Skip to content

[RFC] Add RFC 3986 and WHATWG compliant URL parsing support #14461

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

Open
wants to merge 26 commits into
base: master
Choose a base branch
from
Open

[RFC] Add RFC 3986 and WHATWG compliant URL parsing support #14461

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
196957b
Create separate lexbor extension
kocsismate May 11, 2025
0334e22
Add RFC 3986 and WHATWG compliant URL parsing support
kocsismate Jun 3, 2024
a09a457
Serialization
kocsismate Oct 22, 2024
3abdb0a
Improve error handling
kocsismate Oct 26, 2024
1445e55
Lot of fixes and added support for equalsTo()
kocsismate Nov 11, 2024
e4de160
Add normalization support
kocsismate Nov 13, 2024
77184ce
SOAP test fixes
kocsismate Nov 13, 2024
3b0449d
Fix some memory leaks
kocsismate Nov 13, 2024
5f90823
Some cleanups
kocsismate Nov 18, 2024
b7011b8
Changes based on discussion
kocsismate Nov 30, 2024
f20842a
Removal of Uri\Uri
kocsismate Dec 30, 2024
c88e92b
A lot of fixes and API changes
kocsismate Jan 6, 2025
c743ead
Updates
kocsismate Feb 5, 2025
19b7180
Add new tests, path fixes
kocsismate Feb 9, 2025
fb0c929
Add more tests for verifying the behavior of withers
kocsismate Feb 15, 2025
cf7ca4e
Fix code review comments
kocsismate Feb 19, 2025
9de1271
A few fixes and improvements after feedback
kocsismate Apr 14, 2025
db3b79d
Test fixes
kocsismate Apr 14, 2025
feefccf
Remove WHATWG non-raw getters
kocsismate Apr 18, 2025
190bbfd
Rename WHATWG getters again
kocsismate Apr 26, 2025
d1df694
Add UriComparisonMode
kocsismate Apr 28, 2025
0d1fc02
Expose $softErrors for Uri\WhatWg\Url::resolve()
kocsismate Apr 30, 2025
df1d0b9
Add SensitiveParameter support
kocsismate May 3, 2025
e8261f7
Proper build support
kocsismate May 19, 2025
7530dd9
Review fixes and serialization update according to the RFC
kocsismate May 20, 2025
b75cc5b
Some extension fixes
kocsismate May 25, 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
Prev Previous commit
Next Next commit
Fix some memory leaks
  • Loading branch information
@kocsismate
kocsismate committed May 25, 2025
commit 3b0449de02cc8d2c948c79429a21f7703921c1bd
1 change: 1 addition & 0 deletions ext/soap/php_http.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -478,6 +478,7 @@ int make_http_soap_request(zval *this_ptr,
use_ssl = 1;
} else if (phpurl->scheme == NULL || !zend_string_equals_literal(phpurl->scheme, "http")) {
php_url_free(phpurl);
php_uri_free(uri_internal);
if (request != buf) {
zend_string_release_ex(request, 0);
}
Expand Down
5 changes: 4 additions & 1 deletion ext/uri/php_uri.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -422,13 +422,16 @@ PHP_METHOD(Uri_Rfc3986Uri, normalize)

zend_object *new_object = uri_clone_obj_handler(this_object);
if (UNEXPECTED(EG(exception) != NULL)) {
zend_object_release(new_object);
RETURN_THROWS();
}

uri_internal_t *new_internal_uri = uri_internal_from_obj(new_object);
URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, this_object);
URI_CHECK_INITIALIZATION_RETURN_THROWS(new_internal_uri, new_object); /* TODO fix memory leak of new_object */

if (UNEXPECTED(internal_uri->handler->normalize_uri(new_internal_uri->uri) == FAILURE)) {
zend_throw_error(uri_operation_exception_ce, "Failed to normalize %s", ZSTR_VAL(this_object->ce->name));
zend_object_release(new_object);
RETURN_THROWS();
}

Expand Down
109 changes: 58 additions & 51 deletions ext/uri/php_uri_common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,91 +91,98 @@ uri_property_handler_t *uri_property_handler_from_internal_uri(const uri_interna
void throw_invalid_uri_exception(zval *errors);

