replace reference to Cygwin by MSYS2, add iconv(sub = "c99")

git-svn-id: https://svn.r-project.org/R/trunk@81786 00db46b3-68df-0310-9c12-caf00c1e9a41

doc/NEWS.Rd

@@ -212,6 +212,9 @@
       \item The return value from \code{ks.test()} now has class
       \code{c("ks.test", "htest")} -- packages using \code{try()} need
       to take care to use \code{inherits()} and not \code{==} on the class.
+
+      \item \code{iconv} now allows \code{sub = "c99"} to use C99-style
+      escapes on UTF-8 inputs which cannot be converted to \code{to}.
     }
   }
 

src/library/base/man/iconv.Rd

@@ -1,6 +1,6 @@
 % File src/library/base/man/iconv.Rd
 % Part of the R package, https://www.R-project.org
-% Copyright 1995-2021 R Core Team
+% Copyright 1995-2022 R Core Team
 % Distributed under GPL 2 or later
 
 \name{iconv}
@@ -28,7 +28,9 @@ iconvlist()
     any non-convertible bytes in the input.  (This would normally be a
     single character, but can be more.)  If \code{"byte"}, the indication is
     \code{"<xx>"} with the hex code of the byte.  If \code{"Unicode"}
-    and converting from UTF-8, the Unicode point in the form \code{"<U+xxxx>"}.}
+    and converting from UTF-8, the Unicode point in the form
+    \code{"<U+xxxx>"}, or if \code{c99}, a C99-style escape
+    \code{"\\uxxxx"}.}
   \item{mark}{logical, for expert use.  Should encodings be marked?}
   \item{toRaw}{logical.  Should a list of raw vectors be returned rather
     than a character vector?}
@@ -67,14 +69,14 @@ iconvlist()
   validity checking and will often mis-convert inputs which are invalid
   in encoding \code{from}.
 
-  If \code{sub = "Unicode"} is used for a non-UTF-8 input it is the same
-  as \code{sub = "byte"}.
+  If \code{sub = "Unicode"} or \code{sub = "c99"} is used for a
+  non-UTF-8 input it is the same as \code{sub = "byte"}.
 }
 
 \section{Implementation Details}{
   There are three main implementations of \code{iconv} in use.  Linux's
   most common C runtime, \samp{glibc}, contains one.  Several platforms
-  supply GNU \samp{libiconv}, including macOS, FreeBSD and Cygwin, in
+  supply GNU \samp{libiconv}, including macOS and FreeBSD, in
   some cases with additional encodings.  On Windows we use a version of
   Yukihiro Nakadaira's \samp{win_iconv}, which is based on Windows'
   codepages.  (We have added many encoding names for compatibility with
@@ -187,6 +189,7 @@ iconv(x, "latin1", "ASCII", "?")     # "fa?ile"
 iconv(x, "latin1", "ASCII", "")      # "faile"
 iconv(x, "latin1", "ASCII", "byte")  # "fa<e7>ile"
 iconv(xx, "UTF-8", "ASCII", "Unicode") # "fa<U+00E7>ile"
+iconv(xx, "UTF-8", "ASCII", "c99")   # "fa\u00E7ile"
 
 ## Extracts from old R help files (they are nowadays in UTF-8)
 x <- c("Ekstr\xf8m", "J\xf6reskog", "bi\xdfchen Z\xfcrcher")

src/library/utils/man/download.file.Rd

@@ -1,6 +1,6 @@
 % File src/library/utils/man/download.file.Rd
 % Part of the R package, https://www.R-project.org
-% Copyright 1995-2021 R Core Team
+% Copyright 1995-2022 R Core Team
 % Distributed under GPL 2 or later
 
 \name{download.file}
@@ -183,10 +183,11 @@ download.file(url, destfile, method, quiet = FALSE, mode = "w",
 
   \command{wget} (\url{https://www.gnu.org/software/wget/}) is commonly
   installed on Unix-alikes (but not macOS).  Windows binaries are
-  available from Cygwin, gnuwin32 and elsewhere.
+  available from MSYS2 and elsewhere.
 
   \command{curl} (\url{https://curl.se/}) is installed on macOS and
-  commonly on Unix-alikes.  Windows binaries are available at that URL.
+  increasingly commonly on Unix-alikes.  Windows binaries are available
+  at that URL.
 }
 \section{Setting Proxies}{
   For the Windows-only method \code{"wininet"}, the \sQuote{Internet

src/main/sysutils.c

@@ -727,7 +727,35 @@ SEXP attribute_hidden do_iconv(SEXP call, SEXP op, SEXP args, SEXP env)
 			}
 		    }
 		    goto next_char;
-		}  else if(strcmp(sub, "byte") == 0) {
+		} else if(fromUTF8 && streql(sub, "c99")) {
+		    if(outb < 11) {
+			R_AllocStringBuffer(2*cbuff.bufsize, &cbuff);
+			goto top_of_loop;
+		    }
+		    wchar_t wc;
+		    ssize_t clen = utf8toucs(&wc, inbuf);
+		    if(clen > 0 && inb >= clen) {
+			R_wchar_t ucs;
+			if (IS_HIGH_SURROGATE(wc))
+			    ucs = utf8toucs32(wc, inbuf);
+			else
+			    ucs = (R_wchar_t) wc;
+			inbuf += clen; inb -= clen;
+			if(ucs < 65536) {
+			    // gcc 7 objects to this with unsigned int
+			    snprintf(outbuf, 7, "\\u%04x", (unsigned short) ucs);
+			    outbuf += 6; outb -= 6;
+			} else {
+			    /* R_wchar_t is unsigned int on Windows, 
+			       otherwise wchar_t (usually int).
+			       In any case Unicode points <= 0x10FFFF
+			    */
+			    snprintf(outbuf, 11, "\\u%08x", (unsigned int) ucs);
+			    outbuf += 10; outb -= 10;
+			}
+		    }
+		    goto next_char;
+		} else if(strcmp(sub, "byte") == 0) {
 		    if(outb < 5) {
 			R_AllocStringBuffer(2*cbuff.bufsize, &cbuff);
 			goto top_of_loop;