mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

test: avoid testing exact JSON (#1027)

Browse Source 
* test: avoid testing exact JSON

Avoid testing exact JSON output in html and xml backends.
Reuse the JSON verify helper function among backend test files.
Improve type annotations in html backend.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* Update tests/test_backend_patent_uspto.py

Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

---------

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-02-20 16:20:07 +01:00
committed by GitHub
parent 6796f0a132
commit 1ac010354f
8 changed files with 54 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tests/test_backend_msword.py
View File

@@ -1,4 +1,3 @@
import json
import os
from pathlib import Path
@@ -12,7 +11,7 @@ from docling.datamodel.document import (
)
from docling.document_converter import DocumentConverter
from .verify_utils import verify_docitems
from .verify_utils import verify_document
GENERATE = False
@@ -74,20 +73,6 @@ def verify_export(pred_text: str, gtfile: str):
return pred_text == true_text
def verify_document(pred_doc: DoclingDocument, gtfile: str):
if not os.path.exists(gtfile) or GENERATE:
with open(gtfile, "w") as fw:
json.dump(pred_doc.export_to_dict(), fw, indent=2)
return True
else:
with open(gtfile, "r") as fr:
true_doc = DoclingDocument.model_validate_json(fr.read())
return verify_docitems(pred_doc, true_doc, fuzzy=False)
def test_e2e_docx_conversions():
docx_paths = get_docx_paths()
@@ -114,7 +99,9 @@ def test_e2e_docx_conversions():
pred_itxt, str(gt_path) + ".itxt"
), "export to indented-text"
assert verify_document(doc, str(gt_path) + ".json"), "document document"
assert verify_document(
doc, str(gt_path) + ".json", GENERATE
), "document document"
if docx_path.name == "word_tables.docx":
pred_html: str = doc.export_to_html()