docling/tests/test_legacy_format_transform.py
Peter W. J. Staar f542460af3
fix: fix duplicate title and heading + add e2e tests for html and docx (#186)
* add real e2e tests for html and docx

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the output of itxt

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* reformatted the text

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests (2)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the examples (1)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the output of the test

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the tests, moved the ground-truth

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* moved the ground-truth data

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the html tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* restructure title fix (#187)

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-30 13:14:56 +01:00

53 lines
1.4 KiB
Python

import json
from pathlib import Path
import pytest
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
@pytest.fixture
def test_doc_paths():
return [
Path("tests/data/html/wiki_duck.html"),
Path("tests/data/docx/word_sample.docx"),
Path("tests/data/docx/lorem_ipsum.docx"),
Path("tests/data/pptx/powerpoint_sample.pptx"),
Path("tests/data/2305.03393v1-pg9-img.png"),
Path("tests/data/2206.01062.pdf"),
]
def get_converter():
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = False
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
}
)
return converter
def test_compare_legacy_output(test_doc_paths):
converter = get_converter()
res = converter.convert_all(test_doc_paths, raises_on_error=True)
for conv_res in res:
print(f"Results for {conv_res.input.file}")
print(
json.dumps(
conv_res.legacy_document.model_dump(
mode="json", by_alias=True, exclude_none=True
)
)
)
# assert res.legacy_output == res.legacy_output_transformed