mdocml: Allow string lengths to account for escapes.

mdocml: Allow string lengths to account for escapes.

[kristaps]

Log Message:
-----------
Allow string lengths to account for escapes.  Now all calls to calculate
column width in -Tascii, -Tpdf, and -Tps will account for "more real"
string lengths.

Example:

.Bl -tag -width \s[+123424]foo
.It bar
baz
.El

The size escape will be correctly tossed.

.Bl -tag -width \(aqbar
.It \(aqbar
baz
.El

The \(aq will be correctly handled.

Modified Files:
--------------
    mdocml:
        TODO
        man_term.c
        term.c

Revision Data
-------------
Index: term.c
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/term.c,v
retrieving revision 1.170
retrieving revision 1.171
diff -Lterm.c -Lterm.c -u -p -r1.170 -r1.171
--- term.c
+++ term.c
@@ -458,7 +458,6 @@ void
 term_word(struct termp *p, const char *word)
 {
 	const char	*sv, *seq;
-	int		 sz;
 	size_t		 ssz;
 	enum roffdeco	 deco;
 
@@ -515,7 +514,7 @@ term_word(struct termp *p, const char *w
 			continue;
 
 		seq = ++word;
-		sz = a2roffdeco(&deco, &seq, &ssz);
+		word += a2roffdeco(&deco, &seq, &ssz);
 
 		switch (deco) {
 		case (DECO_RESERVED):
@@ -542,7 +541,6 @@ term_word(struct termp *p, const char *w
 			break;
 		}
 
-		word += sz;
 		if (DECO_NOSPACE == deco && '\0' == *word)
 			p->flags |= TERMP_NOSPACE;
 	}
@@ -645,10 +643,48 @@ term_len(const struct termp *p, size_t s
 size_t
 term_strlen(const struct termp *p, const char *cp)
 {
-	size_t		 sz;
-
-	for (sz = 0; *cp; cp++)
-		sz += (*p->width)(p, *cp);
+	size_t		 sz, ssz, rsz, i;
+	enum roffdeco	 d;
+	const char	*seq, *rhs;
+
+	for (sz = 0; '\0' != *cp; )
+		/*
+		 * Account for escaped sequences within string length
+		 * calculations.  This follows the logic in term_word()
+		 * as we must calculate the width of produced strings.
+		 */
+		if ('\\' == *cp) {
+			seq = ++cp;
+			cp += a2roffdeco(&d, &seq, &ssz);
+
+			switch (d) {
+			case (DECO_RESERVED):
+				rhs = chars_res2str
+					(p->symtab, seq, ssz, &rsz);
+				break;
+			case (DECO_SPECIAL):
+				/* FALLTHROUGH */
+			case (DECO_SSPECIAL):
+				rhs = chars_spec2str
+					(p->symtab, seq, ssz, &rsz);
+
+				/* Allow for one-char escapes. */
+				if (DECO_SSPECIAL != d || rhs)
+					break;
+
+				rhs = seq;
+				rsz = ssz;
+				break;
+			default:
+				rhs = NULL;
+				break;
+			}
+
+			if (rhs)
+				for (i = 0; i < rsz; i++)
+					sz += (*p->width)(p, *rhs++);
+		} else
+			sz += (*p->width)(p, *cp++);
 
 	return(sz);
 }
Index: man_term.c
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/man_term.c,v
retrieving revision 1.84
retrieving revision 1.85
diff -Lman_term.c -Lman_term.c -u -p -r1.84 -r1.85
--- man_term.c
+++ man_term.c
@@ -916,6 +916,10 @@ print_man_foot(struct termp *p, const vo
 	p->rmargin = p->maxrmargin - term_strlen(p, buf);
 	p->offset = 0;
 
+	/* term_strlen() can return zero. */
+	if (p->rmargin == p->maxrmargin)
+		p->rmargin--;
+
 	if (meta->source)
 		term_word(p, meta->source);
 	if (meta->source)
Index: TODO
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/TODO,v
retrieving revision 1.46
retrieving revision 1.47
diff -LTODO -LTODO -u -p -r1.46 -r1.47
--- TODO
+++ TODO
@@ -172,11 +172,6 @@ Several areas can be cleaned up to make 
 * structural issues
 ************************************************************************
 
-- rendering frontend code can calculate widths only for plain strings,
-  not for strings containing escape sequences.  For example, this
-  hinders calculation of the indent required for .Nm \&[ in text(1).
-  comments from kristaps@  Wed, 21 Jul 2010 23:26:08 +0200
-
 - another example of the same problem:
   .Bl -tag -width "\eD{format}XX" -compact
   in OpenBSD ksh(1) gives the wrong width
--
 To unsubscribe send an email to source+unsubscribe@mdocml.bsd.lv