mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat!: Docling v2 (#117)

Browse Source 
---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-10-16 21:02:03 +02:00
committed by GitHub
parent d504432c1e
commit 7d3be0edeb
144 changed files with 15180 additions and 3828 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
tests/test_interfaces.py
View File

@@ -4,13 +4,13 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import DocumentStream
from docling.datamodel.document import ConversionResult, DocumentConversionInput
from docling.datamodel.pipeline_options import PipelineOptions
from docling.document_converter import DocumentConverter
from docling.datamodel.base_models import DocumentStream, InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
GENERATE = True
def get_pdf_path():
@@ -22,49 +22,48 @@ def get_pdf_path():
@pytest.fixture
def converter():
pipeline_options = PipelineOptions()
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options, backend=DoclingParseDocumentBackend
)
}
)
return converter
def test_convert_single(converter: DocumentConverter):
def test_convert_path(converter: DocumentConverter):
pdf_path = get_pdf_path()
print(f"converting {pdf_path}")
doc_result: ConversionResult = converter.convert_single(pdf_path)
verify_conversion_result(input_path=pdf_path, doc_result=doc_result)
doc_result = converter.convert(pdf_path)
verify_conversion_result_v1(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
)
verify_conversion_result_v2(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
)
def test_batch_path(converter: DocumentConverter):
pdf_path = get_pdf_path()
print(f"converting {pdf_path}")
conv_input = DocumentConversionInput.from_paths([pdf_path])
results = converter.convert(conv_input)
for doc_result in results:
verify_conversion_result(input_path=pdf_path, doc_result=doc_result)
def test_batch_bytes(converter: DocumentConverter):
def test_convert_stream(converter: DocumentConverter):
pdf_path = get_pdf_path()
print(f"converting {pdf_path}")
buf = BytesIO(pdf_path.open("rb").read())
docs = [DocumentStream(filename=pdf_path.name, stream=buf)]
conv_input = DocumentConversionInput.from_streams(docs)
stream = DocumentStream(name=pdf_path.name, stream=buf)
results = converter.convert(conv_input)
for doc_result in results:
verify_conversion_result(input_path=pdf_path, doc_result=doc_result)
doc_result = converter.convert(stream)
verify_conversion_result_v1(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
)
verify_conversion_result_v2(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
)