[
https://issues.apache.org/jira/browse/ARROW-9186?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17461670#comment-17461670
]
Dewey Dunnington commented on ARROW-9186:
-----------------------------------------
Reprex:
{code:R}
library(arrow, warn.conflicts = FALSE)
string <- "province_name\nQuébec"
bytes_utf8 <- iconv(string, to = "UTF-8", toRaw = TRUE)[[1]]
bytes_windows1252 <- iconv(string, to = "windows-1252", toRaw = TRUE)[[1]]
temp_utf8 <- tempfile()
temp_windows1252 <- tempfile()
con <- file(temp_utf8, open = "wb")
writeBin(bytes_utf8, con)
close(con)
con <- file(temp_windows1252, open = "wb")
writeBin(bytes_windows1252, con)
close(con)
readr::read_csv(
temp_utf8,
locale = readr::locale(encoding = "UTF-8"),
show_col_types = FALSE
)
#> # A tibble: 1 × 1
#> province_name
#> <chr>
#> 1 Québec
readr::read_csv(
temp_windows1252,
locale = readr::locale(encoding = "windows-1252"),
show_col_types = FALSE
)
#> # A tibble: 1 × 1
#> province_name
#> <chr>
#> 1 Québec
read_csv_arrow(temp_utf8)
#> # A tibble: 1 × 1
#> province_name
#> <chr>
#> 1 Québec
read_csv_arrow(temp_windows1252)
#> # A tibble: 1 × 1
#> province_name
#> <arrw_bnr>
#> 1 51, 75, e9, 62, 65, 63
{code}
> [R] Allow specifying CSV file encoding
> --------------------------------------
>
> Key: ARROW-9186
> URL: https://issues.apache.org/jira/browse/ARROW-9186
> Project: Apache Arrow
> Issue Type: Improvement
> Components: R
> Reporter: Neal Richardson
> Priority: Major
> Fix For: 7.0.0
>
>
> ARROW-9106 did this for Python and we should have the same in R
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
