transcriber14parser.java

编辑视频文件

/*
 * File:     Transcriber14Parser.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.transcriber;

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

import mpi.eudico.server.corpora.clomimpl.abstr.MediaDescriptor;
import mpi.eudico.server.corpora.clomimpl.abstr.Parser;
import mpi.eudico.server.corpora.clomimpl.dobes.AnnotationRecord;
import mpi.eudico.server.corpora.clomimpl.dobes.CVEntryRecord;
import mpi.eudico.server.corpora.clomimpl.dobes.LingTypeRecord;
import mpi.eudico.server.corpora.clomimpl.type.Constraint;

// import org.apache.xerces.parsers.SAXParser;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

import org.xml.sax.helpers.DefaultHandler;

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

import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.StringTokenizer;
import java.util.TreeSet;

import javax.xml.parsers.*;


/**
 * A Parser for Transcriber 1.4 compliant XML files. MAYBE THIS
 * CLASS MUST BE MADE THREAD SAFE BY ADDING SOME SYNCHRONIZED BLOCKS OR BY
 * GIVING UP THE SINGLETON PATTERN.
 *
 * @version sep 2005 the constructor is now public giving up the singleton pattern.
 * The path parameter of all getter methods could be removed in the next parser version
 * (add a public parse(String path) method)
 * Hashtable and Vector in Parser have been replaced by HashMap and ArrayList
 *
 * @author Hennie Brugman
 */
public class Transcriber14Parser extends Parser {
    private static boolean verbose = false;

    //private static Transcriber14Parser parser;
    private static int annotationCounter = 0;
    private static int timeSlotCounter = 0;

    /** Holds value of property DOCUMENT ME! */
    private static final String ANN_PREFIX = "a";

    /** Holds value of property DOCUMENT ME! */
    private static final String TS_PREFIX = "ts";

    /** Holds value of property DOCUMENT ME! */
    private static final String SP_PREFIX = "Sp";

    /** Holds value of property DOCUMENT ME! */
    private static final String SECTION_TIER_NAME = "Sections";

    /** Holds value of property DOCUMENT ME! */
    private static final String TURN_TIER_NAME = "Turns";

    /** Holds value of property DOCUMENT ME! */
    private static final String BACKGROUND_TIER_NAME = "Background";

    /** Holds value of property DOCUMENT ME! */
    private static final String COMMENT_TIER_NAME = "Comments";

    /** Holds value of property DOCUMENT ME! */
    private static final String MODE_TIER_NAME = "Mode";

    /** Holds value of property DOCUMENT ME! */
    private static final String FIDELITY_TIER_NAME = "Fidelity";

    /** Holds value of property DOCUMENT ME! */
    private static final String CHANNEL_TIER_NAME = "Channel";

    /** Holds value of property DOCUMENT ME! */
    private static final String SINGLE_TIER_NAME = "Speech";

    /** Holds value of property DOCUMENT ME! */
    private static final String UTTERANCE_TYPE = "UtteranceType";

    /** Holds value of property DOCUMENT ME! */
    private static final String SECTION_TYPE = "SectionType";

    /** Holds value of property DOCUMENT ME! */
    private static final String TURN_TYPE = "TurnType";

    /** Holds value of property DOCUMENT ME! */
    private static final String MODE_TYPE = "ModeType";

    /** Holds value of property DOCUMENT ME! */
    private static final String FIDELITY_TYPE = "FidelityType";

    /** Holds value of property DOCUMENT ME! */
    private static final String CHANNEL_TYPE = "ChannelType";

    /** Holds value of property DOCUMENT ME! */
    private static final String BACKGROUND_TYPE = "BackgroundType";

    /** Holds value of property DOCUMENT ME! */
    private static final String COMMENT_TYPE = "CommentType";

    /** Holds value of property DOCUMENT ME! */
    private static final String SECTION_TYPE_CV = "SectionTypeCV";

    /** Holds value of property DOCUMENT ME! */
    private static final String TURN_MODE_CV = "TurnModeCV";

    /** Holds value of property DOCUMENT ME! */
    private static final String TURN_FIDELITY_CV = "TurnFidelityCV";

    /** Holds value of property DOCUMENT ME! */
    private static final String TURN_CHANNEL_CV = "TurnChannelCV";

    /** Holds value of property DOCUMENT ME! */
    private static final String SPEAKER_UNSPECIFIED = "Unspecified";

