ROOT" tag which contain all the regions like which again contains all the site information's under tag which again contains all the cell information's under of type vsDataEUtranCellFDD
编辑 @jdweng感谢您的帮助,现在他们又增加了xml,现在又增加了我们使用(XElement)XElement.ReadFrom(reader)获取的摘录xml.本身会抛出内存不足"异常.如何删除不必要的xml部分.我的层次结构是
EDIT @jdweng thanks for your help,now they have increased xml again,and now the snippet xml which we took by using the(XElement)XElement.ReadFrom(reader); itself throwing the Out of memory exception.How can i remove the unnecessary xml part.My hierarchy is
<xn:SubNetwork id="M_ROOT">--------------Root
<xn:SubNetwork id="G-Mum">---------Region
<xn:MeContext id="32509_I_East">-----sites
<xn:VsDataContainer id="BC_3250_32509_L1_B"> ---Cells
<xn:attributes>
<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
</xn:MeContext>
</xn:SubNetwork>
</xn:SubNetwork>
所以我在我的问题的恳求中发布的都是必要的数据,请保留所有不必要的
SO what ever i posted on the very begging of my question is necessary data,rest all unnecessary
编辑 @jdweng,是的,我张贴的是必填项,我正在再次编辑我的问题. 层次结构是
EDIT @jdweng ,yes what ever i posted is the required on,I am editing my question again. Heirarchy is
`<xn:SubNetwork>` --------Root and only one
然后几行
<xn:SubNetwork>
包含地区将成组出现,但是这里只有id以G-
开头是有效的,因此在这里G-Mum
然后<xn:MeContext>
包含站点的站点将以组的形式出现,该站点又包含很多<xn:VsDataContainer>
,但是此处包含子节点<xn:vsDataType>vsDataManagedElement</xn:vsDataType>
的站点是有效的,以便获得<es:eNBId>
.
然后在子节点<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
的几行<xn:VsDataContainer>
包含单元格之后再次出现.this(cells)是最里面的一个.
因此将会有大量的<xn:VsDataContainer>
出现,其中只有用于导入Enbid
的子节点<xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
和用于导入单元格的<xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
子节点
Then after several line
<xn:SubNetwork>
contain Regions will come as groups,But here only id begins with G-
is valid so here G-Mum
Then <xn:MeContext>
contains sites will come as groups which again contains lot of <xn:VsDataContainer>
,but here one contains child node <xn:vsDataType>vsDataManagedElement</xn:vsDataType>
is valid one in order to get <es:eNBId>
.
Then again after several lines <xn:VsDataContainer>
of child nodes <xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
contains cells will come.This(cells) is the inner most one.
SO there will be huge number of <xn:VsDataContainer>
will come,out of it only of child nodes <xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
for getting Enbid
and <xn:vsDataType>vsDataEUtranCellFDD</xn:vsDataType>
for cells are import
编辑 在分析了大文件之后,我知道单元格位于站点下,但是我将其张贴在外面,即vsDataEUtranCellFDD处于标签vsDataENodeBFunction下.我编辑了我发布的xml
EDIT After analyzing big file i came to know that cells are coming under sites ,but i posted it in out side,Ie vsDataEUtranCellFDD is coming under the tag vsDataENodeBFunction.I have edited my xml which i posted
修改10/10/16
xml几乎没有变化,在<xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
的VsDataContainer
之前还有一个VsDataContainer
,由于未捕获vsDataENodeBFunction
.我使用了Skip(1)
但没有用
vsDataManagedElement
EDIT 10/10/16
There is little change in xml ,one more VsDataContainer
was there before VsDataContainer
of <xn:vsDataType>vsDataENodeBFunction</xn:vsDataType>
,Due to that vsDataENodeBFunction
is not caught.I used Skip(1)
but didn't work
vsDataManagedElement
推荐答案
您的文件很大,因此最好使用XmlReader.试试这个代码
You have a very large file so it is best to use XmlReader. Try this code
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Linq;
namespace ConsoleApplication16
{
class Program
{
const string FILENAME = @"c:\temp\test.xml";
enum State
{
GET_SUBNETWORK,
GET_MECONTEXT,
GET_CONTAINERS,
GET_SUBNETWORK_OR_MECONTEXT
}
static void Main(string[] args)
{
XmlReaderSettings settings = new XmlReaderSettings() { IgnoreWhitespace = true };
XmlReader reader = XmlReader.Create(FILENAME, settings);
reader.ReadToFollowing("SubNetwork", "generic.xsd");
Network.network.name = reader.GetAttribute("id");
Network.network.subnetworks = new List<SubNetwork>();
string xnNameSpace = reader.LookupNamespace("xn");
reader.ReadToFollowing("SubNetwork", xnNameSpace);
Sites newSite = null;
SubNetwork subNetWork = null;
Boolean endElement = false;
State state = State.GET_SUBNETWORK;
while (!reader.EOF)
{
switch (state)
{
case State.GET_SUBNETWORK:
if (reader.Name != "xn:SubNetwork")
{
reader.ReadToFollowing("SubNetwork", xnNameSpace);
}
if (!reader.EOF)
{
subNetWork = new SubNetwork();
Network.network.subnetworks.Add(subNetWork);
subNetWork.name = reader.GetAttribute("id");
subNetWork.sites = new List<Sites>();
state = State.GET_MECONTEXT;
}
break;
case State.GET_MECONTEXT :
if (reader.Name != "xn:MeContext")
{
if (reader.NodeType == XmlNodeType.EndElement)
{
endElement = true;
state = State.GET_SUBNETWORK;
}
else
{
endElement = false;
reader.ReadToFollowing("MeContext", xnNameSpace);
}
}
if (!reader.EOF && !endElement)
{
state = State.GET_CONTAINERS;
newSite = new Sites();
subNetWork.sites.Add(newSite);
newSite.sitename = reader.GetAttribute("id");
reader.ReadToFollowing("ManagedElement", xnNameSpace);
reader.ReadToFollowing("VsDataContainer", xnNameSpace);
}
break;
case State.GET_CONTAINERS:
if (!reader.EOF)
{
switch (reader.NodeType)
{
case XmlNodeType.EndElement:
state = State.GET_SUBNETWORK_OR_MECONTEXT;
break;
case XmlNodeType.Text:
string text = reader.ReadContentAsString();
break;
case XmlNodeType.Element:
string elementName = reader.Name;
XElement element = (XElement)XElement.ReadFrom(reader);
if (elementName == "xn:VsDataContainer")
{
XElement vsDataENodeBFunction = element.Descendants().Where(a => a.Name.LocalName == "vsDataENodeBFunction").FirstOrDefault();
if (vsDataENodeBFunction != null)
{
XElement eNBId = element.Descendants().Where(a => a.Name.LocalName == "eNBId").FirstOrDefault();
if (eNBId != null)
{
newSite.eNBId = (int)eNBId;
}
}
List<XElement> vsDataContainers = element.Descendants().Where(a => a.Name.LocalName == "VsDataContainer").ToList();
List<XElement> vsDataEUtranCellFDD = vsDataContainers.Where(x => x.Descendants().Where(a => (a.Name.LocalName == "vsDataType") && ((string)a == "vsDataEUtranCellFDD")).Any()).ToList();
if (vsDataEUtranCellFDD.Any())
{
List<CellName> cells = vsDataEUtranCellFDD.Select(x => new CellName()
{
id = (string)x.Attribute("id"),
earfcndl = (int)x.Descendants().Where(a => a.Name.LocalName == "earfcndl").FirstOrDefault(),
earfcnul = (int)x.Descendants().Where(a => a.Name.LocalName == "earfcnul").FirstOrDefault()
}).ToList();
if (newSite.cellName == null)
{
newSite.cellName = new List<CellName>();
}
newSite.cellName.AddRange(cells);
}
}
break;
default:
Console.WriteLine("Unexpected Results");
string elementText = reader.ReadContentAsString();
Console.ReadLine();
break;
}
}
break;
case State.GET_SUBNETWORK_OR_MECONTEXT :
switch(reader.NodeType)
{
case XmlNodeType.Element :
switch(reader.Name)
{
case "xn:MeContext" :
state = State.GET_MECONTEXT;
break;
case "xn:SubNetwork" :
state = State.GET_SUBNETWORK;
break;
default :
reader.ReadStartElement();
break;
}
break;
case XmlNodeType.Text:
string text = reader.ReadContentAsString();
break;
case XmlNodeType.EndElement:
reader.ReadEndElement();
break;
default:
Console.WriteLine("Unexpected Results");
string elementText = reader.ReadContentAsString();
Console.ReadLine();
break;
}
break;
}
}
}
}
public class Network
{
public static Network network = new Network();
public string name { get; set; }
public List<SubNetwork> subnetworks { get; set; }
}
public class SubNetwork
{
public string name { get; set; }
public List<Sites> sites { get; set; }
}
public class Sites
{
public string sitename { get; set; }
public int eNBId { get; set; }
public List<CellName> cellName { get; set; }
}
public class CellName
{
public string id { get; set; }
public int earfcndl { get; set; }
public int earfcnul { get; set; }
}
}
这篇关于如何在.net中读取具有不同层次结构的xml文件的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!