From 25b3370cfddc9570c187930c3b6296ffc4b7d356 Mon Sep 17 00:00:00 2001
From: Conrad Meyer <cem@FreeBSD.org>
Date: Mon, 9 Sep 2019 16:32:23 +0000
Subject: [PATCH] ddb(4): Add some support for lexing IPv6 addresses

Allow commands to specify that (hex) numbers may start with A-F, by adding
the DRT_HEX flag for db_read_token_flags().  As before, numbers containing
invalid digits for the current radix are rejected.

Also, lex ':' and '::' tokens as tCOLON and tCOLONCOLON respectively.

There is a mild conflict here with lexed "identifiers" (tIDENT): ddb
identifiers may contain arbitrary colons, and the ddb lexer is greedy.  So
the identifier lex will swallow any colons it finds inside identifiers, and
consumers are still unable to expect the token sequence 'tIDENT tCOLON'.
That limitation does not matter for IPv6 addresses, because the lexer always
attempts to lex numbers before identifiers.

Reviewed by:	markj
Differential Revision:	https://reviews.freebsd.org/D21509
---
 sys/ddb/db_lex.c | 16 +++++++++++++---
 sys/ddb/db_lex.h | 13 ++++++++++++-
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/sys/ddb/db_lex.c b/sys/ddb/db_lex.c
index 5b81652bc1f1..457790ee8605 100644
--- a/sys/ddb/db_lex.c
+++ b/sys/ddb/db_lex.c
@@ -163,7 +163,7 @@ static int
 db_lex(int flags)
 {
 	int	c, n, radix_mode;
-	bool	lex_wspace;
+	bool	lex_wspace, lex_hex_numbers;
 
 	switch (flags & DRT_RADIX_MASK) {
 	case DRT_DEFAULT_RADIX:
@@ -181,6 +181,7 @@ db_lex(int flags)
 	}
 
 	lex_wspace = ((flags & DRT_WSPACE) != 0);
+	lex_hex_numbers = ((flags & DRT_HEX) != 0);
 
 	c = db_read_char();
 	for (n = 0; c <= ' ' || c > '~'; n++) {
@@ -193,13 +194,16 @@ db_lex(int flags)
 	    return (tWSPACE);
 	}
 
-	if (c >= '0' && c <= '9') {
+	if ((c >= '0' && c <= '9') ||
+	   (lex_hex_numbers &&
+	   ((c >= 'a' && c <= 'f') ||
+	   (c >= 'A' && c <= 'F')))) {
 	    /* number */
 	    int	r, digit = 0;
 
 	    if (radix_mode != -1)
 		r = radix_mode;
-	    else if (c > '0')
+	    else if (c != '0')
 		r = db_radix;
 	    else {
 		c = db_read_char();
@@ -328,6 +332,12 @@ db_lex(int flags)
 		}
 		db_unread_char(c);
 		return (tEXCL);
+	    case ':':
+		c = db_read_char();
+		if (c == ':')
+			return (tCOLONCOLON);
+		db_unread_char(c);
+		return (tCOLON);
 	    case ';':
 		return (tSEMI);
 	    case '&':
diff --git a/sys/ddb/db_lex.h b/sys/ddb/db_lex.h
index 3dbb42575533..772e71b39a40 100644
--- a/sys/ddb/db_lex.h
+++ b/sys/ddb/db_lex.h
@@ -58,17 +58,26 @@ enum {
 /*
  * Flag bit powers of two for db_read_token_flags.
  * The low 2 bits are reserved for radix selection.
+ *
+ * WSPACE: Yield explicit tWSPACE tokens when one or more whitespace characters
+ *         is consumed.
+ * HEX:    Allow tNUMBER tokens to start with 'A'-'F' without explicit "0x"
+ *         prefix.
  */
 enum {
 	_DRT_WSPACE = 2,
+	_DRT_HEX,
 };
 #ifndef BIT
 #define	BIT(n)	(1ull << (n))
 #endif
 enum {
 	DRT_WSPACE = BIT(_DRT_WSPACE),
+	DRT_HEX = BIT(_DRT_HEX),
 };
-#define	DRT_VALID_FLAGS_MASK	((int)DRT_RADIX_MASK | DRT_WSPACE)
+#define	DRT_VALID_FLAGS_MASK	((int)DRT_RADIX_MASK | \
+    DRT_WSPACE | \
+    DRT_HEX)
 
 void	 db_flush_lex(void);
 char	*db_get_line(void);
@@ -123,5 +132,7 @@ extern char	db_tok_string[TOK_STRING_SIZE];
 #define	tQUESTION	33
 #define	tBIT_NOT	34
 #define	tWSPACE		35
+#define	tCOLON		36
+#define	tCOLONCOLON	37
 
 #endif /* !_DDB_DB_LEX_H_ */