Remove a2roffdeco() and mandoc_special() functions and replace them with

a public (mandoc.h) function mandoc_escape(), which merges the
functionality of both prior functions.

Reason: code duplication.  The a2roffdeco() and mandoc_special()
functions were pretty much the same thing and both quite complex.  This
allows one function to receive improvements in (e.g.) subexpression
handling and performance, instead of having to replicate functionality.

As such, the mandoc_escape() function already handles a superset of the
escapes handled in previous versions and has improvements in performance
(using strcspn(), for example) and reliable handling of subexpressions.

This code Works For Me, but may need work to catch any regressions.
Since the benefits are great (leaner code, simpler API), I'd rather have
it in-tree than floating as a patch.

1 files changed, 31 insertions, 25 deletions

diff --git a/man_validate.c b/man_validate.c
index 03bb120f..e744ed3c 100644
--- a/man_validate.c
+++ b/man_validate.c
@@ -1,4 +1,4 @@
-/*	$Id: man_validate.c,v 1.67 2011/03/22 15:30:30 kristaps Exp $ */
+/*	$Id: man_validate.c,v 1.68 2011/04/09 15:29:40 kristaps Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
@@ -54,7 +54,7 @@ static	int	  check_par(CHKARGS);
 static	int	  check_part(CHKARGS);
 static	int	  check_root(CHKARGS);
 static	int	  check_sec(CHKARGS);
-static	int	  check_text(CHKARGS);
+static	void	  check_text(CHKARGS);
 
 static	int	  post_AT(CHKARGS);
 static	int	  post_fi(CHKARGS);
@@ -151,7 +151,8 @@ man_valid_post(struct man *m)
 
 	switch (m->last->type) {
 	case (MAN_TEXT): 
-		return(check_text(m, m->last));
+		check_text(m, m->last);
+		return(1);
 	case (MAN_ROOT):
 		return(check_root(m, m->last));
 	case (MAN_EQN):
@@ -204,43 +205,48 @@ check_root(CHKARGS)
 	return(1);
 }
 
-
-static int
+static void
 check_text(CHKARGS) 
 {
-	char		*p;
-	int		 pos, c;
+	char		*p, *pp, *cpp;
+	int		 pos;
 	size_t		 sz;
 
-	for (p = n->string, pos = n->pos + 1; *p; p++, pos++) {
-		sz = strcspn(p, "\t\\");
-		p += (int)sz;
+	p = n->string;
+	pos = n->pos + 1;
 
-		if ('\0' == *p)
-			break;
+	while ('\0' != *p) {
+		sz = strcspn(p, "\t\\");
 
+		p += (int)sz;
 		pos += (int)sz;
 
 		if ('\t' == *p) {
-			if (MAN_LITERAL & m->flags)
-				continue;
-			man_pmsg(m, n->line, pos, MANDOCERR_BADTAB);
+			if ( ! (MAN_LITERAL & m->flags))
+				man_pmsg(m, n->line, pos, MANDOCERR_BADTAB);
+			p++;
+			pos++;
 			continue;
-		}
+		} else if ('\0' == *p)
+			break;
 
-		/* Check the special character. */
+		pos++;
+		pp = ++p;
 
-		c = mandoc_special(p);
-		if (c) {
-			p += c - 1;
-			pos += c - 1;
-		} else
+		if (ESCAPE_ERROR == mandoc_escape
+				((const char **)&pp, NULL, NULL)) {
 			man_pmsg(m, n->line, pos, MANDOCERR_BADESCAPE);
-	}
+			break;
+		}
 
-	return(1);
-}
+		cpp = p;
+		while (NULL != (cpp = memchr(cpp, ASCII_HYPH, pp - cpp)))
+			*cpp = '-';
 
+		pos += pp - p;
+		p = pp;
+	}
+}
 
 #define	INEQ_DEFINE(x, ineq, name) \
 static int \