version 1.163, 2010/07/21 20:35:03 |
version 1.186, 2011/04/30 22:24:31 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org> |
* Copyright (c) 2010, 2011 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 |
|
|
#include <string.h> |
#include <string.h> |
|
|
#include "mandoc.h" |
#include "mandoc.h" |
#include "chars.h" |
|
#include "out.h" |
#include "out.h" |
#include "term.h" |
#include "term.h" |
#include "main.h" |
#include "main.h" |
|
|
static void spec(struct termp *, enum roffdeco, |
static void spec(struct termp *, const char *, size_t); |
const char *, size_t); |
|
static void res(struct termp *, const char *, size_t); |
static void res(struct termp *, const char *, size_t); |
static void buffera(struct termp *, const char *, size_t); |
|
static void bufferc(struct termp *, char); |
static void bufferc(struct termp *, char); |
static void adjbuf(struct termp *p, size_t); |
static void adjbuf(struct termp *p, size_t); |
static void encode(struct termp *, const char *, size_t); |
static void encode(struct termp *, const char *, size_t); |
Line 50 term_free(struct termp *p) |
|
Line 47 term_free(struct termp *p) |
|
if (p->buf) |
if (p->buf) |
free(p->buf); |
free(p->buf); |
if (p->symtab) |
if (p->symtab) |
chars_free(p->symtab); |
mchars_free(p->symtab); |
|
|
free(p); |
free(p); |
} |
} |
Line 81 term_alloc(enum termenc enc) |
|
Line 78 term_alloc(enum termenc enc) |
|
{ |
{ |
struct termp *p; |
struct termp *p; |
|
|
p = calloc(1, sizeof(struct termp)); |
p = mandoc_calloc(1, sizeof(struct termp)); |
if (NULL == p) { |
|
perror(NULL); |
|
exit(EXIT_FAILURE); |
|
} |
|
|
|
p->enc = enc; |
p->enc = enc; |
return(p); |
return(p); |
} |
} |
Line 135 term_flushln(struct termp *p) |
|
Line 127 term_flushln(struct termp *p) |
|
size_t vbl; /* number of blanks to prepend to output */ |
size_t vbl; /* number of blanks to prepend to output */ |
size_t vend; /* end of word visual position on output */ |
size_t vend; /* end of word visual position on output */ |
size_t bp; /* visual right border position */ |
size_t bp; /* visual right border position */ |
|
size_t dv; /* temporary for visual pos calculations */ |
int j; /* temporary loop index for p->buf */ |
int j; /* temporary loop index for p->buf */ |
int jhy; /* last hyph before overflow w/r/t j */ |
int jhy; /* last hyph before overflow w/r/t j */ |
size_t maxvis; /* output position of visible boundary */ |
size_t maxvis; /* output position of visible boundary */ |
Line 146 term_flushln(struct termp *p) |
|
Line 139 term_flushln(struct termp *p) |
|
* an indentation, but can be, for tagged lists or columns, a |
* an indentation, but can be, for tagged lists or columns, a |
* small set of values. |
* small set of values. |
*/ |
*/ |
|
assert (p->rmargin >= p->offset); |
|
dv = p->rmargin - p->offset; |
|
maxvis = (int)dv > p->overstep ? dv - (size_t)p->overstep : 0; |
|
dv = p->maxrmargin - p->offset; |
|
mmax = (int)dv > p->overstep ? dv - (size_t)p->overstep : 0; |
|
|
assert(p->offset < p->rmargin); |
|
|
|
maxvis = (int)(p->rmargin - p->offset) - p->overstep < 0 ? |
