Date: Fri, 5 Oct 2012 22:30:16 +0000 (UTC) From: Brooks Davis <brooks@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-vendor@freebsd.org Subject: svn commit: r241236 - in vendor/NetBSD/libc-vis: . dist Message-ID: <201210052230.q95MUG56051825@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: brooks Date: Fri Oct 5 22:30:16 2012 New Revision: 241236 URL: http://svn.freebsd.org/changeset/base/241236 Log: Vendor import of NetBSD's (un)vis(3) as of 2012-10-05 Added: vendor/NetBSD/libc-vis/ vendor/NetBSD/libc-vis/dist/ vendor/NetBSD/libc-vis/dist/unvis.3 (contents, props changed) vendor/NetBSD/libc-vis/dist/unvis.c (contents, props changed) vendor/NetBSD/libc-vis/dist/vis.3 (contents, props changed) vendor/NetBSD/libc-vis/dist/vis.c (contents, props changed) vendor/NetBSD/libc-vis/dist/vis.h (contents, props changed) Added: vendor/NetBSD/libc-vis/dist/unvis.3 ============================================================================== --- /dev/null 00:00:00 1970 (empty, because file is newly added) +++ vendor/NetBSD/libc-vis/dist/unvis.3 Fri Oct 5 22:30:16 2012 (r241236) @@ -0,0 +1,244 @@ +.\" $NetBSD: unvis.3,v 1.23 2011/03/17 14:06:29 wiz Exp $ +.\" +.\" Copyright (c) 1989, 1991, 1993 +.\" The Regents of the University of California. All rights reserved. +.\" +.\" Redistribution and use in source and binary forms, with or without +.\" modification, are permitted provided that the following conditions +.\" are met: +.\" 1. Redistributions of source code must retain the above copyright +.\" notice, this list of conditions and the following disclaimer. +.\" 2. Redistributions in binary form must reproduce the above copyright +.\" notice, this list of conditions and the following disclaimer in the +.\" documentation and/or other materials provided with the distribution. +.\" 3. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)unvis.3 8.2 (Berkeley) 12/11/93 +.\" +.Dd March 12, 2011 +.Dt UNVIS 3 +.Os +.Sh NAME +.Nm unvis , +.Nm strunvis +.Nd decode a visual representation of characters +.Sh LIBRARY +.Lb libc +.Sh SYNOPSIS +.In vis.h +.Ft int +.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 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 strunvisx +functions +are used to decode a visual representation of characters, as produced +by the +.Xr vis 3 +function, back into +the original form. +.Pp +The +.Fn unvis +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 +function decodes the characters pointed to by +.Ar src +into the buffer pointed to by +.Ar dst . +The +.Fn strunvis +function simply copies +.Ar src +to +.Ar dst , +decoding any escape sequences along the way, +and returns the number of characters placed into +.Ar dst , +or \-1 if an +invalid escape sequence was detected. +The size of +.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 +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. +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. +Call +.Fn unvis +with each successive byte, along with a pointer +to this integer, and a pointer to a destination character. +The +.Fn unvis +function has several return codes that must be handled properly. +They are: +.Bl -tag -width UNVIS_VALIDPUSH +.It Li \&0 (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 +pointed to by cp. +.It Dv UNVIS_VALIDPUSH +A valid character has been recognized and is available at the location +pointed to by cp; however, the character currently passed in should +be passed in again. +.It Dv UNVIS_NOCHAR +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. +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 flag set to +.Dv UNVIS_END +to extract any remaining character (the character passed in is ignored). +.Pp +The +.Ar 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 URI strings 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 \e quoted characters. +.Pp +The following code fragment illustrates a proper use of +.Fn unvis . +.Bd -literal -offset indent +int state = 0; +char out; + +while ((ch = getchar()) != EOF) { +again: + switch(unvis(\*[Am]out, ch, \*[Am]state, 0)) { + case 0: + case UNVIS_NOCHAR: + break; + case UNVIS_VALID: + (void)putchar(out); + break; + case UNVIS_VALIDPUSH: + (void)putchar(out); + goto again; + case UNVIS_SYNBAD: + errx(EXIT_FAILURE, "Bad character sequence!"); + } +} +if (unvis(\*[Am]out, '\e0', \*[Am]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 3 +.Rs +.