feat: add log

app/core/config.py

@@ -47,6 +47,10 @@ class Settings(BaseSettings):
     host: str = "0.0.0.0"
     port: int = 8053
 
+    # Logging Settings
+    log_dir: Optional[str] = None  # Defaults to /app/logs in container or ./logs locally
+    log_level: str = "INFO"  # DEBUG, INFO, WARNING, ERROR, CRITICAL
+
     @property
     def pp_doclayout_dir(self) -> Path:
         """Get the PP-DocLayout model directory path."""

app/core/logging_config.py

@@ -0,0 +1,157 @@
+"""Logging configuration with rotation by day and size."""
+
+import logging
+import logging.handlers
+from pathlib import Path
+from typing import Optional
+
+from app.core.config import get_settings
+
+
+class TimedRotatingAndSizeFileHandler(logging.handlers.TimedRotatingFileHandler):
+    """File handler that rotates by both time (daily) and size (100MB)."""
+
+    def __init__(
+        self,
+        filename: str,
+        when: str = "midnight",
+        interval: int = 1,
+        backupCount: int = 30,
+        maxBytes: int = 100 * 1024 * 1024,  # 100MB
+        encoding: Optional[str] = None,
+        delay: bool = False,
+        utc: bool = False,
+        atTime: Optional[logging.handlers.BaseRotatingHandler.atTime] = None,
+    ):
+        """Initialize handler with both time and size rotation.
+
+        Args:
+            filename: Log file path
+            when: When to rotate (e.g., 'midnight', 'H', 'M')
+            interval: Rotation interval
+            backupCount: Number of backup files to keep
+            maxBytes: Maximum file size before rotation (in bytes)
+            encoding: File encoding
+            delay: Delay file opening until first emit
+            utc: Use UTC time
+            atTime: Time to rotate (for 'midnight' rotation)
+        """
+        super().__init__(
+            filename=filename,
+            when=when,
+            interval=interval,
+            backupCount=backupCount,
+            encoding=encoding,
+            delay=delay,
+            utc=utc,
+            atTime=atTime,
+        )
+        self.maxBytes = maxBytes
+
+    def shouldRollover(self, record):
+        """Check if rollover should occur based on time or size."""
+        # Check time-based rotation first
+        if super().shouldRollover(record):
+            return True
+
+        # Check size-based rotation
+        if self.stream is None:
+            self.stream = self._open()
+        if self.maxBytes > 0:
+            msg = "%s\n" % self.format(record)
+            self.stream.seek(0, 2)  # Seek to end
+            if self.stream.tell() + len(msg) >= self.maxBytes:
+                return True
+        return False
+
+
+def setup_logging(log_dir: Optional[str] = None) -> logging.Logger:
+    """Setup application logging with rotation by day and size.
+
+    Args:
+        log_dir: Directory for log files. Defaults to /app/logs in container or ./logs locally.
+
+    Returns:
+        Configured logger instance.
+    """
+    settings = get_settings()
+
+    # Determine log directory
+    if log_dir is None:
+        log_dir = Path("/app/logs") if Path("/app/logs").exists() else Path("./logs")
+    else:
+        log_dir = Path(log_dir)
+
+    # Create log directory if it doesn't exist
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    # Create logger
+    logger = logging.getLogger("doc_processer")
+    logger.setLevel(logging.DEBUG if settings.debug else logging.INFO)
+
+    # Remove existing handlers to avoid duplicates
+    logger.handlers.clear()
+
+    # Create custom formatter that handles missing request_id
+    class RequestIDFormatter(logging.Formatter):
+        """Formatter that handles request_id in log records."""
+
+        def format(self, record):
+            # Add request_id if not present
+            if not hasattr(record, "request_id"):
+                record.request_id = getattr(record, "request_id", "unknown")
+            return super().format(record)
+
+    formatter = RequestIDFormatter(
+        fmt="%(asctime)s - %(name)s - %(levelname)s - [%(request_id)s] - %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+
+    # File handler with rotation by day and size
+    # Rotates daily at midnight OR when file exceeds 100MB, keeps 30 days
+    log_file = log_dir / "doc_processer.log"
+    file_handler = TimedRotatingAndSizeFileHandler(
+        filename=str(log_file),
+        when="midnight",
+        interval=1,
+        backupCount=30,
+        maxBytes=100 * 1024 * 1024,  # 100MB
+        encoding="utf-8",
+    )
+    file_handler.setLevel(logging.DEBUG if settings.debug else logging.INFO)
+    file_handler.setFormatter(formatter)
+
+    # Console handler
+    console_handler = logging.StreamHandler()
+    console_handler.setLevel(logging.INFO)
+    console_handler.setFormatter(formatter)
+
+    # Add handlers
+    logger.addHandler(file_handler)
+    logger.addHandler(console_handler)
+
+    return logger
+
+
+# Global logger instance
+_logger: Optional[logging.Logger] = None
+
+
+def get_logger() -> logging.Logger:
+    """Get the global logger instance."""
+    global _logger
+    if _logger is None:
+        _logger = setup_logging()
+    return _logger
+
+
+class RequestIDAdapter(logging.LoggerAdapter):
+    """Logger adapter that adds request_id to log records."""
+
+    def process(self, msg, kwargs):
+        """Add request_id to extra if not present."""
+        if "extra" not in kwargs:
+            kwargs["extra"] = {}
+        if "request_id" not in kwargs["extra"]:
+            kwargs["extra"]["request_id"] = getattr(self, "request_id", "unknown")
+        return msg, kwargs