The R Project SVN R

Rev

Rev 79695 | Rev 80054 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 79695 Rev 79790
Line 81... Line 81...
81 
  otherwise marked as UTF-8 of any of the inputs is marked as UTF-8.
 81 
  otherwise marked as UTF-8 of any of the inputs is marked as UTF-8.
82 
 
 82 
 
83 
  \code{\link{match}}, \code{\link{pmatch}}, \code{\link{charmatch}},
 83 
  \code{\link{match}}, \code{\link{pmatch}}, \code{\link{charmatch}},
84 
  \code{\link{duplicated}} and \code{\link{unique}} all match in UTF-8
 84 
  \code{\link{duplicated}} and \code{\link{unique}} all match in UTF-8
85 
  if any of the elements are marked as UTF-8.
 85 
  if any of the elements are marked as UTF-8.
86
86 
 
87 
  There is some ambiguity as to what is meant by a \sQuote{Latin-1}
 87 
  There is some ambiguity as to what is meant by a \sQuote{Latin-1}
88 
  locale, since some OSes (notably Windows) make use of character
 88 
  locale, since some OSes (notably Windows) make use of character
89 
  positions undefined (or used for control characters) in the ISO 8859-1
 89 
  positions undefined (or used for control characters) in the ISO 8859-1
90 
  character set.  How such characters are interpreted is
 90 
  character set.  How such characters are interpreted is
91 
  system-dependent but as from \R 3.5.0 they are if possible interpreted
 91 
  system-dependent but as from \R 3.5.0 they are if possible interpreted
Line 98... Line 98...
98 
  For \code{enc2utf8} encodings are always marked: they are for
 98 
  For \code{enc2utf8} encodings are always marked: they are for
99 
  \code{enc2native} in UTF-8 and Latin-1 locales.
 99 
  \code{enc2native} in UTF-8 and Latin-1 locales.
100 
}
 100 
}
101 
\examples{
 101 
\examples{
102 
## x is intended to be in latin1
 102 
## x is intended to be in latin1
103 
x <- "fa\xE7ile"
 103 
x. <- x <- "fa\xE7ile"
104 
Encoding(x)
 104 
Encoding(x.) # "unknown" (Linux) | "latin-1" (Win 32 server) | ....
105 
Encoding(x) <- "latin1"
 105 
Encoding(x) <- "latin1"
106 
x
 106 
x
107 
xx <- iconv(x, "latin1", "UTF-8")
 107 
xx <- iconv(x, "latin1", "UTF-8")
108 
Encoding(c(x, xx))
 108 
Encoding(c(x., x, xx))
109 
c(x, xx)
 109 
c(x, xx)
110 
Encoding(xx) <- "bytes"
 110 
xb <- xx; Encoding(xb) <- "bytes"
111 
xx # will be encoded in hex
 111 
xb # will be encoded in hex
112 
cat("xx = ", xx, "\n", sep = "")
 112 
cat("x = ", x, ", xx = ", xx, ", xb = ", xb, "\n", sep = "")
- 
 
 113 
(Ex <- Encoding(c(x.,x,xx,xb)))
- 
 
 114 
stopifnot(identical(Ex, c(Encoding(x.), Encoding(x),
- 
 
 115 
                          Encoding(xx), Encoding(xb))))
113 
}
 116 
}
114 
\keyword{utilities}
 117 
\keyword{utilities}
115 
\keyword{character}
 118 
\keyword{character}