Add type = "parquet"

NEWS.md

@@ -4,6 +4,8 @@
 
 * `board_s3()` now uses pagination for listing and versioning (#719, @mzorko).
 
+* Added `type = "parquet"` to read and write Parquet files (#729).
+
 # pins 1.1.0
 
 ## Breaking changes

R/pin-read-write.R

@@ -56,9 +56,9 @@ pin_read <- function(board, name, version = NULL, hash = NULL, ...) {
 #'   When retrieving the pin, this will be stored in the `user` key, to
 #'   avoid potential clashes with the metadata that pins itself uses.
 #' @param type File type used to save `x` to disk. Must be one of
-#'   "csv", "json", "rds", "arrow", or "qs". If not supplied, will use JSON for
-#'   bare lists and RDS for everything else. Be aware that CSV and JSON are
-#'   plain text formats, while RDS, Arrow, and
+#'   "csv", "json", "rds", "parquet", "arrow", or "qs". If not supplied, will
+#'   use JSON for bare lists and RDS for everything else. Be aware that CSV and
+#'   JSON are plain text formats, while RDS, Parquet, Arrow, and
 #'   [qs](https://CRAN.R-project.org/package=qs) are binary formats.
 #' @param versioned Should the pin be versioned? The default, `NULL`, will
 #'   use the default for `board`
@@ -133,6 +133,7 @@ object_write <- function(x, path, type = "rds") {
   switch(type,
     rds = write_rds(x, path),
     json = jsonlite::write_json(x, path, auto_unbox = TRUE),
+    parquet = write_parquet(x, path),
     arrow = write_arrow(x, path),
     pickle = abort("'pickle' pins not supported in R"),
     joblib = abort("'joblib' pins not supported in R"),
@@ -168,13 +169,19 @@ write_qs <- function(x, path) {
   invisible(path)
 }
 
+write_parquet <- function(x, path) {
+  check_installed("arrow")
+  arrow::write_parquet(x, path)
+  invisible(path)
+}
+
 write_arrow <- function(x, path) {
   check_installed("arrow")
   arrow::write_feather(x, path)
   invisible(path)
 }
 
-object_types <- c("rds", "json", "arrow", "pickle", "csv", "qs", "file")
+object_types <- c("rds", "json", "parquet", "arrow", "pickle", "csv", "qs", "file")
 
 object_read <- function(meta) {
   path <- fs::path(meta$local$dir, meta$file)
@@ -189,6 +196,7 @@ object_read <- function(meta) {
     switch(type,
       rds = readRDS(path),
       json = jsonlite::read_json(path, simplifyVector = TRUE),
+      parquet = read_parquet(path),
       arrow = read_arrow(path),
       pickle = abort("'pickle' pins not supported in R"),
       joblib = abort("'joblib' pins not supported in R"),
@@ -217,6 +225,11 @@ read_qs <- function(path) {
   qs::qread(path, strict = TRUE)
 }
 
+read_parquet <- function(path) {
+  check_installed("arrow")
+  arrow::read_parquet(path)
+}
+
 read_arrow <- function(path) {
   check_installed("arrow")
   arrow::read_feather(path)

README.Rmd

@@ -70,7 +70,7 @@ It takes three arguments: the board to pin to, an object, and a name:
 board %>% pin_write(head(mtcars), "mtcars")
 ```
 
-As you can see, the data saved as an `.rds` by default, but depending on what you're saving and who else you want to read it, you might use the `type` argument to instead save it as a `csv`, `json`, or `arrow` file.
+As you can see, the data saved as an `.rds` by default, but depending on what you're saving and who else you want to read it, you might use the `type` argument to instead save it as a Parquet, Arrow, CSV, or JSON file.
 
 You can later retrieve the pinned data with `pin_read()`:
 

README.md

@@ -61,7 +61,7 @@ board <- board_temp()
 board
 #> Pin board <pins_board_folder>
 #> Path:
-#> '/var/folders/hv/hzsmmyk9393_m7q3nscx1slc0000gn/T/RtmpTxyyP1/pins-114c073a9ddd2'
+#> '/var/folders/hv/hzsmmyk9393_m7q3nscx1slc0000gn/T/RtmpwGre3p/pins-15a8b4f3f602c'
 #> Cache size: 0
 ```
 
