While i already got my fingers dirty on mandoc_escape(),

profit of the occasion to pull out some spaghetti, that is,
three confusing variables and fourteen pointless assignments
among them; instead, always operate on the official pointers
**start, **end, and *sz, each of which conveys an obvious meaning.

No functional change intended, and the new tests confirm that
everything still (err...) "works", as far as that word can be
applied to the kind of roff(7) mock-up code i'm polishing here.

14 files changed, 281 insertions, 70 deletions

diff --git a/regress/usr.bin/mandoc/roff/esc/Makefile b/regress/usr.bin/mandoc/roff/esc/Makefile
index f8e95e9161c..e9705972a80 100644
--- a/regress/usr.bin/mandoc/roff/esc/Makefile
+++ b/regress/usr.bin/mandoc/roff/esc/Makefile
@@ -1,6 +1,6 @@
-# $OpenBSD: Makefile,v 1.2 2012/05/28 17:08:48 schwarze Exp $
+# $OpenBSD: Makefile,v 1.3 2012/05/28 22:45:34 schwarze Exp $
 
-REGRESS_TARGETS=h z
+REGRESS_TARGETS=one two multi c f h z ignore
 
 # Postprocessing to remove "character backspace" sequences
 # unless they are foolowed by the same character again.
diff --git a/regress/usr.bin/mandoc/roff/esc/c.in b/regress/usr.bin/mandoc/roff/esc/c.in
new file mode 100644
index 00000000000..be95f2bcd03
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/c.in
@@ -0,0 +1,13 @@
+.Dd May 28, 2012
+.Dt ESC-C 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-c
+.Nd the roff escape c sequence: remove trailing space
+.Sh DESCRIPTION
+No space between
+.Dq one
+and
+.Dq word :
+one\c
+word
diff --git a/regress/usr.bin/mandoc/roff/esc/c.out_ascii b/regress/usr.bin/mandoc/roff/esc/c.out_ascii
new file mode 100644
index 00000000000..90ed2c99605
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/c.out_ascii
@@ -0,0 +1,9 @@
+ESC-C(1)                   OpenBSD Reference Manual                   ESC-C(1)
+
+NNAAMMEE
+     eesscc--cc - the roff escape c sequence: remove trailing space
+
+DDEESSCCRRIIPPTTIIOONN
+     No space between ``one'' and ``word'': oneword
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/regress/usr.bin/mandoc/roff/esc/f.in b/regress/usr.bin/mandoc/roff/esc/f.in
new file mode 100644
index 00000000000..c6de2c297a8
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/f.in
@@ -0,0 +1,12 @@
+.Dd May 28, 2012
+.Dt ESC-F 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-f
+.Nd the roff escape f sequence: font changes
+.Sh DESCRIPTION
+numbers: \f3bold\f2italic\f1roman
+.br
+letters: \fBbold\fIitalic\fPback\fRroman
+.br
+multiletter: \f[B]bold\f[I]italic\f[P]back\f[R]roman
diff --git a/regress/usr.bin/mandoc/roff/esc/f.out_ascii b/regress/usr.bin/mandoc/roff/esc/f.out_ascii
new file mode 100644
index 00000000000..594c3a17625
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/f.out_ascii
@@ -0,0 +1,11 @@
+ESC-F(1)                   OpenBSD Reference Manual                   ESC-F(1)
+
+NNAAMMEE
+     eesscc--ff - the roff escape f sequence: font changes
+
+DDEESSCCRRIIPPTTIIOONN
+     numbers: bboolldd_i_t_a_l_i_croman
+     letters: bboolldd_i_t_a_l_i_cbbaacckkroman
+     multiletter: bboolldd_i_t_a_l_i_cbbaacckkroman
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/regress/usr.bin/mandoc/roff/esc/ignore.in b/regress/usr.bin/mandoc/roff/esc/ignore.in
new file mode 100644
index 00000000000..a7350b87cc1
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/ignore.in
@@ -0,0 +1,12 @@
+.Dd May 28, 2012
+.Dt ESC-IGNORE 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-ignore
+.Nd ignored roff escape sequences
+.Sh DESCRIPTION
+multiform: a\kxb\k(xyc\k[xyz]d
+.br
+quoted: a\R'myreg 0'b\R'myreg \A'y'0'c
