-/* $Id: term.c,v 1.149 2010/06/25 18:53:14 kristaps Exp $ */
+/* $Id: term.c,v 1.204 2012/07/10 15:35:41 schwarze Exp $ */
/*
- * Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@bsd.lv>
+ * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
+ * Copyright (c) 2010, 2011, 2012 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
#include <string.h>
#include "mandoc.h"
-#include "chars.h"
#include "out.h"
#include "term.h"
-#include "man.h"
-#include "mdoc.h"
#include "main.h"
-static void spec(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 adjbuf(struct termp *p, size_t);
-static void encode(struct termp *, const char *, size_t);
-
+static size_t cond_width(const struct termp *, int, int *);
+static void adjbuf(struct termp *p, int);
+static void bufferc(struct termp *, char);
+static void encode(struct termp *, const char *, size_t);
+static void encode1(struct termp *, int);
void
term_free(struct termp *p)
if (p->buf)
free(p->buf);
if (p->symtab)
- chars_free(p->symtab);
+ mchars_free(p->symtab);
free(p);
}
(*p->end)(p);
}
-
-struct termp *
-term_alloc(enum termenc enc)
-{
- struct termp *p;
-
- p = calloc(1, sizeof(struct termp));
- if (NULL == p) {
- perror(NULL);
- exit(EXIT_FAILURE);
- }
-
- p->enc = enc;
- return(p);
-}
-
-
/*
* Flush a line of text. A "line" is loosely defined as being something
* that should be followed by a newline, regardless of whether it's
*
* The following flags may be specified:
*
- * - TERMP_NOLPAD: when beginning to write the line, don't left-pad the
- * offset value. This is useful when doing columnar lists where the
- * prior column has right-padded.
- *
* - TERMP_NOBREAK: this is the most important and is used when making
- * columns. In short: don't print a newline and instead pad to the
- * right margin. Used in conjunction with TERMP_NOLPAD.
+ * columns. In short: don't print a newline and instead expect the
+ * next call to do the padding up to the start of the next column.
*
- * - TERMP_TWOSPACE: when padding, make sure there are at least two
- * space characters of padding. Otherwise, rather break the line.
+ * - TERMP_TWOSPACE: make sure there is room for at least two space
+ * characters of padding. Otherwise, rather break the line.
*
* - TERMP_DANGLE: don't newline when TERMP_NOBREAK is specified and
* the line is overrun, and don't pad-right if it's underrun.
*
* - TERMP_HANG: like TERMP_DANGLE, but doesn't newline when
- * overruning, instead save the position and continue at that point
+ * overrunning, instead save the position and continue at that point
* when the next invocation.
*
* In-line line breaking:
size_t vbl; /* number of blanks to prepend to output */
size_t vend; /* end of word visual position on output */
size_t bp; /* visual right border position */
- int j; /* temporary loop index */
- int jhy; /* last hyphen before line overflow */
- size_t maxvis, mmax;
+ size_t dv; /* temporary for visual pos calculations */
+ int j; /* temporary loop index for p->buf */
+ int jhy; /* last hyph before overflow w/r/t j */
+ size_t maxvis; /* output position of visible boundary */
+ size_t mmax; /* used in calculating bp */
/*
* First, establish the maximum columns of "visible" content.
* an indentation, but can be, for tagged lists or columns, a
* small set of values.
*/
-
- 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;
+ 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;
bp = TERMP_NOBREAK & p->flags ? mmax : maxvis;
/*
- * Indent the first line of a paragraph.
- */
- vbl = p->flags & TERMP_NOLPAD ? 0 : p->offset;
-
- /*
- * FIXME: if bp is zero, we still output the first word before
- * breaking the line.
+ * Calculate the required amount of padding.
*/
+ vbl = p->offset + p->overstep > p->viscol ?
+ p->offset + p->overstep - p->viscol : 0;
- vis = vend = i = 0;
- while (i < (int)p->col) {
+ vis = vend = 0;
+ i = 0;
+ while (i < p->col) {
/*
- * Handle literal tab characters.
+ * Handle literal tab characters: collapse all
+ * subsequent tabs into a single huge set of spaces.
*/
- for (j = i; j < (int)p->col; j++) {
- if ('\t' != p->buf[j])
- break;
- vend = (vis/p->tabwidth+1)*p->tabwidth;
+ while (i < p->col && '\t' == p->buf[i]) {
+ vend = (vis / p->tabwidth + 1) * p->tabwidth;
vbl += vend - vis;
vis = vend;
+ i++;
}
/*
* space is printed according to regular spacing rules).
