mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
5cfa72a130
# Bibtex integration Wrap bibtexparser to retrieve a list of docs from a bibtex file. * Get the metadata from the bibtex entries * `page_content` get from the local pdf referenced in the `file` field of the bibtex entry using `pymupdf` * If no valid pdf file, `page_content` set to the `abstract` field of the bibtex entry * Support Zotero flavour using regex to get the file path * Added usage example in `docs/modules/indexes/document_loaders/examples/bibtex.ipynb` --------- Co-authored-by: Sébastien M. Popoff <sebastien.popoff@espci.fr> Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from langchain.document_loaders.bibtex import BibtexLoader
|
|
|
|
BIBTEX_EXAMPLE_FILE = Path(__file__).parent / "sample_documents" / "bibtex.bib"
|
|
|
|
|
|
@pytest.mark.requires("fitz", "bibtexparser")
|
|
def test_load_success() -> None:
|
|
"""Test that returns one document"""
|
|
loader = BibtexLoader(file_path=str(BIBTEX_EXAMPLE_FILE))
|
|
docs = loader.load()
|
|
assert len(docs) == 1
|
|
doc = docs[0]
|
|
assert doc.page_content
|
|
assert set(doc.metadata) == {
|
|
"id",
|
|
"published_year",
|
|
"title",
|
|
"publication",
|
|
"authors",
|
|
"abstract",
|
|
}
|
|
|
|
|
|
@pytest.mark.requires("fitz", "bibtexparser")
|
|
def test_load_max_content_chars() -> None:
|
|
"""Test that cuts off document contents at max_content_chars."""
|
|
loader = BibtexLoader(file_path=str(BIBTEX_EXAMPLE_FILE), max_content_chars=10)
|
|
doc = loader.load()[0]
|
|
assert len(doc.page_content) == 10
|
|
|
|
|
|
@pytest.mark.requires("fitz", "bibtexparser")
|
|
def test_load_load_extra_metadata() -> None:
|
|
"""Test that returns extra metadata fields."""
|
|
loader = BibtexLoader(file_path=str(BIBTEX_EXAMPLE_FILE), load_extra_metadata=True)
|
|
doc = loader.load()[0]
|
|
assert set(doc.metadata) == {
|
|
"id",
|
|
"published_year",
|
|
"title",
|
|
"publication",
|
|
"authors",
|
|
"abstract",
|
|
"booktitle",
|
|
"editor",
|
|
"organization",
|
|
}
|
|
|
|
|
|
@pytest.mark.requires("fitz", "bibtexparser")
|
|
def test_load_file_pattern() -> None:
|
|
"""Test that returns no documents when json file pattern specified."""
|
|
loader = BibtexLoader(
|
|
file_path=str(BIBTEX_EXAMPLE_FILE), file_pattern=r"[^:]+\.json"
|
|
)
|
|
docs = loader.load()
|
|
assert len(docs) == 0
|