eaf20parser.java

编辑视频文件

/*
 * File:     EAF20Parser.java
 * Project:  MPI Linguistic Application
 * Date:     02 May 2007
 *
 * Copyright (C) 2001-2007  Max Planck Institute for Psycholinguistics
 *
 * 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.
 *
 * 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.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

package mpi.eudico.server.corpora.clomimpl.dobes;

import mpi.eudico.server.corpora.clom.TimeSlot;

import mpi.eudico.server.corpora.clomimpl.type.Constraint;
import mpi.eudico.server.corpora.clomimpl.type.LinguisticType;
import mpi.eudico.server.corpora.clomimpl.type.SymbolicAssociation;
import mpi.eudico.server.corpora.clomimpl.type.SymbolicSubdivision;
import mpi.eudico.server.corpora.clomimpl.type.TimeSubdivision;

import org.apache.xerces.parsers.SAXParser;

import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;

import java.io.IOException;

import java.util.Hashtable;
import java.util.Iterator;
import java.util.Locale;
import java.util.Vector;


/**
 * A Parser for Eudico Annotation Format (EAF) compliant XML files. MAYBE THIS
 * CLASS MUST BE MADE THREAD SAFE BY ADDING SOME SYNCHRONIZED BLOCKS OR BY
 * GIVING UP THE SINGLETON PATTERN.
 *
 * @author Hennie Brugman
 * @version 18-Jul-2002
 */
public class EAF20Parser {
    /** The EAF v2.0 XML file is parsed. */
    private static boolean verbose = false;
    private static EAF20Parser parser;

    /** Holds value of property DOCUMENT ME! */
    private final SAXParser saxParser;

    /** Holds value of property DOCUMENT ME! */
    private final Hashtable tiers = new Hashtable();

    /** Holds value of property DOCUMENT ME! */
    private final Vector tierNames = new Vector();

    /** Holds value of property DOCUMENT ME! */
    private final Hashtable tierAttributes = new Hashtable();

    /** Holds value of property DOCUMENT ME! */
    private final Vector linguisticTypes = new Vector();

    /** Holds value of property DOCUMENT ME! */
    private final Vector locales = new Vector();

    /** Holds value of property DOCUMENT ME! */
    private final Hashtable timeSlots = new Hashtable();

    /** Holds value of property DOCUMENT ME! */
    private final Vector timeOrder = new Vector(); // since a Hashtable is not ordered, all time_slot_ids have to be stored in order separately.
    private String mediaFile;
    private String svgFile;
    private String author;
    private String currentTierId;
    private String currentAnnotationId;
    private String content = "";
    private String lastParsed = "";
    private String currentFileName;
    private boolean parseError;

    /**
     * Private constructor for EAFParser because the Singleton pattern is
     * applied here.
     */
    private EAF20Parser() {
        saxParser = new SAXParser();

        try {
            saxParser.setFeature("http://xml.org/sax/features/validation", true);
            saxParser.setFeature("http://apache.org/xml/features/validation/dynamic",
                true);
            saxParser.setProperty("http://apache.org/xml/properties/schema/external-noNamespaceSchemaLocation",
                "http://www.mpi.nl/tools/elan/EAFv2.0.xsd");
            saxParser.setContentHandler(new EAFContentHandler());
        } catch (SAXNotRecognizedException e) {
            e.printStackTrace();
        } catch (SAXNotSupportedException e) {
            e.printStackTrace();
        }
    }

    /**
     * The instance method returns the single incarnation of EAFParser to the
     * caller.
     *
     * @return DOCUMENT ME!
     */
    public static EAF20Parser Instance() {
        if (parser == null) {
            parser = new EAF20Parser();
        }

        return parser;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getMediaFile(String fileName) {
        parse(fileName);

        return mediaFile;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getSVGFile(String fileName) {
        parse(fileName);

        return svgFile;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getAuthor(String fileName) {
        parse(fileName);

        return author;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Vector getLinguisticTypes(String fileName) {
        parse(fileName);

        return linguisticTypes;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Vector getTimeOrder(String fileName) {
        parse(fileName);

        return timeOrder;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Hashtable getTimeSlots(String fileName) {
        parse(fileName);

        return timeSlots;
    }

    /**
     * Returns the names of the Tiers that are present in the Transcription
     * file
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Vector getTierNames(String fileName) {
        parse(fileName);

        return tierNames;
    }

    /**
     * DOCUMENT ME!
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getParticipantOf(String tierName, String fileName) {
        parse(fileName);

        String part = "";

        if (((Hashtable) tierAttributes.get(tierName)).get("PARTICIPANT") != null) {
            part = (String) ((Hashtable) tierAttributes.get(tierName)).get(
                    "PARTICIPANT");
        }

        return part;
    }

    /**
     * DOCUMENT ME!
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public LinguisticType getLinguisticTypeOf(String tierName, String fileName) {
        LinguisticType lt = null;

        parse(fileName);

        String lType = ""; // name of type

        if (((Hashtable) tierAttributes.get(tierName)).get(
                    "LINGUISTIC_TYPE_REF") != null) {
            lType = (String) ((Hashtable) tierAttributes.get(tierName)).get(
                    "LINGUISTIC_TYPE_REF");
        }

        Iterator ltIter = linguisticTypes.iterator();

        while (ltIter.hasNext()) {
            LinguisticType l = (LinguisticType) ltIter.next();

            if (l.getLinguisticTypeName().equals(lType)) {
                lt = l;

                break;
            }
        }

        return lt;
    }

    /**
     * DOCUMENT ME!
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Locale getDefaultLanguageOf(String tierName, String fileName) {
        parse(fileName);

        Locale resultLoc = null;

        String localeId = (String) ((Hashtable) tierAttributes.get(tierName)).get(
                "DEFAULT_LOCALE");
        Iterator locIter = locales.iterator();

        while (locIter.hasNext()) {
            Locale l = (Locale) locIter.next();

            if (l.getLanguage().equals(localeId)) {
                resultLoc = l;
            }
        }

        return resultLoc;
    }

    /**
     * DOCUMENT ME!
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getParentNameOf(String tierName, String fileName) {
        parse(fileName);

        return (String) ((Hashtable) tierAttributes.get(tierName)).get(
            "PARENT_REF");
    }

    /**
     * Returns a Vector with the Annotations for this Tier. Each
     * AnnotationRecord contains begin time, end time and text values
     *
     * <p>
     * MK:02/06/10<br> Elements of Vector are no CLOM/ACM Annotations but yet
     * another Vector of String . The inner Vector is interpreted as variant
     * record in DAFTranscriptionStore.loadTranscription
     * </p>
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return Vector of Vector of String
     */
    public Vector getAnnotationsOf(String tierName, String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        long start = System.currentTimeMillis();

        Vector annotationVector = new Vector();

        // get the tags from the tiers Hashtable
        Hashtable annotations = (Hashtable) tiers.get(tierName);

        // get an iterator that iterates over the tags in the right order.
        Iterator iter = annotations.keySet().iterator();

        while (iter.hasNext()) {
            Vector annotationRecord = new Vector();

            Object key = iter.next();

            annotationRecord.add(key);