Question

我有来自第三方的xml文件。因为xml文件很大（40MB），我使用这种方式使用XmlTextReader逐步解析文件：

class Parser
{
    // ...

    public void ImportFile(string fileName)
    {
        bool isCountryStateFile = IsCountryStateFile(fileName);

        XmlTextReader xmlReader = new XmlTextReader(fileName);
        namespaceManager = new XmlNamespaceManager(xmlReader.NameTable);
        namespaceManager.FillRuianNamespaces();

        xmlReader.WhitespaceHandling = WhitespaceHandling.None;

        while (xmlReader.Read())
        {
            if (xmlReader.NodeType == XmlNodeType.Element &&
                xmlReader.IsStartElement() == true)
            {
                // skip items in country state file (are included in sity state files)
                if (isCountryStateFile && nodesToSkipInCountryStateFile.Contains(xmlReader.Name))
                {
                    Console.WriteLine("Skiping {0}", xmlReader.Name);
                    xmlReader.Skip();
                }

                if (xmlReader.Name == "vf:Vusc")
                {
                    var item = ParseRegion(xmlReader);
                    repository.Save(item);
                    xmlReader.Skip();
                }
                if (xmlReader.Name == "vf:Obec")
                {
                    var item = ParseCity(xmlReader);
                    repository.Save(item);
                    xmlReader.Skip();
                }
            }
        }

        xmlReader.Close();
    }

    private Region ParseRegion(XmlTextReader xmlReader)
    {
        XmlDocument node = new XmlDocument();
        node.LoadXml(xmlReader.ReadOuterXml());

        // parse and compose Region
        // ...

        return result;
    }

    // ...
}

通常，节点的结构为<Cities><City/></Cities>，一切运行良好，但有些节点包含与其父节点同名的子节点：

<?xml version="1.0" encoding="UTF-8"?>
<vf:VymennyFormat xsi:schemaLocation="urn:cz:isvs:ruian:schemas:VymennyFormatTypy:v1 ../ruian/xsd/vymenny_format/VymennyFormatTypy.xsd" xmlns:gml="http://www.opengis.net/gml/3.2" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ami="urn:cz:isvs:ruian:schemas:AdrMistoIntTypy:v1" xmlns:base="urn:cz:isvs:ruian:schemas:BaseTypy:v1" xmlns:coi="urn:cz:isvs:ruian:schemas:CastObceIntTypy:v1" xmlns:com="urn:cz:isvs:ruian:schemas:CommonTypy:v1" xmlns:kui="urn:cz:isvs:ruian:schemas:KatUzIntTypy:v1" xmlns:kri="urn:cz:isvs:ruian:schemas:KrajIntTypy:v1" xmlns:mci="urn:cz:isvs:ruian:schemas:MomcIntTypy:v1" xmlns:mpi="urn:cz:isvs:ruian:schemas:MopIntTypy:v1" xmlns:obi="urn:cz:isvs:ruian:schemas:ObecIntTypy:v1" xmlns:oki="urn:cz:isvs:ruian:schemas:OkresIntTypy:v1" xmlns:opi="urn:cz:isvs:ruian:schemas:OrpIntTypy:v1" xmlns:pai="urn:cz:isvs:ruian:schemas:ParcelaIntTypy:v1" xmlns:pui="urn:cz:isvs:ruian:schemas:PouIntTypy:v1" xmlns:rsi="urn:cz:isvs:ruian:schemas:RegSouIntiTypy:v1" xmlns:spi="urn:cz:isvs:ruian:schemas:SpravObvIntTypy:v1" xmlns:sti="urn:cz:isvs:ruian:schemas:StatIntTypy:v1" xmlns:soi="urn:cz:isvs:ruian:schemas:StavObjIntTypy:v1" xmlns:uli="urn:cz:isvs:ruian:schemas:UliceIntTypy:v1" xmlns:vci="urn:cz:isvs:ruian:schemas:VuscIntTypy:v1" xmlns:vf="urn:cz:isvs:ruian:schemas:VymennyFormatTypy:v1" xmlns:zji="urn:cz:isvs:ruian:schemas:ZsjIntTypy:v1">
    <vf:Data>
        <vf:Vusc> <!-- HERE -->
            <vf:Vusc gml:id="VC.19">
                <vci:Kod>19</vci:Kod>
                <vci:Nazev>Hlavní město Praha</vci:Nazev>
                <vci:RegionSoudrznosti>
                    <rsi:Kod>19</rsi:Kod>
                </vci:RegionSoudrznosti>
                <vci:PlatiOd>2013-06-11T00:00:00</vci:PlatiOd>
                <vci:IdTransakce>241736</vci:IdTransakce>
                <vci:GlobalniIdNavrhuZmeny>413702</vci:GlobalniIdNavrhuZmeny>
                <vci:NutsLau>CZ010</vci:NutsLau>
                <vci:Geometrie>
                    <vci:DefinicniBod>
                        <gml:Point gml:id="DVC.19" srsName="urn:ogc:def:crs:EPSG::5514" srsDimension="2">
                            <gml:pos>-743100.00 -1043300.00</gml:pos>
                        </gml:Point>
                    </vci:DefinicniBod>
                </vci:Geometrie>
            </vf:Vusc>
        </vf:Vusc>
        ...
    </vf:Data>
</vf:VymennyFormat>

在这种情况下如何选择适当的节点来解析只有子节点以及如何使用XmlTextReader.Skip（）跳过像其顶级所有子节点一样的父节点？如果我跳过它，它无论如何都会读到孩子们。

Answer 1

您可以使用XmlReader.ReadSubTree解决此问题。例如：

if (xmlReader.Name == "vf:Vusc")
{
    using (var subtree = xmlReader.ReadSubTree())
    {
        var item = ParseRegion(subtree);
        repository.Save(item);
    }
}

ReadSubTree限制了ParseRegion可以看到的XML量。当ParseRegion返回时，阅读器位于其所在标签的结尾元素处。因此，您的主阅读器循环将永远不会看到内部的“vf：Vusc”标签。

XmlTextReader，跳过具有相同名称的子节点

1 个答案: