/** * The contents of this file are subject to the license and copyright * detailed in the LICENSE and NOTICE files at the root of the source * tree and available online at * * http://www.dspace.org/license/ */ package org.dspace.administer; import static org.dspace.content.service.DSpaceObjectService.MD_COPYRIGHT_TEXT; import static org.dspace.content.service.DSpaceObjectService.MD_INTRODUCTORY_TEXT; import static org.dspace.content.service.DSpaceObjectService.MD_LICENSE; import static org.dspace.content.service.DSpaceObjectService.MD_NAME; import static org.dspace.content.service.DSpaceObjectService.MD_PROVENANCE_DESCRIPTION; import static org.dspace.content.service.DSpaceObjectService.MD_SHORT_DESCRIPTION; import static org.dspace.content.service.DSpaceObjectService.MD_SIDEBAR_TEXT; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.IOException; import java.io.InputStream; import java.io.OutputStream; import java.io.PrintWriter; import java.sql.SQLException; import java.util.HashMap; import java.util.List; import java.util.Map; import javax.xml.parsers.DocumentBuilder; import javax.xml.parsers.ParserConfigurationException; import javax.xml.transform.TransformerException; import javax.xml.xpath.XPath; import javax.xml.xpath.XPathConstants; import javax.xml.xpath.XPathExpressionException; import javax.xml.xpath.XPathFactory; import org.apache.commons.cli.CommandLine; import org.apache.commons.cli.CommandLineParser; import org.apache.commons.cli.DefaultParser; import org.apache.commons.cli.HelpFormatter; import org.apache.commons.cli.Option; import org.apache.commons.cli.Options; import org.apache.commons.cli.ParseException; import org.apache.commons.lang3.StringUtils; import org.dspace.app.util.XMLUtils; import org.dspace.authorize.AuthorizeException; import org.dspace.content.Collection; import org.dspace.content.Community; import org.dspace.content.Item; import org.dspace.content.MetadataFieldName; import org.dspace.content.MetadataSchemaEnum; import org.dspace.content.MetadataValue; import org.dspace.content.factory.ContentServiceFactory; import org.dspace.content.service.CollectionService; import org.dspace.content.service.CommunityService; import org.dspace.core.Context; import org.dspace.eperson.factory.EPersonServiceFactory; import org.dspace.eperson.service.EPersonService; import org.dspace.handle.factory.HandleServiceFactory; import org.dspace.handle.service.HandleService; import org.jdom2.Element; import org.jdom2.output.Format; import org.jdom2.output.XMLOutputter; import org.w3c.dom.Document; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import org.xml.sax.SAXException; /** * This class deals with importing community and collection structures from * an XML file. * * The XML file structure needs to be: *
{@code ** ** * }* *.... *... ** *.... *
* It can be arbitrarily deep, and supports all the metadata elements
* that make up the community and collection metadata. See the system
* documentation for more details.
*
* @author Richard Jones
*/
public class StructBuilder {
/** Name of the root element for the document to be imported. */
static final String INPUT_ROOT = "import_structure";
/*
* Name of the root element for the document produced by importing.
* Community and collection elements are annotated with their identifiers.
*/
static final String RESULT_ROOT = "imported_structure";
/**
* A table to hold metadata for the collection being worked on.
*/
private static final Map {@code StructBuilder -f [XML source] -e [administrator email] -o [output file]}
*
* to import, or
*
* {@code StructBuilder -x -e [administrator email] -o [output file]} to export. The output will contain exactly the same as the source XML
* document, but with the Handle for each imported item added as an attribute.
*
*
* @param argv command line arguments.
* @throws ParserConfigurationException passed through.
* @throws SQLException passed through.
* @throws FileNotFoundException if input or output could not be opened.
* @throws TransformerException if the input document is invalid.
* @throws XPathExpressionException passed through.
*/
public static void main(String[] argv)
throws ParserConfigurationException, SQLException,
IOException, TransformerException, XPathExpressionException {
// Define command line options.
Options options = new Options();
options.addOption("h", "help", false, "Print this help message.");
options.addOption("?", "help");
options.addOption("x", "export", false, "Export the current structure as XML.");
options.addOption("k", "keep-handles", false, "Apply Handles from input document.");
options.addOption(Option.builder("e").longOpt("eperson")
.desc("User who is manipulating the repository's structure.")
