/* * 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.tika.parser.jpeg; import java.io.IOException; import java.io.InputStream; import java.util.Collections; import java.util.Set; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TemporaryResources; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; import org.apache.tika.mime.MediaType; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.image.ImageMetadataExtractor; import org.apache.tika.parser.image.xmp.JempboxExtractor; import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.ContentHandler; import org.xml.sax.SAXException; public class JpegParser extends AbstractParser { /** * Serial version UID */ private static final long serialVersionUID = -1355028253756234603L; private static final Set<MediaType> SUPPORTED_TYPES = Collections.singleton(MediaType.image("jpeg")); public Set<MediaType> getSupportedTypes(ParseContext context) { return SUPPORTED_TYPES; } public void parse( InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException { TemporaryResources tmp = new TemporaryResources(); try { TikaInputStream tis = TikaInputStream.get(stream, tmp); new ImageMetadataExtractor(metadata).parseJpeg(tis.getFile()); new JempboxExtractor(metadata).parse(tis); } finally { tmp.dispose(); } XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata); xhtml.startDocument(); xhtml.endDocument(); } }