source: other-projects/gs3-webservices-java-client/trunk/src/GS3Fedora/org/greenstone/fedora/services/FedoraGS3DL.java@ 22300

/**
 *#########################################################################
 * FedoraGS3DL.java - works with the demo-client for Greenstone 3, of the 
 * Greenstone digital library suite from the New Zealand Digital Library 
 * Project at the  * University of Waikato, New Zealand.
 * <BR><BR>
 * Copyright (C) 2008 New Zealand Digital Library Project
 * <BR><BR>
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 * <BR><BR>
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *########################################################################
 */

package org.greenstone.fedora.services;


import org.greenstone.fedora.services.FedoraGS3Exception.FedoraVersionNotSupportedException;
import org.w3c.dom.Element;
import org.xml.sax.SAXException;

import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.rmi.RemoteException;

import javax.xml.transform.TransformerException;
//import javax.xml.transform.TransformerConfigurationException;

/** 
 * Defines the methods that must be provided to retrieve the datastreams 
 * specific to Greenstone documents stored in a Fedora repository. 
 * @author ak19 
*/
public interface FedoraGS3DL {
    /* CONSTANTS (FOLLOWED BY METHOD DECLARATIONS) */
    
    /** Instead of message router, we indicate that request messages 
     * sent here come from FedoraGS3 */
    public static final String FEDORA_GS3 = "FedoraGS3";
    
    // Some constant string literals we'll be dealing with
    
    /** "greenstone" is the FEDORA PID prefix we'll be working with
     * @see <a href="http://dltj.org/2006/12/fedora-batch-processing/">Fedora batch processing</a>
    */
    public static final String GREENSTONE = "greenstone";
    public static final String GREENSTONE_ = GREENSTONE+":";
    public static final String COLLECTION = "collection";
    public static final String _COLLECTION = "-"+COLLECTION;
    
    public static final String WILDCARD = "*";
    public static final String HYPHEN = "-";
    public static final String COLON = ":";
    public static final String PERIOD = ".";
    
    // public static final String UTF16 = "UTF-16"; // not used
    public static final String UTF8 = "UTF8";
    
    // attribute names
    public static final String TITLE = "Title";
    public static final String ID = "id";
    public static final String NAME = "name";
    public static final String COLLECTIONNAME = "collectionname";
    public static final String QUALIFIER = "qualifier";
    public static final String ENGLISH = "en";
    
    // tag names
    public static final String METADATA = "metadata";
    public static final String SECTION_ELEMENT = "Section";
    
    /** EX marks the XML metadata file that contains Greenstone extracted 
     * metadata */
    public static final String EX = "EX";
    /** Fedora's Dublin Core metadata */
    public static final String DC = "DC";
    /** DLS metadata of Greenstone documents - this metadata set is optionally 
     * provided for top level documents. Not all Greenstone top-level documents 
     * in the Fedora repository may have associated DLS metadata, however.*/
    public static final String DLS = "DLS"; 
    /** Table of contents for a Greenstone-Fedora document which outlines the 
     * structure of the document. */
    public static final String TOC = "TOC";
    /** The SECTION prefix in the name of a section's datastream; 
     * eg. SECTION1.2.2 */
    public static final String SECTION = "SECTION";
    
    
    /* METHOD DEFINITIONS */
    /** @return the default language used to query for titles (and anything else
     * where there are multiple language options). Upon initialisation, this 
     * defaults to English. */
    public String getLanguage();

    /** Sets the the default language used to query for titles (and anything else
     * where there are multiple language options). If the default language for any
     * query is not available, then English ("en") is used. If that's not available
     * then the first other available language is used.
     * @param lang - the two-letter language code to set the default language to. */
    public void setLanguage(String lang);
    
    /** The default maximum number of search results returned for a search. Upon
     * initialisation, this defaults to Java's Integer.MAX_VALUE. */
    public int getMaxResults();
    
