[
https://issues.apache.org/jira/browse/ARROW-14575?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17438279#comment-17438279
]
Dewey Dunnington edited comment on ARROW-14575 at 11/4/21, 1:41 PM:
--------------------------------------------------------------------
It might be nice for clarity to register the package name with the function
(i.e., `arrow_register_translation("year", function(...) {}, package =
"lubridate")` instead of `nse_funcs$year <- function(...) {}`.
Erroring out could look like this (only slightly better than the current error,
though).
{noformat}
library(arrow, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
ds <- InMemoryDataset$create(nycflights13::flights)
funs <- arrow:::.cache$functions
funs[["::"]] <- function(lhs, rhs) {
arrow:::arrow_not_supported("`::`")
}
assign("functions", funs, envir = arrow:::.cache)
ds %>%
mutate(year = lubridate::year(time_hour)) %>%
collect()
#> Warning: In lubridate::year(time_hour), `::` not supported by Arrow; pulling
#> data into R
#> # A tibble: 336,776 × 19{noformat}
A slightly different definition of `::` could ignore it with a warning,
although this is possibly a bit too magical.
{noformat}
library(arrow, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
ds <- InMemoryDataset$create(nycflights13::flights)
funs <- arrow:::.cache$functions
funs[["::"]] <- function(lhs, rhs) {
# already evaluated to an Expression?
rhs <- rhs$field_name
warning(paste0("Replacing `", as.character(substitute(lhs)), "::", rhs, "`
with `", rhs, "`"))
get(rhs, envir = parent.frame(), mode = "function")
}
assign("functions", funs, envir = arrow:::.cache)
ds %>%
mutate(year = lubridate::year(time_hour)) %>%
collect()
#> Warning in lubridate::year: Replacing `lubridate::year` with `year`
#> # A tibble: 336,776 × 19
#> year month day dep_time sched_dep_time dep_delay arr_time
sched_arr_time
#> <int> <int> <int> <int> <int> <dbl> <int>
<int>
#> 1 2013 1 1 517 515 2 830
819
#> 2 2013 1 1 533 529 4 850
830
#> 3 2013 1 1 542 540 2 923
850
#> 4 2013 1 1 544 545 -1 1004
1022
#> 5 2013 1 1 554 600 -6 812
837
#> 6 2013 1 1 554 558 -4 740
728
#> 7 2013 1 1 555 600 -5 913
854
#> 8 2013 1 1 557 600 -3 709
723
#> 9 2013 1 1 557 600 -3 838
846
#> 10 2013 1 1 558 600 -2 753
745
#> # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
#> # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
#> # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour
<dttm>{noformat}
was (Author: paleolimbot):
It might be nice for clarity to register the package name with the function
(i.e., `arrow_register_translation("year", function(...) {}, package =
"lubridate")` instead of `nse_funcs$year <- function(...) {}`.
Erroring out could look like this (only slightly better than the current error,
though).
{noformat}
library(arrow, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
ds <- InMemoryDataset$create(nycflights13::flights)
funs <- arrow:::.cache$functions
funs[["::"]] <- function(lhs, rhs) {
arrow:::arrow_not_supported("`::`")
}
assign("functions", funs, envir = arrow:::.cache)
ds %>%
mutate(year = lubridate::year(time_hour)) %>%
collect()
#> Warning: In lubridate::year(time_hour), `::` not supported by Arrow; pulling
#> data into R
#> # A tibble: 336,776 × 19{noformat}
A slightly different definition of `::` could ignore it with a warning,
although this is possibly a bit too magical.