%A R. Fielding +.%T Relative Uniform Resource Locators +.%O RFC1808 +.Re +.Sh HISTORY +The +.Fn unvis +function +first appeared in +.Bx 4.4 . +The +.Fn strnunvis +and +.Fn strnunvisx +functions appeared in +.Nx 6.0 . Added: vendor/NetBSD/libc-vis/dist/unvis.c ============================================================================== --- /dev/null 00:00:00 1970 (empty, because file is newly added) +++ vendor/NetBSD/libc-vis/dist/unvis.c Fri Oct 5 22:30:16 2012 (r241236) @@ -0,0 +1,553 @@ +/* $NetBSD: unvis.c,v 1.39 2012/03/13 21:13:37 christos Exp $ */ + +/*- + * Copyright (c) 1989, 1993 + * The Regents of the University of California. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include <sys/cdefs.h> +#if defined(LIBC_SCCS) && !defined(lint) +#if 0 +static char sccsid[] = "@(#)unvis.c 8.1 (Berkeley) 6/4/93"; +#else +__RCSID("$NetBSD: unvis.c,v 1.39 2012/03/13 21:13:37 christos Exp $"); +#endif +#endif /* LIBC_SCCS and not lint */ + +#include "namespace.h" +#include <sys/types.h> + +#include <assert.h> +#include <ctype.h> +#include <stdint.h> +#include <stdio.h> +#include <errno.h> +#include <vis.h> + +#ifdef __weak_alias +__weak_alias(strnunvisx,_strnunvisx) +#endif + +#if !HAVE_VIS +/* + * decode driven by state machine + */ +#define S_GROUND 0 /* haven't seen escape char */ +#define S_START 1 /* start decoding special sequence */ +#define S_META 2 /* metachar started (M) */ +#define S_META1 3 /* metachar more, regular char (-) */ +#define S_CTRL 4 /* control char started (^) */ +#define S_OCTAL2 5 /* octal digit 2 */ +#define S_OCTAL3 6 /* octal digit 3 */ +#define S_HEX 7 /* mandatory hex digit */ +#define S_HEX1 8 /* http hex digit */ +#define S_HEX2 9 /* http hex digit 2 */ +#define S_MIME1 10 /* mime hex digit 1 */ +#define S_MIME2 11 /* mime hex digit 2 */ +#define S_EATCRNL 12 /* mime eating CRNL */ +#define S_AMP 13 /* seen & */ +#define S_NUMBER 14 /* collecting number */ +#define S_STRING 15 /* collecting string */ + +#define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7') +#define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10)) +#define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10)) + +/* + * RFC 1866 + */ +static const struct nv { + const char *name; + uint8_t value; +} nv[] = { + { "AElig", 198 }, /* capital AE diphthong (ligature) */ + { "Aacute", 193 }, /* capital A, acute accent */ + { "Acirc", 194 }, /* capital A, circumflex accent */ + { "Agrave", 192 }, /* capital A, grave accent */ + { "Aring", 197 }, /* capital A, ring */ + { "Atilde", 195 }, /* capital A, tilde */ + { "Auml", 196 }, /* capital A, dieresis or umlaut mark */ + { "Ccedil", 199 }, /* capital C, cedilla */ + { "ETH", 208 }, /* capital Eth, Icelandic */ + { "Eacute", 201 }, /* capital E, acute accent */ + { "Ecirc", 202 }, /* capital E, circumflex accent */ + { "Egrave", 200 }, /* capital E, grave accent */ + { "Euml", 203 }, /* capital E, dieresis or umlaut mark */ + { "Iacute", 205 }, /* capital I, acute accent */ + { "Icirc", 206 }, /* capital I, circumflex accent */ + { "Igrave", 204 }, /* capital I, grave accent */ + { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */ + { "Ntilde", 209 }, /* capital N, tilde */ + { "Oacute", 211 }, /* capital O, acute accent */ + { "Ocirc", 