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

sort of works

Browse Source
This commit is contained in:
dockes 2008-09-01 17:31:47 +00:00
parent abaa134dd2
commit fb27dfe822
1 changed files with 24 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
src/filters/rclopxml
View File

@ -1,5 +1,5 @@
#!/bin/sh #!/bin/sh
# @(#$Id: rclopxml,v 1.1 2008-09-01 17:21:18 dockes Exp $ (C) 2004 J.F.Dockes # @(#$Id: rclopxml,v 1.2 2008-09-01 17:31:47 dockes Exp $ (C) 2004 J.F.Dockes
#================================================================ #================================================================
# rcldocx # rcldocx
# Extract text from an openxml msword file (will be extended for spreadsheets) # Extract text from an openxml msword file (will be extended for spreadsheets)
@ -173,9 +173,9 @@ echo '</head>
filename='' filename=''
if test -f word/document.xml ; then if test -f word/document.xml ; then
filenames=word/document.xml filenames=word/document.xml
tagmatch="w:p" tagmatch="w:p"
xmlns_decls=' xmlns_decls='
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
xmlns:ve="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:ve="http://schemas.openxmlformats.org/markup-compatibility/2006"
xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:o="urn:schemas-microsoft-com:office:office"
@ -185,14 +185,17 @@ if test -f word/document.xml ; then
xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w10="urn:schemas-microsoft-com:office:word"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml"' xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml"
'
elif test -f xl/sharedStrings.xml ; then elif test -f xl/sharedStrings.xml ; then
filenames=xl/sharedStrings.xml filenames=xl/sharedStrings.xml
tagmatch='x:t' tagmatch='x:t'
xmlns_decls=' xmlns_decls='
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
xmlns:x="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:x="http://schemas.openxmlformats.org/spreadsheetml/2006/main"
' '
elif test -f ppt/slides/slide1.xml ; then elif test -f ppt/slides/slide1.xml ; then
filenames=`echo ppt/slides/slide*.xml` filenames=`echo ppt/slides/slide*.xml`
tagmatch='a:t' tagmatch='a:t'
@ -201,10 +204,19 @@ elif test -f ppt/slides/slide1.xml ; then
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main" xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
'
# I want to suppress text output for all except a:t, don't know how to do it
# help ! At least get rid of these:
moretemplates='
<xsl:template match="p:attrName">
</xsl:template>
' '
else else
exit 1 # ??
exit 1
fi fi
for filename in $filenames;do for filename in $filenames;do
xsltproc - $filename <<EOF xsltproc - $filename <<EOF
<?xml version="1.0"?> <?xml version="1.0"?>
@ -224,8 +236,7 @@ xsltproc - $filename <<EOF
</p> </p>
</xsl:template> </xsl:template>
<!-- <xsl:template match="*"> $moretemplates
</xsl:template> -->
</xsl:stylesheet> </xsl:stylesheet>
EOF EOF