mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-24 17:30:38 +00:00
9f3b6512be
* whisper transcriber * remove from/to_dict from builders * remove from/to_dict from embedders * remove from/to_dict from fetcher, file_converters * remove from/to_dict from generators, preprocessors * remove from/to_dict from ranker, reader * remove from/to_dict from router, sampler, websearch * pylint * reno * refactor import * remove unused import
48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
import logging
|
|
|
|
import pytest
|
|
|
|
from haystack.preview.components.file_converters.pypdf import PyPDFToDocument
|
|
from haystack.preview.dataclasses import ByteStream
|
|
|
|
|
|
class TestPyPDFToDocument:
|
|
@pytest.mark.unit
|
|
def test_run(self, preview_samples_path):
|
|
"""
|
|
Test if the component runs correctly.
|
|
"""
|
|
paths = [preview_samples_path / "pdf" / "react_paper.pdf"]
|
|
converter = PyPDFToDocument()
|
|
output = converter.run(sources=paths)
|
|
docs = output["documents"]
|
|
assert len(docs) == 1
|
|
assert "ReAct" in docs[0].text
|
|
|
|
@pytest.mark.unit
|
|
def test_run_error_handling(self, preview_samples_path, caplog):
|
|
"""
|
|
Test if the component correctly handles errors.
|
|
"""
|
|
paths = ["non_existing_file.pdf"]
|
|
converter = PyPDFToDocument()
|
|
with caplog.at_level(logging.WARNING):
|
|
converter.run(sources=paths)
|
|
assert "Could not read non_existing_file.pdf" in caplog.text
|
|
|
|
@pytest.mark.unit
|
|
def test_mixed_sources_run(self, preview_samples_path):
|
|
"""
|
|
Test if the component runs correctly when mixed sources are provided.
|
|
"""
|
|
paths = [preview_samples_path / "pdf" / "react_paper.pdf"]
|
|
with open(preview_samples_path / "pdf" / "react_paper.pdf", "rb") as f:
|
|
paths.append(ByteStream(f.read()))
|
|
|
|
converter = PyPDFToDocument()
|
|
output = converter.run(sources=paths)
|
|
docs = output["documents"]
|
|
assert len(docs) == 2
|
|
assert "ReAct" in docs[0].text
|
|
assert "ReAct" in docs[1].text
|