lint

Author: Luan Pham

.pre-commit-config.yaml

@@ -1,35 +1,44 @@
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v2.3.0
-  hooks:
-  - id: check-yaml
-  - id: end-of-file-fixer
-  - id: trailing-whitespace
-  - id: detect-aws-credentials
-  - id: detect-private-key
-  - id: end-of-file-fixer
-  - id: check-added-large-files
-- repo: https://github.com/ambv/black
-  rev: 21.5b0
-  hooks:
-  - id: black
-    language_version: python3.9
-- repo: https://github.com/pycqa/isort
-  rev: 5.8.0
-  hooks:
-  - id: isort
-    args: [--profile, black]
-- repo: https://gitlab.com/pycqa/flake8
-  rev: 3.9.1
-  hooks:
-  - id: flake8
-- repo: https://github.com/myint/autoflake
-  rev: v1.4
-  hooks:
-  - id: autoflake
-    args: [
-      "--in-place",
-      "--remove-unused-variables",
-      "--remove-all-unused-imports",
-      "--exclude=tests/*",
-    ]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: check-yaml
+      - id: check-toml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: detect-aws-credentials
+        args: ["--allow-missing-credentials"]
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: check-added-large-files
+  - repo: https://github.com/ambv/black
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python3.7
+  - repo: https://github.com/pycqa/isort
+    rev: 5.8.0
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://gitlab.com/pycqa/flake8
+    rev: 3.9.1
+    hooks:
+      - id: flake8
+  - repo: https://github.com/myint/autoflake
+    rev: v1.4
+    hooks:
+      - id: autoflake
+        args:
+          [
+            "--in-place",
+            "--remove-unused-variables",
+            "--remove-all-unused-imports",
+            "--ignore-init-module-imports",
+            "--exclude=tests/*",
+          ]
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v2.7.1
+    hooks:
+      - id: prettier
+        types_or: [markdown, yaml]

README.md

@@ -4,28 +4,29 @@
 
 Project Board: https://github.com/users/phamquiluan/projects/3/views/1
 
-
 # Prepare data
 
 1. Download data from here and put to `data` dir: https://drive.google.com/drive/folders/1J_z-laBlG14Fps81FVrUJUjesdND_JTx?usp=sharing
 2. The image dir path `$PWD/data/images`
 
-
 # Dev guide
 
 1. cd into your dir
+
 ```bash
 # for example
 cd text_detection
 ```
 
 2. create venv
+
 ```bash
 python3.9 -m venv env
 . env/bin/activate
 ```
 
 3. install requirements
+
 ```bash
 pip install -r requirements.txt
 ```
@@ -34,8 +35,6 @@ pip install -r requirements.txt
 
 on your Python file.
 
-
-
 # Docker guide
 
 ```

main.py

@@ -19,24 +19,26 @@ def timeit_wrapper(*args, **kwargs):
         result = func(*args, **kwargs)
         end_time = time.perf_counter()
         total_time = end_time - start_time
-        print(f'Function {func.__name__}{args} {kwargs} Took {total_time:.4f} seconds')
+        print(f"Function {func.__name__}{args} {kwargs} Took {total_time:.4f} seconds")
         return result
+
     return timeit_wrapper
 
+
 # load env var
 load_dotenv()
-TABLE_DETECTION_PORT=env["TABLE_DETECTION_PORT"]
-TABLE_RECOGNITION_PORT=env["TABLE_RECOGNITION_PORT"]
-TEXT_DETECTION_PORT=env["TEXT_DETECTION_PORT"]
-TEXT_RECOGNITION_PORT=env["TEXT_RECOGNITION_PORT"]
+TABLE_DETECTION_PORT = env["TABLE_DETECTION_PORT"]
+TABLE_RECOGNITION_PORT = env["TABLE_RECOGNITION_PORT"]
+TEXT_DETECTION_PORT = env["TEXT_DETECTION_PORT"]
+TEXT_RECOGNITION_PORT = env["TEXT_RECOGNITION_PORT"]
 
 
 class Box(BaseModel):
-    name : str = "box"
-    xmin : int
-    xmax : int
-    ymin : int
-    ymax : int
+    name: str = "box"
+    xmin: int
+    xmax: int
+    ymin: int
+    ymax: int
 
     @property
     def width(self):
@@ -61,38 +63,42 @@ def get_intersection(self, box):
             return (xmax - xmin) * (ymax - ymin)
         return 0
 
+
 class Text(Box):
-    name : str = "text"
-    ocr : str = ""
+    name: str = "text"
+    ocr: str = ""
+
 
 class Cell(Box):
-    name : str = "cell"
-    texts : List[Text] = []
+    name: str = "cell"
+    texts: List[Text] = []
 
     def is_valid(self):
         return self.width > CELL_MIN_WIDTH and self.height > CELL_MIN_HEIGHT
 
 
 class Table(Box):
-    name : str = "table"
-    cells : List[Cell] = []
+    name: str = "table"
+    cells: List[Cell] = []
+
 
-def read_tables_from_list(input_list : List[Dict]) -> List[Table]:
+def read_tables_from_list(input_list: List[Dict]) -> List[Table]:
     tables = []
     for item in input_list:
         if item["name"] != "table":
             continue
         new_table = Table(
-            xmin=item["xmin"],
-            ymin=item["ymin"],
-            xmax=item["xmax"],
-            ymax=item["ymax"]
+            xmin=item["xmin"], ymin=item["ymin"], xmax=item["xmax"], ymax=item["ymax"]
         )
-        new_table.cells = [Cell(xmin=i["xmin"], ymin=i["ymin"], xmax=i["xmax"], ymax=i["ymax"]) for i in item["cells"]]
+        new_table.cells = [
+            Cell(xmin=i["xmin"], ymin=i["ymin"], xmax=i["xmax"], ymax=i["ymax"])
+            for i in item["cells"]
+        ]
         tables.append(new_table)
     return tables
 
-def read_texts_from_list(input_list : List[Dict]) -> List[Text]:
+
+def read_texts_from_list(input_list: List[Dict]) -> List[Text]:
     texts = []
     for item in input_list:
         if item["name"] != "text":
@@ -103,34 +109,44 @@ def read_texts_from_list(input_list : List[Dict]) -> List[Text]:
                 ymin=item["ymin"],
                 xmax=item["xmax"],
                 ymax=item["ymax"],
-                ocr=item["ocr"]
+                ocr=item["ocr"],
             )
         )
     return texts
 
+
 @timeit
 def get_table(image_path):
     image_name = os.path.basename(image_path)
     url = f"http://localhost:{TABLE_RECOGNITION_PORT}/ai/infer"
-    files=[
-      ('file',(image_name,open(image_path,'rb'), mimetypes.guess_type(image_path)[0]))
+    files = [
+        (
+            "file",
+            (image_name, open(image_path, "rb"), mimetypes.guess_type(image_path)[0]),
+        )
     ]
     response = requests.request("POST", url, files=files)
     return response.json()
 
+
 @timeit
 def get_ocr(image_path):
     image_name = os.path.basename(image_path)
     url = f"http://localhost:{TEXT_RECOGNITION_PORT}/ai/infer"
-    files=[
-      ('file',(image_name,open(image_path,'rb'), mimetypes.guess_type(image_path)[0]))
+    files = [
+        (
+            "file",
+            (image_name, open(image_path, "rb"), mimetypes.guess_type(image_path)[0]),
+        )
     ]
     response = requests.request("POST", url, files=files)
     return response.json()
 
+
 def get_random_color():
     return tuple((np.random.random(3) * 153 + 102).astype(np.uint8).tolist())
 
+
 def show(img, name="disp", width=1000):
     """
     name: name of window, should be name of img
@@ -143,25 +159,43 @@ def show(img, name="disp", width=1000):
     cv2.destroyAllWindows()
 
 
-def draw(image, table_list : List[Table]):
+def draw(image, table_list: List[Table]):
     vis_image = image.copy()
 
     # draw cell
     for table in table_list:
         for cell in table.cells:
-            cv2.rectangle(vis_image, (cell.xmin, cell.ymin), (cell.xmax, cell.ymax), get_random_color(), -1)
+            cv2.rectangle(
+                vis_image,
+                (cell.xmin, cell.ymin),
+                (cell.xmax, cell.ymax),
+                get_random_color(),
+                -1,
+            )
 
     vis_image = vis_image // 2 + image // 2
 
     # draw table
     for table in table_list:
-        cv2.rectangle(vis_image, (table.xmin, table.ymin), (table.xmax, table.ymax), (0, 0, 255), 4)
+        cv2.rectangle(
+            vis_image,
+            (table.xmin, table.ymin),
+            (table.xmax, table.ymax),
+            (0, 0, 255),
+            4,
+        )
 
     # draw text
     for table in table_list:
         for cell in table.cells:
             for text in cell.texts:
-                cv2.rectangle(vis_image, (text.xmin, text.ymin), (text.xmax, text.ymax), (255, 0, 0), 2)
+                cv2.rectangle(
+                    vis_image,
+                    (text.xmin, text.ymin),
+                    (text.xmax, text.ymax),
+                    (255, 0, 0),
+                    2,
+                )
 
     # put text
     for table in table_list:
@@ -172,43 +206,48 @@ def draw(image, table_list : List[Table]):
                     text.ocr,
                     (text.xmin, text.ymin),
                     cv2.FONT_HERSHEY_SIMPLEX,
-                    0.5, (0, 255, 0), 1)
+                    0.5,
+                    (0, 255, 0),
+                    1,
+                )
     return vis_image
 
 
-def draw_text(image, text_list : List[Text]):
+def draw_text(image, text_list: List[Text]):
     for text in text_list:
-        cv2.rectangle(image, (text.xmin, text.ymin), (text.xmax, text.ymax), (255, 0, 0), 2)
+        cv2.rectangle(
+            image, (text.xmin, text.ymin), (text.xmax, text.ymax), (255, 0, 0), 2
+        )
     return image
 
 
-def merge_text_table(tables : List[Table], texts : List[Text]):
+def merge_text_table(tables: List[Table], texts: List[Text]):
     for table in tables:
         in_table_texts = [t for t in texts if t.get_intersection(table) > 0]
 
         for cell in table.cells:
-            cell.texts = [t for t in in_table_texts if t.get_intersection(cell) / t.area > 0.4]
+            cell.texts = [
+                t for t in in_table_texts if t.get_intersection(cell) / t.area > 0.4
+            ]
+
 
 @timeit
 def main():
-    image_path = '/home/luan/research/Go5-Project/sample.jpg'
+    image_path = "/home/luan/research/Go5-Project/sample.jpg"
 
     # read table
-    output : List = get_table(image_path)
-    tables : List[Table] = read_tables_from_list(output)
+    output: List = get_table(image_path)
+    tables: List[Table] = read_tables_from_list(output)
 
     # read text
-    output : List = get_ocr(image_path)
-    texts : List[Text] = read_texts_from_list(output)
+    output: List = get_ocr(image_path)
+    texts: List[Text] = read_texts_from_list(output)
 
     merge_text_table(tables, texts)
 
     image = cv2.imread(image_path)
     show(draw(image, tables))
 
 
-
-
-
 if __name__ == "__main__":
     main()

table_detection/Install.md

@@ -2,7 +2,6 @@
 
 ##Go into your prefer directory and Clone the repo
 
-
 ```
 mkdir Project
 cd Project/
@@ -30,12 +29,14 @@ pip install mmcv==0.4.3
 ```
 
 ##Clone the repo
+
 ```
 cd Project/Go5-Project/table_detection
 git clone https://github.com/DevashishPrasad/CascadeTabNet.git
 ```
 
 ##Download the Pretrained Model
+
 ```
 gdown "https://drive.google.com/u/0/uc?id=1-mVr4UBicFk3mjUz5tsVPjQ4jzRtiT7V&export=download"
 ```