#define URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, object) do { \
ZEND_ASSERT(internal_uri != NULL); \
ZEND_ASSERT(internal_uri != NULL); \
if (UNEXPECTED(internal_uri->uri == NULL)) { \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
RETURN_THROWS(); \
} \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
RETURN_THROWS(); \
} \
} while (0)

#define URI_CHECK_INITIALIZATION_RETURN(internal_uri, object, return_on_failure) do { \
ZEND_ASSERT(internal_uri != NULL); \
ZEND_ASSERT(internal_uri != NULL); \
if (UNEXPECTED(internal_uri->uri == NULL)) { \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
return return_on_failure; \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
return return_on_failure; \
} \
} while (0)

#define URI_CHECK_INITIALIZATION_RETURN_VOID(internal_uri, object) do { \
ZEND_ASSERT(internal_uri != NULL); \
ZEND_ASSERT(internal_uri != NULL); \
if (UNEXPECTED(internal_uri->uri == NULL)) { \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
return; \
zend_throw_error(uninitialized_uri_exception_ce, "%s object is not correctly initialized", ZSTR_VAL(object->ce->name)); \
return; \
} \
} while (0)

#define URI_GETTER(property_name) do { \
ZEND_PARSE_PARAMETERS_NONE(); \
uri_internal_t *internal_uri = Z_URI_INTERNAL_P(ZEND_THIS); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, Z_OBJ_P(ZEND_THIS)); \
const uri_property_handler_t *property_handler = uri_property_handler_from_internal_uri(internal_uri, property_name); \
ZEND_ASSERT(property_handler != NULL); \
if (property_handler->read_func(internal_uri, return_value) == FAILURE) { \
zend_throw_error(NULL, "%s::$%s property cannot be retrieved", ZSTR_VAL(Z_OBJ_P(ZEND_THIS)->ce->name), ZSTR_VAL(property_name)); \
RETURN_THROWS(); \
} \
ZEND_PARSE_PARAMETERS_NONE(); \
uri_internal_t *internal_uri = Z_URI_INTERNAL_P(ZEND_THIS); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, Z_OBJ_P(ZEND_THIS)); \
const uri_property_handler_t *property_handler = uri_property_handler_from_internal_uri(internal_uri, property_name); \
ZEND_ASSERT(property_handler != NULL); \
if (UNEXPECTED(property_handler->read_func(internal_uri, return_value) == FAILURE)) { \
zend_throw_error(NULL, "%s::$%s property cannot be retrieved", ZSTR_VAL(Z_OBJ_P(ZEND_THIS)->ce->name), ZSTR_VAL(property_name)); \
RETURN_THROWS(); \
} \
} while (0)

#define URI_WITHER_COMMON(property_name, property_zv, return_value) \
uri_internal_t *internal_uri = Z_URI_INTERNAL_P(ZEND_THIS); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, Z_OBJ_P(ZEND_THIS)); \
const uri_property_handler_t *property_handler = uri_property_handler_from_internal_uri(internal_uri, property_name); \
ZEND_ASSERT(property_handler != NULL); \
zend_object *new_object = uri_clone_obj_handler(Z_OBJ_P(ZEND_THIS)); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(internal_uri, Z_OBJ_P(ZEND_THIS)); \
const uri_property_handler_t *property_handler = uri_property_handler_from_internal_uri(internal_uri, property_name); \
ZEND_ASSERT(property_handler != NULL); \
zend_object *new_object = uri_clone_obj_handler(Z_OBJ_P(ZEND_THIS)); \
if (UNEXPECTED(EG(exception) != NULL)) { \
zend_object_release(new_object); \
zval_ptr_dtor(property_zv); \
RETURN_THROWS(); \
} \
uri_internal_t *new_internal_uri = uri_internal_from_obj(new_object); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(new_internal_uri, Z_OBJ_P(ZEND_THIS)); \
if (property_handler->write_func == NULL) { \
zend_readonly_property_modification_error_ex(ZSTR_VAL(Z_OBJ_P(ZEND_THIS)->ce->name), ZSTR_VAL(property_name)); \
RETURN_THROWS(); \
} \
zval errors; \
ZVAL_UNDEF(&errors); \
uri_internal_t *new_internal_uri = uri_internal_from_obj(new_object); \
URI_CHECK_INITIALIZATION_RETURN_THROWS(new_internal_uri, Z_OBJ_P(ZEND_THIS)); /* TODO fix memory leak of new_object */ \
if (property_handler->write_func == NULL) { \
zend_readonly_property_modification_error_ex(ZSTR_VAL(Z_OBJ_P(ZEND_THIS)->ce->name), ZSTR_VAL(property_name)); \
zend_object_release(new_object); \
zval_ptr_dtor(property_zv); \
RETURN_THROWS(); \
} \
zval errors; \
ZVAL_UNDEF(&errors); \
if (property_handler->write_func(new_internal_uri, property_zv, &errors) == FAILURE) { \
throw_invalid_uri_exception(&errors); \
zval_ptr_dtor(&errors); \
RETURN_THROWS(); \
} \
ZEND_ASSERT(Z_TYPE(errors) == IS_UNDEF); \
ZVAL_OBJ(return_value, new_object);
zend_object_release(new_object); \
zval_ptr_dtor(property_zv); \
RETURN_THROWS(); \
} \
ZEND_ASSERT(Z_TYPE(errors) == IS_UNDEF); \
ZVAL_OBJ(return_value, new_object); \
zval_ptr_dtor(property_zv);

