📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
fix(rapidocr_web): Fixed issue #197
SWHLd2f369223d61
diff --git a/ocrweb/rapidocr_web/ocrweb.py b/ocrweb/rapidocr_web/ocrweb.pyindex 45825e7..afc669d 100644--- a/ocrweb/rapidocr_web/ocrweb.py+++ b/ocrweb/rapidocr_web/ocrweb.py@@ -38,7 +38,7 @@ def main():parser.add_argument("-p", "--port", type=int, default=9003, help="IP port")args = parser.parse_args()- print(f"Successfully launched and visit https://{args.ip}:{args.port} to view.")+ print(f"Successfully launched and visit http://{args.ip}:{args.port} to view.")server = make_server(args.ip, args.port, app)server.serve_forever()diff --git a/ocrweb/rapidocr_web/task.py b/ocrweb/rapidocr_web/task.pyindex 20cc78e..73c2b67 100644--- a/ocrweb/rapidocr_web/task.py+++ b/ocrweb/rapidocr_web/task.py@@ -13,69 +13,78 @@ import numpy as npfrom rapidocr_onnxruntime import RapidOCR-class OCRWebUtils():+class OCRWebUtils:def __init__(self) -> None:self.ocr = RapidOCR()self.WebReturn = namedtuple(- 'WebReturn',- ['image', 'total_elapse', 'elapse_part', 'rec_res', 'det_boxes'])+ "WebReturn",+ ["image", "total_elapse", "elapse_part", "rec_res", "det_boxes"],+ )def __call__(self, img_content: str) -> namedtuple:if img_content is None:- raise ValueError('img is None')+ raise ValueError("img is None")img = self.prepare_img(img_content)ocr_res, elapse = self.ocr(img)return self.get_web_result(img, ocr_res, elapse)def prepare_img(self, img_str: str) -> np.ndarray:- img_str = img_str.split(',')[1]- image = base64.b64decode(img_str + '=' * (-len(img_str) % 4))+ img_str = img_str.split(",")[1]+ image = base64.b64decode(img_str + "=" * (-len(img_str) % 4))nparr = np.frombuffer(image, np.uint8)image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)if image.ndim == 2:image = cv2.cvtColor(image, cv2.COLOR_GRAY2BGR)return image- def get_web_result(self,- img: np.ndarray,- ocr_res: List,- elapse: List) -> Tuple[Union[str, List, str, str]]:+ def get_web_result(+ self, img: np.ndarray, ocr_res: List, elapse: List+ ) -> Tuple[Union[str, List, str, str]]:if ocr_res is None:- total_elapse, elapse_part = 0, ''+ total_elapse, elapse_part = 0, ""img_str = self.img_to_base64(img)rec_res = json.dumps([], indent=2, ensure_ascii=False)- boxes = ''+ boxes = ""else:boxes, txts, scores = list(zip(*ocr_res))+ scores = [f"{v:.4f}" for v in scores]rec_res = list(zip(range(len(txts)), txts, scores))rec_res = json.dumps(rec_res, indent=2, ensure_ascii=False)det_im = self.draw_text_det_res(np.array(boxes), img)img_str = self.img_to_base64(det_im)- total_elapse = reduce(lambda x, y: float(x)+float(y), elapse)- elapse_part = ','.join([f'{x:.4f}' for x in elapse])+ total_elapse = reduce(lambda x, y: float(x) + float(y), elapse)+ elapse_part = ",".join([f"{x:.4f}" for x in elapse])- web_return = self.WebReturn(image=img_str,- total_elapse=f'{total_elapse:.4f}',- elapse_part=elapse_part,- rec_res=rec_res,- det_boxes=boxes)+ web_return = self.WebReturn(+ image=img_str,+ total_elapse=f"{total_elapse:.4f}",+ elapse_part=elapse_part,+ rec_res=rec_res,+ det_boxes=boxes,+ )return json.dumps(web_return._asdict())@staticmethoddef img_to_base64(img) -> str:- img = cv2.imencode('.png', img)[1]+ img = cv2.imencode(".png", img)[1]img_str = str(base64.b64encode(img))[2:-1]return img_str@staticmethod- def draw_text_det_res(dt_boxes: np.ndarray,- raw_im: np.ndarray) -> np.ndarray:+ def draw_text_det_res(dt_boxes: np.ndarray, raw_im: np.ndarray) -> np.ndarray:src_im = copy.deepcopy(raw_im)for i, box in enumerate(dt_boxes):box = np.array(box).astype(np.int32).reshape(-1, 2)cv2.polylines(src_im, [box], True, color=(0, 0, 255), thickness=1)- cv2.putText(src_im, str(i), (int(box[0][0]), int(box[0][1])),- cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)+ cv2.putText(+ src_im,+ str(i),+ (int(box[0][0]), int(box[0][1])),+ cv2.FONT_HERSHEY_SIMPLEX,+ 0.5,+ (0, 0, 0),+ 2,+ )return src_imdiff --git a/ocrweb/requirements.txt b/ocrweb/requirements.txtindex 7b13fb3..67915c6 100644--- a/ocrweb/requirements.txt+++ b/ocrweb/requirements.txt@@ -1,6 +1,6 @@-Pillow+Pillow<=10.0.0requests-Flask>=2.1.0-rapidocr_onnxruntime+Flask>=2.1.0, <=3.0.0+rapidocr_onnxruntime>=1.3.0,<=2.0.0get_pypi_latest_versionwheeldiff --git a/ocrweb/setup.py b/ocrweb/setup.pyindex 52466c3..e8c3b6f 100644--- a/ocrweb/setup.py+++ b/ocrweb/setup.py@@ -10,13 +10,13 @@ from get_pypi_latest_version import GetPyPiLatestVersiondef get_readme():root_dir = Path(__file__).resolve().parent.parent- readme_path = str(root_dir / 'docs' / 'doc_whl_rapidocr_web.md')- with open(readme_path, 'r', encoding='utf-8') as f:+ readme_path = str(root_dir / "docs" / "doc_whl_rapidocr_web.md")+ with open(readme_path, "r", encoding="utf-8") as f:readme = f.read()return readme-MODULE_NAME = 'rapidocr_web'+MODULE_NAME = "rapidocr_web"obtainer = GetPyPiLatestVersion()latest_version = obtainer(MODULE_NAME)@@ -24,7 +24,7 @@ VERSION_NUM = obtainer.version_add_one(latest_version)# 优先提取commit message中的语义化版本号,如无,则自动加1if len(sys.argv) > 2:- match_str = ' '.join(sys.argv[2:])+ match_str = " ".join(sys.argv[2:])matched_versions = obtainer.extract_version(match_str)if matched_versions:VERSION_NUM = matched_versions@@ -33,37 +33,40 @@ sys.argv = sys.argv[:2]setuptools.setup(name=MODULE_NAME,version=VERSION_NUM,- platforms='Any',- description='A cross platform OCR Library based on OnnxRuntime.',+ platforms="Any",+ description="A cross platform OCR Library based on OnnxRuntime.",long_description=get_readme(),- long_description_content_type='text/markdown',- author='SWHL',- author_email='[email protected]',- url='https://github.com/RapidAI/RapidOCR',- download_url='https://github.com/RapidAI/RapidOCR.git',- license='Apache-2.0',+ long_description_content_type="text/markdown",+ author="SWHL",+ author_email="[email protected]",+ url="https://github.com/RapidAI/RapidOCR",+ download_url="https://github.com/RapidAI/RapidOCR.git",+ license="Apache-2.0",include_package_data=True,- install_requires=['requests', 'Flask>=2.1.0', 'rapidocr_onnxruntime'],- packages=[MODULE_NAME,- f'{MODULE_NAME}.static.css',- f'{MODULE_NAME}.static.js',- f'{MODULE_NAME}.templates'],- package_data={'': ['*.ico', '*.css', '*.js', '*.html']},+ install_requires=["requests", "Flask>=2.1.0", "rapidocr_onnxruntime"],+ packages=[+ MODULE_NAME,+ f"{MODULE_NAME}.static.css",+ f"{MODULE_NAME}.static.js",+ f"{MODULE_NAME}.templates",+ ],+ package_data={"": ["*.ico", "*.css", "*.js", "*.html"]},keywords=[- 'ocr,text_detection,text_recognition,db,onnxruntime,paddleocr,openvino,rapidocr'+ "ocr,text_detection,text_recognition,db,onnxruntime,paddleocr,openvino,rapidocr"],classifiers=[- 'Programming Language :: Python :: 3.6',- 'Programming Language :: Python :: 3.7',- 'Programming Language :: Python :: 3.8',- 'Programming Language :: Python :: 3.9',- 'Programming Language :: Python :: 3.10',- 'Programming Language :: Python :: 3.11',+ "Programming Language :: Python :: 3.6",+ "Programming Language :: Python :: 3.7",+ "Programming Language :: Python :: 3.8",+ "Programming Language :: Python :: 3.9",+ "Programming Language :: Python :: 3.10",+ "Programming Language :: Python :: 3.11",+ "Programming Language :: Python :: 3.12",],- python_requires='>=3.6,<3.12',+ python_requires=">=3.6,<3.13",entry_points={- 'console_scripts': [- f'{MODULE_NAME}={MODULE_NAME}.ocrweb:main',+ "console_scripts": [+ f"{MODULE_NAME}={MODULE_NAME}.ocrweb:main",],},)