feat: add post-generation script to preserve buffer overflow fix

Created scripts/post-generate.sh that automatically re-applies the critical
buffer overflow fix to parser.h after tree-sitter generate runs. This fix
prevents undefined behavior in set_contains() when accessing an empty array.

The script is automatically executed after tree-sitter generate via the npm
generate script. Added generate:only for cases where post-processing should
be skipped.

package.json

@@ -6,7 +6,8 @@
   "author": "Ismo Vuorinen",
   "license": "MIT",
   "scripts": {
-    "generate": "tree-sitter generate",
+    "generate": "tree-sitter generate && ./scripts/post-generate.sh",
+    "generate:only": "tree-sitter generate",
     "test": "tree-sitter test",
     "parse": "tree-sitter parse",
     "web": "tree-sitter web-ui",

scripts/post-generate.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -e
+
+echo "Running post-generation fixes..."
+
+# Apply critical safety fixes that get overwritten during generation
+echo "  - Applying critical safety fixes..."
+
+# Fix 1: Buffer overflow prevention in parser.h
+# The set_contains function needs a len==0 check to prevent accessing ranges[0]
+# This fix gets overwritten every time tree-sitter generate runs
+if ! grep -q "if (len == 0) return false;" src/tree_sitter/parser.h; then
+  # Insert the safety check right after the function opening
+  # Target: static inline bool set_contains(...) {
+  # Insert: if (len == 0) return false;
+  # Before: uint32_t index = 0;
+
+  # Use perl for cross-platform compatibility (macOS and Linux)
+  perl -i -pe '
+    BEGIN { $in_func = 0; $done = 0; }
+    if (/static inline bool set_contains/) { $in_func = 1; }
+    if ($in_func && /^\s+uint32_t index = 0;/ && !$done) {
+      print "  if (len == 0) return false;\n";
+      $done = 1;
+    }
+    if (/^}/ && $in_func) { $in_func = 0; }
+  ' src/tree_sitter/parser.h
+  echo "    ✓ Applied buffer overflow fix to parser.h"
+else
+  echo "    ✓ Buffer overflow fix already present"
+fi
+
+echo "Post-generation fixes complete!"

src/grammar.json

@@ -7923,4 +7923,4 @@
     "_primary_expression"
   ],
   "reserved": {}
-}
+}

src/node-types.json

@@ -3307,4 +3307,4 @@
     "type": "~",
     "named": false
   }
-]
+]

src/tree_sitter/array.h

@@ -62,7 +62,7 @@ extern "C" {
 /// Push a new `element` onto the end of the array.
 #define array_push(self, element)                            \
   (_array__grow((Array *)(self), 1, array_elem_size(self)), \
-   (self)->contents[(self)->size++] = (element))
+  (self)->contents[(self)->size++] = (element))
 
 /// Increase the array's size by `count` elements.
 /// New elements are zero-initialized.
@@ -218,8 +218,8 @@ static inline void _array__grow(Array *self, uint32_t count, size_t element_size
 
 /// This is not what you're looking for, see `array_splice`.
 static inline void _array__splice(Array *self, size_t element_size,
-                                 uint32_t index, uint32_t old_count,
-                                 uint32_t new_count, const void *elements) {
+                                uint32_t index, uint32_t old_count,
+                                uint32_t new_count, const void *elements) {
   uint32_t new_size = self->size + new_count - old_count;
   uint32_t old_end = index + old_count;
   uint32_t new_end = index + new_count;

src/tree_sitter/parser.h

@@ -152,6 +152,7 @@ struct TSLanguage {
 };
 
 static inline bool set_contains(const TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
+  if (len == 0) return false;
   uint32_t index = 0;
   uint32_t size = len - index;
   while (size > 1) {