thisisnic commented on a change in pull request #10624:
URL: https://github.com/apache/arrow/pull/10624#discussion_r670449282
##########
File path: r/R/dplyr-functions.R
##########
@@ -280,6 +284,68 @@ nse_funcs$str_trim <- function(string, side = c("both",
"left", "right")) {
Expression$create(trim_fun, string)
}
+nse_funcs$substr <- function(string, start, stop) {
+ assert_that(
+ length(start) == 1,
+ msg = "`start` must be length 1 - other lengths are not supported in Arrow"
+ )
+ assert_that(
+ length(stop) == 1,
+ msg = "`stop` must be length 1 - other lengths are not supported in Arrow"
+ )
+
+ # substr treats values as if they're on a continous number line, so values
+ # 0 are effectively blank characters - set `start` to 1 here so Arrow mimics
+ # this behavior
+ if (start <= 0) {
+ start <- 1
+ }
+
+ # if `stop` is lower than `start`, this is invalid, so set `stop` to
+ # 0 so that an empty string will be returned
+ if (stop < start) {
+ stop <- 0
+ }
+
+ Expression$create(
+ "utf8_slice_codeunits",
+ string,
+ options = list(start = start - 1L, stop = stop)
+ )
+}
+
+nse_funcs$substring <- nse_funcs$substr
+
+nse_funcs$str_sub <- function(string, start = 1L, end = -1L) {
+ assert_that(
+ length(start) == 1,
+ msg = "`start` must be length 1 - other lengths are not supported in Arrow"
+ )
+ assert_that(
+ length(end) == 1,
+ msg = "`end` must be length 1 - other lengths are not supported in Arrow"
+ )
+
+ if (end == -1) {
+ end <- .Machine$integer.max
+ }
+
+ if (end < start) {
+ end <- 0
+ }
+
+
+ if (start > 0) {
+ start <- start - 1L
Review comment:
Thanks, good to know, will update with this
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
