mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-19 22:18:11 +00:00
a59bca3661
* Testing black on ui/ * Applying black on docstores * Add latest docstring and tutorial changes * Create a single GH action for Black and docs to reduce commit noise to the minimum, slightly refactor the OpenAPI action too * Remove comments * Relax constraints on pydoc-markdown * Split temporary black from the docs. Pydoc-markdown was obsolete and needs a separate PR to upgrade * Fix a couple of bugs * Add a type: ignore that was missing somehow * Give path to black * Apply Black * Apply Black * Relocate a couple of type: ignore * Update documentation * Make Linux CI run after applying Black * Triggering Black * Apply Black * Remove dependency, does not work well * Remove manually double trailing commas * Update documentation Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
108 lines
4.2 KiB
Python
108 lines
4.2 KiB
Python
from pathlib import Path
|
|
import os
|
|
|
|
import pytest
|
|
|
|
from haystack.nodes import (
|
|
MarkdownConverter,
|
|
DocxToTextConverter,
|
|
PDFToTextConverter,
|
|
PDFToTextOCRConverter,
|
|
TikaConverter,
|
|
AzureConverter,
|
|
ParsrConverter,
|
|
)
|
|
|
|
from conftest import SAMPLES_PATH
|
|
|
|
|
|
@pytest.mark.tika
|
|
@pytest.mark.parametrize(
|
|
# "Converter", [PDFToTextConverter, TikaConverter, PDFToTextOCRConverter]
|
|
"Converter",
|
|
[PDFToTextOCRConverter],
|
|
)
|
|
def test_convert(Converter):
|
|
converter = Converter()
|
|
document = converter.convert(file_path=SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf")[0]
|
|
pages = document["content"].split("\f")
|
|
assert len(pages) == 4 # the sample PDF file has four pages.
|
|
assert pages[0] != "" # the page 1 of PDF contains text.
|
|
assert pages[2] == "" # the page 3 of PDF file is empty.
|
|
# assert text is retained from the document.
|
|
# As whitespace can differ (\n," ", etc.), we standardize all to simple whitespace
|
|
page_standard_whitespace = " ".join(pages[0].split())
|
|
assert "Adobe Systems made the PDF specification available free of charge in 1993." in page_standard_whitespace
|
|
|
|
|
|
@pytest.mark.tika
|
|
@pytest.mark.parametrize("Converter", [PDFToTextConverter, TikaConverter])
|
|
def test_table_removal(Converter):
|
|
converter = Converter(remove_numeric_tables=True)
|
|
document = converter.convert(file_path=SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf")[0]
|
|
pages = document["content"].split("\f")
|
|
# assert numeric rows are removed from the table.
|
|
assert "324" not in pages[0]
|
|
assert "54x growth" not in pages[0]
|
|
|
|
|
|
@pytest.mark.tika
|
|
@pytest.mark.parametrize("Converter", [PDFToTextConverter, TikaConverter])
|
|
def test_language_validation(Converter, caplog):
|
|
converter = Converter(valid_languages=["en"])
|
|
converter.convert(file_path=SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf")
|
|
assert "samples/pdf/sample_pdf_1.pdf is not one of ['en']." not in caplog.text
|
|
|
|
converter = Converter(valid_languages=["de"])
|
|
converter.convert(file_path=SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf")
|
|
assert "samples/pdf/sample_pdf_1.pdf is not one of ['de']." in caplog.text
|
|
|
|
|
|
def test_docx_converter():
|
|
converter = DocxToTextConverter()
|
|
document = converter.convert(file_path=SAMPLES_PATH / "docx" / "sample_docx.docx")[0]
|
|
assert document["content"].startswith("Sample Docx File")
|
|
|
|
|
|
def test_markdown_converter():
|
|
converter = MarkdownConverter()
|
|
document = converter.convert(file_path=SAMPLES_PATH / "markdown" / "sample.md")[0]
|
|
assert document["content"].startswith("What to build with Haystack")
|
|
|
|
|
|
def test_azure_converter():
|
|
# Check if Form Recognizer endpoint and credential key in environment variables
|
|
if "AZURE_FORMRECOGNIZER_ENDPOINT" in os.environ and "AZURE_FORMRECOGNIZER_KEY" in os.environ:
|
|
converter = AzureConverter(
|
|
endpoint=os.environ["AZURE_FORMRECOGNIZER_ENDPOINT"],
|
|
credential_key=os.environ["AZURE_FORMRECOGNIZER_KEY"],
|
|
save_json=True,
|
|
)
|
|
|
|
docs = converter.convert(file_path=SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf")
|
|
assert len(docs) == 2
|
|
assert docs[0]["content_type"] == "table"
|
|
assert len(docs[0]["content"]) == 5 # number of rows
|
|
assert len(docs[0]["content"][0]) == 5 # number of columns, Form Recognizer assumes there are 5 columns
|
|
assert docs[0]["content"][0] == ["", "Column 1", "", "Column 2", "Column 3"]
|
|
assert docs[0]["content"][4] == ["D", "$54.35", "", "$6345.", ""]
|
|
|
|
assert docs[1]["content_type"] == "text"
|
|
assert docs[1]["content"].startswith("A sample PDF file")
|
|
|
|
|
|
def test_parsr_converter():
|
|
converter = ParsrConverter()
|
|
|
|
docs = converter.convert(file_path=str((SAMPLES_PATH / "pdf" / "sample_pdf_1.pdf").absolute()))
|
|
assert len(docs) == 2
|
|
assert docs[0]["content_type"] == "table"
|
|
assert len(docs[0]["content"]) == 5 # number of rows
|
|
assert len(docs[0]["content"][0]) == 4 # number of columns
|
|
assert docs[0]["content"][0] == ["", "Column 1", "Column 2", "Column 3"]
|
|
assert docs[0]["content"][4] == ["D", "$54.35", "$6345.", ""]
|
|
|
|
assert docs[1]["content_type"] == "text"
|
|
assert docs[1]["content"].startswith("A sample PDF file")
|
|
assert docs[1]["content"].endswith("Page 4 of Sample PDF\n… the page 3 is empty.")
|