001/*
002 * This library is part of OpenCms -
003 * the Open Source Content Management System
004 *
005 * Copyright (c) Alkacon Software GmbH & Co. KG (http://www.alkacon.com)
006 *
007 * This library is free software; you can redistribute it and/or
008 * modify it under the terms of the GNU Lesser General Public
009 * License as published by the Free Software Foundation; either
010 * version 2.1 of the License, or (at your option) any later version.
011 *
012 * This library is distributed in the hope that it will be useful,
013 * but WITHOUT ANY WARRANTY; without even the implied warranty of
014 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
015 * Lesser General Public License for more details.
016 *
017 * For further information about Alkacon Software GmbH & Co. KG, please see the
018 * company website: http://www.alkacon.com
019 *
020 * For further information about OpenCms, please see the
021 * project website: http://www.opencms.org
022 *
023 * You should have received a copy of the GNU Lesser General Public
024 * License along with this library; if not, write to the Free Software
025 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
026 */
027
028package org.opencms.search.extractors;
029
030import java.io.InputStream;
031
032/**
033 * Allows extraction of the indexable "plain" text plus (optional) meta information from a given binary
034 * input document format.<p>
035 *
036 * @since 6.0.0
037 */
038public interface I_CmsTextExtractor {
039
040    /**
041     * Extracts the text and meta information from the given binary document.<p>
042     *
043     * The encoding of the input stream is either not required (the document type may have
044     * one common default encoding) or the extractor is able to divine the encoding
045     * from the provided binary array automatically.<p>
046     *
047     * Delivers is the same result as calling <code>{@link #extractText(byte[], String)}</code>
048     * when <code>String == null</code>.<p>
049     *
050     * @param content the binary content of the document to extract the text from
051     * @return the extracted text
052     *
053     * @throws Exception if the text extration fails
054     */
055    I_CmsExtractionResult extractText(byte[] content) throws Exception;
056
057    /**
058     * Extracts the text and meta information from the given binary document, using the specified content encoding.<p>
059     *
060     * The encoding is a hint for the text extractor, if the value given is <code>null</code> then
061     * the text extractor should try to figure out the encoding itself.<p>
062     *
063     * @param content the binary content of the document to extract the text from
064     * @param encoding the encoding to use
065     *
066     * @return the extracted text
067     *
068     * @throws Exception if the text extration fails
069     */
070    I_CmsExtractionResult extractText(byte[] content, String encoding) throws Exception;
071
072    /**
073     * Extracts the text and meta information from the document on the input stream.<p>
074     *
075     * The encoding of the input stream is either not required (the document type may have
076     * one common default encoding) or the extractor is able to divine the encoding
077     * from the provided input stream automatically.<p>
078     *
079     * Delivers is the same result as calling <code>{@link #extractText(InputStream, String)}</code>
080     * when <code>String == null</code>.<p>
081     *
082     * @param in the input stream for the document to extract the text from
083     * @return the extracted text and meta information
084     *
085     * @throws Exception if the text extration fails
086     */
087    I_CmsExtractionResult extractText(InputStream in) throws Exception;
088
089    /**
090     * Extracts the text and meta information from the document on the input stream, using the specified content encoding.<p>
091     *
092     * The encoding is a hint for the text extractor, if the value given is <code>null</code> then
093     * the text extractor should try to figure out the encoding itself.<p>
094     *
095     * @param in the input stream for the document to extract the text from
096     * @param encoding the encoding to use
097     *
098     * @return the extracted text and meta information
099     *
100     * @throws Exception if the text extration fails
101     */
102    I_CmsExtractionResult extractText(InputStream in, String encoding) throws Exception;
103}