+.br
+sizes: a\s0b\s(12c\s[123]d\s'123'e\s'1\w'xy'2'f
diff --git a/regress/usr.bin/mandoc/roff/esc/ignore.out_ascii b/regress/usr.bin/mandoc/roff/esc/ignore.out_ascii
new file mode 100644
index 00000000000..9a936163d89
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/ignore.out_ascii
@@ -0,0 +1,11 @@
+ESC-IGNORE(1)              OpenBSD Reference Manual              ESC-IGNORE(1)
+
+NNAAMMEE
+     eesscc--iiggnnoorree - ignored roff escape sequences
+
+DDEESSCCRRIIPPTTIIOONN
+     multiform: abcd
+     quoted: abc
+     sizes: abcdef
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/regress/usr.bin/mandoc/roff/esc/multi.in b/regress/usr.bin/mandoc/roff/esc/multi.in
new file mode 100644
index 00000000000..a2a76db1e01
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/multi.in
@@ -0,0 +1,10 @@
+.Dd May 28, 2012
+.Dt ESC-MULTI 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-multi
+.Nd roff multi-character escape sequences
+.Sh DESCRIPTION
+\[tno] \[t+-] \[tmu] \[tdi] \[12] \[14] \[34]
+.br
+\C'tno' \C't+-' \C'tmu' \C'tdi' \C'12' \C'14' \C'34'
diff --git a/regress/usr.bin/mandoc/roff/esc/multi.out_ascii b/regress/usr.bin/mandoc/roff/esc/multi.out_ascii
new file mode 100644
index 00000000000..eb4ad133a28
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/multi.out_ascii
@@ -0,0 +1,10 @@
+ESC-MULTI(1)               OpenBSD Reference Manual               ESC-MULTI(1)
+
+NNAAMMEE
+     eesscc--mmuullttii - roff multi-character escape sequences
+
+DDEESSCCRRIIPPTTIIOONN
+     ~ +- x -:- 1/2 1/4 3/4
+     ~ +- x -:- 1/2 1/4 3/4
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/regress/usr.bin/mandoc/roff/esc/one.in b/regress/usr.bin/mandoc/roff/esc/one.in
new file mode 100644
index 00000000000..caed6260cd6
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/one.in
@@ -0,0 +1,14 @@
+.Dd May 28, 2012
+.Dt ESC-ONE 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-one
+.Nd roff one-character escape sequences
+.Sh DESCRIPTION
+backslash: >\e<
+.br
+minus: >\-<
+.br
+acute: >\'<
+.br
+grave: >\`<
diff --git a/regress/usr.bin/mandoc/roff/esc/one.out_ascii b/regress/usr.bin/mandoc/roff/esc/one.out_ascii
new file mode 100644
index 00000000000..8fc54112b4b
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/one.out_ascii
@@ -0,0 +1,12 @@
+ESC-ONE(1)                 OpenBSD Reference Manual                 ESC-ONE(1)
+
+NNAAMMEE
+     eesscc--oonnee - roff one-character escape sequences
+
+DDEESSCCRRIIPPTTIIOONN
+     backslash: >\<
+     minus: >-<
+     acute: >'<
+     grave: >`<
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/regress/usr.bin/mandoc/roff/esc/two.in b/regress/usr.bin/mandoc/roff/esc/two.in
new file mode 100644
index 00000000000..6a5d222ccbb
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/two.in
@@ -0,0 +1,75 @@
+.Dd May 28, 2012
+.Dt ESC-TWO 1
+.Os OpenBSD
+.Sh NAME
+.Nm esc-two
+.Nd roff two-character escape sequences
+.Sh DESCRIPTION
+lines: \(ba \(br \(ul \(bb \(sl \(rs
+.\" groff doesn't know \(rl
+.br
+markers: \(bu \(lz \(sq \(ps \(sc \(lh \(rh \(at \(sh \(CR
+.\" the circle \(ci differs
+.\" the daggers \(dd and \(dg use backspace
+.\" groff doesn't know \(OK
+.br
+legal: \(co \(rg \(tm
+.br
+punctuation: \(em \(en \(hy
+.\" the inverted punctuation \(r! and \(r? use backspace
+.br
+quotes: \(Bq \(bq \(oq \(cq \(aq \(dq \(Fo \(Fc \(fo \(fc
+.\" the double quotes \(lq and \(rq differ
+.br
+brackets: \(lB \(rB \(lC \(rC \(la \(ra \(bv \(lt \(lk \(rt \(rk \(rb
+.\" the left bottom \(lb differs
+.br
+arrows: \(<- \(-> \(lA \(rA \(hA
+.\" the left-right arrow \(<> differs
+.\" groff doesn't know \(va and \(vA
+.\" the vertical arrows \(da, \(ua, \(uA, \(dA use backspace
+.br
+logical: \(AN \(OR \(no \(te \(st \(tf \(3d \(or
+.\" the universal quantifier \(fa uses backspace
+.br
+mathematical: \(pl \(mi \(-+ \(+- \(pc \(mu \(di \(f/ \(**
+\(<= \(>= \(<< \(>> \(eq \(!= \(== \(ne \(=~ \(ap \(~~ \(~= \(pt
+\(es \(mo \(sb \(sp \(ca \(cu
+\(sr \(lc \(rc \(lf \(rf \(if \(Ah \(Im \(Re \(pd
+.\" groff doesn't know \(-~, \(nb, \(nc, \(-h
+.\" these differ: \(nm \(ib \(ip \(/_ \(pp \(gr
+.\" these use backspace: \(c* \(c+ \(is
+.br
+ligatures: \(ff \(fi \(fl \(Fi \(Fl \(AE \(ae \(OE \(oe \(IJ \(ij
+.\" the German eszett \(ss differs
+.br
+accents: \(a" \(a^ \(aa \(ga \(ac \(ad \(ah \(ao \(a~ \(ho \(ha \(ti
+.\" the macron \(a- differs
+.\" groff doesn't know \(a.
+.\" the breve \(ab uses backspace
+.br
+.\" accented and special letters all use backspace:
+.\" \('A \('E \('I \('O \('U \('a \('e \('i \('o \('u
+.\" \(`A \(`E \(`I \(`O \(`U \(`a \(`e \(`i \(`o \(`u
+.\" \(~A \(~N \(~O \(~a \(~n \(~o
+.\" \(:A \(:E \(:I \(:O \(:U \(:a \(:e \(:i \(:o \(:u \(:y
+.\" \(^A \(^E \(^I \(^O \(^U \(^a \(^e \(^i \(^o \(^u
+.\" \(,C \(,c \(/L \(/l \(/O \(/o \(oA \(oa
+.\" \(-D \(Sd \(TP \(Tp
+.\" except:
+special letter: \(.i
+.\" groff doesn't know \(.j
+.br
+currency: \(Do \(Eu \(eu \(Fo
+.\" these use backspace: \(ct \(Ye \(Po \(Cs
+.br
+units: \(de \(fm
+.\" groff doesn't know \(%O, and \(sd and \(mc differ
+.br
+greek letters: \(*A \(*B \(*E \(*Z \(*Y \(*I \(*K \(*L
+\(*M \(*N \(*O \(*P \(*R \(*T \(*U \(*X
+\(*a \(*b \(*g \(*d \(*e \(*y \(*i \(*k
+\(*n \(*o \(*r \(*u \(*x \(*w \(+e \(ts
+.\" these differ: \(*G \(*S \(*F
+.\" these use backspace: \(*D \(*H \(*C \(*Q \(*W
+.\" \(*z \(*h \(*l \(*m \(*c \(*p \(*s \(*t \(*f \(*q \(+h \(+f \+p
diff --git a/regress/usr.bin/mandoc/roff/esc/two.out_ascii b/regress/usr.bin/mandoc/roff/esc/two.out_ascii
new file mode 100644
index 00000000000..d1960bc0bef
--- /dev/null
+++ b/regress/usr.bin/mandoc/roff/esc/two.out_ascii
@@ -0,0 +1,25 @@
+ESC-TWO(1)                 OpenBSD Reference Manual                 ESC-TWO(1)
+
+NNAAMMEE
+     eesscc--ttwwoo - roff two-character escape sequences
+
+DDEESSCCRRIIPPTTIIOONN
+     lines: | | _ | / \
+     markers: o <> [] 9| S <= => @ # _|
+     legal: (C) (R) tm
+     punctuation: -- - -
+     quotes: ,, , ` ' ' " << >> < >
+     brackets: [ ] { } < > | ,- { -. } -'
+     arrows: <- -> <= => <=>
+     logical: ^ v ~ 3 -) .:. .:. |
+     mathematical: + - -+ +- . x -:- / * <= >= << >> = != == !== =~ ~ ~~ ~= oc
+     {} E (= =) (^) U \/ |~ ~| |_ _| oo N I R a
+     ligatures: ff fi fl ffi ffl AE ae OE oe IJ ij
+     accents: " ^ ' ` , " v o ~ , ^ ~
+     special letter: i
+     currency: $ EUR EUR <<
+     units: o '
+     greek letters: A B E Z H I K /\ M N O TT P T Y X a B y d e n i k v o p u
+     x w e s
+
+OpenBSD                          May 28, 2012                          OpenBSD
diff --git a/usr.bin/mandoc/mandoc.c b/usr.bin/mandoc/mandoc.c
index 8c3afd24a7c..2bfb58f0e77 100644
--- a/usr.bin/mandoc/mandoc.c
+++ b/usr.bin/mandoc/mandoc.c
@@ -1,4 +1,4 @@
-/*	$Id: mandoc.c,v 1.33 2012/05/28 17:08:48 schwarze Exp $ */
+/*	$Id: mandoc.c,v 1.34 2012/05/28 22:45:33 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011, 2012 Ingo Schwarze <schwarze@openbsd.org>
@@ -38,20 +38,33 @@ static	char	*time2a(time_t);
 enum mandoc_esc
 mandoc_escape(const char **end, const char **start, int *sz)
 {
-	char		 c, term;
-	int		 i, rlim;
-	const char	*cp, *rstart;
+	const char	*local_start;
+	int		 local_sz;
+	char		 term;
 	enum mandoc_esc	 gly; 
 