|
/* LINTED */ |
|
0 : p->rmargin - p->offset - p->overstep; |
|
mmax = (int)(p->maxrmargin - p->offset) - p->overstep < 0 ? |
|
/* LINTED */ |
|
0 : p->maxrmargin - p->offset - p->overstep; |
|
|
|
bp = TERMP_NOBREAK & p->flags ? mmax : maxvis; |
bp = TERMP_NOBREAK & p->flags ? mmax : maxvis; |
|
|
/* |
/* |
* Indent the first line of a paragraph. |
* Indent the first line of a paragraph. |
*/ |
*/ |
vbl = p->flags & TERMP_NOLPAD ? 0 : p->offset; |
vbl = p->flags & TERMP_NOLPAD ? (size_t)0 : p->offset; |
|
|
vis = vend = i = 0; |
vis = vend = 0; |
|
i = 0; |
|
|
while (i < (int)p->col) { |
while (i < (int)p->col) { |
/* |
/* |
* Handle literal tab characters: collapse all |
* Handle literal tab characters: collapse all |
* subsequent tabs into a single huge set of spaces. |
* subsequent tabs into a single huge set of spaces. |
*/ |
*/ |
for (j = i; j < (int)p->col; j++) { |
while (i < (int)p->col && '\t' == p->buf[i]) { |
if ('\t' != p->buf[j]) |
|
break; |
|
vend = (vis / p->tabwidth + 1) * p->tabwidth; |
vend = (vis / p->tabwidth + 1) * p->tabwidth; |
vbl += vend - vis; |
vbl += vend - vis; |
vis = vend; |
vis = vend; |
|
i++; |
} |
} |
|
|
/* |
/* |
Line 185 term_flushln(struct termp *p) |
|
Line 174 term_flushln(struct termp *p) |
|
* space is printed according to regular spacing rules). |
* space is printed according to regular spacing rules). |
*/ |
*/ |
|
|
/* LINTED */ |
for (j = i, jhy = 0; j < (int)p->col; j++) { |
for (jhy = 0; j < (int)p->col; j++) { |
|
if ((j && ' ' == p->buf[j]) || '\t' == p->buf[j]) |
if ((j && ' ' == p->buf[j]) || '\t' == p->buf[j]) |
break; |
break; |
|
|
Line 224 term_flushln(struct termp *p) |
|
Line 212 term_flushln(struct termp *p) |
|
|
|
/* Remove the p->overstep width. */ |
/* Remove the p->overstep width. */ |
|
|
bp += (int)/* LINTED */ |
bp += (size_t)p->overstep; |
p->overstep; |
|
p->overstep = 0; |
p->overstep = 0; |
} |
} |
|
|
/* |
|
* Skip leading tabs, they were handled above. |
|
*/ |
|
while (i < (int)p->col && '\t' == p->buf[i]) |
|
i++; |
|
|
|
/* Write out the [remaining] word. */ |
/* Write out the [remaining] word. */ |
for ( ; i < (int)p->col; i++) { |
for ( ; i < (int)p->col; i++) { |
if (vend > bp && jhy > 0 && i > jhy) |
if (vend > bp && jhy > 0 && i > jhy) |
Line 242 term_flushln(struct termp *p) |
|
Line 223 term_flushln(struct termp *p) |
|
if ('\t' == p->buf[i]) |
if ('\t' == p->buf[i]) |
break; |
break; |
if (' ' == p->buf[i]) { |
if (' ' == p->buf[i]) { |
while (' ' == p->buf[i]) { |
j = i; |
vbl += (*p->width)(p, p->buf[i]); |
while (' ' == p->buf[i]) |
i++; |
i++; |
} |
dv = (size_t)(i - j) * (*p->width)(p, ' '); |
|
vbl += dv; |
|
vend += dv; |
break; |
break; |
} |
} |
if (ASCII_NBRSP == p->buf[i]) { |
if (ASCII_NBRSP == p->buf[i]) { |
Line 272 term_flushln(struct termp *p) |
|
Line 255 term_flushln(struct termp *p) |
|
p->viscol += (*p->width)(p, p->buf[i]); |
p->viscol += (*p->width)(p, p->buf[i]); |
} |
} |
} |
} |
vend += vbl; |
|
vis = vend; |
vis = vend; |
} |
} |
|
|
|
/* |
|
* If there was trailing white space, it was not printed; |
