diff options
Diffstat (limited to 'src/lib/string/util_string.c')
-rw-r--r-- | src/lib/string/util_string.c | 56 |
1 files changed, 34 insertions, 22 deletions
diff --git a/src/lib/string/util_string.c b/src/lib/string/util_string.c index f934f66f02..c8f12d780e 100644 --- a/src/lib/string/util_string.c +++ b/src/lib/string/util_string.c @@ -1,6 +1,6 @@ /* Copyright (c) 2003-2004, Roger Dingledine * Copyright (c) 2004-2006, Roger Dingledine, Nick Mathewson. - * Copyright (c) 2007-2019, The Tor Project, Inc. */ + * Copyright (c) 2007-2020, The Tor Project, Inc. */ /* See LICENSE for licensing information */ /** @@ -71,7 +71,7 @@ tor_memstr(const void *haystack, size_t hlen, const char *needle) /** Return true iff the 'len' bytes at 'mem' are all zero. */ int -tor_mem_is_zero(const char *mem, size_t len) +fast_mem_is_zero(const char *mem, size_t len) { static const char ZERO[] = { 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, @@ -95,17 +95,14 @@ tor_mem_is_zero(const char *mem, size_t len) int tor_digest_is_zero(const char *digest) { - static const uint8_t ZERO_DIGEST[] = { - 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0 - }; - return tor_memeq(digest, ZERO_DIGEST, DIGEST_LEN); + return safe_mem_is_zero(digest, DIGEST_LEN); } /** Return true iff the DIGEST256_LEN bytes in digest are all zero. */ int tor_digest256_is_zero(const char *digest) { - return tor_mem_is_zero(digest, DIGEST256_LEN); + return safe_mem_is_zero(digest, DIGEST256_LEN); } /** Remove from the string <b>s</b> every character which appears in @@ -212,21 +209,6 @@ strcmpstart(const char *s1, const char *s2) return strncmp(s1, s2, n); } -/** Compare the s1_len-byte string <b>s1</b> with <b>s2</b>, - * without depending on a terminating nul in s1. Sorting order is first by - * length, then lexically; return values are as for strcmp. - */ -int -strcmp_len(const char *s1, const char *s2, size_t s1_len) -{ - size_t s2_len = strlen(s2); - if (s1_len < s2_len) - return -1; - if (s1_len > s2_len) - return 1; - return fast_memcmp(s1, s2, s2_len); -} - /** Compares the first strlen(s2) characters of s1 with s2. Returns as for * strcasecmp. */ @@ -524,6 +506,23 @@ validate_char(const uint8_t *c, uint8_t len) int string_is_utf8(const char *str, size_t len) { + // If str is NULL, don't try to read it + if (!str) { + // We could test for this case, but the low-level logs would produce + // confusing test output. + // LCOV_EXCL_START + if (len) { + // Use the low-level logging function, so that the log module can + // validate UTF-8 (if needed in future code) + tor_log_err_sigsafe( + "BUG: string_is_utf8() called with NULL str but non-zero len."); + // Since it's a bug, we should probably reject this string + return false; + } + // LCOV_EXCL_STOP + return true; + } + for (size_t i = 0; i < len;) { uint8_t num_bytes = bytes_in_char(str[i]); if (num_bytes == 0) // Invalid leading byte found. @@ -541,3 +540,16 @@ string_is_utf8(const char *str, size_t len) } return true; } + +/** As string_is_utf8(), but returns false if the string begins with a UTF-8 + * byte order mark (BOM). + */ +int +string_is_utf8_no_bom(const char *str, size_t len) +{ + if (str && len >= 3 && (!strcmpstart(str, "\uFEFF") || + !strcmpstart(str, "\uFFFE"))) { + return false; + } + return string_is_utf8(str, len); +} |