Skip to content

Use ZSTR_IS_VALID_UTF8 where possible #12869

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 5, 2023
Merged

Use ZSTR_IS_VALID_UTF8 where possible #12869

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions ext/mbstring/mbstring.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1815,7 +1815,7 @@ static size_t mb_get_strlen(zend_string *string, const mbfl_encoding *encoding)
unsigned int char_len = encoding->flag & (MBFL_ENCTYPE_SBCS | MBFL_ENCTYPE_WCS2 | MBFL_ENCTYPE_WCS4);
if (char_len) {
return ZSTR_LEN(string) / char_len;
} else if (php_mb_is_no_encoding_utf8(encoding->no_encoding) && GC_FLAGS(string) & IS_STR_VALID_UTF8) {
} else if (php_mb_is_no_encoding_utf8(encoding->no_encoding) && ZSTR_IS_VALID_UTF8(string)) {
return mb_fast_strlen_utf8((unsigned char*)ZSTR_VAL(string), ZSTR_LEN(string));
}

Expand Down Expand Up @@ -2264,7 +2264,7 @@ PHP_FUNCTION(mb_substr_count)
if (php_mb_is_no_encoding_utf8(enc->no_encoding)) {
/* No need to do any conversion if haystack/needle are already known-valid UTF-8
* (If they are not valid, then not passing them through conversion filters could affect output) */
if (GC_FLAGS(haystack) & IS_STR_VALID_UTF8) {
if (ZSTR_IS_VALID_UTF8(haystack)) {
haystack_u8 = haystack;
} else {
unsigned int num_errors = 0;
Expand All @@ -2274,7 +2274,7 @@ PHP_FUNCTION(mb_substr_count)
}
}

if (GC_FLAGS(needle) & IS_STR_VALID_UTF8) {
if (ZSTR_IS_VALID_UTF8(needle)) {
needle_u8 = needle;
} else {
unsigned int num_errors = 0;
Expand Down Expand Up @@ -3426,7 +3426,7 @@ PHP_FUNCTION(mb_detect_encoding)
strict = MBSTRG(strict_detection);
}

if (size == 1 && *elist == &mbfl_encoding_utf8 && (GC_FLAGS(str) & IS_STR_VALID_UTF8)) {
if (size == 1 && *elist == &mbfl_encoding_utf8 && ZSTR_IS_VALID_UTF8(str)) {
ret = &mbfl_encoding_utf8;
} else {
ret = mb_guess_encoding((unsigned char*)ZSTR_VAL(str), ZSTR_LEN(str), elist, size, strict, order_significant);
Expand Down Expand Up @@ -5496,7 +5496,7 @@ static bool mb_fast_check_utf8_avx2(zend_string *str)
static bool mb_check_str_encoding(zend_string *str, const mbfl_encoding *encoding)
{
if (encoding == &mbfl_encoding_utf8) {
if (GC_FLAGS(str) & IS_STR_VALID_UTF8) {
if (ZSTR_IS_VALID_UTF8(str)) {
return true;
}
bool result = mb_fast_check_utf8(str);
Expand Down Expand Up @@ -5889,7 +5889,7 @@ PHP_FUNCTION(mb_scrub)
RETURN_THROWS();
}

if (enc == &mbfl_encoding_utf8 && (GC_FLAGS(str) & IS_STR_VALID_UTF8)) {
if (enc == &mbfl_encoding_utf8 && ZSTR_IS_VALID_UTF8(str)) {
/* A valid UTF-8 string will not be changed by mb_scrub; so just increment the refcount and return it */
RETURN_STR_COPY(str);
}
Expand Down
2 changes: 1 addition & 1 deletion ext/pcre/php_pcre.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1112,7 +1112,7 @@ static void php_do_pcre_match(INTERNAL_FUNCTION_PARAMETERS, int global) /* {{{ *

static zend_always_inline bool is_known_valid_utf8(
zend_string *subject_str, PCRE2_SIZE start_offset) {
if (!(GC_FLAGS(subject_str) & IS_STR_VALID_UTF8)) {
if (!ZSTR_IS_VALID_UTF8(subject_str)) {
/* We don't know whether the string is valid UTF-8 or not. */
return 0;
}
Expand Down