*/
- /* LINTED */
- for (jhy = 0; j < (int)p->col; j++) {
+ for (j = i, jhy = 0; j < p->col; j++) {
if ((j && ' ' == p->buf[j]) || '\t' == p->buf[j])
break;
- if (8 != p->buf[j]) {
- if (vend > vis && vend < bp &&
- ASCII_HYPH == p->buf[j])
- jhy = j;
- vend++;
- } else
- vend--;
+
+ /* Back over the the last printed character. */
+ if (8 == p->buf[j]) {
+ assert(j);
+ vend -= (*p->width)(p, p->buf[j - 1]);
+ continue;
+ }
+
+ /* Regular word. */
+ /* Break at the hyphen point if we overrun. */
+ if (vend > vis && vend < bp &&
+ ASCII_HYPH == p->buf[j])
+ jhy = j;
+
+ vend += (*p->width)(p, p->buf[j]);
}
/*
if (vend > bp && 0 == jhy && vis > 0) {
vend -= vis;
(*p->endline)(p);
+ p->viscol = 0;
if (TERMP_NOBREAK & p->flags) {
- p->viscol = p->rmargin;
- (*p->advance)(p, p->rmargin);
+ vbl = p->rmargin;
vend += p->rmargin - p->offset;
- } else {
- p->viscol = 0;
+ } else
vbl = p->offset;
- }
/* Remove the p->overstep width. */
- bp += (int)/* LINTED */
- p->overstep;
+ bp += (size_t)p->overstep;
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. */
- for ( ; i < (int)p->col; i++) {
+ for ( ; i < p->col; i++) {
if (vend > bp && jhy > 0 && i > jhy)
break;
if ('\t' == p->buf[i])
break;
if (' ' == p->buf[i]) {
- while (' ' == p->buf[i]) {
- vbl++;
+ j = i;
+ while (' ' == p->buf[i])
i++;
- }
+ dv = (size_t)(i - j) * (*p->width)(p, ' ');
+ vbl += dv;
+ vend += dv;
break;
}
if (ASCII_NBRSP == p->buf[i]) {
- vbl++;
+ vbl += (*p->width)(p, ' ');
continue;
}
vbl = 0;
}
- if (ASCII_HYPH == p->buf[i])
+ if (ASCII_HYPH == p->buf[i]) {
(*p->letter)(p, '-');
- else
- (*p->letter)(p, p->buf[i]);
+ p->viscol += (*p->width)(p, '-');
+ continue;
+ }
- p->viscol += 1;
+ (*p->letter)(p, p->buf[i]);
+ if (8 == p->buf[i])
+ p->viscol -= (*p->width)(p, p->buf[i-1]);
+ else
+ p->viscol += (*p->width)(p, p->buf[i]);
}
- vend += vbl;
vis = vend;
}
+ /*
+ * If there was trailing white space, it was not printed;
+ * so reset the cursor position accordingly.
+ */
+ if (vis)
+ vis -= vbl;
+
p->col = 0;
p->overstep = 0;
if (TERMP_HANG & p->flags) {
/* We need one blank after the tag. */
- p->overstep = /* LINTED */
- vis - maxvis + 1;
+ p->overstep = (int)(vis - maxvis + (*p->width)(p, ' '));
/*
- * Behave exactly the same way as groff:
* If we have overstepped the margin, temporarily move
* it to the right and flag the rest of the line to be
* shorter.
- * If we landed right at the margin, be happy.
- * If we are one step before the margin, temporarily
- * move it one step LEFT and flag the rest of the line
- * to be longer.
*/
- if (p->overstep >= -1) {
- assert((int)maxvis + p->overstep >= 0);
- /* LINTED */
- maxvis += p->overstep;
- } else
+ if (p->overstep < 0)
p->overstep = 0;
+ return;
} else if (TERMP_DANGLE & p->flags)
return;
- /* Right-pad. */
- if (maxvis > vis + /* LINTED */
- ((TERMP_TWOSPACE & p->flags) ? 1 : 0)) {
- p->viscol += maxvis - vis;
- (*p->advance)(p, maxvis - vis);
- vis += (maxvis - vis);
- } else { /* ...or newline break. */
+ /* If the column was overrun, break the line. */
+ if (maxvis <= vis +
+ ((TERMP_TWOSPACE & p->flags) ? (*p->width)(p, ' ') : 0)) {
(*p->endline)(p);
- p->viscol = p->rmargin;
- (*p->advance)(p, p->rmargin);
+ p->viscol = 0;
}
}
{
p->flags |= TERMP_NOSPACE;
- if (0 == p->col && 0 == p->viscol) {
- p->flags &= ~TERMP_NOLPAD;
- return;
- }
- term_flushln(p);
- p->flags &= ~TERMP_NOLPAD;
+ if (p->col || p->viscol)
+ term_flushln(p);
}
term_newln(p);
p->viscol = 0;
- (*p->endline)(p);
-}
-
-
-static void
-spec(struct termp *p, const char *word, size_t len)
-{
- const char *rhs;
- size_t sz;
-
- rhs = chars_a2ascii(p->symtab, word, len, &sz);
- if (rhs)
- encode(p, rhs, sz);
-}
-
-
-static void
-res(struct termp *p, const char *word, size_t len)
-{
- const char *rhs;
- size_t sz;
-
- rhs = chars_a2res(p->symtab, word, len, &sz);
- if (rhs)
- encode(p, rhs, sz);
+ if (0 < p->skipvsp)
+ p->skipvsp--;
+ else
+ (*p->endline)(p);
}
-
void
term_fontlast(struct termp *p)
{
p->fonti--;
}
-
/*
* Handle pwords, partial words, which may be either a single word or a
* phrase that cannot be broken down (such as a literal string). This
void
term_word(struct termp *p, const char *word)
{
- const char *sv, *seq;
- int sz;
+ const char *seq, *cp;
+ char c;
+ int sz, uc;
size_t ssz;
- enum roffdeco deco;
-
- 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;
- }
+ enum mandoc_esc esc;
if ( ! (TERMP_NOSPACE & p->flags)) {
- bufferc(p, ' ');
- if (TERMP_SENTENCE & p->flags)
+ if ( ! (TERMP_KEEP & p->flags)) {
+ if (TERMP_PREKEEP & p->flags)
+ p->flags |= TERMP_KEEP;
bufferc(p, ' ');
+ if (TERMP_SENTENCE & p->flags)
+ bufferc(p, ' ');
+ } else
+ bufferc(p, ASCII_NBRSP);
}
if ( ! (p->flags & TERMP_NONOSPACE))
p->flags &= ~TERMP_NOSPACE;
+ else
+ p->flags |= TERMP_NOSPACE;
- p->flags &= ~TERMP_SENTENCE;
+ p->flags &= ~(TERMP_SENTENCE | TERMP_IGNDELIM);
- /* FIXME: use strcspn. */
-
- while (*word) {
+ while ('\0' != *word) {
if ('\\' != *word) {
- encode(p, word, 1);
- word++;
+ if (TERMP_SKIPCHAR & p->flags) {
+ p->flags &= ~TERMP_SKIPCHAR;
+ word++;
+ continue;
+ }
+ ssz = strcspn(word, "\\");
+ encode(p, word, ssz);
+ word += (int)ssz;
continue;
}
- seq = ++word;
- sz = a2roffdeco(&deco, &seq, &ssz);
+ word++;
+ esc = mandoc_escape(&word, &seq, &sz);
+ if (ESCAPE_ERROR == esc)
+ break;
- switch (deco) {
- case (DECO_RESERVED):
- res(p, seq, ssz);
+ if (TERMENC_ASCII != p->enc)
+ switch (esc) {
+ case (ESCAPE_UNICODE):
+ uc = mchars_num2uc(seq + 1, sz - 1);
+ if ('\0' == uc)
+ break;
+ encode1(p, uc);
+ continue;
+ case (ESCAPE_SPECIAL):
+ uc = mchars_spec2cp(p->symtab, seq, sz);
+ if (uc <= 0)
+ break;
+ encode1(p, uc);
+ continue;
+ default:
+ break;
+ }
+
+ switch (esc) {
+ case (ESCAPE_UNICODE):
+ encode1(p, '?');
