diff --git a/.github/workflows/gen_whl_to_pypi_rapid_layout.yml b/.github/workflows/gen_whl_to_pypi_rapid_layout.yml index f4cfb49..9028515 100644 --- a/.github/workflows/gen_whl_to_pypi_rapid_layout.yml +++ b/.github/workflows/gen_whl_to_pypi_rapid_layout.yml @@ -73,7 +73,7 @@ jobs: wget https://github.com/RapidAI/RapidOCR/releases/download/v1.1.0/rapid_layout_models.zip unzip rapid_layout_models.zip mv rapid_layout_models/*.onnx rapid_layout/models/ - python setup_layout.py bdist_wheel + python setup_layout.py bdist_wheel ${{ github.event.head_commit.message }} # - name: Publish distribution 📦 to Test PyPI # uses: pypa/gh-action-pypi-publish@v1.5.0 diff --git a/docs/doc_whl_rapid_layout.md b/docs/doc_whl_rapid_layout.md index 506f17a..29f40cf 100644 --- a/docs/doc_whl_rapid_layout.md +++ b/docs/doc_whl_rapid_layout.md @@ -7,7 +7,7 @@ ### 1. Install package by pypi. ```bash -$ pip install rapidocr-layout +$ pip install rapid-layout ``` ### 2. Run by script. diff --git a/docs/doc_whl_rapid_table.md b/docs/doc_whl_rapid_table.md index db95c31..6534b24 100644 --- a/docs/doc_whl_rapid_table.md +++ b/docs/doc_whl_rapid_table.md @@ -6,24 +6,28 @@ ### 1. Install package by pypi. ```bash -$ pip install rapidocr-table +$ pip install rapid-table ``` ### 2. Run by script. +- RapidTable has the default `model_path` value, you can set the different value of `model_path` to use different models, e.g. `table_engine = RapidTable(model_path='ch_ppstructure_mobile_v2_SLANet.onnx')` +- See details, for [README_Table](https://github.com/RapidAI/RapidOCR/blob/a87133a6fc3b8ee696e246028e529f7b2319d138/python/rapid_structure/docs/README_Table.md) . +- 📌 `table.jpg` source: [link](https://github.com/RapidAI/RapidOCR/blob/a87133a6fc3b8ee696e246028e529f7b2319d138/python/rapid_structure/test_images/table.jpg) + ```python import cv2 from rapid_table import RapidTable -rapid_table = RapidTable() +table_engine = RapidTable() -img = cv2.imread('test_images/table.jpg') -table_html_str, _ = rapid_table(img) +img = cv2.imread('table.jpg') +table_html_str, _ = table_engine(img) print(table_html_str) ``` ### 3. Run by command line. ```bash -$ rapid_table --img_path test_images/table.jpg +$ rapid_table -v -img table.jpg ``` ### 4. Result. diff --git a/python/rapid_structure/docs/README_Layout.md b/python/rapid_structure/docs/README_Layout.md index 0af0662..008c429 100644 --- a/python/rapid_structure/docs/README_Layout.md +++ b/python/rapid_structure/docs/README_Layout.md @@ -40,22 +40,22 @@ 3. 终端运行 - 用法: - ```bash - $ rapid_layout -h - usage: rapid_layout [-h] [-v] -img IMG_PATH [-m MODEL_PATH] + ```bash + $ rapid_layout -h + usage: rapid_layout [-h] [-v] -img IMG_PATH [-m MODEL_PATH] - optional arguments: - -h, --help show this help message and exit - -v, --vis Wheter to visualize the layout results. - -img IMG_PATH, --img_path IMG_PATH - Path to image for layout. - -m MODEL_PATH, --model_path MODEL_PATH - The model path used for inference. - ``` + optional arguments: + -h, --help show this help message and exit + -v, --vis Wheter to visualize the layout results. + -img IMG_PATH, --img_path IMG_PATH + Path to image for layout. + -m MODEL_PATH, --model_path MODEL_PATH + The model path used for inference. + ``` - 示例: - ```bash - $ rapid_layout -v -img layout.png - ``` + ```bash + $ rapid_layout -v -img test_images/layout.png + ``` 4. 结果 - 返回结果 diff --git a/python/rapid_structure/docs/README_Table.md b/python/rapid_structure/docs/README_Table.md index 1e1f97f..8a3b0e9 100644 --- a/python/rapid_structure/docs/README_Table.md +++ b/python/rapid_structure/docs/README_Table.md @@ -28,17 +28,33 @@ import cv2 from rapid_table import RapidTable - rapid_table = RapidTable() + # RapidTable类提供model_path参数，可以自行指定上述2个模型，默认是en_ppstructure_mobile_v2_SLANet.onnx + # table_engine = RapidTable(model_path='ch_ppstructure_mobile_v2_SLANet.onnx') + table_engine = RapidTable() img = cv2.imread('test_images/table.jpg') - table_html_str, _ = rapid_table(img) + table_html_str, _ = table_engine(img) print(table_html_str) ``` 3. 终端运行 - ```bash - # 假设在rapid_structure目录下 - $ rapid_table --img_path test_images/table.jpg - ``` + - 用法: + ```bash + $ rapid_table -h + usage: rapid_table [-h] [-v] -img IMG_PATH [-m MODEL_PATH] + + optional arguments: + -h, --help show this help message and exit + -v, --vis Wheter to visualize the layout results. + -img IMG_PATH, --img_path IMG_PATH + Path to image for layout. + -m MODEL_PATH, --model_path MODEL_PATH + The model path used for inference. + ``` + - 示例: + ```bash + $ rapid_table -v -img test_images/table.jpg + ``` + 4. 