212 }, /* capital O, circumflex accent */ + { "Ograve", 210 }, /* capital O, grave accent */ + { "Oslash", 216 }, /* capital O, slash */ + { "Otilde", 213 }, /* capital O, tilde */ + { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */ + { "THORN", 222 }, /* capital THORN, Icelandic */ + { "Uacute", 218 }, /* capital U, acute accent */ + { "Ucirc", 219 }, /* capital U, circumflex accent */ + { "Ugrave", 217 }, /* capital U, grave accent */ + { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */ + { "Yacute", 221 }, /* capital Y, acute accent */ + { "aacute", 225 }, /* small a, acute accent */ + { "acirc", 226 }, /* small a, circumflex accent */ + { "acute", 180 }, /* acute accent */ + { "aelig", 230 }, /* small ae diphthong (ligature) */ + { "agrave", 224 }, /* small a, grave accent */ + { "amp", 38 }, /* ampersand */ + { "aring", 229 }, /* small a, ring */ + { "atilde", 227 }, /* small a, tilde */ + { "auml", 228 }, /* small a, dieresis or umlaut mark */ + { "brvbar", 166 }, /* broken (vertical) bar */ + { "ccedil", 231 }, /* small c, cedilla */ + { "cedil", 184 }, /* cedilla */ + { "cent", 162 }, /* cent sign */ + { "copy", 169 }, /* copyright sign */ + { "curren", 164 }, /* general currency sign */ + { "deg", 176 }, /* degree sign */ + { "divide", 247 }, /* divide sign */ + { "eacute", 233 }, /* small e, acute accent */ + { "ecirc", 234 }, /* small e, circumflex accent */ + { "egrave", 232 }, /* small e, grave accent */ + { "eth", 240 }, /* small eth, Icelandic */ + { "euml", 235 }, /* small e, dieresis or umlaut mark */ + { "frac12", 189 }, /* fraction one-half */ + { "frac14", 188 }, /* fraction one-quarter */ + { "frac34", 190 }, /* fraction three-quarters */ + { "gt", 62 }, /* greater than */ + { "iacute", 237 }, /* small i, acute accent */ + { "icirc", 238 }, /* small i, circumflex accent */ + { "iexcl", 161 }, /* inverted exclamation mark */ + { "igrave", 236 }, /* small i, grave accent */ + { "iquest", 191 }, /* inverted question mark */ + { "iuml", 239 }, /* small i, dieresis or umlaut mark */ + { "laquo", 171 }, /* angle quotation mark, left */ + { "lt", 60 }, /* less than */ + { "macr", 175 }, /* macron */ + { "micro", 181 }, /* micro sign */ + { "middot", 183 }, /* middle dot */ + { "nbsp", 160 }, /* no-break space */ + { "not", 172 }, /* not sign */ + { "ntilde", 241 }, /* small n, tilde */ + { "oacute", 243 }, /* small o, acute accent */ + { "ocirc", 244 }, /* small o, circumflex accent */ + { "ograve", 242 }, /* small o, grave accent */ + { "ordf", 170 }, /* ordinal indicator, feminine */ + { "ordm", 186 }, /* ordinal indicator, masculine */ + { "oslash", 248 }, /* small o, slash */ + { "otilde", 245 }, /* small o, tilde */ + { "ouml", 246 }, /* small o, dieresis or umlaut mark */ + { "para", 182 }, /* pilcrow (paragraph sign) */ + { "plusmn", 177 }, /* plus-or-minus sign */ + { "pound", 163 }, /* pound sterling sign */ + { "quot", 34 }, /* double quote */ + { "raquo", 187 }, /* angle quotation mark, right */ + { "reg", 174 }, /* registered sign */ + { "sect", 167 }, /* section sign */ + { "shy", 173 }, /* soft hyphen */ + { "sup1", 185 }, /* superscript one */ + { "sup2", 178 }, /* superscript two */ + { "sup3", 179 }, /* superscript three */ + { "szlig", 223 }, /* small sharp s, German (sz ligature) */ + { "thorn", 254 }, /* small thorn, Icelandic */ + { "times", 215 }, /* multiply sign */ + { "uacute", 250 }, /* small u, acute accent */ + { "ucirc", 251 }, /* small u, circumflex accent */ + { "ugrave", 249 }, /* small u, grave accent */ + { "uml", 168 }, /* umlaut (dieresis) */ + { "uuml", 252 }, /* small u, dieresis or umlaut mark */ + { "yacute", 253 }, /* small y, acute accent */ + { "yen", 165 }, /* yen sign */ + { "yuml", 255 }, /* small y, dieresis or umlaut mark */ +}; + +/* + * unvis - decode characters previously encoded by vis + */ +int +unvis(char *cp, int c, int *astate, int flag) +{ + unsigned char uc = (unsigned char)c; + unsigned char st, ia, is, lc; + +/* + * Bottom 8 bits of astate hold the state machine state. + * Top 8 bits hold the current character in the http 1866 nv string decoding + */ +#define GS(a) ((a) & 0xff) +#define SS(a, b) (((uint32_t)(a) << 24) | (b)) +#define GI(a) ((uint32_t)(a) >> 24) + + _DIAGASSERT(cp != NULL); + _DIAGASSERT(astate != NULL); + st = GS(*astate); + + if (flag & UNVIS_END) { + switch (st) { + case S_OCTAL2: + case S_OCTAL3: + case S_HEX2: + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case S_GROUND: + return UNVIS_NOCHAR; + default: + return UNVIS_SYNBAD; + } + } + + switch (st) { + + case S_GROUND: + *cp = 0; + if ((flag & VIS_NOESCAPE) == 0 && c == '\\') { + *astate = SS(0, S_START); + return UNVIS_NOCHAR; + } + if ((flag & VIS_HTTP1808) && c == '%') { + *astate = SS(0, S_HEX1); + return UNVIS_NOCHAR; + } + if ((flag & VIS_HTTP1866) && c == '&') { + *astate = SS(0, S_AMP); + return UNVIS_NOCHAR; + } + if ((flag & VIS_MIMESTYLE) && c == '=') { + *astate = SS(0, S_MIME1); + return UNVIS_NOCHAR; + } + *cp = c; + return UNVIS_VALID; + + case S_START: + switch(c) { + case '\\': + *cp = c; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + *cp = (c - '0'); + *astate = SS(0, S_OCTAL2); + return UNVIS_NOCHAR; + case 'M': + *cp = (char)0200; + *astate = SS(0, S_META); + return UNVIS_NOCHAR; + case '^': + *astate = SS(0, S_CTRL); + return UNVIS_NOCHAR; + case 'n': + *cp = '\n'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'r': + *cp = '\r'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'b': + *cp = '\b'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'a': + *cp = '\007'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'v': + *cp = '\v'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 't': + *cp = '\t'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'f': + *cp = '\f'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 's': + *cp = ' '; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'E': + *cp = '\033'; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + case 'x': + *astate = SS(0, S_HEX); + return UNVIS_NOCHAR; + case '\n': + /* + * hidden newline + */ + *astate = SS(0, S_GROUND); + return UNVIS_NOCHAR; + case '$': + /* + * hidden marker + */ + *astate = SS(0, S_GROUND); + return UNVIS_NOCHAR; + } + goto bad; + + case S_META: + if (c == '-') + *astate = SS(0, S_META1); + else if (c == '^') + *astate = SS(0, S_CTRL); + else + goto bad; + return UNVIS_NOCHAR; + + case S_META1: + *astate = SS(0, S_GROUND); + *cp |= c; + return UNVIS_VALID; + + case S_CTRL: + if (c == '?') + *cp |= 0177; + else + *cp |= c & 037; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + + case S_OCTAL2: /* second possible octal digit */ + if (isoctal(uc)) { + /* + * yes - and maybe a third + */ + *cp = (*cp << 3) + (c - '0'); + *astate = SS(0, S_OCTAL3); + return UNVIS_NOCHAR; + } + /* + * no - done with current sequence, push back passed char + */ + *astate = SS(0, S_GROUND); + return UNVIS_VALIDPUSH; + + case S_OCTAL3: /* third possible octal digit */ + *astate = SS(0, S_GROUND); + if (isoctal(uc)) { + *cp = (*cp << 3) + (c - '0'); + return UNVIS_VALID; + } + /* + * we were done, push back passed char + */ + return UNVIS_VALIDPUSH; + + case S_HEX: + if (!isxdigit(uc)) + goto bad; + /*FALLTHROUGH*/ + case S_HEX1: + if (isxdigit(uc)) { + *cp = xtod(uc); + *astate = SS(0, S_HEX2); + return UNVIS_NOCHAR; + } + /* + * no - done with current sequence, push back passed char + */ + *astate = SS(0, S_GROUND); + return UNVIS_VALIDPUSH; + + case S_HEX2: + *astate = S_GROUND; + if (isxdigit(uc)) { + *cp = xtod(uc) | (*cp << 4); + return UNVIS_VALID; + } + return UNVIS_VALIDPUSH; + + case S_MIME1: + if (uc == '\n' || uc == '\r') { + *astate = SS(0, S_EATCRNL); + return UNVIS_NOCHAR; + } + if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { + *cp = XTOD(uc); + *astate = SS(0, S_MIME2); + return UNVIS_NOCHAR; + } + goto bad; + + case S_MIME2: + if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { + *astate = SS(0, S_GROUND); + *cp = XTOD(uc) | (*cp << 4); + return UNVIS_VALID; + } + goto bad; + + case S_EATCRNL: + switch (uc) { + case '\r': + case '\n': + return UNVIS_NOCHAR; + case '=': + *astate = SS(0, S_MIME1); + return UNVIS_NOCHAR; + default: + *cp = uc; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + } + + case S_AMP: + *cp = 0; + if (uc == '#') { + *astate = SS(0, S_NUMBER); + return UNVIS_NOCHAR; + } + *astate = SS(0, S_STRING); + /*FALLTHROUGH*/ + + case S_STRING: + ia = *cp; /* index in the array */ + is = GI(*astate); /* index in the string */ + lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */ + + if (uc == ';') + uc = '\0'; + + for (; ia < __arraycount(nv); ia++) { + if (is != 0 && nv[ia].name[is - 1] != lc) + goto bad; + if (nv[ia].name[is] == uc) + break; + } + + if (ia == __arraycount(nv)) + goto bad; + + if (uc != 0) { + *cp = ia; + *astate = SS(is + 1, S_STRING); + return UNVIS_NOCHAR; + } + + *cp = nv[ia].value; + *astate = SS(0, S_GROUND); + return UNVIS_VALID; + + case S_NUMBER: + if (uc == ';') + return UNVIS_VALID; + if (!isdigit(uc)) + goto bad; + *cp += (*cp * 10) + uc - '0'; + return UNVIS_NOCHAR; + + default: + bad: + /* + * decoder in unknown state - (probably uninitialized) + */ + *astate = SS(0, S_GROUND); + return UNVIS_SYNBAD; + } +} + +/* + * strnunvisx - decode src into dst + * + * Number of chars decoded into dst is returned, -1 on error. + * Dst is null terminated. + */ + +int +strnunvisx(char *dst, size_t dlen, const char *src, int flag) +{ + char c; + char t = '\0', *start = dst; + int state = 0; + + _DIAGASSERT(src != NULL); + _DIAGASSERT(dst != NULL); +#define CHECKSPACE() \ + do { \ + if (dlen-- == 0) { \ + errno = ENOSPC; \ + return -1; \ + } \ + } while (/*CONSTCOND*/0) + + while ((c = *src++) != '\0') { + again: + switch (unvis(&t, c, &state, flag)) { + case UNVIS_VALID: + CHECKSPACE(); + *dst++ = t; + break; + case UNVIS_VALIDPUSH: + CHECKSPACE(); + *dst++ = t; + goto again; + case 0: + case UNVIS_NOCHAR: + break; + case UNVIS_SYNBAD: + errno = EINVAL; + return -1; + default: + _DIAGASSERT(/*CONSTCOND*/0); + errno = EINVAL; + return -1; + } + } + if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) { + CHECKSPACE(); + *dst++ = t; + } + CHECKSPACE(); + *dst = '\0'; + return (int)(dst - start); +} + +int +strunvisx(char *dst, const char *src, int flag) +{ + return strnunvisx(dst, (size_t)~0, src, flag); +} + +int +strunvis(char *dst, const char *src) +{ + return strnunvisx(dst, (size_t)~0, src, 0); +} + +int +strnunvis(char *dst, size_t dlen, const char *src) +{ + return strnunvisx(dst, dlen, src, 0); +} +#endif Added: vendor/NetBSD/libc-vis/dist/vis.3 ============================================================================== --- /dev/null 00:00:00 1970 (empty, because file is newly added) +++ vendor/NetBSD/libc-vis/dist/vis.3 Fri Oct 5 22:30:16 2012 (r241236) @@ -0,0 +1,441 @@ +.\" $NetBSD: vis.3,v 1.27 2011/05/17 07:10:39 joerg Exp $ +.\" +.\" Copyright (c) 1989, 1991, 1993 +.\" The Regents of the University of California. All rights reserved. +.\" +.\" Redistribution and use in source and binary forms, with or without +.\" modification, are permitted provided that the following conditions +.\" are met: +.\" 1. Redistributions of source code must retain the above copyright +.\" notice, this list of conditions and the following disclaimer. +.\" 2. Redistributions in binary form must reproduce the above copyright +.\" notice, this list of conditions and the following disclaimer in the +.