irc: support merge operator

Signed-off-by: NotAShelf <raf@notashelf.dev>
Change-Id: Icfb0cc81542e637d4b91c6a5788370fb6a6a6964

src/irc/evaluator.cpp

@@ -117,13 +117,13 @@ struct Evaluator::Impl {
       v.mkPath(state.rootPath(CanonPath(n->value)));
     } else if (auto* n = node->get_if<ConstBoolNode>()) {
       v.mkBool(n->value);
-    } else if (auto* n = node->get_if<ConstNullNode>()) {  // NOLINT(bugprone-branch-clone)
+    } else if (auto* n = node->get_if<ConstNullNode>()) { // NOLINT(bugprone-branch-clone)
       v.mkNull();
     } else if (auto* n = node->get_if<ConstURINode>()) {
       // Parse and validate URI, then create string with URI context
       auto parsed = parseURL(n->value, true);
-      // Store URI with context - the parsed URL string
-      v.mkString(parsed.to_string(), nix::NixStringContext{}, state.mem);
+      // Store URI with context - use simple mkString with context
+      v.mkString(parsed.to_string(), nix::NixStringContext{});
     } else if (auto* n = node->get_if<VarNode>()) {
       Value* bound = env ? env->lookup(n->index) : nullptr;
       if (!bound && env && n->name.has_value()) {
@@ -298,6 +298,32 @@ struct Evaluator::Impl {
           // ++ is list concatenation in Nix; string concat uses ADD (+)
           state.error<EvalError>("list concatenation not yet implemented").debugThrow();
           break;
+        case BinaryOp::MERGE: {
+          // // is attrset merge - right overrides left
+          if (left->type() != nAttrs || right->type() != nAttrs) {
+            state.error<EvalError>("attrset merge requires two attrsets").debugThrow();
+          }
+
+          // Build a map of right attrs first (these have priority)
+          std::unordered_map<Symbol, Value*> right_attrs;
+          for (auto& attr : *right->attrs()) {
+            right_attrs[attr.name] = attr.value;
+          }
+
+          // Copy right attrs to result
+          auto builder = state.buildBindings(left->attrs()->size() + right->attrs()->size());
+          for (auto& attr : *right->attrs()) {
+            builder.insert(attr.name, attr.value);
+          }
+          // Add left attrs that don't exist in right
+          for (auto& attr : *left->attrs()) {
+            if (right_attrs.find(attr.name) == right_attrs.end()) {
+              builder.insert(attr.name, attr.value);
+            }
+          }
+          v.mkAttrs(builder.finish());
+          break;
+        }
         default:
           state.error<EvalError>("unknown binary operator").debugThrow();
         }

src/irc/ir_gen.cpp

@@ -162,7 +162,8 @@ struct IRGenerator::Impl {
         name_resolver.bind(key);
       }
       std::vector<std::pair<std::string, std::shared_ptr<Node>>> new_bindings;
-      for (const auto& [key, val] : n->bindings) {
+      new_bindings.reserve(n->bindings.size());
+for (const auto& [key, val] : n->bindings) {
         new_bindings.push_back({key, convert(val)});
       }
       auto body = convert(n->body);
@@ -177,7 +178,8 @@ struct IRGenerator::Impl {
         name_resolver.bind(key);
       }
       std::vector<std::pair<std::string, std::shared_ptr<Node>>> new_bindings;
-      for (const auto& [key, val] : n->bindings) {
+      new_bindings.reserve(n->bindings.size());
+for (const auto& [key, val] : n->bindings) {
         new_bindings.push_back({key, convert(val)});
       }
       auto body = convert(n->body);

