clean-office.xslt

<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
	<xsl:output omit-xml-declaration="yes" method="xml" cdata-section-elements="script"></xsl:output>
	<xsl:template match="/ | node() | @*">
		<xsl:copy>
			<xsl:apply-templates select="node() | @*"></xsl:apply-templates>
		</xsl:copy>
	</xsl:template>
	<xsl:template match="*[      (self::br or self::p or self::div)     and      normalize-space(translate(., &apos; &apos;, &apos;&apos;)) = &apos;&apos;     and      not(@*)     and      not(processing-instruction())     and      not(comment())     and      not(*[not(self::br) or @* or * or node()])     and      not(following::node()[not(         (self::text() or self::br or self::p or self::div)        and         normalize-space(translate(., &apos; &apos;, &apos;&apos;)) = &apos;&apos;        and         not(@*)        and         not(processing-instruction())        and         not(comment())        and         not(*[not(self::br) or @* or * or node()])       )])     ]">
		<!-- ignore all paragraphs and line-breaks at the end that have nothing but (non-breaking) spaces and line breaks -->
	</xsl:template>
	<xsl:template match="br[parent::div and not(preceding-sibling::node()) and not(following-sibling::node())]">
		<!-- Chrome generates <div><br/></div>. Renders differently in different browsers. Replace it with a non-breaking space -->
		<xsl:text></xsl:text>
	</xsl:template>
	<xsl:template match="@class[starts-with(string(.),&apos;Mso&apos;)]"/>
	<xsl:template match="@class[starts-with(string(.),&apos;xl&apos;)]"/>
	<xsl:template match="style|@style|comment()|@xml:lang|@lang"/>
	<xsl:template match="@cellspacing|@cellpadding|colgroup"/>
	<xsl:template match="@width[parent::table]|@border[parent::table]"/>
	<xsl:template match="@width[parent::td]|@height[parent::td]"/>
	<xsl:template match="span">
		<xsl:apply-templates select="node() | @*"/>
	</xsl:template>

</xsl:stylesheet>