Skip to content

Improve performance of unpack() with nameless repetitions #18803

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 3 commits into from
Jun 10, 2025
Merged

Improve performance of unpack() with nameless repetitions #18803

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7508f8b
Improve performance of unpack() with nameless repetitions
nielsdos Jun 8, 2025
366e527
fix null deref
nielsdos Jun 9, 2025
e192e7c
swap condition
nielsdos Jun 10, 2025
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
2 changes: 2 additions & 0 deletions UPGRADING
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -567,6 +567,8 @@ MBString:
. Improved performance of array functions with callbacks
(array_find, array_filter, array_map, usort, ...).
. Improved performance of urlencode() and rawurlencode().
. Improved unpack() performance with nameless repetitions by avoiding
creating temporary strings and reparsing them.

- XMLReader:
. Improved property access performance.
Expand Down
40 changes: 21 additions & 19 deletions ext/standard/pack.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -885,12 +885,15 @@ PHP_FUNCTION(unpack)
if ((inputpos + size) <= inputlen) {

zend_string* real_name;
zend_long long_key = 0;
zval val;

if (repetitions == 1 && namelen > 0) {
if (namelen == 0) {
real_name = NULL;
long_key = i + 1;
} else if (repetitions == 1) {
/* Use a part of the formatarg argument directly as the name. */
real_name = zend_string_init_fast(name, namelen);

} else {
/* Need to add the 1-based element number to the name */
char buf[MAX_LENGTH_OF_LONG + 1];
Expand All @@ -912,7 +915,6 @@ PHP_FUNCTION(unpack)
size = len;

ZVAL_STRINGL(&val, &input[inputpos], len);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}
case 'A': {
Expand All @@ -939,7 +941,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_STRINGL(&val, &input[inputpos], len + 1);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}
/* New option added for Z to remain in-line with the Perl implementation */
Expand All @@ -964,7 +965,6 @@ PHP_FUNCTION(unpack)
len = s;

ZVAL_STRINGL(&val, &input[inputpos], len);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -979,7 +979,9 @@ PHP_FUNCTION(unpack)


if (size > INT_MAX / 2) {
zend_string_release(real_name);
if (real_name) {
zend_string_release_ex(real_name, false);
}
zend_argument_value_error(1, "repeater must be less than or equal to %d", INT_MAX / 2);
RETURN_THROWS();
}
Expand Down Expand Up @@ -1016,7 +1018,6 @@ PHP_FUNCTION(unpack)
ZSTR_VAL(buf)[len] = '\0';

ZVAL_STR(&val, buf);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -1026,7 +1027,6 @@ PHP_FUNCTION(unpack)
zend_long v = (type == 'c') ? (int8_t) x : x;

ZVAL_LONG(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -1046,7 +1046,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_LONG(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -1062,7 +1061,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_LONG(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -1082,8 +1080,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_LONG(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);

break;
}

Expand All @@ -1104,7 +1100,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_LONG(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}
#endif
Expand All @@ -1124,7 +1119,6 @@ PHP_FUNCTION(unpack)
}

ZVAL_DOUBLE(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

Expand All @@ -1143,13 +1137,12 @@ PHP_FUNCTION(unpack)
}

ZVAL_DOUBLE(&val, v);
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
break;
}

case 'x':
/* Do nothing with input, just skip it */
break;
goto no_output;

case 'X':
if (inputpos < size) {
Expand All @@ -1160,7 +1153,7 @@ PHP_FUNCTION(unpack)
php_error_docref(NULL, E_WARNING, "Type %c: outside of string", type);
}
}
break;
goto no_output;

case '@':
if (repetitions <= inputlen) {
Expand All @@ -1170,10 +1163,19 @@ PHP_FUNCTION(unpack)
}

i = repetitions - 1; /* Done, break out of for loop */
break;
goto no_output;
}

zend_string_release(real_name);
if (real_name) {
zend_symtable_update(Z_ARRVAL_P(return_value), real_name, &val);
} else {
zend_hash_index_update(Z_ARRVAL_P(return_value), long_key, &val);
}

no_output:
if (real_name) {
zend_string_release_ex(real_name, false);
}

inputpos += size;
if (inputpos < 0) {
Expand Down