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

test: avoid testing exact JSON in CSV backend (#1038)

Browse Source 
* feat: updated verify_export
Moved verify_export to verify_utils
Reuse verify_export in tests

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>

* feat: replace verify_export with verify_document in CSV conversion tests

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>

---------

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>
This commit is contained in:
Suehtam
2025-02-24 07:10:40 +00:00
committed by GitHub
parent d8a81c3168
commit 1d17e7397a
7 changed files with 22 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tests/test_backend_csv.py
View File

@@ -8,6 +8,8 @@ from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult, DoclingDocument
from docling.document_converter import DocumentConverter
from .verify_utils import verify_document, verify_export
GENERATE = False
@@ -33,22 +35,6 @@ def get_converter():
return converter
def verify_export(pred_text: str, gtfile: str):
if not os.path.exists(gtfile) or GENERATE:
with open(gtfile, "w") as fw:
fw.write(pred_text)
return True
else:
with open(gtfile, "r") as fr:
true_text = fr.read()
assert pred_text == true_text, "pred_itxt==true_itxt"
return pred_text == true_text
def test_e2e_valid_csv_conversions():
valid_csv_paths = get_csv_paths()
converter = get_converter()
@@ -72,8 +58,7 @@ def test_e2e_valid_csv_conversions():
pred_itxt, str(gt_path) + ".itxt"
), "export to indented-text"
pred_json: str = json.dumps(doc.export_to_dict(), indent=2)
assert verify_export(pred_json, str(gt_path) + ".json"), "export to json"
assert verify_document(doc, str(gt_path) + ".json"), "export to json"
def test_e2e_invalid_csv_conversions():