|
* so reset the cursor position accordingly. |
|
*/ |
|
vis -= vbl; |
|
|
p->col = 0; |
p->col = 0; |
p->overstep = 0; |
p->overstep = 0; |
|
|
Line 287 term_flushln(struct termp *p) |
|
Line 275 term_flushln(struct termp *p) |
|
|
|
if (TERMP_HANG & p->flags) { |
if (TERMP_HANG & p->flags) { |
/* We need one blank after the tag. */ |
/* We need one blank after the tag. */ |
p->overstep = /* LINTED */ |
p->overstep = (int)(vis - maxvis + (*p->width)(p, ' ')); |
vis - maxvis + (*p->width)(p, ' '); |
|
|
|
/* |
/* |
* Behave exactly the same way as groff: |
* Behave exactly the same way as groff: |
Line 302 term_flushln(struct termp *p) |
|
Line 289 term_flushln(struct termp *p) |
|
*/ |
*/ |
if (p->overstep >= -1) { |
if (p->overstep >= -1) { |
assert((int)maxvis + p->overstep >= 0); |
assert((int)maxvis + p->overstep >= 0); |
/* LINTED */ |
maxvis += (size_t)p->overstep; |
maxvis += p->overstep; |
|
} else |
} else |
p->overstep = 0; |
p->overstep = 0; |
|
|
Line 311 term_flushln(struct termp *p) |
|
Line 297 term_flushln(struct termp *p) |
|
return; |
return; |
|
|
/* Right-pad. */ |
/* Right-pad. */ |
if (maxvis > vis + /* LINTED */ |
if (maxvis > vis + |
((TERMP_TWOSPACE & p->flags) ? |
((TERMP_TWOSPACE & p->flags) ? (*p->width)(p, ' ') : 0)) { |
(*p->width)(p, ' ') : 0)) { |
|
p->viscol += maxvis - vis; |
p->viscol += maxvis - vis; |
(*p->advance)(p, maxvis - vis); |
(*p->advance)(p, maxvis - vis); |
vis += (maxvis - vis); |
vis += (maxvis - vis); |
Line 361 term_vspace(struct termp *p) |
|
Line 346 term_vspace(struct termp *p) |
|
|
|
|
|
static void |
static void |
spec(struct termp *p, enum roffdeco d, const char *word, size_t len) |
numbered(struct termp *p, const char *word, size_t len) |
{ |
{ |
|
char c; |
|
|
|
if ('\0' != (c = mchars_num2char(word, len))) |
|
encode(p, &c, 1); |
|
} |
|
|
|
|
|
static void |
|
spec(struct termp *p, const char *word, size_t len) |
|
{ |
const char *rhs; |
const char *rhs; |
size_t sz; |
size_t sz; |
|
|
rhs = chars_spec2str(p->symtab, word, len, &sz); |
rhs = mchars_spec2str(p->symtab, word, len, &sz); |
if (rhs) |
if (rhs) |
encode(p, rhs, sz); |
encode(p, rhs, sz); |
else if (DECO_SSPECIAL == d) |
else if (1 == len) |
encode(p, word, len); |
encode(p, word, len); |
} |
} |
|
|
Line 380 res(struct termp *p, const char *word, size_t len) |
|
Line 375 res(struct termp *p, const char *word, size_t len) |
|
const char *rhs; |
const char *rhs; |
size_t sz; |
size_t sz; |
|
|
rhs = chars_res2str(p->symtab, word, len, &sz); |
rhs = mchars_res2str(p->symtab, word, len, &sz); |
if (rhs) |
if (rhs) |
encode(p, rhs, sz); |
encode(p, rhs, sz); |
} |
} |
Line 459 term_fontpop(struct termp *p) |
|
Line 454 term_fontpop(struct termp *p) |
|
void |
void |
term_word(struct termp *p, const char *word) |
term_word(struct termp *p, const char *word) |
{ |
{ |
const char *sv, *seq; |
const char *seq; |
int sz; |
int sz; |
size_t ssz; |
size_t ssz; |
enum roffdeco deco; |
enum mandoc_esc esc; |
|
|
sv = word; |
|
|
|
if (word[0] && '\0' == word[1]) |
|
switch (word[0]) { |
