nixos/nix
1
1
Fork 0
mirror of https://github.com/NixOS/nix.git synced 2025-11-09 12:06:01 +01:00
Code Activity

libutil: Fix handling of unescaped spaces, quotes and shevrons in queries and fragments

Browse source 
Turns out we didn't have tests for some of the important behavior introduced
for flake reference fragments and url queries [1]. This is rather important
and is relied upon by existing tooling. This fixes up these exact cases before
handing off the URL to the Boost.URL parser.

To the best of my knowledge this implements the same behavior as prior regex-based
parser did [2]:

> fragmentRegex = "(?:" + pcharRegex + "|[/? \"^])*";
> queryRegex = "(?:" + pcharRegex + "|[/? \"])*";

[1]: 9c0a09f09f
[2]: https://github.com/NixOS/nix/blob/2.30.2/src/libutil/include/nix/util/url-parts.hh
This commit is contained in:
Sergei Zimmerman 2025-08-16 23:00:31 +03:00
parent 0fd9ef0cf3
commit dc1b2012af
No known key found for this signature in database
4 changed files with 96 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

91
src/libutil/url.cc
View file

@ -11,28 +11,6 @@ namespace nix {
std::regex refRegex(refRegexS, std::regex::ECMAScript);
std::regex revRegex(revRegexS, std::regex::ECMAScript);
/**
* Drop trailing shevron for output installable syntax.
*
* FIXME: parseURL shouldn't really be used for parsing the OutputSpec, but it does
* get used. That code should actually use ExtendedOutputsSpec::parseOpt.
*/
static std::string_view dropShevronSuffix(std::string_view url)
{
auto shevron = url.rfind("^");
if (shevron == std::string_view::npos)
return url;
return url.substr(0, shevron);
}
/**
* Percent encode spaces in the url.
*/
static std::string percentEncodeSpaces(std::string_view url)
{
return replaceStrings(std::string(url), " ", percentEncode(" "));
}
ParsedURL::Authority ParsedURL::Authority::parse(std::string_view encodedAuthority)
{
auto parsed = boost::urls::parse_authority(encodedAuthority);
@ -108,14 +86,65 @@ std::string ParsedURL::Authority::to_string() const
return std::move(oss).str();
}
/**
* Additional characters that don't need URL encoding in the fragment.
*/
static constexpr boost::urls::grammar::lut_chars extraAllowedCharsInFragment = " \"^";
/**
* Additional characters that don't need URL encoding in the query.
*/
static constexpr boost::urls::grammar::lut_chars extraAllowedCharsInQuery = " \"";
static std::string percentEncodeCharSet(std::string_view s, auto charSet)
{
std::string res;
for (auto c : s) {
if (charSet(c))
res += percentEncode(std::string_view{&c, &c + 1});
else
res += c;
}
return res;
}
ParsedURL parseURL(const std::string & url)
try {
/* Drop the shevron suffix used for the flakerefs. Shevron character is reserved and
shouldn't appear in normal URIs. */
auto unparsedView = dropShevronSuffix(url);
/* For back-compat literal spaces are allowed. */
auto withFixedSpaces = percentEncodeSpaces(unparsedView);
auto urlView = boost::urls::url_view(withFixedSpaces);
auto unparsedView = url;
/* Account for several non-standard properties of nix urls (for back-compat):
* - Allow unescaped spaces ' ' and '"' characters in queries.
* - Allow '"', ' ' and '^' characters in the fragment component.
* We could write our own grammar for this, but fixing it up here seems
* more concise, since the deviation is rather minor.
*/
std::string fixedEncodedUrl = [&]() {
std::string fixed;
std::string_view view = url;
if (auto beforeQuery = splitPrefixTo(view, '?')) {
fixed += *beforeQuery;
fixed += '?';
auto fragmentStart = view.find('#');
auto queryView = view.substr(0, fragmentStart);
auto fixedQuery = percentEncodeCharSet(queryView, extraAllowedCharsInQuery);
fixed += fixedQuery;
view.remove_prefix(std::min(fragmentStart, view.size()));
}
if (auto beforeFragment = splitPrefixTo(view, '#')) {
fixed += *beforeFragment;
fixed += '#';
auto fixedFragment = percentEncodeCharSet(view, extraAllowedCharsInFragment);
fixed += fixedFragment;
return fixed;
}
fixed += view;
return fixed;
}();
auto urlView = boost::urls::url_view(fixedEncodedUrl);
if (!urlView.has_scheme())
throw BadURL("'%s' doesn't have a scheme", url);
@ -176,12 +205,12 @@ std::string percentEncode(std::string_view s, std::string_view keep)
StringMap decodeQuery(const std::string & query)
try {
/* For back-compat literal spaces are allowed. */
auto withFixedSpaces = percentEncodeSpaces(query);
/* For back-compat unescaped characters are allowed. */
auto fixedEncodedQuery = percentEncodeCharSet(query, extraAllowedCharsInQuery);
StringMap result;
auto encodedQuery = boost::urls::params_encoded_view(withFixedSpaces);
auto encodedQuery = boost::urls::params_encoded_view(fixedEncodedQuery);
for (auto && [key, value, value_specified] : encodedQuery) {
if (!value_specified) {
warn("dubious URI query '%s' is missing equal sign '%s', ignoring", std::string_view(key), "=");