[PATCH] uniform parsing of names in libroff

[Ingo Schwarze <schwarze@usta.de>]

Hi,

i just started to implement .rm (remove macro) in libroff,
then realized that i would be introducing the third place
where names (that is, to be precise, roff macro and string names)
get parsed.

The following patch moves this parsing into its own function,
to be soon reused by roff_rm().

I put that function roff_getname() in libroff (and not in
libmandoc) because i do not expect any macro package to deal
with that kind of low-level stuff.

The interface is similar to mandoc_getarg(), but much simpler,
because quotes count as normal characters in this context,
space characters cannot be escaped, and backslashes are only
allowed in pairs.  Yes, parsing of names has its own rules,
and they are quite different from the rules for parsing of
arguments.  See, this is roff, right?

As a bonus:
 - Both roff_ds and roff_nr become much shorter.
 - We get an ERROR when there are escapes in a name.

OK?

Yours,
  Ingo

P.S.
Maybe we can use this for roff_block() as well, but that is not
as straighforward, so i haven't done it right away.


Index: main.c
===================================================================
RCS file: /cvs/src/usr.bin/mandoc/main.c,v
retrieving revision 1.65
diff -u -p -r1.65 main.c
--- main.c	9 Jan 2011 13:16:48 -0000	1.65
+++ main.c	10 Jan 2011 22:29:54 -0000
@@ -179,6 +179,7 @@ static	const char * const	mandocerrs[MAN
 
 	"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",
Index: mandoc.h
===================================================================
RCS file: /cvs/src/usr.bin/mandoc/mandoc.h,v
retrieving revision 1.28
diff -u -p -r1.28 mandoc.h
--- mandoc.h	9 Jan 2011 14:30:48 -0000	1.28
+++ mandoc.h	10 Jan 2011 22:29:54 -0000
@@ -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 */
Index: roff.c
===================================================================
RCS file: /cvs/src/usr.bin/mandoc/roff.c,v
retrieving revision 1.27
diff -u -p -r1.27 roff.c
--- roff.c	4 Jan 2011 22:28:17 -0000	1.27
+++ roff.c	10 Jan 2011 22:29:54 -0000
@@ -130,6 +130,7 @@ static	enum rofferr	 roff_cond_sub(ROFF_
 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))
@@ -1245,6 +1217,41 @@ roff_userdef(ROFF_ARGS)
 	return(*szp > 1 && '\n' == (*bufp)[(int)*szp - 2] ?
 	   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.

--
 To unsubscribe send an email to tech+unsubscribe@mdocml.bsd.lv