Merge pull request #14296 from lovesegfault/nix-s3-more-tests

fix(nix-prefetch-url): correctly extract filename from URLs with query parameters

src/libutil/include/nix/util/url.hh

@@ -408,6 +408,17 @@ struct VerbatimURL
                 [](const ParsedURL & url) -> std::string_view { return url.scheme; }},
             raw);
     }
+
+    /**
+     * Get the last non-empty path segment from the URL.
+     *
+     * This is useful for extracting filenames from URLs.
+     * For example, "https://example.com/path/to/file.txt?query=value"
+     * returns "file.txt".
+     *
+     * @return The last non-empty path segment, or std::nullopt if no such segment exists.
+     */
+    std::optional<std::string> lastPathSegment() const;
 };
 
 std::ostream & operator<<(std::ostream & os, const VerbatimURL & url);

src/libutil/url.cc

@@ -4,6 +4,7 @@
 #include "nix/util/split.hh"
 #include "nix/util/canon-path.hh"
 #include "nix/util/strings-inline.hh"
+#include "nix/util/file-system.hh"
 
 #include <boost/url.hpp>
 
@@ -440,4 +441,21 @@ std::ostream & operator<<(std::ostream & os, const VerbatimURL & url)
     return os;
 }
 
+std::optional<std::string> VerbatimURL::lastPathSegment() const
+{
+    try {
+        auto parsedUrl = parsed();
+        auto segments = parsedUrl.pathSegments(/*skipEmpty=*/true);
+        if (std::ranges::empty(segments))
+            return std::nullopt;
+        return segments.back();
+    } catch (BadURL &) {
+        // Fall back to baseNameOf for unparsable URLs
+        auto name = baseNameOf(to_string());
+        if (name.empty())
+            return std::nullopt;
+        return std::string{name};
+    }
+}
+
 } // namespace nix