fix regex parser error

internal/bootstrap.cm

@@ -1,4 +1,4 @@
-// Hidden vars (os, args, core_path) come from env
+// Hidden vars (os, args, core_path, use_mcode) come from env
 // args[0] = script name, args[1..] = user args
 var load_internal = os.load_internal
 function use_embed(name) {
@@ -27,6 +27,14 @@ var par_path = core_path + "/parse.cm"
 var tokenize_mod = mach_eval("tokenize", text(fd.slurp(tok_path)), {use: use_basic})
 var parse_mod = mach_eval("parse", text(fd.slurp(par_path)), {use: use_basic})
 
+// Optionally load mcode compiler module
+var mcode_mod = null
+var mcode_path = null
+if (use_mcode) {
+  mcode_path = core_path + "/mcode.cm"
+  mcode_mod = mach_eval("mcode", text(fd.slurp(mcode_path)), {use: use_basic})
+}
+
 // analyze: tokenize + parse, check for errors
 function analyze(src, filename) {
   var tok_result = tokenize_mod(src, filename)
@@ -61,6 +69,16 @@ function analyze(src, filename) {
   return ast
 }
 
+// Run AST through either mcode or mach pipeline
+function run_ast(name, ast, env) {
+  var compiled = null
+  if (use_mcode) {
+    compiled = mcode_mod(ast)
+    return mcode_run(name, json.encode(compiled), env)
+  }
+  return mach_eval_ast(name, json.encode(ast), env)
+}
+
 // use() with ƿit pipeline for .cm modules
 function use(path) {
   var file_path = path + '.cm'
@@ -77,7 +95,7 @@ function use(path) {
   if (fd.is_file(file_path)) {
     script = text(fd.slurp(file_path))
     ast = analyze(script, file_path)
-    result = mach_eval_ast(path, json.encode(ast), {use: use})
+    result = run_ast(path, ast, {use: use})
     use_cache[path] = result
     return result
   }
@@ -105,4 +123,4 @@ while (_j < length(args)) {
 
 var script = text(fd.slurp(script_file))
 var ast = analyze(script, script_file)
-mach_eval_ast(program, json.encode(ast), {use: use, args: user_args, json: json})
+run_ast(program, ast, {use: use, args: user_args, json: json})

parse.cm

@@ -357,7 +357,11 @@ var parse = function(tokens, src, filename) {
       }
       node.pattern = pattern_str
       if (length(flags) > 0) node.flags = flags
-      advance()
+      // Skip all tokens consumed by the regex re-scan
+      while (true) {
+        advance()
+        if (tok.kind == "eof" || tok.at >= rpos) break
+      }
       ast_node_end(node)
       return node
     }

source/cell.c

@@ -295,7 +295,7 @@ static void print_usage(const char *prog)
   printf("Options:\n");
   printf("  --ast <code|file>          Output AST as JSON\n");
   printf("  --tokenize <code|file>     Output token array as JSON\n");
-  printf("  --mcode <code|file>        Output MCODE IR as JSON\n");
+  printf("  --mcode <script> [args]    Run through mcode compilation pipeline\n");
   printf("  --run-mcode <code|file>    Compile and run through MCODE interpreter\n");
   printf("  --mach <code|file>         Output MACH bytecode\n");
   printf("  --mach-run <code|file>     Compile and run through MACH VM\n");
@@ -420,66 +420,6 @@ int cell_init(int argc, char **argv)
     }
   }
 
-  /* Check for --mcode flag to output MCODE JSON IR */
-  if (argc >= 3 && strcmp(argv[1], "--mcode") == 0) {
-    const char *script_or_file = argv[2];
-    char *script = NULL;
-    char *allocated_script = NULL;
-    const char *filename = "<eval>";
-
-    struct stat st;
-    if (stat(script_or_file, &st) == 0 && S_ISREG(st.st_mode)) {
-      FILE *f = fopen(script_or_file, "r");
-      if (!f) {
-        printf("Failed to open file: %s\n", script_or_file);
-        return 1;
-      }
-      allocated_script = malloc(st.st_size + 1);
-      if (!allocated_script) {
-        fclose(f);
-        printf("Failed to allocate memory for script\n");
-        return 1;
-      }
-      size_t read_size = fread(allocated_script, 1, st.st_size, f);
-      fclose(f);
-      allocated_script[read_size] = '\0';
-      script = allocated_script;
-      filename = script_or_file;
-    } else {
-      script = (char *)script_or_file;
-    }
-
-    cJSON *ast = JS_ASTTree(script, strlen(script), filename);
-    if (!ast) {
-      printf("Failed to parse AST\n");
-      free(allocated_script);
-      return 1;
-    }
-
-    if (print_tree_errors(ast)) {
-      cJSON_Delete(ast);
-      free(allocated_script);
-      return 1;
-    }
-
-    cJSON *mcode = JS_McodeTree(ast);
-    cJSON_Delete(ast);
-
-    if (!mcode) {
-      printf("Failed to generate MCODE\n");
-      free(allocated_script);
-      return 1;
-    }
-
-    char *pretty = cJSON_Print(mcode);
-    cJSON_Delete(mcode);
-    printf("%s\n", pretty);
-    free(pretty);
-
-    free(allocated_script);
-    return 0;
-  }
-
   /* Check for --run-mcode flag to execute via MCODE interpreter */
   if (argc >= 3 && strcmp(argv[1], "--run-mcode") == 0) {
     const char *filename = argv[2];
@@ -681,6 +621,13 @@ int cell_init(int argc, char **argv)
   }
 
