Add linting and formatting tools configuration (#194)

* Add linting and formatting tools configuration

Added `ruff` and `mypy` configurations in `pyproject.toml` to enable strict linting and static type checking. This includes specifications for excluded directories, line length, complexity limits, inline quotes style, and various mypy checks to ensure code quality and consistency. Additionally, moved `jsonschema` to correct dependency section and enhanced pytest setup with additional options.

* Reformat

* Update linting tool in build workflow

Replace flake8 with ruff in the GitHub Actions build workflow. The new tool improves linting checks and applies fixes automatically where possible.

* Exclude proto directory from relevant tools

Added 'hyperstyle/src/python/review/inspectors/common/inspector/proto' to the exclusion lists in two different configuration sections to ensure the directory is ignored by relevant tools. This change will help maintain cleaner project management and avoid unnecessary processing of proto files.

---------

Co-authored-by: meanmail <[email protected]>

Author: meanmail

.github/workflows/build.yml

@@ -71,15 +71,11 @@ jobs:
           echo $PMD_DIRECTORY && echo $PMD_VERSION
           echo $GOLANG_LINT_DIRECTORY && echo $GOLANG_LINT_VERSION
 
-      - name: Lint with flake8
+      - name: Lint
         run: |
           cd /review
           # stop the build if there are Python syntax errors or undefined names
-          /hyperstyle/bin/flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=.git,__pycache__,docs/source/conf.py,old,build,dist,venv,test/resources,.eggs,review.egg-info,.pytest_cache,node_modules,hyperstyle/src/python/review/inspectors/common/inspector/proto
-
-          # TODO: change max-complexity into 10 after refactoring
-          # TODO: remove R504, A003, E800, E402, WPS1, WPS2, WPS3, WPS4, WPS5, WPS6, H601
-          /hyperstyle/bin/flake8 . --count --max-complexity=11 --max-line-length=120 --max-doc-length=120 --ignore=R504,A003,E800,E402,W503,WPS,H601,N400,I100,I201,I202, --statistics --exclude=.git,__pycache__,docs/source/conf.py,old,build,dist,venv,test/resources,.eggs,review.egg-info,.pytest_cache,node_modules,hyperstyle/src/python/review/inspectors/common/inspector/proto
+          /hyperstyle/bin/ruff check --unsafe-fixes --preview .
 
       - name: Check installed module can run python linters
         run: |

hyperstyle/src/python/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from pathlib import Path
 
 MAIN_FOLDER = Path(__file__)

hyperstyle/src/python/common/tool_arguments.py

@@ -1,6 +1,8 @@
+from __future__ import annotations
+
 from dataclasses import dataclass
 from enum import Enum, unique
-from typing import List, Optional
+from typing import ClassVar
 
 from hyperstyle.src.python.review.common.language import Language
 from hyperstyle.src.python.review.common.language_version import LanguageVersion
@@ -9,91 +11,110 @@
 
 @unique
 class VerbosityLevel(Enum):
-    """
-    Same meaning as the logging level. Should be used in command-line args.
-    """
+    """Same meaning as the logging level. Should be used in command-line args."""
+
     DEBUG = 3
     INFO = 2
     ERROR = 1
     DISABLE = 0
 
     @classmethod
-    def values(cls) -> List[int]:
+    def values(cls) -> list[int]:
         return [member.value for member in VerbosityLevel]
 
 
 @dataclass(frozen=True)
 class ArgumentsInfo:
-    short_name: Optional[str]
+    short_name: str | None
     long_name: str
     description: str
 
 
 @unique
 class RunToolArgument(Enum):
-    VERBOSITY = ArgumentsInfo('-v', '--verbosity',
-                              'Choose logging level: '
-                              f'{VerbosityLevel.ERROR.value} - ERROR; '
-                              f'{VerbosityLevel.INFO.value} - INFO; '
-                              f'{VerbosityLevel.DEBUG.value} - DEBUG; '
-                              f'{VerbosityLevel.DISABLE.value} - disable logging; '
-                              'default is 0')
+    VERBOSITY = ArgumentsInfo(
+        "-v",
+        "--verbosity",
+        "Choose logging level: "
+        f"{VerbosityLevel.ERROR.value} - ERROR; "
+        f"{VerbosityLevel.INFO.value} - INFO; "
+        f"{VerbosityLevel.DEBUG.value} - DEBUG; "
+        f"{VerbosityLevel.DISABLE.value} - disable logging; "
+        "default is 0",
+    )
 
