The R Project SVN R

% File src/library/base/man/substr.Rd
% Part of the R package, https://www.R-project.org
% Copyright 1995-2014 R Core Team
% Distributed under GPL 2 or later

\name{substr}
\alias{substr}
\alias{substring}
\alias{substr<-}
\alias{substring<-}
\title{Substrings of a Character Vector}
\usage{
substr(x, start, stop)
substring(text, first, last = 1000000L)
substr(x, start, stop) <- value
substring(text, first, last = 1000000L) <- value
}
\arguments{
  \item{x, text}{a character vector.}
  \item{start, first}{integer.  The first element to be replaced.}
  \item{stop, last}{integer.  The last element to be replaced.}
  \item{value}{a character vector, recycled if necessary.}
}
\description{
  Extract or replace substrings in a character vector.
}
\details{
  \code{substring} is compatible with S, with \code{first} and
  \code{last} instead of \code{start} and \code{stop}.
  For vector arguments, it expands the arguments cyclically to the
  length of the longest \emph{provided} none are of zero length.

  When extracting, if \code{start} is larger than the string length then
  \code{""} is returned.

  For the extraction functions, \code{x} or \code{text} will be
  converted to a character vector by \code{\link{as.character}} if it is not
  already one.

  For the replacement functions, if \code{start} is larger than the
  string length then no replacement is done.  If the portion to be
  replaced is longer than the replacement string, then only the
  portion the length of the string is replaced.

  If any argument is an \code{NA} element, the corresponding element of
  the answer is \code{NA}.

  Elements of the result will be have the encoding declared as that of
  the current locale (see \code{\link{Encoding}}) if the corresponding
  input had a declared Latin-1 or UTF-8 encoding and the current locale
  is either Latin-1 or UTF-8.

  If an input element has declared \code{"bytes"} encoding (see
  \code{\link{Encoding}}, the subsetting is done in units of bytes not
  characters.
}
\value{
  For \code{substr}, a character vector of the same length and with the
  same attributes as \code{x} (after possible coercion).

  For \code{substring}, a character vector of length the longest of the
  arguments.  This will have names taken from \code{x} (if it has any
  after coercion, repeated as needed), and other attributes copied from
  \code{x} if it is the longest of the arguments).

  Elements of \code{x} with a declared encoding (see
  \code{\link{Encoding}}) will be returned with the same encoding.
}
\note{
  The S4 version of \code{substring<-} ignores \code{last}; this version
  does not.

  These functions are often used with \code{\link{nchar}} to truncate a
  display.  That does not really work (you want to limit the width, not
  the number of characters, so it would be better to use
  \code{\link{strtrim}}), but at least make sure you use the default
  \code{nchar(type = "c")}.
}
\references{
  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
  \emph{The New S Language}.
  Wadsworth & Brooks/Cole.  (\code{substring}.)
}
\seealso{
 \code{\link{strsplit}}, \code{\link{paste}}, \code{\link{nchar}}.
}
\examples{
substr("abcdef", 2, 4)
substring("abcdef", 1:6, 1:6)
## strsplit is more efficient ...

substr(rep("abcdef", 4), 1:4, 4:5)
x <- c("asfef", "qwerty", "yuiop[", "b", "stuff.blah.yech")
substr(x, 2, 5)
substring(x, 2, 4:6)

substring(x, 2) <- c("..", "+++")
x
}
\keyword{character}