    /** Holds value of property DOCUMENT ME! */
    private SAXParser saxParser;
    private DefaultHandler transcriberHandler;
    private TranscriberDecoderInfo decoderInfo;
    private boolean singleSpeechTier = false;
    private String lastParsed = "";
    private String currentFileName;
    private boolean parseError;

    // members to store parse results
    private String audioFileName;
    private String scribe;
    private String language;
    private String date;
    private HashMap speakersHash = new HashMap();
    private ArrayList sectionArrayList = new ArrayList();
    private ArrayList utteranceRecords = new ArrayList();
    private ArrayList backgroundArrayList = new ArrayList();
    private HashMap timeSlots = new HashMap();
    private HashMap annotRecordToTierMap = new HashMap();
    private TreeSet tierNameSet = new TreeSet();
    private HashMap topicHash = new HashMap();
    private ArrayList commentRecords = new ArrayList();
    private HashMap controlledVocabularies = null;

    // members to remember current parse state
    private SectionRecord currentSectionRecord;
    private SectionRecord lastSectionRecord;
    private TurnRecord currentTurnRecord;
    private TurnRecord lastTurnRecord;
    private String currentSpeakerId;
    private String speakersForCurrentTurn;
    private String lastSyncTime;
    private HashMap currentSpeakerContents = new HashMap(); // contains utterances under construction
    private BackgroundRecord lastBackgroundRecord;
    private String currentComments = "";

    /**
     * Private constructor for Transcriber14Parser because the Singleton pattern is
     * applied here.
     */
    public Transcriber14Parser() {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        factory.setValidating(false);
        factory.setNamespaceAware(false);

        try {
            saxParser = factory.newSAXParser();
        } catch (Exception e) {
            e.printStackTrace();
        }

        transcriberHandler = new Transcriber14Handler();
    }

    /**
     * The instance method returns the single incarnation of TranscriberParser to the
     * caller.
     *
     * @return DOCUMENT ME!
     */

    /*
    public static Transcriber14Parser Instance() {
        if (parser == null) {
            parser = new Transcriber14Parser();
        }

        return parser;
    }
    */

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

        return null;
    }

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

        ArrayList mediaDescriptors = new ArrayList();

        if (audioFileName != null) {
            // compose audio file url
            String urlString = pathToURLString(fileName);
            String mediaURL = urlString.substring(0,
                    urlString.lastIndexOf("/") + 1) + audioFileName;

            if (!mediaURL.endsWith(".wav")) {
                mediaURL += ".wav";
            }

            MediaDescriptor md = new MediaDescriptor(mediaURL,
                    MediaDescriptor.WAV_MIME_TYPE);
            mediaDescriptors.add(md);
        }

        return mediaDescriptors;
    }

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

        return null;
    }

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

        return scribe;
    }

    /**
     * DOCUMENT ME!
     *
     * @param fileName DOCUMENT ME!
     *
     * @return DOCUMENT ME!
     */
    public ArrayList getLinguisticTypes(String fileName) {
        ArrayList lingTypeRecords = new ArrayList();

        parse(fileName);

        // Transcriber uses a number of fixed linguistic types.
        LingTypeRecord lt = new LingTypeRecord();
        lt.setLingTypeId(UTTERANCE_TYPE);
        lt.setTimeAlignable("true");
        lt.setStereoType(null);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(SECTION_TYPE);
        lt.setTimeAlignable("true");
        lt.setStereoType(null);
        lt.setControlledVocabulary(SECTION_TYPE_CV);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(TURN_TYPE);
        lt.setTimeAlignable("true");
        lt.setStereoType(Constraint.stereoTypes[Constraint.TIME_SUBDIVISION]);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(MODE_TYPE);
        lt.setTimeAlignable("false");
        lt.setStereoType(Constraint.stereoTypes[Constraint.SYMBOLIC_ASSOCIATION]);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(FIDELITY_TYPE);
        lt.setTimeAlignable("false");
        lt.setStereoType(Constraint.stereoTypes[Constraint.SYMBOLIC_ASSOCIATION]);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(CHANNEL_TYPE);
        lt.setTimeAlignable("false");
        lt.setStereoType(Constraint.stereoTypes[Constraint.SYMBOLIC_ASSOCIATION]);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(BACKGROUND_TYPE);
        lt.setTimeAlignable("true");
        lt.setStereoType(null);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        lt = new LingTypeRecord();
        lt.setLingTypeId(COMMENT_TYPE);
        lt.setTimeAlignable("true");
        lt.setStereoType(null);
        lt.setControlledVocabulary(null);
        lt.setGraphicReferences("false");

        lingTypeRecords.add(lt);

        return lingTypeRecords;