libutil: Refactor percentDecode,percentEncode to use Boost.URL

The myriad of hand-rolled URL parsing and validation code
is a constant source of problems. Regexes are not a great way
of writing parsers and there's a history of getting them wrong.
Boost.URL is a good library we can outsource most of the heavy
lifting to.

packaging/dependencies.nix

@@ -62,6 +62,7 @@ scope: {
         "--with-context"
         "--with-coroutine"
         "--with-iostreams"
+        "--with-url"
       ];
       enableIcu = false;
     }).overrideAttrs

src/libutil-tests/url.cc

@@ -1,5 +1,7 @@
 #include "nix/util/url.hh"
+#include "nix/util/tests/gmock-matchers.hh"
 #include <gtest/gtest.h>
+#include <gmock/gmock.h>
 
 namespace nix {
 
@@ -289,6 +291,14 @@ TEST(percentDecode, trailingPercent)
     ASSERT_EQ(d, s);
 }
 
+TEST(percentDecode, incompleteEncoding)
+{
+    ASSERT_THAT(
+        []() { percentDecode("%1"); },
+        ::testing::ThrowsMessage<BadURL>(
+            testing::HasSubstrIgnoreANSIMatcher("error: invalid URI parameter '%1': incomplete pct-encoding")));
+}
+
 /* ----------------------------------------------------------------------------
  * percentEncode
  * --------------------------------------------------------------------------*/

src/libutil/meson.build

@@ -57,7 +57,7 @@ deps_private += blake3
 
 boost = dependency(
   'boost',
-  modules : ['context', 'coroutine', 'iostreams'],
+  modules : ['context', 'coroutine', 'iostreams', 'url'],
   include_type: 'system',
   version: '>=1.82.0'
 )

src/libutil/url.cc

@@ -4,6 +4,8 @@
 #include "nix/util/split.hh"
 #include "nix/util/canon-path.hh"
 
+#include <boost/url.hpp>
+
 namespace nix {
 
 std::regex refRegex(refRegexS, std::regex::ECMAScript);
@@ -48,21 +50,17 @@ ParsedURL parseURL(const std::string & url)
 
 std::string percentDecode(std::string_view in)
 {
-    std::string decoded;
+    auto pctView = boost::urls::make_pct_string_view(in);
-    for (size_t i = 0; i < in.size();) {
+    if (pctView.has_value())
-        if (in[i] == '%') {
+        return pctView->decode();
-            if (i + 2 >= in.size())
+    auto error = pctView.error();
-                throw BadURL("invalid URI parameter '%s'", in);
+    throw BadURL("invalid URI parameter '%s': %s", in, error.message());
-            try {
-                decoded += std::stoul(std::string(in, i + 1, 2), 0, 16);
-                i += 3;
-            } catch (...) {
-                throw BadURL("invalid URI parameter '%s'", in);
 }
-        } else
+
-            decoded += in[i++];
+std::string percentEncode(std::string_view s, std::string_view keep)
-    }
+{
-    return decoded;
+    return boost::urls::encode(
+        s, [keep](char c) { return boost::urls::unreserved_chars(c) || keep.find(c) != keep.npos; });
 }
 
 StringMap decodeQuery(const std::string & query)
@@ -85,19 +83,6 @@ StringMap decodeQuery(const std::string & query)
 const static std::string allowedInQuery = ":@/?";
 const static std::string allowedInPath = ":@/";
 
-std::string percentEncode(std::string_view s, std::string_view keep)
-{
-    std::string res;
-    for (auto & c : s)
-        // unreserved + keep
-        if ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || strchr("-._~", c)
-            || keep.find(c) != std::string::npos)
-            res += c;
-        else
-            res += fmt("%%%02X", c & 0xFF);
-    return res;
-}
-
 std::string encodeQuery(const StringMap & ss)
 {
     std::string res;