dafparser.java

编辑视频文件

/*
 * File:     DAFParser.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.LinguisticType;

import org.xml.sax.AttributeList;
import org.xml.sax.HandlerBase;
import org.xml.sax.InputSource;
import org.xml.sax.SAXParseException;

import java.io.File;

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

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;


/**
 * A Parser for Dobes Annotation Format (DAF) 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 6-Jul-2001
 */
public class DAFParser extends HandlerBase {
    private static DAFParser parser;

    /** The DOBES DAF XML file is parsed. */
    private final Float ORDERED_KEYS_KEY = new Float(0.12345);
    private boolean verbose;
    private SAXParser saxParser;
    private String lastParsed;
    private String currentFileName;
    private File xmlFile;
    private boolean parseError;
    private Hashtable tiers;
    private Vector tierNames;
    private Hashtable tierAttributes;
    private String mediaFile;
    private String author;
    private Vector linguisticTypes;
    private Vector locales;
    private Hashtable timeSlots;
    private Vector timeOrder; // since a Hashtable is not ordered, all time_slot_ids have to be stored in order separately.
    private String currentTierId;
    private String currentAnnotationId;
    private String currentSpeakerId;
    private String currentStart;
    private String currentEnd;
    private String content;

    /**
     * Private constructor for DAFParser because the Singleton pattern is
     * applied here.
     */
    private DAFParser() {
        try {
            SAXParserFactory factory = SAXParserFactory.newInstance();
            factory.setValidating(false);
            saxParser = factory.newSAXParser();
            lastParsed = "";
            verbose = false;
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

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

        return parser;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getMediaFile(String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        return mediaFile;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getAuthor(String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        return author;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Vector getLinguisticTypes(String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        return linguisticTypes;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Vector getTimeOrder(String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        return timeOrder;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public Hashtable getTimeSlots(String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(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) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            parse(fileName);
        }

        //	Vector tierNames = new Vector(tiers.keySet());
        //	Collections.sort(tierNames);
        return tierNames;
    }

    /**
     * DOCUMENT ME!
     *
     * @param tierName DOCUMENT ME!
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public String getParticipantOf(String tierName, String fileName) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(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;

        // make sure that the correct file has been parsed
        if (!lastParsed.equals(fileName)) {
            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) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(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) {
        // make sure that the correct file has been parsed
        if (!lastParsed.equals(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>