@@ -71,13 +71,14 @@ arguments: the board to pin to, an object, and a name:
 ``` r
 board %>% pin_write(head(mtcars), "mtcars")
 #> Guessing `type = 'rds'`
-#> Creating new version '20230223T220424Z-a800d'
+#> Creating new version '20230303T233508Z-a800d'
 #> Writing to pin 'mtcars'
 ```
 
 As you can see, the data saved as an `.rds` by default, but depending on
 what you’re saving and who else you want to read it, you might use the
-`type` argument to instead save it as a `csv`, `json`, or `arrow` file.
+`type` argument to instead save it as a Parquet, Arrow, CSV, or JSON
+file.
 
 You can later retrieve the pinned data with `pin_read()`:
 

tests/testthat/_snaps/pin-read-write.md

@@ -23,7 +23,7 @@
       pin_write(board, mtcars, name = "mtcars", type = "froopy-loops")
     Condition
       Error in `object_write()`:
-      ! `type` must be one of "rds", "json", "arrow", "pickle", "csv", or "qs", not "froopy-loops".
+      ! `type` must be one of "rds", "json", "parquet", "arrow", "pickle", "csv", or "qs", not "froopy-loops".
     Code
       pin_write(board, mtcars, name = "mtcars", metadata = 1)
     Condition

tests/testthat/test-pin-read-write.R

@@ -8,13 +8,16 @@ test_that("can round trip all types", {
   pin_write(board, df, "df-1", type = "rds")
   expect_equal(pin_read(board, "df-1"), df)
 
-  pin_write(board, df, "df-2", type = "arrow")
+  pin_write(board, df, "df-2", type = "parquet")
   expect_equal(pin_read(board, "df-2"), df)
 
-  pin_write(board, df, "df-3", type = "csv")
+  pin_write(board, df, "df-3", type = "arrow")
+  expect_equal(pin_read(board, "df-2"), df)
+
+  pin_write(board, df, "df-4", type = "csv")
   expect_equal(pin_read(board, "df-3"), df)
 
-  pin_write(board, df, "df-4", type = "qs")
+  pin_write(board, df, "df-5", type = "qs")
   expect_equal(pin_read(board, "df-4"), df)
 
   # List

vignettes/pins.Rmd

@@ -63,7 +63,8 @@ But you can choose another option depending on your goals:
 
 -   `type = "rds"` uses `writeRDS()` to create a binary R data file. It can save any R object but it's only readable from R, not other languages.
 -   `type = "csv"` uses `write.csv()` to create a `.csv` file. CSVs can read by any application, but only support simple columns (e.g. numbers, strings, dates), can take up a lot of disk space, and can be slow to read.
--   `type = "arrow"` uses `arrow::write_feather()` to create an arrow/feather file. [Arrow](https://arrow.apache.org) is a modern, language-independent, high-performance file format designed for data science. Not every tool can read arrow files, but support is growing rapidly.
+-   `type = "parquet"` uses `arrow::write_parquet()` to create a Parquet file. [Parquet](https://parquet.apache.org/) is a modern, language-independent, column-oriented file format for efficient data storage and retrieval. Parquet is a storage format used with [Arrow](https://arrow.apache.org), an in-memory columnar format.
+-   `type = "arrow"` uses `arrow::write_feather()` to create an Arrow/Feather file. Read the [FAQs from the Arrow project](https://arrow.apache.org/faq/) for more on the differences between Arrow and Parquet as file formats.
 -   `type = "json"` uses `jsonlite::write_json()` to create a `.json` file. Pretty much every programming language can read json files, but they only work well for nested lists.
 -   `type = "qs"` uses `qs::qsave()` to create a binary R data file, like `writeRDS()`. This format achieves faster read/write speeds than RDS, and compresses data more efficiently, making it a good choice for larger objects. Read more on the [qs package](https://github.com/traversc/qs).