src/core/logging.py

"""Logging configuration for CiteScan."""
import logging
import sys
from pathlib import Path
from typing import Any
import json
from datetime import datetime

from .config import settings


class JSONFormatter(logging.Formatter):
    """Custom JSON formatter for structured logging."""

    def format(self, record: logging.LogRecord) -> str:
        """Format log record as JSON."""
        log_data: dict[str, Any] = {
            "timestamp": datetime.utcnow().isoformat(),
            "level": record.levelname,
            "logger": record.name,
            "message": record.getMessage(),
            "module": record.module,
            "function": record.funcName,
            "line": record.lineno,
        }

        # Add exception info if present
        if record.exc_info:
            log_data["exception"] = self.formatException(record.exc_info)

        # Add extra fields
        if hasattr(record, "extra"):
            log_data.update(record.extra)

        return json.dumps(log_data, ensure_ascii=False)


class TextFormatter(logging.Formatter):
    """Custom text formatter with colors for console output."""

    COLORS = {
        "DEBUG": "\033[36m",      # Cyan
        "INFO": "\033[32m",       # Green
        "WARNING": "\033[33m",    # Yellow
        "ERROR": "\033[31m",      # Red
        "CRITICAL": "\033[35m",   # Magenta
    }
    RESET = "\033[0m"

    def format(self, record: logging.LogRecord) -> str:
        """Format log record with colors."""
        color = self.COLORS.get(record.levelname, self.RESET)
        record.levelname = f"{color}{record.levelname}{self.RESET}"
        return super().format(record)


def setup_logging() -> None:
    """Setup logging configuration based on settings."""
    # Create logs directory if it doesn't exist
    log_file_path = Path(settings.log_file)
    log_file_path.parent.mkdir(parents=True, exist_ok=True)

    # Root logger
    root_logger = logging.getLogger()
    root_logger.setLevel(getattr(logging, settings.log_level))

    # Remove existing handlers
    root_logger.handlers.clear()

    # Console handler
    console_handler = logging.StreamHandler(sys.stdout)
    console_handler.setLevel(getattr(logging, settings.log_level))

    if settings.log_format == "json":
        console_formatter = JSONFormatter()
    else:
        console_formatter = TextFormatter(
            fmt="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
            datefmt="%Y-%m-%d %H:%M:%S"
        )

    console_handler.setFormatter(console_formatter)
    root_logger.addHandler(console_handler)

    # File handler (always JSON for easier parsing)
    file_handler = logging.FileHandler(log_file_path, encoding="utf-8")
    file_handler.setLevel(getattr(logging, settings.log_level))
    file_handler.setFormatter(JSONFormatter())
    root_logger.addHandler(file_handler)

    # Reduce noise from third-party libraries
    logging.getLogger("urllib3").setLevel(logging.WARNING)
    logging.getLogger("httpx").setLevel(logging.WARNING)
    logging.getLogger("httpcore").setLevel(logging.WARNING)
    logging.getLogger("asyncio").setLevel(logging.WARNING)


def get_logger(name: str) -> logging.Logger:
    """Get a logger instance with the given name.

    Args:
        name: Logger name (typically __name__)

    Returns:
        Logger instance
    """
    return logging.getLogger(name)