code-review基础方法 #1
Conversation
Signed-off-by: tangbin <[email protected]>
WalkthroughThe changes refactor the code review functionality by replacing a static analysis approach with an interactive CLI interface that optionally utilizes AI-generated suggestions. The Changes
Sequence Diagram(s)sequenceDiagram
participant U as User
participant CLI as CommandLine
participant CA as CodeAnalyzer
participant AI as AIModelHandler
U->>CLI: Run review(file_path, ai=True)
CLI->>CA: Parse and analyze code
CA-->>CLI: Return static analysis findings
CLI->>AI: Request AI suggestions with context
AI-->>CLI: Return AI-generated review
CLI->>U: Display combined analysis and suggestions
Poem
✨ Finishing Touches
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 10
🧹 Nitpick comments (7)
ai_review/rules/security_rules.py (1)
13-22: Enhance secret detection patterns and handle edge cases.Consider these improvements to make the secret detection more robust:
- Add more secret patterns
- Handle different naming conventions
- Add checks for string literals
- secret_patterns = {'password', 'secret_key', 'api_key'} + secret_patterns = { + 'password', 'passwd', 'pwd', + 'secret', 'secret_key', + 'api_key', 'api_token', + 'auth', 'credentials', + 'private_key', 'access_key' + } + + def _is_secret_name(name: str) -> bool: + name = name.lower() + return any( + pattern in name.replace('_', '') + for pattern in secret_patterns + ) + return [{ 'msg': f"疑似硬编码凭证: {node.targets[0].id}", 'level': 'high', 'lineno': node.lineno } for node in ast.walk(tree) - if isinstance(node, ast.Assign) - and any(pattern in node.targets[0].id.lower() for pattern in secret_patterns)] + if (isinstance(node, ast.Assign) and + hasattr(node.targets[0], 'id') and + _is_secret_name(node.targets[0].id))]🧰 Tools
🪛 Ruff (0.8.2)
20-20: Undefined name
ast(F821)
21-21: Undefined name
ast(F821)
ai_review/core/parser.py (3)
9-16: Enhance function metadata extraction.Consider adding more useful metadata for functions:
def get_function_defs(self) -> list: """提取所有函数定义元数据""" return [{ 'name': node.name, 'args': [arg.arg for arg in node.args.args], + 'defaults': [ + ast.literal_eval(default) if isinstance(default, ast.Constant) + else '...' for default in node.args.defaults + ], + 'decorators': [ + ast.unparse(decorator) for decorator in node.decorator_list + ], + 'returns': ast.unparse(node.returns) if node.returns else None, 'lineno': node.lineno, + 'end_lineno': node.end_lineno, 'docstring': ast.get_docstring(node) } for node in ast.walk(self.tree) if isinstance(node, ast.FunctionDef)]
18-24: Enhance class hierarchy analysis.Consider adding more class metadata and handling nested classes:
def get_class_hierarchy(self) -> list: """解析类继承结构""" return [{ 'name': node.name, 'bases': [base.id for base in node.bases if isinstance(base, ast.Name)], - 'methods': [n.name for n in node.body if isinstance(n, ast.FunctionDef)] + 'methods': [n.name for n in node.body if isinstance(n, ast.FunctionDef)], + 'class_vars': [ + n.targets[0].id for n in node.body + if isinstance(n, ast.Assign) + ], + 'decorators': [ + ast.unparse(decorator) for decorator in node.decorator_list + ], + 'nested_classes': [ + n.name for n in node.body + if isinstance(n, ast.ClassDef) + ], + 'docstring': ast.get_docstring(node) } for node in ast.walk(self.tree) if isinstance(node, ast.ClassDef)]
26-28: Add error handling for AST visualization.Add error handling and provide options for visualization format:
- def code_visualization(self) -> str: + def code_visualization(self, format_type: str = 'dump') -> str: """生成AST可视化结构""" - return astunparse.dump(self.tree) + try: + if format_type == 'dump': + return astunparse.dump(self.tree) + elif format_type == 'unparse': + return astunparse.unparse(self.tree) + else: + raise ValueError(f"Unsupported format type: {format_type}") + except Exception as e: + raise RuntimeError(f"Failed to visualize AST: {e}")ai_review/cli/main.py (1)
40-42: Consider making rule loading more flexible.The current implementation hardcodes the security rules path. Consider making this configurable to easily add or modify rule types.
