freebsd-skq/contrib/mdocml/term_ascii.c

388 lines
9.4 KiB
C
Raw Normal View History

2017-07-31 19:17:54 +00:00
/* $Id: term_ascii.c,v 1.58 2017/06/14 14:24:20 schwarze Exp $ */
/*
* Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
2017-06-08 19:29:07 +00:00
* Copyright (c) 2014, 2015, 2017 Ingo Schwarze <schwarze@openbsd.org>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
2016-01-15 23:08:59 +00:00
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHORS DISCLAIM ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
2016-01-15 23:08:59 +00:00
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
#include "config.h"
#include <sys/types.h>
#include <assert.h>
#if HAVE_WCHAR
#include <locale.h>
#endif
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#if HAVE_WCHAR
#include <wchar.h>
#endif
#include "mandoc.h"
2014-11-22 18:08:25 +00:00
#include "mandoc_aux.h"
#include "out.h"
#include "term.h"
2016-01-15 23:08:59 +00:00
#include "manconf.h"
#include "main.h"
2016-01-15 23:08:59 +00:00
static struct termp *ascii_init(enum termenc, const struct manoutput *);
static int ascii_hspan(const struct termp *,
const struct roffsu *);
static size_t ascii_width(const struct termp *, int);
static void ascii_advance(struct termp *, size_t);
static void ascii_begin(struct termp *);
static void ascii_end(struct termp *);
static void ascii_endline(struct termp *);
static void ascii_letter(struct termp *, int);
2016-01-15 23:08:59 +00:00
static void ascii_setwidth(struct termp *, int, int);
#if HAVE_WCHAR
static void locale_advance(struct termp *, size_t);
static void locale_endline(struct termp *);
static void locale_letter(struct termp *, int);
static size_t locale_width(const struct termp *, int);
#endif
2014-11-22 18:08:25 +00:00
static struct termp *
2016-01-15 23:08:59 +00:00
ascii_init(enum termenc enc, const struct manoutput *outopts)
{
2016-01-15 23:08:59 +00:00
#if HAVE_WCHAR
char *v;
2016-01-15 23:08:59 +00:00
#endif
struct termp *p;
2017-06-08 19:29:07 +00:00
p = mandoc_calloc(1, sizeof(*p));
p->tcol = p->tcols = mandoc_calloc(1, sizeof(*p->tcol));
p->maxtcol = 1;
2016-01-15 23:08:59 +00:00
p->line = 1;
2014-11-22 18:08:25 +00:00
p->defrmargin = p->lastrmargin = 78;
p->fontq = mandoc_reallocarray(NULL,
2017-06-08 19:29:07 +00:00
(p->fontsz = 8), sizeof(*p->fontq));
p->fontq[0] = p->fontl = TERMFONT_NONE;
p->begin = ascii_begin;
p->end = ascii_end;
p->hspan = ascii_hspan;
p->type = TERMTYPE_CHAR;
p->enc = TERMENC_ASCII;
p->advance = ascii_advance;
p->endline = ascii_endline;
p->letter = ascii_letter;
2014-11-22 18:08:25 +00:00
p->setwidth = ascii_setwidth;
p->width = ascii_width;
#if HAVE_WCHAR
if (TERMENC_ASCII != enc) {
2016-01-15 23:08:59 +00:00
/*
* Do not change any of this to LC_ALL. It might break
* the formatting by subtly changing the behaviour of
* various functions, for example strftime(3). As a
* worst case, it might even cause buffer overflows.
*/
v = TERMENC_LOCALE == enc ?
