The R Project SVN R

Rev

Rev 79719 | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 79719 Rev 80028
Line 1... Line 1...
1 
% File src/library/base/man/validUTF8.Rd
 1 
% File src/library/base/man/validUTF8.Rd
2 
% Part of the R package, https://www.R-project.org
 2 
% Part of the R package, https://www.R-project.org
3 
% Copyright 2015-2020 R Core Team
 3 
% Copyright 2015-2021 R Core Team
4 
% Distributed under GPL 2 or later
 4 
% Distributed under GPL 2 or later
5 
 
 5 
 
6 
\name{validUTF8}
 6 
\name{validUTF8}
7 
\title{Check if a Character Vector is Validly Encoded}
 7 
\title{Check if a Character Vector is Validly Encoded}
8 
\alias{validUTF8}
 8 
\alias{validUTF8}
Line 60... Line 60...
60 
Encoding(x) <-"UTF-8"
 60 
Encoding(x) <-"UTF-8"
61 
validEnc(x) # typically the last, x[10], is invalid
 61 
validEnc(x) # typically the last, x[10], is invalid
62 
 
 62 
 
63 
## Maybe advantageous to declare it "unknown":
 63 
## Maybe advantageous to declare it "unknown":
64 
G <- x ; Encoding(G[!validEnc(G)]) <- "unknown"
 64 
G <- x ; Encoding(G[!validEnc(G)]) <- "unknown"
65 
try( substr(x, 1,1) ) # gives 'invalid multibyte string' error
 65 
try( substr(x, 1,1) ) # gives 'invalid multibyte string' error in a UTF-8 locale
66 
try( substr(G, 1,1) ) # works
 66 
try( substr(G, 1,1) ) # works in a UTF-8 locale
67 
nchar(G) # fine, too
 67 
nchar(G) # fine, too
68 
## but it is not "more valid" typically:
 68 
## but it is not "more valid" typically:
69 
all.equal(validEnc(x),
 69 
all.equal(validEnc(x),
70 
          validEnc(G)) # typically TRUE
 70 
          validEnc(G)) # typically TRUE
71 
}
 71 
}