preprocessing_fn.py

def preprocessing_fn(inputs):
    
    def tokenize_text(text, sequence_length=MAX_SEQ_LEN):
	  ...
        return tf.reshape(tokens, [-1, sequence_length])
 
    def preprocess_bert_input(text, segment_id=0):
        input_word_ids = tokenize_text(text)
        ...        
        return (
            input_word_ids, 
            input_mask,
            input_type_ids
        )
    ...
 
    input_word_ids, input_mask, input_type_ids = \
        preprocess_bert_input(_fill_in_missing(inputs['text']))
 
    return {
        'input_word_ids': input_word_ids,
        'input_mask': input_mask,
        'input_type_ids': input_type_ids,
        'label': inputs['label']
    }