Gaslight & Steam Dev Blog

#!perl
use File::Find;
use File::Copy;
use File::Path;
use HTML::Entities; 
 
# Configuration:
$origContent_path = "/MyConvertDirectory/MyExportedContent";
$origConverted_path = "/MyConvertDirectory/MyConvertedXMLContent";
$origConvertedDCR_path = "/MyConvertDirectory/MyConvertedDCRContent";
$saxon_path = "C:\\Saxon\\saxon9.jar";
$xsl_path = "/MyConvertDirectory/convertXML.xsl";
$xsl2dcr_path = "/MyConvertDirectory/convertDCR.xsl";
 
my $dir = $origContent_path;
print "Starting at ".$dir."\n\n";
print "Processing...";
mkpath( $origConvertedDCR_path ) if not -e $origConvertedDCR_path;
use Cwd;
find(\&convertItems, $dir);
find(\&cleanupFilesDirs, $origConverted_path);
find(\&stripDCR, $origConvertedDCR_path);
print "\n";
print "Done!\n";
 
#
sub convertItems {
	return unless -d;
	my $sourcedir = $File::Find::name;
	my $targetdir = $File::Find::name;
	$targetdir =~ s/Home/SiteContent/o;
	$targetdir =~ s/\s//g;
	$targetdir =~ s/\b([A-Z]{1})([A-Za-z]+)\b/\l$1$2/g;
	print "Transform ".$sourcedir." to ".$targetdir."\n";
	print ".";
	mkpath( $targetdir ) if not -e $targetdir;
	system "java -jar $saxon_path -o \"$targetdir\" -s \"$sourcedir\" -xsl \"$xsl_path\"";
	system "java -jar $saxon_path -o \"$origConvertedDCR_path\" -s \"$sourcedir\" -xsl \"$xsl2dcr_path\"";
}
# Decode entities in the content
# Then rename each file to Unix format, removing spaces, and making the name all lower case.
# Since I'm exceptionally lazy, I just unlink the item if it's size is 39 (meaning Saxon parsed the item, but the XSL transform returned just an XML header as the contents of the file)
# Except for the decoding and not stripping the extension, this method is the same as the method below
sub cleanupFilesDirs {
	-d and return; #skip item if it's a directory
	if(-s $_ < 39) {unlink $_ and return;}
	my $filename = $_;
	open(XMLCONTENT, "<$filename") or return;
	open(XMLOUT, ">temp.xml") or return;
	while() {
		chomp;
		my $content = $_;
		$content = decode_entities($content)."\n";
		print XMLOUT $content;
	}
	close XMLCONTENT;
	close XMLOUT;
	unlink $filename;
	$filename =~ s/([A-Za-z])\s?-\s/$1-/g;
	$filename =~ s/\s//g;
	$filename =~ s/^([A-Z])/\l$1/;
#	print  "Renaming content item temp.xml to ".$filename."\n";
	move ("temp.xml","$filename");
}
# Rename each file to Unix format, removing spaces, making the name all lower case and stripping off the extension.  Since DCR files reside in a single directory, the path is flattened.
# Since I'm exceptionally lazy, I just unlink the item if it's size is 39 (meaning Saxon parsed the item, but the XSL transform returned just an XML header as the contents of the file)
sub stripDCR {
	-d and return; #skip item if it's a directory
	if(-s $_ < 39) {unlink $_;}
	my $oldname = $_;
	my $newname = $oldname;
	chomp($newname);
	$newname =~ s/\s//g;
	$newname =~ s/^([A-Z])/\l$1/;
	$newname =~ s/_?\.xml$//;
	$newname =~ s/([A-Za-z])\s?-\s/$1 - /g;
#	print  "Renaming DCR item ".$oldname." to ".$newname."\n";
	if ($oldname eq $newname) { return;}
	rename($oldname, $newname);
}
exit;

<xsl:stylesheet version="2.0"
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs = "http://www.w3.org/2001/XMLSchema"
    xmlns:date="http://exslt.org/dates-and-times"
    exclude-result-prefixes="xs date">
<xsl:output omit-xml-declaration="no" method="xml" indent="no" doctype-system="dcr4.5.dtd" />
<xsl:template match="/">
  <!-- matched root -->
   <xsl:apply-templates select="docTopNode"/>
 </xsl:template>
 
 <xsl:template match="docTopNode">
  <xsl:variable name="docTitle" select="title" />
  <record name="{$docTitle}" type="content"><item name="newsitem"><value>
   <item name="title"><value><xsl:value-of select="title"/></value></item>
   <item name="mainContent"><value><xsl:value-of select="docContent/docBodyContent"/></value></item>
   <item name="sequence"><value>1</value></item>
  </value></item></record>
 </xsl:template>
 
 <xsl:template name="FormatDate">
  <xsl:param name="DateTime" />
  <xsl:value-of select="concat(substring($DateTime,6,2),'/',substring($DateTime,9,2),'/',substring($DateTime,1,4))"/>
 </xsl:template>
 <xsl:template name="FormatTime">
  <xsl:param name="thisTime" />
  <xsl:value-of select="substring($thisTime,12,8)"/>
 </xsl:template>
 
 <xsl:function name="date:parse-date" as="xs:string">
  <xsl:param name="parsable-date" />
  <xsl:choose>
   <xsl:when test="$parsable-date = '' ">2001-01-01</xsl:when>
   <xsl:otherwise>
    <xsl:value-of select="xs:string(xs:dateTime(xs:dateTime('1970-01-01T00:00:00') + $parsable-date *
 xs:dayTimeDuration('PT0.001S')))" />
   </xsl:otherwise>
  </xsl:choose>
 </xsl:function>
</xsl:stylesheet>

<?xml version="1.0"?>
<docTopNode>
	<title>Document Title</title>
	<docContent>
		<docBodyContent>
			&lt;p&gt;This might be some escapedHTML content with formatting&lt;/p&gt;
		</docBodyContent>
		<unusedContentNode>
			This should be ignored by the XSL.
		</unusedContentNode>
		<postingDate>1148281200000</postingDate>
	</docContent>
</docTopNode>