Initial commit: bositao cloud (jnpf-java-cloud-v6x)

刘光辉

5 小时以前 06f314545ac3514d7ce28939920866ae8188d31c

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
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());
    }
}