XSLT: moving a grouping html elements into section levels

Question

I\'m trying to write an XSLT that organizes an HTML file into different section levels depending on the header level. Here is my input:

Answer 1

I was able to get something working for my addendum above. I added logic into the body template to test for header tags. It may not work for every situation, but it is doing well for my task.

<xsl:template match="body">
<xsl:choose>
<xsl:when test="descendant::h1">
<xsl:apply-templates/>
</xsl:when>
<xsl:otherwise>
<section level="1">
<item>
<block ccm="yes" onbup="no" quickref="no" web="no">
<xsl:apply-templates/>
</block>
</item>
</section>              
</xsl:otherwise>
</xsl:choose>        
</xsl:template>

Answer 2

Here is an XSLT 2.0 stylesheet:

<xsl:stylesheet 
  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
  xmlns:xs="http://www.w3.org/2001/XMLSchema"
  xmlns:mf="http://example.com/mf"
  exclude-result-prefixes="xs mf"
  version="2.0">

  <xsl:output indent="yes"/>

  <xsl:function name="mf:group" as="node()*">
    <xsl:param name="elements" as="element()*"/>
    <xsl:param name="level" as="xs:integer"/>
    <xsl:for-each-group select="$elements" group-starting-with="*[local-name() eq concat('h', $level)]">
      <xsl:choose>
        <xsl:when test="self::*[local-name() eq concat('h', $level)]">
          <section level="{$level}">
            <xsl:element name="header{$level}"><xsl:apply-templates/></xsl:element>
            <xsl:sequence select="mf:group(current-group() except ., $level + 1)"/>
          </section>
        </xsl:when>
        <xsl:otherwise>
          <xsl:apply-templates select="current-group()"/>
        </xsl:otherwise>
      </xsl:choose>
    </xsl:for-each-group>
  </xsl:function>

  <xsl:template match="@* | node()">
    <xsl:copy>
      <xsl:apply-templates select="@*, node()"/>
    </xsl:copy>
  </xsl:template>

  <xsl:template match="/html">
    <document>
      <xsl:apply-templates select="body"/>
    </document>
  </xsl:template>

  <xsl:template match="body">
    <xsl:sequence select="mf:group(*, 1)"/>
  </xsl:template>

</xsl:stylesheet>

It should do what you asked for, although it does not stop at four nested levels but rather groups as long as it finds h[n] elements.

Answer 3

An XSLT 1.0 solution (essentially borrowed by Jenni Tennison):

<xsl:stylesheet version="1.0"
 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 <xsl:output omit-xml-declaration="yes" indent="yes"/>
 <xsl:strip-space elements="*"/>

 <xsl:template match="html">
   <document><xsl:apply-templates/></document>
 </xsl:template>

 <xsl:template match="body">
   <xsl:apply-templates select="h1" />
 </xsl:template>

 <xsl:key name="next-headings" match="h6"
          use="generate-id(preceding-sibling::*[self::h1 or self::h2 or
                                               self::h3 or self::h4 or
                                               self::h5][1])" />
 <xsl:key name="next-headings" match="h5"
          use="generate-id(preceding-sibling::*[self::h1 or self::h2 or
                                               self::h3 or self::h4][1])" />
 <xsl:key name="next-headings" match="h4"
          use="generate-id(preceding-sibling::*[self::h1 or self::h2 or
                                               self::h3][1])" />
 <xsl:key name="next-headings" match="h3"
          use="generate-id(preceding-sibling::*[self::h1 or self::h2][1])" />
 <xsl:key name="next-headings" match="h2"
          use="generate-id(preceding-sibling::h1[1])" />

 <xsl:key name="immediate-nodes"
          match="node()[not(self::h1 | self::h2 | self::h3 | self::h4 |
                           self::h5 | self::h6)]"
          use="generate-id(preceding-sibling::*[self::h1 or self::h2 or
                                               self::h3 or self::h4 or
                                               self::h5 or self::h6][1])" />

 <xsl:template match="h1 | h2 | h3 | h4 | h5 | h6">
   <xsl:variable name="vLevel" select="substring-after(name(), 'h')" />
   <section level="{$vLevel}">
      <xsl:element name="header{$vLevel}">
        <xsl:apply-templates />
      </xsl:element>
      <xsl:apply-templates select="key('immediate-nodes', generate-id())" />
      <xsl:apply-templates select="key('next-headings', generate-id())" />
   </section>
 </xsl:template>

