=================================================================== RCS file: /cvs/mandoc/term.c,v retrieving revision 1.191 retrieving revision 1.203 diff -u -p -r1.191 -r1.203 --- mandoc/term.c 2011/05/15 22:29:50 1.191 +++ mandoc/term.c 2012/05/31 22:29:13 1.203 @@ -1,7 +1,7 @@ -/* $Id: term.c,v 1.191 2011/05/15 22:29:50 kristaps Exp $ */ +/* $Id: term.c,v 1.203 2012/05/31 22:29:13 schwarze Exp $ */ /* - * Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons - * Copyright (c) 2010, 2011 Ingo Schwarze + * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons + * Copyright (c) 2010, 2011, 2012 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 @@ -33,9 +33,11 @@ #include "term.h" #include "main.h" +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) @@ -69,18 +71,6 @@ term_end(struct termp *p) (*p->end)(p); } - -struct termp * -term_alloc(enum termenc enc) -{ - struct termp *p; - - p = mandoc_calloc(1, sizeof(struct termp)); - 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 @@ -90,22 +80,18 @@ term_alloc(enum termenc enc) * * 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: @@ -145,9 +131,10 @@ term_flushln(struct termp *p) bp = TERMP_NOBREAK & p->flags ? mmax : maxvis; /* - * Indent the first line of a paragraph. + * Calculate the required amount of padding. */ - vbl = p->flags & TERMP_NOLPAD ? (size_t)0 : p->offset; + vbl = p->offset + p->overstep > p->viscol ? + p->offset + p->overstep - p->viscol : 0; vis = vend = 0; i = 0; @@ -198,14 +185,12 @@ term_flushln(struct termp *p) 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. */ @@ -247,10 +232,14 @@ term_flushln(struct termp *p) 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]); + continue; } + + (*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]); } vis = vend; } @@ -259,7 +248,8 @@ term_flushln(struct termp *p) * If there was trailing white space, it was not printed; * so reset the cursor position accordingly. */ - vis -= vbl; + if (vis) + vis -= vbl; p->col = 0; p->overstep = 0; @@ -284,25 +274,18 @@ term_flushln(struct termp *p) * 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); - maxvis += (size_t)p->overstep; - } else + if (p->overstep < -1) p->overstep = 0; + return; } else if (TERMP_DANGLE & p->flags) return; - /* Right-pad. */ - if (maxvis > vis + + /* If the column was overrun, break the line. */ + if (maxvis <= vis + ((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); + p->viscol = 0; } } @@ -317,12 +300,8 @@ term_newln(struct termp *p) { 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); } @@ -338,7 +317,10 @@ term_vspace(struct termp *p) term_newln(p); p->viscol = 0; - (*p->endline)(p); + if (0 < p->skipvsp) + p->skipvsp--; + else + (*p->endline)(p); } void @@ -415,7 +397,7 @@ term_word(struct termp *p, const char *word) { const char *seq, *cp; char c; - int sz; + int sz, uc; size_t ssz; enum mandoc_esc esc; @@ -438,28 +420,50 @@ term_word(struct termp *p, const char *word) p->flags &= ~(TERMP_SENTENCE | TERMP_IGNDELIM); while ('\0' != *word) { - if ((ssz = strcspn(word, "\\")) > 0) + if ('\\' != *word) { + if (TERMP_SKIPCHAR & p->flags) { + p->flags &= ~TERMP_SKIPCHAR; + word++; + continue; + } + ssz = strcspn(word, "\\"); encode(p, word, ssz); - - word += (int)ssz; - if ('\\' != *word) + word += (int)ssz; continue; + } word++; esc = mandoc_escape(&word, &seq, &sz); if (ESCAPE_ERROR == esc) break; + 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): - if ('\0' != (c = mchars_num2char(seq, sz))) + c = mchars_num2char(seq, sz); + if ('\0' != c) encode(p, &c, 1); break; - case (ESCAPE_PREDEF): - cp = mchars_res2str(p->symtab, seq, sz, &ssz); - if (NULL != cp) - encode(p, cp, ssz); - break; case (ESCAPE_SPECIAL): cp = mchars_spec2str(p->symtab, seq, sz, &ssz); if (NULL != cp) @@ -473,6 +477,8 @@ term_word(struct termp *p, const char *word) case (ESCAPE_FONTITALIC): term_fontrepl(p, TERMFONT_UNDER); break; + case (ESCAPE_FONT): + /* FALLTHROUGH */ case (ESCAPE_FONTROMAN): term_fontrepl(p, TERMFONT_NONE); break; @@ -480,9 +486,14 @@ term_word(struct termp *p, const char *word) term_fontlast(p); break; case (ESCAPE_NOSPACE): - if ('\0' == *word) + if (TERMP_SKIPCHAR & p->flags) + p->flags &= ~TERMP_SKIPCHAR; + else if ('\0' == *word) p->flags |= TERMP_NOSPACE; break; + case (ESCAPE_SKIPCHAR): + p->flags |= TERMP_SKIPCHAR; + break; default: break; } @@ -512,12 +523,49 @@ bufferc(struct termp *p, char c) p->buf[p->col++] = c; } +/* + * See encode(). + * Do this for a single (probably unicode) value. + * Does not check for non-decorated glyphs. + */ static void +encode1(struct termp *p, int c) +{ + enum termfont f; + + if (TERMP_SKIPCHAR & p->flags) { + p->flags &= ~TERMP_SKIPCHAR; + return; + } + + 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, len; + if (TERMP_SKIPCHAR & p->flags) { + p->flags &= ~TERMP_SKIPCHAR; + return; + } + /* LINTED */ len = sz; @@ -541,13 +589,16 @@ encode(struct termp *p, const char *word, size_t sz) adjbuf(p, p->col + 1 + (len * 3)); for (i = 0; i < len; i++) { - if ( ! isgraph((unsigned char)word[i])) { + if (ASCII_HYPH != word[i] && + ! isgraph((unsigned char)word[i])) { p->buf[p->col++] = word[i]; continue; } if (TERMFONT_UNDER == f) p->buf[p->col++] = '_'; + else if (ASCII_HYPH == word[i]) + p->buf[p->col++] = '-'; else p->buf[p->col++] = word[i]; @@ -563,13 +614,24 @@ 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, rsz, i; - int ssz, c; + int ssz, skip, c; const char *seq, *rhs; + enum mandoc_esc esc; static const char rej[] = { '\\', ASCII_HYPH, ASCII_NBRSP, '\0' }; /* @@ -579,27 +641,51 @@ term_strlen(const struct termp *p, const char *cp) */ sz = 0; + skip = 0; while ('\0' != *cp) { rsz = strcspn(cp, rej); for (i = 0; i < rsz; i++) - sz += (*p->width)(p, *cp++); + sz += cond_width(p, *cp++, &skip); + c = 0; switch (*cp) { case ('\\'): cp++; - rhs = NULL; - switch (mandoc_escape(&cp, &seq, &ssz)) { - case (ESCAPE_ERROR): + 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 += (*p->width)(p, c); + sz += cond_width(p, c, &skip); break; - case (ESCAPE_PREDEF): - rhs = mchars_res2str - (p->symtab, seq, ssz, &rsz); - break; case (ESCAPE_SPECIAL): rhs = mchars_spec2str (p->symtab, seq, ssz, &rsz); @@ -610,6 +696,9 @@ term_strlen(const struct termp *p, const char *cp) rhs = seq; rsz = ssz; break; + case (ESCAPE_SKIPCHAR): + skip = 1; + break; default: break; } @@ -617,15 +706,20 @@ term_strlen(const struct termp *p, const char *cp) if (NULL == rhs) break; + if (skip) { + skip = 0; + break; + } + for (i = 0; i < rsz; i++) sz += (*p->width)(p, *rhs++); break; case (ASCII_NBRSP): - sz += (*p->width)(p, ' '); + sz += cond_width(p, ' ', &skip); cp++; break; case (ASCII_HYPH): - sz += (*p->width)(p, '-'); + sz += cond_width(p, '-', &skip); cp++; break; default: