Refactoring in preparation for .rm support:

Unify parsing of names given as roff request arguments into a new
function roff_getname(), which is rather different from the parsing
function for normal arguments, mandoc_getarg(), because names cannot
be quoted and cannot contain whitespace or escaped characters.
The new function now throws an ERROR when finding escaped characters
in a name.
"I'm fine with this." kristaps@

3 files changed, 49 insertions, 40 deletions

diff --git a/usr.bin/mandoc/main.c b/usr.bin/mandoc/main.c
index 6e699387762..682a3b1bb03 100644
--- a/usr.bin/mandoc/main.c
+++ b/usr.bin/mandoc/main.c
@@ -1,4 +1,4 @@
-/*	$Id: main.c,v 1.65 2011/01/09 13:16:48 schwarze Exp $ */
+/*	$Id: main.c,v 1.66 2011/01/10 23:53:32 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
@@ -179,6 +179,7 @@ static	const char * const	mandocerrs[MANDOCERR_MAX] = {
 
 	"input stack limit exceeded, infinite loop?",
 	"skipping bad character",
+	"escaped character not allowed in a name",
 	"skipping text before the first section header",
 	"skipping unknown macro",
 	"NOT IMPLEMENTED: skipping request",
diff --git a/usr.bin/mandoc/mandoc.h b/usr.bin/mandoc/mandoc.h
index fc317069d5e..bb2a7074f12 100644
--- a/usr.bin/mandoc/mandoc.h
+++ b/usr.bin/mandoc/mandoc.h
@@ -1,4 +1,4 @@
-/*	$Id: mandoc.h,v 1.28 2011/01/09 14:30:48 schwarze Exp $ */
+/*	$Id: mandoc.h,v 1.29 2011/01/10 23:53:32 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -116,6 +116,7 @@ enum	mandocerr {
 
 	MANDOCERR_ROFFLOOP, /* input stack limit exceeded, infinite loop? */
 	MANDOCERR_BADCHAR, /* skipping bad character */
+	MANDOCERR_NAMESC, /* escaped character not allowed in a name */
 	MANDOCERR_NOTEXT, /* skipping text before the first section header */
 	MANDOCERR_MACRO, /* skipping unknown macro */
 	MANDOCERR_REQUEST, /* NOT IMPLEMENTED: skipping request */
diff --git a/usr.bin/mandoc/roff.c b/usr.bin/mandoc/roff.c
index f4bc46244b7..7f58211bc55 100644
--- a/usr.bin/mandoc/roff.c
+++ b/usr.bin/mandoc/roff.c
@@ -1,4 +1,4 @@
-/*	$Id: roff.c,v 1.27 2011/01/04 22:28:17 schwarze Exp $ */
+/*	$Id: roff.c,v 1.28 2011/01/10 23:53:32 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>
@@ -130,6 +130,7 @@ static	enum rofferr	 roff_cond_sub(ROFF_ARGS);
 static	enum rofferr	 roff_ds(ROFF_ARGS);
 static	enum roffrule	 roff_evalcond(const char *, int *);
 static	void		 roff_freestr(struct roff *);
+static	char		*roff_getname(struct roff *, char **, int, int);
 static	const char	*roff_getstrn(const struct roff *, 
 				const char *, size_t);
 static	enum rofferr	 roff_line_ignore(ROFF_ARGS);
@@ -1052,25 +1053,13 @@ roff_ds(ROFF_ARGS)
 	 * will have `bar  "     ' as its value.
 	 */
 
-	name = *bufp + pos;
+	string = *bufp + pos;
+	name = roff_getname(r, &string, ln, pos);
 	if ('\0' == *name)
 		return(ROFF_IGN);
 
-	string = name;
-	/* Read until end of name. */
-	while (*string && ' ' != *string)
-		string++;
-
-	/* Nil-terminate name. */
-	if (*string)
-		*(string++) = '\0';
-	
-	/* Read past spaces. */
-	while (*string && ' ' == *string)
-		string++;
-
-	/* Read passed initial double-quote. */
-	if (*string && '"' == *string)
+	/* Read past initial double-quote. */
+	if ('"' == *string)
 		string++;
 
 	/* The rest is the value. */
@@ -1083,31 +1072,14 @@ roff_ds(ROFF_ARGS)
 static enum rofferr
 roff_nr(ROFF_ARGS)
 {
-	const char	*key, *val;
+	const char	*key;
+	char		*val;
 	struct reg	*rg;
 
-	key = &(*bufp)[pos];
+	val = *bufp + pos;
+	key = roff_getname(r, &val, ln, pos);
 	rg = r->regs->regs;
 
-	/* Parse register request. */
-	while ((*bufp)[pos] && ' ' != (*bufp)[pos])
-		pos++;
-
-	/*
-	 * Set our nil terminator.  Because this line is going to be
-	 * ignored anyway, we can munge it as we please.
-	 */
-	if ((*bufp)[pos])
-		(*bufp)[pos++] = '\0';
-
-	/* Skip whitespace to register token. */
-	while ((*bufp)[pos] && ' ' == (*bufp)[pos])
-		pos++;
-
-	val = &(*bufp)[pos];
-
-	/* Process register token. */
-
 	if (0 == strcmp(key, "nS")) {
 		rg[(int)REG_nS].set = 1;
 		if ( ! roff_parse_nat(val, &rg[(int)REG_nS].v.u))
@@ -1246,6 +1218,41 @@ roff_userdef(ROFF_ARGS)
 	   ROFF_REPARSE : ROFF_APPEND);
 }
 
+
+static char *
+roff_getname(struct roff *r, char **cpp, int ln, int pos)
+{
+	char	 *name, *cp;
+
+	name = *cpp;
+	if ('\0' == *name)
+		return(name);
+
+	/* Read until end of name. */
+	for (cp = name; '\0' != *cp && ' ' != *cp; cp++) {
+		if ('\\' != *cp)
+			continue;
+		cp++;
+		if ('\\' == *cp)
+			continue;
+		(*r->msg)(MANDOCERR_NAMESC, r->data, ln, pos, NULL);
+		*cp = '\0';
+		name = cp;
+	}
+
+	/* Nil-terminate name. */
+	if ('\0' != *cp)
+		*(cp++) = '\0';
+
+	/* Read past spaces. */
+	while (' ' == *cp)
+		cp++;
+
+	*cpp = cp;
+	return(name);
+}
+
+
 /*
  * Store *string into the user-defined string called *name.
  * In multiline mode, append to an existing entry and append '\n';