mdocml: Refactoring in preparation for .rm support: Unify parsing of

mdocml: Refactoring in preparation for .rm support: Unify parsing of

[schwarze]

Log Message:
-----------
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@

Modified Files:
--------------
    mdocml:
        main.c
        mandoc.h
        roff.c

Revision Data
-------------
Index: mandoc.h
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/mandoc.h,v
retrieving revision 1.51
retrieving revision 1.52
diff -Lmandoc.h -Lmandoc.h -u -p -r1.51 -r1.52
--- mandoc.h
+++ mandoc.h
@@ -114,6 +114,7 @@ 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: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/roff.c,v
retrieving revision 1.120
retrieving revision 1.121
diff -Lroff.c -Lroff.c -u -p -r1.120 -r1.121
--- roff.c
+++ roff.c
@@ -134,6 +134,7 @@ 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);
@@ -520,7 +521,7 @@ roff_endparse(struct roff *r)
 {
 
 	if (r->last)
-		(*r->msg)(MANDOCERR_SCOPEEXIT, r->data, 
+		(*r->msg)(MANDOCERR_SCOPEEXIT, r->data,
 				r->last->line, r->last->col, NULL);
 
 	if (r->tbl) {
@@ -1056,25 +1057,13 @@ 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. */
@@ -1087,31 +1076,14 @@ 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))
@@ -1249,6 +1221,41 @@ 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.
Index: main.c
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/main.c,v
retrieving revision 1.136
retrieving revision 1.137
diff -Lmain.c -Lmain.c -u -p -r1.136 -r1.137
--- main.c
+++ main.c
@@ -192,6 +192,7 @@ 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",
--
 To unsubscribe send an email to source+unsubscribe@mdocml.bsd.lv