- analyzer = CodeAnalyzer(['ai_review.rules.security_rules']) + rule_paths = config.get('rules', ['ai_review.rules.security_rules']) + analyzer = CodeAnalyzer(rule_paths)ai_review/config/model_config.yaml (1)
11-12: Make model path configurable and add newline at EOF.The local model path should be environment-specific, and the file should end with a newline as per YAML standards.
local_models: - codegen2_path: /models/codegen2-3.7B + codegen2_path: ${CODEGEN2_MODEL_PATH} +🧰 Tools
🪛 YAMLlint (1.35.1)
[error] 12-12: no new line character at the end of file
(new-line-at-end-of-file)
requirements.txt (1)
27-27: Consider using fixed version for OpenAI package.Using
>=for version constraints can lead to unexpected breaking changes. Consider using a fixed version like other dependencies.-openai>=1.12.0 +openai==1.12.0
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
ai_review/cli/main.py(1 hunks)ai_review/config/model_config.yaml(1 hunks)ai_review/core/analyzer.py(1 hunks)ai_review/core/model_adapter.py(1 hunks)ai_review/core/parser.py(1 hunks)ai_review/rules/security_rules.py(1 hunks)requirements.txt(1 hunks)
🧰 Additional context used
🪛 Ruff (0.8.2)
ai_review/rules/security_rules.py
8-8: Undefined name ast
(F821)
9-9: Undefined name ast
(F821)
20-20: Undefined name ast
(F821)
21-21: Undefined name ast
(F821)
ai_review/core/model_adapter.py
2-2: configparser.ConfigParser imported but unused
Remove unused import: configparser.ConfigParser
(F401)
10-10: Undefined name yaml
(F821)
🪛 YAMLlint (1.35.1)
ai_review/config/model_config.yaml
[error] 12-12: no new line character at the end of file
(new-line-at-end-of-file)
🔇 Additional comments (2)
ai_review/cli/main.py (2)
28-35: LGTM! Good use of Click for CLI and type hints.The function signature is well-defined with proper type hints, and the Click decorators provide a clear CLI interface.
44-54: LGTM! Well-structured output with good visual hierarchy.The color-coded output based on severity and clear separation between AI and static analysis results improves readability.
| import openai | ||
| from configparser import ConfigParser | ||
|
|
||
| class AIModelHandler: | ||
| def __init__(self, config_path='model_config.yaml'): | ||
| self.config = self._load_config(config_path) | ||
|
|
||
| def _load_config(self, path): | ||
| with open(path) as f: | ||
| return yaml.safe_load(f) |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling and improve configuration management.
