usr/src/cmd/mandoc/term_ascii.c

   1 /*      $Id: term_ascii.c,v 1.43 2015/02/16 14:11:41 schwarze Exp $ */
   2 /*
   3  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
   4  * Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org>
   5  *
   6  * Permission to use, copy, modify, and distribute this software for any
   7  * purpose with or without fee is hereby granted, provided that the above
   8  * copyright notice and this permission notice appear in all copies.
   9  *
  10  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
  11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
  12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
  13  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
  14  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
  15  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  16  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  17  */
  18 #include "config.h"
  19
  20 #include <sys/types.h>
  21
  22 #include <assert.h>
  23 #if HAVE_WCHAR
  24 #include <locale.h>
  25 #endif
  26 #include <stdint.h>
  27 #include <stdio.h>
  28 #include <stdlib.h>
  29 #include <unistd.h>
  30 #if HAVE_WCHAR
  31 #include <wchar.h>
  32 #endif
  33
  34 #include "mandoc.h"
  35 #include "mandoc_aux.h"
  36 #include "out.h"
  37 #include "term.h"
  38 #include "main.h"
  39
  40 static  struct termp     *ascii_init(enum termenc,
  41                                 const struct mchars *, char *);
  42 static  double            ascii_hspan(const struct termp *,
  43                                 const struct roffsu *);
  44 static  size_t            ascii_width(const struct termp *, int);
  45 static  void              ascii_advance(struct termp *, size_t);
  46 static  void              ascii_begin(struct termp *);
  47 static  void              ascii_end(struct termp *);
  48 static  void              ascii_endline(struct termp *);
  49 static  void              ascii_letter(struct termp *, int);
  50 static  void              ascii_setwidth(struct termp *, int, size_t);
  51
  52 #if HAVE_WCHAR
  53 static  void              locale_advance(struct termp *, size_t);
  54 static  void              locale_endline(struct termp *);
  55 static  void              locale_letter(struct termp *, int);
  56 static  size_t            locale_width(const struct termp *, int);
  57 #endif
  58
  59
  60 static struct termp *
  61 ascii_init(enum termenc enc, const struct mchars *mchars, char *outopts)
  62 {
  63         const char      *toks[5];
  64         char            *v;
  65         struct termp    *p;
  66         const char      *errstr;
  67         int             num;
  68
  69         p = mandoc_calloc(1, sizeof(struct termp));
  70
  71         p->symtab = mchars;
  72         p->tabwidth = 5;
  73         p->defrmargin = p->lastrmargin = 78;
  74         p->fontq = mandoc_reallocarray(NULL,
  75              (p->fontsz = 8), sizeof(enum termfont));
  76         p->fontq[0] = p->fontl = TERMFONT_NONE;
  77
  78         p->begin = ascii_begin;
  79         p->end = ascii_end;
  80         p->hspan = ascii_hspan;
  81         p->type = TERMTYPE_CHAR;
  82
  83         p->enc = TERMENC_ASCII;
  84         p->advance = ascii_advance;
  85         p->endline = ascii_endline;
  86         p->letter = ascii_letter;
  87         p->setwidth = ascii_setwidth;
  88         p->width = ascii_width;
  89
  90 #if HAVE_WCHAR
  91         if (TERMENC_ASCII != enc) {
  92                 v = TERMENC_LOCALE == enc ?
  93                     setlocale(LC_ALL, "") :
  94                     setlocale(LC_CTYPE, "en_US.UTF-8");
  95                 if (NULL != v && MB_CUR_MAX > 1) {
  96                         p->enc = enc;
  97                         p->advance = locale_advance;
  98                         p->endline = locale_endline;
  99                         p->letter = locale_letter;
 100                         p->width = locale_width;
 101                 }
 102         }
 103 #endif
 104
 105         toks[0] = "indent";
 106         toks[1] = "width";
 107         toks[2] = "mdoc";
 108         toks[3] = "synopsis";
 109         toks[4] = NULL;
 110
 111         while (outopts && *outopts)
 112                 switch (getsubopt(&outopts, UNCONST(toks), &v)) {
 113                 case 0:
 114                         num = strtonum(v, 0, 1000, &errstr);
 115                         if (!errstr)
 116                                 p->defindent = num;
 117                         break;
 118                 case 1:
 119                         num = strtonum(v, 0, 1000, &errstr);
 120                         if (!errstr)
 121                                 p->defrmargin = num;
 122                         break;
 123                 case 2:
 124                         /*
 125                          * Temporary, undocumented mode
 126                          * to imitate mdoc(7) output style.
