Update vis/unvis modules from NetBSD

COPYING

@@ -122,7 +122,6 @@ Files:
  src/strmode.c
  src/strnstr.c
  src/unvis.c
- src/vis.c
 Copyright:
  Copyright © 1980, 1982, 1986, 1989-1994
      The Regents of the University of California.  All rights reserved.
@@ -315,6 +314,16 @@ License: BSD-2-clause-NetBSD
  ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  POSSIBILITY OF SUCH DAMAGE.
 
+Files:
+ src/vis.c
+Copyright:
+ Copyright © 1989, 1993
+     The Regents of the University of California.  All rights reserved.
+ .
+ Copyright © 1999, 2005 The NetBSD Foundation, Inc.
+ All rights reserved.
+License: BSD-3-clause-Regents and BSD-2-clause-NetBSD
+
 Files:
  include/bsd/sys/endian.h
  man/byteorder.3bsd

include/bsd/vis.h

+/*	$NetBSD: vis.h,v 1.25 2017/04/23 01:57:36 christos Exp $	*/
+
 /*-
  * Copyright (c) 1990, 1993
  *	The Regents of the University of California.  All rights reserved.
@@ -27,7 +29,6 @@
  * SUCH DAMAGE.
  *
  *	@(#)vis.h	8.1 (Berkeley) 6/2/93
- * $FreeBSD: src/include/vis.h,v 1.11 2003/10/30 10:40:49 phk Exp $
  */
 
 #ifndef LIBBSD_VIS_H
@@ -38,25 +39,34 @@
 /*
  * to select alternate encoding format
  */
-#define	VIS_OCTAL	0x01	/* use octal \ddd format */
-#define	VIS_CSTYLE	0x02	/* use \[nrft0..] where appropriate */
+#define	VIS_OCTAL	0x0001	/* use octal \ddd format */
+#define	VIS_CSTYLE	0x0002	/* use \[nrft0..] where appropriate */
 
 /*
  * to alter set of characters encoded (default is to encode all
  * non-graphic except space, tab, and newline).
  */
-#define	VIS_SP		0x04	/* also encode space */
-#define	VIS_TAB		0x08	/* also encode tab */
-#define	VIS_NL		0x10	/* also encode newline */
+#define	VIS_SP		0x0004	/* also encode space */
+#define	VIS_TAB		0x0008	/* also encode tab */
+#define	VIS_NL		0x0010	/* also encode newline */
 #define	VIS_WHITE	(VIS_SP | VIS_TAB | VIS_NL)
-#define	VIS_SAFE	0x20	/* only encode "unsafe" characters */
+#define	VIS_SAFE	0x0020	/* only encode "unsafe" characters */
+#define	VIS_DQ		0x8000	/* also encode double quotes */
 
 /*
  * other
  */
-#define	VIS_NOSLASH	0x40	/* inhibit printing '\' */
-#define	VIS_HTTPSTYLE	0x80	/* http-style escape % HEX HEX */
-#define	VIS_GLOB	0x100	/* encode glob(3) magics */
+#define	VIS_NOSLASH	0x0040	/* inhibit printing '\' */
+#define	VIS_HTTP1808	0x0080	/* http-style escape % hex hex */
+#define	VIS_HTTPSTYLE	0x0080	/* http-style escape % hex hex */
+#define	VIS_MIMESTYLE	0x0100	/* mime-style escape = HEX HEX */
+#define	VIS_HTTP1866	0x0200	/* http-style &#num; or &string; */
+#define	VIS_NOESCAPE	0x0400	/* don't decode `\' */
+#define	_VIS_END	0x0800	/* for unvis */
+#define	VIS_GLOB	0x1000	/* encode glob(3) magic characters */
+#define	VIS_SHELL	0x2000	/* encode shell special characters [not glob] */
+#define	VIS_META	(VIS_WHITE | VIS_GLOB | VIS_SHELL)
+#define	VIS_NOLOCALE	0x4000	/* encode using the C locale */
 
 /*
  * unvis return codes
@@ -70,7 +80,7 @@
 /*
  * unvis flags
  */
-#define	UNVIS_END	1	/* no more characters */
+#define	UNVIS_END	_VIS_END	/* no more characters */
 
 #ifdef LIBBSD_OVERLAY
 #include <sys/cdefs.h>
@@ -80,12 +90,33 @@
 
 __BEGIN_DECLS
 char	*vis(char *, int, int, int);
+char	*nvis(char *, size_t, int, int, int);
+
+char	*svis(char *, int, int, int, const char *);
+char	*snvis(char *, size_t, int, int, int, const char *);
+
 int	strvis(char *, const char *, int);
+int	stravis(char **, const char *, int);
+int	strnvis(char *, size_t, const char *, int);
+
+int	strsvis(char *, const char *, int, const char *);
+int	strsnvis(char *, size_t, const char *, int, const char *);
+
 int	strvisx(char *, const char *, size_t, int);
-int	strnvis(char *, const char *, size_t, int);
+int	strnvisx(char *, size_t, const char *, size_t, int);
+int	strenvisx(char *, size_t, const char *, size_t, int, int *);
+
+int	strsvisx(char *, const char *, size_t, int, const char *);
+int	strsnvisx(char *, size_t, const char *, size_t, int, const char *);
+int	strsenvisx(char *, size_t, const char *, size_t , int, const char *,
+    int *);
+
 int	strunvis(char *, const char *);
+int	strnunvis(char *, size_t, const char *);
+
 int	strunvisx(char *, const char *, int);
-ssize_t strnunvis(char *, const char *, size_t);
+int	strnunvisx(char *, size_t, const char *, int);
+
 int	unvis(char *, int, int *, int);
 __END_DECLS
 

man/unvis.3bsd

-.\"	$OpenBSD: unvis.3,v 1.15 2005/07/22 03:16:58 jaredy Exp $
+.\"	$NetBSD: unvis.3,v 1.29 2017/10/24 19:14:55 abhinav Exp $
 .\"
 .\" Copyright (c) 1989, 1991, 1993
 .\"	The Regents of the University of California.  All rights reserved.
@@ -27,13 +27,17 @@
 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 .\" SUCH DAMAGE.
 .\"
-.Dd $Mdocdate: May 31 2007 $
+.\"     @(#)unvis.3	8.2 (Berkeley) 12/11/93
+.\"
+.Dd March 12, 2011
 .Dt UNVIS 3bsd
 .Os
 .Sh NAME
 .Nm unvis ,
 .Nm strunvis ,
-.Nm strnunvis
+.Nm strnunvis ,
+.Nm strunvisx ,
+.Nm strnunvisx
 .Nd decode a visual representation of characters
 .Sh LIBRARY
 .ds str-Lb-libbsd Utility functions from BSD systems (libbsd, \-lbsd)
@@ -44,88 +48,91 @@
 .Xr libbsd 7
 for include usage.)
 .Ft int
-.Fn unvis "char *cp" "char c" "int *astate" "int flag"
+.Fn unvis "char *cp" "int c" "int *astate" "int flag"
+.Ft int
+.Fn strunvis "char *dst" "const char *src"
+.Ft int
+.Fn strnunvis "char *dst" "size_t dlen" "const char *src"
 .Ft int
-.Fn strunvis "char *dst" "char *src"
-.Ft ssize_t
-.Fn strnunvis "char *dst" "char *src" "size_t size"
+.Fn strunvisx "char *dst" "const char *src" "int flag"
+.Ft int
+.Fn strnunvisx "char *dst" "size_t dlen" "const char *src" "int flag"
 .Sh DESCRIPTION
 The
 .Fn unvis ,
 .Fn strunvis
 and
-.Fn strnunvis
-functions are used to decode a visual representation of characters,
-as produced by the
+.Fn strunvisx
+functions
+are used to decode a visual representation of characters, as produced
+by the
 .Xr vis 3bsd
-function, back into the original form.
+function, back into
+the original form.
+.Pp
+The
 .Fn unvis
-is called with successive characters in
-.Fa c
-until a valid
-sequence is recognized, at which time the decoded character is
-available at the character pointed to by
-.Fa cp .
+function is called with successive characters in
+.Ar c
+until a valid sequence is recognized, at which time the decoded
+character is available at the character pointed to by
+.Ar cp .
 .Pp
+The
 .Fn strunvis
-decodes the characters pointed to by
-.Fa src
+function decodes the characters pointed to by
+.Ar src
 into the buffer pointed to by
-.Fa dst .
-.Pp
-.Fn strnunvis
-decodes the characters pointed to by
-.Fa src
-into the buffer pointed to by
-.Fa dst ,
-writing a maximum of
-.Fa size
-bytes.
+.Ar dst .
 The
 .Fn strunvis
 function simply copies
-.Fa src
+.Ar src
 to
-.Fa dst ,
+.Ar dst ,
 decoding any escape sequences along the way,
 and returns the number of characters placed into
-.Fa dst ,
+.Ar dst ,
 or \-1 if an
 invalid escape sequence was detected.
 The size of
-.Fa dst
-should be
-equal to the size of
-.Fa src
+.Ar dst
+should be equal to the size of
+.Ar src
 (that is, no expansion takes place during decoding).
+.Pp
+The
+.Fn strunvisx
+function does the same as the
 .Fn strunvis
-terminates the destination string with a trailing NUL byte;
-.Fn strnunvis
-does so if
-.Fa size
-is larger than 0.
+function,
+but it allows you to add a flag that specifies the style the string
+.Ar src
+is encoded with.
+Currently, the supported flags are:
+.Dv VIS_HTTPSTYLE
+and
+.Dv VIS_MIMESTYLE .
 .Pp
 The
 .Fn unvis
-function implements a state machine that can be used to decode an arbitrary
-stream of bytes.
+function implements a state machine that can be used to decode an
+arbitrary stream of bytes.
 All state associated with the bytes being decoded is stored outside the
 .Fn unvis
 function (that is, a pointer to the state is passed in), so
 calls decoding different streams can be freely intermixed.
-To start decoding a stream of bytes, first initialize an integer
-to zero.
+To start decoding a stream of bytes, first initialize an integer to zero.
 Call
 .Fn unvis
 with each successive byte, along with a pointer
 to this integer, and a pointer to a destination character.
-.Sh RETURN VALUES
