replaced tokenizer json

app.py

@@ -7,11 +7,13 @@ import tree_sitter_languages  # Pre-built parsers for multiple languages
 from tokenizers import Tokenizer
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 
+
 tokenizer = Tokenizer.from_file("syntax_bpe_tokenizer.json")  # New BPE tokenizer
 model = tf.keras.models.load_model("crv3.keras")  # CNN model
 
 parser = Parser()
-parser.set_language(tree_sitter_languages.get_language("java"))
+java_lang = tree_sitter_languages.get_language("java")  # Get Java language object
+parser.set_language(java_lang)  # Set it for the parser
 
 def syntax_aware_tokenize(code):
     """Tokenizes Java code using Tree-Sitter (AST-based)."""