squash a couple of commits

.Rbuildignore

@@ -5,3 +5,4 @@
 ^CODEOWNERS$
 ^\.github$
 ^\.lintr$
+^[.]?air[.]toml$

R/get_container.R

@@ -1,83 +1,83 @@
-#' Get Azure storage container
-#'
-#' The environment variable "AZ_STORAGE_EP" should be set. This provides the URL
-#'  for the default Azure storage endpoint.
-#' Use [list_container_names] to get a list of available container names.
-#'
-#' @param container_name Name of the container as a string. `NULL` by default,
-#'  which means the function will look instead for a container name stored in
-#'  the environment variable "AZ_CONTAINER"
-#' @param token An Azure authentication token. If left as `NULL`, a token
-#'  returned by [get_auth_token] will be used
-#' @param endpoint_url An Azure endpoint URL. If left as `NULL`, the default,
-#'  the value of the environment variable "AZ_STORAGE_EP" will be used
-#' @param ... arguments to be passed through to [get_auth_token], if a token is
-#'  not already supplied
-#' @returns An Azure blob container (list object of class "blob_container")
-#' @export
-get_container <- function(
-  container_name = NULL,
-  token = NULL,
-  endpoint_url = NULL,
-  ...
-) {
-  msg1 <- paste0(
-    "{.var container_name} is empty. ",
-    "Did you forget to set an environment variable?"
-  )
-  msg2 <- paste0(
-    "{.var endpoint_url} is empty. ",
-    "Did you forget to set an environment variable?"
-  )
-  container_name <- (container_name %||% check_envvar("AZ_CONTAINER")) |>
-    check_nzchar(msg1)
-  endpoint_url <- (endpoint_url %||% check_envvar("AZ_STORAGE_EP")) |>
-    check_nzchar(msg2)
-  token <- token %||% get_auth_token(...)
-
-  get_azure_endpoint(token, endpoint_url) |>
-    AzureStor::blob_container(container_name)
-}
-
-
-#' Return a list of container names that are found at the endpoint
-#'
-#' @inheritParams get_container
-#' @returns A character vector of all container names found
-#' @export
-list_container_names <- function(token = NULL, endpoint_url = NULL, ...) {
-  token <- token %||% get_auth_token(...)
-  endpoint <- get_azure_endpoint(token, endpoint_url)
-  container_list <- AzureStor::list_blob_containers(endpoint)
-  stopifnot("no containers found" = length(container_list) >= 1L)
-  names(container_list)
-}
-
-
-#' Return an Azure "blob_endpoint"
-#'
-#' This function will return the endpoint specified in the environment variable
-#' "AZ_STORAGE_EP" by default
-#'
-#' @inheritParams get_container
-#' @returns An Azure blob endpoint (object of class "blob_endpoint")
-#' @keywords internal
-get_azure_endpoint <- function(token = NULL, endpoint_url = NULL, ...) {
-  token <- token %||% get_auth_token(...)
-  endpoint_url <- endpoint_url %||% check_envvar("AZ_STORAGE_EP")
-  AzureStor::blob_endpoint(endpoint_url, token = token)
-}
-
-
-#' Check that an environment variable exists
-#'
-#' The function prints a helpful error if the variable is not found, else
-#'  it returns the value of `Sys.getenv(x)`
-#'
-#' @param x the *name* of the environment variable to be found and checked
-#' @returns the value of the environment variable named in `x`
-#' @export
-check_envvar <- function(x) {
-  cst_msg <- cst_error_msg("The environment variable {.envvar {x}} is not set")
-  check_scalar_type(Sys.getenv(x, NA_character_), "string", cst_msg)
-}
+#' Get Azure storage container
+#'
+#' The environment variable "AZ_STORAGE_EP" should be set. This provides the URL
+#'  for the default Azure storage endpoint.
+#' Use [list_container_names] to get a list of available container names.
+#'
+#' @param container_name Name of the container as a string. `NULL` by default,
+#'  which means the function will look instead for a container name stored in
+#'  the environment variable "AZ_CONTAINER"
+#' @param token An Azure authentication token. If left as `NULL`, a token
+#'  returned by [get_auth_token] will be used
+#' @param endpoint_url An Azure endpoint URL. If left as `NULL`, the default,
+#'  the value of the environment variable "AZ_STORAGE_EP" will be used
+#' @param ... arguments to be passed through to [get_auth_token], if a token is
+#'  not already supplied
+#' @returns An Azure blob container (list object of class "blob_container")
+#' @export
+get_container <- function(
+  container_name = NULL,
+  token = NULL,
+  endpoint_url = NULL,
+  ...
+) {
+  msg1 <- paste0(
+    "{.var container_name} is empty. ",
+    "Did you forget to set an environment variable?"
+  )
+  msg2 <- paste0(
+    "{.var endpoint_url} is empty. ",
+    "Did you forget to set an environment variable?"
+  )
+  container_name <- (container_name %||% check_envvar("AZ_CONTAINER")) |>
+    check_nzchar(msg1)
+  endpoint_url <- (endpoint_url %||% check_envvar("AZ_STORAGE_EP")) |>
+    check_nzchar(msg2)
+  token <- token %||% get_auth_token(...)
+
+  get_azure_endpoint(token, endpoint_url) |>
+    AzureStor::blob_container(container_name)
+}
+
+
+#' Return a list of container names that are found at the endpoint
+#'
+#' @inheritParams get_container
+#' @returns A character vector of all container names found
+#' @export
+list_container_names <- function(token = NULL, endpoint_url = NULL, ...) {
+  token <- token %||% get_auth_token(...)
+  endpoint <- get_azure_endpoint(token, endpoint_url)
+  container_list <- AzureStor::list_blob_containers(endpoint)
+  stopifnot("no containers found" = length(container_list) >= 1L)
+  names(container_list)
+}
+
+
+#' Return an Azure "blob_endpoint"
+#'
+#' This function will return the endpoint specified in the environment variable
+#' "AZ_STORAGE_EP" by default
+#'
+#' @inheritParams get_container
+#' @returns An Azure blob endpoint (object of class "blob_endpoint")
+#' @keywords internal
+get_azure_endpoint <- function(token = NULL, endpoint_url = NULL, ...) {
+  token <- token %||% get_auth_token(...)
+  endpoint_url <- endpoint_url %||% check_envvar("AZ_STORAGE_EP")
+  AzureStor::blob_endpoint(endpoint_url, token = token)
+}
+
+
+#' Check that an environment variable exists
+#'
+#' The function prints a helpful error if the variable is not found, else
+#'  it returns the value of `Sys.getenv(x)`
+#'
+#' @param x the *name* of the environment variable to be found and checked
+#' @returns the value of the environment variable named in `x`
+#' @export
+check_envvar <- function(x) {
+  cst_msg <- cst_error_msg("The environment variable {.envvar {x}} is not set")
+  check_scalar_type(Sys.getenv(x, NA_character_), "string", cst_msg)
+}

