tabula-java/src/test/java/technology/tabula/TestObjectExtractor.java at master · fin/tabula-java · GitHub

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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
package technology.tabula;

import static org.junit.Assert.*;

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

import org.apache.pdfbox.pdmodel.PDDocument;
import org.junit.Test;

public class TestObjectExtractor {

    @Test(expected=IOException.class)
    public void testWrongPasswordRaisesException() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/encrypted.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document, "wrongpass");
        oe.extract().next();
    }

    @Test(expected=IOException.class)
    public void testEmptyOnEncryptedFileRaisesException() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/encrypted.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        oe.extract().next();
    }

    @Test
    public void testCanReadPDFWithOwnerEncryption() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        PageIterator pi = oe.extract();
        int i = 0;
        while (pi.hasNext()) {
            i++;
            pi.next();
        }
        assertEquals(2, i);
    }

    @Test
    public void testGoodPassword() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/encrypted.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document, "userpassword");
        List<Page> pages = new ArrayList<Page>();
        PageIterator pi = oe.extract();
        while (pi.hasNext()) {
            pages.add(pi.next());
        }
        assertEquals(1, pages.size());
    }

    @Test
    public void testTextExtractionDoesNotRaise() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/rotated_page.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        PageIterator pi = oe.extract();

        assertTrue(pi.hasNext());
        assertNotNull(pi.next());
        assertFalse(pi.hasNext());

    }

    @Test
    public void testShouldDetectRulings() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/should_detect_rulings.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        PageIterator pi = oe.extract();

        while (pi.hasNext()) {
            assertNotEquals(0, pi.next().getRulings().size());
        }
    }

    @Test
    public void testDontThrowNPEInShfill() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/labor.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        PageIterator pi = oe.extract();
        assertTrue(pi.hasNext());
        try {
            Page p = pi.next();
            assertNotNull(p);
        }
        catch (NullPointerException e) {
            fail("NPE in ObjectExtractor " + e.toString());
        }
    }

    @Test
    public void testExtractOnePage() throws IOException{
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf");
        assertEquals(2, pdf_document.getNumberOfPages());

        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        Page page = oe.extract(2);

        assertNotNull(page);

    }

    @Test(expected = IndexOutOfBoundsException.class)
    public void testExtractWrongPageNumber() throws IOException{
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf");
        assertEquals(2, pdf_document.getNumberOfPages());

        ObjectExtractor oe = new ObjectExtractor(pdf_document);
        oe.extract(3);

    }

    @Test
    public void testExtractWithoutExtractingRulings() throws IOException {
        PDDocument pdf_document = PDDocument.load("src/test/resources/technology/tabula/should_detect_rulings.pdf");
        ObjectExtractor oe = new ObjectExtractor(pdf_document, null, false, false);
        PageIterator pi = oe.extract();

        assertTrue(pi.hasNext());
        Page page = pi.next();
        assertNotNull(page);
        assertEquals(0, page.getRulings().size());
        assertFalse(pi.hasNext());
    }

}