+ break;
+ case (ESCAPE_NUMBERED):
+ c = mchars_num2char(seq, sz);
+ if ('\0' != c)
+ encode(p, &c, 1);
break;
- case (DECO_SPECIAL):
- spec(p, seq, ssz);
+ case (ESCAPE_SPECIAL):
+ cp = mchars_spec2str(p->symtab, seq, sz, &ssz);
+ if (NULL != cp)
+ encode(p, cp, ssz);
+ else if (1 == ssz)
+ encode(p, seq, sz);
break;
- case (DECO_BOLD):
+ case (ESCAPE_FONTBOLD):
term_fontrepl(p, TERMFONT_BOLD);
break;
- case (DECO_ITALIC):
+ case (ESCAPE_FONTITALIC):
term_fontrepl(p, TERMFONT_UNDER);
break;
- case (DECO_ROMAN):
+ case (ESCAPE_FONT):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTROMAN):
term_fontrepl(p, TERMFONT_NONE);
break;
- case (DECO_PREVIOUS):
+ case (ESCAPE_FONTPREV):
term_fontlast(p);
break;
- default:
+ case (ESCAPE_NOSPACE):
+ if (TERMP_SKIPCHAR & p->flags)
+ p->flags &= ~TERMP_SKIPCHAR;
+ else if ('\0' == *word)
+ p->flags |= TERMP_NOSPACE;
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;
+ case (ESCAPE_SKIPCHAR):
+ p->flags |= TERMP_SKIPCHAR;
break;
default:
break;
}
+ }
}
-
static void
-adjbuf(struct termp *p, size_t sz)
+adjbuf(struct termp *p, int sz)
{
if (0 == p->maxcols)
while (sz >= p->maxcols)
p->maxcols <<= 2;
- p->buf = realloc(p->buf, p->maxcols);
- if (NULL == p->buf) {
- perror(NULL);
- exit(EXIT_FAILURE);
- }
+ p->buf = mandoc_realloc
+ (p->buf, sizeof(int) * (size_t)p->maxcols);
}
-
static void
-buffera(struct termp *p, const char *word, size_t sz)
+bufferc(struct termp *p, char c)
{
- if (p->col + sz >= p->maxcols)
- adjbuf(p, p->col + sz);
+ if (p->col + 1 >= p->maxcols)
+ adjbuf(p, p->col + 1);
- memcpy(&p->buf[(int)p->col], word, sz);
- p->col += sz;
+ p->buf[p->col++] = c;
}
-
+/*
+ * See encode().
+ * Do this for a single (probably unicode) value.
+ * Does not check for non-decorated glyphs.
+ */
static void
-bufferc(struct termp *p, char c)
+encode1(struct termp *p, int c)
{
+ enum termfont f;
- if (p->col + 1 >= p->maxcols)
- adjbuf(p, p->col + 1);
+ if (TERMP_SKIPCHAR & p->flags) {
+ p->flags &= ~TERMP_SKIPCHAR;
+ return;
+ }
- p->buf[(int)p->col++] = c;
-}
+ if (p->col + 4 >= p->maxcols)
+ adjbuf(p, p->col + 4);
+
+ f = term_fonttop(p);
+ if (TERMFONT_NONE == f) {
+ p->buf[p->col++] = c;
+ return;
+ } else if (TERMFONT_UNDER == f) {
+ p->buf[p->col++] = '_';
+ } else
+ p->buf[p->col++] = c;
+
+ p->buf[p->col++] = 8;
+ p->buf[p->col++] = c;
+}
static void
encode(struct termp *p, const char *word, size_t sz)
{
enum termfont f;
- int i;
+ int i, len;
+
+ if (TERMP_SKIPCHAR & p->flags) {
+ p->flags &= ~TERMP_SKIPCHAR;
+ return;
+ }
+
+ /* LINTED */
+ len = sz;
/*
* Encode and buffer a string of characters. If the current
*/
if (TERMFONT_NONE == (f = term_fonttop(p))) {
- buffera(p, word, sz);
+ if (p->col + len >= p->maxcols)
+ adjbuf(p, p->col + len);
+ for (i = 0; i < len; i++)
+ p->buf[p->col++] = word[i];
return;
}
- for (i = 0; i < (int)sz; i++) {
- if ( ! isgraph((u_char)word[i])) {
- bufferc(p, word[i]);
+ /* Pre-buffer, assuming worst-case. */
+
+ if (p->col + 1 + (len * 3) >= p->maxcols)
+ adjbuf(p, p->col + 1 + (len * 3));
+
+ for (i = 0; i < len; i++) {
+ if (ASCII_HYPH != word[i] &&
+ ! isgraph((unsigned char)word[i])) {
+ p->buf[p->col++] = word[i];
continue;
