converted to xslt

src/filters/rclsoff

@@ -18,10 +18,6 @@ progname="rclsoff"
 filetype=openoffice
 
 
-
-
-
-
 #RECFILTCOMMONCODE
 ##############################################################################
 # !! Leave the previous line unmodified!! Code imported from the
@@ -88,7 +84,7 @@ umask 77
 # !! Leave the following line unmodified !
 #ENDRECFILTCOMMONCODE
 
-checkcmds awk iconv unzip
+checkcmds xsltproc
 
 # We need a temporary directory
 if test z"$RECOLL_TMPDIR" != z; then
@@ -116,92 +112,98 @@ trap cleanup EXIT HUP QUIT INT TERM
 unzip -q -d $tmpdir/rclsofftmp "$infile"
 cd $tmpdir/rclsofftmp
 
-# Note: there can be newlines inside the description field, we don't want
-# them...
-descsedprog='/<dc:description>/,/<\/dc:description>/{
-s!.*<dc:description>!!
-s!</dc:description>.*!!
-H
-${
-g
-s/\n/ /g
-p
-}
-}
-'
-description=`sed -n -e "$descsedprog" meta.xml`
-#echo description "$description"
+echo '<html><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">'
 
-# Takes tag name as parameter and creates sed program to extract single
-# line meta tags values.
-setmetasedprog() {
-metasedprog="s/\"/'/g"'
-/.*<'"$1"'>\([^<]*\).*/s//\1/p
-'
-}
+xsltproc - meta.xml <<EOF
+<?xml version="1.0"?>
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" 
+  xmlns:xlink="http://www.w3.org/1999/xlink" 
+  xmlns:dc="http://purl.org/dc/elements/1.1/" 
+  xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" 
+  xmlns:ooo="http://openoffice.org/2004/office"
+  exclude-result-prefixes="office xlink meta ooo dc"
+  >
 
-setmetasedprog dc:subject
-subject=`sed -n -e "$metasedprog" meta.xml`
-#echo subject: $subject
+<xsl:output method="html" encoding="UTF-8"/>
 
-setmetasedprog dc:title
-title=`sed -n -e "$metasedprog" meta.xml`
-#echo title: $title
+<xsl:template match="/office:document-meta">
+  <xsl:apply-templates select="office:meta/dc:description"/>
+  <xsl:apply-templates select="office:meta/dc:subject"/>
+  <xsl:apply-templates select="office:meta/dc:title"/>
+  <xsl:apply-templates select="office:meta/meta:keyword"/>
+  <xsl:apply-templates select="office:meta/dc:creator"/>
+</xsl:template>
 
-setmetasedprog meta:keyword
-keywords=`sed -n -e "$metasedprog" meta.xml`
-#echo keywords: $keywords
+<xsl:template match="dc:title">
+<title> <xsl:value-of select="."/> </title><xsl:text>
+</xsl:text>
+</xsl:template>
 
-setmetasedprog dc:creator
-creator=`sed -n -e "$metasedprog" meta.xml`
-#echo creator: $creator
+<xsl:template match="dc:description">
+  <meta>
+  <xsl:attribute name="name">abstract</xsl:attribute>
+  <xsl:attribute name="content">
+     <xsl:value-of select="."/>
+  </xsl:attribute>
+  </meta><xsl:text>
+</xsl:text>
+</xsl:template>
 
-# Note: next expr inserts a newline at each end of paragraph (for preview)
-content="`sed -e 's!</text:p>!\\
-!g' -e 's/<[^>]*>/ /g' < content.xml`"
+<xsl:template match="dc:subject">
+  <meta>
+  <xsl:attribute name="name">keywords</xsl:attribute>
+  <xsl:attribute name="content">
+     <xsl:value-of select="."/>
+  </xsl:attribute>
+  </meta><xsl:text>
+</xsl:text>
+</xsl:template>
 
-#echo content "$content"
+<xsl:template match="dc:creator">
+  <meta>
+  <xsl:attribute name="name">author</xsl:attribute>
+  <xsl:attribute name="content">
+     <xsl:value-of select="."/>
+  </xsl:attribute>
+  </meta><xsl:text>
+</xsl:text>
+</xsl:template>
 
-# output the result
-echo '<html><head>'
-echo '<title>' "$title" '</title>'
-echo '<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">'
-echo '<meta name="description" content="' "$description $subject" '">'
-echo '<meta name="keywords" content="' "$keywords" '">'
-echo '<meta name="author" content="' "$creator" '">'
-echo '</head><body><p>'
+<xsl:template match="meta:keyword">
+  <meta>
+  <xsl:attribute name="name">keywords</xsl:attribute>
+  <xsl:attribute name="content">
+     <xsl:value-of select="."/>
+  </xsl:attribute>
+  </meta><xsl:text>
+</xsl:text>
+</xsl:template>
 
-# The strange 'BEGIN' setup is to prevent 'file' from thinking this file
-# is an awk program
-echo "$content" | sed -e "s/&apos;/'/g" -e 's/&quot;/"/g' |\
-awk 'BEGIN'\
-' {
-  cont = ""
-}
-{
-    $0 = cont $0
-    cont = ""
+</xsl:stylesheet>
+EOF
 
-    if ($0 ~ /[­-]$/) {
-      # Note : soft-hyphen is iso8859 0xad
-      # Break at last whitespace
-      match($0, "[ \t][^ \t]+$")
-      line = substr($0, 0, RSTART)
-      cont = substr($0, RSTART, RLENGTH-1)
-      $0 = line
-    }
+echo '</head><body>'
 
-    if($0 == "\f") {
-        print "</p>\n<hr>\n<p>"
-        next
-    } 
+xsltproc - content.xml <<EOF
+<?xml version="1.0"?>
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0"
+  exclude-result-prefixes="text"
+>
 
-    print $0 "<br>"
-}
-END {
-    printf("</p></body></html>\n");
-}' | iconv -f UTF-8 -t UTF-8 -c -s 
+<xsl:output method="html" encoding="UTF-8"/>
 
+<xsl:template match="text:p">
+  <p><xsl:value-of select="."/></p><xsl:text>
+  </xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>
+EOF
+echo '</body></html>'
 cd /
-# exit normally
 exit 0