Spaces:
Running
Running
File size: 2,868 Bytes
cfd3735 |
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 |
from pathlib import Path
from langchain.docstore.document import Document
from langchain.document_loaders.csv_loader import CSVLoader
class TestCSVLoader:
# Tests that a CSV file with valid data is loaded successfully.
def test_csv_loader_load_valid_data(self) -> None:
# Setup
file_path = self._get_csv_file_path("test_nominal.csv")
expected_docs = [
Document(
page_content="column1: value1\ncolumn2: value2\ncolumn3: value3",
metadata={"source": file_path, "row": 0},
),
Document(
page_content="column1: value4\ncolumn2: value5\ncolumn3: value6",
metadata={"source": file_path, "row": 1},
),
]
# Exercise
loader = CSVLoader(file_path=file_path)
result = loader.load()
# Assert
assert result == expected_docs
# Tests that an empty CSV file is handled correctly.
def test_csv_loader_load_empty_file(self) -> None:
# Setup
file_path = self._get_csv_file_path("test_empty.csv")
expected_docs: list = []
# Exercise
loader = CSVLoader(file_path=file_path)
result = loader.load()
# Assert
assert result == expected_docs
# Tests that a CSV file with only one row is handled correctly.
def test_csv_loader_load_single_row_file(self) -> None:
# Setup
file_path = self._get_csv_file_path("test_one_row.csv")
expected_docs = [
Document(
page_content="column1: value1\ncolumn2: value2\ncolumn3: value3",
metadata={"source": file_path, "row": 0},
)
]
# Exercise
loader = CSVLoader(file_path=file_path)
result = loader.load()
# Assert
assert result == expected_docs
# Tests that a CSV file with only one column is handled correctly.
def test_csv_loader_load_single_column_file(self) -> None:
# Setup
file_path = self._get_csv_file_path("test_one_col.csv")
expected_docs = [
Document(
page_content="column1: value1",
metadata={"source": file_path, "row": 0},
),
Document(
page_content="column1: value2",
metadata={"source": file_path, "row": 1},
),
Document(
page_content="column1: value3",
metadata={"source": file_path, "row": 2},
),
]
# Exercise
loader = CSVLoader(file_path=file_path)
result = loader.load()
# Assert
assert result == expected_docs
# utility functions
def _get_csv_file_path(self, file_name: str) -> str:
return str(Path(__file__).resolve().parent / "test_docs" / "csv" / file_name)
|