You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by GitBox <gi...@apache.org> on 2022/02/14 21:58:48 UTC

[GitHub] [arrow] jonkeane commented on a change in pull request #12324: ARROW-15013: [R] Expose concatenate at the R level

jonkeane commented on a change in pull request #12324:
URL: https://github.com/apache/arrow/pull/12324#discussion_r806267955



##########
File path: r/tests/testthat/test-Array.R
##########
@@ -989,6 +989,59 @@ test_that("auto int64 conversion to int can be disabled (ARROW-10093)", {
   })
 })
 
+test_that("concat_arrays works", {
+  concat_empty <- concat_arrays()
+  expect_true(concat_empty$type == null())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_empty_typed <- concat_arrays(type = int64())
+  expect_true(concat_empty_typed$type == int64())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_int <- concat_arrays(Array$create(1:3), Array$create(4:5))
+  expect_true(concat_int$type == int32())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  concat_int64 <- concat_arrays(
+    Array$create(1:3),
+    Array$create(4:5, type = int64()),
+    type = int64()
+  )
+  expect_true(concat_int64$type == int64())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  expect_error(
+    concat_arrays(
+      Array$create(1:3),
+      Array$create(4:5, type = int64())
+    ),
+    "must be identically typed"
+  )
+})
+
+test_that("c() works for Array", {
+  expect_r6_class(c(Array$create(1L), Array$create(1L)), "Array")
+
+  struct <- call_function(
+    "make_struct",
+    Array$create(1L),
+    options = list(field_names = "")
+  )
+  expect_r6_class(c(struct, struct), "StructArray")
+
+  list <- Array$create(list(1))
+  expect_r6_class(c(list, list), "ListArray")
+
+  list <- Array$create(list(), type = large_list_of(float64()))
+  expect_r6_class(c(list, list), "LargeListArray")
+
+  list <- Array$create(list(),type = fixed_size_list_of(float64(), 1L))
+  expect_r6_class(c(list, list), "FixedSizeListArray")
+
+  list <- Array$create(list(),type = map_of(string(), float64()))

Review comment:
       ```suggestion
     list <- Array$create(list(), type = map_of(string(), float64()))
   ```

##########
File path: r/tests/testthat/test-Array.R
##########
@@ -989,6 +989,59 @@ test_that("auto int64 conversion to int can be disabled (ARROW-10093)", {
   })
 })
 
+test_that("concat_arrays works", {
+  concat_empty <- concat_arrays()
+  expect_true(concat_empty$type == null())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_empty_typed <- concat_arrays(type = int64())
+  expect_true(concat_empty_typed$type == int64())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_int <- concat_arrays(Array$create(1:3), Array$create(4:5))
+  expect_true(concat_int$type == int32())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  concat_int64 <- concat_arrays(
+    Array$create(1:3),
+    Array$create(4:5, type = int64()),
+    type = int64()
+  )
+  expect_true(concat_int64$type == int64())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  expect_error(
+    concat_arrays(
+      Array$create(1:3),
+      Array$create(4:5, type = int64())
+    ),
+    "must be identically typed"
+  )
+})
+
+test_that("c() works for Array", {
+  expect_r6_class(c(Array$create(1L), Array$create(1L)), "Array")
+
+  struct <- call_function(
+    "make_struct",
+    Array$create(1L),
+    options = list(field_names = "")
+  )
+  expect_r6_class(c(struct, struct), "StructArray")
+
+  list <- Array$create(list(1))
+  expect_r6_class(c(list, list), "ListArray")
+
+  list <- Array$create(list(), type = large_list_of(float64()))
+  expect_r6_class(c(list, list), "LargeListArray")
+
+  list <- Array$create(list(),type = fixed_size_list_of(float64(), 1L))

Review comment:
       ```suggestion
     list <- Array$create(list(), type = fixed_size_list_of(float64(), 1L))
   ```

##########
File path: r/tests/testthat/test-Array.R
##########
@@ -989,6 +989,59 @@ test_that("auto int64 conversion to int can be disabled (ARROW-10093)", {
   })
 })
 
+test_that("concat_arrays works", {
+  concat_empty <- concat_arrays()
+  expect_true(concat_empty$type == null())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_empty_typed <- concat_arrays(type = int64())
+  expect_true(concat_empty_typed$type == int64())
+  expect_equal(concat_empty$length(), 0L)
+
+  concat_int <- concat_arrays(Array$create(1:3), Array$create(4:5))
+  expect_true(concat_int$type == int32())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  concat_int64 <- concat_arrays(
+    Array$create(1:3),
+    Array$create(4:5, type = int64()),
+    type = int64()
+  )
+  expect_true(concat_int64$type == int64())
+  expect_true(all(concat_int == Array$create(1:5)))
+
+  expect_error(
+    concat_arrays(
+      Array$create(1:3),
+      Array$create(4:5, type = int64())
+    ),
+    "must be identically typed"
+  )
+})
+
+test_that("c() works for Array", {

Review comment:
       Could? Should? you also test for things like `c(Array$create(1L), 2L)` I imagine that would error, but does it with an informative message? 

##########
File path: r/R/array.R
##########
@@ -216,6 +216,76 @@ Array$create <- function(x, type = NULL) {
 #' @include arrowExports.R
 Array$import_from_c <- ImportArray
 
+
+#' Concatenate zero or more Arrays
+#'
+#' @param ... zero or more [Array] objects to concatenate
+#' @param type An optional `type` describing the desired
+#'   type for the final Array.
+#'
+#' @return An [Array]
+#' @export
+#'
+#' @examples
+#' concat_arrays(Array$create(1:3), Array$create(4:5))
+#'
+concat_arrays <- function(..., type = NULL) {
+  dots <- lapply(list2(...), Array$create, type = type)
+
+  if (length(dots) == 0 && is.null(type)) {
+    return(Array$create(logical(), type = null()))
+  } else if (length(dots) == 0) {
+    return(Array$create(logical(), type = null())$cast(type))
+  }
+
+  if (!is.null(type)) {
+    dots <- lapply(dots, function(array) array$cast(type))
+  }
+
+  arrow__Concatenate(dots)
+}
+
+# The c() method uses non-standard dispatch in R
+# and has some peculiarities when multiple types are passed to ....
+# However, with a method defined for all subclasses of Array, it will
+# do what a user expects most of the time.

Review comment:
       Out of (morbid?) curiosity: what does it do without the subclasses? 




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org