    /** Set the default maximum number of search results returned for a search. 
     * @param maxresults - the new default maximum number of search results to 
     * be returned. */
    public void setMaxResults(int maxresults);
    
    /** @return fedora's baseURL */
    public String getBaseURL();
    
    /** @return the portAddressURL of the Fedora APIA web service
     * (should be the endpoint location in the APIA's WSDL file). 
     * Else set this in the .properties file to something else. */
    public String getPortAddressURL();
    
    /** @return the baseURL for gsdlAssocFiles */
    public String getAssocFileBaseURL();
    
    /* GET COLLECTIONS, DOCUMENTS, SECTIONS, AND TITLES */
    
    /** Gets all greenstone collections. Searches for greenstone:*-collection.
     * @return an array of Strings containing the pids of all collections 
     * matching the format greenstone:*-collection. */
    public String[] getCollections() throws RemoteException;
    
    /** @return the &lt;name&gt;s (in greenstone:&lt;name&gt;-collection) for the collections
     * indicated by collPIDs. 
     * @param collPIDs - an array of Strings denoting the pids for greenstone
     * collections stored in the fedora repositoryl. These should be of the
     * format "greenstone:&lt;collectionName&gt;-collection". */
    public String[] getCollectionNames(String[] collPIDs);

    /** @return "greenstone:&lt;name&gt;-collection" for all &lt;name&gt;s in the 
     * parameter collNames.
     * @param collNames - a list of names of greenstone collections
     * stored in the fedora repository. */
    public String[] getCollectionPIDs(String[] collNames);

    /** @return greenstone:&lt;name&gt;-collection for the &lt;name&gt; denoted by  
     * parameter collName.
     * @param collName - the name of a greenstone collection stored 
     * stored in the fedora repository. */
    public String getCollectionPID(String collName);

    /** 
     * Gets the title of the collection denoted by the given collection's pid by
     * retrieving the title metadata for it from the collection's EX datastream. 
     * @return the title (in the default language, else English, else the
     * first title found) for the particular collection denoted by its PID. 
     * @param collPID is the pid of a greenstone collection in the fedora 
     * repository. */
    public String getCollectionTitle(String collPID) 
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;

    /** @return the collection titles for all the collections indicated by
     * collPIDs. 
     * @param collPIDs - a list of pids identifying greenstone collections 
     * stored in the fedora repository. */
    public String[] getCollectionTitles(String[] collPIDs) 
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;

    /** @return the title metadata for the given doc objects of a collection. 
     * These titles are returned in the same order as the given docIDs. 
     * @param docPIDs - a list of pids identifying documents stored in the 
     * fedora repository. */
    public String[] getDocTitles(String[] docPIDs)
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;
    
    /** Gets the title metadata for a particular doc object in a collection
     * denoted by docPID. The docPID already contains the collection name. 
     * @return the title for the fedora document item denoted by docPID
     * @param docPID is the pid of the document in the fedora repository 
     * (docPID is of the form greenstone:&lt;colName&gt;-&lt;doc-identifier&gt; */
    public String getDocTitle(String docPID) 
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;

    /** @return the title metadata for the given document sections. 
     * These titles are returned in the same order as the given docPIDs
     * and associated sectionIDs. 
     * @param docPIDs - a list of pids identifying documents stored in the 
     * fedora repository. 
     * @param sectionIDs - a list of sectionIDs identifying individual sections
     * of documents stored in the fedora repository whose titles are requested. */
    public String[] getSectionTitles(String[] docPIDs, String[] sectionIDs) 
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;
    
    /** @return the title metadata for the given document section. 
     * (The docPID already contain the collection name anyway.) 
     * @param docPID - a pid identifying a document in the fedora repository. 
     * @param sectionID - the sectionID of the section of the 
     * document whose title is requested. */
    public String getSectionTitle(String docPID, String sectionID) 
        throws UnsupportedEncodingException, RemoteException, 
            SAXException, IOException;
    
