The R Project SVN – R – Diff – /trunk/src/library/base/man/validUTF8.Rd

 % File src/library/base/man/validUTF8.Rd
 % Part of the R package, https://www.R-project.org
-% Copyright 2015 R Core Team
+% Copyright 2015-2018 R Core Team
 % Distributed under GPL 2 or later
 \name{validUTF8}
+\title{Check if a Character Vector is Validly Encoded}
 \alias{validUTF8}
 \alias{validEnc}
-\title{
-  Check if a Character Vector is Validly Encoded
-}
 \description{
   Check if each element of a character vector is valid in its implied
   encoding.
+}
 \usage{
 validUTF8(x)
 validEnc(x)
+}
 \arguments{
-  \item{x}{A character vector.}
+  \item{x}{a character vector.}
+}
 \details{
   These use similar checks to those used by functions such as
   \code{\link{grep}}.
    ## from a CRAN check log
    "\xfa\xb4\xbf\xbf\x9f")
 validUTF8(x)
 validEnc(x) # depends on the locale
 Encoding(x) <-"UTF-8"
+validEnc(x) # typically the last, x[10], is invalid
+## Maybe advantageous to declare it "unknown":
+G <- x ; Encoding(G[!validEnc(G)]) <- "unknown"
+try( substr(x, 1,1) ) # gives 'invalid multibyte string' error
+try( substr(G, 1,1) ) # works
+nchar(G) # fine, too
+## but it is not "more valid" typically:
-validEnc(x)
+all.equal(validEnc(x),
+          validEnc(G)) # typically TRUE
+}

The R Project SVN R