|
case('.'): |
|
/* FALLTHROUGH */ |
|
case(','): |
|
/* FALLTHROUGH */ |
|
case(';'): |
|
/* FALLTHROUGH */ |
|
case(':'): |
|
/* FALLTHROUGH */ |
|
case('?'): |
|
/* FALLTHROUGH */ |
|
case('!'): |
|
/* FALLTHROUGH */ |
|
case(')'): |
|
/* FALLTHROUGH */ |
|
case(']'): |
|
if ( ! (TERMP_IGNDELIM & p->flags)) |
|
p->flags |= TERMP_NOSPACE; |
|
break; |
|
default: |
|
break; |
|
} |
|
|
|
if ( ! (TERMP_NOSPACE & p->flags)) { |
if ( ! (TERMP_NOSPACE & p->flags)) { |
if ( ! (TERMP_KEEP & p->flags)) { |
if ( ! (TERMP_KEEP & p->flags)) { |
if (TERMP_PREKEEP & p->flags) |
if (TERMP_PREKEEP & p->flags) |
Line 503 term_word(struct termp *p, const char *word) |
|
Line 472 term_word(struct termp *p, const char *word) |
|
|
|
if ( ! (p->flags & TERMP_NONOSPACE)) |
if ( ! (p->flags & TERMP_NONOSPACE)) |
p->flags &= ~TERMP_NOSPACE; |
p->flags &= ~TERMP_NOSPACE; |
|
else |
|
p->flags |= TERMP_NOSPACE; |
|
|
p->flags &= ~TERMP_SENTENCE; |
p->flags &= ~(TERMP_SENTENCE | TERMP_IGNDELIM); |
|
|
while (*word) { |
while ('\0' != *word) { |
if ((ssz = strcspn(word, "\\")) > 0) |
if ((ssz = strcspn(word, "\\")) > 0) |
encode(p, word, ssz); |
encode(p, word, ssz); |
|
|
word += ssz; |
word += (int)ssz; |
if ('\\' != *word) |
if ('\\' != *word) |
continue; |
continue; |
|
|
seq = ++word; |
word++; |
sz = a2roffdeco(&deco, &seq, &ssz); |
esc = mandoc_escape(&word, &seq, &sz); |
|
if (ESCAPE_ERROR == esc) |
|
break; |
|
|
switch (deco) { |
switch (esc) { |
case (DECO_RESERVED): |
case (ESCAPE_NUMBERED): |
res(p, seq, ssz); |
numbered(p, seq, sz); |
break; |
break; |
case (DECO_SPECIAL): |
case (ESCAPE_PREDEF): |
/* FALLTHROUGH */ |
res(p, seq, sz); |
case (DECO_SSPECIAL): |
|
spec(p, deco, seq, ssz); |
|
break; |
break; |
case (DECO_BOLD): |
case (ESCAPE_SPECIAL): |
|
spec(p, seq, sz); |
|
break; |
|
case (ESCAPE_FONTBOLD): |
term_fontrepl(p, TERMFONT_BOLD); |
term_fontrepl(p, TERMFONT_BOLD); |
break; |
break; |
case (DECO_ITALIC): |
case (ESCAPE_FONTITALIC): |
term_fontrepl(p, TERMFONT_UNDER); |
term_fontrepl(p, TERMFONT_UNDER); |
break; |
break; |
case (DECO_ROMAN): |
case (ESCAPE_FONTROMAN): |
term_fontrepl(p, TERMFONT_NONE); |
term_fontrepl(p, TERMFONT_NONE); |
break; |
break; |
case (DECO_PREVIOUS): |
case (ESCAPE_FONTPREV): |
term_fontlast(p); |
term_fontlast(p); |
break; |
break; |
default: |
case (ESCAPE_NOSPACE): |
|
if ('\0' == *word) |
|
p->flags |= TERMP_NOSPACE; |
break; |
break; |
} |
|
|
|
word += sz; |
|
if (DECO_NOSPACE == deco && '\0' == *word) |
|
p->flags |= TERMP_NOSPACE; |
|
} |
|
|
|
/* |
|
* Note that we don't process the pipe: the parser sees it as |
|
* punctuation, but we don't in terms of typography. |
|
*/ |
|
if (sv[0] && '\0' == sv[1]) |
|
switch (sv[0]) { |
|
case('('): |
|
/* FALLTHROUGH */ |
|
case('['): |
|
p->flags |= TERMP_NOSPACE; |
|
break; |
|
default: |
default: |
break; |
break; |
} |
} |
|
} |
} |
} |
|
|
|
|
Line 573 adjbuf(struct termp *p, size_t sz) |
|
Line 532 adjbuf(struct termp *p, size_t sz) |
|
while (sz >= p->maxcols) |
while (sz >= p->maxcols) |
p->maxcols <<= 2; |
p->maxcols <<= 2; |
|
