Существует ли более быстрый способ хранения / чтения данных из документа XML?

Question

Я работал над приложением формы Windows в VB. NET, чтобы проанализировать большой документ XML, который является японско-английским sh словарем. Первоначально я создал анализатор на основе строк, который считывал все теги XML и извлекал их содержимое вручную. В среднем для полного анализа файла XML потребовалось около 30 секунд. На данный момент я никогда не слышал о десериализации.

Тогда, благодаря нескольким пользователям на этом сайте , я получил XML работает десериализатор, который загружает все данные из файла XML в объект класса. Brilliant. Но для загрузки в среднем требуется 20 секунд.

Хотя это повышение эффективности на 33%, мне интересно, есть ли еще лучший подход, о котором я не знал или не рассматривал. Или, возможно, неэффективность моих существующих определений кода / класса, которую я могу, по крайней мере, уменьшить.

Файл имеет длину 4,7 миллиона строк и отображает информацию для более чем 180 000 словарных статей, поэтому я готов принять, что не будьте более быстрым методом разбора XML. Мне интересно, может ли быть какой-нибудь альтернативный способ хранения данных, чем в текстовом формате XML, который может быть прочитан приложением формы Windows быстрее.

Вот код В настоящее время я использую для десериализации:

Sub Deserialise()
    Dim settings As XmlReaderSettings = New XmlReaderSettings
    settings.DtdProcessing = DtdProcessing.Parse

    Dim xmlPath As String = Path.Combine(Application.StartupPath, jmdictpath)

    Dim serialiser As New XmlSerializer(GetType(JMdict))

    Using rdr As Xml.XmlReader = Xml.XmlReader.Create(xmlPath, settings)
        dict = CType(serialiser.Deserialize(rdr), JMdict)
    End Using
End Sub

А вот определения классов:

<XmlRoot>
Public Class JMdict
    <XmlElement("entry")>
    Public Property entrylist As List(Of Entry)
End Class

<Serializable()>
<XmlType("entry")>
Public Class Entry
    <XmlElement("ent_seq")>
    Public Property EntrySequence As Integer
    <XmlElement("k_ele")>
    Public Property Keywords As List(Of KeywordElement)
    <XmlElement("r_ele")>
    Public Property Readings As List(Of ReadingElement)
    <XmlElement("sense")>
    Public Property Senses As List(Of SenseElement)
End Class

<Serializable()>
<XmlType("k_ele")>
Public Class KeywordElement
    <XmlElement("keb")>
    Public Property Keyword As String
    <XmlElement("ke_pri")>
    Public Property KeywordPriority As List(Of String)
    <XmlElement("ke_inf")>
    Public Property KeywordOrthography As List(Of String)
End Class

<Serializable()>
<XmlType("r_ele")>
Public Class ReadingElement

    <XmlElement("reb")>
    Public Property Reading As String
    <XmlElement("re_pri")>
    Public Property ReadingPriority As List(Of String)
    <XmlElement("re_inf")>
    Public Property ReadingOrthography As List(Of String)
    <XmlElement("re_restr")>
    Public Property ReadingToKeywordRestriction As List(Of String)

    Private _NotTrueReading As Boolean

    <XmlElement("re_nokanji")>
    Public Property NotTrueReading As String
        Get
            Return _NotTrueReading
        End Get
        Set
            If NotTrueReading IsNot Nothing Then
                _NotTrueReading = True
            Else
                _NotTrueReading = False
            End If
        End Set
    End Property
End Class

<Serializable()>
<XmlType("sense")>
Public Class SenseElement
    <XmlElement("pos")>
    Public Property PartOfSpeech As List(Of String)
    <XmlElement("gloss")>
    Public Property Gloss As List(Of GlossElement)

    <XmlElement("stagk")>
    Public Property SenseRestrictedToKeyword As List(Of String)
    <XmlElement("stagr")>
    Public Property SenseRestrictedToReading As List(Of String)

    <XmlElement("xref")>
    Public Property CrossReference As List(Of String)
    <XmlElement("ant")>
    Public Property Antonym As List(Of String)
    <XmlElement("field")>
    Public Property Field As List(Of String)
    <XmlElement("dial")>
    Public Property Dialect As List(Of String)
    <XmlElement("s_inf")>
    Public Property SenseInformation As List(Of String)
    <XmlElement("misc")>
    Public Property Misc As List(Of String)
    <XmlElement("lsource")>
    Public Property LanguageSource As List(Of LanguageSourceElement)
End Class


<Serializable()>
<XmlType("gloss")>
Public Class GlossElement
    <XmlAttribute("xml:lang")>
    Public Property Language As String
    <XmlAttribute("g_type")>
    Public Property GlossType As String
    <XmlText>
    Public Property Text As String
    Public Overrides Function ToString() As String
        Return Text
    End Function
End Class