 127                          */
 128                         p->mdocstyle = 1;
 129                         p->defindent = 5;
 130                         break;
 131                 case 3:
 132                         p->synopsisonly = 1;
 133                         break;
 134                 default:
 135                         break;
 136                 }
 137
 138         /* Enforce a lower boundary. */
 139         if (p->defrmargin < 58)
 140                 p->defrmargin = 58;
 141
 142         return(p);
 143 }
 144
 145 void *
 146 ascii_alloc(const struct mchars *mchars, char *outopts)
 147 {
 148
 149         return(ascii_init(TERMENC_ASCII, mchars, outopts));
 150 }
 151
 152 void *
 153 utf8_alloc(const struct mchars *mchars, char *outopts)
 154 {
 155
 156         return(ascii_init(TERMENC_UTF8, mchars, outopts));
 157 }
 158
 159 void *
 160 locale_alloc(const struct mchars *mchars, char *outopts)
 161 {
 162
 163         return(ascii_init(TERMENC_LOCALE, mchars, outopts));
 164 }
 165
 166 static void
 167 ascii_setwidth(struct termp *p, int iop, size_t width)
 168 {
 169
 170         p->rmargin = p->defrmargin;
 171         if (iop > 0)
 172                 p->defrmargin += width;
 173         else if (iop == 0)
 174                 p->defrmargin = width ? width : p->lastrmargin;
 175         else if (p->defrmargin > width)
 176                 p->defrmargin -= width;
 177         else
 178                 p->defrmargin = 0;
 179         p->lastrmargin = p->rmargin;
 180         p->rmargin = p->maxrmargin = p->defrmargin;
 181 }
 182
 183 void
 184 ascii_sepline(void *arg)
 185 {
 186         struct termp    *p;
 187         size_t           i;
 188
 189         p = (struct termp *)arg;
 190         putchar('\n');
 191         for (i = 0; i < p->defrmargin; i++)
 192                 putchar('-');
 193         putchar('\n');
 194         putchar('\n');
 195 }
 196
 197 static size_t
 198 ascii_width(const struct termp *p, int c)
 199 {
 200
 201         return(1);
 202 }
 203
 204 void
 205 ascii_free(void *arg)
 206 {
 207
 208         term_free((struct termp *)arg);
 209 }
 210
 211 static void
 212 ascii_letter(struct termp *p, int c)
 213 {
 214
 215         putchar(c);
 216 }
 217
 218 static void
 219 ascii_begin(struct termp *p)
 220 {
 221
 222         (*p->headf)(p, p->argf);
 223 }
 224
 225 static void
 226 ascii_end(struct termp *p)
 227 {
 228
 229         (*p->footf)(p, p->argf);
 230 }
 231
 232 static void
 233 ascii_endline(struct termp *p)
 234 {
 235
 236         putchar('\n');
 237 }
 238
 239 static void
 240 ascii_advance(struct termp *p, size_t len)
 241 {
 242         size_t          i;
 243
 244         for (i = 0; i < len; i++)
 245                 putchar(' ');
 246 }
 247
 248 static double
 249 ascii_hspan(const struct termp *p, const struct roffsu *su)
 250 {
 251         double           r;
 252
 253         /*
 254          * Approximate based on character width.
 255          * None of these will be actually correct given that an inch on
 256          * the screen depends on character size, terminal, etc., etc.