   /* Default: run script through mach-run bootstrap pipeline */
+  int use_mcode = 0;
+  int arg_start = 1;
+  if (argc >= 3 && strcmp(argv[1], "--mcode") == 0) {
+    use_mcode = 1;
+    arg_start = 2;
+  }
+
   if (!find_cell_shop()) return 1;
 
   size_t boot_size;
@@ -720,8 +667,9 @@ int cell_init(int argc, char **argv)
   JSValue hidden_env = JS_NewObject(ctx);
   JS_SetPropertyStr(ctx, hidden_env, "os", js_os_use(ctx));
   JS_SetPropertyStr(ctx, hidden_env, "core_path", JS_NewString(ctx, core_path));
+  JS_SetPropertyStr(ctx, hidden_env, "use_mcode", JS_NewBool(ctx, use_mcode));
   JSValue args_arr = JS_NewArray(ctx);
-  for (int i = 1; i < argc; i++) {
+  for (int i = arg_start; i < argc; i++) {
     JSValue str = JS_NewString(ctx, argv[i]);
     JS_ArrayPush(ctx, &args_arr, str);
   }

source/runtime.c

@@ -10467,6 +10467,35 @@ static JSValue js_mach_eval_ast (JSContext *ctx, JSValue this_val, int argc, JSV
   return result;
 }
 
+/* mcode_run(name, mcode_json, env?) - run pre-compiled mcode JSON */
+static JSValue js_mcode_run (JSContext *ctx, JSValue this_val, int argc, JSValue *argv) {
+  if (argc < 2 || !JS_IsText (argv[0]) || !JS_IsText (argv[1]))
+    return JS_ThrowTypeError (ctx, "mcode_run requires (name, mcode_json) text arguments");
+
+  const char *name = JS_ToCString (ctx, argv[0]);
+  if (!name) return JS_EXCEPTION;
+
+  const char *json_str = JS_ToCString (ctx, argv[1]);
+  if (!json_str) {
+    JS_FreeCString (ctx, name);
+    return JS_EXCEPTION;
+  }
+
+  cJSON *mcode = cJSON_Parse (json_str);
+  JS_FreeCString (ctx, json_str);
+
+  if (!mcode) {
+    JS_FreeCString (ctx, name);
+    return JS_ThrowSyntaxError (ctx, "mcode_run: failed to parse mcode JSON");
+  }
+
+  JSValue env = (argc >= 3 && JS_IsObject (argv[2])) ? argv[2] : JS_NULL;
+  JSValue result = JS_CallMcodeTreeEnv (ctx, mcode, env);
+  cJSON_Delete (mcode);
+  JS_FreeCString (ctx, name);
+  return result;
+}
+
 /* ============================================================================
  * stone() function - deep freeze with blob support
  * ============================================================================
@@ -11561,6 +11590,7 @@ static void JS_AddIntrinsicBaseObjects (JSContext *ctx) {
     js_set_global_cfunc(ctx, "eval", js_cell_eval, 2);
     js_set_global_cfunc(ctx, "mach_eval", js_mach_eval, 3);
     js_set_global_cfunc(ctx, "mach_eval_ast", js_mach_eval_ast, 3);
+    js_set_global_cfunc(ctx, "mcode_run", js_mcode_run, 3);
     js_set_global_cfunc(ctx, "stone", js_cell_stone, 1);
     js_set_global_cfunc(ctx, "length", js_cell_length, 1);
     js_set_global_cfunc(ctx, "call", js_cell_call, 3);