- Remove unused import and add missing import:
-from configparser import ConfigParser
+import yaml- Add error handling for file operations and configuration loading:
def __init__(self, config_path='model_config.yaml'):
+ try:
self.config = self._load_config(config_path)
+ except FileNotFoundError:
+ raise ValueError(f"Configuration file not found: {config_path}")
+ except yaml.YAMLError as e:
+ raise ValueError(f"Invalid YAML configuration: {e}")
def _load_config(self, path):
with open(path) as f:
return yaml.safe_load(f)- Consider using environment variables for the config path:
+import os
+
class AIModelHandler:
- def __init__(self, config_path='model_config.yaml'):
+ def __init__(self, config_path=None):
+ config_path = config_path or os.getenv('AI_REVIEW_CONFIG', 'model_config.yaml')📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| import openai | |
| from configparser import ConfigParser | |
| class AIModelHandler: | |
| def __init__(self, config_path='model_config.yaml'): | |
| self.config = self._load_config(config_path) | |
| def _load_config(self, path): | |
| with open(path) as f: | |
| return yaml.safe_load(f) | |
| import openai | |
| import yaml | |
| import os | |
| class AIModelHandler: | |
| def __init__(self, config_path=None): | |
| config_path = config_path or os.getenv('AI_REVIEW_CONFIG', 'model_config.yaml') | |
| try: | |
| self.config = self._load_config(config_path) | |
| except FileNotFoundError: | |
| raise ValueError(f"Configuration file not found: {config_path}") | |
| except yaml.YAMLError as e: | |
| raise ValueError(f"Invalid YAML configuration: {e}") | |
| def _load_config(self, path): | |
| with open(path) as f: | |
| return yaml.safe_load(f) |
🧰 Tools
🪛 Ruff (0.8.2)
2-2: configparser.ConfigParser imported but unused
Remove unused import: configparser.ConfigParser
(F401)
10-10: Undefined name yaml
(F821)
| def get_code_review(self, code_snippet: str, context: dict) -> str: | ||
| """调用AI模型进行语义级审查""" | ||
| prompt = f"""作为资深Python架构师，请审查以下代码： | ||
| {code_snippet} | ||
| 审查重点： | ||
| 1. 架构设计合理性 | ||
| 2. 异常处理完整性 | ||
| 3. 性能优化空间 | ||
| 4. 安全合规性 | ||
| 请用中文按严重性分级输出建议""" | ||
|
|
||
| response = openai.ChatCompletion.create( | ||
| model=self.config['openai']['model_name'], | ||
| messages=[{"role": "user", "content": prompt}], | ||
| temperature=self.config['openai']['temperature'] | ||
| ) | ||
| return response.choices[0].message.content |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling and enhance API usage.
- Add error handling for API calls
- Validate API configuration
- Enhance prompt with context
- Add rate limiting
def get_code_review(self, code_snippet: str, context: dict) -> str:
"""调用AI模型进行语义级审查"""
+ if not self.config.get('openai', {}).get('api_key'):
+ raise ValueError("OpenAI API key not configured")
+
+ openai.api_key = self.config['openai']['api_key']
+
prompt = f"""作为资深Python架构师，请审查以下代码：
+
+上下文信息：
+文件路径: {context.get('file_path', 'Unknown')}
+代码类型: {context.get('code_type', 'Unknown')}
+
{code_snippet}
+
审查重点：
1. 架构设计合理性
2. 异常处理完整性
3. 性能优化空间
4. 安全合规性
请用中文按严重性分级输出建议"""
- response = openai.ChatCompletion.create(
- model=self.config['openai']['model_name'],
- messages=[{"role": "user", "content": prompt}],
- temperature=self.config['openai']['temperature']
- )
- return response.choices[0].message.content
+ try:
+ response = openai.ChatCompletion.create(
+ model=self.config['openai']['model_name'],
+ messages=[{"role": "user", "content": prompt}],
+ temperature=self.config['openai']['temperature'],
+ max_tokens=self.config['openai'].get('max_tokens', 1000),
+ timeout=self.config['openai'].get('timeout', 30)
+ )
+ return response.choices[0].message.content
+ except openai.error.OpenAIError as e:
+ raise RuntimeError(f"OpenAI API error: {e}")
+ except Exception as e:
+ raise RuntimeError(f"Unexpected error during code review: {e}")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| def get_code_review(self, code_snippet: str, context: dict) -> str: | |
| """调用AI模型进行语义级审查""" | |
| prompt = f"""作为资深Python架构师，请审查以下代码： | |
| {code_snippet} | |
| 审查重点： | |
| 1. 架构设计合理性 | |
| 2. 异常处理完整性 | |
| 3. 性能优化空间 | |
| 4. 安全合规性 | |
| 请用中文按严重性分级输出建议""" | |