}
if (TERMFONT_UNDER == f)
- bufferc(p, '_');
+ p->buf[p->col++] = '_';
+ else if (ASCII_HYPH == word[i])
+ p->buf[p->col++] = '-';
else
- bufferc(p, word[i]);
+ p->buf[p->col++] = word[i];
- bufferc(p, 8);
- bufferc(p, word[i]);
+ p->buf[p->col++] = 8;
+ p->buf[p->col++] = word[i];
}
}
-
size_t
term_len(const struct termp *p, size_t sz)
{
return((*p->width)(p, ' ') * sz);
}
+static size_t
+cond_width(const struct termp *p, int c, int *skip)
+{
+
+ if (*skip) {
+ (*skip) = 0;
+ return(0);
+ } else
+ return((*p->width)(p, c));
+}
size_t
term_strlen(const struct termp *p, const char *cp)
{
- size_t sz;
+ size_t sz, rsz, i;
+ int ssz, skip, c;
+ const char *seq, *rhs;
+ enum mandoc_esc esc;
+ static const char rej[] = { '\\', ASCII_HYPH, ASCII_NBRSP, '\0' };
+
+ /*
+ * 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;
+ skip = 0;
+ while ('\0' != *cp) {
+ rsz = strcspn(cp, rej);
+ for (i = 0; i < rsz; i++)
+ sz += cond_width(p, *cp++, &skip);
+
+ c = 0;
+ switch (*cp) {
+ case ('\\'):
+ cp++;
+ esc = mandoc_escape(&cp, &seq, &ssz);
+ if (ESCAPE_ERROR == esc)
+ return(sz);
+
+ if (TERMENC_ASCII != p->enc)
+ switch (esc) {
+ case (ESCAPE_UNICODE):
+ c = mchars_num2uc
+ (seq + 1, ssz - 1);
+ if ('\0' == c)
+ break;
+ sz += cond_width(p, c, &skip);
+ continue;
+ case (ESCAPE_SPECIAL):
+ c = mchars_spec2cp
+ (p->symtab, seq, ssz);
+ if (c <= 0)
+ break;
+ sz += cond_width(p, c, &skip);
+ continue;
+ default:
+ break;
+ }
+
+ rhs = NULL;
+
+ switch (esc) {
+ case (ESCAPE_UNICODE):
+ sz += cond_width(p, '?', &skip);
+ break;
+ case (ESCAPE_NUMBERED):
+ c = mchars_num2char(seq, ssz);
+ if ('\0' != c)
+ sz += cond_width(p, c, &skip);
+ break;
+ case (ESCAPE_SPECIAL):
+ rhs = mchars_spec2str
+ (p->symtab, seq, ssz, &rsz);
+
+ if (ssz != 1 || rhs)
+ break;
+
+ rhs = seq;
+ rsz = ssz;
+ break;
+ case (ESCAPE_SKIPCHAR):
+ skip = 1;
+ break;
+ default:
+ break;
+ }
+
+ if (NULL == rhs)
+ break;
- for (sz = 0; *cp; cp++)
- sz += (*p->width)(p, *cp);
+ if (skip) {
+ skip = 0;
+ break;
+ }
+
+ for (i = 0; i < rsz; i++)
+ sz += (*p->width)(p, *rhs++);
+ break;
+ case (ASCII_NBRSP):
+ sz += cond_width(p, ' ', &skip);
+ cp++;
+ break;
+ case (ASCII_HYPH):
+ sz += cond_width(p, '-', &skip);
+ cp++;
+ break;
+ default:
+ break;
+ }
+ }
return(sz);
}
-
+/* ARGSUSED */
size_t
term_vspan(const struct termp *p, const struct roffsu *su)
{
r);
}
-
size_t
term_hspan(const struct termp *p, const struct roffsu *su)
{
- double r;
-
- /* XXX: CM, IN, and PT are approximations. */
+ double v;
- switch (su->unit) {
- case (SCALE_CM):
- r = 4 * su->scale;
- break;
- case (SCALE_IN):
- /* XXX: this is an approximation. */
- r = 10 * su->scale;
- break;
- case (SCALE_PC):
- r = (10 * su->scale) / 6;
- break;
- case (SCALE_PT):
- r = (10 * su->scale) / 72;
- break;
- case (SCALE_MM):
- r = su->scale / 1000; /* FIXME: double-check. */
- break;
- case (SCALE_VS):
- r = su->scale * 2 - 1; /* FIXME: double-check. */
- break;
- default:
- r = su->scale;
- break;
- }
-
- if (r < 0.0)
- r = 0.0;
- return((size_t)/* LINTED */
- r);
+ v = ((*p->hspan)(p, su));
+ if (v < 0.0)
+ v = 0.0;
+ return((size_t) /* LINTED */
+ v);
}
-
-
git.ckatri.com / mandoc.git / blobdiff