[R-gregmisc-users] SF.net SVN: r-gregmisc:[1808] trunk/gtools

[<wa...@us...>]

Revision: 1808
          http://sourceforge.net/p/r-gregmisc/code/1808
Author:   warnes
Date:     2014-04-17 16:56:34 +0000 (Thu, 17 Apr 2014)
Log Message:
-----------
Add ASCIIfy function posted to RDevel by Arni Magnusson

Modified Paths:
--------------
    trunk/gtools/DESCRIPTION
    trunk/gtools/NAMESPACE

Added Paths:
-----------
    trunk/gtools/R/ASCIIfy.R
    trunk/gtools/man/ASCIIfy.Rd

Modified: trunk/gtools/DESCRIPTION
===================================================================
--- trunk/gtools/DESCRIPTION	2014-04-10 02:32:21 UTC (rev 1807)
+++ trunk/gtools/DESCRIPTION	2014-04-17 16:56:34 UTC (rev 1808)
@@ -1,8 +1,8 @@
 Package: gtools
 Title: Various R programming tools
 Description: Various R programming tools
-Version: 3.3.1
-Date: 2014-03-01
+Version: 3.4.0
+Date: 2014-04-15
 Author: Gregory R. Warnes, Ben Bolker, and Thomas Lumley
 Maintainer: Gregory R. Warnes <gr...@wa...>
 License: LGPL-2.1

Modified: trunk/gtools/NAMESPACE
===================================================================
--- trunk/gtools/NAMESPACE	2014-04-10 02:32:21 UTC (rev 1807)
+++ trunk/gtools/NAMESPACE	2014-04-17 16:56:34 UTC (rev 1808)
@@ -4,6 +4,7 @@
        addLast,
        ask,
        assert,
+       ASCIIfy,
        binsearch,
        capture,
        checkRVersion,

Added: trunk/gtools/R/ASCIIfy.R
===================================================================
--- trunk/gtools/R/ASCIIfy.R	                        (rev 0)
+++ trunk/gtools/R/ASCIIfy.R	2014-04-17 16:56:34 UTC (rev 1808)
@@ -0,0 +1,39 @@
+ASCIIfy <- function(string, bytes=2, fallback="?")
+{
+  bytes <- match.arg(as.character(bytes), 1:2)
+  convert <- function(char)  # convert to ASCII, e.g. "z", "\xfe", or "\u00fe"
+  {
+    raw <- charToRaw(char)
+    if(length(raw)==1 && raw<=127)  # 7-bit
+      ascii <- char
+    else if(length(raw)==1 && bytes==1)  # 8-bit to \x00
+      ascii <- paste0("\\x", raw)
+    else if(length(raw)==1 && bytes==2)  # 8-bit to \u0000
+      ascii <- paste0("\\u", chartr(" ","0",formatC(as.character(raw),width=4)))
+    else if(length(raw)==2 && bytes==1)  # 16-bit to \x00, if possible
+      if(utf8ToInt(char) <= 255)
+        ascii <- paste0("\\x", format.hexmode(utf8ToInt(char)))
+      else {
+        ascii <- fallback; warning(char, " could not be converted to 1 byte")}
+    else if(length(raw)==2 && bytes==2)  # UTF-8 to \u0000
+      ascii <- paste0("\\u", format.hexmode(utf8ToInt(char),width=4))
+    else {
+      ascii <- fallback
+      warning(char, " could not be converted to ", bytes, " byte")}
+    return(ascii)
+  }
+
+  if(length(string) > 1)
+  {
+    sapply(string, ASCIIfy, bytes=bytes, fallback=fallback, USE.NAMES=FALSE)
+  }
+  else
+  {
+    input <- unlist(strsplit(string,""))  # "c"  "a"  "f"  "<\'e>"
+    output <- character(length(input))    # ""   ""   ""   ""
+    for(i in seq_along(input))
+      output[i] <- convert(input[i])      # "c"  "a"  "f"  "\\u00e9"
+    output <- paste(output, collapse="")  # "caf\\u00e9"
+    return(output)
+  }
+}

Added: trunk/gtools/man/ASCIIfy.Rd
===================================================================
--- trunk/gtools/man/ASCIIfy.Rd	                        (rev 0)
+++ trunk/gtools/man/ASCIIfy.Rd	2014-04-17 16:56:34 UTC (rev 1808)
@@ -0,0 +1,47 @@
+\name{ASCIIfy}
+\alias{ASCIIfy}
+\title{Convert Characters to ASCII}
+\description{
+  Convert character vector to ASCII, replacing non-ASCII characters with
+  single-byte (\samp{\x00}) or two-byte (\samp{\u0000}) codes.
+}
+\usage{
+ASCIIfy(x, bytes = 2, fallback = "?")
+}
+\arguments{
+  \item{x}{a character vector, possibly containing non-ASCII
+    characters.}
+  \item{bytes}{either \code{1} or \code{2}, for single-byte
+    (\samp{\x00}) or two-byte (\samp{\u0000}) codes.}
+  \item{fallback}{an output character to use, when input characters
+    cannot be converted.}
+}
+\value{
+  A character vector like \code{x}, except non-ASCII characters have
+  been replaced with \samp{\x00} or \samp{\u0000} codes.
+}
+\author{Arni Magnusson \email{ar...@ha...}}
+\note{
+  To render single backslashes, use these or similar techniques:
+  \verb{
+    write(ASCIIfy(x), "file.txt")
+    cat(paste(ASCIIfy(x), collapse="\n"), "\n", sep="")}
+
+  The resulting strings are plain ASCII and can be used in R functions
+  and datasets to improve package portability.
+}
+\seealso{
+  \code{\link[tools]{showNonASCII}} identifies non-ASCII characters in
+  a character vector.
+}
+\examples{
+cities <- c("S\u00e3o Paulo", "Reykjav\u00edk")
+print(cities)
+ASCIIfy(cities, 1)
+ASCIIfy(cities, 2)
+
+athens <- "\u0391\u03b8\u03ae\u03bd\u03b1"
+print(athens)
+ASCIIfy(athens)
+}
+\keyword{}

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.