#define URI_WITHER_STR(property_name) do { \
zend_string *value; \
ZEND_PARSE_PARAMETERS_START(1, 1) \
Z_PARAM_PATH_STR_OR_NULL(value) \
ZEND_PARSE_PARAMETERS_END(); \
zend_string *value; \
ZEND_PARSE_PARAMETERS_START(1, 1) \
Z_PARAM_PATH_STR_OR_NULL(value) \
ZEND_PARSE_PARAMETERS_END(); \
zval zv; \
if (value == NULL) { \
ZVAL_NULL(&zv); \
if (value == NULL) { \
ZVAL_NULL(&zv); \
} else { \
ZVAL_STR_COPY(&zv, value); \
} \
ZVAL_STR_COPY(&zv, value); \
} \
URI_WITHER_COMMON(property_name, &zv, return_value) \
} while (0)

#define URI_WITHER_LONG(property_name) do { \
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggest URI_WITHER_LONG_OR_NULL to match the URI_WITHER_STR_OR_NULL

zend_long value; \
bool value_is_null; \
ZEND_PARSE_PARAMETERS_START(1, 1) \
Z_PARAM_LONG_OR_NULL(value, value_is_null) \
ZEND_PARSE_PARAMETERS_END(); \
zend_long value; \
bool value_is_null; \
ZEND_PARSE_PARAMETERS_START(1, 1) \
Z_PARAM_LONG_OR_NULL(value, value_is_null) \
ZEND_PARSE_PARAMETERS_END(); \
zval zv; \
if (value_is_null) {\
if (value_is_null) {\
ZVAL_NULL(&zv); \
} else { \
ZVAL_LONG(&zv, value); \
} else { \
ZVAL_LONG(&zv, value); \
} \
URI_WITHER_COMMON(property_name, &zv, return_value); \
} while (0)
Expand Down
6 changes: 3 additions & 3 deletions ext/uri/php_uriparser.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,12 +57,12 @@ typedef enum {
UriUriA *new_uriparser_uri = uriparser_parse_uri(str, NULL, errors); \
if (new_uriparser_uri == NULL) { \
smart_str_free(&uri_str); \
zend_string_free(str); \
zend_string_release(str); \
return FAILURE; \
} \
uriparser_free_uri(uriparser_uri); \
internal_uri->uri = (void *) new_uriparser_uri; \
smart_str_free(&uri_str); \
smart_str_free(&uri_str); \
return SUCCESS; \
} while (0)

Expand Down Expand Up @@ -119,7 +119,7 @@ static void uriparser_append_scheme(const uri_internal_t *internal_uri, smart_st
uriparser_read_scheme(internal_uri, &tmp);
if (Z_TYPE(tmp) == IS_STRING) {
smart_str_append(uri_str, Z_STR(tmp));
smart_str_appendl(uri_str, "://", sizeof("://") - 1); // TODO apply the algorithm at https://datatracker.ietf.org/doc/html/rfc3986#section-5.3
smart_str_appendl(uri_str, "://", sizeof("://") - 1); /* TODO apply the algorithm at https://datatracker.ietf.org/doc/html/rfc3986#section-5.3 */
}

zval_ptr_dtor(&tmp);
Expand Down