Start nanoparquet format

NAMESPACE

@@ -20,6 +20,7 @@ S3method(print,tar_resources_feather)
 S3method(print,tar_resources_fst)
 S3method(print,tar_resources_future)
 S3method(print,tar_resources_gcp)
+S3method(print,tar_resources_nanoparquet)
 S3method(print,tar_resources_network)
 S3method(print,tar_resources_parquet)
 S3method(print,tar_resources_qs)
@@ -34,12 +35,14 @@ S3method(resources_validate,tar_resources_feather)
 S3method(resources_validate,tar_resources_fst)
 S3method(resources_validate,tar_resources_future)
 S3method(resources_validate,tar_resources_gcp)
+S3method(resources_validate,tar_resources_nanoparquet)
 S3method(resources_validate,tar_resources_network)
 S3method(resources_validate,tar_resources_parquet)
 S3method(resources_validate,tar_resources_qs)
 S3method(resources_validate,tar_resources_url)
 S3method(store_assert_format,default)
 S3method(store_assert_format,tar_feather)
+S3method(store_assert_format,tar_nanoparquet)
 S3method(store_assert_format,tar_parquet)
 S3method(store_assert_format,tar_store_file)
 S3method(store_assert_format,tar_url)
@@ -54,6 +57,7 @@ S3method(store_assert_format_setting,fst_dt)
 S3method(store_assert_format_setting,fst_tbl)
 S3method(store_assert_format_setting,gcp_file)
 S3method(store_assert_format_setting,keras)
+S3method(store_assert_format_setting,nanoparquet)
 S3method(store_assert_format_setting,parquet)
 S3method(store_assert_format_setting,qs)
 S3method(store_assert_format_setting,rds)
@@ -74,6 +78,7 @@ S3method(store_class_format,fst)
 S3method(store_class_format,fst_dt)
 S3method(store_class_format,fst_tbl)
 S3method(store_class_format,keras)
+S3method(store_class_format,nanoparquet)
 S3method(store_class_format,parquet)
 S3method(store_class_format,qs)
 S3method(store_class_format,rds)
@@ -86,6 +91,7 @@ S3method(store_convert_object,tar_feather)
 S3method(store_convert_object,tar_fst)
 S3method(store_convert_object,tar_fst_dt)
 S3method(store_convert_object,tar_fst_tbl)
+S3method(store_convert_object,tar_nanoparquet)
 S3method(store_convert_object,tar_parquet)
 S3method(store_convert_object,tar_store_custom)
 S3method(store_convert_object,tar_store_file)
@@ -112,6 +118,7 @@ S3method(store_get_packages,tar_fst_dt)
 S3method(store_get_packages,tar_fst_tbl)
 S3method(store_get_packages,tar_gcp)
 S3method(store_get_packages,tar_keras)
+S3method(store_get_packages,tar_nanoparquet)
 S3method(store_get_packages,tar_parquet)
 S3method(store_get_packages,tar_qs)
 S3method(store_get_packages,tar_torch)
@@ -162,6 +169,7 @@ S3method(store_read_path,tar_fst)
 S3method(store_read_path,tar_fst_dt)
 S3method(store_read_path,tar_fst_tbl)
 S3method(store_read_path,tar_keras)
+S3method(store_read_path,tar_nanoparquet)
 S3method(store_read_path,tar_parquet)
 S3method(store_read_path,tar_qs)
 S3method(store_read_path,tar_rds)
@@ -205,6 +213,7 @@ S3method(store_write_object,tar_url)
 S3method(store_write_path,tar_feather)
 S3method(store_write_path,tar_fst)
 S3method(store_write_path,tar_keras)
+S3method(store_write_path,tar_nanoparquet)
 S3method(store_write_path,tar_parquet)
 S3method(store_write_path,tar_qs)
 S3method(store_write_path,tar_rds)
@@ -477,6 +486,7 @@ export(tar_resources_feather)
 export(tar_resources_fst)
 export(tar_resources_future)
 export(tar_resources_gcp)
+export(tar_resources_nanoparquet)
 export(tar_resources_network)
 export(tar_resources_parquet)
 export(tar_resources_qs)

