From 28caa35a97ed4837a62cb054f66cf02041292cc5 Mon Sep 17 00:00:00 2001
From: Eelco Dolstra <edolstra@gmail.com>
Date: Wed, 8 Jan 2025 18:38:53 +0100
Subject: [PATCH] parsePathFlakeRefWithFragment(): Handle 'path?query' without
 a fragment

Commands like `nix flake metadata '.?submodules=1'` ignored the query
part of the URL, while `nix build '.?submodules=1#foo'` did work
correctly because of the presence of the fragment part.
---
 src/libflake/flake/flakeref.cc                | 27 +++++++------------
 tests/functional/flakes/flake-in-submodule.sh | 13 +++++++++
 2 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/src/libflake/flake/flakeref.cc b/src/libflake/flake/flakeref.cc
index 60efe1612..58cd45632 100644
--- a/src/libflake/flake/flakeref.cc
+++ b/src/libflake/flake/flakeref.cc
@@ -89,23 +89,16 @@ std::pair<FlakeRef, std::string> parsePathFlakeRefWithFragment(
     bool allowMissing,
     bool isFlake)
 {
-    std::string path = url;
-    std::string fragment = "";
-    std::map<std::string, std::string> query;
-    auto pathEnd = url.find_first_of("#?");
-    auto fragmentStart = pathEnd;
-    if (pathEnd != std::string::npos && url[pathEnd] == '?') {
-        fragmentStart = url.find("#");
-    }
-    if (pathEnd != std::string::npos) {
-        path = url.substr(0, pathEnd);
-    }
-    if (fragmentStart != std::string::npos) {
-        fragment = percentDecode(url.substr(fragmentStart+1));
-    }
-    if (pathEnd != std::string::npos && fragmentStart != std::string::npos && url[pathEnd] == '?') {
-        query = decodeQuery(url.substr(pathEnd + 1, fragmentStart - pathEnd - 1));
-    }
+    static std::regex pathFlakeRegex(
+        R"(([^?#]*)(\?([^#]*))?(#(.*))?)",
+        std::regex::ECMAScript);
+
+    std::smatch match;
+    auto succeeds = std::regex_match(url, match, pathFlakeRegex);
+    assert(succeeds);
+    auto path = match[1].str();
+    auto query = decodeQuery(match[3]);
+    auto fragment = percentDecode(match[5].str());
 
     if (baseDir) {
         /* Check if 'url' is a path (either absolute or relative
diff --git a/tests/functional/flakes/flake-in-submodule.sh b/tests/functional/flakes/flake-in-submodule.sh
index 817f77783..643d729ff 100755
--- a/tests/functional/flakes/flake-in-submodule.sh
+++ b/tests/functional/flakes/flake-in-submodule.sh
@@ -63,3 +63,16 @@ flakeref=git+file://$rootRepo\?submodules=1\&dir=submodule
 echo '"foo"' > "$rootRepo"/submodule/sub.nix
 [[ $(nix eval --json "$flakeref#sub" ) = '"foo"' ]]
 [[ $(nix flake metadata --json "$flakeref" | jq -r .locked.rev) = null ]]
+
+# Test that `nix flake metadata` parses `submodule` correctly.
+cat > "$rootRepo"/flake.nix <<EOF
+{
+    outputs = { self }: {
+    };
+}
+EOF
+git -C "$rootRepo" add flake.nix
+git -C "$rootRepo" commit -m "Add flake.nix"
+
+storePath=$(nix flake metadata --json "$rootRepo?submodules=1" | jq -r .path)
+[[ -e "$storePath/submodule" ]]