2016-01-15 23:08:59 +00:00
setlocale(LC_CTYPE, "") :
setlocale(LC_CTYPE, UTF8_LOCALE);
if (NULL != v && MB_CUR_MAX > 1) {
p->enc = enc;
p->advance = locale_advance;
p->endline = locale_endline;
p->letter = locale_letter;
p->width = locale_width;
}
}
#endif
2016-01-15 23:08:59 +00:00
if (outopts->mdoc) {
p->mdocstyle = 1;
p->defindent = 5;
}
if (outopts->indent)
p->defindent = outopts->indent;
if (outopts->width)
p->defrmargin = outopts->width;
if (outopts->synopsisonly)
p->synopsisonly = 1;
return p;
}
void *
2016-01-15 23:08:59 +00:00
ascii_alloc(const struct manoutput *outopts)
{
2016-01-15 23:08:59 +00:00
return ascii_init(TERMENC_ASCII, outopts);
}
void *
2016-01-15 23:08:59 +00:00
utf8_alloc(const struct manoutput *outopts)
{
2016-01-15 23:08:59 +00:00
return ascii_init(TERMENC_UTF8, outopts);
}
void *
2016-01-15 23:08:59 +00:00
locale_alloc(const struct manoutput *outopts)
{
2016-01-15 23:08:59 +00:00
return ascii_init(TERMENC_LOCALE, outopts);
}
2014-11-22 18:08:25 +00:00
static void
2016-01-15 23:08:59 +00:00
ascii_setwidth(struct termp *p, int iop, int width)
2014-11-22 18:08:25 +00:00
{
2016-01-15 23:08:59 +00:00
width /= 24;
2017-06-08 19:29:07 +00:00
p->tcol->rmargin = p->defrmargin;
if (iop > 0)
2014-11-22 18:08:25 +00:00
p->defrmargin += width;
else if (iop == 0)
2016-01-15 23:08:59 +00:00
p->defrmargin = width ? (size_t)width : p->lastrmargin;
else if (p->defrmargin > (size_t)width)
2014-11-22 18:08:25 +00:00
p->defrmargin -= width;
else
p->defrmargin = 0;
2017-06-08 19:29:07 +00:00
p->lastrmargin = p->tcol->rmargin;
p->tcol->rmargin = p->maxrmargin = p->defrmargin;
2014-11-22 18:08:25 +00:00
}
void
2016-07-23 11:45:42 +00:00
terminal_sepline(void *arg)
{
struct termp *p;
size_t i;
p = (struct termp *)arg;
2016-07-23 11:45:42 +00:00
(*p->endline)(p);
for (i = 0; i < p->defrmargin; i++)
2016-07-23 11:45:42 +00:00
(*p->letter)(p, '-');
(*p->endline)(p);
(*p->endline)(p);
}
static size_t
ascii_width(const struct termp *p, int c)
{
2016-01-15 23:08:59 +00:00
return 1;
}
void
ascii_free(void *arg)
{
term_free((struct termp *)arg);
}
static void
ascii_letter(struct termp *p, int c)
{
2014-11-22 18:08:25 +00:00
putchar(c);
}
static void
ascii_begin(struct termp *p)
{
(*p->headf)(p, p->argf);
}
static void
ascii_end(struct termp *p)
{
(*p->footf)(p, p->argf);
}
static void
ascii_endline(struct termp *p)
{
2016-01-15 23:08:59 +00:00
p->line++;
2017-06-08 19:29:07 +00:00
p->tcol->offset -= p->ti;
p->ti = 0;
putchar('\n');
}
static void
ascii_advance(struct termp *p, size_t len)
{
2014-11-22 18:08:25 +00:00
size_t i;
for (i = 0; i < len; i++)
putchar(' ');
}
2016-01-15 23:08:59 +00:00
static int
ascii_hspan(const struct termp *p, const struct roffsu *su)
{
double r;
switch (su->unit) {
case SCALE_BU:
2016-01-15 23:08:59 +00:00
r = su->scale;
break;
2014-11-22 18:08:25 +00:00
case SCALE_CM:
2016-01-15 23:08:59 +00:00
r = su->scale * 240.0 / 2.54;
break;
case SCALE_FS:
2016-01-15 23:08:59 +00:00
r = su->scale * 65536.0;
break;
2014-11-22 18:08:25 +00:00
case SCALE_IN:
2016-01-15 23:08:59 +00:00
r = su->scale * 240.0;
break;
case SCALE_MM:
2016-01-15 23:08:59 +00:00
r = su->scale * 0.24;
break;
2016-01-15 23:08:59 +00:00
case SCALE_VS:
2014-11-22 18:08:25 +00:00
case SCALE_PC:
2016-01-15 23:08:59 +00:00
r = su->scale * 40.0;
break;
2014-11-22 18:08:25 +00:00
case SCALE_PT:
2016-01-15 23:08:59 +00:00
r = su->scale * 10.0 / 3.0;
break;
case SCALE_EN:
case SCALE_EM:
2016-01-15 23:08:59 +00:00
r = su->scale * 24.0;
break;
default:
abort();
}
2016-01-15 23:08:59 +00:00
return r > 0.0 ? r + 0.01 : r - 0.01;
}
const char *
ascii_uc2str(int uc)
{
static const char nbrsp[2] = { ASCII_NBRSP, '\0' };
static const char *tab[] = {
"<NUL>","<SOH>","<STX>","<ETX>","<EOT>","<ENQ>","<ACK>","<BEL>",
"<BS>", "\t", "<LF>", "<VT>", "<FF>", "<CR>", "<SO>", "<SI>",
"<DLE>","<DC1>","<DC2>","<DC3>","<DC4>","<NAK>","<SYN>","<ETB>",
"<CAN>","<EM>", "<SUB>","<ESC>","<FS>", "<GS>", "<RS>", "<US>",
" ", "!", "\"", "#", "$", "%", "&", "'",
"(", ")", "*", "+", ",", "-", ".", "/",
"0", "1", "2", "3", "4", "5", "6", "7",
"8", "9", ":", ";", "<", "=", ">", "?",
"@", "A", "B", "C", "D", "E", "F", "G",
"H", "I", "J", "K", "L", "M", "N", "O",
"P", "Q", "R", "S", "T", "U", "V", "W",
"X", "Y", "Z", "[", "\\", "]", "^", "_",
"`", "a", "b", "c", "d", "e", "f", "g",
"h", "i", "j", "k", "l", "m", "n", "o",
"p", "q", "r", "s", "t", "u", "v", "w",
"x", "y", "z", "{", "|", "}", "~", "<DEL>",
"<80>", "<81>", "<82>", "<83>", "<84>", "<85>", "<86>", "<87>",
"<88>", "<89>", "<8A>", "<8B>", "<8C>", "<8D>", "<8E>", "<8F>",
"<90>", "<91>", "<92>", "<93>", "<94>", "<95>", "<96>", "<97>",
2017-07-31 19:17:54 +00:00
"<98>", "<99>", "<9A>", "<9B>", "<9C>", "<9D>", "<9E>", "<9F>",
nbrsp, "!", "/\bc", "GBP", "o\bx", "=\bY", "|", "<sec>",
"\"", "(C)", "_\ba", "<<", "~", "", "(R)", "-",
"<deg>","+-", "2", "3", "'", ",\bu", "<par>",".",
",", "1", "_\bo", ">>", "1/4", "1/2", "3/4", "?",
"`\bA", "'\bA", "^\bA", "~\bA", "\"\bA","o\bA", "AE", ",\bC",
"`\bE", "'\bE", "^\bE", "\"\bE","`\bI", "'\bI", "^\bI", "\"\bI",
"-\bD", "~\bN", "`\bO", "'\bO", "^\bO", "~\bO", "\"\bO","x",
"/\bO", "`\bU", "'\bU", "^\bU", "\"\bU","'\bY", "Th", "ss",
"`\ba", "'\ba", "^\ba", "~\ba", "\"\ba","o\ba", "ae", ",\bc",
"`\be", "'\be", "^\be", "\"\be","`\bi", "'\bi", "^\bi", "\"\bi",
"d", "~\bn", "`\bo", "'\bo", "^\bo", "~\bo", "\"\bo","-:-",
"/\bo", "`\bu", "'\bu", "^\bu", "\"\bu","'\by", "th", "\"\by",
"A", "a", "A", "a", "A", "a", "'\bC", "'\bc",
"^\bC", "^\bc", "C", "c", "C", "c", "D", "d",
"/\bD", "/\bd", "E", "e", "E", "e", "E", "e",
"E", "e", "E", "e", "^\bG", "^\bg", "G", "g",
"G", "g", ",\bG", ",\bg", "^\bH", "^\bh", "/\bH", "/\bh",
"~\bI", "~\bi", "I", "i", "I", "i", "I", "i",
"I", "i", "IJ", "ij", "^\bJ", "^\bj", ",\bK", ",\bk",
"q", "'\bL", "'\bl", ",\bL", ",\bl", "L", "l", "L",
"l", "/\bL", "/\bl", "'\bN", "'\bn", ",\bN", ",\bn", "N",
"n", "'n", "Ng", "ng", "O", "o", "O", "o",
"O", "o", "OE", "oe", "'\bR", "'\br", ",\bR", ",\br",
"R", "r", "'\bS", "'\bs", "^\bS", "^\bs", ",\bS", ",\bs",
"S", "s", ",\bT", ",\bt", "T", "t", "/\bT", "/\bt",
"~\bU", "~\bu", "U", "u", "U", "u", "U", "u",
"U", "u", "U", "u", "^\bW", "^\bw", "^\bY", "^\by",
"\"\bY","'\bZ", "'\bz", "Z", "z", "Z", "z", "s",
"b", "B", "B", "b", "6", "6", "O", "C",
"c", "D", "D", "D", "d", "d", "3", "@",
"E", "F", ",\bf", "G", "G", "hv", "I", "/\bI",
"K", "k", "/\bl", "l", "W", "N", "n", "~\bO",
"O", "o", "OI", "oi", "P", "p", "YR", "2",
"2", "SH", "sh", "t", "T", "t", "T", "U",
"u", "Y", "V", "Y", "y", "/\bZ", "/\bz", "ZH",
"ZH", "zh", "zh", "/\b2", "5", "5", "ts", "w",
"|", "||", "|=", "!", "DZ", "Dz", "dz", "LJ",
"Lj", "lj", "NJ", "Nj", "nj", "A", "a", "I",
"i", "O", "o", "U", "u", "U", "u", "U",
"u", "U", "u", "U", "u", "@", "A", "a",
"A", "a", "AE", "ae", "/\bG", "/\bg", "G", "g",
"K", "k", "O", "o", "O", "o", "ZH", "zh",
"j", "DZ", "Dz", "dz", "'\bG", "'\bg", "HV", "W",
"`\bN", "`\bn", "A", "a", "'\bAE","'\bae","O", "o"};
assert(uc >= 0);
if ((size_t)uc < sizeof(tab)/sizeof(tab[0]))
2016-01-15 23:08:59 +00:00
return tab[uc];
return mchars_uc2str(uc);
}
#if HAVE_WCHAR
static size_t
locale_width(const struct termp *p, int c)
{
int rc;
2014-11-22 18:08:25 +00:00
if (c == ASCII_NBRSP)
c = ' ';
rc = wcwidth(c);
if (rc < 0)
rc = 0;
2016-01-15 23:08:59 +00:00
return rc;
}
static void
locale_advance(struct termp *p, size_t len)
{
2014-11-22 18:08:25 +00:00
size_t i;
for (i = 0; i < len; i++)
putwchar(L' ');
}
static void
locale_endline(struct termp *p)
{
2016-01-15 23:08:59 +00:00
p->line++;
2017-06-08 19:29:07 +00:00
p->tcol->offset -= p->ti;
p->ti = 0;
putwchar(L'\n');
}
static void
locale_letter(struct termp *p, int c)
{
2014-11-22 18:08:25 +00:00
putwchar(c);
}
#endif