[PATCH v4] sscanf: implement basic character sets

[Jessica Yu]

Implement basic character sets for the '%[' conversion specifier.

The '%[' conversion specifier matches a nonempty sequence of characters
from the specified set of accepted (or with '^', rejected) characters
between the brackets. The substring matched is to be made up of characters
in (or not in) the set. This is useful for matching substrings that are
delimited by something other than spaces.

This implementation differs from its glibc counterpart in the following ways:
(1) No support for character ranges (e.g., 'a-z' or '0-9')
(2) The hyphen '-' is not a special character
(3) The closing bracket ']' cannot be matched
(4) No support (yet) for discarding matching input ('%*[')

Signed-off-by: Jessica Yu <jeyu@xxxxxxxxxx>
---
Patch based on linux-next-20160226.

v4:
 - To avoid allocations (i.e. kstrndup), use a bitmap to represent
   the character set (suggested by Rasmus Villemoes)
 - Add a comment to document non-glibc behavior and provide example usage
 - Check for '[' in the '*' (discard) case. Since it is not supported
   yet, it is considered malformed input

v3:
 - Fix memory leak in error path (kfree() before returning)
 - Remove redundant condition in while loop
 - Style fix (*op)() -> op()

v2:
 - Use kstrndup() to copy the character set from fmt instead of using a
   statically allocated array

 lib/vsprintf.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 525c8e1..9a3b860 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2640,8 +2640,12 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 		if (*fmt == '*') {
 			if (!*str)
 				break;
-			while (!isspace(*fmt) && *fmt != '%' && *fmt)
+			while (!isspace(*fmt) && *fmt != '%' && *fmt) {
+				/* '%*[' not yet supported, invalid format */
+				if (*fmt == '[')
+					return num;
 				fmt++;
+			}
 			while (!isspace(*str) && *str)
 				str++;
 			continue;
@@ -2714,6 +2718,57 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 			num++;
 		}
 		continue;
+		/*
+		 * Warning: This implementation of the '[' conversion specifier
+		 * deviates from its glibc counterpart in the following ways:
+		 * (1) It does NOT support ranges i.e. '-' is NOT a special character
+		 * (2) It cannot match the closing bracket ']' itself
+		 * (3) A field width is required
+		 * (4) '%*[' (discard matching input) is currently not supported
+		 *
+		 * Example usage:
+		 * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", buf1, buf2, buf3);
+		 * if (ret < 3)
+		 *    // etc..
+		 */
+		case '[':
+		{
+			char *s = (char *)va_arg(args, char *);
+			DECLARE_BITMAP(set, 256) = {0};
+			unsigned int len = 0;
+			bool negate = (*fmt == '^');
+
+			/* field width is required */
+			if (field_width == -1)
+				return num;
+
+			if (negate)
+				++fmt;
+
+			for ( ; *fmt && *fmt != ']'; ++fmt, ++len)
+				set_bit((u8)*fmt, set);
+
+			/* no ']' or no character set found */
+			if (!*fmt || !len)
+				return num;
+			++fmt;
+
+			if (negate) {
+				bitmap_complement(set, set, 256);
+				/* exclude null '\0' byte */
+				clear_bit(0, set);
+			}
+
+			/* match must be non-empty */
+			if (!test_bit((u8)*str, set))
+				return num;
+
+			while (test_bit((u8)*str, set) && field_width--)
+				*s++ = *str++;
+			*s = '\0';
+			++num;
+		}
+		continue;
 		case 'o':
 			base = 8;
 			break;
-- 
2.4.3