Changeset 28923 for main/trunk

Timestamp:

2014-03-19T10:57:48+13:00 (10 years ago)

Author:

ak19

Message:

Tidy up and changes resulting from UTF8 encoding issues

File:

• main/trunk/model-sites-dev/von-sparql/collect/nz-natlib-cat/pre-import/RUN_NZ.sh (modified) (2 diffs)

main/trunk/model-sites-dev/von-sparql/collect/nz-natlib-cat/pre-import/RUN_NZ.sh

@@ -2 +2 @@
 
 full_filename=NZDataFull.xml
+full_filename_utf8=NZDataFull-UTF8.xml
 
 if [ ! -f $full_filename ] ; then
   echo "Did not detect uncompressed MARC-XML file '$full_filename'"
-  echo " => Including ISO-8859-1 character encoding XML processing instruction at start"  
+  echo " => Including UTF-8 character encoding XML processing instruction at start"  
   echo "<?xml version=\"1.0\" encoding=\"utf-8\"?>" > $full_filename
   echo "<collection xmlns=\"http://www.loc.gov/MARC21/slim\">" >> $full_filename 
@@ -13 +14 @@
   echo "</collection>" >> $full_filename
   echo " => ... Done"  
+fi
+
+if [ ! -f $full_filename_utf8 ] ; then
+
+  echo "Fixing 'alien' character encodings issues within a UTF-8 file"
+
+  java -cp UTF8_Fix/bin UTF8Fix "$full_filename" "$full_filename_utf8"
 
 fi