结果 - 返回结果 ```html diff --git a/python/rapid_structure/rapid_layout/rapid_layout.py b/python/rapid_structure/rapid_layout/rapid_layout.py index 9c6319e..41fc71f 100644 --- a/python/rapid_structure/rapid_layout/rapid_layout.py +++ b/python/rapid_structure/rapid_layout/rapid_layout.py @@ -83,10 +83,10 @@ def main(): help='The model path used for inference.') args = parser.parse_args() - layout_engine = RapidLayout(args.model_path) + rapid_layout = RapidLayout(args.model_path) img = cv2.imread(args.img_path) - layout_res, elapse = layout_engine(img) + layout_res, elapse = rapid_layout(img) print(layout_res) if args.vis: diff --git a/python/rapid_structure/rapid_table/rapid_table.py b/python/rapid_structure/rapid_table/rapid_table.py index 895cf41..27027e6 100644 --- a/python/rapid_structure/rapid_table/rapid_table.py +++ b/python/rapid_structure/rapid_table/rapid_table.py @@ -1,10 +1,12 @@ # -*- encoding: utf-8 -*- # @Author: SWHL # @Contact: liekkaskono@163.com -import time +import argparse import copy +import time from pathlib import Path +import cv2 import numpy as np from rapidocr_onnxruntime import RapidOCR @@ -54,24 +56,40 @@ class RapidTable(): return dt_boxes, rec_res -def main(): - import argparse - import cv2 +def vis_table(table_res: str, save_path: str) -> None: + style_res = '''''' + prefix_table, suffix_table = table_res.split('') + new_table_res = f'{prefix_table}{style_res}{suffix_table}' + with open(save_path, 'w', encoding='utf-8') as f: + f.write(new_table_res) + print(f'The infer result has saved in {save_path}') + +def main() -> None: parser = argparse.ArgumentParser() - parser.add_argument('--img_path', type=str, required=True) - parser.add_argument('--model_path', type=str, - default=str(root_dir / 'models' / 'en_ppstructure_mobile_v2_SLANet.onnx')) + parser.add_argument('-v', '--vis', action='store_true', + help='Wheter to visualize the layout results.') + parser.add_argument('-img', '--img_path', type=str, required=True, + help='Path to image for layout.') + parser.add_argument('-m', '--model_path', type=str, + default=str(root_dir / 'models' / 'en_ppstructure_mobile_v2_SLANet.onnx'), + help='The model path used for inference.') args = parser.parse_args() rapid_table = RapidTable(args.model_path) img = cv2.imread(args.img_path) - table_html_str, elapse = rapid_table(img) - print(table_html_str) + if args.vis: + img_path = Path(args.img_path) + save_path = img_path.resolve().parent / f'vis_{img_path.stem}.html' + vis_table(table_html_str, str(save_path)) + if __name__ == '__main__': main() diff --git a/python/rapid_structure/setup_layout.py b/python/rapid_structure/setup_layout.py index cb117cf..c6e1ca2 100644 --- a/python/rapid_structure/setup_layout.py +++ b/python/rapid_structure/setup_layout.py @@ -1,7 +1,9 @@ # -*- encoding: utf-8 -*- # @Author: SWHL # @Contact: liekkaskono@163.com +import re import subprocess +import sys from pathlib import Path import setuptools @@ -12,8 +14,7 @@ def get_latest_version(package_name): capture_output=True) output = output.stdout.decode('utf-8') if output: - output = list(filter(lambda x: len(x) > 0, output.split('\n'))) - return output[0].strip().split(' ')[-1][1:-1] + return extract_version(output) return None @@ -35,10 +36,26 @@ def get_readme(): return readme +def extract_version(message: str) -> str: + pattern = r'\d+\.(?:\d+\.)*\d+' + matched_versions = re.findall(pattern, message) + if matched_versions: + return matched_versions[0] + return '' + + MODULE_NAME = 'rapid_layout' latest_version = get_latest_version(MODULE_NAME) VERSION_NUM = 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1 +if len(sys.argv) > 2: + match_str = ' '.join(sys.argv[2:]) + matched_versions = extract_version(match_str) + if matched_versions: + VERSION_NUM = matched_versions +sys.argv = sys.argv[:2] + setuptools.setup( name=MODULE_NAME, version=VERSION_NUM, diff --git a/python/rapid_structure/setup_table.py b/python/rapid_structure/setup_table.py index 34eb257..50fa369 100644 --- a/python/rapid_structure/setup_table.py +++ b/python/rapid_structure/setup_table.py @@ -75,7 +75,7 @@ setuptools.setup( f'{MODULE_NAME}.models', f'{MODULE_NAME}.table_matcher', f'{MODULE_NAME}.table_structure'], - package_data={'': ['*.onnx']}, + package_data={'': ['en_ppstructure_mobile_v2_SLANet.onnx']}, keywords=[ 'ppstructure,table,rapidocr,rapid_table' ],