R/caching.R

# caching.R

# Directory to store cache files
CACHE_DIR <- "./cache_data"

# Ensure cache directory exists
if (!dir.exists(CACHE_DIR)) {
  dir.create(CACHE_DIR, recursive = TRUE)
}

#' Generate a cache key from an operation name and its arguments.
#' 
#' @param operation_name A string identifying the operation.
#' @param ... Arguments to the operation, used to create a unique hash.
#' @return A string representing the cache key.
generate_cache_key <- function(operation_name, ...) {
  # Create a list of arguments
  args_list <- list(...)
  
  # Combine operation name and a digest of the arguments
  # Ensure consistent ordering of named arguments for consistent hashing
  if (length(args_list) > 0) {
    if (!is.null(names(args_list))) {
      args_list <- args_list[order(names(args_list))]
    }
    # Use deparse and digest for complex arguments
    args_digest <- digest::digest(lapply(args_list, deparse))
    key_string <- paste(operation_name, args_digest, sep = "_")
  } else {
    key_string <- operation_name
  }
  
  # Sanitize the key to be a valid filename
  key_string <- gsub("[^a-zA-Z0-9_.-]", "_", key_string)
  return(paste0(key_string, ".rds"))
}

#' Retrieve an item from the cache.
#'
#' @param key The cache key (typically generated by generate_cache_key).
#' @param max_age_seconds The maximum age of the cache file in seconds. 
#'                        If the cache file is older, it's considered stale.
#'                        Default is NULL (no age check).
#' @return The cached item, or NULL if not found or stale.
get_cached_item <- function(key, max_age_seconds = NULL) {
  cache_file_path <- file.path(CACHE_DIR, key)
  if (file.exists(cache_file_path)) {
    if (!is.null(max_age_seconds)) {
      file_info <- file.info(cache_file_path)
      if (difftime(Sys.time(), file_info$mtime, units = "secs") > max_age_seconds) {
        # Cache is stale
        message(paste("Cache stale for key:", key, "- Recomputing."))
        return(NULL)
      }
    }
    message(paste("Cache hit for key:", key))
    return(readRDS(cache_file_path))
  } else {
    message(paste("Cache miss for key:", key))
    return(NULL)
  }
}

#' Save an item to the cache.
#'
#' @param key The cache key.
#' @param value The item to save.
save_cached_item <- function(key, value) {
  if (is.null(value)) {
    # Avoid saving NULLs if an operation truly returns NULL
    # Or handle as an explicit cache clear if needed
    message(paste("Skipping saving NULL value to cache for key:", key))
    return()
  }
  cache_file_path <- file.path(CACHE_DIR, key)
  tryCatch({
    saveRDS(value, file = cache_file_path)
    message(paste("Saved item to cache. Key:", key))
  }, error = function(e) {
    warning(paste("Error saving item to cache for key:", key, ":", e$message))
  })
}

#' Clear the entire cache directory.
clear_all_cache <- function() {
  files_in_cache <- list.files(CACHE_DIR, full.names = TRUE)
  if (length(files_in_cache) > 0) {
    removed_files <- file.remove(files_in_cache)
    message(paste("Cleared", sum(removed_files), "files from cache."))
  } else {
    message("Cache directory is already empty.")
  }
}

# Ensure digest package is available
if (!requireNamespace("digest", quietly = TRUE)) {
  # This is a server-side script, so direct installation might be okay
  # but ideally should be in requirements or Dockerfile.
  # For now, just message that it's needed.
  message("Package 'digest' is not installed. Cache key generation might not be robust. Please install it.")
}