XSLT 1.0 Word Count with HTML

Question

I want to call a pattern that cuts a field to 30 words. However, this field contains HTML and HTML should not be counted as a word.

Answer 1

Try this, although admittedly translating the call is a little ugly:

<xsl:template match="field">
  <xsl:value-of select="string-length(translate(normalize-space(.),'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789',''))+1" />
</xsl:template>

, , , , , . , normalize-space(.), , , . , , . , <p>My<b>text</b> test</p>, 2, Mytext .

, :

<xsl:template match="field">
  <xsl:call-template name="countwords">
    <xsl:with-param name="text" select="normalize-space(.)" />
  </xsl:call-template>
</xsl:template>

<xsl:template name="countwords">
  <xsl:param name="count" select="0" />
  <xsl:param name="text" />
  <xsl:choose>
    <xsl:when test="contains($text,' ')">
      <xsl:call-template name="countwords">
        <xsl:with-param name="count" select="$count + 1" />
        <xsl:with-param name="text" select="substring-after($text,' ')" />
      </xsl:call-template>
    </xsl:when>
    <xsl:otherwise><xsl:value-of select="$count + 1" /></xsl:otherwise>
  </xsl:choose>
</xsl:template>

normalize-space(.) , , $text, count , substring-after($text,' '). , $text $count + 1 (+1 ).

, , .

EDIT: : , , , . , xml, - , , , :

<xsl:template name="countwords">
  <xsl:param name="count" select="0" />
  <xsl:param name="text" />
  <xsl:choose>
    <xsl:when test="$count = 30" />
    <xsl:when test="contains($text,' ')">
      <xsl:if test="$count != 0"><xsl:text>&#32;</xsl:text></xsl:if>
      <xsl:value-of select="substring-before($text,' ')" />
      <xsl:call-template name="countwords">
        <xsl:with-param name="count" select="$count + 1" />
        <xsl:with-param name="text" select="substring-after($text,' ')" />
      </xsl:call-template>
    </xsl:when>
    <xsl:otherwise><xsl:value-of select="$text" /></xsl:otherwise>
  </xsl:choose>
</xsl:template>

<xsl:when, , 30, , .

EDIT: , , XML-:

<xsl:template match="field">
  <xsl:call-template name="countwords">
    <xsl:with-param name="text" select="." />
  </xsl:call-template>
</xsl:template>

<xsl:template name="countwords">
  <xsl:param name="count" select="0" />
  <xsl:param name="text" />
  <xsl:choose>
    <xsl:when test="starts-with($text, '&lt;')">
      <xsl:value-of select="concat(substring-before($text,'&gt;'),'&gt;')" />
      <xsl:call-template name="countwords">
        <xsl:with-param name="count">
          <xsl:choose>
            <xsl:when test="starts-with(substring-after($text,'&gt;'),' ')"><xsl:value-of select="$count + 1" /></xsl:when>
            <xsl:otherwise><xsl:value-of select="$count" /></xsl:otherwise>
          </xsl:choose>
        </xsl:with-param>
        <xsl:with-param name="text" select="substring-after($text,'&gt;')" />
      </xsl:call-template>
    </xsl:when>
    <xsl:when test="(contains($text, '&lt;') and contains($text, ' ') and string-length(substring-before($text,' ')) &lt; string-length(substring-before($text,'&lt;'))) or (contains($text,' ') and not(contains($text,'&lt;')))">
      <xsl:choose>
        <xsl:when test="$count &lt; 29"><xsl:value-of select="concat(substring-before($text, ' '),'&#32;')" /></xsl:when>
        <xsl:when test="$count = 29"><xsl:value-of select="substring-before($text, ' ')" /></xsl:when>
      </xsl:choose>
      <xsl:call-template name="countwords">
        <xsl:with-param name="count">
          <xsl:choose>
            <xsl:when test="normalize-space(substring-before($text, ' ')) = ''"><xsl:value-of select="$count" /></xsl:when>
            <xsl:otherwise><xsl:value-of select="$count + 1" /></xsl:otherwise>
          </xsl:choose>
        </xsl:with-param>
        <xsl:with-param name="text" select="substring-after($text,' ')" />
      </xsl:call-template>
    </xsl:when>
    <xsl:when test="(contains($text, '&lt;') and contains($text, ' ') and string-length(substring-before($text,' ')) &gt; string-length(substring-before($text,'&lt;'))) or contains($text,'&lt;')">
      <xsl:if test="$count &lt; 30">
        <xsl:value-of select="substring-before($text, '&lt;')" />
      </xsl:if>
      <xsl:call-template name="countwords">
        <xsl:with-param name="count" select="$count" />
        <xsl:with-param name="text" select="concat('&lt;',substring-after($text,'&lt;'))" />
      </xsl:call-template>
    </xsl:when>
    <xsl:otherwise>
      <xsl:if test="$count &lt; 30">
        <xsl:value-of select="$text" />
      </xsl:if>
    </xsl:otherwise>
  </xsl:choose>
</xsl:template>

- , , , !

Answer 2

:

, , , . .

() :

<xsl:template name="wordCount">
    <xsl:param name="input" required="yes"/>
    <xsl:param name="sep" select="'‒–—―'"/>
    <xsl:variable name="big"><xsl:value-of select="normalize-space(translate($input, $sep, ' '))"/></xsl:variable>
    <xsl:variable name="small"><xsl:value-of select="translate($big, ' ', '')"/></xsl:variable>
    <xsl:value-of select="string-length($big)-string-length($small)"/>
</xsl:template>

$sep ( ), .

, , ( ):

<xsl:call-template name="wordCount">
    <xsl:with-param name="input">
        <!-- templates etc to output text from html -->
    </xsl:with-param>
</xsl:call-template>