-	cp = *end;
-	rstart = cp;
-	if (start)
-		*start = rstart;
-	i = rlim = 0;
+	/*
+	 * When the caller doesn't provide return storage,
+	 * use local storage.
+	 */
+
+	if (NULL == start)
+		start = &local_start;
+	if (NULL == sz)
+		sz = &local_sz;
+
+	/*
+	 * Beyond the backslash, at least one input character
+	 * is part of the escape sequence.  With one exception
+	 * (see below), that character won't be returned.
+	 */
+
 	gly = ESCAPE_ERROR;
+	*start = ++*end;
+	*sz = 0;
 	term = '\0';
 
-	switch ((c = cp[i++])) {
+	switch ((*start)[-1]) {
 	/*
 	 * First the glyphs.  There are several different forms of
 	 * these, but each eventually returns a substring of the glyph
@@ -59,7 +72,7 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	 */
 	case ('('):
 		gly = ESCAPE_SPECIAL;
-		rlim = 2;
+		*sz = 2;
 		break;
 	case ('['):
 		gly = ESCAPE_SPECIAL;
@@ -69,14 +82,15 @@ mandoc_escape(const char **end, const char **start, int *sz)
 		 * Unicode codepoint.  Here, however, only check whether
 		 * it's not a zero-width escape.
 		 */
-		if ('u' == cp[i] && ']' != cp[i + 1])
+		if ('u' == (*start)[0] && ']' != (*start)[1])
 			gly = ESCAPE_UNICODE;
 		term = ']';
 		break;
 	case ('C'):
-		if ('\'' != cp[i])
+		if ('\'' != **start)
 			return(ESCAPE_ERROR);
 		gly = ESCAPE_SPECIAL;
+		*start = ++*end;
 		term = '\'';
 		break;
 
@@ -87,7 +101,6 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	 * let us just skip the next character.
 	 */
 	case ('z'):
-		(*end)++;
 		return(ESCAPE_SKIPCHAR);
 
 	/*
@@ -114,21 +127,17 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	case ('f'):
 		if (ESCAPE_ERROR == gly)
 			gly = ESCAPE_FONT;
-
-		rstart= &cp[i];
-		if (start) 
-			*start = rstart;
-
-		switch (cp[i++]) {
+		switch (**start) {
 		case ('('):
-			rlim = 2;
+			*start = ++*end;
+			*sz = 2;
 			break;
 		case ('['):
+			*start = ++*end;
 			term = ']';
 			break;
 		default:
-			rlim = 1;
-			i--;
+			*sz = 1;
 			break;
 		}
 		break;
@@ -150,9 +159,10 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	case ('X'):
 		/* FALLTHROUGH */
 	case ('Z'):
-		if ('\'' != cp[i++])
+		if ('\'' != **start)
 			return(ESCAPE_ERROR);
 		gly = ESCAPE_IGNORE;
+		*start = ++*end;
 		term = '\'';
 		break;
 