    /** @return a list of the fedora pids of all (document) objects in the 
     * given greenstone collection stored in fedora's repository. All 
     * pids that do not map to a collection are assumed to be documents.
     * @param colPID is the pid of the greenstone collection stored in
     * the fedora repository. */
    public String[] getCollectionDocs(String colPID) throws RemoteException;

    /** Given the pid of a document fedora data object, this method will return 
     * all itemIDs that are part of that data object and are Sections. 
     * @return an array of itemIDs of the Sections of the document, 
     * indicated by docPID, in ascending order. These are of the form: "SECTION1.*"
     * @param docPID is a fedora pid identifying a greenstone document object. */
    public String[] getSectionNames(String docPID) throws RemoteException;

    /** Given the pid of a document fedora data object, this method will return all
     * itemIDs that are part of that data object and are Sections, but just the 
     * Section numbers are returned. 
     * @return an array of itemIDs of the Section numbers of the document 
     * indicated by docPID, in ascending order. Return values are of form: "1.*".
     * @param docPID is a fedora pid identifying a greenstone document object. */
    public String[] getSectionNumbers(String docPID) throws RemoteException;

    /** @return the titles for the document sections denoted by the parameters.
     * @param docPID is a fedora pid identifying a greenstone document object.
     * @param sectionIDs is a list of identifiers identifying sections in the
     * document denoted by docPID, whose titles need to be returned. Each 
     * sectionID may sectionID may be either a section name (e.g. SECTION1.5.1) 
     * or a section number (eg. 1.5.1). */
    public String[] getTitles(String docPID, String[] sectionIDs) 
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;

    /** @return the title for the document section denoted by the parameters.
     * @param docPID is a fedora pid identifying a greenstone document object.
     * @param sectionID identifies the particular section in the
     * document denoted by docPID, whose title needs to be returned. The 
     * sectionID may sectionID may be either a section name (e.g. SECTION1.5.1) 
     * or a section number (eg. 1.5.1). */
    public String getTitle(String docPID, String sectionID)
        throws RemoteException, UnsupportedEncodingException, 
            SAXException, IOException;

    /** @return the &lt;docName&gt; in the parameter docPID (which is of the form: 
     *  greenstone:&lt;colname&gt;-&lt;docName&gt;) 
     *  @param docPID is the pid of a greenstone document in the fedora 
     *  repository. */
    public String getDocName(String docPID);
    
    /** @return the &lt;name&gt; in the parameter collPID 
     * (greenstone:&lt;name&gt;-collection) 
     * @param collPID is the pid of a greenstone collection in the fedora 
     * repository. 
    */
    public String getCollectionName(String collPID);
    
    /* GETTING A DOCUMENT OR SECTION'S DATA STREAMS */
    
    /* All "greenstone:*" objects in fedora (be they collections or documents) 
     * have TOC, EX and DC datastreams. The following methods return the content
     * (XML) of these datastreams as is. */
    /** All objects (incl "greenstone:*" objects) in fedora - be they collections, 
     * top-level documents or document sections) have an EX datastream. This method
     * returns the content (XML) of the DC datastream as it is stored in fedora's 
     * repository. 
     * @return a String version of the XML in the DC datastream for the fedora object
     * denoted by pid.
     * @param pid - the fedora persistent identifier for an item in the fedora
     * repository. */
    public String getDC(String pid) throws RemoteException, UnsupportedEncodingException;

    /** All "greenstone:*" objects in fedora (be they collections, top-level 
     * documents or document sections) have an EX datastream. This method 
     * returns the content (XML) of the EX datastream as is.
     * @return a String version of the XML in the DC datastream for the fedora
     * object denoted by pid.
     * @param pid - the fedora persistent identifier for an item in the fedora
     * repository. */
    public String getEX(String pid) throws RemoteException, UnsupportedEncodingException;

