version 1.30.2.1, 2014/08/17 22:14:28 |
version 1.61, 2018/05/20 21:37:34 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org> |
* Copyright (c) 2014, 2015, 2017, 2018 Ingo Schwarze <schwarze@openbsd.org> |
* |
* |
* Permission to use, copy, modify, and distribute this software for any |
* Permission to use, copy, modify, and distribute this software for any |
* purpose with or without fee is hereby granted, provided that the above |
* purpose with or without fee is hereby granted, provided that the above |
* copyright notice and this permission notice appear in all copies. |
* copyright notice and this permission notice appear in all copies. |
* |
* |
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES |
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHORS DISCLAIM ALL WARRANTIES |
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF |
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF |
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR |
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR |
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES |
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES |
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN |
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
|
|
|
|
#include <sys/types.h> |
#include <sys/types.h> |
|
|
#ifdef USE_WCHAR |
#include <assert.h> |
|
#if HAVE_WCHAR |
|
#include <langinfo.h> |
#include <locale.h> |
#include <locale.h> |
#endif |
#endif |
#include <stdint.h> |
#include <stdint.h> |
#include <stdio.h> |
#include <stdio.h> |
#include <stdlib.h> |
#include <stdlib.h> |
|
#include <string.h> |
#include <unistd.h> |
#include <unistd.h> |
#ifdef USE_WCHAR |
#if HAVE_WCHAR |
#include <wchar.h> |
#include <wchar.h> |
#endif |
#endif |
|
|
|
|
#include "mandoc_aux.h" |
#include "mandoc_aux.h" |
#include "out.h" |
#include "out.h" |
#include "term.h" |
#include "term.h" |
|
#include "manconf.h" |
#include "main.h" |
#include "main.h" |
|
|
/* |
static struct termp *ascii_init(enum termenc, const struct manoutput *); |
* Sadly, this doesn't seem to be defined on systems even when they |
static int ascii_hspan(const struct termp *, |
* support it. For the time being, remove it and let those compiling |
|
* the software decide for themselves what to use. |
|
*/ |
|
#if 0 |
|
#if ! defined(__STDC_ISO_10646__) |
|
# undef USE_WCHAR |
|
#endif |
|
#endif |
|
|
|
static struct termp *ascii_init(enum termenc, char *); |
|
static double ascii_hspan(const struct termp *, |
|
const struct roffsu *); |
const struct roffsu *); |
static size_t ascii_width(const struct termp *, int); |
static size_t ascii_width(const struct termp *, int); |
static void ascii_advance(struct termp *, size_t); |
static void ascii_advance(struct termp *, size_t); |
Line 56 static void ascii_begin(struct termp *); |
|
Line 49 static void ascii_begin(struct termp *); |
|
static void ascii_end(struct termp *); |
static void ascii_end(struct termp *); |
static void ascii_endline(struct termp *); |
static void ascii_endline(struct termp *); |
static void ascii_letter(struct termp *, int); |
static void ascii_letter(struct termp *, int); |
static void ascii_setwidth(struct termp *, int, size_t); |
static void ascii_setwidth(struct termp *, int, int); |
|
|
#ifdef USE_WCHAR |
#if HAVE_WCHAR |
static void locale_advance(struct termp *, size_t); |
static void locale_advance(struct termp *, size_t); |
static void locale_endline(struct termp *); |
static void locale_endline(struct termp *); |
static void locale_letter(struct termp *, int); |
static void locale_letter(struct termp *, int); |
Line 67 static size_t locale_width(const struct termp *, in |
|
Line 60 static size_t locale_width(const struct termp *, in |
|
|
|
|
|
static struct termp * |
static struct termp * |
ascii_init(enum termenc enc, char *outopts) |
ascii_init(enum termenc enc, const struct manoutput *outopts) |
{ |
{ |
const char *toks[4]; |
#if HAVE_WCHAR |
char *v; |
char *v; |
|
#endif |
struct termp *p; |
struct termp *p; |
|
|
p = mandoc_calloc(1, sizeof(struct termp)); |
p = mandoc_calloc(1, sizeof(*p)); |
|
p->tcol = p->tcols = mandoc_calloc(1, sizeof(*p->tcol)); |
|
p->maxtcol = 1; |
|
|
p->tabwidth = 5; |
p->line = 1; |
p->defrmargin = p->lastrmargin = 78; |
p->defrmargin = p->lastrmargin = 78; |
|
p->fontq = mandoc_reallocarray(NULL, |
|
(p->fontsz = 8), sizeof(*p->fontq)); |
|
p->fontq[0] = p->fontl = TERMFONT_NONE; |
|
|
p->begin = ascii_begin; |
p->begin = ascii_begin; |
p->end = ascii_end; |
p->end = ascii_end; |
Line 90 ascii_init(enum termenc enc, char *outopts) |
|
Line 89 ascii_init(enum termenc enc, char *outopts) |
|
p->setwidth = ascii_setwidth; |
p->setwidth = ascii_setwidth; |
p->width = ascii_width; |
p->width = ascii_width; |
|
|
#ifdef USE_WCHAR |
#if HAVE_WCHAR |
if (TERMENC_ASCII != enc) { |
if (TERMENC_ASCII != enc) { |
|
|
|
/* |
|
* 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 ? |
v = TERMENC_LOCALE == enc ? |
setlocale(LC_ALL, "") : |
setlocale(LC_CTYPE, "") : |
setlocale(LC_CTYPE, "en_US.UTF-8"); |
setlocale(LC_CTYPE, UTF8_LOCALE); |
if (NULL != v && MB_CUR_MAX > 1) { |
|
|
/* |
|
* We only support UTF-8, |
|
* so revert to ASCII for anything else. |
|
*/ |
|
|
|
if (v != NULL && |
|
strcmp(nl_langinfo(CODESET), "UTF-8") != 0) |
|
v = setlocale(LC_CTYPE, "C"); |
|
|
|
if (v != NULL && MB_CUR_MAX > 1) { |
p->enc = enc; |
p->enc = enc; |
p->advance = locale_advance; |
p->advance = locale_advance; |
p->endline = locale_endline; |
p->endline = locale_endline; |
Line 105 ascii_init(enum termenc enc, char *outopts) |
|
Line 122 ascii_init(enum termenc enc, char *outopts) |
|
} |
} |
#endif |
#endif |
|
|
toks[0] = "indent"; |
if (outopts->mdoc) { |
toks[1] = "width"; |
p->mdocstyle = 1; |
toks[2] = "mdoc"; |
p->defindent = 5; |
toks[3] = NULL; |
} |
|
if (outopts->indent) |
|
p->defindent = outopts->indent; |
|
if (outopts->width) |
|
p->defrmargin = outopts->width; |
|
if (outopts->synopsisonly) |
|
p->synopsisonly = 1; |
|
|
while (outopts && *outopts) |
assert(p->defindent < UINT16_MAX); |
switch (getsubopt(&outopts, UNCONST(toks), &v)) { |
assert(p->defrmargin < UINT16_MAX); |
case 0: |
return p; |
p->defindent = (size_t)atoi(v); |
|
break; |
|
case 1: |
|
p->defrmargin = (size_t)atoi(v); |
|
break; |
|
case 2: |
|
/* |
|
* Temporary, undocumented mode |
|
* to imitate mdoc(7) output style. |
|
*/ |
|
p->mdocstyle = 1; |
|
p->defindent = 5; |
|
break; |
|
default: |
|
break; |
|
} |
|
|
|
/* Enforce a lower boundary. */ |
|
if (p->defrmargin < 58) |
|
p->defrmargin = 58; |
|
|
|
return(p); |
|
} |
} |
|
|
void * |
void * |
ascii_alloc(char *outopts) |
ascii_alloc(const struct manoutput *outopts) |
{ |
{ |
|
|
return(ascii_init(TERMENC_ASCII, outopts)); |
return ascii_init(TERMENC_ASCII, outopts); |
} |
} |
|
|
void * |
void * |
utf8_alloc(char *outopts) |
utf8_alloc(const struct manoutput *outopts) |
{ |
{ |
|
|
return(ascii_init(TERMENC_UTF8, outopts)); |
return ascii_init(TERMENC_UTF8, outopts); |
} |
} |
|
|
void * |
void * |
locale_alloc(char *outopts) |
locale_alloc(const struct manoutput *outopts) |
{ |
{ |
|
|
return(ascii_init(TERMENC_LOCALE, outopts)); |
return ascii_init(TERMENC_LOCALE, outopts); |
} |
} |
|
|
static void |
static void |
ascii_setwidth(struct termp *p, int iop, size_t width) |
ascii_setwidth(struct termp *p, int iop, int width) |
{ |
{ |
|
|
p->rmargin = p->defrmargin; |
width /= 24; |
if (0 < iop) |
p->tcol->rmargin = p->defrmargin; |
|
if (iop > 0) |
p->defrmargin += width; |
p->defrmargin += width; |
else if (0 > iop) |
else if (iop == 0) |
|
p->defrmargin = width ? (size_t)width : p->lastrmargin; |
|
else if (p->defrmargin > (size_t)width) |
p->defrmargin -= width; |
p->defrmargin -= width; |
else |
else |
p->defrmargin = width ? width : p->lastrmargin; |
p->defrmargin = 0; |
p->lastrmargin = p->rmargin; |
if (p->defrmargin > 1000) |
p->rmargin = p->maxrmargin = p->defrmargin; |
p->defrmargin = 1000; |
|
p->lastrmargin = p->tcol->rmargin; |
|
p->tcol->rmargin = p->maxrmargin = p->defrmargin; |
} |
} |
|
|
|
void |
|
terminal_sepline(void *arg) |
|
{ |
|
struct termp *p; |
|
size_t i; |
|
|
|
p = (struct termp *)arg; |
|
(*p->endline)(p); |
|
for (i = 0; i < p->defrmargin; i++) |
|
(*p->letter)(p, '-'); |
|
(*p->endline)(p); |
|
(*p->endline)(p); |
|
} |
|
|
static size_t |
static size_t |
ascii_width(const struct termp *p, int c) |
ascii_width(const struct termp *p, int c) |
{ |
{ |
|
|
return(1); |
return 1; |
} |
} |
|
|
void |
void |
|
|
ascii_endline(struct termp *p) |
ascii_endline(struct termp *p) |
{ |
{ |
|
|
|
p->line++; |
|
p->tcol->offset -= p->ti; |
|
p->ti = 0; |
putchar('\n'); |
putchar('\n'); |
} |
} |
|
|
Line 220 ascii_advance(struct termp *p, size_t len) |
|
Line 243 ascii_advance(struct termp *p, size_t len) |
|
{ |
{ |
size_t i; |
size_t i; |
|
|
|
assert(len < UINT16_MAX); |
for (i = 0; i < len; i++) |
for (i = 0; i < len; i++) |
putchar(' '); |
putchar(' '); |
} |
} |
|
|
static double |
static int |
ascii_hspan(const struct termp *p, const struct roffsu *su) |
ascii_hspan(const struct termp *p, const struct roffsu *su) |
{ |
{ |
double r; |
double r; |
|
|
/* |
|
* Approximate based on character width. |
|
* None of these will be actually correct given that an inch on |
|
* the screen depends on character size, terminal, etc., etc. |
|
*/ |
|
switch (su->unit) { |
switch (su->unit) { |
case SCALE_BU: |
case SCALE_BU: |
r = su->scale * 10.0 / 240.0; |
r = su->scale; |
break; |
break; |
case SCALE_CM: |
case SCALE_CM: |
r = su->scale * 10.0 / 2.54; |
r = su->scale * 240.0 / 2.54; |
break; |
break; |
case SCALE_FS: |
case SCALE_FS: |
r = su->scale * 2730.666; |
r = su->scale * 65536.0; |
break; |
break; |
case SCALE_IN: |
case SCALE_IN: |
r = su->scale * 10.0; |
r = su->scale * 240.0; |
break; |
break; |
case SCALE_MM: |
case SCALE_MM: |
r = su->scale / 100.0; |
r = su->scale * 0.24; |
break; |
break; |
|
case SCALE_VS: |
case SCALE_PC: |
case SCALE_PC: |
r = su->scale * 10.0 / 6.0; |
r = su->scale * 40.0; |
break; |
break; |
case SCALE_PT: |
case SCALE_PT: |
r = su->scale * 10.0 / 72.0; |
r = su->scale * 10.0 / 3.0; |
break; |
break; |
case SCALE_VS: |
|
r = su->scale * 2.0 - 1.0; |
|
break; |
|
case SCALE_EN: |
case SCALE_EN: |
/* FALLTHROUGH */ |
|
case SCALE_EM: |
case SCALE_EM: |
r = su->scale; |
r = su->scale * 24.0; |
break; |
break; |
default: |
default: |
abort(); |
abort(); |
/* NOTREACHED */ |
|
} |
} |
|
return r > 0.0 ? r + 0.01 : r - 0.01; |
|
} |
|
|
return(r); |
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>", |
|
"<98>", "<99>", "<9A>", "<9B>", "<9C>", "<9D>", "<9E>", "<9F>", |
|
nbrsp, "!", "/\bc", "GBP", "o\bx", "=\bY", "|", "<section>", |
|
"\"", "(C)", "_\ba", "<<", "~", "", "(R)", "-", |
|
"<degree>","+-","^2", "^3", "'","<micro>","<paragraph>",".", |
|
",", "^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", |
|
"Dh", "~\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", |
|
"dh", "~\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])) |
|
return tab[uc]; |
|
return mchars_uc2str(uc); |
} |
} |
|
|
#ifdef USE_WCHAR |
#if HAVE_WCHAR |
static size_t |
static size_t |
locale_width(const struct termp *p, int c) |
locale_width(const struct termp *p, int c) |
{ |
{ |
Line 283 locale_width(const struct termp *p, int c) |
|
Line 373 locale_width(const struct termp *p, int c) |
|
rc = wcwidth(c); |
rc = wcwidth(c); |
if (rc < 0) |
if (rc < 0) |
rc = 0; |
rc = 0; |
return(rc); |
return rc; |
} |
} |
|
|
static void |
static void |
Line 291 locale_advance(struct termp *p, size_t len) |
|
Line 381 locale_advance(struct termp *p, size_t len) |
|
{ |
{ |
size_t i; |
size_t i; |
|
|
|
assert(len < UINT16_MAX); |
for (i = 0; i < len; i++) |
for (i = 0; i < len; i++) |
putwchar(L' '); |
putwchar(L' '); |
} |
} |
|
|
locale_endline(struct termp *p) |
locale_endline(struct termp *p) |
{ |
{ |
|
|
|
p->line++; |
|
p->tcol->offset -= p->ti; |
|
p->ti = 0; |
putwchar(L'\n'); |
putwchar(L'\n'); |
} |
} |
|
|