在Java中识别文件类型

以下是一个简单而肮脏的例子,说明如何使用Tika来检测文件类型,而不对文件执行任何额外的解析：

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.HashMap;

import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaMetadataKeys;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.xml.sax.helpers.DefaultHandler;

public class Detector {

    public static void main(String[] args) throws Exception {
        File file = new File("/pats/to/file.xls");

        AutoDetectParser parser = new AutoDetectParser();
        parser.setParsers(new HashMap<MediaType,Parser>());

        Metadata metadata = new Metadata();
        metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY,file.getName());

        InputStream stream = new FileInputStream(file);
        parser.parse(stream,new DefaultHandler(),metadata,new ParseContext());
        stream.close();

        String mimeType = metadata.get(HttpHeaders.CONTENT_TYPE);
        System.out.println(mimeType);
    }

}