 257          */
 258         switch (su->unit) {
 259         case SCALE_BU:
 260                 r = su->scale * 10.0 / 240.0;
 261                 break;
 262         case SCALE_CM:
 263                 r = su->scale * 10.0 / 2.54;
 264                 break;
 265         case SCALE_FS:
 266                 r = su->scale * 2730.666;
 267                 break;
 268         case SCALE_IN:
 269                 r = su->scale * 10.0;
 270                 break;
 271         case SCALE_MM:
 272                 r = su->scale / 100.0;
 273                 break;
 274         case SCALE_PC:
 275                 r = su->scale * 10.0 / 6.0;
 276                 break;
 277         case SCALE_PT:
 278                 r = su->scale * 10.0 / 72.0;
 279                 break;
 280         case SCALE_VS:
 281                 r = su->scale * 2.0 - 1.0;
 282                 break;
 283         case SCALE_EN:
 284                 /* FALLTHROUGH */
 285         case SCALE_EM:
 286                 r = su->scale;
 287                 break;
 288         default:
 289                 abort();
 290                 /* NOTREACHED */
 291         }
 292
 293         return(r);
 294 }
 295
 296 const char *
 297 ascii_uc2str(int uc)
 298 {
 299         static const char nbrsp[2] = { ASCII_NBRSP, '\0' };
 300         static const char *tab[] = {
 301         "<NUL>","<SOH>","<STX>","<ETX>","<EOT>","<ENQ>","<ACK>","<BEL>",
 302         "<BS>", "\t",   "<LF>", "<VT>", "<FF>", "<CR>", "<SO>", "<SI>",
 303         "<DLE>","<DC1>","<DC2>","<DC3>","<DC4>","<NAK>","<SYN>","<ETB>",
 304         "<CAN>","<EM>", "<SUB>","<ESC>","<FS>", "<GS>", "<RS>", "<US>",
 305         " ",    "!",    "\"",   "#",    "$",    "%",    "&",    "'",
 306         "(",    ")",    "*",    "+",    ",",    "-",    ".",    "/",
 307         "0",    "1",    "2",    "3",    "4",    "5",    "6",    "7",
 308         "8",    "9",    ":",    ";",    "<",    "=",    ">",    "?",
 309         "@",    "A",    "B",    "C",    "D",    "E",    "F",    "G",
 310         "H",    "I",    "J",    "K",    "L",    "M",    "N",    "O",
 311         "P",    "Q",    "R",    "S",    "T",    "U",    "V",    "W",
 312         "X",    "Y",    "Z",    "[",    "\\",   "]",    "^",    "_",
 313         "`",    "a",    "b",    "c",    "d",    "e",    "f",    "g",
 314         "h",    "i",    "j",    "k",    "l",    "m",    "n",    "o",
 315         "p",    "q",    "r",    "s",    "t",    "u",    "v",    "w",
 316         "x",    "y",    "z",    "{",    "|",    "}",    "~",    "<DEL>",
 317         "<80>", "<81>", "<82>", "<83>", "<84>", "<85>", "<86>", "<87>",
 318         "<88>", "<89>", "<8A>", "<8B>", "<8C>", "<8D>", "<8E>", "<8F>",
 319         "<90>", "<91>", "<92>", "<93>", "<94>", "<95>", "<96>", "<97>",
 320         "<99>", "<99>", "<9A>", "<9B>", "<9C>", "<9D>", "<9E>", "<9F>",
 321         nbrsp,  "!",    "/\bc", "GBP",  "o\bx", "=\bY", "|",    "<sec>",
 322         "\"",   "(C)",  "_\ba", "<<",   "~",    "",     "(R)",  "-",
 323         "<deg>","+-",   "2",    "3",    "'",    ",\bu", "<par>",".",
 324         ",",    "1",    "_\bo", ">>",   "1/4",  "1/2",  "3/4",  "?",
 325         "`\bA", "'\bA", "^\bA", "~\bA", "\"\bA","o\bA", "AE",   ",\bC",
 326         "`\bE", "'\bE", "^\bE", "\"\bE","`\bI", "'\bI", "^\bI", "\"\bI",
 327         "-\bD", "~\bN", "`\bO", "'\bO", "^\bO", "~\bO", "\"\bO","x",
 328         "/\bO", "`\bU", "'\bU", "^\bU", "\"\bU","'\bY", "Th",   "ss",
 329         "`\ba", "'\ba", "^\ba", "~\ba", "\"\ba","o\ba", "ae",   ",\bc",
 330         "`\be", "'\be", "^\be", "\"\be","`\bi", "'\bi", "^\bi", "\"\bi",
 331         "d",    "~\bn", "`\bo", "'\bo", "^\bo", "~\bo", "\"\bo","-:-",
 332         "/\bo", "`\bu", "'\bu", "^\bu", "\"\bu","'\by", "th",   "\"\by",
 333         "A",    "a",    "A",    "a",    "A",    "a",    "'\bC", "'\bc",
 334         "^\bC", "^\bc", "C",    "c",    "C",    "c",    "D",    "d",
 335         "/\bD", "/\bd", "E",    "e",    "E",    "e",    "E",    "e",
 336         "E",    "e",    "E",    "e",    "^\bG", "^\bg", "G",    "g",
 337         "G",    "g",    ",\bG", ",\bg", "^\bH", "^\bh", "/\bH", "/\bh",
 338         "~\bI", "~\bi", "I",    "i",    "I",    "i",    "I",    "i",
 339         "I",    "i",    "IJ",   "ij",   "^\bJ", "^\bj", ",\bK", ",\bk",
 340         "q",    "'\bL", "'\bl", ",\bL", ",\bl", "L",    "l",    "L",
 341         "l",    "/\bL", "/\bl", "'\bN", "'\bn", ",\bN", ",\bn", "N",
 342         "n",    "'n",   "Ng",   "ng",   "O",    "o",    "O",    "o",
 343         "O",    "o",    "OE",   "oe",   "'\bR", "'\br", ",\bR", ",\br",
 344         "R",    "r",    "'\bS", "'\bs", "^\bS", "^\bs", ",\bS", ",\bs",
 345         "S",    "s",    ",\bT", ",\bt", "T",    "t",    "/\bT", "/\bt",
 346         "~\bU", "~\bu", "U",    "u",    "U",    "u",    "U",    "u",
 347         "U",    "u",    "U",    "u",    "^\bW", "^\bw", "^\bY", "^\by",
 348         "\"\bY","'\bZ", "'\bz", "Z",    "z",    "Z",    "z",    "s",
 349         "b",    "B",    "B",    "b",    "6",    "6",    "O",    "C",
 350         "c",    "D",    "D",    "D",    "d",    "d",    "3",    "@",
 351         "E",    "F",    ",\bf", "G",    "G",    "hv",   "I",    "/\bI",
 352         "K",    "k",    "/\bl", "l",    "W",    "N",    "n",    "~\bO",
 353         "O",    "o",    "OI",   "oi",   "P",    "p",    "YR",   "2",
 354         "2",    "SH",   "sh",   "t",    "T",    "t",    "T",    "U",
 355         "u",    "Y",    "V",    "Y",    "y",    "/\bZ", "/\bz", "ZH",
 356         "ZH",   "zh",   "zh",   "/\b2", "5",    "5",    "ts",   "w",
 357         "|",    "||",   "|=",   "!",    "DZ",   "Dz",   "dz",   "LJ",
 358         "Lj",   "lj",   "NJ",   "Nj",   "nj",   "A",    "a",    "I",
 359         "i",    "O",    "o",    "U",    "u",    "U",    "u",    "U",
 360         "u",    "U",    "u",    "U",    "u",    "@",    "A",    "a",
 361         "A",    "a",    "AE",   "ae",   "/\bG", "/\bg", "G",    "g",
 362         "K",    "k",    "O",    "o",    "O",    "o",    "ZH",   "zh",
 363         "j",    "DZ",   "Dz",   "dz",   "'\bG", "'\bg", "HV",   "W",
 364         "`\bN", "`\bn", "A",    "a",    "'\bAE","'\bae","O",    "o"};
 365
 366         assert(uc >= 0);
 367         if ((size_t)uc < sizeof(tab)/sizeof(tab[0]))
 368                 return(tab[uc]);
 369         return(mchars_uc2str(uc));
 370 }
 371
 372 #if HAVE_WCHAR
 373 static size_t
 374 locale_width(const struct termp *p, int c)
 375 {
 376         int             rc;
 377
 378         if (c == ASCII_NBRSP)
 379                 c = ' ';
 380         rc = wcwidth(c);
 381         if (rc < 0)
 382                 rc = 0;
 383         return(rc);
 384 }
 385
 386 static void
 387 locale_advance(struct termp *p, size_t len)
 388 {
 389         size_t          i;
 390
 391         for (i = 0; i < len; i++)
 392                 putwchar(L' ');
 393 }
 394
 395 static void
 396 locale_endline(struct termp *p)
 397 {
 398
 399         putwchar(L'\n');
 400 }
 401
 402 static void
 403 locale_letter(struct termp *p, int c)
 404 {
 405
 406         putwchar(c);
 407 }
 408 #endif