mailbox/memory/src/main/java/org/apache/james/mailbox/inmemory/JsoupTextExtractor.java

/****************************************************************
 * Licensed to the Apache Software Foundation (ASF) under one   *
 * or more contributor license agreements.  See the NOTICE file *
 * distributed with this work for additional information        *
 * regarding copyright ownership.  The ASF licenses this file   *
 * to you under the Apache License, Version 2.0 (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.apache.org/licenses/LICENSE-2.0                 *
 *                                                              *
 * Unless required by applicable law or agreed to in writing,   *
 * software distributed under the License is distributed on an  *
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY       *
 * KIND, either express or implied.  See the License for the    *
 * specific language governing permissions and limitations      *
 * under the License.                                           *
 ****************************************************************/

package org.apache.james.mailbox.inmemory;

import java.io.InputStream;
import java.util.List;
import java.util.Map;

import org.apache.commons.io.IOUtils;
import org.apache.james.mailbox.store.extractor.ParsedContent;
import org.apache.james.mailbox.store.extractor.TextExtractor;
import org.jsoup.Jsoup;

import com.google.common.collect.Maps;


public class JsoupTextExtractor implements TextExtractor {

    @Override
    public ParsedContent extractContent(InputStream inputStream, String contentType, String fileName) throws Exception {
        Map<String, List<String>> emptyMetadata = Maps.newHashMap();
        if (contentType != null) {
           if (contentType.equals("text/plain")) {
            return new ParsedContent(IOUtils.toString(inputStream), emptyMetadata);
           }
           if (contentType.equals("text/html")) {
               String text = Jsoup.parse(IOUtils.toString(inputStream)).text();
               return new ParsedContent(text, emptyMetadata);
           }
        }
        return new ParsedContent(null, emptyMetadata);
    }
}