Question

我从数据库（MSSQL2014）生成XML输出，现在想将数据和XSD架构信息一起用于R数据框。

数据来源：select top 1 * from person.person as p join person.EmailAddress as ea on p.businessEntityID = ea.businessentityID join person.PersonPhone as pphone on p.businessEntityID = pphone.businessentityID for XML AUTO, ELEMENTS, XMLSCHEMA('person');

执行查询：

library(XML)
(xml_data <- xmlParse(gsub("&thinsp;", "", "C:\\dissertation\\smta\\indata\\01_Source_Query.XML", fixed = TRUE), asText = TRUE))

xml_attrib <- xpathSApply(doc=xml, path="//person",  xmlAttrs)

df2 <- data.frame(t(xml_attrib))
df2

以下是文件生成。我试过这个R代码导入但是不成功。有没有人有指导/提示指出我正确的方向？

RCODE：

<xsd:schema targetNamespace="person" xmlns:schema="person" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:sqltypes="http://schemas.microsoft.com/sqlserver/2004/sqltypes" elementFormDefault="qualified">
  <xsd:import namespace="http://schemas.microsoft.com/sqlserver/2004/sqltypes" schemaLocation="http://schemas.microsoft.com/sqlserver/2004/sqltypes/sqltypes.xsd" />
  <xsd:import namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactInfo" />
  <xsd:import namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactRecord" />
  <xsd:import namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactTypes" />
  <xsd:import namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/IndividualSurvey" />
  <xsd:element name="p">
    <xsd:complexType>
      <xsd:sequence>
        <xsd:element name="BusinessEntityID" type="sqltypes:int" />
        <xsd:element name="PersonType">
          <xsd:simpleType>
            <xsd:restriction base="sqltypes:nchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="2" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="NameStyle" type="sqltypes:bit" sqltypes:sqlTypeAlias="[AdventureWorks2014].[dbo].[NameStyle]" />
        <xsd:element name="Title" minOccurs="0">
          <xsd:simpleType>
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="8" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="FirstName">
          <xsd:simpleType sqltypes:sqlTypeAlias="[AdventureWorks2014].[dbo].[Name]">
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="50" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="MiddleName" minOccurs="0">
          <xsd:simpleType sqltypes:sqlTypeAlias="[AdventureWorks2014].[dbo].[Name]">
            <xsd:restri ction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="50" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="LastName">
          <xsd:simpleType sqltypes:sqlTypeAlias="[AdventureWorks2014].[dbo].[Name]">
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="50" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="Suffix" minOccurs="0">
          <xsd:simpleType>
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="10" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="EmailPromotion" type="sqltypes:int" />
        <xsd:element name="AdditionalContactInfo" minOccurs="0">
          <xsd:complexType sqltypes:xmlSchemaCollection="[AdventureWorks2014].[Person].[AdditionalContactInfoSchemaCollection]">
            <xsd:complexContent>
              <xsd:restriction base="sqltypes:xml">
                <xsd:sequence>
                  <xsd:any processContents="strict" minOccurs="0" maxOccurs="unbounded" namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactInfo http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactRecord http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/ContactTypes"
                  /></xsd:sequence>
              </xsd:restriction>
            </xsd:complexContent>
          </xsd:complexType>
        </xsd:element>
        <xsd:element name="Demographics" minOccurs="0">
          <xsd:complexType sqltypes:xmlSchemaCollection="[AdventureWorks2014].[Person].[IndividualSurveySchemaCollection]">
            <xsd:complexContent>
              <xsd:restriction base="sqltypes:xml">
                <xsd:sequence>
                  <xsd:any processContents="strict" minOccurs="0" maxOccurs="unbounded" namespace="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/IndividualSurvey" /></xsd:sequence>
              </xsd:restriction>
            </xsd:complexContent>
          </xsd:complexType>
        </xsd:element>
        <xsd :element name="rowguid" type="sqltypes:uniqueidentifier" />
        <xsd:element name="ModifiedDate" type="sqltypes:datetime" />
        <xsd:element ref="schema:ea" minOccurs="0" maxOccurs="unbounded" /></xsd:sequence>
    </xsd:complexType>
  </xsd:element>
  <xsd:element name="ea">
    <xsd:complexType>
      <xsd:sequence>
        <xsd:element name="BusinessEntityID" type="sqltypes:int" />
        <xsd:element name="EmailAddressID" type="sqltypes:int" />
        <xsd:element name="EmailAddress" minOccurs="0">
          <xsd:simpleType>
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="50" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="rowguid" type="sqltypes:uniqueidentifier" />
        <xsd:element name="ModifiedDate" type="sqltypes:datetime" />
        <xsd:element ref="schema:pphone" minOccurs="0" maxOccurs="unbounded" /></xsd:sequence>
    </xsd:complexType>
  </xsd:element>
  <xsd:element name="pphone">
    <xsd:complexType>
      <xsd:sequence>
        <xsd:element name="BusinessEntityID" type="sqltypes:int" />
        <xsd:element name="PhoneNumber">
          <xsd:simpleType sqltypes:sqlTypeAlias="[AdventureWorks2014].[dbo].[Phone]">
            <xsd:restriction base="sqltypes:nvarchar" sqltypes:localeId="1033" sqltypes:sqlCompareOptions="IgnoreCase IgnoreKanaType IgnoreWidth" sqltypes:sqlSortId="52">
              <xsd:maxLength value="25" /></xsd:restriction>
          </xsd:simpleType>
        </xsd:element>
        <xsd:element name="PhoneNumberTypeID" type="sqltypes:int" />
        <xsd:element name="ModifiedDate" type="sqltypes:datetime" /></xsd:sequence>
    </xsd:complexType>
  </xsd:element>
</xsd:schema>
<p xmlns="person">
  <BusinessEntityID>1</BusinessEntityID>
  <PersonType>EM</PersonType>
  <NameStyle>0</NameStyle>
  <FirstName>Ken</FirstName>
  <MiddleName>J</MiddleName>
  <LastName>Sánchez</LastName>
  <EmailPromotion>0</EmailPromotion>
  <Demographics>
    <IndividualSurvey xmlns="http://schemas.microsoft.com/sqlserver/2004/07/adventure-works/IndividualSurvey">
      <TotalPurchaseYTD>0</TotalPurchaseYTD>
    </IndividualSurvey>
  </Demographics>
  <rowguid>92C4279F-1207-48A3-8448-4636514EB7E2</rowgu id>
    <ModifiedDate>2009-01-07T00:00:00</ModifiedDate>
    <ea>
      <BusinessEntityID>1</BusinessEntityID>
      <EmailAddressID>1</EmailAddressID>
      <EmailAddress>ken0@adventure-works.com</EmailAddress>
      <rowguid>8A1901E4-671B-431A-871C-EADB2942E9EE</rowguid>
      <ModifiedDate>2009-01-07T00:00:00</ModifiedDate>
      <pphone>
        <BusinessEntityID>1</BusinessEntityID>
        <PhoneNumber>697-555-0142</PhoneNumber>
        <PhoneNumberTypeID>1</PhoneNumberTypeID>
        <ModifiedDate>2009-01-07T00:00:00</ModifiedDate>
      </pphone>
    </ea>
</p>

{{1}}

Answer 1

我更喜欢rest / xml2包来解析文件。

library(xml2)
library(rvest)
page<-read_html("C:\\dissertation\\smta\\indata\\01_Source_Query.XML")

persons<-html_nodes(page,  xpath = "//p")

fieldnames<-xml_name(xml_find_all(persons, ".//*"))
fields<-xml_text(xml_find_all(persons, ".//*"))
df<-data.frame(fieldnames, fields)

该文件似乎对html感兴趣。上面的代码读取数据文件，找到人员的段落标记

，并提取字段名称和值，并将它们放入数据框中。如果文件中有多个人，那么定义字段名称和值的行将需要进行矢量化（最有可能是供应）。需要进行一些清理才能删除添加到最终数据框中的一些无关行祝你好运。

将XSD和数据导入R

1 个答案: