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

chore: format JSON test files to enable comparison (#1511)

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-05-02 11:52:18 +03:00
committed by GitHub
parent b147331f2a
commit de56523974
49 changed files with 2373840 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tests/verify_utils.py
View File

@@ -293,6 +293,7 @@ def verify_conversion_result_v1(
generate: bool = False,
ocr_engine: Optional[str] = None,
fuzzy: bool = False,
indent: int = 2,
):
PageList = TypeAdapter(List[Page])
@@ -323,11 +324,13 @@ def verify_conversion_result_v1(
if generate: # only used when re-generating truth
pages_path.parent.mkdir(parents=True, exist_ok=True)
with open(pages_path, "w") as fw:
fw.write(json.dumps(doc_pred_pages, default=pydantic_encoder))
fw.write(
json.dumps(doc_pred_pages, default=pydantic_encoder, indent=indent)
)
json_path.parent.mkdir(parents=True, exist_ok=True)
with open(json_path, "w") as fw:
fw.write(json.dumps(doc_pred, default=pydantic_encoder))
fw.write(json.dumps(doc_pred, default=pydantic_encoder, indent=indent))
md_path.parent.mkdir(parents=True, exist_ok=True)
with open(md_path, "w") as fw:
@@ -377,6 +380,7 @@ def verify_conversion_result_v2(
generate: bool = False,
ocr_engine: Optional[str] = None,
fuzzy: bool = False,
indent: int = 2,
):
PageList = TypeAdapter(List[Page])
@@ -405,11 +409,13 @@ def verify_conversion_result_v2(
if generate: # only used when re-generating truth
pages_path.parent.mkdir(parents=True, exist_ok=True)
with open(pages_path, "w") as fw:
fw.write(json.dumps(doc_pred_pages, default=pydantic_encoder))
fw.write(
json.dumps(doc_pred_pages, default=pydantic_encoder, indent=indent)
)
json_path.parent.mkdir(parents=True, exist_ok=True)
with open(json_path, "w") as fw:
fw.write(json.dumps(doc_pred, default=pydantic_encoder))
fw.write(json.dumps(doc_pred, default=pydantic_encoder, indent=indent))
md_path.parent.mkdir(parents=True, exist_ok=True)
with open(md_path, "w") as fw: