33 lines
1.0 KiB
Python
33 lines
1.0 KiB
Python
|
from typing import List
|
||
|
|
|
||
|
|
def parse_code_structure(code: str) -> dict:
|
||
|
|
"""解析代码结构，返回基本信息"""
|
||
|
|
lines = code.split('\n')
|
||
|
|
return {
|
||
|
|
"total_lines": len(lines),
|
||
|
|
"non_empty_lines": len([l for l in lines if l.strip()]),
|
||
|
|
"code_lines": lines
|
||
|
|
}
|
||
|
|
|
||
|
|
def detect_language(code: str) -> str:
|
||
|
|
"""简单检测代码语言"""
|
||
|
|
code_stripped = code.strip()
|
||
|
|
|
||
|
|
if code_stripped.startswith(('def ', 'import ', 'from ', 'class ', 'if __name__')):
|
||
|
|
return 'python'
|
||
|
|
elif 'function' in code or 'const' in code or 'let' in code or '=>' in code:
|
||
|
|
return 'javascript'
|
||
|
|
elif 'public class' in code or 'private void' in code:
|
||
|
|
return 'java'
|
||
|
|
elif 'std::' in code or '#include <iostream>' in code:
|
||
|
|
return 'cpp'
|
||
|
|
|
||
|
|
return 'unknown'
|
||
|
|
|
||
|
|
def extract_code_blocks(text: str) -> List[str]:
|
||
|
|
"""从文本中提取代码块"""
|
||
|
|
import re
|
||
|
|
pattern = r'```[\w]*\n([\s\S]*?)```'
|
||
|
|
matches = re.findall(pattern, text)
|
||
|
|
return matches if matches else []
|