ARROW-15802 [R] bindings for lubridate::make_datetime() and lubridate::make_date()

r/NEWS.md

@@ -22,6 +22,7 @@
 * `read_csv_arrow()`'s readr-style type `T` is now mapped to `timestamp(unit = "ns")` instead of `timestamp(unit = "s")`.
 * `lubridate`:
   * component extraction functions: `tz()` (timezone), `semester()` (semester), `dst()` (daylight savings time indicator), `date()` (extract date), `epiyear()` (epiyear), improvements to `month()`, which now works with integer inputs.
+  * `make_date()` and `make_datetime()` to create `Date` objects from numeric parts. 
 * date-time functionality:
   * `as.Date()` to convert to date
 

r/R/dplyr-funcs-datetime.R

@@ -187,6 +187,27 @@ register_bindings_datetime <- function() {
   register_binding("date", function(x) {
     build_expr("cast", x, options = list(to_type = date32()))
   })
+  register_binding("make_date", function(year = 1970L, month = 1L, day = 1L) {
+    x <- call_binding("paste", year, month, day, sep = "-")
+    x <- call_binding("strptime", x, format = "%Y-%m-%d", unit = "s")
+    build_expr("cast", x, options = cast_options(to_type = date32()))
+  })
+  register_binding("make_datetime", function(year = 1970L,
+                                             month = 1L,
+                                             day = 1L,
+                                             hour = 0L,
+                                             min = 0L,
+                                             sec = 0,
+                                             tz = NULL) {
+  x <- call_binding("paste", year, month, day, hour, min, sec, sep = "-")
+  # ParseTimestampStrptime currently ignores the timezone information (ARROW-12820).
+  # Stop if tz is provided.
+  if (is.character(tz)) {
+    arrow_not_supported("Time zone argument")
+  }
+
+  build_expr("strptime", x, options = list(format = "%Y-%m-%d-%H-%M-%S", unit = 0L))
+  })
 }
 
 binding_format_datetime <- function(x, format = "", tz = "", usetz = FALSE) {

r/tests/testthat/test-dplyr-funcs-datetime.R

@@ -974,3 +974,50 @@ test_that("date() errors with unsupported inputs", {
     regexp = "Unsupported cast from double to date32 using function cast_date32"
   )
 })
+
+test_that("make_date & make_datetime", {
+  set.seed(12345)
+  test_df <- tibble(
+    year = sample(1969:2069, 12),
+    month = 1:12,
+    day = sample(1:28, 12, replace = TRUE),
+    hour = sample(0:23, 12, replace = TRUE),
+    min = sample(0:59, 12),
+    sec = sample(0:59, 12)
+  )
+
+  compare_dplyr_binding(
+    .input %>%
+      mutate(composed_date = make_date(year, month, day)) %>%
+      collect(),
+    test_df
+  )
+
+  compare_dplyr_binding(
+    .input %>%
+      mutate(composed_date_r_obj = make_date(1999, 12, 31)) %>%
+      collect(),
+    test_df
+  )
+
+  compare_dplyr_binding(
+    .input %>%
+      mutate(composed_datetime = make_datetime(year, month, day, hour, min, sec)) %>%
+      collect(),
+    test_df,
+    # the make_datetime binding uses strptime which does not support tz, hence
+    # a mismatch in tzone attribute (ARROW-12820)
+    ignore_attr = TRUE
+  )
+
+  compare_dplyr_binding(
+    .input %>%
+      mutate(
+        composed_datetime_r_obj = make_datetime(1999, 12, 31, 14, 15, 16)) %>%
+      collect(),
+    test_df,
+    # the make_datetime binding uses strptime which does not support tz, hence
+    # a mismatch in tzone attribute (ARROW-12820)
+    ignore_attr = TRUE
+  )
+})