| response = openai.ChatCompletion.create( | |
| model=self.config['openai']['model_name'], | |
| messages=[{"role": "user", "content": prompt}], | |
| temperature=self.config['openai']['temperature'] | |
| ) | |
| return response.choices[0].message.content | |
| def get_code_review(self, code_snippet: str, context: dict) -> str: | |
| """调用AI模型进行语义级审查""" | |
| if not self.config.get('openai', {}).get('api_key'): | |
| raise ValueError("OpenAI API key not configured") | |
| openai.api_key = self.config['openai']['api_key'] | |
| prompt = f"""作为资深Python架构师，请审查以下代码： | |
| 上下文信息： | |
| 文件路径: {context.get('file_path', 'Unknown')} | |
| 代码类型: {context.get('code_type', 'Unknown')} | |
| {code_snippet} | |
| 审查重点： | |
| 1. 架构设计合理性 | |
| 2. 异常处理完整性 | |
| 3. 性能优化空间 | |
| 4. 安全合规性 | |
| 请用中文按严重性分级输出建议""" | |
| try: | |
| response = openai.ChatCompletion.create( | |
| model=self.config['openai']['model_name'], | |
| messages=[{"role": "user", "content": prompt}], | |
| temperature=self.config['openai']['temperature'], | |
| max_tokens=self.config['openai'].get('max_tokens', 1000), | |
| timeout=self.config['openai'].get('timeout', 30) | |
| ) | |
| return response.choices[0].message.content | |
| except openai.error.OpenAIError as e: | |
| raise RuntimeError(f"OpenAI API error: {e}") | |
| except Exception as e: | |
| raise RuntimeError(f"Unexpected error during code review: {e}") |
| click==8.1.7 | ||
| tqdm==4.66.2 | ||
| requests==2.31.0 |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Verify requests package version for security vulnerabilities.
The requests package is security-critical as it handles HTTP communications.
🌐 Web query:
What is the latest version of the requests package and are there any known security vulnerabilities in version 2.31.0?
💡 Result:
The latest version of the Python requests package is 2.32.3, released on May 21, 2024[6][8]. This version includes security patches and stability improvements over previous releases.
For version 2.31.0, there is one known security vulnerability:
- CVE-2024-35195 (CVSS score: 5.6/10): A session persistence vulnerability where certificate verification remains disabled for subsequent requests to the same host if the initial request used
verify=False[2][5][8]. This could allow authenticated attackers to bypass TLS verification in subsequent connections[5].
Key details about the vulnerability:
- Affects all versions prior to 2.32.0
- Fixed in requests >=2.32.0 through improved connection handling[5][6]
- Requires local access and specific session configurations to exploit[5]
- Major vendors like IBM and SUSE have issued security bulletins recommending upgrades[2][5]
While some sources note that practical exploitation is difficult[3], upgrading to >=2.32.0 remains the official mitigation[5][6]. The current recommendation is to use requests 2.32.3 which contains all security patches and stability updates[6][8].
Citations:
- 1: https://pypi.org/project/requests/
- 2: https://www.ibm.com/support/pages/security-bulletin-ibm-maximo-application-suite-monitor-component-vulnerable-requests-2310-py3-none-anywhl-cve-2024-35195
- 3: Vulnerability in requests==2.31.0 seleniumbase/SeleniumBase#2838
- 4: https://pypi.org/project/requests/2.7.0/
- 5: https://www.suse.com/security/cve/CVE-2024-35195.html
- 6: https://requests.readthedocs.io/en/latest/community/updates/
- 7: https://www.activestate.com/resources/quick-reads/how-to-pip-install-requests-python-package/
- 8: https://security.snyk.io/package/pip/requests/2.31.0
- 9: requests-2.31.0-py3-none-any.whl: 1 vulnerabilities (highest severity is: 5.6) - autoclosed netscaler/ansible-collection-netscaleradc#440
- 10: https://github.com/psf/requests/blob/main/HISTORY.md
Action Required: Upgrade the requests Package to Mitigate Vulnerability
- The current version in
requirements.txtisrequests==2.31.0, which is affected by a known security vulnerability (CVE-2024-35195) related to session persistence whenverify=Falseis used. - This vulnerability is fixed in requests versions 2.32.0 and later. The latest version, as of May 21, 2024, is 2.32.3, which includes essential security patches and stability improvements.
