Mostly complete implementation of the 'c' (character available)

roff conditional, except that the .char request still isn't supported
and that behaviour differs from groff in many edge cases.
But at least valid character names and numbers are now distinguished
from invalid ones.
This also fixes the bug that parsing of the 'c' conditional was
incomplete, which resulted in leaking the tested character to the
input parser at the beginning of the body when the condition was
inverted.

3 files changed, 60 insertions, 14 deletions

diff --git a/TODO b/TODO
index 2701a745..efd11431 100644
--- a/TODO
+++ b/TODO
@@ -181,9 +181,6 @@ are mere guesses, and some may be wrong.
   pali dot rohar at gmail dot com 16 Jul 2018 13:03:35 +0200
   loc *  exist ***  algo ***  size **  imp *
 
-- support .ds requests inside tbl(7) code,
-  see tbl(1) for an example
-
 - support mdoc(7) and man(7) macros inside tbl(7) code;
   probably requires the parser reorg and letting tbl(7)
   use roff_node such that macro sets can mix;
@@ -320,9 +317,6 @@ are mere guesses, and some may be wrong.
 * formatting issues: ugly output
 ************************************************************************
 
-- .UR can nest inside .TP,
-  see roff(7) for examples
-
 - revisit empty in-line macros
   look at the difference between "Em x Em ." and "Sq x Em ."
   Carsten Kunze  Fri, 12 Dec 2014 00:15:41 +0100
diff --git a/roff.7 b/roff.7
index 12455f8d..56db5b6e 100644
--- a/roff.7
+++ b/roff.7
@@ -1005,13 +1005,13 @@ is
 or
 .Sq o
 .Pq odd page ,
-it evaluates to true.
+it evaluates to true, and the
+.Ar body
+starts with the next character.
 .It
 If the first character of
 .Ar condition
 is
-.Sq c
-.Pq character available ,
 .Sq e
 .Pq even page ,
 .Sq t
@@ -1019,7 +1019,20 @@ is
 or
 .Sq v
 .Pq vroff mode ,
-it evaluates to false.
+it evaluates to false, and the
+.Ar body
+starts with the next character.
+.It
+If the first character of
+.Ar condition
+is
+.Sq c
+.Pq character available ,
+it evaluates to true if the following character is an ASCII character
+or a valid character escape sequence, or to false otherwise.
+The
+.Ar body
+starts with the character following that next character.
 .It
 If the first character of
 .Ar condition
diff --git a/roff.c b/roff.c
index 05873d89..b393e0a7 100644
--- a/roff.c
+++ b/roff.c
@@ -2168,9 +2168,10 @@ out:
 static int
 roff_evalcond(struct roff *r, int ln, char *v, int *pos)
 {
-	char	*cp, *name;
-	size_t	 sz;
-	int	 deftype, number, savepos, istrue, wanttrue;
+	const char	*start, *end;
+	char		*cp, *name;
+	size_t		 sz;
+	int		 deftype, len, number, savepos, istrue, wanttrue;
 
 	if ('!' == v[*pos]) {
 		wanttrue = 0;
@@ -2185,12 +2186,50 @@ roff_evalcond(struct roff *r, int ln, char *v, int *pos)
 	case 'o':
 		(*pos)++;
 		return wanttrue;
-	case 'c':
 	case 'e':
 	case 't':
 	case 'v':
 		(*pos)++;
 		return !wanttrue;
+	case 'c':
+		do {
+			(*pos)++;
+		} while (v[*pos] == ' ');
+
+		/*
+		 * Quirk for groff compatibility:
+		 * The horizontal tab is neither available nor unavailable.
+		 */
+
+		if (v[*pos] == '\t') {
+			(*pos)++;
+			return 0;
+		}
+
+		/* Printable ASCII characters are available. */
+
+		if (v[*pos] != '\\') {
+			(*pos)++;
+			return wanttrue;
+		}
+
+		end = v + ++*pos;
+		switch (mandoc_escape(&end, &start, &len)) {
+		case ESCAPE_SPECIAL:
+			istrue = mchars_spec2cp(start, len) != -1;
+			break;
+		case ESCAPE_UNICODE:
+			istrue = 1;
+			break;
+		case ESCAPE_NUMBERED:
+			istrue = mchars_num2char(start, len) != -1;
+			break;
+		default:
+			istrue = !wanttrue;
+			break;
+		}
+		*pos = end - v;
+		return istrue == wanttrue;
 	case 'd':
 	case 'r':
 		cp = v + *pos + 1;