src/irc/parser.cpp

@@ -95,6 +95,7 @@ struct Token {
     STAR,
     SLASH,
     CONCAT,
+    MERGE,
     EQEQ,
     NE,
     LT,
@@ -173,6 +174,10 @@ public:
         tokens.push_back(TOKEN(CONCAT));
         pos += 2;
         col += 2;
+      } else if (c == '/' && pos + 1 < input.size() && input[pos + 1] == '/') {
+        tokens.push_back(TOKEN(MERGE));
+        pos += 2;
+        col += 2;
       } else if (c == '&' && pos + 1 < input.size() && input[pos + 1] == '&') {
         tokens.push_back(TOKEN(AND));
         pos += 2;
@@ -237,13 +242,13 @@ public:
       } else if (isalpha(c)) {
         // Check if it's a URI (contains ://) - look ahead
         size_t lookahead = pos;
-        while (lookahead < input.size() && (isalnum(input[lookahead]) || input[lookahead] == '_' ||
-                                             input[lookahead] == '-' || input[lookahead] == '+' ||
-                                             input[lookahead] == '.'))
+        while (lookahead < input.size() &&
+               (isalnum(input[lookahead]) || input[lookahead] == '_' || input[lookahead] == '-' ||
+                input[lookahead] == '+' || input[lookahead] == '.'))
           lookahead++;
         std::string potential_scheme = input.substr(pos, lookahead - pos);
-        if (lookahead + 2 < input.size() && input[lookahead] == ':' && input[lookahead + 1] == '/' &&
-            input[lookahead + 2] == '/') {
+        if (lookahead + 2 < input.size() && input[lookahead] == ':' &&
+            input[lookahead + 1] == '/' && input[lookahead + 2] == '/') {
           // It's a URI, consume the whole thing
           tokenize_uri();
         } else {
@@ -267,7 +272,7 @@ private:
   size_t line;
   size_t col;
 
-  void emit(Token t) {
+  void emit(const Token& t) {
     tokens.push_back(t);
     pos++;
     col++;
@@ -394,7 +399,7 @@ private:
   void tokenize_ident() {
     size_t start = pos;
     while (pos < input.size() && (isalnum(input[pos]) || input[pos] == '_' || input[pos] == '-' ||
-                                   input[pos] == '+' || input[pos] == '.'))
+                                  input[pos] == '+' || input[pos] == '.'))
       pos++;
     std::string ident = input.substr(start, pos - start);
 
@@ -471,6 +476,8 @@ public:
   // Get operator precedence (higher = tighter binding)
   int get_precedence(Token::Type type) {
     switch (type) {
+    case Token::MERGE:
+      return 1; // Low precedence - binds loosely, but must be > 0 to be recognized as binary op
     case Token::OR:
       return 1;
     case Token::AND:
@@ -511,6 +518,8 @@ public:
       return BinaryOp::DIV;
     case Token::CONCAT:
       return BinaryOp::CONCAT;
+    case Token::MERGE:
+      return BinaryOp::MERGE;
     case Token::EQEQ:
       return BinaryOp::EQ;
     case Token::NE:

src/irc/types.h

@@ -43,7 +43,23 @@ enum class NodeType : uint8_t {
   ERROR = 0xFF
 };
 
-enum class BinaryOp : uint8_t { ADD, SUB, MUL, DIV, CONCAT, EQ, NE, LT, GT, LE, GE, AND, OR, IMPL };
+enum class BinaryOp : uint8_t {
+  ADD,
+  SUB,
+  MUL,
+  DIV,
+  CONCAT,
+  EQ,
+  NE,
+  LT,
+  GT,
+  LE,
+  GE,
+  AND,
+  OR,
+  IMPL,
+  MERGE
+};
 
 enum class UnaryOp : uint8_t { NEG, NOT };
 
@@ -203,11 +219,11 @@ struct ForceNode {
 // Node wraps a variant for type-safe AST
 class Node {
 public:
-  using Variant = std::variant<ConstIntNode, ConstFloatNode, ConstStringNode, ConstPathNode,
-                               ConstBoolNode, ConstNullNode, ConstURINode, VarNode, LambdaNode,
-                               AppNode, BinaryOpNode, UnaryOpNode, AttrsetNode, SelectNode,
-                               HasAttrNode, WithNode, IfNode, LetNode, LetRecNode, AssertNode,
-                               ThunkNode, ForceNode>;
+  using Variant =
+      std::variant<ConstIntNode, ConstFloatNode, ConstStringNode, ConstPathNode, ConstBoolNode,
+                   ConstNullNode, ConstURINode, VarNode, LambdaNode, AppNode, BinaryOpNode,
+                   UnaryOpNode, AttrsetNode, SelectNode, HasAttrNode, WithNode, IfNode, LetNode,
+                   LetRecNode, AssertNode, ThunkNode, ForceNode>;
 
   Variant data;