fix(cypher): reject unconsumed query tokens

cbm_parse previously returned success when parse_return_item stopped before postfix list indexing or an arbitrary trailing token. A query containing labels(n)[0] could therefore ignore its alias, aggregate, ordering, and limit and execute as an unbounded projection.

Require TOK_EOF after parse_post_where in src/cypher/cypher.c and transfer the parent cursor after a recursively validated UNION tail. Route both list-index rejection paths through one diagnostic that gives supported labels(n) and n.label/count(*) rewrites.

Add parser regressions in tests/test_cypher.c. Verified 155/155 Cypher tests under ASan/UBSan, all three UNION tests, source-safety, an optimized CLI rejection, and the supported five-row node-label aggregation.

Signed-off-by: Andrew Hundt <ATHundt@gmail.com>

src/cypher/cypher.c

@@ -1548,6 +1548,13 @@ static int parse_string_func_item(parser_t *p, cbm_return_item_t *item) {
     return 0;
 }
 
+static void set_unsupported_list_index_error(parser_t *p) {
+    snprintf(p->error, sizeof(p->error),
+             "unsupported expression: list indexing/slicing '[...]' is not supported; return "
+             "labels(n) AS labels directly, or group scalar node labels with RETURN n.label AS "
+             "label, count(*) AS node_count ORDER BY node_count DESC LIMIT 5");
+}
+
 static int parse_return_item(parser_t *p, cbm_return_item_t *item) {
     memset(item, 0, sizeof(*item));
     int rc = 0;
@@ -1583,8 +1590,7 @@ static int parse_return_item(parser_t *p, cbm_return_item_t *item) {
                      "trim, ltrim, rtrim, reverse, labels, type, id, keys, properties)",
                      item->variable ? item->variable : "?");
         } else {
-            snprintf(p->error, sizeof(p->error),
-                     "unsupported expression: list indexing/slicing '[...]' is not supported");
+            set_unsupported_list_index_error(p);
         }
         safe_str_free(&item->variable);
         safe_str_free(&item->property);
@@ -1880,6 +1886,8 @@ static int parse_post_where(parser_t *p, cbm_query_t *q, // NOLINT(misc-no-recur
         q->union_next = sub.query;
         sub.query = NULL;
         cbm_parse_free(&sub);
+        /* The recursive parser owns and validates the complete UNION tail. */
+        p->pos = p->count - SKIP_ONE;
     }
     return 0;
 }
@@ -1943,6 +1951,19 @@ int cbm_parse(const cbm_token_t *tokens, int token_count, // NOLINT(misc-no-recu
         return CBM_NOT_FOUND;
     }
 
+    if (!check(&p, TOK_EOF)) {
+        if (check(&p, TOK_LBRACKET)) {
+            set_unsupported_list_index_error(&p);
+            out->error = heap_strdup(p.error);
+        } else {
+            snprintf(p.error, sizeof(p.error), "unexpected trailing token '%s' at pos %d",
+                     peek(&p)->text, peek(&p)->pos);
+            out->error = heap_strdup(p.error);
+        }
+        cbm_query_free(q);
+        return CBM_NOT_FOUND;
+    }
+
     out->query = q;
     return 0;
 }

tests/test_cypher.c

@@ -2769,6 +2769,35 @@ TEST(cypher_issue240_labels_function) {
     PASS();
 }
 
+TEST(cypher_rejects_list_index_after_function_result) {
+    cbm_query_t *q = NULL;
+    char *err = NULL;
+    int rc = cbm_cypher_parse("MATCH (n) RETURN labels(n)[0] AS label, count(*) AS count "
+                              "ORDER BY count DESC LIMIT 5",
+                              &q, &err);
+    ASSERT(rc != 0);
+    ASSERT_NULL(q);
+    ASSERT_NOT_NULL(err);
+    ASSERT_NOT_NULL(strstr(err, "list indexing"));
+    ASSERT_NOT_NULL(strstr(err, "labels(n) AS labels"));
+    ASSERT_NOT_NULL(strstr(err, "n.label AS label"));
+    ASSERT_NOT_NULL(strstr(err, "count(*) AS node_count"));
+    free(err);
+    PASS();
+}
+
+TEST(cypher_rejects_unconsumed_trailing_tokens) {
+    cbm_query_t *q = NULL;
+    char *err = NULL;
+    int rc = cbm_cypher_parse("MATCH (n) RETURN n.name trailing", &q, &err);
+    ASSERT(rc != 0);
+    ASSERT_NULL(q);
+    ASSERT_NOT_NULL(err);
+    ASSERT_NOT_NULL(strstr(err, "unexpected trailing token"));
+    free(err);
+    PASS();
+}
+
 /* #237: DISTINCT applied before ORDER BY + LIMIT */
 TEST(cypher_issue237_distinct_order_limit) {
     cbm_store_t *s = setup_cypher_store();
@@ -2969,6 +2998,8 @@ SUITE(cypher) {
     /* Execution */
     RUN_TEST(cypher_exec_match_all_functions);
     RUN_TEST(cypher_issue240_labels_function);
+    RUN_TEST(cypher_rejects_list_index_after_function_result);
+    RUN_TEST(cypher_rejects_unconsumed_trailing_tokens);
     RUN_TEST(cypher_issue237_distinct_order_limit);
     RUN_TEST(cypher_issue873_distinct_order_limit_dedupes_before_limit);
     RUN_TEST(cypher_issue873_distinct_limit_dedupes_before_limit);