 The
 .Fn unvis
 function has several return codes that must be handled properly.
 They are:
 .Bl -tag -width UNVIS_VALIDPUSH
-.It Li \&0 (zero)
+.It Li \&0 No (zero)
 Another character is necessary; nothing has been recognized yet.
 .It Dv UNVIS_VALID
 A valid character has been recognized and is available at the location
@@ -140,30 +147,41 @@ however, the character currently passed in should be passed in again.
 A valid sequence was detected, but no character was produced.
 This return code is necessary to indicate a logical break between characters.
 .It Dv UNVIS_SYNBAD
-An invalid escape sequence was detected, or the decoder is in an
-unknown state.
+An invalid escape sequence was detected, or the decoder is in an unknown state.
 The decoder is placed into the starting state.
 .El
 .Pp
 When all bytes in the stream have been processed, call
 .Fn unvis
-one more time with
-.Fa flag
-set to
+one more time with flag set to
 .Dv UNVIS_END
 to extract any remaining character (the character passed in is ignored).
 .Pp
 The
-.Fn strunvis
-function returns the number of bytes written (not counting
-the trailing NUL byte) or \-1 if an error occurred.
+.Fa flag
+argument is also used to specify the encoding style of the source.
+If set to
+.Dv VIS_HTTPSTYLE
+or
+.Dv VIS_HTTP1808 ,
+.Fn unvis
+will decode URI strings as specified in RFC 1808.
+If set to
+.Dv VIS_HTTP1866 ,
+.Fn unvis
+will decode entity references and numeric character references
+as specified in RFC 1866.
+If set to
+.Dv VIS_MIMESTYLE ,
+.Fn unvis
+will decode MIME Quoted-Printable strings as specified in RFC 2045.
+If set to
+.Dv VIS_NOESCAPE ,
+.Fn unvis
+will not decode
+.Ql \e
+quoted characters.
 .Pp
-The
-.Fn strnunvis
-function returns the number of bytes (not counting the trailing NUL byte)
-that would be needed to fully convert the input string, or \-1 if an
-error occurred.
-.Sh EXAMPLES
 The following code fragment illustrates a proper use of
 .Fn unvis .
 .Bd -literal -offset indent
@@ -177,25 +195,72 @@ again:
 	case UNVIS_NOCHAR:
 		break;
 	case UNVIS_VALID:
-		(void) putchar(out);
+		(void)putchar(out);
 		break;
 	case UNVIS_VALIDPUSH:
-		(void) putchar(out);
+		(void)putchar(out);
 		goto again;
 	case UNVIS_SYNBAD:
-		(void)fprintf(stderr, "bad sequence!\en");
-		exit(1);
+		errx(EXIT_FAILURE, "Bad character sequence!");
 	}
 }
-if (unvis(&out, (char)0, &state, UNVIS_END) == UNVIS_VALID)
-	(void) putchar(out);
+if (unvis(&out, '\e0', &state, UNVIS_END) == UNVIS_VALID)
+	(void)putchar(out);
 .Ed
+.Sh ERRORS
+The functions
+.Fn strunvis ,
+.Fn strnunvis ,
+.Fn strunvisx ,
+and
+.Fn strnunvisx
+will return \-1 on error and set
+.Va errno
+to:
+.Bl -tag -width Er
+.It Bq Er EINVAL
+An invalid escape sequence was detected, or the decoder is in an unknown state.
+.El
+.Pp
+In addition the functions
+.Fn strnunvis
+and
+.Fn strnunvisx
+will can also set
+.Va errno
+on error to:
+.Bl -tag -width Er
+.It Bq Er ENOSPC
+Not enough space to perform the conversion.
+.El
 .Sh SEE ALSO
 .Xr unvis 1 ,
 .Xr vis 1 ,
 .Xr vis 3bsd
+.Rs
+.%A R. Fielding
+.%T Relative Uniform Resource Locators
+.%O RFC1808
+.Re
 .Sh HISTORY
 The
 .Fn unvis
-function first appeared in
+function
+first appeared in
 .Bx 4.4 .
+The
+.Fn strnunvis
+and
+.Fn strnunvisx
+functions appeared in
+.Nx 6.0 .
+.Sh BUGS
+The names
+.Dv VIS_HTTP1808
+and
+.Dv VIS_HTTP1866
+are wrong.
+Percent-encoding was defined in RFC 1738, the original RFC for URL.
+RFC 1866 defines HTML 2.0, an application of SGML, from which it
+inherits concepts of numeric character references and entity
+references.

src/libbsd.map

@@ -144,4 +144,16 @@ LIBBSD_0.9 {
     flopenat;
 
     pidfile_fileno;
+
+    nvis;
+    snvis;
+    stravis;
+    strenvisx;
+    strnunvisx;
+    strsenvisx;
+    strsnvis;
+    strsnvisx;
+    strsvis;
+    strsvisx;
+    svis;
 } LIBBSD_0.8;