Handle output encoding for unicode, numbered and named escape sequences

in one common, safe way instead of three different ways.  In particular,
* skip NUL, it is used to mean "no output desired"
* deny 0x01-0x1F and 0x7F-0x9F, print REPLACEMENT CHARACTER instead
* print 0x20-0x7E literally or name-encoded, as required
* print characters above 0x9F numerically

1 files changed, 11 insertions, 23 deletions

diff --git a/usr.bin/mandoc/html.c b/usr.bin/mandoc/html.c
index 47c59297012..a0c2f20eaae 100644
--- a/usr.bin/mandoc/html.c
+++ b/usr.bin/mandoc/html.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: html.c,v 1.48 2014/10/27 13:29:30 schwarze Exp $ */
+/*	$OpenBSD: html.c,v 1.49 2014/10/27 16:28:30 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -435,40 +435,28 @@ print_encode(struct html *h, const char *p, int norecurse)
 		case ESCAPE_UNICODE:
 			/* Skip past "u" header. */
 			c = mchars_num2uc(seq + 1, len - 1);
-
-			/*
-			 * XXX Security warning:
-			 * For now, forbid Unicode obfuscation of ASCII
-			 * characters.  An audit of the callers is
-			 * required before this can be removed.
-			 */
-
-			if (c < 0x80)
-				c = 0xFFFD;
-
-			printf("&#x%x;", c);
 			break;
 		case ESCAPE_NUMBERED:
 			c = mchars_num2char(seq, len);
-			if ( ! ('\0' == c || print_escape(c)))
-				putchar(c);
 			break;
 		case ESCAPE_SPECIAL:
 			c = mchars_spec2cp(h->symtab, seq, len);
-			if (c <= 0)
-				break;
-			if (c < 0x20 || c > 0x7e)
-				printf("&#%d;", c);
-			else if ( ! print_escape(c))
-				putchar(c);
 			break;
 		case ESCAPE_NOSPACE:
 			if ('\0' == *p)
 				nospace = 1;
-			break;
+			continue;
 		default:
-			break;
+			continue;
 		}
+		if (c <= 0)
+			continue;
+		if (c < 0x20 || (c > 0x7E && c < 0xA0))
+			c = 0xFFFD;
+		if (c > 0x7E)
+			printf("&#%d;", c);
+		else if ( ! print_escape(c))
+			putchar(c);
 	}
 
 	return(nospace);