R/class_nanoparquet.R

@@ -0,0 +1,66 @@
+#' @export
+store_class_format.nanoparquet <- function(format) {
+  c("tar_nanoparquet", "tar_store")
+}
+
+#' @export
+store_assert_format_setting.nanoparquet <- function(format) {
+}
+
+#' @export
+store_read_path.tar_nanoparquet <- function(store, path) {
+  object <- getNamespace("nanoparquet")[["read_parquet"]](
+    file = path,
+    options = store_nanoparquet_options()
+  )
+  metadata <- getNamespace("nanoparquet")[["parquet_metadata"]](file = path)
+  classes <- metadata$file_meta_data$key_value_metadata[[1L]]
+  class(object) <- classes$value[classes$key == "class"]
+  object
+}
+
+#' @export
+store_write_path.tar_nanoparquet <- function(store, object, path) {
+  metadata <- class(object)
+  names(metadata) <- rep("class", length(metadata))
+  getNamespace("nanoparquet")[["write_parquet"]](
+    x = object,
+    file = path,
+    metadata = metadata,
+    compression = store$resources$nanoparquet[["compression"]],
+    options = store_nanoparquet_options()
+  )
+}
+
+#' @export
+store_assert_format.tar_nanoparquet <- function(store, object, name) { # nolint
+  msg <- paste(
+    "target",
+    name,
+    "has nanoparquet format, so it must be a data frame",
+    "which can be converted to a tibble."
+  )
+  tar_assert_inherits(
+    x = object %|||% data.frame(),
+    class = "data.frame",
+    msg = msg
+  )
+}
+
+#' @export
+store_convert_object.tar_nanoparquet <- function(store, object) {
+  if_any(is.null(object), as.data.frame(NULL), object)
+}
+
+#' @export
+store_get_packages.tar_nanoparquet <- function(store) {
+  "nanoparquet"
+}
+
+store_nanoparquet_options <- function() {
+  getNamespace("nanoparquet")[["parquet_options"]](
+    class = character(0L),
+    use_arrow_metadata = TRUE,
+    write_arrow_metadata = TRUE
+  )
+}

R/class_resources_nanoparquet.R

@@ -0,0 +1,29 @@
+resources_nanoparquet_init <- function(
+  compression = "snappy"
+) {
+  resources_nanoparquet_new(
+    compression = compression
+  )
+}
+
+resources_nanoparquet_new <- function(
+  compression = NULL
+) {
+  force(compression)
+  enclass(environment(), c("tar_resources_nanoparquet", "tar_resources"))
+}
+
+#' @export
+resources_validate.tar_resources_nanoparquet <- function(resources) {
+  tar_assert_scalar(resources$compression)
+  tar_assert_chr(resources$compression)
+  tar_assert_nzchar(resources$compression)
+}
+
+#' @export
+print.tar_resources_nanoparquet <- function(x, ...) {
+  cat(
+    "<tar_resources_nanoparquet>\n ",
+    paste0(paste_list(as.list(x)), collapse = "\n  ")
+  )
+}

R/tar_resources.R

@@ -53,7 +53,7 @@
 #' @param feather Output of function [tar_resources_feather()].
 #'   Non-default arguments to `arrow::read_feather()` and
 #'   `arrow::write_feather()` for `arrow`/feather-based storage formats.
-#'   Applies to all formats ending with the `"_feather"` suffix.
+#'   Applies to the `"feather"` storage format.
 #'   For details on formats, see the `format` argument of [tar_target()].
 #' @param fst Output of function `tar_resources_fst()`.
 #'   Non-default arguments to `fst::read_fst()` and
@@ -75,6 +75,12 @@
 #'   See the cloud storage section of
 #'   <https://books.ropensci.org/targets/data.html>
 #'   for details for instructions.
+#' @param nanoparquet Output of function `tar_resources_nanoparquet()`.
+#'   Non-default arguments to `nanoparquet::read_parquet()` and
+#'   `nanoparquet::write_parquet()` for `arrow`/parquet-based storage formats.
+#'   Applies to the `"nanoparquet"` storage format.
+#'   For details on formats, see the `format` argument of [tar_target()].
+#' @param qs Output of function `tar_resources_qs()`.
 #' @param network Output of function `tar_resources_network()`.
 #'   Settings to configure how to handle unreliable network connections
 #'   in the case of uploading, downloading, and checking data
@@ -88,7 +94,7 @@
 #' @param parquet Output of function `tar_resources_parquet()`.
 #'   Non-default arguments to `arrow::read_parquet()` and
 #'   `arrow::write_parquet()` for `arrow`/parquet-based storage formats.
-#'   Applies to all formats ending with the `"_parquet"` suffix.
+#'   Applies to the `"parquet"` storage format.
 #'   For details on formats, see the `format` argument of [tar_target()].
 #' @param qs Output of function `tar_resources_qs()`.
 #'   Non-default arguments to `qs::qread()` and
@@ -120,6 +126,7 @@ tar_resources <- function(
   fst = tar_option_get("resources")$fst,
   future = tar_option_get("resources")$future,
   gcp = tar_option_get("resources")$gcp,
+  nanoparquet = tar_option_get("resources")$nanoparquet,
   network = tar_option_get("resources")$network,
   parquet = tar_option_get("resources")$parquet,
   qs = tar_option_get("resources")$qs,

