Defining your own Extractors

/*
 * Copyright 2003-2004 Michael Franken, Zilverline.
 *
 * The contents of this file, or the files included with this file, are subject to
 * the current version of ZILVERLINE Collaborative Source License for the
 * Zilverline Search Engine (the "License"); You may not use this file except in
 * compliance with the License.
 *
 * You may obtain a copy of the License at
 *
 *     http://www.zilverline.org.
 *
 * See the License for the rights, obligations and
 * limitations governing use of the contents of the file.
 *
 * The Original and Upgraded Code is the Zilverline Search Engine. The developer of
 * the Original and Upgraded Code is Michael Franken. Michael Franken owns the
 * copyrights in the portions it created. All Rights Reserved.
 *
 */
package org.zilverline.extractors;
import java.io.File;
/**
 * This interface defines the type of family of extractors. Extractors extract
 * all relevant info from a File, and return the info in a ParsedFileInfo
 * Object. These are mappings used by zilverline to plugin extractors based on
 * file extensions. The plugin is a java class that implements the Extractor
 * interface and needs to be available on the classpath.
 * 
 * <p>
 * So if for example you specify the mapping "pdf =>
 * org.zilverline.extractors.PDFExtractor" make sure
 * org.zilverline.extractors.PDFExtractor is available, otherwise an Exception
 * will be raised and handled by zilverline.
 * </p>
 * 
 * <p>
 * Right now you can use the TEXT, HTML, WORD and PDF extractors, and define the
 * extensions you want to map. You can not use wildcards, but you can define
 * multiple extensions for one Extractor. By default the extensions are treated
 * case insensitively, but you can change that. Note that you van use an empty
 * extension as well.
 * </p>
 * 
 * @author Michael Franken
 * @version $Revision: 1.7 $
 * 
 * @see org.zilverline.extractors.ParsedFileInfo
 */
public interface Extractor {
    /**
     * This method extracts all relevant info of the file as an ParsedFileInfo
     * object.
     * 
     * @param f
     *            the File to extract content from
     * 
     * @return ParsedFileInfo the object containing relevant info of the
     *         provided file
     */
    ParsedFileInfo extractInfo(File f);
}

/*
 * Copyright 2003-2004 Michael Franken, Zilverline.
 *
 * The contents of this file, or the files included with this file, are subject to
 * the current version of ZILVERLINE Collaborative Source License for the
 * Zilverline Search Engine (the "License"); You may not use this file except in
 * compliance with the License.
 *
 * You may obtain a copy of the License at
 *
 *     http://www.zilverline.org.
 *
 * See the License for the rights, obligations and
 * limitations governing use of the contents of the file.
 *
 * The Original and Upgraded Code is the Zilverline Search Engine. The developer of
 * the Original and Upgraded Code is Michael Franken. Michael Franken owns the
 * copyrights in the portions it created. All Rights Reserved.
 *
 */
package org.zilverline.extractors;
import java.io.File;
import java.io.Reader;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
/**
 * Java bean for the Result of a Parsed File. Used in {@link Extractor}.
 * 
 * @author Michael Franken
 * @version $Revision: 1.7 $
 */
public class ParsedFileInfo {
    /** logger for Commons logging. */
    private static Log log = LogFactory.getLog(ParsedFileInfo.class);
    private File file;
    private Reader reader;
    private String author = "";
    private String title = "";
    private String summary = "";
    private long creationDate;
    private long modificationDate;
    private String type = "";
    private long size;
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public String getAuthor() {
        return author;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public long getCreationDate() {
        return creationDate;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public long getModificationDate() {
        return modificationDate;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public Reader getReader() {
        return reader;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public String getSummary() {
        return summary;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public String getType() {
        return type;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param string
     */
    public void setAuthor(String string) {
        author = string;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param theDate
     */
    public void setCreationDate(long theDate) {
        creationDate = theDate;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param theDate
     */
    public void setModificationDate(long theDate) {
        modificationDate = theDate;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param thisReader
     */
    public void setReader(Reader thisReader) {
        this.reader = thisReader;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param string
     */
    public void setSummary(String string) {
        summary = string;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param string
     */
    public void setType(String string) {
        type = string;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public File getFile() {
        return file;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public long getSize() {
        return size;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return
     */
    public String getTitle() {
        return title;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param thisFile
     */
    public void setFile(File thisFile) {
        this.file = thisFile;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param l
     */
    public void setSize(long l) {
        size = l;
    }
    /**
     * DOCUMENT ME!
     * 
     * @param string
     */
    public void setTitle(String string) {
        title = string;
    }
    /**
     * DOCUMENT ME!
     * 
     * @return string
     */
    public String toString() {
        StringBuffer info = new StringBuffer();
        info.append("File: " + file.getName());
        info.append(", type: " + type);
        info.append(", title: " + title);
        info.append(", author: " + author);
        info.append(", creationDate: " + creationDate);
        info.append(", modificationDate: " + modificationDate);
        info.append(", size: " + size);
        info.append(", summary: " + summary);
        return info.toString();
    }
}