mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-11 14:18:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update examples and test cases

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-09 15:20:27 +02:00
parent 080042d06d
commit 0dfbd0b6fc
25 changed files with 181 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/data/2203.01017v2.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/2206.01062.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/2305.03393v1-pg9.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/2305.03393v1.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/redp5110.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/redp5695.pages.json
View File

File diff suppressed because one or more lines are too long

14
tests/test_e2e_conversion.py
View File

@@ -1,9 +1,10 @@
from pathlib import Path
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, PipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result
@@ -22,14 +23,17 @@ 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

17
tests/test_interfaces.py
View File

@@ -4,10 +4,10 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import DocumentStream
from docling.datamodel.base_models import DocumentStream, InputFormat
from docling.datamodel.document import ConversionResult, DocumentConversionInput
from docling.datamodel.pipeline_options import PipelineOptions
from docling.document_converter import DocumentConverter
from docling.datamodel.pipeline_options import PdfPipelineOptions, PipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result
@@ -21,14 +21,17 @@ 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
@@ -61,7 +64,7 @@ def test_batch_bytes(converter: DocumentConverter):
print(f"converting {pdf_path}")
buf = BytesIO(pdf_path.open("rb").read())
docs = [DocumentStream(filename=pdf_path.name, stream=buf)]
docs = [DocumentStream(name=pdf_path.name, stream=buf)]
conv_input = DocumentConversionInput.from_streams(docs)
results = converter.convert(conv_input)

16
tests/test_options.py
View File

@@ -3,10 +3,10 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import ConversionStatus
from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter
from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter, PdfFormatOption
@pytest.fixture
@@ -17,15 +17,19 @@ def test_doc_path():
def get_converters_with_table_options():
for cell_matching in [True, False]:
for mode in [TableFormerMode.FAST, TableFormerMode.ACCURATE]:
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 = cell_matching
pipeline_options.table_structure_options.mode = mode
converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options,
backend=DoclingParseDocumentBackend,
)
}
)
yield converter