The data is from the Finnish ministry of justice election results
curl -O http://tulospalvelu.vaalit.fi/K2012/data/k-2012_ehd_maa.csv.zip
unzip k-2012_ehd_maa.csv.zip
head -n 1 kv-2012_teat_maa.csv > scandinavian.csv
iconv -f ISO-8859-1 -t UTF-8 scandinavian.csv > scandinavian-utf.csv
$ file -I scandinavian.csv
scandinavian.csv: text/plain; charset=iso-8859-1
$ file -I scandinavian-utf.csv
scandinavian-utf.csv: text/plain; charset=utf-8
| library("readr") | |
| library("dplyr") | |
| ##################################################################### | |
| # works as expected when column types are chr and file is iso-8859-1 | |
| read_delim( | |
| "scandinavian.csv", | |
| ";", | |
| locale = locale("fi", encoding = "iso-8859-1"), | |
| escape_double = FALSE, | |
| col_names = FALSE, | |
| trim_ws = TRUE | |
| ) %>% glimpse() %>% select(X11,X12) | |
| # X11 X12 | |
| # <chr> <chr> | |
| # 1 VAS VÄNST | |
| ##################################################################### | |
| # works as expected when column types are fctr and file is UTF-8 | |
| read_delim( | |
| "scandinavian-utf.csv", | |
| ";", | |
| locale = locale("fi", encoding = "UTF-8"), | |
| escape_double = FALSE, | |
| col_names = FALSE, | |
| col_types = cols(X11 = col_factor(c("VAS")), X12 = col_factor(c("VÄNST"))), | |
| trim_ws = TRUE | |
| ) %>% glimpse() %>% select(X11,X12) | |
| # X11 X12 | |
| # <chr> <chr> | |
| # 1 VAS VÄNST | |
| ##################################################################### | |
| # works unexpectedly when column types are fctr and file is iso-8859-1 | |
| read_delim( | |
| "scandinavian.csv", | |
| ";", | |
| locale = locale("fi", encoding = "iso-8859-1"), | |
| escape_double = FALSE, | |
| col_names = FALSE, | |
| col_types = cols(X11 = col_factor(c("VAS")), X12 = col_factor(c("VÄNST"))), | |
| trim_ws = TRUE | |
| ) %>% glimpse() %>% select(X11,X12) | |
| # X11 X12 | |
| # <chr> <chr> | |
| # 1 VAS NA | |
| # should see: | |
| # X11 X12 | |
| # <chr> <chr> | |
| # 1 VAS VÄNST |