term_ascii.c

   1 /*      $Id: term_ascii.c,v 1.60 2018/04/13 18:31:00 schwarze Exp $ */
   2 /*
   3  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
   4  * Copyright (c) 2014, 2015, 2017, 2018 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 AUTHORS DISCLAIM ALL WARRANTIES
  11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
  12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHORS 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 <langinfo.h>
  25 #include <locale.h>
  26 #endif
  27 #include <stdint.h>
  28 #include <stdio.h>
  29 #include <stdlib.h>
  30 #include <string.h>
  31 #include <unistd.h>
  32 #if HAVE_WCHAR
  33 #include <wchar.h>
  34 #endif
  35
  36 #include "mandoc.h"
  37 #include "mandoc_aux.h"
  38 #include "out.h"
  39 #include "term.h"
  40 #include "manconf.h"
  41 #include "main.h"
  42
  43 static  struct termp     *ascii_init(enum termenc, const struct manoutput *);
  44 static  int               ascii_hspan(const struct termp *,
  45                                 const struct roffsu *);
  46 static  size_t            ascii_width(const struct termp *, int);
  47 static  void              ascii_advance(struct termp *, size_t);
  48 static  void              ascii_begin(struct termp *);
  49 static  void              ascii_end(struct termp *);
  50 static  void              ascii_endline(struct termp *);
  51 static  void              ascii_letter(struct termp *, int);
  52 static  void              ascii_setwidth(struct termp *, int, int);
  53
  54 #if HAVE_WCHAR
  55 static  void              locale_advance(struct termp *, size_t);
  56 static  void              locale_endline(struct termp *);
  57 static  void              locale_letter(struct termp *, int);
  58 static  size_t            locale_width(const struct termp *, int);
  59 #endif
  60
  61
  62 static struct termp *
  63 ascii_init(enum termenc enc, const struct manoutput *outopts)
  64 {
  65 #if HAVE_WCHAR
  66         char            *v;
  67 #endif
  68         struct termp    *p;
  69
  70         p = mandoc_calloc(1, sizeof(*p));
  71         p->tcol = p->tcols = mandoc_calloc(1, sizeof(*p->tcol));
  72         p->maxtcol = 1;
  73
  74         p->line = 1;
  75         p->defrmargin = p->lastrmargin = 78;
  76         p->fontq = mandoc_reallocarray(NULL,
  77              (p->fontsz = 8), sizeof(*p->fontq));
  78         p->fontq[0] = p->fontl = TERMFONT_NONE;
  79
  80         p->begin = ascii_begin;
  81         p->end = ascii_end;
  82         p->hspan = ascii_hspan;
  83         p->type = TERMTYPE_CHAR;
  84
  85         p->enc = TERMENC_ASCII;
  86         p->advance = ascii_advance;
  87         p->endline = ascii_endline;
  88         p->letter = ascii_letter;
  89         p->setwidth = ascii_setwidth;
  90         p->width = ascii_width;
  91
  92 #if HAVE_WCHAR
  93         if (TERMENC_ASCII != enc) {
  94
  95                 /*
  96                  * Do not change any of this to LC_ALL.  It might break
  97                  * the formatting by subtly changing the behaviour of
  98                  * various functions, for example strftime(3).  As a
  99                  * worst case, it might even cause buffer overflows.
 100                  */
 101
 102                 v = TERMENC_LOCALE == enc ?
 103                     setlocale(LC_CTYPE, "") :
 104                     setlocale(LC_CTYPE, UTF8_LOCALE);
 105
 106                 /*
 107                  * We only support UTF-8,
 108                  * so revert to ASCII for anything else.
