djnavarro commented on code in PR #12154:
URL: https://github.com/apache/arrow/pull/12154#discussion_r908325212
##########
r/R/util.R:
##########
@@ -215,3 +215,74 @@ handle_csv_read_error <- function(e, schema, call) {
is_compressed <- function(compression) {
!identical(compression, "uncompressed")
}
+
+parse_period_unit <- function(x) {
+
+ # the regexp matches against fractional units, but per lubridate
+ # supports integer multiples of a known unit only
+ match_info <- regexpr(
+ pattern = " *(?<multiple>[0-9.,]+)? *(?<unit>[^ \t\n]+)",
+ text = x[[1]],
+ perl = TRUE
+ )
+
+ capture_start <- attr(match_info, "capture.start")
+ capture_length <- attr(match_info, "capture.length")
+ capture_end <- capture_start + capture_length - 1L
+
+ str_unit <- substr(x, capture_start[[2]], capture_end[[2]])
+ str_multiple <- substr(x, capture_start[[1]], capture_end[[1]])
+
+ known_units <- c("nanosecond", "microsecond", "millisecond", "second",
+ "minute", "hour", "day", "week", "month", "quarter", "year")
+
+ # match the period unit
+ str_unit_start <- substr(str_unit, 1, 3)
+ unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L
+
+ if (any(is.na(unit))) {
+ abort(sprintf("Unknown unit '%s'", str_unit))
+ }
+
+ # empty string in multiple interpreted as 1
+ if (capture_length[[1]] == 0) {
+ multiple <- 1L
+
+ } else {
+
+ # special cases: interpret fractions of 1 second as integer
+ # multiples of nanoseconds, microseconds, or milliseconds
+ # to mirror lubridate syntax
+ multiple <- as.numeric(str_multiple)
+
+ if (unit == 3L & multiple < 10^-6) {
Review Comment:
With any luck the latest commits should fix it. I just worked out how to use
the `lintr` package, so hopefully the remaining linting issues should be fixed
now
--
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]
