Merge release 1.11.3, almost all code by kristaps@:

* Unicode output support (no Unicode input yet, though).
* Refactoring: completely handle predefined strings in roff.c.
- New function mandoc_escape() replaces a2roffdeco() and mandoc_special().
- Start using mandoc_getarg() in mdoc_argv.c.
- Clean up parsing of delimiters in mdoc(7).
* And many minor fixes and lots of cleanup.

1 files changed, 1 insertions, 238 deletions

diff --git a/usr.bin/mandoc/out.c b/usr.bin/mandoc/out.c
index 48e3b3c5c8b..eaebdc4a697 100644
--- a/usr.bin/mandoc/out.c
+++ b/usr.bin/mandoc/out.c
@@ -1,4 +1,4 @@
-/*	$Id: out.c,v 1.13 2011/04/21 22:59:54 schwarze Exp $ */
+/*	$Id: out.c,v 1.14 2011/05/29 21:22:18 schwarze Exp $ */
 /*
  * Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org>
@@ -170,243 +170,6 @@ time2a(time_t t, char *dst, size_t sz)
 	(void)strftime(p, sz, "%Y", &tm);
 }
 
-
-int
-a2roffdeco(enum roffdeco *d, const char **word, size_t *sz)
-{
-	int		 i, j, lim;
-	char		 term, c;
-	const char	*wp;
-	enum roffdeco	 dd;
-
-	*d = DECO_NONE;
-	lim = i = 0;
-	term = '\0';
-	wp = *word;
-
-	switch ((c = wp[i++])) {
-	case ('('):
-		*d = DECO_SPECIAL;
-		lim = 2;
-		break;
-	case ('F'):
-		/* FALLTHROUGH */
-	case ('f'):
-		*d = 'F' == c ? DECO_FFONT : DECO_FONT;
-
-		switch (wp[i++]) {
-		case ('('):
-			lim = 2;
-			break;
-		case ('['):
-			term = ']';
-			break;
-		case ('3'):
-			/* FALLTHROUGH */
-		case ('B'):
-			*d = DECO_BOLD;
-			return(i);
-		case ('2'):
-			/* FALLTHROUGH */
-		case ('I'):
-			*d = DECO_ITALIC;
-			return(i);
-		case ('P'):
-			*d = DECO_PREVIOUS;
-			return(i);
-		case ('1'):
-			/* FALLTHROUGH */
-		case ('R'):
-			*d = DECO_ROMAN;
-			return(i);
-		default:
-			i--;
-			lim = 1;
-			break;
-		}
-		break;
-	case ('k'):
-		/* FALLTHROUGH */
-	case ('M'):
-		/* FALLTHROUGH */
-	case ('m'):
-		/* FALLTHROUGH */
-	case ('*'):
-		if ('*' == c)
-			*d = DECO_RESERVED;
-
-		switch (wp[i++]) {
-		case ('('):
-			lim = 2;
-			break;
-		case ('['):
-			term = ']';
-			break;
-		default:
-			i--;
-			lim = 1;
-			break;
-		}
-		break;
-
-	case ('N'):
-
-		/*
-		 * Sequence of characters:  backslash,  'N' (i = 0),
-		 * starting delimiter (i = 1), character number (i = 2).
-		 */
-
-		*word = wp + 2;
-		*sz = 0;
-
-		/*
-		 * Cannot use a digit as a starting delimiter;
-		 * but skip the digit anyway.
-		 */
-
-		if (isdigit((int)wp[1]))
-			return(2);
-
-		/*
-		 * Any non-digit terminates the character number.
-		 * That is, the terminating delimiter need not
-		 * match the starting delimiter.
-		 */
-
-		for (i = 2; isdigit((int)wp[i]); i++)
-			(*sz)++;
-
-		/*
-		 * This is only a numbered character
-		 * if the character number has at least one digit.
-		 */
-
-		if (*sz)
-			*d = DECO_NUMBERED;
-
-		/*
-		 * Skip the terminating delimiter, even if it does not
-		 * match, and even if there is no character number.
-		 */
-
-		return(++i);
-
-	case ('h'):
-		/* FALLTHROUGH */
-	case ('v'):
-		/* FALLTHROUGH */
-	case ('s'):
-		j = 0;
-		if ('+' == wp[i] || '-' == wp[i]) {
-			i++;
-			j = 1;
-		}
-
-		switch (wp[i++]) {
-		case ('('):
-			lim = 2;
-			break;
-		case ('['):
-			term = ']';
-			break;
-		case ('\''):
-			term = '\'';
-			break;
-		case ('0'):
-			j = 1;
-			/* FALLTHROUGH */
-		default:
-			i--;
-			lim = 1;
-			break;
-		}
-
-		if ('+' == wp[i] || '-' == wp[i]) {
-			if (j)
-				return(i);
-			i++;
-		} 
-
-		/* Handle embedded numerical subexp or escape. */
-
-		if ('(' == wp[i]) {
-			while (wp[i] && ')' != wp[i])
-				if ('\\' == wp[i++]) {
-					/* Handle embedded escape. */
-					*word = &wp[i];
-					i += a2roffdeco(&dd, word, sz);
-				}
-
-			if (')' == wp[i++])
-				break;
-
-			*d = DECO_NONE;
-			return(i - 1);
-		} else if ('\\' == wp[i]) {
-			*word = &wp[++i];
-			i += a2roffdeco(&dd, word, sz);
-		}
-
-		break;
-	case ('['):
-		*d = DECO_SPECIAL;
-		term = ']';
-		break;
-	case ('c'):
-		*d = DECO_NOSPACE;
-		return(i);
-	case ('z'):
-		*d = DECO_NONE;
-		if ('\\' == wp[i]) {
-			*word = &wp[++i];
-			return(i + a2roffdeco(&dd, word, sz));
-		} else
-			lim = 1;
-		break;
-	case ('o'):
-		/* FALLTHROUGH */
-	case ('w'):
-		if ('\'' == wp[i++]) {
-			term = '\'';
-			break;
-		} 
-		/* FALLTHROUGH */
-	default:
-		*d = DECO_SSPECIAL;
-		i--;
-		lim = 1;
-		break;
-	}
-
-	assert(term || lim);
-	*word = &wp[i];
-
-	if (term) {
-		j = i;
-		while (wp[i] && wp[i] != term)
-			i++;
-		if ('\0' == wp[i]) {
-			*d = DECO_NONE;
-			return(i);
-		}
-
-		assert(i >= j);
-		*sz = (size_t)(i - j);
-
-		return(i + 1);
-	}
-
-	assert(lim > 0);
-	*sz = (size_t)lim;
-
-	for (j = 0; wp[i] && j < lim; j++)
-		i++;
-	if (j < lim)
-		*d = DECO_NONE;
-
-	return(i);
-}
-
 /*
  * Calculate the abstract widths and decimal positions of columns in a
  * table.  This routine allocates the columns structures then runs over