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

Change code to use unordered/ordered list, robustifications

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-11 14:53:38 +02:00
parent 3ee97c42b2
commit 95c1f80087
14 changed files with 111 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
tests/data/powerpoint_sample.pptx
View File

Binary file not shown.

2
tests/test_e2e_conversion.py
View File

@@ -3,7 +3,7 @@ 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 PdfPipelineOptions, PipelineOptions
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2

1
tests/test_e2e_ocr_conversion.py
View File

@@ -8,7 +8,6 @@ from docling.datamodel.pipeline_options import (
EasyOcrOptions,
OcrOptions,
PdfPipelineOptions,
PipelineOptions,
TesseractCliOcrOptions,
TesseractOcrOptions,
)

2
tests/test_interfaces.py
View File

@@ -6,7 +6,7 @@ import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import DocumentStream, InputFormat
from docling.datamodel.document import ConversionResult, DocumentConversionInput
from docling.datamodel.pipeline_options import PdfPipelineOptions, PipelineOptions
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2

1
tests/verify_utils.py
View File

@@ -2,7 +2,6 @@ import json
from pathlib import Path
from typing import List
from docling_core.types import BaseText
from docling_core.types import Document as DsDocument
from docling_core.types.experimental import DoclingDocument
from pydantic import TypeAdapter