- Recommendation: Update the
requirements.txtentry to use at least version 2.32.0 (ideally 2.32.3) to ensure that the security vulnerability is addressed.
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (7)
ai_review/rules/security_rules.py (2)
5-9: Enhance unsafe function detection with additional patterns.Consider expanding the set of unsafe functions to include more potentially dangerous operations:
unsafe_calls = { 'eval', 'exec', 'pickle.loads', 'pickle.load', 'subprocess.call', 'subprocess.Popen', 'os.system', - 'tempfile.mktemp' # Use mkstemp instead + 'tempfile.mktemp', # Use mkstemp instead + 'input', # Potentially dangerous in Python 2 + 'yaml.load', # Use yaml.safe_load instead + 'marshal.loads', # Similar risks to pickle + 'sqlite3.connect' # Check for SQL injection if user input is used }
21-21: Expand secret detection patterns.The current set of patterns could miss some common secret patterns:
-secret_patterns = {'password', 'secret_key', 'api_key'} +secret_patterns = { + 'password', 'passwd', 'pwd', + 'secret', 'secret_key', + 'api_key', 'apikey', 'api_token', + 'access_key', 'access_token', + 'auth', 'credentials', + 'private_key', 'ssh_key' +}ai_review/core/parser.py (2)
7-10: Improve error chaining in exception handling.Use error chaining to preserve the original exception context:
try: self.tree = ast.parse(source_code) except SyntaxError as e: - raise ValueError(f"Invalid Python syntax at line {e.lineno}: {e.msg}") + raise ValueError(f"Invalid Python syntax at line {e.lineno}: {e.msg}") from e🧰 Tools
🪛 Ruff (0.8.2)
10-10: Within an
exceptclause, raise exceptions withraise ... from errorraise ... from Noneto distinguish them from errors in exception handling(B904)
24-24: Handle complex base class expressions.The current implementation might miss base classes that aren't simple names:
- 'bases': [base.id for base in node.bases if isinstance(base, ast.Name)], + 'bases': [astunparse.unparse(base).strip() for base in node.bases],ai_review/core/analyzer.py (2)
1-6: Clean up duplicate imports.Remove redundant imports:
-from typing import Dict, List +from typing import Dict, List, Callable from .parser import ASTParser import importlib -from typing import Dict, List, Callable🧰 Tools
🪛 Ruff (0.8.2)
5-5: Redefinition of unused
Dictfrom line 1Remove definition:
Dict(F811)
5-5: Redefinition of unused
Listfrom line 1Remove definition:
List(F811)
26-29: Improve error chaining in rule loading.Use error chaining to preserve the original exception context:
except ImportError as e: - raise ImportError(f"Failed to import rule module {module_name}: {e}") + raise ImportError(f"Failed to import rule module {module_name}: {e}") from e except Exception as e: - raise RuntimeError(f"Error loading rules from {module_name}: {e}") + raise RuntimeError(f"Error loading rules from {module_name}: {e}") from e🧰 Tools
🪛 Ruff (0.8.2)
27-27: Within an
exceptclause, raise exceptions withraise ... from errorraise ... from Noneto distinguish them from errors in exception handling(B904)
29-29: Within an
exceptclause, raise exceptions withraise ... from errorraise ... from Noneto distinguish them from errors in exception handling(B904)
ai_review/config/model_config.yaml (1)
9-10: Add newline at end of file and validate local model path.
