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 (#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

14
tests/test_backend_patent_uspto.py
View File

@@ -1,6 +1,5 @@
"""Test methods in module docling.backend.patent_uspto_backend.py."""
import json
import logging
import os
from pathlib import Path
@@ -14,6 +13,8 @@ from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend, XmlTab
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument
from .verify_utils import verify_document
GENERATE: bool = False
DATA_PATH: Path = Path("./tests/data/uspto/")
GT_PATH: Path = Path("./tests/data/groundtruth/docling_v2/")
@@ -110,12 +111,11 @@ def test_patent_groundtruth(patents, groundtruth):
assert (
pred_md == gt_names[md_name]
), f"Markdown file mismatch against groundtruth {md_name}"
json_name = path.stem + ".json"
if json_name in gt_names:
pred_json = json.dumps(doc.export_to_dict(), indent=2)
assert (
pred_json == gt_names[json_name]
), f"JSON file mismatch against groundtruth {json_name}"
json_path = path.with_suffix(".json")
if json_path.stem in gt_names:
assert verify_document(
doc, str(json_path), GENERATE
), f"JSON file mismatch against groundtruth {json_path}"
itxt_name = path.stem + ".itxt"
if itxt_name in gt_names:
pred_itxt = doc._export_to_indented_text()