fix remaining errors

NEWS.md

@@ -6,13 +6,15 @@
   - changes in `$write_csv()` and `sink_csv()`: `has_header` is renamed
     `include_header` and there's a new argument `include_bom`.
   - `pl$cov()` gains a `ddof` argument.
-  - `$cumsum()`, `$cumprod()`, `$cummin()`, `$cummax()`, `$cumcount()`,  are
+  - `$cumsum()`, `$cumprod()`, `$cummin()`, `$cummax()`, `$cumcount()`  are
     renamed `$cum_sum()`, `$cum_prod()`, `$cum_min()`, `$cum_max()`, 
     `$cum_count()`.
   - `take()` and `take_every()` are renamed `$gather()` and `gather_every()`.
   - `$shift()` and `$shift_and_fill()` now accept Expr as input.
   - when `reverse = TRUE`, `$arg_sort()` now places null values in the first
     positions.
+  - Removed argument `ambiguous` in `$dt$truncate()` and `$dt$round()`.
+  - `$str$concat()` gains an argument `ignore_nulls`.
 
 ## Breaking changes
 

R/expr__datetime.R

@@ -4,10 +4,6 @@
 #' @name ExprDT_truncate
 #' @param every string encoding duration see details.
 #' @param offset optional string encoding duration see details.
-#' @param ambiguous Determine how to deal with ambiguous datetimes:
-#' * `"raise"` (default): raise
-#' * `"earliest"`: use the earliest datetime
-#' * `"latest"`: use the latest datetime
 #'
 #' @details The ``every`` and ``offset`` argument are created with the
 #' the following string language:
@@ -39,11 +35,8 @@
 #'   pl$col("datetime")$dt$truncate("4s", offset("3s"))$alias("truncated_4s_offset_2s")
 #' )
 #' df
-ExprDT_truncate = function(
-    every, # str
-    offset = NULL, # : str | timedelta | None = None,
-    ambiguous = "raise") {
-  .pr$Expr$dt_truncate(self, every, offset, ambiguous) |>
+ExprDT_truncate = function(every, offset = NULL) {
+  .pr$Expr$dt_truncate(self, every, offset) |>
     unwrap("in dt$truncate()")
 }
 
@@ -57,10 +50,6 @@ ExprDT_truncate = function(
 #'
 #' @param every string encoding duration see details.
 #' @param ofset optional string encoding duration see details.
-#' @param ambiguous Determine how to deal with ambiguous datetimes:
-#' * `"raise"` (default): raise
-#' * `"earliest"`: use the earliest datetime
-#' * `"latest"`: use the latest datetime
 #'
 #' @details The ``every`` and ``offset`` argument are created with the
 #' the following string language:
@@ -96,8 +85,8 @@ ExprDT_truncate = function(
 #'   pl$col("datetime")$dt$truncate("4s", offset("3s"))$alias("truncated_4s_offset_2s")
 #' )
 #' df
-ExprDT_round = function(every, offset = NULL, ambiguous = "raise") {
-  .pr$Expr$dt_round(self, every, offset, ambiguous) |>
+ExprDT_round = function(every, offset = NULL) {
+  .pr$Expr$dt_round(self, every, offset) |>
     unwrap("in dt$round()")
 }
 

R/expr__string.R

@@ -135,18 +135,22 @@ ExprStr_len_chars = function() {
 #' @description Vertically concatenate the values in the Series to a single
 #' string value.
 #' @param delimiter The delimiter to insert between consecutive string values.
+#' @param ignore_nulls Ignore null values. If `FALSE`, null values will be
+#' propagated: if the column contains any null values, the output is null.
 #' @keywords ExprStr
 #' @return Expr of Utf8 concatenated
 #' @examples
 #' # concatenate a Series of strings to a single string
 #' df = pl$DataFrame(foo = c("1", NA, 2))
 #' df$select(pl$col("foo")$str$concat("-"))
+#' df$select(pl$col("foo")$str$concat("-", ignore_nulls = FALSE))
 #'
 #' # Series list of strings to Series of concatenated strings
 #' df = pl$DataFrame(list(bar = list(c("a", "b", "c"), c("1", "2", NA))))
 #' df$select(pl$col("bar")$list$eval(pl$col()$str$concat())$list$first())
-ExprStr_concat = function(delimiter = "-") {
-  .pr$Expr$str_concat(self, delimiter)
+ExprStr_concat = function(delimiter = "-", ignore_nulls = TRUE) {
+  .pr$Expr$str_concat(self, delimiter, ignore_nulls) |>
+    unwrap("in $concat():")
 }
 
 #' Convert a string to uppercase

R/extendr-wrappers.R

@@ -515,7 +515,7 @@ Expr$explode <- function() .Call(wrap__Expr__explode, self)
 
 Expr$flatten <- function() .Call(wrap__Expr__flatten, self)
 
-Expr$take_every <- function(n) .Call(wrap__Expr__take_every, self, n)
+Expr$gather_every <- function(n) .Call(wrap__Expr__gather_every, self, n)
 
 Expr$hash <- function(seed, seed_1, seed_2, seed_3) .Call(wrap__Expr__hash, self, seed, seed_1, seed_2, seed_3)
 
@@ -667,9 +667,9 @@ Expr$str_to_datetime <- function(format, time_unit, time_zone, strict, exact, ca
 
