=================================================================== RCS file: /cvs/mandoc/term.c,v retrieving revision 1.137 retrieving revision 1.164 diff -u -p -r1.137 -r1.164 --- mandoc/term.c 2010/05/17 22:11:42 1.137 +++ mandoc/term.c 2010/07/25 22:56:47 1.164 @@ -1,6 +1,7 @@ -/* $Id: term.c,v 1.137 2010/05/17 22:11:42 kristaps Exp $ */ +/* $Id: term.c,v 1.164 2010/07/25 22:56:47 kristaps Exp $ */ /* - * Copyright (c) 2008, 2009 Kristaps Dzonsons + * Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons + * Copyright (c) 2010 Ingo Schwarze * * Permission to use, copy, modify, and distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -22,22 +23,19 @@ #include #include +#include #include #include #include -#include #include "mandoc.h" #include "chars.h" #include "out.h" #include "term.h" -#include "man.h" -#include "mdoc.h" #include "main.h" -static struct termp *term_alloc(enum termenc, size_t); -static void term_free(struct termp *); -static void spec(struct termp *, const char *, size_t); +static void spec(struct termp *, enum roffdeco, + 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); @@ -45,50 +43,51 @@ static void adjbuf(struct termp *p, size_t); static void encode(struct termp *, const char *, size_t); -void * -ascii_alloc(size_t width) +void +term_free(struct termp *p) { - return(term_alloc(TERMENC_ASCII, width)); + if (p->buf) + free(p->buf); + if (p->symtab) + chars_free(p->symtab); + + free(p); } void -terminal_free(void *arg) +term_begin(struct termp *p, term_margin head, + term_margin foot, const void *arg) { - term_free((struct termp *)arg); + p->headf = head; + p->footf = foot; + p->argf = arg; + (*p->begin)(p); } -static void -term_free(struct termp *p) +void +term_end(struct termp *p) { - if (p->buf) - free(p->buf); - if (p->symtab) - chars_free(p->symtab); - - free(p); + (*p->end)(p); } -static struct termp * -term_alloc(enum termenc enc, size_t width) +struct termp * +term_alloc(enum termenc enc) { - struct termp *p; + struct termp *p; p = calloc(1, sizeof(struct termp)); if (NULL == p) { perror(NULL); exit(EXIT_FAILURE); } + p->enc = enc; - /* Enforce some lower boundary. */ - if (width < 60) - width = 60; - p->defrmargin = width - 2; return(p); } @@ -136,8 +135,10 @@ term_flushln(struct termp *p) 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 */ - size_t maxvis, mmax; + 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. @@ -162,13 +163,20 @@ term_flushln(struct termp *p) */ vbl = p->flags & TERMP_NOLPAD ? 0 : p->offset; - /* - * FIXME: if bp is zero, we still output the first word before - * breaking the line. - */ - vis = vend = i = 0; + while (i < (int)p->col) { + /* + * 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; + vbl += vend - vis; + vis = vend; + } /* * Count up visible word characters. Control sequences @@ -178,27 +186,39 @@ term_flushln(struct termp *p) */ /* LINTED */ - for (j = i; j < (int)p->col; j++) { - if (j && ' ' == p->buf[j]) + for (jhy = 0; j < (int)p->col; j++) { + if ((j && ' ' == p->buf[j]) || '\t' == p->buf[j]) break; - if (8 == p->buf[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]); } /* * Find out whether we would exceed the right margin. * If so, break to the next line. */ - if (vend > bp && vis > 0) { + if (vend > bp && 0 == jhy && vis > 0) { vend -= vis; - putchar('\n'); + (*p->endline)(p); if (TERMP_NOBREAK & p->flags) { - for (j = 0; j < (int)p->rmargin; j++) - putchar(' '); + p->viscol = p->rmargin; + (*p->advance)(p, p->rmargin); vend += p->rmargin - p->offset; } else { + p->viscol = 0; vbl = p->offset; } @@ -209,17 +229,27 @@ term_flushln(struct termp *p) 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++) { + 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++; - } + vbl += (i - j) * (*p->width)(p, ' '); break; } if (ASCII_NBRSP == p->buf[i]) { - vbl++; + vbl += (*p->width)(p, ' '); continue; } @@ -229,11 +259,18 @@ term_flushln(struct termp *p) * so