mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
00c6ec8a2d
# Fix Telegram API loader + add tests. I was testing this integration and it was broken with next error: ```python message_threads = loader._get_message_threads(df) KeyError: False ``` Also, this particular loader didn't have any tests / related group in poetry, so I added those as well. @hwchase17 / @eyurtsev please take a look on this fix PR. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
90 lines
2.8 KiB
Python
90 lines
2.8 KiB
Python
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)
|