.hasArg().argName("eperson").required().build());
options.addOption(Option.builder("f").longOpt("file")
.desc("File of new structure information.")
.hasArg().argName("input").build());
options.addOption(Option.builder("o").longOpt("output")
.desc("File to receive the structure map ('-' for standard out).")
.hasArg().argName("output").required().build());
// Parse the command line.
CommandLineParser parser = new DefaultParser();
CommandLine line = null;
try {
line = parser.parse(options, argv);
} catch (ParseException ex) {
System.err.println(ex.getMessage());
usage(options);
System.exit(1);
}
// If the user asked for help, give it and exit.
if (line.hasOption('h') || line.hasOption('?')) {
giveHelp(options);
System.exit(0);
}
// Otherwise, analyze the command.
// Must be import or export.
if (!(line.hasOption('f') || line.hasOption('x'))) {
giveHelp(options);
System.exit(1);
}
// Open the output stream.
String output = line.getOptionValue('o');
OutputStream outputStream;
if ("-".equals(output)) {
outputStream = System.out;
} else {
outputStream = new FileOutputStream(output);
}
// create a context
Context context = new Context();
// set the context.
String eperson = line.getOptionValue('e');
try {
context.setCurrentUser(ePersonService.findByEmail(context, eperson));
} catch (SQLException ex) {
System.err.format("That user could not be found: %s%n", ex.getMessage());
System.exit(1);
}
// Export? Import?
if (line.hasOption('x')) { // export
exportStructure(context, outputStream);
outputStream.close();
} else { // Must be import
String input = line.getOptionValue('f');
if (null == input) {
usage(options);
System.exit(1);
}
InputStream inputStream;
if ("-".equals(input)) {
inputStream = System.in;
} else {
inputStream = new FileInputStream(input);
}
boolean keepHandles = options.hasOption("k");
importStructure(context, inputStream, outputStream, keepHandles);
inputStream.close();
outputStream.close();
// save changes from import
context.complete();
}
System.exit(0);
}
/**
* Import new Community/Collection structure.
*
* @param context
* @param input XML which describes the new communities and collections.
* @param output input, annotated with the new objects' identifiers.
* @param keepHandles true if Handles should be set from input.
* @throws IOException
* @throws ParserConfigurationException
* @throws SAXException
* @throws TransformerException
* @throws SQLException
*/
static void importStructure(Context context, InputStream input,
OutputStream output, boolean keepHandles)
throws IOException, ParserConfigurationException, SQLException,
TransformerException, XPathExpressionException {
// load the XML
Document document = null;
try {
document = loadXML(input);
} catch (IOException ex) {
System.err.format("The input document could not be read: %s%n", ex.getMessage());
System.exit(1);
} catch (SAXException ex) {
System.err.format("The input document could not be parsed: %s%n", ex.getMessage());
System.exit(1);
}
// run the preliminary validation, to be sure that the the XML document
// is properly structured.
try {
validate(document);
} catch (XPathExpressionException ex) {
System.err.format("The input document is invalid: %s%n", ex.getMessage());
System.exit(1);
}
// Check for 'identifier' attributes -- possibly output by this class.
XPath xPath = XPathFactory.newInstance().newXPath();
NodeList identifierNodes = (NodeList) xPath.compile("//*[@identifier]")
.evaluate(document, XPathConstants.NODESET);
if (identifierNodes.getLength() > 0) {
if (!keepHandles) {
System.err.println("The input document has 'identifier' attributes, which will be ignored.");
} else {
for (int i = 0; i < identifierNodes.getLength() ; i++) {
String identifier = identifierNodes.item(i).getAttributes().item(0).getTextContent();
if (handleService.resolveToURL(context, identifier) != null) {
System.err.printf("The input document contains handle %s,"
+ " which is in use already. Aborting...%n",
identifier);
System.exit(1);
}
}
}
}
// load the mappings into the member variable hashmaps
communityMap.put("name", MD_NAME);
communityMap.put("description", MD_SHORT_DESCRIPTION);
communityMap.put("intro", MD_INTRODUCTORY_TEXT);
communityMap.put("copyright", MD_COPYRIGHT_TEXT);
communityMap.put("sidebar", MD_SIDEBAR_TEXT);
collectionMap.put("name", MD_NAME);
collectionMap.put("description", MD_SHORT_DESCRIPTION);
collectionMap.put("intro", MD_INTRODUCTORY_TEXT);
collectionMap.put("copyright", MD_COPYRIGHT_TEXT);
collectionMap.put("sidebar", MD_SIDEBAR_TEXT);
collectionMap.put("license", MD_LICENSE);
collectionMap.put("provenance", MD_PROVENANCE_DESCRIPTION);
Element[] elements = new Element[]{};
try {
// get the top level community list
NodeList first = (NodeList) xPath.compile("/import_structure/community")
.evaluate(document, XPathConstants.NODESET);
// run the import starting with the top level communities
elements = handleCommunities(context, first, null, keepHandles);
} catch (TransformerException ex) {
System.err.format("Input content not understood: %s%n", ex.getMessage());
System.exit(1);
} catch (AuthorizeException ex) {
System.err.format("Not authorized: %s%n", ex.getMessage());
System.exit(1);
}
// generate the output
final Element root = new Element(RESULT_ROOT);
for (Element element : elements) {
root.addContent(element);
}
// finally write the string into the output file.