 <xsl:template match="/*/*/node()" priority="-20">
   <xsl:copy-of select="." />
 </xsl:template>
</xsl:stylesheet>

when this transformation is applied on the following XML document:

<html>
    <body>
        <h1>1</h1>
        <p>1</p>
        <h2>1.1</h2>
        <p>2</p>
        <h3>1.1.1</h3>
        <p>3</p>
        <h2>1.2</h2>
        <p>4</p>
        <h1>2</h1>
        <p>5</p>
        <h2>2.1</h2>
        <p>6</p>
    </body>
</html>

the wanted result is produced:

<document>
   <section level="1">
      <header1>1</header1>
      <p>1</p>
      <section level="2">
         <header2>1.1</header2>
         <p>2</p>
         <section level="3">
            <header3>1.1.1</header3>
            <p>3</p>
         </section>
      </section>
      <section level="2">
         <header2>1.2</header2>
         <p>4</p>
      </section>
   </section>
   <section level="1">
      <header1>2</header1>
      <p>5</p>
      <section level="2">
         <header2>2.1</header2>
         <p>6</p>
      </section>
   </section>
</document>

Answer 4

A more general grouping in XSLT 1.0

<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:key name="kHeaderByPreceding"
             match="body/*[starts-with(name(),'h')]"
             use="generate-id(preceding-sibling::*
                                 [starts-with(name(),'h')]
                                 [substring(name(current()),2)
                                   > substring(name(),2)][1])"/>
    <xsl:key name="kElementByPreceding"
             match="body/*[not(starts-with(name(),'h'))]"
             use="generate-id(preceding-sibling::*
                                 [starts-with(name(),'h')][1])"/>
    <xsl:template match="node()|@*" mode="copy">
        <xsl:copy>
            <xsl:apply-templates select="node()|@*" mode="copy"/>
        </xsl:copy>
    </xsl:template>
    <xsl:template match="body">
        <document>
            <xsl:apply-templates select="key('kHeaderByPreceding','')"/>
        </document>
    </xsl:template>
    <xsl:template match="body/*[starts-with(name(),'h')]">
        <section level="{substring(name(),2)}">
            <xsl:element name="header{substring(name(),2)}">
                <xsl:apply-templates mode="copy"/>
            </xsl:element>
            <xsl:apply-templates select="key('kElementByPreceding',
                                             generate-id())"
                                 mode="copy"/>
            <xsl:apply-templates select="key('kHeaderByPreceding',
                                             generate-id())"/>
        </section>
    </xsl:template>
    <xsl:template match="text()"/>
</xsl:stylesheet>

Output:

<document>
    <section level="1">
        <header1>HEADER 1 CONTENT</header1>
        <p>Level 1 para</p>
        <p>Level 1 para</p>
        <p>Level 1 para</p>
        <p>Level 1 para</p>
        <section level="2">
            <header2>Header 2 CONTENT</header2>
            <p>Level 2 para</p>
            <p>Level 2 para</p>
            <p>Level 2 para</p>
            <p>Level 2 para</p>
        </section>
    </section>
</document>

And with a more complex input sample like:

<body>
    <h1>1</h1>
    <p>1</p>
    <h2>1.1</h2>
    <p>2</p>
    <h3>1.1.1</h3>
    <p>3</p>
    <h2>1.2</h2>
    <p>4</p>
    <h1>2</h1>
    <p>5</p>
    <h2>2.1</h2>
    <p>6</p>
</body>

Output:

<document>
    <section level="1">
        <header1>1</header1>
        <p>1</p>
        <section level="2">
            <header2>1.1</header2>
            <p>2</p>
            <section level="3">
                <header3>1.1.1</header3>
                <p>3</p>
            </section>
        </section>
        <section level="2">
            <header2>1.2</header2>
            <p>4</p>
        </section>
    </section>
    <section level="1">
        <header1>2</header1>
        <p>5</p>
        <section level="2">
            <header2>2.1</header2>
            <p>6</p>
        </section>
    </section>
</document>