-    inspectors = [inspector.lower() for inspector in InspectorType.available_values()]
-    disabled_inspectors_example = f'-d {inspectors[0].lower()},{inspectors[1].lower()}'
+    inspectors: ClassVar = [inspector.lower() for inspector in InspectorType.available_values()]
+    disabled_inspectors_example = f"-d {inspectors[0].lower()},{inspectors[1].lower()}"
 
-    DISABLE = ArgumentsInfo('-d', '--disable',
-                            'Disable inspectors. '
-                            f'Available values: {", ".join(inspectors)}. '
-                            f'Example: {disabled_inspectors_example}')
+    DISABLE = ArgumentsInfo(
+        "-d",
+        "--disable",
+        'Disable inspectors. '
+        f'Available values: {", ".join(inspectors)}. '
+        f'Example: {disabled_inspectors_example}',
+    )
 
-    DUPLICATES = ArgumentsInfo(None, '--allow-duplicates',
-                               'Allow duplicate issues found by different linters. '
-                               'By default, duplicates are skipped.')
+    DUPLICATES = ArgumentsInfo(
+        None,
+        "--allow-duplicates",
+        "Allow duplicate issues found by different linters. " "By default, duplicates are skipped.",
+    )
 
-    LANG = ArgumentsInfo(None, '--language',
-                         'Specify the language to inspect. The tool will check all languages by default. '
-                         'Available values are: '
-                         f'{", ".join([l.lower() for l in Language.values()])}.')
+    LANG = ArgumentsInfo(
+        None,
+        "--language",
+        'Specify the language to inspect. The tool will check all languages by default. '
+        'Available values are: '
+        f'{", ".join([l.lower() for l in Language.values()])}.',
+    )
 
-    LANG_VERSION = ArgumentsInfo(None, '--language-version',
-                                 'Specify the language version for JAVA inspectors. '
-                                 'Available values are: '
-                                 f'{LanguageVersion.PYTHON_3.value}, {LanguageVersion.JAVA_8.value}, '
-                                 f'{LanguageVersion.JAVA_11.value}, {LanguageVersion.KOTLIN.value}.')
+    LANG_VERSION = ArgumentsInfo(
+        None,
+        "--language-version",
+        "Specify the language version for JAVA inspectors. "
+        "Available values are: "
+        f"{LanguageVersion.PYTHON_3.value}, {LanguageVersion.JAVA_8.value}, "
+        f"{LanguageVersion.JAVA_11.value}, {LanguageVersion.KOTLIN.value}.",
+    )
 
-    CPU = ArgumentsInfo(None, '--n-cpu',
-                        'Specify number of cpu that can be used to run inspectors')
+    CPU = ArgumentsInfo(None, "--n-cpu", "Specify number of cpu that can be used to run inspectors")
 
-    PATH = ArgumentsInfo(None, 'path', 'Path to file or directory to inspect.')
+    PATH = ArgumentsInfo(None, "path", "Path to file or directory to inspect.")
 
-    FORMAT = ArgumentsInfo('-f', '--format',
-                           'The output format. Default is JSON.')
+    FORMAT = ArgumentsInfo("-f", "--format", "The output format. Default is JSON.")
 
-    START_LINE = ArgumentsInfo('-s', '--start-line',
-                               'The first line to be analyzed. It starts from 1.')
+    START_LINE = ArgumentsInfo("-s", "--start-line", "The first line to be analyzed. It starts from 1.")
 
-    END_LINE = ArgumentsInfo('-e', '--end-line', 'The end line to be analyzed or None.')
+    END_LINE = ArgumentsInfo("-e", "--end-line", "The end line to be analyzed or None.")
 