final org.jdom2.Document xmlOutput = new org.jdom2.Document(root);
try {
new XMLOutputter().output(xmlOutput, output);
} catch (IOException e) {
System.out.printf("Unable to write to output file %s: %s%n",
output, e.getMessage());
System.exit(1);
}
}
/**
* Add a single community, and its children, to the Document.
*
* @param community
* @return a fragment representing this Community.
*/
private static Element exportACommunity(Community community) {
// Export this Community.
Element element = new Element("community");
element.setAttribute("identifier", community.getHandle());
element.addContent(new Element("name").setText(community.getName()));
element.addContent(new Element("description")
.setText(communityService.getMetadataFirstValue(community,
MetadataSchemaEnum.DC.getName(), "description", "abstract", Item.ANY)));
element.addContent(new Element("intro")
.setText(communityService.getMetadataFirstValue(community,
MetadataSchemaEnum.DC.getName(), "description", null, Item.ANY)));
element.addContent(new Element("copyright")
.setText(communityService.getMetadataFirstValue(community,
MetadataSchemaEnum.DC.getName(), "rights", null, Item.ANY)));
element.addContent(new Element("sidebar")
.setText(communityService.getMetadataFirstValue(community,
MetadataSchemaEnum.DC.getName(), "description", "tableofcontents", Item.ANY)));
// Export this Community's Community children.
for (Community subCommunity : community.getSubcommunities()) {
element.addContent(exportACommunity(subCommunity));
}
// Export this Community's Collection children.
for (Collection collection : community.getCollections()) {
element.addContent(exportACollection(collection));
}
return element;
}
/**
* Add a single Collection to the Document.
*
* @param collection
* @return a fragment representing this Collection.
*/
private static Element exportACollection(Collection collection) {
// Export this Collection.
Element element = new Element("collection");
element.setAttribute("identifier", collection.getHandle());
element.addContent(new Element("name").setText(collection.getName()));
element.addContent(new Element("description")
.setText(collectionService.getMetadataFirstValue(collection,
MetadataSchemaEnum.DC.getName(), "description", "abstract", Item.ANY)));
element.addContent(new Element("intro")
.setText(collectionService.getMetadataFirstValue(collection,
MetadataSchemaEnum.DC.getName(), "description", null, Item.ANY)));
element.addContent(new Element("copyright")
.setText(collectionService.getMetadataFirstValue(collection,
MetadataSchemaEnum.DC.getName(), "rights", null, Item.ANY)));
element.addContent(new Element("sidebar")
.setText(collectionService.getMetadataFirstValue(collection,
MetadataSchemaEnum.DC.getName(), "description", "tableofcontents", Item.ANY)));
element.addContent(new Element("license")
.setText(collectionService.getMetadataFirstValue(collection,
MetadataSchemaEnum.DC.getName(), "rights", "license", Item.ANY)));
// Provenance is special: multivalued
for (MetadataValue value : collectionService.getMetadata(collection,
MetadataSchemaEnum.DC.getName(), "provenance", null, Item.ANY)) {
element.addContent(new Element("provenance")
.setText(value.getValue()));
}
return element;
}
/**
* Write out the existing Community/Collection structure.
*/
static void exportStructure(Context context, OutputStream output) {
// Build a document from the Community/Collection hierarchy.
Element rootElement = new Element(INPUT_ROOT); // To be read by importStructure, perhaps
List