package jnpf.dmsService.search.extract;

import jnpf.dmsService.search.DmsSearchProperties;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.io.TempDir;

import java.io.OutputStream;
import java.nio.file.Files;
import java.nio.file.Path;

import static org.junit.jupiter.api.Assertions.assertFalse;
import static org.junit.jupiter.api.Assertions.assertTrue;

class DmsTextExtractionServiceTest {
    @TempDir
    Path directory;

    @Test
    void extractsDocxText() throws Exception {
        Path file = directory.resolve("quality.docx");
        try (XWPFDocument document = new XWPFDocument();
             OutputStream output = Files.newOutputStream(file)) {
            document.createParagraph().createRun().setText("质量管理规程");
            document.write(output);
        }

        DmsTextExtractionResult result = service().extract(file, file.getFileName().toString());

        assertTrue(result.getText().contains("质量管理规程"));
        assertFalse(result.isOcrRequired());
    }

    @Test
    void marksImageOnlyPdfForOcr() throws Exception {
        Path file = directory.resolve("scan.pdf");
        try (PDDocument document = new PDDocument()) {
            document.addPage(new PDPage());
            document.save(file.toFile());
        }

        DmsTextExtractionResult result = service().extract(file, file.getFileName().toString());

        assertTrue(result.isOcrRequired());
    }

    private DmsTextExtractionService service() {
        return new DmsTextExtractionService(new DmsSearchProperties());
    }
}