write preceding white space now. */ if (vbl) { - for (j = 0; j < (int)vbl; j++) - putchar(' '); + (*p->advance)(p, vbl); + p->viscol += vbl; vbl = 0; } - putchar(p->buf[i]); + + if (ASCII_HYPH == p->buf[i]) { + (*p->letter)(p, '-'); + p->viscol += (*p->width)(p, '-'); + } else { + (*p->letter)(p, p->buf[i]); + p->viscol += (*p->width)(p, p->buf[i]); + } } vend += vbl; vis = vend; @@ -243,14 +280,15 @@ term_flushln(struct termp *p) p->overstep = 0; if ( ! (TERMP_NOBREAK & p->flags)) { - putchar('\n'); + p->viscol = 0; + (*p->endline)(p); return; } if (TERMP_HANG & p->flags) { /* We need one blank after the tag. */ p->overstep = /* LINTED */ - vis - maxvis + 1; + vis - maxvis + (*p->width)(p, ' '); /* * Behave exactly the same way as groff: @@ -274,13 +312,15 @@ term_flushln(struct termp *p) /* Right-pad. */ if (maxvis > vis + /* LINTED */ - ((TERMP_TWOSPACE & p->flags) ? 1 : 0)) - for ( ; vis < maxvis; vis++) - putchar(' '); - else { /* ...or newline break. */ - putchar('\n'); - for (i = 0; i < (int)p->rmargin; i++) - putchar(' '); + ((TERMP_TWOSPACE & p->flags) ? + (*p->width)(p, ' ') : 0)) { + p->viscol += maxvis - vis; + (*p->advance)(p, maxvis - vis); + vis += (maxvis - vis); + } else { /* ...or newline break. */ + (*p->endline)(p); + p->viscol = p->rmargin; + (*p->advance)(p, p->rmargin); } } @@ -295,7 +335,7 @@ term_newln(struct termp *p) { p->flags |= TERMP_NOSPACE; - if (0 == p->col) { + if (0 == p->col && 0 == p->viscol) { p->flags &= ~TERMP_NOLPAD; return; } @@ -315,19 +355,22 @@ term_vspace(struct termp *p) { term_newln(p); - putchar('\n'); + p->viscol = 0; + (*p->endline)(p); } static void -spec(struct termp *p, const char *word, size_t len) +spec(struct termp *p, enum roffdeco d, const char *word, size_t len) { const char *rhs; size_t sz; - rhs = chars_a2ascii(p->symtab, word, len, &sz); + rhs = chars_spec2str(p->symtab, word, len, &sz); if (rhs) encode(p, rhs, sz); + else if (DECO_SSPECIAL == d) + encode(p, word, len); } @@ -337,7 +380,7 @@ res(struct termp *p, const char *word, size_t len) const char *rhs; size_t sz; - rhs = chars_a2res(p->symtab, word, len, &sz); + rhs = chars_res2str(p->symtab, word, len, &sz); if (rhs) encode(p, rhs, sz); } @@ -448,9 +491,14 @@ term_word(struct termp *p, const char *word) } 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)) @@ -458,14 +506,13 @@ term_word(struct termp *p, const char *word) p->flags &= ~TERMP_SENTENCE; - /* FIXME: use strcspn. */ - while (*word) { - if ('\\' != *word) { - encode(p, word, 1); - word++; + if ((ssz = strcspn(word, "\\")) > 0) + encode(p, word, ssz); + + word += ssz; + if ('\\' != *word) continue; - } seq = ++word; sz = a2roffdeco(&deco, &seq, &ssz); @@ -475,7 +522,9 @@ term_word(struct termp *p, const char *word) res(p, seq, ssz); break; case (DECO_SPECIAL): - spec(p, seq, ssz); + /* FALLTHROUGH */ + case (DECO_SSPECIAL): + spec(p, deco, seq, ssz); break; case (DECO_BOLD): term_fontrepl(p, TERMFONT_BOLD); @@ -502,7 +551,7 @@ term_word(struct termp *p, const char *word) * 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]) + if (sv[0] && '\0' == sv[1]) switch (sv[0]) { case('('): /* FALLTHROUGH */ @@ -590,8 +639,29 @@ encode(struct termp *p, const char *word, size_t sz) size_t -term_vspan(const struct roffsu *su) +term_len(const struct termp *p, size_t sz) { + + return((*p->width)(p, ' ') * sz); +} + + +size_t +term_strlen(const struct termp *p, const char *cp) +{ + size_t sz; + + for (sz = 0; *cp; cp++) + sz += (*p->width)(p, *cp); + + return(sz); +} + + +/* ARGSUSED */ +size_t +term_vspan(const struct termp *p, const struct roffsu *su) +{ double r; switch (su->unit) { @@ -626,41 +696,13 @@ term_vspan(const struct roffsu *su) size_t -term_hspan(const struct roffsu *su) +term_hspan(const struct termp *p, const struct roffsu *su) { - double r; + double v; - /* XXX: CM, IN, and PT are approximations. */ - - 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); } - -