如何使用 XSLT 2.0 将 csv 文件转换为结构化 XML 文件？

Question

我想将下面的 CSV 转换为 XML

CSV 输入示例

01,TeacherHeader1
02,StudentHeader1
03,SubjectHeader1
10,Grade1,Score99
10,Grade2,Score99
48,SubjectTrailer1
49,StudentTrailer1
02,StudentHeader2
03,SubjectHeader1
10,Grade1,Score50
10,Grade2,Score50
48,SubjectTrailer1
49,StudentTrailer2
50,TeacherTrailer1

输出应该是

  <FileHeader> 
    <id>01</id>  
    <name>TeacherHeader1</name> 
  </FileHeader>  
  <GroupRecord> 
    <GroupHeader> 
      <id>02</id>  
      <name>StudentHeader1</name> 
    </GroupHeader>  
    <AccountRecord> 
      <AccountHeader> 
        <id>03</id>  
        <name>SubjectHeader1</name> 
      </AccountHeader>  
      <AccountDetails> 
        <Details> 
          <id>10</id>  
          <name>Grade1</name>  
          <value>Score99</value> 
        </Details>  
        <Details> 
          <id>10</id>  
          <name>Grade2</name>  
          <value>Score99</value> 
        </Details> 
      </AccountDetails>  
      <AccountTrailer> 
        <id>48</id>  
        <name>SubjectTrailer1</name> 
      </AccountTrailer> 
    </AccountRecord>  
    <GroupTrailer> 
      <id>49</id>  
      <name>StudentTrailer1</name> 
    </GroupTrailer> 
  </GroupRecord>  
  <GroupRecord> 
    <GroupHeader> 
      <id>02</id>  
      <name>StudentHeader2</name> 
    </GroupHeader>  
    <AccountRecord> 
      <AccountHeader> 
        <id>03</id>  
        <name>SubjectHeader1</name> 
      </AccountHeader>  
      <AccountDetails> 
        <Details> 
          <id>10</id>  
          <name>Grade1</name>  
          <value>Score99</value> 
        </Details>  
        <Details> 
          <id>10</id>  
          <name>Grade2</name>  
          <value>Score99</value> 
        </Details> 
      </AccountDetails>  
      <AccountTrailer> 
        <id>48</id>  
        <name>SubjectTrailer1</name> 
      </AccountTrailer> 
    </AccountRecord>  
    <GroupTrailer> 
      <id>49</id>  
      <name>StudentTrailer2</name> 
    </GroupTrailer> 
  </GroupRecord>  
  <FileTrailer> 
    <id>50</id>  
    <name>TeacherTrailer1</name> 
  </FileTrailer> 

在哪里

01 = FileHeader 
02 = GroupHeader (grouped inside GroupRecord)
03 = AccountHeader (grouped inside AccountRecord)
10 = Details (grouped inside AccountDetails)
48 = AccountTrailer (grouped inside AccountRecord)
49 = GroupTrailer (group inside GroupRecord)
50 = FileTrailer  

我想将上面的 CSV 转换为结构正确的 XML，如上所示。 任何帮助将不胜感激。谢谢。

Answer 1

正如我在评论中所说，您可以使用 unparsed-text 和 tokenize 处理文本文件以将其转换为 XML（或在 XSLT 3 中使用 unparsed-text-lines 和 tokenize 如果可用），然后其余的可以使用嵌套的xsl:for-each-groups 来完成任务，甚至可以在建立规则模式后使用一两个递归函数；以下尝试拼出嵌套的for-each-groups：

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema"
    expand-text="yes"
    xmlns:mf="http://example.com/mf"
    exclude-result-prefixes="#all"
    version="3.0">

  <xsl:param name="data" as="xs:string">01,TeacherHeader1
02,StudentHeader1
03,SubjectHeader1
10,Grade1,Score99
10,Grade2,Score99
48,SubjectTrailer1
49,StudentTrailer1
02,StudentHeader2
03,SubjectHeader1
10,Grade1,Score50
10,Grade2,Score50
48,SubjectTrailer1
49,StudentTrailer2
50,TeacherTrailer1</xsl:param>

<xsl:param name="header-ids" as="xs:string*"
  select="'01', '02', '03', '10', '48', '49', '50'"/>

<xsl:param name="header-names" as="xs:string*"
  select="'FileHeader ', 'GroupHeader', 'AccountHeader', 'Details', 'AccountTrailer', 'GroupTrailer', 'FileTrailer'"/>

  <xsl:variable name="lines">
      <xsl:for-each select="tokenize($data, '\r?\n')">
          <line>
              <xsl:variable name="tokens" as="xs:string*" select="tokenize(., ',')"/>
              <id>{$tokens[1]}</id>
              <name>{$tokens[2]}</name>
              <xsl:if test="$tokens[3]">
                  <value>{$tokens[3]}</value>
              </xsl:if>
          </line>
      </xsl:for-each>
  </xsl:variable>

  <xsl:mode on-no-match="shallow-copy"/>

  <xsl:output method="xml" indent="yes"/>

  <xsl:template match="/" name="xsl:initial-template">
      <xsl:for-each-group select="$lines/line" group-starting-with="line[id = '01']">
          <File>
              <xsl:apply-templates select="."/>
              <xsl:for-each-group select="current-group() except ." group-ending-with="line[id = '50']">
                  <xsl:for-each-group select="current-group()[position() lt last()]" group-starting-with="line[id = '02']">
                      <GroupRecord>
                          <xsl:apply-templates select="."/>
                          <xsl:for-each-group select="current-group() except ." group-ending-with="line[id = '49']">
                              <xsl:for-each-group select="current-group()[position() lt last()]" group-starting-with="line[id = '03']">
                                  <AccountRecord>
                                      <xsl:apply-templates select="."/>
                                      <AccountDetails>
                                          <xsl:apply-templates select="(current-group() except .)[id != '48']"/>
                                      </AccountDetails>
                                      <xsl:apply-templates select="current-group()[id = '48']"/>
                                  </AccountRecord>
                              </xsl:for-each-group>
                              <xsl:apply-templates select="current-group()[last()]"/>
                          </xsl:for-each-group>
                      </GroupRecord>
                  </xsl:for-each-group>
                  <xsl:apply-templates select="current-group()[last()]"/>
              </xsl:for-each-group>
          </File>
      </xsl:for-each-group>
  </xsl:template>

  <xsl:template match="line">
      <xsl:element name="{$header-names[index-of($header-ids, current()/id)]}">
          <xsl:apply-templates/>
      </xsl:element>
  </xsl:template>

</xsl:stylesheet>

https://xsltfiddle.liberty-development.net/gWEaSv8。为了示例的完整性和紧凑性，示例数据已被内联，但您当然可以使用 <xsl:param name="data" as="xs:string" select="unparsed-text('file.txt')"/> 代替。我还使用了 xsl:mode 声明和 name="xsl:initial-template"，这两个 XSLT 3 特性都需要适应 XSLT 2 处理器来拼出身份转换并使用不同的模板名称，例如name="main" 作为代码的入口点。我还在那里使用了像 <id>{$tokens[1]}</id> 这样的文本值模板，对于 XSLT 2 处理器，您需要使用例如<id><xsl:value-of select="$tokens[1]"/</id>.