|
p->buf = realloc(p->buf, p->maxcols); |
p->buf = mandoc_realloc(p->buf, p->maxcols); |
if (NULL == p->buf) { |
|
perror(NULL); |
|
exit(EXIT_FAILURE); |
|
} |
|
} |
} |
|
|
|
|
static void |
static void |
buffera(struct termp *p, const char *word, size_t sz) |
|
{ |
|
|
|
if (p->col + sz >= p->maxcols) |
|
adjbuf(p, p->col + sz); |
|
|
|
memcpy(&p->buf[(int)p->col], word, sz); |
|
p->col += sz; |
|
} |
|
|
|
|
|
static void |
|
bufferc(struct termp *p, char c) |
bufferc(struct termp *p, char c) |
{ |
{ |
|
|
Line 617 encode(struct termp *p, const char *word, size_t sz) |
|
Line 560 encode(struct termp *p, const char *word, size_t sz) |
|
*/ |
*/ |
|
|
if (TERMFONT_NONE == (f = term_fonttop(p))) { |
if (TERMFONT_NONE == (f = term_fonttop(p))) { |
buffera(p, word, sz); |
if (p->col + sz >= p->maxcols) |
|
adjbuf(p, p->col + sz); |
|
memcpy(&p->buf[(int)p->col], word, sz); |
|
p->col += sz; |
return; |
return; |
} |
} |
|
|
|
/* Pre-buffer, assuming worst-case. */ |
|
|
|
if (p->col + 1 + (sz * 3) >= p->maxcols) |
|
adjbuf(p, p->col + 1 + (sz * 3)); |
|
|
for (i = 0; i < (int)sz; i++) { |
for (i = 0; i < (int)sz; i++) { |
if ( ! isgraph((u_char)word[i])) { |
if ( ! isgraph((u_char)word[i])) { |
bufferc(p, word[i]); |
p->buf[(int)p->col++] = word[i]; |
continue; |
continue; |
} |
} |
|
|
if (TERMFONT_UNDER == f) |
if (TERMFONT_UNDER == f) |
bufferc(p, '_'); |
p->buf[(int)p->col++] = '_'; |
else |
else |
bufferc(p, word[i]); |
p->buf[(int)p->col++] = word[i]; |
|
|
bufferc(p, 8); |
p->buf[(int)p->col++] = 8; |
bufferc(p, word[i]); |
p->buf[(int)p->col++] = word[i]; |
} |
} |
} |
} |
|
|
Line 649 term_len(const struct termp *p, size_t sz) |
|
Line 600 term_len(const struct termp *p, size_t sz) |
|
size_t |
size_t |
term_strlen(const struct termp *p, const char *cp) |
term_strlen(const struct termp *p, const char *cp) |
{ |
{ |
size_t sz; |
size_t sz, rsz, i; |
|
int ssz; |
|
enum mandoc_esc esc; |
|
const char *seq, *rhs; |
|
|
for (sz = 0; *cp; cp++) |
/* |
sz += (*p->width)(p, *cp); |
* Account for escaped sequences within string length |
|
* calculations. This follows the logic in term_word() as we |
|
* must calculate the width of produced strings. |
|
*/ |
|
|
|
sz = 0; |
|
while ('\0' != *cp) |
|
switch (*cp) { |
|
case ('\\'): |
|
++cp; |
|
esc = mandoc_escape(&cp, &seq, &ssz); |
|
if (ESCAPE_ERROR == esc) |
|
return(sz); |
|
|
|
switch (esc) { |
|
case (ESCAPE_PREDEF): |
|
rhs = mchars_res2str |
|
(p->symtab, seq, ssz, &rsz); |
|
break; |
|
case (ESCAPE_SPECIAL): |
|
rhs = mchars_spec2str |
|
(p->symtab, seq, ssz, &rsz); |
|
|
|
if (ssz != 1 || rhs) |
|
break; |
|
|
|
rhs = seq; |
|
rsz = ssz; |
|
break; |
|
default: |
|
rhs = NULL; |
|
break; |
|
} |
|
|
|
if (NULL == rhs) |
|
break; |
|
|
|
for (i = 0; i < rsz; i++) |
|
sz += (*p->width)(p, *rhs++); |
|
break; |
|
case (ASCII_NBRSP): |
|
sz += (*p->width)(p, ' '); |
|
cp++; |
|
break; |
|
case (ASCII_HYPH): |
|
sz += (*p->width)(p, '-'); |
|
cp++; |
|
break; |
|
default: |
|
sz += (*p->width)(p, *cp++); |
|
break; |
|
} |
|
|
return(sz); |
return(sz); |
} |
} |