update common pre-commit configs and commit the results of running pr…

…e-commit run -a

.gitignore

@@ -31,4 +31,4 @@ paddleocr.egg-info/
 /deploy/android_demo/app/.cxx/
 /deploy/android_demo/app/cache/
 test_tipc/web/models/
-test_tipc/web/node_modules/
+test_tipc/web/node_modules/

.pre-commit-config.yaml

@@ -1,26 +1,22 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: a11d9314b22d8f8c7556443875b731ef05965464
+    rev: v4.6.0
     hooks:
+    -   id: check-added-large-files
+        args: ['--maxkb=512']
+    -   id: check-case-conflict
     -   id: check-merge-conflict
     -   id: check-symlinks
     -   id: detect-private-key
-        files: (?!.*paddle)^.*$
     -   id: end-of-file-fixer
-        files: \.md$
     -   id: trailing-whitespace
-        files: \.md$
+        files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|py|md)$
 -   repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: v1.0.1
+    rev: v1.5.1
     hooks:
-    -   id: forbid-crlf
-        files: \.md$
     -   id: remove-crlf
-        files: \.md$
-    -   id: forbid-tabs
-        files: \.md$
     -   id: remove-tabs
-        files: \.md$
+        files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|py)$
 -   repo: local
     hooks:
     -   id: clang-format
@@ -31,7 +27,7 @@ repos:
         files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|cuh|proto)$
 # For Python files
 -   repo: https://github.com/psf/black.git
-    rev: 23.3.0
+    rev: 24.4.2
     hooks:
     -   id: black
         files: (.*\.(py|pyi|bzl)|BUILD|.*\.BUILD|WORKSPACE)$
@@ -47,4 +43,3 @@ repos:
             - --show-source
             - --statistics
         exclude: ^benchmark/|^test_tipc/
-

MANIFEST.in

@@ -7,4 +7,4 @@ recursive-include ppocr/postprocess *.py
 recursive-include tools/infer *.py
 recursive-include tools __init__.py
 recursive-include ppocr/utils/e2e_utils *.py
-recursive-include ppstructure *.py
+recursive-include ppstructure *.py

README.md

@@ -207,12 +207,12 @@ PaddleOCR is being oversight by a [PMC](https://github.com/PaddlePaddle/PaddleOC
 <details open>
 <summary>PP-Structure 文档分析</summary>
 
-- 版面分析+表格识别  
+- 版面分析+表格识别
 <div align="center">
     <img src="./ppstructure/docs/table/ppstructure.GIF" width="800">
 </div>
 
-- SER（语义实体识别）  
+- SER（语义实体识别）
 <div align="center">
     <img src="https://user-images.githubusercontent.com/14270174/185310636-6ce02f7c-790d-479f-b163-ea97a5a04808.jpg" width="600">
 </div>

README_en.md

@@ -119,11 +119,11 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
         - [Mobile](./deploy/lite/readme.md)
         - [Paddle2ONNX](./deploy/paddle2onnx/readme.md)
         - [PaddleCloud](./deploy/paddlecloud/README.md)
-        - [Benchmark](./doc/doc_en/benchmark_en.md)  
+        - [Benchmark](./doc/doc_en/benchmark_en.md)
 - [PP-Structure 🔥](./ppstructure/README.md)
     - [Quick Start](./ppstructure/docs/quickstart_en.md)
     - [Model Zoo](./ppstructure/docs/models_list_en.md)
-    - [Model training](./doc/doc_en/training_en.md)  
+    - [Model training](./doc/doc_en/training_en.md)
         - [Layout Analysis](./ppstructure/layout/README.md)
         - [Table Recognition](./ppstructure/table/README.md)
         - [Key Information Extraction](./ppstructure/kie/README.md)
@@ -136,7 +136,7 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
     - [Text recognition](./doc/doc_en/algorithm_overview_en.md)
     - [End-to-end OCR](./doc/doc_en/algorithm_overview_en.md)
     - [Table Recognition](./doc/doc_en/algorithm_overview_en.md)
-    - [Key Information Extraction](./doc/doc_en/algorithm_overview_en.md)  
+    - [Key Information Extraction](./doc/doc_en/algorithm_overview_en.md)
     - [Add New Algorithms to PaddleOCR](./doc/doc_en/add_new_algorithm_en.md)
 - Data Annotation and Synthesis
     - [Semi-automatic Annotation Tool: PPOCRLabel](https://github.com/PFCCLab/PPOCRLabel/blob/main/README.md)
@@ -188,7 +188,7 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
 <details open>
 <summary>PP-StructureV2</summary>
 
