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

More renaming, design enrichment interface

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-11 10:21:31 +02:00
parent 051beae203
commit 304d16029a
17 changed files with 85 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/test_e2e_ocr_conversion.py
View File

@@ -39,11 +39,11 @@ def save_output(pdf_path: Path, doc_result: ConversionResult, engine: str):
doctags_fn = os.path.join(parent, f"{pdf_path.stem}{eng}.doctags.txt")
with open(doctags_fn, "w") as fd:
fd.write(doc_result.render_as_doctags_v1())
fd.write(doc_result.render_as_doctags())
md_fn = os.path.join(parent, f"{pdf_path.stem}{eng}.md")
with open(md_fn, "w") as fd:
fd.write(doc_result.render_as_markdown_v1())
fd.write(doc_result.render_as_markdown())
def get_pdf_paths():

4
tests/test_interfaces.py
View File

@@ -54,7 +54,7 @@ def test_batch_path(converter: DocumentConverter):
conv_input = DocumentConversionInput.from_paths([pdf_path])
results = converter.convert(conv_input)
results = converter.convert_batch(conv_input)
for doc_result in results:
verify_conversion_result_v1(input_path=pdf_path, doc_result=doc_result)
verify_conversion_result_v2(input_path=pdf_path, doc_result=doc_result)
@@ -69,7 +69,7 @@ def test_batch_bytes(converter: DocumentConverter):
docs = [DocumentStream(name=pdf_path.name, stream=buf)]
conv_input = DocumentConversionInput.from_streams(docs)
results = converter.convert(conv_input)
results = converter.convert_batch(conv_input)
for doc_result in results:
verify_conversion_result_v1(input_path=pdf_path, doc_result=doc_result)
verify_conversion_result_v2(input_path=pdf_path, doc_result=doc_result)

4
tests/verify_utils.py
View File

@@ -198,8 +198,8 @@ def verify_conversion_result_v1(
doc_pred_pages: List[Page] = doc_result.pages
doc_pred: DsDocument = doc_result.legacy_output
doc_pred_md = doc_result.render_as_markdown_v1()
doc_pred_dt = doc_result.render_as_doctags_v1()
doc_pred_md = doc_result.render_as_markdown()
doc_pred_dt = doc_result.render_as_doctags()
engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"
gt_subpath = input_path.parent / "groundtruth" / "docling_v1" / input_path.name