eaf23parser.java

编辑视频文件

/*
 * File:     EAF23Parser.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.abstr.LinkedFileDescriptor;
import mpi.eudico.server.corpora.clomimpl.abstr.MediaDescriptor;
import mpi.eudico.server.corpora.clomimpl.abstr.Parser;

import org.apache.xerces.parsers.SAXParser;

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

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Locale;
import java.util.Vector;


/**
 * A Parser for Eudico Annotation Format (EAF) compliant XML files.
 * In version 2.3 support for LinkedFleDescrptors and for stereotype
 * Included In is added.
 *
 * @author Hennie Brugman
 * @author Han Sloetjes
 * @version 1-Dec-2003
 * @version jun 2004 addition of ControlledVocabularies
 * @version sep 2005 the constructor is now public giving up the singleton pattern
 * the path parameter of all getter methods can be removed in the next parser version
 * (replace by a public parse(String path) method)
 * @version Feb 2006 support for LinkedFleDescrptors and for stereotype
 * Included In is added. For compatibility reasons the filename parameter to the getters is maintained.
 */
public class EAF23Parser extends Parser {
    /** The EAF v2.3 XML file is parsed. */
    private static boolean verbose = false;

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

    /** stores tiername - tierrecord pairs */
    private final HashMap tierMap = new HashMap();

    /** a map with tiername - ArrayList with Annotation Records pairs */
    private final HashMap tiers = new HashMap();

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

    /** Holds value of property DOCUMENT ME! */

    //private final HashMap tierAttributes = new HashMap();

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

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

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

    /** stores the ControlledVocabulary objects by their ID */
    private final HashMap controlledVocabularies = new HashMap();

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

    /**
     * Singleton pattern is removed in version 2.2.
     */
    public EAF23Parser() {
        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/EAFv2.3.xsd");
            saxParser.setContentHandler(new EAFContentHandler());
        } catch (SAXNotRecognizedException e) {
            e.printStackTrace();
        } catch (SAXNotSupportedException e) {
            e.printStackTrace();
        }
    }

    /**
     * For backward compatibility; not used anymore
     *
     * @param fileName the eaf filename, parameter also for historic reasons
     *
     * @return media file name
     */
    public String getMediaFile(String fileName) {
        parse(fileName);

        return mediaFile;
    }

    /**
     * Returns the media descriptors
     *
     * @param fileName the eaf filename, parameter also for historic reasons
     *
     * @return the media descriptors
     */
    public ArrayList getMediaDescriptors(String fileName) {
        parse(fileName);

        return mediaDescriptors;
    }

    /**
     * Returns the linked file descriptors
     *
     * @param fileName the eaf file name, for historic reasons
     *
     * @return a list of linked file descriptors
     */
    public ArrayList getLinkedFileDescriptors(String fileName) {
        parse(fileName);

        return linkedFileDescriptors;
    }

    /**
     * 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 ArrayList getLinguisticTypes(String fileName) {
        parse(fileName);

        return linguisticTypes;
    }

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

        return timeOrder;
    }

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

        return timeSlots;
    }

    /**
     * Returns a Hastable of ArrayLists with the cv id's as keys.<br>
     * Each ArrayList can contain one String, the description and an
     * unknown number of CVEntryRecords.
     *
     * @param fileName the eaf filename
     *
     * @return a Hastable of ArrayLists with the cv id's as keys
     */
    public HashMap getControlledVocabularies(String fileName) {
        parse(fileName);

        return controlledVocabularies;
    }

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

        return tierNames;
    }

    /**
     * Returns participant attribute of a tier.
     * The tier record is not used in TranscriptionStore yet.
     *
     * @param tierName name of tier
     * @param fileName the eaf
     *
     * @return the participant
     */
    public String getParticipantOf(String tierName, String fileName) {
        parse(fileName);

        //String part = "";
        if (tierMap.get(tierName) != null) {
            if (((TierRecord) tierMap.get(tierName)).getParticipant() != null) {
                return ((TierRecord) tierMap.get(tierName)).getParticipant();
            }
        }

        /*
        if (((HashMap) tierAttributes.get(tierName)).get("PARTICIPANT") != null) {
            part = (String) ((HashMap) tierAttributes.get(tierName)).get(
                    "PARTICIPANT");
        }
        */
        return "";
    }

    /**
     * Returns the name of the linguistic type of a tier.
     * The tier record is not used in TranscriptionStore yet.
     *
     * @param tierName the name of the tier
     * @param fileName the eaf
     *
     * @return name of the type
     */
    public String getLinguisticTypeIDOf(String tierName, String fileName) {
        parse(fileName);

        //String lType = ""; // name of type
        if (tierMap.get(tierName) != null) {
            if (((TierRecord) tierMap.get(tierName)).getLinguisticType() != null) {
                return ((TierRecord) tierMap.get(tierName)).getLinguisticType();
            }
        }

        /*
        if (((HashMap) tierAttributes.get(tierName)).get(
                    "LINGUISTIC_TYPE_REF") != null) {
            lType = (String) ((HashMap) tierAttributes.get(tierName)).get(
                    "LINGUISTIC_TYPE_REF");
        }
        */
        return "";
    }

    /**
     * Returns the Locale object for a tier.
     *
     * @param tierName the name of the tier
     * @param fileName the eaf
     *
     * @return the default Locale object
     */
    public Locale getDefaultLanguageOf(String tierName, String fileName) {
        parse(fileName);

        Locale resultLoc = null;

        String localeId = null;

        //String localeId = (String) ((HashMap) tierAttributes.get(tierName)).get(
        //        "DEFAULT_LOCALE");
        if (tierMap.get(tierName) != null) {
            localeId = ((TierRecord) tierMap.get(tierName)).getDefaultLocale();
        }

        Iterator locIter = locales.iterator();

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

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

        return resultLoc;
    }

    /**
     * Returns the name of the parent tier, if any.
     *
     * @param tierName the name of the tier
     * @param fileName the eaf
     *
     * @return the name of the parent tier, or null
     */
    public String getParentNameOf(String tierName, String fileName) {
        parse(fileName);

        if (tierMap.get(tierName) != null) {
            return ((TierRecord) tierMap.get(tierName)).getParentTier();
        }

        //return (String) ((HashMap) tierAttributes.get(tierName)).get(
        //    "PARENT_REF");
        return null;
    }

    /**
     * Returns a ArrayList with the Annotations for this Tier. Each
     * AnnotationRecord contains begin time, end time and text values
     *
     * @param tierName the name of the tier
     * @param fileName the eaf
     *
     * @return ArrayList of AnnotationRecord objects for the tier
     */
    public ArrayList getAnnotationsOf(String tierName, String fileName) {
        // make sure that the correct file has been parsed
        parse(fileName);

        //long start = System.currentTimeMillis();
        return (ArrayList) tiers.get(tierName);

        /*
        ArrayList annotationList = new ArrayList();

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

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

        while (iter.hasNext()) {
            Object key = iter.next();

            annotationList.add(annotations.get(key));
        }

        //long duration = System.currentTimeMillis() - start;

        //    System.out.println("Extracting Annotations took " + duration + " milli seconds");
        return annotationList;
        */
    }

    /**
     * Parses a EAF v2.3 xml file.
     *
     * @param fileName the EAF v2.3 xml file that must be parsed.
     */
    private void parse(String fileName) {
        //long start = System.currentTimeMillis();
        //		System.out.println("Parse : " + fileName);
        //		System.out.println("Free memory : " + Runtime.getRuntime().freeMemory());
        // only parse the same file once
        if (lastParsed.equals(fileName)) {
            return;