<Serializable()>
<XmlType("lsource")>
Public Class LanguageSourceElement
    <XmlAttribute("xml:lang")>
    Public Property Language As String
    <XmlAttribute("ls_type")>
    Public Property LanguageSourceType As String

    Private _IsWaseieigo As Boolean
    <XmlAttribute("ls_wasei")>
    Public Property IsWaseieigo As String
        Get
            Return _IsWaseieigo
        End Get
        Set
            If IsWaseieigo = "y" Then
                _IsWaseieigo = True
            Else
                _IsWaseieigo = False
            End If
            '_IsWaseieigo = Value
        End Set
    End Property

    <XmlText>
    Public Property Text As String
    Public Overrides Function ToString() As String
        Return Text
    End Function

End Class

Что мы думаем? Есть ли надежда на более быстрое решение?

EDIT - Вот пример XML:

<entry>
<ent_seq>1486440</ent_seq>
<k_ele>
<keb>美術</keb>
<ke_pri>ichi1</ke_pri>
<ke_pri>news1</ke_pri>
<ke_pri>nf02</ke_pri>
</k_ele>
<r_ele>
<reb>びじゅつ</reb>
<re_pri>ichi1</re_pri>
<re_pri>news1</re_pri>
<re_pri>nf02</re_pri>
</r_ele>
<sense>
<pos>&n;</pos>
<pos>&adj-no;</pos>
<gloss>art</gloss>
<gloss>fine arts</gloss>
</sense>
<sense>
<gloss xml:lang="dut">kunst</gloss>
<gloss xml:lang="dut">schone kunsten</gloss>
</sense>
<sense>
<gloss xml:lang="fre">art</gloss>
<gloss xml:lang="fre">beaux-arts</gloss>
</sense>
<sense>
<gloss xml:lang="ger">Kunst</gloss>
<gloss xml:lang="ger">die schönen Künste</gloss>
<gloss xml:lang="ger">bildende Kunst</gloss>
</sense>
<sense>
<gloss xml:lang="ger">Produktionsdesign</gloss>
<gloss xml:lang="ger">Szenographie</gloss>
</sense>
<sense>
<gloss xml:lang="hun">művészet</gloss>
<gloss xml:lang="hun">művészeti</gloss>
<gloss xml:lang="hun">művészi</gloss>
<gloss xml:lang="hun">rajzóra</gloss>
<gloss xml:lang="hun">szépművészet</gloss>
</sense>
<sense>
<gloss xml:lang="rus">изящные искусства; искусство</gloss>
<gloss xml:lang="rus">{～{的}} художественный, артистический</gloss>
</sense>
<sense>
<gloss xml:lang="slv">umetnost</gloss>
<gloss xml:lang="slv">likovna umetnost</gloss>
</sense>
<sense>
<gloss xml:lang="spa">bellas artes</gloss>
</sense>
</entry>

И все это заключено в теги

Answer 1

Попробуйте xml linq. Код ниже не проверен, так как вы не опубликовали xml. :

Imports System.Xml
Imports System.Xml.Linq
Imports System.IO
Module Module1
    Const FILENAME As String = "c:\temp\test.xml"
    Sub Main()
        Dim JMdict As JMdict = JMdict.Parse(FILENAME)
    End Sub

    Public Class JMdict
        Public Property entrylist As List(Of Entry)

        Public Shared Function Parse(filename As String) As JMdict
            Dim reader As New StreamReader(filename)
            reader.ReadLine()
            Dim doc As XDocument = XDocument.Load(reader)
            Dim newJMdict As New JMdict()
            Dim jmDict = doc.Root

            newJMdict.entrylist = jmDict.Elements("entry").Select(Function(x) Entry.Parse(x)).ToList()
            Return newJMdict
        End Function
    End Class

    Public Class Entry
        Public Property EntrySequence As Integer
        Public Property Keywords As List(Of KeywordElement)
        Public Property Readings As List(Of ReadingElement)
        Public Property Senses As List(Of SenseElement)

        Public Shared Function Parse(xEntry As XElement) As Entry
            Dim newEntry As New Entry()
            newEntry.EntrySequence = CType(xEntry.Element("ent_seq"), Integer)
            newEntry.Keywords = xEntry.Elements("k_ele").Select(Function(x) KeywordElement.Parse(x)).ToList()

            newEntry.Readings = xEntry.Elements("r_ele").Select(Function(x) ReadingElement.Parse(x)).ToList()
            newEntry.Senses = xEntry.Elements("sense").Select(Function(x) SenseElement.Parse(x)).ToList()


            Return newEntry
        End Function
    End Class

    Public Class KeywordElement
        Public Property Keyword As String
        Public Property KeywordPriority As List(Of String)
        Public Property KeywordOrthography As List(Of String)