R/list_files.R

@@ -1,57 +1,57 @@
-#' List files in a container
-#'
-#' Recursively (or not, if desired) lists all files found in a container. Search
-#' can be restricted to a particular 'subdirectory' of the container, and/or
-#' to files with a specific extension. The function assumes that all file names
-#' end with a ".ext" extension of some sort.
-#'
-#' The function does not support filtering by file name, only by file extension.
-#'
-#' The returned file list (character vector) contains the full paths to the
-#' files, ready to be passed perhaps to a `read_azure_*` function, or further
-#' filtered by you. If you just want the names of the files without the folder
-#' path, use [basename()] to extract these.
-#'
-#' @inheritParams read_azure_parquet
-#' @param path (optional) subdirectory of the container to list files within.
-#'  `""` (the root folder of the container) by default
-#' @param ext (optional) A string giving the extension of a particular file type
-#'  you want to restrict the list to. No need to include the initial ".". The
-#'  default, `""`, means no filtering by file extension will be applied. Can be
-#'  a regular expression.
-#' @param recursive A Boolean value: whether to list files recursively. `TRUE`
-#'  by default
-#'
-#' @importFrom rlang .data
-#' @returns A vector of file names, or an empty character vector if none found
-#' @examples \dontrun{
-#'   list_files(get_container("example"), ext = "csv")
-#' }
-#' @export
-list_files <- function(container, path = "", ext = "", recursive = TRUE) {
-  stopifnot(rlang::is_character(c(path, ext), 2))
-  stopifnot(rlang::is_bool(recursive))
-  pnf_msg <- ct_error_msg("Path {.val {path}} not found")
-  check_that(path, \(x) AzureStor::blob_dir_exists(container, x), pnf_msg)
-
-  tbl <- AzureStor::list_blobs(container, path, recursive = recursive)
-  if (nrow(tbl) > 0) {
-    ext_rx <- if (nzchar(ext)) sub("^\\.+", "", ext) else ".*" # nolint
-    tbl <- tbl |>
-      dplyr::filter(!.data[["isdir"]] & gregg(.data[["name"]], "\\.{ext_rx}$"))
-  }
-
-  # A zero-row tbl can result if `path` is initially empty, or via the filter
-  # step above. We handle this the same way, no matter which route led here.
-  if (nrow(tbl) == 0) {
-    fix_path <- \(p) sub("^/+$", "", sub("^([^/])(.*)", "/\\1\\2", p)) # nolint
-    ext <- if (nzchar(ext)) paste0(" ", ext)
-    msg <- "No{ext} files found in {.val [{container$name}]:{fix_path(path)}}"
-    if (rlang::is_interactive()) {
-      cli::cli_alert_info(msg)
-    }
-    invisible(character(0))
-  } else {
-    tbl[["name"]]
-  }
-}
+#' List files in a container
+#'
+#' Recursively (or not, if desired) lists all files found in a container. Search
+#' can be restricted to a particular 'subdirectory' of the container, and/or
+#' to files with a specific extension. The function assumes that all file names
+#' end with a ".ext" extension of some sort.
+#'
+#' The function does not support filtering by file name, only by file extension.
+#'
+#' The returned file list (character vector) contains the full paths to the
+#' files, ready to be passed perhaps to a `read_azure_*` function, or further
+#' filtered by you. If you just want the names of the files without the folder
+#' path, use [basename()] to extract these.
+#'
+#' @inheritParams read_azure_parquet
+#' @param path (optional) subdirectory of the container to list files within.
+#'  `""` (the root folder of the container) by default
+#' @param ext (optional) A string giving the extension of a particular file type
+#'  you want to restrict the list to. No need to include the initial ".". The
+#'  default, `""`, means no filtering by file extension will be applied. Can be
+#'  a regular expression.
+#' @param recursive A Boolean value: whether to list files recursively. `TRUE`
+#'  by default
+#'
+#' @importFrom rlang .data
+#' @returns A vector of file names, or an empty character vector if none found
+#' @examples \dontrun{
+#'   list_files(get_container("example"), ext = "csv")
+#' }
+#' @export
+list_files <- function(container, path = "", ext = "", recursive = TRUE) {
+  stopifnot(rlang::is_character(c(path, ext), 2))
+  stopifnot(rlang::is_bool(recursive))
+  pnf_msg <- ct_error_msg("Path {.val {path}} not found")
+  check_that(path, \(x) AzureStor::blob_dir_exists(container, x), pnf_msg)
+
+  tbl <- AzureStor::list_blobs(container, path, recursive = recursive)
+  if (nrow(tbl) > 0) {
+    ext_rx <- if (nzchar(ext)) sub("^\\.+", "", ext) else ".*" # nolint
+    tbl <- tbl |>
+      dplyr::filter(!.data[["isdir"]] & gregg(.data[["name"]], "\\.{ext_rx}$"))
+  }
+
+  # A zero-row tbl can result if `path` is initially empty, or via the filter
+  # step above. We handle this the same way, no matter which route led here.
+  if (nrow(tbl) == 0) {
+    fix_path <- \(p) sub("^/+$", "", sub("^([^/])(.*)", "/\\1\\2", p)) # nolint
+    ext <- if (nzchar(ext)) paste0(" ", ext)
+    msg <- "No{ext} files found in {.val [{container$name}]:{fix_path(path)}}"
+    if (rlang::is_interactive()) {
+      cli::cli_alert_info(msg)
+    }
+    invisible(character(0))
+  } else {
+    tbl[["name"]]
+  }
+}