eafskeletonparser.java

编辑视频文件

/*
 * File:     EAFSkeletonParser.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.clomimpl.abstr.ParseException;
import mpi.eudico.server.corpora.clomimpl.abstr.TierImpl;
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 mpi.util.CVEntry;
import mpi.util.ControlledVocabulary;

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;


/**
 * Parses an eaf file, creating objects of ControlledVocabularies,
 * LinguisticTypes and Tiers only. The rest is skipped.
 *
 * @author Han Sloetjes
 * @version 1.0 jan 2006: reflects EAFv2.2.xsd
 * @version 2.0 jan 2007: reflects EAFv2.4.xsd, attribute "ANNOTATOR" added to
 * element "TIER"
 */
public class EAFSkeletonParser {
    /** the sax parser */
    private final SAXParser saxParser;

    /** the currently supported eaf version */
    private final String version = "2.4";
    private String fileName;

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

    /** stores linguistic types records! */
    private final ArrayList lingTypeRecords = new ArrayList();
    private ArrayList linguisticTypes;

    /** stores the Locales */
    private final ArrayList locales = new ArrayList();

    /** stores the ControlledVocabulary objects */
    private final ArrayList cvList = new ArrayList();
    private String currentTierId;
    private String currentCVId;
    private ControlledVocabulary currentCV;
    private String currentEntryDesc;
    private String content = "";

    /**
     * Creates a new EAFSkeletonParser instance
     *
     * @param fileName the file to be parsed
     *
     * @throws ParseException any exception that can occur when creating
     * a parser
     * @throws NullPointerException thrown when the filename is null
     */
    public EAFSkeletonParser(String fileName) throws ParseException {
        if (fileName == null) {
            throw new NullPointerException();
        }

        this.fileName = fileName;
        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/EAFv2.4.xsd");
            saxParser.setContentHandler(new EAFSkeletonHandler());
        } catch (SAXNotRecognizedException e) {
            e.printStackTrace();
            throw new ParseException(e.getMessage());
        } catch (SAXNotSupportedException e) {
            e.printStackTrace();
            throw new ParseException(e.getMessage());
        }
    }

    /*
       public ArrayList getMediaDescriptors() {
           return null;
       }
     */

    /**
     * @see mpi.eudico.server.corpora.clomimpl.abstr.Parser#getLinguisticTypes(java.lang.String)
     */
    public ArrayList getLinguisticTypes() {
        return linguisticTypes;
    }

    /**
     * Returns a list of tier objects.
     *
     * @return a list of tiers
     */
    public ArrayList getTiers() {
        return tiers;
    }

    /**
     * Returns a list of the tiernames in the same order as in the file.
     *
     * @return a list of the tiernames in the same order as in the .eaf file
     */
    public ArrayList getTierOrder() {
        return tierOrder;
    }

    /**
     * Returns a list of CVs.
     *
     * @return a list of Controlled Vocabularies
     */
    public ArrayList getControlledVocabularies() {
        return cvList;
    }

    /**
     * Returns the current version of the skeleton parser.
     *
     * @return the current version
     */
    public String getVersion() {
        return version;
    }

    /**
     * Starts the actual parsing.
     *
     * @throws ParseException any parse exception
     */
    public void parse() throws ParseException {
        // init maps and lists
        try {
            saxParser.parse(fileName);
            createObjects();
        } catch (SAXException sax) {
            System.out.println("Parsing error: " + sax.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 
            // is thrown in such case
            File f = new File(fileName);

            if (f.exists()) {
                try {
                    FileInputStream fis = new FileInputStream(f);
                    InputSource source = new InputSource(fis);
                    saxParser.parse(source);
                    createObjects();

                    // just catch any exception
                } catch (Exception ee) {
                    System.out.println("Parsing retry error: " +
                        ee.getMessage());
                    throw new ParseException(ee.getMessage(), ee.getCause());
                }
            }
        } catch (IOException ioe) {
            System.out.println("IO error: " + ioe.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 
            // is thrown in such case
            File f = new File(fileName);

            if (f.exists()) {
                try {
                    FileInputStream fis = new FileInputStream(f);
                    InputSource source = new InputSource(fis);
                    saxParser.parse(source);
                    createObjects();

                    // just catch any exception
                } catch (Exception ee) {
                    System.out.println("Parsing retry error: " +
                        ee.getMessage());
                    throw new ParseException(ee.getMessage(), ee.getCause());
                }
            }
        } catch (Exception e) {
            throw new ParseException(e.getMessage(), e.getCause());
        }
    }

    /**
     * After parsing create objects from the records; tiers and linguistic
     * types. CV's + CVEntries and Locales have already been made.
     */
    private void createObjects() {
        linguisticTypes = new ArrayList(lingTypeRecords.size());

        for (int i = 0; i < lingTypeRecords.size(); i++) {
            LingTypeRecord ltr = (LingTypeRecord) lingTypeRecords.get(i);

            LinguisticType lt = new LinguisticType(ltr.getLingTypeId());

            boolean timeAlignable = true;

            if (ltr.getTimeAlignable().equals("false")) {
                timeAlignable = false;
            }

            lt.setTimeAlignable(timeAlignable);

            boolean graphicReferences = false;

            if (ltr.getGraphicReferences().equals("true")) {
                graphicReferences = true;
            }

            lt.setGraphicReferences(graphicReferences);

            String stereotype = ltr.getStereoType();
            Constraint c = null;

            if (stereotype != null) {
                stereotype = stereotype.replace('_', ' '); // for backwards compatibility

                if (stereotype.equals(
                            Constraint.stereoTypes[Constraint.TIME_SUBDIVISION])) {
                    c = new TimeSubdivision();