Generate a column specification

When printed, only the first 20 columns are printed by default. To override, set options(readr.num_columns) can be used to modify this (a value of 0 turns off printing).

spec_delim(file, delim, quote = "\"", escape_backslash = FALSE,
  escape_double = TRUE, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = c("", "NA"), quoted_na = TRUE,
  comment = "", trim_ws = FALSE, skip = 0, n_max = 0,
  guess_max = 1000, progress = show_progress(),
  skip_empty_rows = TRUE)

spec_csv(file, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = c("", "NA"), quoted_na = TRUE,
  quote = "\"", comment = "", trim_ws = TRUE, skip = 0,
  n_max = 0, guess_max = 1000, progress = show_progress(),
  skip_empty_rows = TRUE)

spec_csv2(file, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = c("", "NA"), quoted_na = TRUE,
  quote = "\"", comment = "", trim_ws = TRUE, skip = 0,
  n_max = 0, guess_max = 1000, progress = show_progress(),
  skip_empty_rows = TRUE)

spec_tsv(file, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = c("", "NA"), quoted_na = TRUE,
  quote = "\"", comment = "", trim_ws = TRUE, skip = 0,
  n_max = 0, guess_max = 1000, progress = show_progress(),
  skip_empty_rows = TRUE)

spec_table(file, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = "NA", skip = 0, n_max = 0,
  guess_max = 1000, progress = show_progress(), comment = "",
  skip_empty_rows = TRUE)

spec_table2(file, col_names = TRUE, col_types = NULL,
  locale = default_locale(), na = "NA", skip = 0, n_max = 0,
  guess_max = 1000, progress = show_progress(), comment = "",
  skip_empty_rows = TRUE)

Arguments

file	Either a path to a file, a connection, or literal data (either a single string or a raw vector). Files ending in .gz, .bz2, .xz, or .zip will be automatically uncompressed. Files starting with http://, https://, ftp://, or ftps:// will be automatically downloaded. Remote gz files can also be automatically downloaded and decompressed. Literal data is most useful for examples and tests. It must contain at least one new line to be recognised as data (instead of a path) or be a vector of greater than length 1. Using a value of clipboard() will read from the system clipboard.
delim	Single character used to separate fields within a record.
quote	Single character used to quote strings.
escape_backslash	Does the file use backslashes to escape special characters? This is more general than escape_double as backslashes can be used to escape the delimiter character, the quote character, or to add special characters like \n.
escape_double	Does the file escape quotes by doubling them? i.e. If this option is TRUE, the value """" represents a single quote, \".
col_names	Either TRUE, FALSE or a character vector of column names. If TRUE, the first row of the input will be used as the column names, and will not be included in the data frame. If FALSE, column names will be generated automatically: X1, X2, X3 etc. If col_names is a character vector, the values will be used as the names of the columns, and the first row of the input will be read into the first row of the output data frame. Missing (NA) column names will generate a warning, and be filled in with dummy names X1, X2 etc. Duplicate column names will generate a warning and be made unique with a numeric prefix.
col_types	One of NULL, a cols() specification, or a string. See vignette("readr") for more details. If NULL, all column types will be imputed from the first 1000 rows on the input. This is convenient (and fast), but not robust. If the imputation fails, you'll need to supply the correct types yourself. If a column specification created by cols(), it must contain one column specification for each column. If you only want to read a subset of the columns, use cols_only(). Alternatively, you can use a compact string representation where each character represents one column: c = character, i = integer, n = number, d = double, l = logical, f = factor, D = date, T = date time, t = time, ? = guess, or _/- to skip the column.
locale	The locale controls defaults that vary from place to place. The default locale is US-centric (like R), but you can use locale() to create your own locale that controls things like the default time zone, encoding, decimal mark, big mark, and day/month names.
na	Character vector of strings to interpret as missing values. Set this option to character() to indicate no missing values.
quoted_na	Should missing values inside quotes be treated as missing values (the default) or strings.
comment	A string used to identify comments. Any text after the comment characters will be silently ignored.
trim_ws	Should leading and trailing whitespace be trimmed from each field before parsing it?
skip	Number of lines to skip before reading data.
n_max	Maximum number of records to read.
guess_max	Maximum number of records to use for guessing column types.
progress	Display a progress bar? By default it will only display in an interactive session and not while knitting a document. The display is updated every 50,000 values and will only display if estimated reading time is 5 seconds or more. The automatic progress bar can be disabled by setting option readr.show_progress to FALSE.
skip_empty_rows	Should blank rows be ignored altogether? i.e. If this option is TRUE then blank rows will not be represented at all. If it is FALSE then they will be represented by NA values in all the columns.

Value

The col_spec generated for the file.

Examples

# Input sources -------------------------------------------------------------
# Retrieve specs from a path
spec_csv(system.file("extdata/mtcars.csv", package = "readr"))
#> Parsed with column specification:
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )
spec_csv(system.file("extdata/mtcars.csv.zip", package = "readr"))
#> Parsed with column specification:
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )

# Or directly from a string (must contain a newline)
spec_csv("x,y\n1,2\n3,4")
#> cols(
#>   x = col_double(),
#>   y = col_double()
#> )

# Column types --------------------------------------------------------------
# By default, readr guesses the columns types, looking at the first 1000 rows.
# You can specify the number of rows used with guess_max.
spec_csv(system.file("extdata/mtcars.csv", package = "readr"), guess_max = 20)
#> Parsed with column specification:
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )
#> cols(
#>   mpg = col_double(),
#>   cyl = col_double(),
#>   disp = col_double(),
#>   hp = col_double(),
#>   drat = col_double(),
#>   wt = col_double(),
#>   qsec = col_double(),
#>   vs = col_double(),
#>   am = col_double(),
#>   gear = col_double(),
#>   carb = col_double()
#> )