R/tar_resources_nanoparquet.R

@@ -0,0 +1,32 @@
+#' @title Target resources: nanoparquet storage format
+#' @export
+#' @family resources
+#' @description Create the nanoparquet argument of `tar_resources()`
+#'   to specify optional settings for nanoparquet data frame storage formats
+#'   powered by the `nanoparquet` R package.
+#'   See the `format` argument of [tar_target()] for details.
+#' @inheritSection tar_resources Resources
+#' @return Object of class `"tar_resources_nanoparquet"`, to be supplied
+#'   to the nanoparquet argument of `tar_resources()`.
+#' @param compression Character of length 1, `compression`
+#'   argument of `nanoparquet::write_parquet()`. Defaults to `"snappy"`.
+#' @examples
+#' # Somewhere in you target script file (usually _targets.R):
+#' tar_target(
+#'   name,
+#'   command(),
+#'   format = "nanoparquet",
+#'   resources = tar_resources(
+#'     nanoparquet = tar_resources_nanoparquet(compression = "zstd")
+#'   )
+#' )
+tar_resources_nanoparquet <- function(
+  compression = targets::tar_option_get("resources")$nanoparquet$compression
+) {
+  compression <- compression %|||% "snappy"
+  out <- resources_nanoparquet_init(
+    compression = compression
+  )
+  resources_validate(out)
+  out
+}

R/tar_target.R

@@ -28,18 +28,22 @@
 #'   * `"qs"`: Uses `qs::qsave()` and `qs::qread()`. Should work for
 #'     most objects, much faster than `"rds"`. Optionally set the
 #'     preset for `qsave()` through `tar_resources()` and `tar_resources_qs()`.
-#'   * `"feather"`: Uses `arrow::write_feather()` and
-#'     `arrow::read_feather()` (version 2.0). Much faster than `"rds"`,
-#'     but the value must be a data frame. Optionally set
-#'     `compression` and `compression_level` in `arrow::write_feather()`
-#'     through `tar_resources()` and `tar_resources_feather()`.
-#'     Requires the `arrow` package (not installed by default).
+#'   * `"nanoparquet"`: Uses `nanoparquet::write_parquet()` and
+#'     `nanoparquet::read_parquet()`. Much faster than `"rds"`, but
+#'     the value must be a data frame and is converted into a `tibble`.
+#'     Requires the `nanoparquet` package (not installed by default).
 #'   * `"parquet"`: Uses `arrow::write_parquet()` and
 #'     `arrow::read_parquet()` (version 2.0). Much faster than `"rds"`,
 #'     but the value must be a data frame. Optionally set
 #'     `compression` and `compression_level` in `arrow::write_parquet()`
 #'     through `tar_resources()` and `tar_resources_parquet()`.
 #'     Requires the `arrow` package (not installed by default).
+#'   * `"feather"`: Uses `arrow::write_feather()` and
+#'     `arrow::read_feather()` (version 2.0). Much faster than `"rds"`,
+#'     but the value must be a data frame. Optionally set
+#'     `compression` and `compression_level` in `arrow::write_feather()`
+#'     through `tar_resources()` and `tar_resources_feather()`.
+#'     Requires the `arrow` package (not installed by default).
 #'   * `"fst"`: Uses `fst::write_fst()` and `fst::read_fst()`.
 #'     Much faster than `"rds"`, but the value must be
 #'     a data frame. Optionally set the compression level for