Skip to content

Add the Uri\Rfc3986\Uri class to ext/uri without wither support #18836

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 13 commits into
base: master
Choose a base branch
from
+1,818 −146
Open

Add the Uri\Rfc3986\Uri class to ext/uri without wither support #18836

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
60675b6
Add Uri\Rfc3986\Uri class to ext/uri
kocsismate Jun 11, 2025
ca85779
Review round 1 fixes
kocsismate Jun 11, 2025
db3cdf2
Another batch of fixes
kocsismate Jun 13, 2025
7907ccf
Fix memory management
kocsismate Jun 14, 2025
d430892
Fix Windows build
kocsismate Jun 14, 2025
00d4091
Improve and simplify exceptions
kocsismate Jun 15, 2025
42c6e58
Remove accidentally added extra ;
kocsismate Jun 15, 2025
8bf1722
Try to incorporate uriparser_copy_uri into uriparser
kocsismate Jun 15, 2025
484bbf3
uriparser improvements
kocsismate Jun 18, 2025
34c3f0a
More improvements
kocsismate Jun 22, 2025
1525e64
Allocate on stack
kocsismate Jun 26, 2025
7541b33
Fixes after rebase
kocsismate Jul 1, 2025
471a762
Another fix for uriparser
kocsismate Jul 1, 2025
File filter

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
Another batch of fixes
  • Loading branch information
@kocsismate
kocsismate committed Jul 1, 2025
commit db3cdf28b470669e6b0b09e26f47e34d8884bbf6
4 changes: 1 addition & 3 deletions ext/uri/php_uri.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -846,12 +846,10 @@ static PHP_MINIT_FUNCTION(uri)

zend_hash_init(&uri_handlers, 4, NULL, NULL, true);

if (uri_handler_register(&uriparser_uri_handler) == FAILURE) {
if (PHP_MINIT(uri_uriparser)(INIT_FUNC_ARGS_PASSTHRU) == FAILURE) {
return FAILURE;
}

uriparser_module_init();

if (uri_handler_register(&lexbor_uri_handler) == FAILURE) {
return FAILURE;
}
Expand Down
58 changes: 41 additions & 17 deletions ext/uri/php_uriparser.c
View file
Open in desktop
Copy link
Member

Choose a reason for hiding this comment

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

Something I'm only noticing now: I think this should rather be called ext/uri/parser_rfc3986.c and php_lexbor.c would be ext/uri/parser_whatwg.c. The php_uriparser.c name is confusing to me, because uriparser is an extremely generic term.

To give another comparison with ext/random, since it is architecturally similar: Each engine has its own engine_enginename.c file, e.g. engine_xoshiro256starstar.c.
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,11 @@ void *uriparser_parse_uri(const zend_string *uri_str, const void *base_url, zval
static void uriparser_free_uri(void *uri);
static void throw_invalid_uri_exception(void);

static inline size_t get_text_range_length(const UriTextRangeA *range)
{
return range->afterLast - range->first;
}

static void uriparser_copy_text_range(UriTextRangeA *text_range, UriTextRangeA *new_text_range, bool use_safe)
{
if (text_range->first == NULL || text_range->afterLast == NULL || (text_range->first > text_range->afterLast && !use_safe)) {
Expand All @@ -33,7 +38,7 @@ static void uriparser_copy_text_range(UriTextRangeA *text_range, UriTextRangeA *
new_text_range->first = uriSafeToPointToA;
new_text_range->afterLast = uriSafeToPointToA;
} else {
size_t length = (size_t) (text_range->afterLast - text_range->first);
size_t length = get_text_range_length(text_range);
char *dup = emalloc(length);
memcpy(dup, text_range->first, length);

Expand Down Expand Up @@ -135,8 +140,8 @@ static zend_result uriparser_read_scheme(const uri_internal_t *internal_uri, uri
}

if (uriparser_uri->scheme.first != NULL && uriparser_uri->scheme.afterLast != NULL) {
zend_string *str = zend_string_init(uriparser_uri->scheme.first, uriparser_uri->scheme.afterLast - uriparser_uri->scheme.first, false);
ZVAL_STR(retval, str);
zend_string *str = zend_string_init(uriparser_uri->scheme.first, get_text_range_length(&uriparser_uri->scheme), false);
ZVAL_NEW_STR(retval, str);
} else {
ZVAL_NULL(retval);
}
Expand All @@ -152,7 +157,7 @@ zend_result uriparser_read_userinfo(const uri_internal_t *internal_uri, uri_comp
}

if (uriparser_uri->userInfo.first != NULL && uriparser_uri->userInfo.afterLast != NULL) {
ZVAL_STRINGL(retval, uriparser_uri->userInfo.first, uriparser_uri->userInfo.afterLast - uriparser_uri->userInfo.first);
ZVAL_STRINGL(retval, uriparser_uri->userInfo.first, get_text_range_length(&uriparser_uri->userInfo));
} else {
ZVAL_NULL(retval);
}
Expand All @@ -168,7 +173,7 @@ static zend_result uriparser_read_username(const uri_internal_t *internal_uri, u
}

if (uriparser_uri->userInfo.first != NULL && uriparser_uri->userInfo.afterLast != NULL) {
size_t length = uriparser_uri->userInfo.afterLast - uriparser_uri->userInfo.first;
size_t length = get_text_range_length(&uriparser_uri->userInfo);
char *c = memchr(uriparser_uri->userInfo.first, ':', length);

if (c == NULL && length > 0) {
Expand All @@ -193,7 +198,7 @@ static zend_result uriparser_read_password(const uri_internal_t *internal_uri, u
}

if (uriparser_uri->userInfo.first != NULL && uriparser_uri->userInfo.afterLast != NULL) {
const char *c = memchr(uriparser_uri->userInfo.first, ':', uriparser_uri->userInfo.afterLast - uriparser_uri->userInfo.first);
const char *c = memchr(uriparser_uri->userInfo.first, ':', get_text_range_length(&uriparser_uri->userInfo));
Copy link
Member

Choose a reason for hiding this comment

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

This implementation is inconsistent with the implementation in uriparser_read_username.

if (c != NULL && uriparser_uri->userInfo.afterLast - c - 1 > 0) {
ZVAL_STRINGL(retval, c + 1, uriparser_uri->userInfo.afterLast - c - 1);
Expand All @@ -214,17 +219,17 @@ static zend_result uriparser_read_host(const uri_internal_t *internal_uri, uri_c
return FAILURE;
}

if (uriparser_uri->hostText.first != NULL && uriparser_uri->hostText.afterLast != NULL && uriparser_uri->hostText.afterLast - uriparser_uri->hostText.first > 0) {
if (uriparser_uri->hostText.first != NULL && uriparser_uri->hostText.afterLast != NULL && get_text_range_length(&uriparser_uri->hostText) > 0) {
if (uriparser_uri->hostData.ip6 != NULL) {
smart_str host_str = {0};

smart_str_appendc(&host_str, '[');
smart_str_appendl(&host_str, uriparser_uri->hostText.first, uriparser_uri->hostText.afterLast - uriparser_uri->hostText.first);
smart_str_appendl(&host_str, uriparser_uri->hostText.first, get_text_range_length(&uriparser_uri->hostText));
smart_str_appendc(&host_str, ']');

ZVAL_NEW_STR(retval, smart_str_extract(&host_str));
} else {
ZVAL_STRINGL(retval, uriparser_uri->hostText.first, uriparser_uri->hostText.afterLast - uriparser_uri->hostText.first);
ZVAL_STRINGL(retval, uriparser_uri->hostText.first, get_text_range_length(&uriparser_uri->hostText));
}
} else {
ZVAL_NULL(retval);
Expand All @@ -233,13 +238,26 @@ static zend_result uriparser_read_host(const uri_internal_t *internal_uri, uri_c
return SUCCESS;
}

static int str_to_int(const char *str, int len)
Copy link
Member

Choose a reason for hiding this comment

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

I guess len should actually be a size_t to be strictly correct, and i too.
{
int result = 0;

for (int i = 0; i < len; ++i) {
result = result * 10 + (str[i] - '0');
}

return result;
}

static zend_result uriparser_read_port(const uri_internal_t *internal_uri, uri_component_read_mode_t read_mode, zval *retval)
{
uriparser_uris_t *uriparser_uris = (uriparser_uris_t *) internal_uri->uri;
UriUriA *uriparser_uri = uriparser_uris->uri;
UriUriA *uriparser_uri = uriparser_read_uri(internal_uri->uri, read_mode);
if (UNEXPECTED(uriparser_uri == NULL)) {
return FAILURE;
}

if (uriparser_uri->portText.first != NULL && uriparser_uri->portText.afterLast != NULL) {
ZVAL_LONG(retval, strtol(uriparser_uri->portText.first, NULL, 10));
ZVAL_LONG(retval, str_to_int(uriparser_uri->portText.first, get_text_range_length(&uriparser_uri->portText)));
} else {
ZVAL_NULL(retval);
}
Expand All @@ -262,11 +280,11 @@ static zend_result uriparser_read_path(const uri_internal_t *internal_uri, uri_c
smart_str_appendc(&str, '/');
}

smart_str_appendl(&str, uriparser_uri->pathHead->text.first, (size_t) ((uriparser_uri->pathHead->text).afterLast - (uriparser_uri->pathHead->text).first));
smart_str_appendl(&str, uriparser_uri->pathHead->text.first, get_text_range_length(&uriparser_uri->pathHead->text));

for (p = uriparser_uri->pathHead->next; p != NULL; p = p->next) {
smart_str_appendc(&str, '/');
smart_str_appendl(&str, p->text.first, (int) ((p->text).afterLast - (p->text).first));
smart_str_appendl(&str, p->text.first, get_text_range_length(&p->text));
}

ZVAL_NEW_STR(retval, smart_str_extract(&str));
Expand All @@ -287,7 +305,7 @@ static zend_result uriparser_read_query(const uri_internal_t *internal_uri, uri_
}

if (uriparser_uri->query.first != NULL && uriparser_uri->query.afterLast != NULL) {
ZVAL_STRINGL(retval, uriparser_uri->query.first, uriparser_uri->query.afterLast - uriparser_uri->query.first);
ZVAL_STRINGL(retval, uriparser_uri->query.first, get_text_range_length(&uriparser_uri->query));
} else {
ZVAL_NULL(retval);
}
Expand All @@ -303,7 +321,7 @@ static zend_result uriparser_read_fragment(const uri_internal_t *internal_uri, u
}

if (uriparser_uri->fragment.first != NULL && uriparser_uri->fragment.afterLast != NULL) {
ZVAL_STRINGL(retval, uriparser_uri->fragment.first, uriparser_uri->fragment.afterLast - uriparser_uri->fragment.first);
ZVAL_STRINGL(retval, uriparser_uri->fragment.first, get_text_range_length(&uriparser_uri->fragment));
} else {
ZVAL_NULL(retval);
}
Expand Down Expand Up @@ -336,13 +354,19 @@ static void uriparser_free(UriMemoryManager *memory_manager, void *ptr)
efree(ptr);
}

void uriparser_module_init(void)
PHP_MINIT_FUNCTION(uri_uriparser)
{
if (uri_handler_register(&uriparser_uri_handler) == FAILURE) {
return FAILURE;
}

defaultMemoryManager.malloc = uriparser_malloc;
defaultMemoryManager.calloc = uriparser_calloc;
defaultMemoryManager.realloc = uriparser_realloc;
defaultMemoryManager.reallocarray = uriparser_reallocarray;
defaultMemoryManager.free = uriparser_free;

return SUCCESS;
}

static uriparser_uris_t *uriparser_create_uris(
Expand Down
2 changes: 1 addition & 1 deletion ext/uri/php_uriparser.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ typedef struct uriparser_uris_t {
zend_string *normalized_uri_str;
} uriparser_uris_t;

void uriparser_module_init(void);
PHP_MINIT_FUNCTION(uri_uriparser);

zend_result uriparser_read_userinfo(const uri_internal_t *internal_uri, uri_component_read_mode_t read_mode, zval *retval);

Expand Down