- Add a newline at the end of the file
- Consider making the local model path configurable via environment variable:
local_models: - codegen2_path: /models/codegen2-3.7B + codegen2_path: ${LOCAL_MODEL_PATH:-/models/codegen2-3.7B} +🧰 Tools
🪛 YAMLlint (1.35.1)
[error] 10-10: no new line character at the end of file
(new-line-at-end-of-file)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
ai_review/config/model_config.yaml(1 hunks)ai_review/core/analyzer.py(1 hunks)ai_review/core/parser.py(1 hunks)ai_review/rules/security_rules.py(1 hunks)
🧰 Additional context used
🪛 Ruff (0.8.2)
ai_review/core/parser.py
10-10: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
ai_review/core/analyzer.py
5-5: Redefinition of unused Dict from line 1
Remove definition: Dict
(F811)
5-5: Redefinition of unused List from line 1
Remove definition: List
(F811)
27-27: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
29-29: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
🪛 YAMLlint (1.35.1)
ai_review/config/model_config.yaml
[error] 10-10: no new line character at the end of file
(new-line-at-end-of-file)
Signed-off-by: tangbin <[email protected]>
…code-review.git into feature.code_review_base
There was a problem hiding this comment.
Actionable comments posted: 0
🔭 Outside diff range comments (2)
ai_review/analyzers/ast_parser.py (2)
10-11: 🛠️ Refactor suggestionImprove complexity calculation.
The current complexity calculation is oversimplified. Cyclomatic complexity should consider:
- Conditional statements (if/elif)
- Loops (for/while)
- Exception handlers (try/except)
- Boolean operations (and/or)
Here's an example implementation:
def visit_FunctionDef(self, node: ast.FunctionDef) -> None: """Calculate cyclomatic complexity of functions.""" complexity = 1 # Base complexity # Helper to count branches def count_branches(node: ast.AST) -> int: count = 0 # If statements add branches if isinstance(node, ast.If): count += len(node.orelse) + 1 # Loops add complexity elif isinstance(node, (ast.For, ast.While)): count += 1 # Try/except blocks add complexity elif isinstance(node, ast.Try): count += len(node.handlers) # Boolean operations add complexity elif isinstance(node, ast.BoolOp): count += len(node.values) - 1 return count # Walk the AST and count branches for child in ast.walk(node): complexity += count_branches(child) self.function_complexity[node.name] = complexity self.generic_visit(node)
17-18:⚠️ Potential issueVerify the
referencesattribute.The code references
self.referencesbut this attribute is not initialized in__init__. This could lead to AttributeError.Add initialization in
__init__:def __init__(self): self.findings = [] self.function_complexity = {} + self.references = [] # Initialize references list
🧹 Nitpick comments (2)
ai_review/analyzers/ast_parser.py (2)
26-27: Consider removing unnecessary override.The
visit_Assertmethod simply delegates to the parent class without adding any custom logic. Unless you plan to add specific assertion handling logic in the future, this override can be safely removed as the parent class's implementation will be used by default.
3-27: Improve code quality with documentation and type hints.The class could benefit from:
- Class-level docstring explaining its purpose and usage
- Method-level docstrings for all methods
- Type hints for all parameters and return values
- Better error messages in Chinese since comments are in Chinese
Example improvements:
class ASTAnalyzer(ast.NodeVisitor): """AST visitor that analyzes code for complexity and unused variables. Attributes: findings: List of analysis findings function_complexity: Dict mapping function names to their complexity """ def __init__(self) -> None: self.findings: list[str] = [] self.function_complexity: dict[str, int] = {} def visit_FunctionDef(self, node: ast.FunctionDef) -> None: """Calculate cyclomatic complexity of functions. Args: node: The function definition node """ complexity = len(node.body) self.function_complexity[node.name] = complexity self.generic_visit(node) def visit_Name(self, node: ast.Name) -> None: """Detect unused variables. Args: node: The name node """ if isinstance(node.ctx, ast.Store): if not any(ref.id == node.id for ref in self.references): self.findings.append(f"未使用的变量: {node.id}")🧰 Tools
🪛 Ruff (0.8.2)
16-17: Use a single
ifstatement instead of nestedifstatements(SIM102)
22-23: Use a single
ifstatement instead of nestedifstatements(SIM102)
Summary by CodeRabbit
New Features
Chores