\" documentation and/or other materials provided with the distribution. +.\" 3. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)vis.3 8.1 (Berkeley) 6/9/93 +.\" +.Dd March 12, 2011 +.Dt VIS 3 +.Os +.Sh NAME +.Nm vis , +.Nm nvis , +.Nm strvis , +.Nm strnvis , +.Nm strvisx , +.Nm strnvisx , +.Nm svis , +.Nm snvis , +.Nm strsvis , +.Nm strsnvis , +.Nm strsvisx +.Nm strsnvisx +.Nd visually encode characters +.Sh LIBRARY +.Lb libc +.Sh SYNOPSIS +.In vis.h +.Ft char * +.Fn vis "char *dst" "int c" "int flag" "int nextc" +.Ft char * +.Fn nvis "char *dst" "size_t dlen" "int c" "int flag" "int nextc" +.Ft int +.Fn strvis "char *dst" "const char *src" "int flag" +.Ft int +.Fn strnvis "char *dst" "size_t dlen" "const char *src" "int flag" +.Ft int +.Fn strvisx "char *dst" "const char *src" "size_t len" "int flag" +.Ft int +.Fn strnvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag" +.Ft char * +.Fn svis "char *dst" "int c" "int flag" "int nextc" "const char *extra" +.Ft char * +.Fn snvis "char *dst" "size_t dlen" "int c" "int flag" "int nextc" "const char *extra" +.Ft int +.Fn strsvis "char *dst" "const char *src" "int flag" "const char *extra" +.Ft int +.Fn strsnvis "char *dst" "size_t dlen" "const char *src" "int flag" "const char *extra" +.Ft int +.Fn strsvisx "char *dst" "const char *src" "size_t len" "int flag" "const char *extra" +.Ft int +.Fn strsnvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag" "const char *extra" +.Sh DESCRIPTION +The +.Fn vis +function +copies into +.Fa dst +a string which represents the character +.Fa c . +If +.Fa c +needs no encoding, it is copied in unaltered. +The string is null terminated, and a pointer to the end of the string is +returned. +The maximum length of any encoding is four +characters (not including the trailing +.Dv NUL ) ; +thus, when +encoding a set of characters into a buffer, the size of the buffer should +be four times the number of characters encoded, plus one for the trailing +.Dv NUL . +The flag parameter is used for altering the default range of +characters considered for encoding and for altering the visual +representation. +The additional character, +.Fa nextc , +is only used when selecting the +.Dv VIS_CSTYLE +encoding format (explained below). +.Pp +The +.Fn strvis , +.Fn strnvis , +.Fn strvisx , +and +.Fn strnvisx +functions copy into +.Fa dst +a visual representation of +the string +.Fa src . +The +.Fn strvis +and +.Fn strnvis +functions encode characters from +.Fa src +up to the +first +.Dv NUL . +The +.Fn strvisx +and +.Fn strnvisx +functions encode exactly +.Fa len +characters from +.Fa src +(this +is useful for encoding a block of data that may contain +.Dv NUL Ns 's ) . +Both forms +.Dv NUL +terminate +.Fa dst . +The size of +.Fa dst +must be four times the number +of characters encoded from +.Fa src +(plus one for the +.Dv NUL ) . +Both +forms return the number of characters in dst (not including +the trailing +.Dv NUL ) . +The +.Dq n +versions of the functions also take an additional argument +.Fa dlen +that indicates the length of the +.Fa dst +buffer. +If +.Fa dlen +is not large enough to fix the converted string then the +.Fn strnvis +and +.Fn strnvisx +functions return \-1 and set +.Va errno +to +.Dv ENOSPC . +.Pp +The functions +.Fn svis , +.Fn snvis , +.Fn strsvis , +.Fn strsnvis , +.Fn strsvisx , +and +.Fn strsnvisx +correspond to +.Fn vis , +.Fn nvis , +.Fn strvis , +.Fn strnvis , +.Fn strvisx , +and +.Fn strnvisx +but have an additional argument +.Fa extra , +pointing to a +.Dv NUL +terminated list of characters. +These characters will be copied encoded or backslash-escaped into +.Fa dst . +These functions are useful e.g. to remove the special meaning +of certain characters to shells. *** DIFF OUTPUT TRUNCATED AT 1000 LINES ***
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201210052230.q95MUG56051825>