PaddleOCR/tests/pipelines/test_formula_recognition.py
Lin Manhui 3d03ca5500
[Breaking][Feat] New PaddleOCR inference package (#15046)
* Init new paddleocr

* Remove unused dependency

* Fix typos

* Fix

* Add doc understanding modules

* Fix package finding

* Normalize name

* Fix setting bugs

* Fix setting bug

* Support single model inference

* Add PP-ChatOCRv4-doc

* Add pp_chatocrv4_doc tests

* Enable MKL-DNN when available

* add seal_text_detection modules

* add layout_detection and table_cells_detection modules

* add testing scripts

* Fix desc

* add text_image_unwarping and table_structure_recognition modules

* add formula_recognition and doc_vlm modules

* update formula_recognition default_model_name

* add MKLDNN_BLOCKLIST

* update MKLDNN log

* add seal rec pipeline

* fix sth

* fix sth

* add doc preprocessor pipeline

* fix sth

* add doc understanding

* add table_rec_v2, ppstructurev3, formula_rec pipelines

* move test files

* forward kwargs to pipeline.predict

* clean test files

* Add missing kwargs

* Fix typo

* Fix typo

* rerun CI

* update mkldnn BLOCKLIST

* update

* update warning message

* fix cli args

* update PIPELINE_MKLDNN_BLOCKLIST

* update  of  workflow

* skip resource_intensive tests

* update config

* skip ppdocbee test_predict_params

---------

Co-authored-by: zhangyue66 <zhangyue66@baidu.com>
Co-authored-by: zhangzelun <zhangzelun@baidu.com>
2025-05-04 15:59:02 +08:00

69 lines
1.7 KiB
Python

import pytest
from paddleocr import FormulaRecognitionPipeline
from ..testing_utils import (
TEST_DATA_DIR,
check_simple_inference_result,
check_wrapper_simple_inference_param_forwarding,
)
@pytest.fixture(scope="module")
def formula_recognition_engine() -> FormulaRecognitionPipeline:
return FormulaRecognitionPipeline()
# TODO: Should we separate unit tests and integration tests?
@pytest.mark.parametrize(
"image_path",
[
TEST_DATA_DIR / "doc_with_formula.png",
],
)
def test_predict(
formula_recognition_engine: FormulaRecognitionPipeline, image_path: str
) -> None:
"""
Test FormulaRecognitionPipeline's formula_recognition functionality.
Args:
formula_recognition_engine: An instance of `FormulaRecognitionPipeline`.
image_path: Path to the image to be processed.
"""
result = formula_recognition_engine.predict(str(image_path))
check_simple_inference_result(result)
res = result[0]
assert isinstance(res["formula_res_list"], list)
assert len(res["formula_res_list"]) > 0
# TODO: Also check passing `None`
@pytest.mark.parametrize(
"params",
[
{"use_doc_orientation_classify": False},
{"use_doc_unwarping": False},
{"use_layout_detection": False},
{"layout_threshold": 0.5},
{"layout_nms": True},
{"layout_unclip_ratio": 1.5},
{"layout_merge_bboxes_mode": "large"},
],
)
def test_predict_params(
monkeypatch,
formula_recognition_engine: FormulaRecognitionPipeline,
params: dict,
) -> None:
check_wrapper_simple_inference_param_forwarding(
monkeypatch,
formula_recognition_engine,
"paddlex_pipeline",
"dummy_path",
params,
)
# TODO: Test init params