Cursor Extractor | 2026 |

extractor = CursorExtractor(schema) for log_file in Path("data/raw/logs").glob("*.log"): content = log_file.read_text() extractor.extract_from_text(content, str(log_file))

def __init__(self, schema: Dict[str, str]): self.schema = schema # field -> regex pattern self.results = []

import re import json from pathlib import Path from typing import Dict, Any class CursorExtractor: """Hybrid regex + placeholder for AI refinement"""

def save(self, output_path: str): with open(output_path, 'w') as f: json.dump(self.results, f, indent=2) schema = "timestamp": r"(\d4-\d2-\d2T\d2:\d2:\d2.\d+Z)", "request_id": r"RequestId: ([a-f0-9-]+)", "duration_ms": r"Duration: (\d+.\d+) ms", "memory_mb": r"MemorySize: (\d+) MB"

extractor.save("extractor/output/structured_logs.json")

Архивчик

Весь Архив

Любимые Сцылочки

Наши Темы