 Expr$str_to_time <- function(format, strict, exact, cache, ambiguous) .Call(wrap__Expr__str_to_time, self, format, strict, exact, cache, ambiguous)
 
-Expr$dt_truncate <- function(every, offset, ambiguous) .Call(wrap__Expr__dt_truncate, self, every, offset, ambiguous)
+Expr$dt_truncate <- function(every, offset) .Call(wrap__Expr__dt_truncate, self, every, offset)
 
-Expr$dt_round <- function(every, offset, ambiguous) .Call(wrap__Expr__dt_round, self, every, offset, ambiguous)
+Expr$dt_round <- function(every, offset) .Call(wrap__Expr__dt_round, self, every, offset)
 
 Expr$dt_time <- function() .Call(wrap__Expr__dt_time, self)
 
@@ -851,7 +851,7 @@ Expr$str_len_bytes <- function() .Call(wrap__Expr__str_len_bytes, self)
 
 Expr$str_len_chars <- function() .Call(wrap__Expr__str_len_chars, self)
 
-Expr$str_concat <- function(delimiter) .Call(wrap__Expr__str_concat, self, delimiter)
+Expr$str_concat <- function(delimiter, ignore_nulls) .Call(wrap__Expr__str_concat, self, delimiter, ignore_nulls)
 
 Expr$str_to_uppercase <- function() .Call(wrap__Expr__str_to_uppercase, self)
 

tests/testthat/test-expr.R

@@ -1485,7 +1485,7 @@ test_that("Expr explode/flatten", {
 })
 
 
-test_that("take_every", {
+test_that("gather_every", {
   df = pl$DataFrame(list(a = 0:24))$select(pl$col("a")$gather_every(6))
   expect_identical(
     df$to_list()[[1L]],

tests/testthat/test-expr_string.R

@@ -7,7 +7,7 @@ test_that("str$strptime datetime", {
 
   expect_error(
     pl$lit(txt_datetimes)$str$strptime(pl$Datetime(), format = "%Y-%m-%d %H:%M:%S")$lit_to_s(),
-    "strict datetime"
+    "Conversion .* failed"
   )
 
   expect_identical(
@@ -35,7 +35,7 @@ test_that("str$strptime date", {
 
   expect_grepl_error(
     pl$lit(txt_dates)$str$strptime(pl$Date, format = "%Y-%m-%d")$lit_to_s(),
-    "strict date parsing failed"
+    "Conversion from `str` to `date` failed"
   )
 
   expect_identical(
@@ -69,7 +69,7 @@ test_that("str$strptime time", {
 
   expect_grepl_error(
     pl$lit(txt_times)$str$strptime(pl$Time, format = "%H:%M:%S %z")$lit_to_s(),
-    "strict time parsing failed"
+    "Conversion from `str` to `time` failed"
   )
 
   expect_equal(
@@ -81,10 +81,6 @@ test_that("str$strptime time", {
   )
 })
 
-
-
-
-
 test_that("str$len_bytes str$len_chars", {
   test_str = c("Café", NA, "345", "東京") |> enc2utf8()
   Encoding(test_str)
@@ -623,23 +619,22 @@ test_that("str$str_explode", {
 
 test_that("str$parse_int", {
   expect_identical(
-    pl$lit(c("110", "101", "010"))$str$parse_int(2)$to_r(),
+    pl$lit(c("110", "101", "010"))$str$parse_int(2)$shrink_dtype()$to_r(),
     c(6L, 5L, 2L)
   )
 
   expect_identical(
-    pl$lit(c("110", "101", "010"))$str$parse_int()$to_r(),
+    pl$lit(c("110", "101", "010"))$str$parse_int()$shrink_dtype()$to_r(),
     c(6L, 5L, 2L)
   )
 
-
   expect_identical(
-    pl$lit(c("110", "101", "010"))$str$parse_int(10)$to_r(),
+    pl$lit(c("110", "101", "010"))$str$parse_int(10)$shrink_dtype()$to_r(),
     c(110L, 101L, 10L)
   )
 
   expect_identical(
-    pl$lit(c("110", "101", "hej"))$str$parse_int(10, FALSE)$to_r(),
+    pl$lit(c("110", "101", "hej"))$str$parse_int(10, FALSE)$shrink_dtype()$to_r(),
     c(110L, 101L, NA)
   )
 

tests/testthat/test-lazy.R

@@ -251,9 +251,9 @@ test_that("drop_nulls", {
   expect_equal(pl$DataFrame(tmp)$lazy()$drop_nulls("mpg")$collect()$height, 29, ignore_attr = TRUE)
   expect_equal(pl$DataFrame(tmp)$lazy()$drop_nulls("hp")$collect()$height, 32, ignore_attr = TRUE)
   expect_equal(pl$DataFrame(tmp)$lazy()$drop_nulls(c("mpg", "hp"))$collect()$height, 29, ignore_attr = TRUE)
-  expect_identical(
-    result(pl$DataFrame(mtcars)$lazy()$drop_nulls("bad")$collect())$err$contexts(),
-    list(PolarsError = "not found: bad")
+  expect_error(
+    pl$DataFrame(mtcars)$lazy()$drop_nulls("bad")$collect(),
+    "not found: unable to find column \"bad\""
   )
 })