File size: 1,485 Bytes
58d33f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from pathlib import Path

from langchain.document_loaders import (
    PDFMinerLoader,
    PyMuPDFLoader,
    UnstructuredPDFLoader,
)


def test_unstructured_pdf_loader() -> None:
    """Test unstructured loader."""
    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
    loader = UnstructuredPDFLoader(str(file_path))
    docs = loader.load()

    assert len(docs) == 1


def test_pdfminer_loader() -> None:
    """Test PDFMiner loader."""
    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
    loader = PDFMinerLoader(str(file_path))
    docs = loader.load()

    assert len(docs) == 1

    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
    loader = PDFMinerLoader(str(file_path))

    docs = loader.load()
    assert len(docs) == 1


def test_pymupdf_loader() -> None:
    """Test PyMuPDF loader."""
    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
    loader = PyMuPDFLoader(str(file_path))

    docs = loader.load()
    assert len(docs) == 1

    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
    loader = PyMuPDFLoader(str(file_path))

    docs = loader.load()
    assert len(docs) == 16
    assert loader.web_path is None

    web_path = "https://people.sc.fsu.edu/~jpeterson/hello_world.pdf"
    loader = PyMuPDFLoader(web_path)

    docs = loader.load()
    assert loader.web_path == web_path
    assert loader.file_path != web_path
    assert len(docs) == 1