{noformat}
library(arrow, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
ds <- InMemoryDataset$create(nycflights13::flights)
funs <- arrow:::.cache$functions
funs[["::"]] <- function(lhs, rhs) {
# already evaluated to an Expression?
rhs <- rhs$field_name
warning(paste0("Replacing `", as.character(substitute(lhs)), "::", rhs, "`
with `", rhs, "`"))
get(rhs, envir = parent.frame(), mode = "function")
}
assign("functions", funs, envir = arrow:::.cache)ds %>%
mutate(year = lubridate::year(time_hour)) %>%
collect()
#> Warning in lubridate::year: Replacing `lubridate::year` with `year`
#> # A tibble: 336,776 × 19
#> year month day dep_time sched_dep_time dep_delay arr_time
sched_arr_time
#> <int> <int> <int> <int> <int> <dbl> <int>
<int>
#> 1 2013 1 1 517 515 2 830
819
#> 2 2013 1 1 533 529 4 850
830
#> 3 2013 1 1 542 540 2 923
850
#> 4 2013 1 1 544 545 -1 1004
1022
#> 5 2013 1 1 554 600 -6 812
837
#> 6 2013 1 1 554 558 -4 740
728
#> 7 2013 1 1 555 600 -5 913
854
#> 8 2013 1 1 557 600 -3 709
723
#> 9 2013 1 1 557 600 -3 838
846
#> 10 2013 1 1 558 600 -2 753
745
#> # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
#> # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
#> # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour
<dttm>{noformat}
> [R] Allow functions with {{pkg::}} prefixes
> -------------------------------------------
>
> Key: ARROW-14575
> URL: https://issues.apache.org/jira/browse/ARROW-14575
> Project: Apache Arrow
> Issue Type: Bug
> Components: R
> Reporter: Jonathan Keane
> Assignee: Dewey Dunnington
> Priority: Major
>
> Currently we implement a number of functions from packages like {lubridate}
> which work well when called without namespacing (e.g. {{year()}}), however if
> someone calls {{lubridate::year()}} we get a not-implemented method (e.g.
> {{Warning: Expression lubridate::year(time_hour) not supported in Arrow}}).
> Is it possible for us to look and see if we have an arrow function that
> matches the function itself.
> {code:r}
> library(arrow, warn.conflicts = FALSE)
> library(dplyr, warn.conflicts = FALSE)
> ds <- InMemoryDataset$create(nycflights13::flights)
> ds %>%
> mutate(year = lubridate::year(time_hour)) %>%
> collect()
> #> Warning: Expression lubridate::year(time_hour) not supported in Arrow;
> pulling
> #> data into R
> #> # A tibble: 336,776 × 19
> #> year month day dep_time sched_dep_time dep_delay arr_time
> sched_arr_time
> #> <dbl> <int> <int> <int> <int> <dbl> <int>
> <int>
> #> 1 2013 1 1 517 515 2 830
> 819
> #> 2 2013 1 1 533 529 4 850
> 830
> #> 3 2013 1 1 542 540 2 923
> 850
> #> 4 2013 1 1 544 545 -1 1004
> 1022
> #> 5 2013 1 1 554 600 -6 812
> 837
> #> 6 2013 1 1 554 558 -4 740
> 728
> #> 7 2013 1 1 555 600 -5 913
> 854
> #> 8 2013 1 1 557 600 -3 709
> 723
> #> 9 2013 1 1 557 600 -3 838
> 846
> #> 10 2013 1 1 558 600 -2 753
> 745
> #> # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
> #> # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
> #> # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour
> <dttm>
> ds %>%
> mutate(year = year(time_hour)) %>%
> collect()
> #> # A tibble: 336,776 × 19
> #> year month day dep_time sched_dep_time dep_delay arr_time
> sched_arr_time
> #> <int> <int> <int> <int> <int> <dbl> <int>
> <int>
> #> 1 2013 1 1 517 515 2 830
> 819
> #> 2 2013 1 1 533 529 4 850
> 830
> #> 3 2013 1 1 542 540 2 923
> 850
> #> 4 2013 1 1 544 545 -1 1004
> 1022
> #> 5 2013 1 1 554 600 -6 812
> 837
> #> 6 2013 1 1 554 558 -4 740
> 728
> #> 7 2013 1 1 555 600 -5 913
> 854
> #> 8 2013 1 1 557 600 -3 709
> 723
> #> 9 2013 1 1 557 600 -3 838
> 846
> #> 10 2013 1 1 558 600 -2 753
> 745
> #> # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
> #> # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
> #> # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour
> <dttm>
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
