feat!: Docling v2 (#117)

---------

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

View File

@@ -1,13 +1,18 @@
from pathlib import Path
import yaml
from docling_core.types.doc import DoclingDocument
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 PipelineOptions
from docling.document_converter import DocumentConverter
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 = False
GENERATE_V1 = False
GENERATE_V2 = False
def get_pdf_paths():
@@ -22,14 +27,17 @@ def get_pdf_paths():
def get_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
@@ -43,8 +51,12 @@ def test_e2e_conversions():
for pdf_path in pdf_paths:
print(f"converting {pdf_path}")
doc_result: ConversionResult = converter.convert_single(pdf_path)
doc_result: ConversionResult = converter.convert(pdf_path)
verify_conversion_result(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
verify_conversion_result_v1(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE_V1
)
verify_conversion_result_v2(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE_V2
)