-    NEW_FORMAT = ArgumentsInfo(None, '--new-format',
-                               'The argument determines whether the tool '
-                               'should use the new format')
+    NEW_FORMAT = ArgumentsInfo(
+        None, "--new-format", "The argument determines whether the tool " "should use the new format"
+    )
 
-    HISTORY = ArgumentsInfo(None, '--history',
-                            'JSON string, which contains lists of issues in the previous submissions '
-                            'for other tasks for one user.')
+    HISTORY = ArgumentsInfo(
+        None,
+        "--history",
+        "JSON string, which contains lists of issues in the previous submissions "
+        "for other tasks for one user.",
+    )
 
-    WITH_ALL_CATEGORIES = ArgumentsInfo(None, '--with-all-categories',
-                                        'Without this flag, all issues will be categorized into 5 main categories: '
-                                        'CODE_STYLE, BEST_PRACTICES, ERROR_PRONE, COMPLEXITY, INFO.')
+    WITH_ALL_CATEGORIES = ArgumentsInfo(
+        None,
+        "--with-all-categories",
+        "Without this flag, all issues will be categorized into 5 main categories: "
+        "CODE_STYLE, BEST_PRACTICES, ERROR_PRONE, COMPLEXITY, INFO.",
+    )
 
-    GROUP_BY_DIFFICULTY = ArgumentsInfo(None, '--group-by-difficulty',
-                                        'With this flag, the final grade will be grouped by the issue difficulty.')
+    GROUP_BY_DIFFICULTY = ArgumentsInfo(
+        None,
+        "--group-by-difficulty",
+        "With this flag, the final grade will be grouped by the issue difficulty.",
+    )
 
     IJ_CONFIG = ArgumentsInfo(
         None,
-        '--ij-config',
-        'JSON string containing information for setting up a connection to the IJ server '
-        'for each language to be analyzed with the IJ inspector. '
-        'It should be a dictionary of dictionaries where for each language host and port are specified.',
+        "--ij-config",
+        "JSON string containing information for setting up a connection to the IJ server "
+        "for each language to be analyzed with the IJ inspector. "
+        "It should be a dictionary of dictionaries where for each language host and port are specified.",
     )

hyperstyle/src/python/review/application_config.py

@@ -1,32 +1,35 @@
+from __future__ import annotations
+
 from dataclasses import dataclass
-from typing import Optional, Set
+from typing import TYPE_CHECKING
 
-from hyperstyle.src.python.review.common.language import Language
-from hyperstyle.src.python.review.inspectors.common.inspector.inspector_type import InspectorType
+if TYPE_CHECKING:
+    from hyperstyle.src.python.review.common.language import Language
+    from hyperstyle.src.python.review.inspectors.common.inspector.inspector_type import InspectorType
 
 
 @dataclass
 class ApplicationConfig:
-    disabled_inspectors: Set[InspectorType]
+    disabled_inspectors: set[InspectorType]
     allow_duplicates: bool
     n_cpu: int
     inspectors_config: dict
     with_all_categories: bool
     start_line: int = 1
-    language: Optional[Language] = None
-    end_line: Optional[int] = None
+    language: Language | None = None
+    end_line: int | None = None
     new_format: bool = False
-    history: Optional[str] = None
+    history: str | None = None
     group_by_difficulty: bool = False
-    ij_config: Optional[str] = None
+    ij_config: str | None = None
 
     @staticmethod
-    def get_default_config() -> 'ApplicationConfig':
+    def get_default_config() -> ApplicationConfig:
         return ApplicationConfig(
             disabled_inspectors=set(),
             allow_duplicates=False,
             n_cpu=1,
-            inspectors_config={'n_cpu': 1},
+            inspectors_config={"n_cpu": 1},
             with_all_categories=True,
             start_line=1,
             language=None,

hyperstyle/src/python/review/common/file_system.py

@@ -1,11 +1,13 @@
+from __future__ import annotations
+
 import linecache
 import logging
 import os
 import tempfile
+from collections.abc import Callable
 from contextlib import contextmanager
 from enum import Enum, unique
 from pathlib import Path
-from typing import Callable, List, Optional, Tuple, Union
 
 logger = logging.getLogger(__name__)
 
@@ -19,32 +21,32 @@ class FileSystemItem(Enum):
 
