eaf24parser.java

编辑视频文件

/*
 * File:     EAF24Parser.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 mpi.eudico.server.corpora.clomimpl.abstr.PropertyImpl;

import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.ErrorHandler;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLReader;

import org.xml.sax.helpers.XMLReaderFactory;

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;


/**
 * A (SAX2) Parser for Elan Annotation Format (EAF) compliant XML files.
 *
 * @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.
 * @version Dec 2006 element PROPERTY has been added to the HEADER element, attribute
 * ANNOTATOR has been added to element TIER
 */
public class EAF24Parser extends Parser {
    private boolean verbose = false;
    private XMLReader reader;

    /** 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 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 docProperties = new ArrayList();

    /** stores the time slots orderd by id */
    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 PropertyImpl currentProperty;
    private boolean parseError;

    /**
     * Constructor, creates a new XMLReader
     *
     */
    public EAF24Parser() {
        try {
            reader = XMLReaderFactory.createXMLReader(
                    "org.apache.xerces.parsers.SAXParser");
            reader.setFeature("http://xml.org/sax/features/namespaces", true);
            reader.setFeature("http://xml.org/sax/features/validation", true);
            reader.setFeature("http://apache.org/xml/features/validation/schema",
                true);
            reader.setFeature("http://apache.org/xml/features/validation/dynamic",
                true);
            reader.setProperty("http://java.sun.com/xml/jaxp/properties/schemaSource",
                this.getClass().getResource("/mpi/eudico/resources/EAFv2.4.xsd")
                    .openStream());

            //reader.setProperty("http://apache.org/xml/properties/schema/external-noNamespaceSchemaLocation",
            //		"http://www.mpi.nl/tools/elan/EAFv2.4.xsd");
            reader.setContentHandler(new EAFContentHandler());

            //reader.setErrorHandler(new EAFErrorHandler());
        } catch (SAXException se) {
            se.printStackTrace();
        } catch (IOException ioe) {
            ioe.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;
    }

    /**
     * Returns a list of PropertyImpl objects that have been retrieved from the eaf.
     *
     * @see mpi.eudico.server.corpora.clomimpl.abstr.Parser#getTranscriptionProperties(java.lang.String)
     */
    public ArrayList getTranscriptionProperties(String fileName) {
        parse(fileName);

        return docProperties;
    }

    /**
     * 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);

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

        return "";
    }

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

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

        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);

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

        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;

        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 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);

        return (ArrayList) tiers.get(tierName);
    }

    /**
     * Parses a EAF v2.4 (or <) xml file.
     *
     * @param fileName the EAF v2.4 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;
        }

        // (re)set everything to null for each parse
        tiers.clear();
        tierNames.clear(); // HB, 2-1-02, to store name IN ORDER

        //tierAttributes.clear();
        mediaFile = "";
        linguisticTypes.clear();
        locales.clear();
        timeSlots.clear();
        timeOrder.clear();
        mediaDescriptors.clear();
        linkedFileDescriptors.clear();
        controlledVocabularies.clear();

        // parse the file
        lastParsed = fileName;
        currentFileName = fileName;

        try {
            reader.parse(fileName);
        } catch (SAXException e) {
            System.out.println("Parsing error: " + e.getMessage());

            // the SAX parser can have difficulties with certain characters in 
            // the filepath: try to create an InputSource for the parser 
            // HS Mar 2007: depending on Xerces version a SAXException or an IOException