tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

openxml word: be more specific for extracting text, avoids treating some image parameters as text

Browse Source
This commit is contained in:
Jean-Francois Dockes 2020-07-15 10:49:06 +02:00
parent b8be14bd7b
commit b4306b71c0
1 changed files with 28 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
src/filters/openxml-word-body.xsl
View File

@ -1,27 +1,28 @@
<?xml version="1.0"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
xmlns:ve="http://schemas.openxmlformats.org/markup-compatibility/2006"
xmlns:o="urn:schemas-microsoft-com:office:office"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"
xmlns:v="urn:schemas-microsoft-com:vml"
xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
xmlns:w10="urn:schemas-microsoft-com:office:word"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml">
<xsl:output omit-xml-declaration="yes"/>
<xsl:template match="/">
<div>
<xsl:apply-templates/>
</div>
</xsl:template>
<xsl:template match="w:p">
<p>
<xsl:value-of select="."/>
</p>
</xsl:template>
</xsl:stylesheet>
<?xml version="1.0"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
xmlns:ve="http://schemas.openxmlformats.org/markup-compatibility/2006"
xmlns:o="urn:schemas-microsoft-com:office:office"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"
xmlns:v="urn:schemas-microsoft-com:vml"
xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
xmlns:w10="urn:schemas-microsoft-com:office:word"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml">
<xsl:output omit-xml-declaration="yes"/>
<xsl:template match="/">
<div>
<xsl:for-each select="//w:p">
<p>
<xsl:for-each select=".//w:t">
<xsl:text> </xsl:text>
<xsl:value-of select="." />
</xsl:for-each>
</p>
</xsl:for-each>
</div>
</xsl:template>
</xsl:stylesheet>