package com.arms.api.sample;

import java.io.IOException;
import java.util.List;

import lombok.extern.slf4j.Slf4j;
import org.springframework.ai.document.Document;
import org.springframework.ai.reader.ExtractedTextFormatter;
import org.springframework.ai.reader.markdown.MarkdownDocumentReader;
import org.springframework.ai.reader.markdown.config.MarkdownDocumentReaderConfig;
import org.springframework.ai.reader.pdf.PagePdfDocumentReader;
import org.springframework.ai.reader.pdf.ParagraphPdfDocumentReader;
import org.springframework.ai.reader.pdf.config.PdfDocumentReaderConfig;
import org.springframework.ai.reader.tika.TikaDocumentReader;
import org.springframework.ai.transformer.splitter.TokenTextSplitter;
import org.springframework.ai.vectorstore.VectorStore;
import org.springframework.core.io.ByteArrayResource;
import org.springframework.core.io.Resource;
import org.springframework.core.io.ResourceLoader;
import org.springframework.stereotype.Component;

import lombok.AllArgsConstructor;

@Component
@AllArgsConstructor
@Slf4j
public class MyPagePdfDocumentReader {

	private final ResourceLoader resourceLoader;

	private final VectorStore vectorStore;

	List<Document> getDocsFromPdf() {
		log.info("start getDocsFromPdf");
		Resource resource = resourceLoader.getResource("classpath:pmbokpdf/PMBOK_4th_Edition.pdf");
        try {
            byte[] data = resource.getInputStream().readAllBytes();
			Resource newResource = new ByteArrayResource(data) {
				@Override
				public String getFilename() {
					return "PMBOK_4th_Edition_한글판_UNLOCK.pdf";
				}
			};
			TikaDocumentReader pdfReader
					= new TikaDocumentReader(resource);
			TokenTextSplitter tokenTextSplitter = new TokenTextSplitter();

			vectorStore.write(tokenTextSplitter.split(pdfReader.read()));
			log.info("end getDocsFromPdf");
			return pdfReader.read();
        } catch (IOException e) {
            throw new RuntimeException(e);
        }

	}


}