-- layout analysis + table recognition  
+- layout analysis + table recognition
 <div align="center">
     <img src="./ppstructure/docs/table/ppstructure.GIF" width="800">
 </div>
@@ -209,7 +209,7 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
 - RE (Relation Extraction)
 <div align="center">
     <img src="https://user-images.githubusercontent.com/25809855/186094813-3a8e16cc-42e5-4982-b9f4-0134dfb5688d.png" width="600">
-</div>  
+</div>
 
 <div align="center">
     <img src="https://user-images.githubusercontent.com/14270174/185393805-c67ff571-cf7e-4217-a4b0-8b396c4f22bb.jpg" width="600">

applications/PCB字符识别/gen_data/corpus/text.txt

@@ -27,4 +27,4 @@ K06
 KIEY
 NZQJ
 UN1B
-6X4
+6X4

applications/光功率计数码管字符识别/光功率计数码管字符识别.md

@@ -434,16 +434,16 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/PP-
 
 ```
 output/rec/
-├── best_accuracy.pdopt  
-├── best_accuracy.pdparams  
-├── best_accuracy.states  
-├── config.yml  
-├── iter_epoch_3.pdopt  
-├── iter_epoch_3.pdparams  
-├── iter_epoch_3.states  
-├── latest.pdopt  
-├── latest.pdparams  
-├── latest.states  
+├── best_accuracy.pdopt
+├── best_accuracy.pdparams
+├── best_accuracy.states
+├── config.yml
+├── iter_epoch_3.pdopt
+├── iter_epoch_3.pdparams
+├── iter_epoch_3.states
+├── latest.pdopt
+├── latest.pdparams
+├── latest.states
 └── train.log
 ```
 

applications/包装生产日期识别.md

@@ -243,7 +243,7 @@ def get_cropus(f):
     elif 0.7 < rad < 0.8:
         f.write('20{:02d}-{:02d}-{:02d}'.format(year, month, day))
     elif 0.8 < rad < 0.9:
-        f.write('20{:02d}.{:02d}.{:02d}'.format(year, month, day))  
+        f.write('20{:02d}.{:02d}.{:02d}'.format(year, month, day))
     else:
         f.write('{:02d}:{:02d}:{:02d} {:02d}'.format(hours, minute, second, file_id2))
 

applications/印章弯曲文字识别.md

@@ -409,7 +409,7 @@ def crop_seal_from_img(label_file, data_dir, save_dir, save_gt_path):
 
 
 
-if __name__ == "__main__":  
+if __name__ == "__main__":
 
     # 数据处理
     gen_extract_label("./seal_labeled_datas", "./seal_labeled_datas/Label.txt", "./seal_ppocr_gt/seal_det_img.txt", "./seal_ppocr_gt/seal_ppocr_img.txt")
@@ -523,7 +523,7 @@ def gen_xml_label(mode='train'):
         xml_file = open(("./seal_VOC/Annotations" + '/' + i_name + '.xml'), 'w')
         xml_file.write('<annotation>\n')
         xml_file.write('    <folder>seal_VOC</folder>\n')
-        xml_file.write('    <filename>' + str(img_name) + '</filename>\n')  
+        xml_file.write('    <filename>' + str(img_name) + '</filename>\n')
         xml_file.write('    <path>' + 'Annotations/' + str(img_name) + '</path>\n')
         xml_file.write('    <size>\n')
         xml_file.write('        <width>' + str(width) + '</width>\n')
@@ -553,7 +553,7 @@ def gen_xml_label(mode='train'):
             xml_file.write('            <ymax>'+str(ymax)+'</ymax>\n')
             xml_file.write('        </bndbox>\n')
             xml_file.write('    </object>\n')
-        xml_file.write('</annotation>')  
+        xml_file.write('</annotation>')
         xml_file.close()
     print(f'{mode} xml save done!')