Skip to content

src: fix and cleanup URL::SerializeURL #41759

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

Closed
wants to merge 6 commits into from
Closed

src: fix and cleanup URL::SerializeURL #41759

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b47430c
src: fix query/fragment serialization in URL::SerializeURL
addaleax Jan 29, 2022
c9ea544
src: reserve string allocation space early in URL::SerializeURL
addaleax Jan 29, 2022
2fe8dcf
src: use const reference instead of pointer in URL::SerializeURL
addaleax Jan 29, 2022
438849a
fixup! src: use const reference instead of pointer in URL::SerializeURL
addaleax Jan 31, 2022
6552e41
fixup! src: use const reference instead of pointer in URL::SerializeURL
addaleax Jan 31, 2022
08ec1d5
fixup! src: use const reference instead of pointer in URL::SerializeURL
addaleax Feb 7, 2022
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
64 changes: 41 additions & 23 deletions src/node_url.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@

#include <cmath>
#include <cstdio>
#include <numeric>
#include <string>
#include <vector>

Expand Down Expand Up @@ -1545,44 +1546,61 @@ void URL::Parse(const char* input,
} // NOLINT(readability/fn_size)

// https://url.spec.whatwg.org/#url-serializing
std::string URL::SerializeURL(const struct url_data* url,
std::string URL::SerializeURL(const url_data& url,
bool exclude = false) {
std::string output = url->scheme;
if (url->flags & URL_FLAGS_HAS_HOST) {
std::string output;
output.reserve(
10 + // We generally insert < 10 separator characters between URL parts
url.scheme.size() +
url.username.size() +
url.password.size() +
url.host.size() +
url.query.size() +
url.fragment.size() +
url.href.size() +
std::accumulate(
url.path.begin(),
url.path.end(),
0,
[](size_t sum, const auto& str) { return sum + str.size(); }));

output += url.scheme;
if (url.flags & URL_FLAGS_HAS_HOST) {
output += "//";
if (url->flags & URL_FLAGS_HAS_USERNAME ||
url->flags & URL_FLAGS_HAS_PASSWORD) {
if (url->flags & URL_FLAGS_HAS_USERNAME) {
output += url->username;
if (url.flags & URL_FLAGS_HAS_USERNAME ||
url.flags & URL_FLAGS_HAS_PASSWORD) {
if (url.flags & URL_FLAGS_HAS_USERNAME) {
output += url.username;
}
if (url->flags & URL_FLAGS_HAS_PASSWORD) {
output += ":" + url->password;
if (url.flags & URL_FLAGS_HAS_PASSWORD) {
output += ":" + url.password;
}
output += "@";
}
output += url->host;
if (url->port != -1) {
output += ":" + std::to_string(url->port);
output += url.host;
if (url.port != -1) {
output += ":" + std::to_string(url.port);
}
}
if (url->flags & URL_FLAGS_CANNOT_BE_BASE) {
output += url->path[0];
if (url.flags & URL_FLAGS_CANNOT_BE_BASE) {
output += url.path[0];
} else {
if (!(url->flags & URL_FLAGS_HAS_HOST) &&
url->path.size() > 1 &&
url->path[0].empty()) {
if (!(url.flags & URL_FLAGS_HAS_HOST) &&
url.path.size() > 1 &&
url.path[0].empty()) {
output += "/.";
}
for (size_t i = 1; i < url->path.size(); i++) {
output += "/" + url->path[i];
for (size_t i = 1; i < url.path.size(); i++) {
output += "/" + url.path[i];
}
}
if (url->flags & URL_FLAGS_HAS_QUERY) {
output = "?" + url->query;
if (url.flags & URL_FLAGS_HAS_QUERY) {
output += "?" + url.query;
Copy link
Member

Choose a reason for hiding this comment

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

Typo indeed. Do we have tests for SerializeURL?

Copy link
Member Author

Choose a reason for hiding this comment

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

Not explicitly, I think. And I don't quite know where to put regression tests for this either.

Copy link
Member

Choose a reason for hiding this comment

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

Isn't this something that should be added to https://github.com/web-platform-tests/wpt/blob/master/url/resources/urltestdata.json?

}
if (!exclude && url->flags & URL_FLAGS_HAS_FRAGMENT) {
output = "#" + url->fragment;
if (!exclude && (url.flags & URL_FLAGS_HAS_FRAGMENT)) {
output += "#" + url.fragment;
}
output.shrink_to_fit();
return output;
}

Expand Down
6 changes: 3 additions & 3 deletions src/node_url.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ class URL {
const struct url_data* base,
bool has_base);

static std::string SerializeURL(const struct url_data* url, bool exclude);
static std::string SerializeURL(const url_data& url, bool exclude);

URL(const char* input, const size_t len) {
Parse(input, len, kUnknownState, &context_, false, nullptr, false);
Expand Down Expand Up @@ -174,7 +174,7 @@ class URL {
}

std::string href() const {
return SerializeURL(&context_, false);
return SerializeURL(context_, false);
}

// Get the path of the file: URL in a format consumable by native file system
Expand All @@ -193,7 +193,7 @@ class URL {
URL() : URL("") {}

private:
struct url_data context_;
url_data context_;
};

} // namespace url
Expand Down