| % Generated by roxygen2: do not edit by hand |
| % Please edit documentation in R/csv.R |
| \name{csv_convert_options} |
| \alias{csv_convert_options} |
| \title{CSV Convert Options} |
| \usage{ |
| csv_convert_options( |
| check_utf8 = TRUE, |
| null_values = c("", "NA"), |
| true_values = c("T", "true", "TRUE"), |
| false_values = c("F", "false", "FALSE"), |
| strings_can_be_null = FALSE, |
| col_types = NULL, |
| auto_dict_encode = FALSE, |
| auto_dict_max_cardinality = 50L, |
| include_columns = character(), |
| include_missing_columns = FALSE, |
| timestamp_parsers = NULL, |
| decimal_point = "." |
| ) |
| } |
| \arguments{ |
| \item{check_utf8}{Logical: check UTF8 validity of string columns?} |
| |
| \item{null_values}{Character vector of recognized spellings for null values. |
| Analogous to the \code{na.strings} argument to |
| \code{\link[utils:read.csv]{read.csv()}} or \code{na} in \code{\link[readr:read_csv]{readr::read_csv()}}.} |
| |
| \item{true_values}{Character vector of recognized spellings for \code{TRUE} values} |
| |
| \item{false_values}{Character vector of recognized spellings for \code{FALSE} values} |
| |
| \item{strings_can_be_null}{Logical: can string / binary columns have |
| null values? Similar to the \code{quoted_na} argument to \code{\link[readr:read_csv]{readr::read_csv()}}} |
| |
| \item{col_types}{A \code{Schema} or \code{NULL} to infer types} |
| |
| \item{auto_dict_encode}{Logical: Whether to try to automatically |
| dictionary-encode string / binary data (think \code{stringsAsFactors}). |
| This setting is ignored for non-inferred columns (those in \code{col_types}).} |
| |
| \item{auto_dict_max_cardinality}{If \code{auto_dict_encode}, string/binary columns |
| are dictionary-encoded up to this number of unique values (default 50), |
| after which it switches to regular encoding.} |
| |
| \item{include_columns}{If non-empty, indicates the names of columns from the |
| CSV file that should be actually read and converted (in the vector's order).} |
| |
| \item{include_missing_columns}{Logical: if \code{include_columns} is provided, should |
| columns named in it but not found in the data be included as a column of |
| type \code{null()}? The default (\code{FALSE}) means that the reader will instead |
| raise an error.} |
| |
| \item{timestamp_parsers}{User-defined timestamp parsers. If more than one |
| parser is specified, the CSV conversion logic will try parsing values |
| starting from the beginning of this vector. Possible values are |
| (a) \code{NULL}, the default, which uses the ISO-8601 parser; |
| (b) a character vector of \link[base:strptime]{strptime} parse strings; or |
| (c) a list of \link{TimestampParser} objects.} |
| |
| \item{decimal_point}{Character to use for decimal point in floating point numbers.} |
| } |
| \description{ |
| CSV Convert Options |
| } |
| \examples{ |
| \dontshow{if (arrow_with_dataset()) withAutoprint(\{ # examplesIf} |
| tf <- tempfile() |
| on.exit(unlink(tf)) |
| writeLines("x\n1\nNULL\n2\nNA", tf) |
| read_csv_arrow(tf, convert_options = csv_convert_options(null_values = c("", "NA", "NULL"))) |
| open_csv_dataset(tf, convert_options = csv_convert_options(null_values = c("", "NA", "NULL"))) |
| \dontshow{\}) # examplesIf} |
| } |