[
https://issues.apache.org/jira/browse/ARROW-17429?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
SHIMA Tatsuya updated ARROW-17429:
----------------------------------
Description:
The error message displayed when a non-convertible type is specified does not
seem to help in the development version.
{code:r}
tbl <- tibble::tibble(time = c("1970-01-01T12:00:00+12:00"))
csv_file <- tempfile()
on.exit(unlink(csv_file))
write.csv(tbl, csv_file, row.names = FALSE)
arrow::read_csv_arrow(csv_file, col_types = "?", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <dttm>
#> 1 1970-01-01 00:00:00
arrow::read_csv_arrow(csv_file, col_types = "c", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <chr>
#> 1 1970-01-01T12:00:00+12:00
arrow::read_csv_arrow(csv_file, col_types = "i", col_names = "x", skip = 1)
#> Error in as.data.frame(tab): object 'tab' not found
arrow::read_csv_arrow(csv_file, col_types = "T", col_names = "x", skip = 1)
#> Error in as.data.frame(tab): object 'tab' not found
{code}
In arrow 9.0.0
{code:r}
tbl <- tibble::tibble(time = c("1970-01-01T12:00:00+12:00"))
csv_file <- tempfile()
on.exit(unlink(csv_file))
write.csv(tbl, csv_file, row.names = FALSE)
arrow::read_csv_arrow(csv_file, col_types = "?", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <dttm>
#> 1 1970-01-01 00:00:00
arrow::read_csv_arrow(csv_file, col_types = "c", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <chr>
#> 1 1970-01-01T12:00:00+12:00
arrow::read_csv_arrow(csv_file, col_types = "i", col_names = "x", skip = 1)
#> Error:
#> ! Invalid: In CSV column #0: CSV conversion error to int32: invalid value
'1970-01-01T12:00:00+12:00'
arrow::read_csv_arrow(csv_file, col_types = "T", col_names = "x", skip = 1)
#> Error:
#> ! Invalid: In CSV column #0: CSV conversion error to timestamp[ns]: expected
no zone offset in '1970-01-01T12:00:00+12:00'
{code}
was:
The error message displayed when a non-convertible type is specified does not
seem to help in the development version.
{code:r}
tbl <- tibble::tibble(time = c("1970-01-01T12:00:00+12:00"))
csv_file <- tempfile()
on.exit(unlink(csv_file))
write.csv(tbl, csv_file, row.names = FALSE)
arrow::read_csv_arrow(csv_file, col_types = "?", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <dttm>
#> 1 1970-01-01 00:00:00
arrow::read_csv_arrow(csv_file, col_types = "c", col_names = "x", skip = 1)
#> # A tibble: 1 × 1
#> x
#> <chr>
#> 1 1970-01-01T12:00:00+12:00
arrow::read_csv_arrow(csv_file, col_types = "i", col_names = "x", skip = 1)
#> Error in as.data.frame(tab): object 'tab' not found
arrow::read_csv_arrow(csv_file, col_types = "T", col_names = "x", skip = 1)
#> Error in as.data.frame(tab): object 'tab' not found
{code}
> [R] Error messages are not helpful of read_csv_arrow with col_types option
> --------------------------------------------------------------------------
>
> Key: ARROW-17429
> URL: https://issues.apache.org/jira/browse/ARROW-17429
> Project: Apache Arrow
> Issue Type: Bug
> Components: R
> Affects Versions: 9.0.0
> Reporter: SHIMA Tatsuya
> Priority: Major
>
> The error message displayed when a non-convertible type is specified does not
> seem to help in the development version.
> {code:r}
> tbl <- tibble::tibble(time = c("1970-01-01T12:00:00+12:00"))
> csv_file <- tempfile()
> on.exit(unlink(csv_file))
> write.csv(tbl, csv_file, row.names = FALSE)
> arrow::read_csv_arrow(csv_file, col_types = "?", col_names = "x", skip = 1)
> #> # A tibble: 1 × 1
> #> x
> #> <dttm>
> #> 1 1970-01-01 00:00:00
> arrow::read_csv_arrow(csv_file, col_types = "c", col_names = "x", skip = 1)
> #> # A tibble: 1 × 1
> #> x
> #> <chr>
> #> 1 1970-01-01T12:00:00+12:00
> arrow::read_csv_arrow(csv_file, col_types = "i", col_names = "x", skip = 1)
> #> Error in as.data.frame(tab): object 'tab' not found
> arrow::read_csv_arrow(csv_file, col_types = "T", col_names = "x", skip = 1)
> #> Error in as.data.frame(tab): object 'tab' not found
> {code}
> In arrow 9.0.0
> {code:r}
> tbl <- tibble::tibble(time = c("1970-01-01T12:00:00+12:00"))
> csv_file <- tempfile()
> on.exit(unlink(csv_file))
> write.csv(tbl, csv_file, row.names = FALSE)
> arrow::read_csv_arrow(csv_file, col_types = "?", col_names = "x", skip = 1)
> #> # A tibble: 1 × 1
> #> x
> #> <dttm>
> #> 1 1970-01-01 00:00:00
> arrow::read_csv_arrow(csv_file, col_types = "c", col_names = "x", skip = 1)
> #> # A tibble: 1 × 1
> #> x
> #> <chr>
> #> 1 1970-01-01T12:00:00+12:00
> arrow::read_csv_arrow(csv_file, col_types = "i", col_names = "x", skip = 1)
> #> Error:
> #> ! Invalid: In CSV column #0: CSV conversion error to int32: invalid value
> '1970-01-01T12:00:00+12:00'
> arrow::read_csv_arrow(csv_file, col_types = "T", col_names = "x", skip = 1)
> #> Error:
> #> ! Invalid: In CSV column #0: CSV conversion error to timestamp[ns]:
> expected no zone offset in '1970-01-01T12:00:00+12:00'
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
