001/*
002 *  Copyright (c) 2023-2026, Agents-Flex (fuhai999@gmail.com).
003 *  <p>
004 *  Licensed under the Apache License, Version 2.0 (the "License");
005 *  you may not use this file except in compliance with the License.
006 *  You may obtain a copy of the License at
007 *  <p>
008 *  http://www.apache.org/licenses/LICENSE-2.0
009 *  <p>
010 *  Unless required by applicable law or agreed to in writing, software
011 *  distributed under the License is distributed on an "AS IS" BASIS,
012 *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
013 *  See the License for the specific language governing permissions and
014 *  limitations under the License.
015 */
016package com.agentsflex.core.file2text.extractor;
017
018import com.agentsflex.core.file2text.source.DocumentSource;
019
020import java.io.IOException;
021import java.util.Comparator;
022
023public interface FileExtractor {
024
025    Comparator<FileExtractor> ORDER_COMPARATOR =
026        Comparator.comparingInt(FileExtractor::getOrder);
027
028    /**
029     * 判断该 Extractor 是否支持处理此文档
030     */
031    boolean supports(DocumentSource source);
032
033    String extractText(DocumentSource source) throws IOException;
034
035    default int getOrder() {
036        return 100;
037    }
038}