Basic setup

.gitignore

@@ -0,0 +1,55 @@
+# Created by .ignore support plugin (hsz.mobi)
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion
+
+*.iml
+
+## Directory-based project format:
+.idea/
+# if you remove the above rule, at least ignore the following:
+
+# User-specific stuff:
+# .idea/workspace.xml
+# .idea/tasks.xml
+# .idea/dictionaries
+
+# Sensitive or high-churn files:
+# .idea/dataSources.ids
+# .idea/dataSources.xml
+# .idea/sqlDataSources.xml
+# .idea/dynamic.xml
+# .idea/uiDesigner.xml
+
+# Gradle:
+# .idea/gradle.xml
+# .idea/libraries
+
+# Mongo Explorer plugin:
+# .idea/mongoSettings.xml
+
+## File-based project format:
+*.ipr
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+/out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+
+# Repository specifics
+*.jar
+*.lic
+*.xml
+
+

transform.han2sbmarc.sh

@@ -0,0 +1,23 @@
+# Script to process files with HAN data (HAN-Marc) with an xslt-transformation to get MARC21 records
+
+basedir=$1
+
+inputdir=$1/raw.hanmarc
+outputdir=$1/out.swissbib-MARC
+xslt=$basedir/xslt/
+output=HAN.marc21.nr
+cp=$1/libs/saxon9.jar
+institutioncode=$2
+
+nr=1
+
+echo "start HAN-Marc -> Marc21 transformation"
+
+for datei in $inputdir/*.xml
+do
+
+	echo "file: "$datei
+	java -Xms2024m -Xmx2024m  -cp $cp  net.sf.saxon.Transform -s:$datei -xsl:$xslt -o:$outputdir/$output$nr.xml institutioncode=$institutioncode
+	nr=$(($nr+1))
+
+done

transform.into.1.line.pl

@@ -0,0 +1,61 @@
+#!/usr/bin/perl
+
+
+use strict;
+
+sub ltrim($);
+
+my $first_line = '<collection>';
+my $start_record = '<record';
+my $end_record = '</record>';
+my $leerzeile = '^$';
+my $last_line = '</collection>';
+my $xml_declaration = '<\?xml';
+
+
+
+my $line_to_write = "";
+my $in_declaration_section = 0;
+my $in_record_section = 0;
+
+
+
+while (<>) {
+
+   if (/$leerzeile/) {
+   	  next;
+   }elsif (/($xml_declaration|$first_line|$last_line)/) {
+      writeline($_);
+      next;
+   } elsif (/$start_record/) {
+   	  chomp;
+   	  $line_to_write =  ltrim($_);
+   	  $in_record_section = 1;	
+      #$line_to_write .=  $_;
+   } elsif (/$end_record/) {
+   	  chomp;
+   	  $line_to_write .=  ltrim($_);
+   	  $line_to_write .=  "\n";
+   	  $in_record_section = 0;
+   	  writeline($line_to_write);	
+      next;
+   	}	 else {
+   	  chomp;
+      $line_to_write .= ltrim($_);
+
+   	}   
+}
+
+
+sub writeline {
+
+   print $_[0]; 
+}
+
+sub ltrim($)
+{
+	my $string = shift;
+	$string =~ s/^\s+//;
+	return $string;
+}
+

transform.into.1.line.sh

@@ -0,0 +1,21 @@
+#Script purpose: call perl script to flatten the lines
+
+basedir=$1
+
+inputdir=$basedir/out.swissbib-MARC
+outputdir=$basedir/out.swissbib-MARC-1line
+
+plfile=$basedir/transform.into.1.line.pl
+
+echo "start perl transformation to flatten records into one single line"
+
+for datei in $inputdir/*.xml
+do
+
+	filename=`basename ${datei} .xml`
+
+	#suffix format.xml for the file name is necessary for the next steps
+	echo  "transformation of "$datei "into "$filename.format.xml 
+	perl $plfile $datei  > $outputdir/$filename.format.xml
+
+done

workflow.HAN.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Script that controls the main workflow
+
+basedir=$PWD
+
+$basedir/transform.han2sbmarc.sh $basedir HAN
+#$basedir/remove.marc.namespaces.sh $basedir
+$basedir/transform.into.1.line.sh $basedir

xslt/info.md

@@ -0,0 +1,2 @@
+# Information on xslt-scripts
+