package com.example.tika;

import org.apache.tika.Tika;
import org.apache.tika.detect.DefaultDetector;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
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.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ToXMLContentHandler;
import org.springframework.core.io.InputStreamResource;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;

public class TikaAnalysis {

    public static String detectDocTypeUsingDetector(InputStream stream) throws Exception {
        Detector detector = new DefaultDetector();
        Metadata metadata = new Metadata();

        MediaType mediaType = detector.detect(stream, metadata);
        return mediaType.toString();
    }

    public static String detectDocTypeUsingFacade(InputStream stream) throws IOException {

        Tika tika = new Tika();
        String mediaType = tika.detect(stream);
        return mediaType;
    }

    public static String extractContentUsingParser(InputStream stream) throws IOException, TikaException, SAXException {
        Parser parser = new AutoDetectParser();
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();

        parser.parse(stream, handler, metadata, context);
        return handler.toString();
    }

    public static String extractContentUsingFacade(InputStream stream) throws IOException, TikaException {

        Tika tika = new Tika();
        String content = tika.parseToString(stream);
        return content;
    }

    public static String parseToHTML(Path path) throws IOException, SAXException, TikaException {
        InputStream stream = Files.newInputStream(path);
        ContentHandler handler = new ToXMLContentHandler();

        AutoDetectParser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        try  {
            parser.parse(stream, handler, metadata);
            return handler.toString();
        } catch (Exception e){
            e.printStackTrace();
        }
        return "unlucky";
    }

    public static Metadata extractMetadatatUsingParser(Path stream) throws IOException, SAXException, TikaException {
        TikaInputStream inputStream = TikaInputStream.get(stream);
        Parser parser = new AutoDetectParser();
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();

        parser.parse(inputStream, handler, metadata, context);
        return metadata;
    }
}