diff options
author | Ramsay Jones <ramsay@ramsay1.demon.co.uk> | 2013-05-16 20:41:24 +0100 |
---|---|---|
committer | Christopher Li <sparse@chrisli.org> | 2013-05-17 10:53:08 -0700 |
commit | 0edb7edecdd571c2663eb12acac1b27b9acac657 (patch) | |
tree | 68bebe8beb001786e1d3691c667d4e2fc48e04af | |
parent | 9f97967a950c4a81e071c0f191e59cd8c2c89ed7 (diff) | |
download | sparse-0edb7edecdd571c2663eb12acac1b27b9acac657.tar.gz |
char.c: Fix parsing of escapes
When parsing a string or character constant, the parse_escape()
function returns a pointer to the character at which to resume
parsing. However, in the case of an hex or octal escape, it was
returning a one-past-the-end pointer. Thus, a string like:
char str[3] = "\x61\x62\x63";
was being parsed as:
'\x61', 'x', '6', '2', '\x63'
which, in turn, provokes an 'too long initializer' warning.
Also, fix an off-by-one error in get_char_constant() when setting
the 'end' pointer for a TOKEN_CHAR or TOKEN_WIDE_CHAR. Despite the
name, the string->length of the token is actually the size of the
allocated memory (ie len+1), so we need to compensate by using
'token->string->length - 1'.
Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk>
Signed-off-by: Christopher Li <sparse@chrisli.org>
-rw-r--r-- | char.c | 9 | ||||
-rw-r--r-- | validation/escapes.c | 12 |
2 files changed, 18 insertions, 3 deletions
@@ -27,9 +27,10 @@ static const char *parse_escape(const char *p, unsigned *val, const char *end, i case 'x': { unsigned mask = -(1U << (bits - 4)); for (c = 0; p < end; c = (c << 4) + d) { - d = hexval(*p++); + d = hexval(*p); if (d > 16) break; + p++; if (c & mask) { warning(pos, "hex escape sequence out of range"); @@ -42,8 +43,10 @@ static const char *parse_escape(const char *p, unsigned *val, const char *end, i if (p + 2 < end) end = p + 2; c -= '0'; - while (p < end && (d = *p++ - '0') < 8) + while (p < end && (d = *p - '0') < 8) { c = (c << 3) + d; + p++; + } if ((c & 0400) && bits < 9) warning(pos, "octal escape sequence out of range"); @@ -65,7 +68,7 @@ void get_char_constant(struct token *token, unsigned long long *val) case TOKEN_CHAR: case TOKEN_WIDE_CHAR: p = token->string->data; - end = p + token->string->length; + end = p + token->string->length - 1; break; case TOKEN_CHAR_EMBEDDED_0 ... TOKEN_CHAR_EMBEDDED_3: end = p + type - TOKEN_CHAR; diff --git a/validation/escapes.c b/validation/escapes.c index 4a1b030e..5f526b9c 100644 --- a/validation/escapes.c +++ b/validation/escapes.c @@ -4,6 +4,16 @@ static int e[] = { '\'', '\"', '\?', '\\', static char *s = "\'\"\?\\ \a\b\f\n\r\t\v \377\xcafe"; static int bad_e[] = { '\c', '\0123', '\789', '\xdefg' }; + +static char a_hex[3] = "\x61\x62\x63"; +static char b_hex[3] = "\x61\x62\x63\x64"; +static char c_hex[3] = "\x61\x62"; +static char d_hex[3] = "\x61"; + +static char a_oct[3] = "\141\142\143"; +static char b_oct[3] = "\141\142\143\144"; +static char c_oct[3] = "\141\142"; +static char d_oct[3] = "\141"; /* * check-name: Character escape sequences * @@ -16,5 +26,7 @@ escapes.c:6:30: warning: multi-character character constant escapes.c:6:39: warning: multi-character character constant escapes.c:6:47: warning: hex escape sequence out of range escapes.c:6:47: warning: multi-character character constant +escapes.c:9:24: warning: too long initializer-string for array of char +escapes.c:14:24: warning: too long initializer-string for array of char * check-error-end */ |