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: add options for choosing OCR engines (#118)

Browse Source 
---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2024-10-08 19:07:08 +02:00
committed by GitHub
parent d412c363d7
commit f96ea86a00
20 changed files with 699 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/verify_utils.py
View File

@@ -130,7 +130,11 @@ def verify_dt(doc_pred_dt, doc_true_dt):
def verify_conversion_result(
input_path: Path, doc_result: ConversionResult, generate=False
input_path: Path,
doc_result: ConversionResult,
generate: bool = False,
ocr_engine: str = None,
skip_cells: bool = False,
):
PageList = TypeAdapter(List[Page])
@@ -143,10 +147,11 @@ def verify_conversion_result(
doc_pred_md = doc_result.render_as_markdown()
doc_pred_dt = doc_result.render_as_doctags()
pages_path = input_path.with_suffix(".pages.json")
json_path = input_path.with_suffix(".json")
md_path = input_path.with_suffix(".md")
dt_path = input_path.with_suffix(".doctags.txt")
engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"
pages_path = input_path.with_suffix(f"{engine_suffix}.pages.json")
json_path = input_path.with_suffix(f"{engine_suffix}.json")
md_path = input_path.with_suffix(f"{engine_suffix}.md")
dt_path = input_path.with_suffix(f"{engine_suffix}.doctags.txt")
if generate: # only used when re-generating truth
with open(pages_path, "w") as fw:
@@ -173,9 +178,10 @@ def verify_conversion_result(
with open(dt_path, "r") as fr:
doc_true_dt = fr.read()
assert verify_cells(
doc_pred_pages, doc_true_pages
), f"Mismatch in PDF cell prediction for {input_path}"
if not skip_cells:
assert verify_cells(
doc_pred_pages, doc_true_pages
), f"Mismatch in PDF cell prediction for {input_path}"
# assert verify_output(
# doc_pred, doc_true