mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-29 20:00:46 +00:00
834f8c4902
* Change return types of file converters * Change return types of preprocessor * Change return types of crawler * Adapt utils to functions to new return types * Adapt __init__.py to new method names * Prevent circular imports * Update Documentation & Code Style * Let DocStores' run method accept Documents * Adapt tests to new return types * Update Documentation & Code Style * Put "# type: ignore" to right place * Remove id_hash_keys property from Document primitive * Update Documentation & Code Style * Adapt tests to new return types and missing id_hash_keys property * Fix mypy * Fix mypy * Adapt PDFToTextOCRConverter * Remove id_hash_keys from RestAPI tests * Update Documentation & Code Style * Rename tests * Remove redundant setting of content_type="text" * Add DeprecationWarning * Add id_hash_keys to elasticsearch_index_to_document_store * Change document type from dict to Docuemnt in PreProcessor test * Fix file path in Tutorial 5 * Remove added output in Tutorial 5 * Update Documentation & Code Style * Fix file_paths in Tutorial 9 + fix gz files in fetch_archive_from_http * Adapt tutorials to new return types * Adapt tutorial 14 to new return types * Update Documentation & Code Style * Change assertions to HaystackErrors * Import HaystackError correctly Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
122 lines
4.9 KiB
Python
122 lines
4.9 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 docs[0].content.shape[0] == 4 # number of rows
|
|
assert docs[0].content.shape[1] == 5 # number of columns, Form Recognizer assumes there are 5 columns
|
|
assert list(docs[0].content.columns) == ["", "Column 1", "", "Column 2", "Column 3"]
|
|
assert list(docs[0].content.iloc[3]) == ["D", "$54.35", "", "$6345.", ""]
|
|
assert (
|
|
docs[0].meta["preceding_context"] == "specification. These proprietary technologies are not "
|
|
"standardized and their\nspecification is published only on "
|
|
"Adobe's website. Many of them are also not\nsupported by "
|
|
"popular third-party implementations of PDF."
|
|
)
|
|
assert docs[0].meta["following_context"] == ""
|
|
|
|
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 docs[0].content.shape[0] == 4 # number of rows
|
|
assert docs[0].content.shape[1] == 4
|
|
assert list(docs[0].content.columns) == ["", "Column 1", "Column 2", "Column 3"]
|
|
assert list(docs[0].content.iloc[3]) == ["D", "$54.35", "$6345.", ""]
|
|
assert (
|
|
docs[0].meta["preceding_context"] == "specification. These proprietary technologies are not "
|
|
"standardized and their\nspecification is published only on "
|
|
"Adobe's website. Many of them are also not\nsupported by popular "
|
|
"third-party implementations of PDF."
|
|
)
|
|
assert docs[0].meta["following_context"] == ""
|
|
|
|
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.")
|