langchain/tests/integration_tests/document_loaders/test_bshtml.py
Maciej Bryński aa345a4bb7
Add get_text_separator parameter to BSHTMLLoader (#3551)
By default get_text doesn't separate content of different HTML tag.
Adding option for specifying separator helps with document splitting.
2023-04-26 16:10:16 -07:00

45 lines
1.2 KiB
Python

import sys
from pathlib import Path
import pytest
from langchain.document_loaders.html_bs import BSHTMLLoader
def test_bs_html_loader() -> None:
"""Test unstructured loader."""
file_path = Path(__file__).parent.parent / "examples/example.html"
loader = BSHTMLLoader(str(file_path), get_text_separator="|")
docs = loader.load()
assert len(docs) == 1
metadata = docs[0].metadata
content = docs[0].page_content
assert metadata["title"] == "Chew dad's slippers"
assert metadata["source"] == str(file_path)
assert content[:2] == "\n|"
@pytest.mark.skipif(
bool(sys.flags.utf8_mode) or not sys.platform.startswith("win"),
reason="default encoding is utf8",
)
def test_bs_html_loader_non_utf8() -> None:
"""Test providing encoding to BSHTMLLoader."""
file_path = Path(__file__).parent.parent / "examples/example-utf8.html"
with pytest.raises(UnicodeDecodeError):
BSHTMLLoader(str(file_path)).load()
loader = BSHTMLLoader(str(file_path), open_encoding="utf8")
docs = loader.load()
assert len(docs) == 1
metadata = docs[0].metadata
assert metadata["title"] == "Chew dad's slippers"
assert metadata["source"] == str(file_path)