[CodeStyle] Replace black with ruff format and format all python and jupyter files (#6470)

* [CodeStyle] Replace `black` with `ruff format` and format all python and jupyter files

* clean black config

* fix a format

Author: SigureMo

.pre-commit-config.yaml

@@ -33,13 +33,11 @@ repos:
         language: system
         files: .+README(\.cn)?\.md$
 # For Python files
--   repo: https://github.com/psf/black.git
-    rev: 23.3.0
-    hooks:
-    -   id: black
-        files: \.py$
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.5
+    rev: v0.1.13
     hooks:
     -   id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]
+        types_or: [ python, pyi ]
+    -   id: ruff-format
+        types_or: [ python, pyi, jupyter ]

.pre-commit-hooks/convert_markdown_into_html.py

@@ -73,7 +73,7 @@
 
 def convert_markdown_into_html(argv=None):
     parser = argparse.ArgumentParser()
-    parser.add_argument('filenames', nargs='*', help='Filenames to fix')
+    parser.add_argument("filenames", nargs="*", help="Filenames to fix")
     args = parser.parse_args(argv)
 
     retv = 0
@@ -91,5 +91,5 @@ def convert_markdown_into_html(argv=None):
     return retv
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     sys.exit(convert_markdown_into_html())

ci_scripts/CAPItools/main.py

@@ -16,7 +16,7 @@
 # 解析所有的函数, 类, 枚举, 返回一个字典
 # 多线程使用并不安全, 请不要使用多线程
 def analysis_file(path):
-    header = CppHeaderParser.CppHeader(path, encoding='utf8')
+    header = CppHeaderParser.CppHeader(path, encoding="utf8")
     data = json.loads(header.toJSON())
     return data
 
@@ -36,8 +36,8 @@ def generate_docs(
         func_name = item["name"].replace("/", "")
 
         # Note: 操作符仅不生成rst，实际上在Overview列表依然会呈现以提示存在此操作符
-        if func_name.startswith('operator'):
-            checkwords = func_name.replace('operator', '', 1)
+        if func_name.startswith("operator"):
+            checkwords = func_name.replace("operator", "", 1)
             if re.search(r"\w", checkwords) is None:
                 continue  # 跳过操作符声明
         rst_dir = os.path.join(save_dir, LANGUAGE, path, func_name + ".rst")
@@ -47,7 +47,7 @@ def generate_docs(
             helper.create_and_write_file(rst_dir, LANGUAGE)
         except:
             print(traceback.format_exc())
-            print('FAULT GENERATE:' + rst_dir)
+            print("FAULT GENERATE:" + rst_dir)
 
     for item in all_class:
         path = item["filename"].replace("../", "").replace(".h", "")
@@ -62,7 +62,7 @@ def generate_docs(
             helper.create_and_write_file(rst_dir, LANGUAGE)
         except:
             print(traceback.format_exc())
-            print('FAULT GENERATE:' + rst_dir)
+            print("FAULT GENERATE:" + rst_dir)
 
 
 # cpp 对应 python api
@@ -80,13 +80,13 @@ def cpp2py(data: dict):
 # 2. 提取待生成文档的PADDLE_API list
 # 3. 生成文档
 if __name__ == "__main__":
-    root_dir = ''
-    save_dir = '.'  # 默认保存在当前目录
+    root_dir = ""
+    save_dir = "."  # 默认保存在当前目录
     if len(sys.argv) == 3:
         root_dir = sys.argv[1]
         save_dir = sys.argv[2]
 
-    if root_dir == '':
+    if root_dir == "":
         try:
             import inspect
 
@@ -95,8 +95,8 @@ def cpp2py(data: dict):
             root_dir = os.path.dirname(inspect.getsourcefile(paddle))
         except:
             # for simple run
-            root_dir = '../paddle'
-            save_dir = '.'  # 默认保存在当前目录
+            root_dir = "../paddle"
+            save_dir = "."  # 默认保存在当前目录
 
     all_funcs = []
     all_class = []
@@ -115,8 +115,8 @@ def cpp2py(data: dict):
                 cpp2py_api_list = cpp2py(cpp2py_data).copy()
 
             # 跳过文件中未包含PADDLE_API
-            with open(file_path, encoding='utf-8') as f:
-                if 'PADDLE_API ' not in f.read():
+            with open(file_path, encoding="utf-8") as f:
+                if "PADDLE_API " not in f.read():
                     continue
 
             print("Parsing: ", file_path)
@@ -131,9 +131,9 @@ def cpp2py(data: dict):
             all_class.extend(current_class)
             overview_list.append(
                 {
-                    'h_file': file_path,
-                    'class': current_class,
-                    'function': current_func,
+                    "h_file": file_path,
+                    "class": current_class,
+                    "function": current_func,
                 }
             )
 

ci_scripts/CAPItools/utils.py

@@ -4,7 +4,7 @@
 def get_PADDLE_API_func(data: dict):
     result = []
     for i in data["functions"]:
-        if 'PADDLE_API' in i['debug']:
+        if "PADDLE_API" in i["debug"]:
             result.append(i)
     return result
 
@@ -32,7 +32,7 @@ def get_parameters(parameters):
     # parameter_api = ""  # 这里解析是给api使用的 (暂时不用)
     parameter_dict = {}
     for i in parameters:
-        parameter_type_tmp = i['type'].replace(" &", "").replace(" *", "")
+        parameter_type_tmp = i["type"].replace(" &", "").replace(" *", "")
         # * 和 & 情况
         # parameter_api += parameter_type_tmp
 
@@ -41,18 +41,18 @@ def get_parameters(parameters):
         if i["pointer"] == 1:
             # parameter_api += "*"
             parameter_type_tmp += "*"
-        if i["constant"] == 1 and not parameter_type_tmp.startswith('const'):
+        if i["constant"] == 1 and not parameter_type_tmp.startswith("const"):
             parameter_type_tmp = "const " + parameter_type_tmp
         # parameter_api += f" {i['name']}, "
-        desc = i.get('desc', '').replace('  ', '')
+        desc = i.get("desc", "").replace("  ", "")
 
         # special progress for none parameter name case
-        if i['name'] == '&':
+        if i["name"] == "&":
             continue
         else:
-            parameter_dict[i['name']] = {
-                'type': parameter_type_tmp,
-                'intro': desc,
+            parameter_dict[i["name"]] = {
+                "type": parameter_type_tmp,
+                "intro": desc,
             }
         # parameter += f"\t- **{i['name']}** ({parameter_type_tmp}) - {desc}\n"
     # 去掉末尾的逗号
@@ -67,27 +67,27 @@ def get_parameters(parameters):
 # 解析后分别将对应关键字后的内容放入字典对应关键字后
 def parse_doxygen(doxygen):
     doxygen_dict = {
-        'intro': '',
-        'returns': '',
-        'param_intro': {},
-        'note': '',
+        "intro": "",
+        "returns": "",
+        "param_intro": {},
+        "note": "",
     }
 
-    if '@' in doxygen:
-        doxygen = doxygen[doxygen.find('@') :]
-        for doxygen_part in doxygen.split('@'):
-            if doxygen_part.startswith('brief '):
-                doxygen_dict['intro'] = doxygen_part.replace('brief ', '', 1)
-            elif doxygen_part.startswith('return '):
-                doxygen_dict['returns'] = doxygen_part.replace('return ', '', 1)
-            elif doxygen_part.startswith('param '):
-                param_intro = doxygen_part.replace('param ', '', 1)
-                param_name = param_intro[: param_intro.find(' ')]
-                doxygen_dict['param_intro'][param_name] = param_intro[
-                    param_intro.find(' ') + 1 :
+    if "@" in doxygen:
+        doxygen = doxygen[doxygen.find("@") :]
+        for doxygen_part in doxygen.split("@"):
+            if doxygen_part.startswith("brief "):
+                doxygen_dict["intro"] = doxygen_part.replace("brief ", "", 1)
+            elif doxygen_part.startswith("return "):
+                doxygen_dict["returns"] = doxygen_part.replace("return ", "", 1)
+            elif doxygen_part.startswith("param "):
+                param_intro = doxygen_part.replace("param ", "", 1)
+                param_name = param_intro[: param_intro.find(" ")]
+                doxygen_dict["param_intro"][param_name] = param_intro[
+                    param_intro.find(" ") + 1 :
                 ]
-            elif doxygen_part.startswith('note '):
-                doxygen_dict['note'] = doxygen_part.replace('note ', '', 1)
+            elif doxygen_part.startswith("note "):
+                doxygen_dict["note"] = doxygen_part.replace("note ", "", 1)
             else:
                 pass