[Java] PDF - tika

tika의 목적

• 다양한 문서(PPT,XML,PDF)를 하나의 프로그램으로 메타데이터나 텍스트를 추출 하기위한 목적
• Tika (The Apache toolkit)

tika의 장점

• 무료
• 범용성

tika의 단점

• 아직 단점은 잘 모르겠음

구현

<!-- https://mvnrepository.com/artifact/org.apache.tika/tika-core -->
<dependency>
	<groupId>org.apache.tika</groupId>
	<artifactId>tika-core</artifactId>
	<version>1.27</version>
</dependency>

<!-- https://mvnrepository.com/artifact/org.apache.tika/tika-parsers -->
 <dependency>
	 <groupId>org.apache.tika</groupId>
	 <artifactId>tika-parsers</artifactId>
	 <version>1.27</version>
 </dependency>

import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;


import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.SAXException;


public class PdfReaderUtil {

	public static void main(String args[]) {
		System.out.println("start!");
		
	    PdfReaderUtil pdfReaderUtil = new PdfReaderUtil();

		try {

			String text3 = pdfReaderUtil.readPdfByTika1(filePath);
            String text4 = pdfReaderUtil.readPdfByTika2(filePath);
            
            System.out.println("readPdfByTika1:"+text3);
			System.out.println("readPdfByTika2:"+text4);
            
            
		} catch (Exception e) {
			System.out.println("exception : " + e);
		}
        
		System.out.println("end !");
	}

	public static String readPdfByTika1(String filePath) throws IOException, TikaException, SAXException {
		Parser parser = new AutoDetectParser();
		BodyContentHandler bodyContentHandler = new BodyContentHandler(Integer.MAX_VALUE);

		TesseractOCRConfig tesseractOCRConfig = new TesseractOCRConfig();
		PDFParserConfig pDFParserConfig = new PDFParserConfig();
		pDFParserConfig.setExtractInlineImages(true);

		ParseContext parseContext = new ParseContext();
		parseContext.set(TesseractOCRConfig.class, tesseractOCRConfig);
		parseContext.set(PDFParserConfig.class, pDFParserConfig);
		
        parseContext.set(Parser.class, parser);

		FileInputStream fileInputStream = new FileInputStream(filePath);
		Metadata metadata = new Metadata();
		parser.parse(fileInputStream, bodyContentHandler, metadata, parseContext);
		String content = bodyContentHandler.toString();
		return content;
	}

	public static String readPdfByTika2(String filePath) throws Exception {
		File file = new File(filePath);
		BodyContentHandler bodyContentHandler = new BodyContentHandler();
		AutoDetectParser autoDetectParser = new AutoDetectParser();
		Metadata metadata = new Metadata();
		try (InputStream inputStream = new FileInputStream(file)) {
			autoDetectParser.parse(inputStream, bodyContentHandler, metadata);
			return bodyContentHandler.toString();
		}

	}
}