 109                  */
 110
 111                 if (v != NULL &&
 112                     strcmp(nl_langinfo(CODESET), "UTF-8") != 0)
 113                         v = setlocale(LC_CTYPE, "C");
 114
 115                 if (v != NULL && MB_CUR_MAX > 1) {
 116                         p->enc = enc;
 117                         p->advance = locale_advance;
 118                         p->endline = locale_endline;
 119                         p->letter = locale_letter;
 120                         p->width = locale_width;
 121                 }
 122         }
 123 #endif
 124
 125         if (outopts->mdoc) {
 126                 p->mdocstyle = 1;
 127                 p->defindent = 5;
 128         }
 129         if (outopts->indent)
 130                 p->defindent = outopts->indent;
 131         if (outopts->width)
 132                 p->defrmargin = outopts->width;
 133         if (outopts->synopsisonly)
 134                 p->synopsisonly = 1;
 135
 136         return p;
 137 }
 138
 139 void *
 140 ascii_alloc(const struct manoutput *outopts)
 141 {
 142
 143         return ascii_init(TERMENC_ASCII, outopts);
 144 }
 145
 146 void *
 147 utf8_alloc(const struct manoutput *outopts)
 148 {
 149
 150         return ascii_init(TERMENC_UTF8, outopts);
 151 }
 152
 153 void *
 154 locale_alloc(const struct manoutput *outopts)
 155 {
 156
 157         return ascii_init(TERMENC_LOCALE, outopts);
 158 }
 159
 160 static void
 161 ascii_setwidth(struct termp *p, int iop, int width)
 162 {
 163
 164         width /= 24;
 165         p->tcol->rmargin = p->defrmargin;
 166         if (iop > 0)
 167                 p->defrmargin += width;
 168         else if (iop == 0)
 169                 p->defrmargin = width ? (size_t)width : p->lastrmargin;
 170         else if (p->defrmargin > (size_t)width)
 171                 p->defrmargin -= width;
 172         else
 173                 p->defrmargin = 0;
 174         p->lastrmargin = p->tcol->rmargin;
 175         p->tcol->rmargin = p->maxrmargin = p->defrmargin;
 176 }
 177
 178 void
 179 terminal_sepline(void *arg)
 180 {
 181         struct termp    *p;
 182         size_t           i;
 183
 184         p = (struct termp *)arg;
 185         (*p->endline)(p);
 186         for (i = 0; i < p->defrmargin; i++)
 187                 (*p->letter)(p, '-');
 188         (*p->endline)(p);
 189         (*p->endline)(p);
 190 }
 191
 192 static size_t
 193 ascii_width(const struct termp *p, int c)
 194 {
 195
 196         return 1;
 197 }
 198
 199 void
 200 ascii_free(void *arg)
 201 {
 202
 203         term_free((struct termp *)arg);
 204 }
 205
 206 static void
 207 ascii_letter(struct termp *p, int c)
 208 {
 209
 210         putchar(c);
 211 }
 212
 213 static void
 214 ascii_begin(struct termp *p)
 215 {
 216
 217         (*p->headf)(p, p->argf);
 218 }
 219
 220 static void
 221 ascii_end(struct termp *p)
 222 {
 223
 224         (*p->footf)(p, p->argf);
 225 }
 226
 227 static void
 228 ascii_endline(struct termp *p)
 229 {
 230
 231         p->line++;
 232         p->tcol->offset -= p->ti;
 233         p->ti = 0;
 234         putchar('\n');
 235 }
 236
 237 static void
 238 ascii_advance(struct termp *p, size_t len)
 239 {
 240         size_t          i;
 241
 242         for (i = 0; i < len; i++)
 243                 putchar(' ');
 244 }
 245
 246 static int
 247 ascii_hspan(const struct termp *p, const struct roffsu *su)
 248 {
 249         double           r;
 250
 251         switch (su->unit) {
 252         case SCALE_BU:
 253                 r = su->scale;
 254                 break;
 255         case SCALE_CM:
 256                 r = su->scale * 240.0 / 2.54;
 257                 break;
 258         case SCALE_FS:
 259                 r = su->scale * 65536.0;
 260                 break;
 261         case SCALE_IN:
 262                 r = su->scale * 240.0;
 263                 break;
 264         case SCALE_MM:
 265                 r = su->scale * 0.24;
 266                 break;
 267         case SCALE_VS:
 268         case SCALE_PC:
 269                 r = su->scale * 40.0;
 270                 break;
 271         case SCALE_PT:
 272                 r = su->scale * 10.0 / 3.0;
 273                 break;
 274         case SCALE_EN:
 275         case SCALE_EM:
 276                 r = su->scale * 24.0;
 277                 break;
 278         default:
 279                 abort();
 280         }
 281         return r > 0.0 ? r + 0.01 : r - 0.01;
 282 }
 283
 284 const char *
 285 ascii_uc2str(int uc)
 286 {
 287         static const char nbrsp[2] = { ASCII_NBRSP, '\0' };
 288         static const char *tab[] = {
 289         "<NUL>","<SOH>","<STX>","<ETX>","<EOT>","<ENQ>","<ACK>","<BEL>",
 290         "<BS>", "\t",   "<LF>", "<VT>", "<FF>", "<CR>", "<SO>", "<SI>",
 291         "<DLE>","<DC1>","<DC2>","<DC3>","<DC4>","<NAK>","<SYN>","<ETB>",
 292         "<CAN>","<EM>", "<SUB>","<ESC>","<FS>", "<GS>", "<RS>", "<US>",
 293         " ",    "!",    "\"",   "#",    "$",    "%",    "&",    "'",
 294         "(",    ")",    "*",    "+",    ",",    "-",    ".",    "/",
 295         "0",    "1",    "2",    "3",    "4",    "5",    "6",    "7",
 296         "8",    "9",    ":",    ";",    "<",    "=",    ">",    "?",
 297         "@",    "A",    "B",    "C",    "D",    "E",    "F",    "G",
 298         "H",    "I",    "J",    "K",    "L",    "M",    "N",    "O",
 299         "P",    "Q",    "R",    "S",    "T",    "U",    "V",    "W",
 300         "X",    "Y",    "Z",    "[",    "\\",   "]",    "^",    "_",
 301         "`",    "a",    "b",    "c",    "d",    "e",    "f",    "g",
 302         "h",    "i",    "j",    "k",    "l",    "m",    "n",    "o",
 303         "p",    "q",    "r",    "s",    "t",    "u",    "v",    "w",
 304         "x",    "y",    "z",    "{",    "|",    "}",    "~",    "<DEL>",
 305         "<80>", "<81>", "<82>", "<83>", "<84>", "<85>", "<86>", "<87>",
 306         "<88>", "<89>", "<8A>", "<8B>", "<8C>", "<8D>", "<8E>", "<8F>",
 307         "<90>", "<91>", "<92>", "<93>", "<94>", "<95>", "<96>", "<97>",
 308         "<98>", "<99>", "<9A>", "<9B>", "<9C>", "<9D>", "<9E>", "<9F>",
 309         nbrsp,  "!",    "/\bc", "GBP",  "o\bx", "=\bY", "|",    "<section>",
 310         "\"",   "(C)",  "_\ba", "<<",   "~",    "",     "(R)",  "-",
 311         "<degree>","+-","^2",   "^3",   "'","<micro>","<paragraph>",".",
 312         ",",    "^1",   "_\bo", ">>",   "1/4",  "1/2",  "3/4",  "?",
 313         "`\bA", "'\bA", "^\bA", "~\bA", "\"\bA","o\bA", "AE",   ",\bC",
 314         "`\bE", "'\bE", "^\bE", "\"\bE","`\bI", "'\bI", "^\bI", "\"\bI",
 315         "Dh",   "~\bN", "`\bO", "'\bO", "^\bO", "~\bO", "\"\bO","x",
 316         "/\bO", "`\bU", "'\bU", "^\bU", "\"\bU","'\bY", "Th",   "ss",
 317         "`\ba", "'\ba", "^\ba", "~\ba", "\"\ba","o\ba", "ae",   ",\bc",
 318         "`\be", "'\be", "^\be", "\"\be","`\bi", "'\bi", "^\bi", "\"\bi",
 319         "dh",   "~\bn", "`\bo", "'\bo", "^\bo", "~\bo", "\"\bo","/",
 320         "/\bo", "`\bu", "'\bu", "^\bu", "\"\bu","'\by", "th",   "\"\by",
 321         "A",    "a",    "A",    "a",    "A",    "a",    "'\bC", "'\bc",
 322         "^\bC", "^\bc", "C",    "c",    "C",    "c",    "D",    "d",
 323         "/\bD", "/\bd", "E",    "e",    "E",    "e",    "E",    "e",
 324         "E",    "e",    "E",    "e",    "^\bG", "^\bg", "G",    "g",
 325         "G",    "g",    ",\bG", ",\bg", "^\bH", "^\bh", "/\bH", "/\bh",
 326         "~\bI", "~\bi", "I",    "i",    "I",    "i",    "I",    "i",
 327         "I",    "i",    "IJ",   "ij",   "^\bJ", "^\bj", ",\bK", ",\bk",
 328         "q",    "'\bL", "'\bl", ",\bL", ",\bl", "L",    "l",    "L",
 329         "l",    "/\bL", "/\bl", "'\bN", "'\bn", ",\bN", ",\bn", "N",
 330         "n",    "'n",   "Ng",   "ng",   "O",    "o",    "O",    "o",
 331         "O",    "o",    "OE",   "oe",   "'\bR", "'\br", ",\bR", ",\br",
 332         "R",    "r",    "'\bS", "'\bs", "^\bS", "^\bs", ",\bS", ",\bs",
 333         "S",    "s",    ",\bT", ",\bt", "T",    "t",    "/\bT", "/\bt",
 334         "~\bU", "~\bu", "U",    "u",    "U",    "u",    "U",    "u",
 335         "U",    "u",    "U",    "u",    "^\bW", "^\bw", "^\bY", "^\by",
 336         "\"\bY","'\bZ", "'\bz", "Z",    "z",    "Z",    "z",    "s",
 337         "b",    "B",    "B",    "b",    "6",    "6",    "O",    "C",
 338         "c",    "D",    "D",    "D",    "d",    "d",    "3",    "@",
 339         "E",    "F",    ",\bf", "G",    "G",    "hv",   "I",    "/\bI",
 340         "K",    "k",    "/\bl", "l",    "W",    "N",    "n",    "~\bO",
 341         "O",    "o",    "OI",   "oi",   "P",    "p",    "YR",   "2",
 342         "2",    "SH",   "sh",   "t",    "T",    "t",    "T",    "U",
 343         "u",    "Y",    "V",    "Y",    "y",    "/\bZ", "/\bz", "ZH",
 344         "ZH",   "zh",   "zh",   "/\b2", "5",    "5",    "ts",   "w",
 345         "|",    "||",   "|=",   "!",    "DZ",   "Dz",   "dz",   "LJ",
 346         "Lj",   "lj",   "NJ",   "Nj",   "nj",   "A",    "a",    "I",
 347         "i",    "O",    "o",    "U",    "u",    "U",    "u",    "U",
 348         "u",    "U",    "u",    "U",    "u",    "@",    "A",    "a",
 349         "A",    "a",    "AE",   "ae",   "/\bG", "/\bg", "G",    "g",
 350         "K",    "k",    "O",    "o",    "O",    "o",    "ZH",   "zh",
 351         "j",    "DZ",   "Dz",   "dz",   "'\bG", "'\bg", "HV",   "W",
 352         "`\bN", "`\bn", "A",    "a",    "'\bAE","'\bae","O",    "o"};
 353
 354         assert(uc >= 0);
 355         if ((size_t)uc < sizeof(tab)/sizeof(tab[0]))
 356                 return tab[uc];
 357         return mchars_uc2str(uc);
 358 }
 359
 360 #if HAVE_WCHAR
 361 static size_t
 362 locale_width(const struct termp *p, int c)
 363 {
 364         int             rc;
 365
 366         if (c == ASCII_NBRSP)
 367                 c = ' ';
 368         rc = wcwidth(c);
 369         if (rc < 0)
 370                 rc = 0;
 371         return rc;
 372 }
 373
 374 static void
 375 locale_advance(struct termp *p, size_t len)
 376 {
 377         size_t          i;
 378
 379         for (i = 0; i < len; i++)
 380                 putwchar(L' ');
 381 }
 382
 383 static void
 384 locale_endline(struct termp *p)
 385 {
 386
 387         p->line++;
 388         p->tcol->offset -= p->ti;
 389         p->ti = 0;
 390         putwchar(L'\n');
 391 }
 392
 393 static void
 394 locale_letter(struct termp *p, int c)
 395 {
 396
 397         putwchar(c);
 398 }
 399 #endif