mandoc: Rudimentary implementation of the \A escape sequence, following

mandoc: Rudimentary implementation of the \A escape sequence, following

[schwarze]

Log Message:
-----------
Rudimentary implementation of the \A escape sequence, following groff 
semantics (test identifier for syntactical validity), not at all 
following the completely unrelated Heirloom semantics (define 
hyperlink target position).

The main motivation for providing this implementation is to get \A 
into the parsing class ESCAPE_EXPAND that corresponds to groff parsing
behaviour, which is quite similar to the \B escape sequence (test
numerical expression for syntactical validity).  This is likely
to improve parsing of nested escape sequences in the future.

Validation isn't perfect yet.  In particular, this implementation
rejects \A arguments containing some escape sequences that groff
allows to slip through.  But that is unlikely to cause trouble even 
in documents using \A for non-trivial purposes.  Rejecting the nested
escapes in question might even improve robustnest because the rejected 
names are unlikely to really be usable for practical purposes - no   
matter that groff dubiously considers them syntactically valid.

Modified Files:
--------------
    mandoc:
        roff.c
        roff_escape.c
        roff.7

Revision Data
-------------
Index: roff.7
===================================================================
RCS file: /home/cvs/mandoc/mandoc/roff.7,v
retrieving revision 1.119
retrieving revision 1.120
diff -Lroff.7 -Lroff.7 -u -p -r1.119 -r1.120
--- roff.7
+++ roff.7
@@ -2021,8 +2021,23 @@ End conditional input; see
 Paddable non-breaking space character.
 .It Ic \e0
 Digit width space character.
-.It Ic \eA\(aq Ns Ar string Ns Ic \(aq
-Anchor definition; ignored by
+.It Ic \eA\(aq Ns Ar name Ns Ic \(aq
+Interpolate
+.Sq 1
+if
+.Ar name
+is a syntactically valid identifier that can be used
+as a name for a macro or user-defined string, or
+.Sq 0
+otherwise.
+This is a thoroughly non-portable groff extension.
+Heirloom troff uses the same escape sequence with the same syntax
+for a completely different purpose,
+defining a hyperlink target position, also called an
+.Dq anchor ,
+with the given
+.Ar name .
+The Heirloom semantics is not supported by
 .Xr mandoc 1 .
 .It Ic \ea
 Leader character; ignored by
Index: roff.c
===================================================================
RCS file: /home/cvs/mandoc/mandoc/roff.c,v
retrieving revision 1.390
retrieving revision 1.391
diff -Lroff.c -Lroff.c -u -p -r1.390 -r1.391
--- roff.c
+++ roff.c
@@ -1520,6 +1520,11 @@ roff_expand(struct roff *r, struct buf *
 					*dst++ = '"';
 			}
 			continue;
+		case 'A':
+			ubuf[0] = iendarg > iarg ? '1' : '0';
+			ubuf[1] = '\0';
+			res = ubuf;
+			break;
 		case 'B':
 			npos = 0;
 			ubuf[0] = iendarg > iarg && iend > iendarg &&
Index: roff_escape.c
===================================================================
RCS file: /home/cvs/mandoc/mandoc/roff_escape.c,v
retrieving revision 1.4
retrieving revision 1.5
diff -Lroff_escape.c -Lroff_escape.c -u -p -r1.4 -r1.5
--- roff_escape.c
+++ roff_escape.c
@@ -73,6 +73,7 @@ roff_escape(const char *buf, const int l
 	int		 maxl;		/* expected length of the argument */
 	int		 argl;		/* actual length of the argument */
 	int		 c, i;		/* for \[char...] parsing */
+	int 		 valid_A;	/* for \A parsing */
 	enum mandoc_esc	 rval;		/* return value */
 	enum mandocerr	 err;		/* diagnostic code */
 	char		 esc_name;
@@ -181,12 +182,12 @@ roff_escape(const char *buf, const int l
 
 	/* Quoted arguments */
 
+	case 'A':
 	case 'B':
 	case 'w':
 		rval = ESCAPE_EXPAND;
 		term = '\b';
 		break;
-	case 'A':
 	case 'D':
 	case 'H':
 	case 'L':
@@ -301,6 +302,7 @@ roff_escape(const char *buf, const int l
 
 	/* Advance to the end of the argument. */
 
+	valid_A = 1;
 	iendarg = iarg;
 	while (maxl > 0) {
 		if (buf[iendarg] == '\0') {
@@ -319,11 +321,20 @@ roff_escape(const char *buf, const int l
 			break;
 		}
 		if (buf[iendarg] == buf[iesc]) {
-			if (roff_escape(buf, ln, iendarg,
-			    &sesc, &sarg, &sendarg, &send) == ESCAPE_EXPAND)
+			switch (roff_escape(buf, ln, iendarg,
+			    &sesc, &sarg, &sendarg, &send)) {
+			case ESCAPE_EXPAND:
 				goto out_sub;
+			case ESCAPE_UNDEF:
+				break;
+			default:
+				valid_A = 0;
+				break;
+			}
 			iendarg = iend = send;
 		} else {
+			if (buf[iendarg] == ' ' || buf[iendarg] == '\t')
+				valid_A = 0;
 			if (maxl != INT_MAX)
 				maxl--;
 			iend = ++iendarg;
@@ -341,6 +352,10 @@ roff_escape(const char *buf, const int l
 		if (resc == NULL && argl == 2 &&
 		    buf[iarg] == '.' && buf[iarg + 1] == 'T')
 			rval = ESCAPE_DEVICE;
+		break;
+	case 'A':
+		if (valid_A == 0)
+			iendarg = iarg;
 		break;
 	case 'O':
 		switch (buf[iarg]) {
--
 To unsubscribe send an email to source+unsubscribe@mandoc.bsd.lv