 @unique
 class Encoding(Enum):
-    ISO_ENCODING = 'ISO-8859-1'
-    UTF_ENCODING = 'utf-8'
+    ISO_ENCODING = "ISO-8859-1"
+    UTF_ENCODING = "utf-8"
 
 
 # Make sure all extensions (except an empty one) have a dot
 @unique
 class Extension(Enum):
-    EMPTY = ''
-    PY = '.py'
-    JAVA = '.java'
-    KT = '.kt'
-    JS = '.js'
-    KTS = '.kts'
-    GO = '.go'
+    EMPTY = ""
+    PY = ".py"
+    JAVA = ".java"
+    KT = ".kt"
+    JS = ".js"
+    KTS = ".kts"
+    GO = ".go"
 
     # Not empty extensions are returned with a dot, for example, '.txt'
     # If file has no extensions, an empty one ('') is returned
     @classmethod
-    def from_file(cls, file: Union[Path, str]) -> Optional['Extension']:
+    def from_file(cls, file: Path | str) -> Extension | None:
         try:
             return Extension(get_extension_from_file(file))
         except ValueError:
             return None
 
 
-def get_extension_from_file(file: Union[Path, str]) -> str:
+def get_extension_from_file(file: Path | str) -> str:
     return os.path.splitext(file)[1]
 
 
@@ -58,19 +60,20 @@ def all_items_condition(name: str) -> bool:
 # To get all files or subdirs (depends on the last parameter) from root that match item_condition
 # Note that all subdirs or files already contain the full path for them
 def get_all_file_system_items(
-        root: Path,
-        item_condition: ItemCondition = all_items_condition,
-        item_type: FileSystemItem = FileSystemItem.FILE,
-        without_subdirs: bool = False,
-) -> List[Path]:
+    root: Path,
+    item_condition: ItemCondition = all_items_condition,
+    item_type: FileSystemItem = FileSystemItem.FILE,
+    without_subdirs: bool = False,
+) -> list[Path]:
     if not root.is_dir():
-        raise ValueError(f'The {root} is not a directory')
+        msg = f"The {root} is not a directory"
+        raise ValueError(msg)
 
     items = []
     for fs_tuple in os.walk(root):
         for item in fs_tuple[item_type.value]:
             if item_condition(item):
-                items.append(Path(os.path.join(fs_tuple[FileSystemItem.PATH.value], item)))
+                items.append(Path(fs_tuple[FileSystemItem.PATH.value]) / item)
 
         if without_subdirs:
             break
@@ -85,7 +88,7 @@ def new_temp_dir() -> Path:
         yield Path(temp_dir)
 
 
-def new_temp_file(suffix: Extension = Extension.EMPTY) -> Tuple[str, str]:
+def new_temp_file(suffix: Extension = Extension.EMPTY) -> tuple[str, str]:
     yield tempfile.mkstemp(suffix=suffix.value)
 
 
@@ -96,11 +99,11 @@ def get_file_line(path: Path, line_number: int):
     ).strip()
 
 
-def get_content_from_file(file_path: Path, encoding: str = Encoding.ISO_ENCODING.value,
-                          to_strip_nl: bool = True) -> str:
-    with open(file_path, 'r', encoding=encoding) as f:
-        content = f.read()
-        return content if not to_strip_nl else content.rstrip('\n')
+def get_content_from_file(
+    file_path: Path, encoding: str = Encoding.ISO_ENCODING.value, to_strip_nl: bool = True
+) -> str:
+    content = Path(file_path).read_text(encoding=encoding)
+    return content if not to_strip_nl else content.rstrip("\n")
 
 
 # Before using it, check that there are no line breaks in the string
@@ -109,7 +112,7 @@ def __is_line_empty(line: str) -> bool:
 
 
 def __is_comment(line: str) -> bool:
-    return line.strip().startswith(('#', '//'))
+    return line.strip().startswith(("#", "//"))
 
 
 def get_total_code_lines_from_file(path: Path) -> int:
@@ -124,6 +127,6 @@ def get_total_code_lines_from_code(code: str) -> int:
 
 def check_set_up_env_variable(variable_name: str) -> bool:
     if variable_name not in os.environ:
-        logger.warning(f'{variable_name} was not set up!')
+        logger.warning(f"{variable_name} was not set up!")
         return False
     return True