ARROW-12198: [R] bindings for strptime

r/R/dplyr-functions.R

@@ -338,3 +338,20 @@ get_stringr_pattern_options <- function(pattern) {
 contains_regex <- function(string) {
   grepl("[.\\|()[{^$*+?]", string)
 }
+
+nse_funcs$strptime <- function(x, format = "%Y-%m-%d %H:%M:%S", tz = NULL, unit = "ms") {
+  # Arrow uses unit for time parsing, strptime() does not.
+  # Arrow has no default option for strptime (format, unit),
+  # we suggest following format = "%Y-%m-%d %H:%M:%S", unit = MILLI/1L/"ms",
+  # (ARROW-12809)
+
+  # ParseTimestampStrptime currently ignores the timezone information (ARROW-12820).
+  # Stop if tz is provided.
+  if (is.character(tz)) {
+    arrow_not_supported("Time zone argument")
+  }
+
+  unit <- make_valid_time_unit(unit, c(valid_time64_units, valid_time32_units))
+
+  Expression$create("strptime", x, options = list(format = format, unit = unit))
+}

r/src/compute.cpp

@@ -234,6 +234,13 @@ std::shared_ptr<arrow::compute::FunctionOptions> make_compute_options(
                                      max_replacements);
   }
 
+  if (func_name == "strptime") {
+    using Options = arrow::compute::StrptimeOptions;
+    return std::make_shared<Options>(
+        cpp11::as_cpp<std::string>(options["format"]),
+        cpp11::as_cpp<arrow::TimeUnit::type>(options["unit"]));
+  }
+
   if (func_name == "split_pattern" || func_name == "split_pattern_regex") {
     using Options = arrow::compute::SplitPatternOptions;
     int64_t max_splits = -1;

r/tests/testthat/test-dplyr-string-functions.R

@@ -493,3 +493,78 @@ test_that("edge cases in string detection and replacement", {
     tibble(x = c("ABC"))
   )
 })
+
+test_that("strptime", {
+
+  t_string <- tibble(x = c("2018-10-07 19:04:05", NA))
+  t_stamp <- tibble(x = c(lubridate::ymd_hms("2018-10-07 19:04:05"), NA))
+
+  expect_equal(
+    t_string %>%
+      Table$create() %>%
+      mutate(
+        x = strptime(x)
+      ) %>%
+      collect(),
+    t_stamp,
+    check.tzone = FALSE
+  )
+
+  expect_equal(
+    t_string %>%
+      Table$create() %>%
+      mutate(
+        x = strptime(x, format = "%Y-%m-%d %H:%M:%S")
+      ) %>%
+      collect(),
+    t_stamp,
+    check.tzone = FALSE
+  )
+
+  expect_equal(
+    t_string %>%
+      Table$create() %>%
+      mutate(
+        x = strptime(x, format = "%Y-%m-%d %H:%M:%S", unit = "ns")
+      ) %>%
+      collect(),
+    t_stamp,
+    check.tzone = FALSE
+  )
+
+  expect_equal(
+    t_string %>%
+      Table$create() %>%
+      mutate(
+        x = strptime(x, format = "%Y-%m-%d %H:%M:%S", unit = "s")
+      ) %>%
+      collect(),
+    t_stamp,
+    check.tzone = FALSE
+  )
+
+  tstring <- tibble(x = c("08-05-2008", NA))
+  tstamp <- tibble(x = c(strptime("08-05-2008", format = "%m-%d-%Y"), NA))
+
+  expect_equal(
+    tstring %>%
+      Table$create() %>%
+      mutate(
+        x = strptime(x, format = "%m-%d-%Y")
+      ) %>%
+      collect(),
+    tstamp,
+    check.tzone = FALSE
+  )
+
+})
+
+test_that("errors in strptime", {
+  # Error when tz is passed
+
+  x <- Expression$field_ref("x")
+  expect_error(
+    nse_funcs$strptime(x, tz = "PDT"),
+    'Time zone argument not supported by Arrow'
+  )
+})