Docling/tests/test_document_picture_classifier.py
Christoph Auer 3960b199d6
feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905)
* Add DoclingParseV3 backend implementation

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Use docling-core with docling-parse types

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes and test updates

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix streams

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix streams

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Reset tests

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test units

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add back DoclingParse v1 backend, pipeline options

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update locks

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update docling-core to 2.22.0

Update dependency library docling-core to latest release 2.22.0
Fix regression tests and ground truth files

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* Ground-truth files updated

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update tests, use TextCell.from_ocr property

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Text fixes, new test data

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Rename docling backend to v4

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Test all backends, fixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Reset all tests to use docling-parse v1 for now

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for DPv4 backend init, better test coverage

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* test_input_doc use default backend

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-03-18 10:38:19 +01:00

81 lines
2.9 KiB
Python

from pathlib import Path
from docling_core.types.doc import PictureClassificationData
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
def get_converter():
pipeline_options = PdfPipelineOptions()
pipeline_options.generate_page_images = True
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = False
pipeline_options.do_code_enrichment = False
pipeline_options.do_formula_enrichment = False
pipeline_options.do_picture_classification = True
pipeline_options.generate_picture_images = True
pipeline_options.images_scale = 2
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfPipeline,
pipeline_options=pipeline_options,
)
}
)
return converter
def test_picture_classifier():
pdf_path = Path("tests/data/pdf/picture_classification.pdf")
converter = get_converter()
print(f"converting {pdf_path}")
doc_result: ConversionResult = converter.convert(pdf_path)
results = doc_result.document.pictures
assert len(results) == 2
res = results[0]
assert len(res.annotations) == 1
assert type(res.annotations[0]) == PictureClassificationData
classification_data = res.annotations[0]
assert classification_data.provenance == "DocumentPictureClassifier"
assert (
len(classification_data.predicted_classes) == 16
), "Number of predicted classes is not equal to 16"
confidences = [pred.confidence for pred in classification_data.predicted_classes]
assert confidences == sorted(
confidences, reverse=True
), "Predictions are not sorted in descending order of confidence"
assert (
classification_data.predicted_classes[0].class_name == "bar_chart"
), "The prediction is wrong for the bar chart image."
res = results[1]
assert len(res.annotations) == 1
assert type(res.annotations[0]) == PictureClassificationData
classification_data = res.annotations[0]
assert classification_data.provenance == "DocumentPictureClassifier"
assert (
len(classification_data.predicted_classes) == 16
), "Number of predicted classes is not equal to 16"
confidences = [pred.confidence for pred in classification_data.predicted_classes]
assert confidences == sorted(
confidences, reverse=True
), "Predictions are not sorted in descending order of confidence"
assert (
classification_data.predicted_classes[0].class_name == "map"
), "The prediction is wrong for the bar chart image."