        Public Shared Function Parse(xKeywordElement As XElement) As KeywordElement
            Dim newKeywordElement As New KeywordElement()
            newKeywordElement.Keyword = CType(xKeywordElement.Element("key"), String)
            newKeywordElement.KeywordPriority = xKeywordElement.Elements("ke_pri").Select(Function(x) CType(x, String)).ToList()
            newKeywordElement.KeywordOrthography = xKeywordElement.Elements("ke_inf").Select(Function(x) CType(x, String)).ToList()

            Return newKeywordElement
        End Function


    End Class

    Public Class ReadingElement

        Public Property Reading As String
        Public Property ReadingPriority As List(Of String)
        Public Property ReadingOrthography As List(Of String)
        Public Property ReadingToKeywordRestriction As List(Of String)

        Private _NotTrueReading As Boolean

        Public Property NotTrueReading As String
            Get
                Return _NotTrueReading
            End Get
            Set(value As String)
                If NotTrueReading IsNot Nothing Then
                    _NotTrueReading = True
                Else
                    _NotTrueReading = False
                End If
            End Set
        End Property

        Public Shared Function Parse(xReadingElement As XElement) As ReadingElement
            Dim newReadingElement As New ReadingElement
            newReadingElement.Reading = CType(xReadingElement.Element("reb"), String)
            newReadingElement.ReadingPriority = xReadingElement.Elements("re_pri").Select(Function(x) CType(x, String)).ToList()
            newReadingElement.ReadingOrthography = xReadingElement.Elements("re_inf").Select(Function(x) CType(x, String)).ToList()
            newReadingElement.ReadingToKeywordRestriction = xReadingElement.Elements("re_restr").Select(Function(x) CType(x, String)).ToList()

            newReadingElement.NotTrueReading = CType(xReadingElement.Element("re_nokanji"), String)

            Return newReadingElement
        End Function
    End Class

    Public Class SenseElement
        Public Property PartOfSpeech As List(Of String)
        Public Property Gloss As List(Of GlossElement)

        Public Property SenseRestrictedToKeyword As List(Of String)
        Public Property SenseRestrictedToReading As List(Of String)
        Public Property CrossReference As List(Of String)
        Public Property Antonym As List(Of String)
        Public Property Field As List(Of String)
        Public Property Dialect As List(Of String)
        Public Property SenseInformation As List(Of String)
        Public Property Misc As List(Of String)
        Public Property LanguageSource As List(Of LanguageSourceElement)

        Public Shared Function Parse(xSenseElement As XElement) As SenseElement
            Dim newSenseElement As New SenseElement
            newSenseElement.PartOfSpeech = xSenseElement.Elements("pos").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.Gloss = xSenseElement.Elements("gloss").Select(Function(x) GlossElement.Parse(x)).ToList()
            newSenseElement.SenseRestrictedToKeyword = xSenseElement.Elements("stagk").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.SenseRestrictedToReading = xSenseElement.Elements("stagr").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.CrossReference = xSenseElement.Elements("xref").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.Antonym = xSenseElement.Elements("ant").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.Field = xSenseElement.Elements("field").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.Dialect = xSenseElement.Elements("dial").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.SenseInformation = xSenseElement.Elements("s_inf").Select(Function(x) CType(x, String)).ToList()
            newSenseElement.Misc = xSenseElement.Elements("misc").Select(Function(x) CType(x, String)).ToList()

            newSenseElement.LanguageSource = xSenseElement.Elements("lsource").Select(Function(x) LanguageSourceElement.Parse(x)).ToList()
            Return newSenseElement
        End Function
    End Class

    Public Class GlossElement
        Public Property Language As String
        Public Property GlossType As String
        Public Property Text As String

        Public Shared Function Parse(xGlossElement As XElement) As GlossElement
            Dim newGlossElement As New GlossElement

            newGlossElement.Language = CType(xGlossElement.Attributes().Where(Function(x) x.Name.LocalName = "lang").FirstOrDefault(), String)
            newGlossElement.GlossType = CType(xGlossElement.Attribute("g_type"), String)
            newGlossElement.Text = CType(xGlossElement, String)
            Return newGlossElement
        End Function
    End Class

    Public Class LanguageSourceElement

        Public Property Language As String
        Public Property LanguageSourceType As String

        Public IsWaseieigo As Boolean

        Public Property Text As String

        Public Shared Function Parse(xLanguageSourceElement As XElement) As LanguageSourceElement
            Dim newLanguageSourceElement As New LanguageSourceElement
            newLanguageSourceElement.Language = CType(xLanguageSourceElement.Attributes().Where(Function(x) x.Name.LocalName = "lang").FirstOrDefault(), String)
            newLanguageSourceElement.LanguageSourceType = CType(xLanguageSourceElement.Attribute("ls_type"), String)
            newLanguageSourceElement.IsWaseieigo = IIf(CType(xLanguageSourceElement.Attribute("ls_wasei"), String) = "y", True, False)
            newLanguageSourceElement.Text = CType(xLanguageSourceElement, String)
            Return newLanguageSourceElement
        End Function

    End Class
End Module