@@ -178,10 +188,11 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	case ('w'):
 		/* FALLTHROUGH */
 	case ('x'):
+		if ('\'' != **start)
+			return(ESCAPE_ERROR);
 		if (ESCAPE_ERROR == gly)
 			gly = ESCAPE_IGNORE;
-		if ('\'' != cp[i++])
-			return(ESCAPE_ERROR);
+		*start = ++*end;
 		term = '\'';
 		break;
 
@@ -190,17 +201,17 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	 * XXX Do any other escapes need similar handling?
 	 */
 	case ('N'):
-		if ('\0' == cp[i])
+		if ('\0' == **start)
 			return(ESCAPE_ERROR);
-		*end = &cp[++i];
-		if (isdigit((unsigned char)cp[i-1]))
+		(*end)++;
+		if (isdigit((unsigned char)**start)) {
+			*sz = 1;
 			return(ESCAPE_IGNORE);
+		}
+		(*start)++;
 		while (isdigit((unsigned char)**end))
 			(*end)++;
-		if (start)
-			*start = &cp[i];
-		if (sz)
-			*sz = *end - &cp[i];
+		*sz = *end - *start;
 		if ('\0' != **end)
 			(*end)++;
 		return(ESCAPE_NUMBERED);
@@ -211,54 +222,43 @@ mandoc_escape(const char **end, const char **start, int *sz)
 	case ('s'):
 		gly = ESCAPE_IGNORE;
 
-		rstart = &cp[i];
-		if (start) 
-			*start = rstart;
-
 		/* See +/- counts as a sign. */
-		c = cp[i];
-		if ('+' == c || '-' == c || ASCII_HYPH == c)
-			++i;
+		if ('+' == **end || '-' == **end || ASCII_HYPH == **end)
+			(*end)++;
 
-		switch (cp[i++]) {
+		switch (**end) {
 		case ('('):
-			rlim = 2;
+			*start = ++*end;
+			*sz = 2;
 			break;
 		case ('['):
+			*start = ++*end;
 			term = ']';
 			break;
 		case ('\''):
+			*start = ++*end;
 			term = '\'';
 			break;
 		default:
-			rlim = 1;
-			i--;
+			*sz = 1;
 			break;
 		}
 
-		/* See +/- counts as a sign. */
-		c = cp[i];
-		if ('+' == c || '-' == c || ASCII_HYPH == c)
-			++i;
-
 		break;
 
 	/*
 	 * Anything else is assumed to be a glyph.
+	 * In this case, pass back the character after the backslash.
 	 */
 	default:
 		gly = ESCAPE_SPECIAL;
-		rlim = 1;
-		i--;
+		*start = --*end;
+		*sz = 1;
 		break;
 	}
 
 	assert(ESCAPE_ERROR != gly);
 
-	*end = rstart = &cp[i];
-	if (start)
-		*start = rstart;
-
 	/*
 	 * Read up to the terminating character,
 	 * paying attention to nested escapes.
@@ -280,15 +280,13 @@ mandoc_escape(const char **end, const char **start, int *sz)
 				break;
 			}
 		}
-		rlim = (*end)++ - rstart;
+		*sz = (*end)++ - *start;
 	} else {
-		assert(rlim > 0);
-		if ((size_t)rlim > strlen(rstart))
+		assert(*sz > 0);
+		if ((size_t)*sz > strlen(*start))
 			return(ESCAPE_ERROR);
-		*end += rlim;
+		*end += *sz;
 	}
-	if (sz)
-		*sz = rlim;
 
 	/* Run post-processors. */
 
@@ -298,12 +296,13 @@ mandoc_escape(const char **end, const char **start, int *sz)
 		 * Pretend that the constant-width font modes are the
 		 * same as the regular font modes.
 		 */
-		if (2 == rlim && 'C' == *rstart)
-			rstart++;
-		else if (1 != rlim)
+		if (2 == *sz && 'C' == **start) {
+			(*start)++;
+			(*sz)--;
+		} else if (1 != *sz)
 			break;
 
-		switch (*rstart) {
+		switch (**start) {
 		case ('3'):
 			/* FALLTHROUGH */
 		case ('B'):
@@ -325,9 +324,7 @@ mandoc_escape(const char **end, const char **start, int *sz)
 		}
 		break;
 	case (ESCAPE_SPECIAL):
-		if (1 != rlim)
-			break;
-		if ('c' == *rstart)
+		if (1 == *sz && 'c' == **start)
 			gly = ESCAPE_NOSPACE;
 		break;
 	default: