mirror of
https://github.com/yhirose/cpp-httplib.git
synced 2026-10-17 10:59:39 +00:00
Apply path encoding to open_stream()
ClientImpl::open_stream() passed the caller-supplied path straight to the request line, so it ignored path_encode_ entirely and always behaved as if set_path_encode(false) had been called. The same path therefore produced different bytes on the wire depending on which API was used: Get() "/a b" -> GET /a%20b HTTP/1.1 open_stream() "/a b" -> GET /a b HTTP/1.1 A space is the request-target delimiter, so the streaming form is not merely inconsistent: an RFC 9112 conformant server reads the target as "/a" and the version as "b". Non-ASCII bytes and '+' diverged the same way, the latter changing the value a server that decodes '+' as space sees. Extract the path/query splitting and encoding out of ClientImpl::write_request into detail::encode_request_target() and call it from both paths, so the encoding rule lives in one place. open_stream() appends Params before encoding, matching ClientImpl::Get(path, params), which builds its target the same way. Note a behavior change: with path encoding enabled, CR/LF in the target is now percent-encoded and sent rather than rejected with Error::Write, matching Get(). This is not a weakening of the CR/LF guard in write_request_line() -- that check is independent of path_encode_ and still backstops set_path_encode(false), where encode_path() does nothing.
This commit is contained in:
1 parent
d66d9a9599
commit
5b9d1495ff
2 files changed
+262
-41
No files matched your search
@@ -7947,6 +7947,43 @@ inline std::string normalize_query_string(const std::string &query) {
|
||||
return result;
|
||||
}
|
||||
|
||||
// Build the request target that goes on the wire from a caller-supplied path.
|
||||
// Shared by the buffered send path and the streaming API so that both put the
|
||||
// same bytes in the request line for the same input.
|
||||
inline std::string encode_request_target(const std::string &target,
|
||||
bool path_encode) {
|
||||
// `substr(0, npos)` yields the whole string, which is what the no-query
|
||||
// case needs.
|
||||
auto query_pos = target.find('?');
|
||||
auto path_part = target.substr(0, query_pos);
|
||||
std::string query_part;
|
||||
if (query_pos != std::string::npos) {
|
||||
query_part = target.substr(query_pos + 1);
|
||||
}
|
||||
|
||||
auto result = path_encode ? encode_path(path_part) : std::move(path_part);
|
||||
|
||||
if (!query_part.empty()) {
|
||||
// When path encoding is disabled the caller has supplied an already-encoded
|
||||
// target and expects the exact bytes to be sent on the wire, so skip
|
||||
// normalization for the query too. Normalizing would decode-then-re-encode
|
||||
// it and corrupt pre-encoded binary payloads (e.g. turning `%20` into `+`,
|
||||
// which a strict RFC 3986 server decodes back as `+`, not a space).
|
||||
if (path_encode) {
|
||||
auto normalized = normalize_query_string(query_part);
|
||||
if (!normalized.empty()) {
|
||||
result += '?';
|
||||
result += normalized;
|
||||
}
|
||||
} else {
|
||||
result += '?';
|
||||
result += query_part;
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
inline bool parse_multipart_boundary(const std::string &content_type,
|
||||
std::string &boundary) {
|
||||
std::map<std::string, std::string> params;
|
||||
@@ -13240,7 +13277,12 @@ ClientImpl::open_stream(const std::string &method, const std::string &path,
|
||||
handle.response = detail::make_unique<Response>();
|
||||
handle.error = Error::Success;
|
||||
|
||||
auto query_path = params.empty() ? path : append_query_params(path, params);
|
||||
// Encode the target exactly like the buffered send path does, so that the
|
||||
// same `path` produces the same request line through either API.
|
||||
auto raw_query_path =
|
||||
params.empty() ? path : append_query_params(path, params);
|
||||
auto query_path = detail::encode_request_target(raw_query_path, path_encode_);
|
||||
|
||||
handle.connection_ = detail::make_unique<ClientConnection>();
|
||||
|
||||
{
|
||||
@@ -13885,52 +13927,26 @@ inline bool ClientImpl::write_request(Stream &strm, Request &req,
|
||||
{
|
||||
detail::BufferStream bstrm;
|
||||
|
||||
// Extract path and query from req.path
|
||||
std::string path_part, query_part;
|
||||
// Extract the query from req.path. The encoding itself is delegated to
|
||||
// `encode_request_target`; the raw query is still needed here to decide
|
||||
// between populating `req.params` from it and falling back to building a
|
||||
// query out of caller-supplied `req.params`.
|
||||
auto query_pos = req.path.find('?');
|
||||
if (query_pos != std::string::npos) {
|
||||
path_part = req.path.substr(0, query_pos);
|
||||
query_part = req.path.substr(query_pos + 1);
|
||||
} else {
|
||||
path_part = req.path;
|
||||
query_part = "";
|
||||
}
|
||||
auto query_part = query_pos == std::string::npos
|
||||
? std::string()
|
||||
: req.path.substr(query_pos + 1);
|
||||
|
||||
// Encode path part. If the original `req.path` already contained a
|
||||
// query component, preserve its raw query string (including parameter
|
||||
// order) instead of reparsing and reassembling it which may reorder
|
||||
// parameters due to container ordering (e.g. `Params` uses
|
||||
// `std::multimap`). When there is no query in `req.path`, fall back to
|
||||
// building a query from `req.params` so existing callers that pass
|
||||
// `Params` continue to work.
|
||||
auto path_with_query =
|
||||
path_encode_ ? detail::encode_path(path_part) : path_part;
|
||||
detail::encode_request_target(req.path, path_encode_);
|
||||
|
||||
if (!query_part.empty()) {
|
||||
// Normalize the query string (decode then re-encode) while preserving
|
||||
// the original parameter order. When path encoding is disabled the
|
||||
// caller has supplied an already-encoded target and expects the exact
|
||||
// bytes to be sent on the wire, so skip normalization for the query
|
||||
// too. Normalizing here would decode-then-re-encode the query and
|
||||
// corrupt pre-encoded binary payloads (e.g. turning `%20` into `+`,
|
||||
// which a strict RFC 3986 server decodes back as `+`, not a space).
|
||||
if (path_encode_) {
|
||||
auto normalized = detail::normalize_query_string(query_part);
|
||||
if (!normalized.empty()) { path_with_query += '?' + normalized; }
|
||||
} else {
|
||||
path_with_query += '?' + query_part;
|
||||
}
|
||||
|
||||
// Still populate req.params for handlers/users who read them.
|
||||
// The query already came in through `req.path`; still populate
|
||||
// `req.params` for handlers/users who read them.
|
||||
detail::parse_query_text(query_part, req.params);
|
||||
} else {
|
||||
// No query in path; parse any query_part (empty) and append params
|
||||
// from `req.params` when present (preserves prior behavior for
|
||||
// callers who provide Params separately).
|
||||
detail::parse_query_text(query_part, req.params);
|
||||
if (!req.params.empty()) {
|
||||
path_with_query = append_query_params(path_with_query, req.params);
|
||||
}
|
||||
} else if (!req.params.empty()) {
|
||||
// No query in `req.path`; build one from `req.params` so existing
|
||||
// callers that pass `Params` separately continue to work.
|
||||
path_with_query = append_query_params(path_with_query, req.params);
|
||||
}
|
||||
|
||||
// Write request line and headers
|
||||
|
||||
Reference in new issue
Block a user