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

chore: fix or ignore runtime and deprecation warnings (#1660)

Browse Source 
* chore: fix or catch deprecation warnings

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

* chore: update poetry lock with latest docling-core

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

---------

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-05-28 17:55:31 +02:00
committed by GitHub
parent b3e0042813
commit 3942923125
7 changed files with 116 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/test_backend_csv.py
View File

@@ -39,8 +39,15 @@ def test_e2e_valid_csv_conversions():
print(f"converting {csv_path}")
gt_path = csv_path.parent.parent / "groundtruth" / "docling_v2" / csv_path.name
conv_result: ConversionResult = converter.convert(csv_path)
if csv_path.stem in (
"csv-too-few-columns",
"csv-too-many-columns",
"csv-inconsistent-header",
):
with warns(UserWarning, match="Inconsistent column lengths"):
conv_result: ConversionResult = converter.convert(csv_path)
else:
conv_result: ConversionResult = converter.convert(csv_path)
doc: DoclingDocument = conv_result.document

14
tests/test_legacy_format_transform.py
View File

@@ -38,17 +38,15 @@ def get_converter():
def test_compare_legacy_output(test_doc_paths):
converter = get_converter()
res = converter.convert_all(test_doc_paths, raises_on_error=True)
for conv_res in res:
print(f"Results for {conv_res.input.file}")
print(
json.dumps(
conv_res.legacy_document.model_dump(
mode="json", by_alias=True, exclude_none=True
with pytest.warns(DeprecationWarning, match="Use document instead"):
print(
json.dumps(
conv_res.legacy_document.model_dump(
mode="json", by_alias=True, exclude_none=True
)
)
)
)
# assert res.legacy_output == res.legacy_output_transformed

8
tests/verify_utils.py
View File

@@ -4,6 +4,7 @@ import warnings
from pathlib import Path
from typing import List, Optional
import pytest
from docling_core.types.doc import (
DocItem,
DoclingDocument,
@@ -302,9 +303,8 @@ def verify_conversion_result_v1(
)
doc_pred_pages: List[Page] = doc_result.pages
doc_pred: DsDocument = doc_result.legacy_document
with warnings.catch_warnings():
warnings.simplefilter("ignore", DeprecationWarning)
with pytest.warns(DeprecationWarning, match="Use document instead"):
doc_pred: DsDocument = doc_result.legacy_document
doc_pred_md = doc_result.legacy_document.export_to_markdown()
doc_pred_dt = doc_result.legacy_document.export_to_document_tokens()
@@ -391,7 +391,7 @@ def verify_conversion_result_v2(
doc_pred_pages: List[Page] = doc_result.pages
doc_pred: DoclingDocument = doc_result.document
doc_pred_md = doc_result.document.export_to_markdown()
doc_pred_dt = doc_result.document.export_to_document_tokens()
doc_pred_dt = doc_result.document.export_to_doctags()
engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"