    /** 
     * Some "greenstone:*" top-level documents in the fedora repository (but not 
     * greenstone collections or document sections) have a DLS metadata datastream. 
     * This method returns the content (XML) of the DLS datastream as is.
     * @return a String version of the XML in the DLS datastream for the fedora
     * object denoted by pid.
     * @param pid - the fedora persistent identifier for an item in the fedora
     * repository.
     * */
    public String getDLS(String pid) throws RemoteException, UnsupportedEncodingException;
    
    /** All "greenstone:*" objects in fedora (be they collections or documents) 
     * have a TOC datastream. This method returns the content (XML) of the TOC  
     * datastream as is. (Calls default fedora-system 3 dissemination &lt;pid&gt;/TOC.)
     * @return a String version of the XML in the DC datastream for the fedora
     * object denoted by pid.
     * @param pid - the fedora persistent identifier for an item in the fedora
     * repository. 
    */
    public String getTOC(String pid) throws RemoteException, UnsupportedEncodingException;
    
    /** @return the section's XML (as a String) as it is stored in fedora. 
     * Works out if sectionID is a sectionName or sectionNumber.
     * @param docPID is a fedora pid identifying a greenstone document object.
     * @param sectionID identifies the particular section in the
     * document denoted by docPID, may be a section name or number. */
    public String getSection(String docPID, String sectionID)
        throws RemoteException, UnsupportedEncodingException;
    
    /** @return the required section's DC metadata XML datastream.
     * @param docPID is a fedora pid identifying a greenstone document object.
     * @param sectionID identifies the particular section in the
     * document denoted by docPID, may be a section name or number. */
    public String getSectionDCMetadata(String docPID, String sectionID)
        throws RemoteException, UnsupportedEncodingException;

    /** @return the required section's EX metadata XML datastream.
     * @param docPID is a fedora pid identifying a greenstone document object.
     * @param sectionID identifies the particular section in the
     * document denoted by docPID, may be a section name or number. */
    public String getSectionEXMetadata(String docPID, String sectionID)
        throws RemoteException, UnsupportedEncodingException;
    
    /* METHODS FOR GETTING THE STRUCTURE OF DOCUMENTS */

    /** @return the part of the TOC XML file (which outlines doc structure)  
     * relating to the given section. This includes the section denoted by
     * sectionID as well as all descendent subsections thereof. 
     * @param docPID - a fedora pid identifying a greenstone document object.
     * @param sectionID - identifies the particular section in the
     * document denoted by docPID, may be a section name or number. 
     * @param structure can contain any combination of: ancestors, parent, 
     * siblings, children, descendants, entire, specifying the portion of 
     * the structure to retrieve.
     * @param info can contain any combination of: siblingPosition, numSiblings, 
     * numChildren, requesting additional information about the structure. */
    public Element getSectionStructureXML(String docPID, String sectionID, String structure, String info)
        throws RemoteException, UnsupportedEncodingException, SAXException, IOException;

    /* BROWSING */
    
    /** Allows browsing document titles of a greenstone collection stored in 
     * the fedora repository by letter. 
     * @return the browse results for documents that start with any letter from 
     * A to Z. Returns the document pids whose titles start with the given letter.
     * @param letter is the starting letter to browse by. */
    public String[] browseTitlesByLetter(String collName, String letter) 
        throws RemoteException, FedoraVersionNotSupportedException;

    /** Allows querying document titles of a greenstone collection stored in 
     * the fedora repository for a term that may occur anywhere in their titles. 
     * @return the document pids whose titles contain the parameter term.
     * @param titleContents is the word or phrase to search the collection's 
     * document titles for. 
     * @param startsWith - if true, searches for titles that start with 
     * titleContents. Else it searches for titles that contain titleContents. */
    public String[] searchDocumentTitles(String collName, String titleContents,
            boolean startsWith) 
        throws RemoteException, FedoraVersionNotSupportedException;

    /* The following single method can be used instead.
     * ComparisonOperator can be contains or startswith. */
    /* public String[] browse(String term, ComparisonOperator?); */
}