ARROW-14442: [R] fix behaviour when converting timestamps with "" as tzone

r/R/arrow-package.R

@@ -23,7 +23,7 @@
 #' @importFrom rlang eval_tidy new_data_mask syms env new_environment env_bind set_names exec
 #' @importFrom rlang is_bare_character quo_get_expr quo_get_env quo_set_expr .data seq2 is_interactive
 #' @importFrom rlang expr caller_env is_character quo_name is_quosure enexpr enexprs as_quosure
-#' @importFrom rlang is_list call2 is_empty as_function
+#' @importFrom rlang is_list call2 is_empty as_function inform
 #' @importFrom tidyselect vars_pull vars_rename vars_select eval_select
 #' @useDynLib arrow, .registration = TRUE
 #' @keywords internal

r/src/type_infer.cpp

@@ -72,7 +72,8 @@ std::shared_ptr<arrow::DataType> InferArrowTypeFromVector<INTSXP>(SEXP x) {
   } else if (Rf_inherits(x, "POSIXct")) {
     auto tzone_sexp = Rf_getAttrib(x, symbols::tzone);
     if (Rf_isNull(tzone_sexp)) {
-      return timestamp(TimeUnit::MICRO);
+      auto systzone_sexp = cpp11::package("base")["Sys.timezone"];
+      return timestamp(TimeUnit::MICRO, CHAR(STRING_ELT(systzone_sexp(), 0)));
     } else {
       return timestamp(TimeUnit::MICRO, CHAR(STRING_ELT(tzone_sexp, 0)));
     }
@@ -88,7 +89,8 @@ std::shared_ptr<arrow::DataType> InferArrowTypeFromVector<REALSXP>(SEXP x) {
   if (Rf_inherits(x, "POSIXct")) {
     auto tzone_sexp = Rf_getAttrib(x, symbols::tzone);
     if (Rf_isNull(tzone_sexp)) {
-      return timestamp(TimeUnit::MICRO);
+      auto systzone_sexp = cpp11::package("base")["Sys.timezone"];
+      return timestamp(TimeUnit::MICRO, CHAR(STRING_ELT(systzone_sexp(), 0)));
     } else {
       return timestamp(TimeUnit::MICRO, CHAR(STRING_ELT(tzone_sexp, 0)));
     }

r/tests/testthat/test-Array.R

@@ -260,18 +260,39 @@ test_that("array supports POSIXct (ARROW-3340)", {
   expect_array_roundtrip(times2, timestamp("us", "US/Eastern"))
 })
 
-test_that("array supports POSIXct without timezone", {
-  # Make sure timezone is not set
-  withr::with_envvar(c(TZ = ""), {
+test_that("array uses local timezone for POSIXct without timezone", {
+  withr::with_timezone("", {
     times <- strptime("2019-02-03 12:34:56", format = "%Y-%m-%d %H:%M:%S") + 1:10
-    expect_array_roundtrip(times, timestamp("us", ""))
+    expect_equal(attr(times, "tzone"), NULL)
+    expect_array_roundtrip(times, timestamp("us", Sys.timezone()))
 
     # Also test the INTSXP code path
     skip("Ingest_POSIXct only implemented for REALSXP")
     times_int <- as.integer(times)
     attributes(times_int) <- attributes(times)
     expect_array_roundtrip(times_int, timestamp("us", ""))
   })
+
+  # If there is a timezone set, we record that
+  withr::with_timezone("Pacific/Marquesas", {
+    times <- strptime("2019-02-03 12:34:56", format = "%Y-%m-%d %H:%M:%S") + 1:10
+    expect_equal(attr(times, "tzone"), "Pacific/Marquesas")
+    expect_array_roundtrip(times, timestamp("us", "Pacific/Marquesas"))
+
+    times_with_tz <- strptime(
+      "2019-02-03 12:34:56",
+      format = "%Y-%m-%d %H:%M:%S",
+      tz = "Asia/Katmandu") + 1:10
+    expect_equal(attr(times, "tzone"), "Asia/Katmandu")
+    expect_array_roundtrip(times, timestamp("us", "Asia/Katmandu"))
+  })
+
+  # and although the TZ is NULL in R, we set it to the Sys.timezone()
+  withr::with_timezone(NA, {
+    times <- strptime("2019-02-03 12:34:56", format = "%Y-%m-%d %H:%M:%S") + 1:10
+    expect_equal(attr(times, "tzone"), NULL)
+    expect_array_roundtrip(times, timestamp("us", Sys.timezone()))
+  })
 })
 
 test_that("Timezone handling in Arrow roundtrip (ARROW-3543)", {

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

@@ -651,7 +651,6 @@ test_that("extract yday from date", {
 })
 
 test_that("leap_year mirror lubridate", {
-
   compare_dplyr_binding(
     .input %>%
       mutate(x = leap_year(date)) %>%
@@ -679,7 +678,6 @@ test_that("leap_year mirror lubridate", {
       ))
     )
   )
-
 })
 
 test_that("am/pm mirror lubridate", {
@@ -699,10 +697,8 @@ test_that("am/pm mirror lubridate", {
         ),
         format = "%Y-%m-%d %H:%M:%S"
       )
-
     )
   )
-
 })
 
 test_that("extract tz", {