restrict JSON fields templates

Signed-off-by: Sukriti-Sharma4 <[email protected]>

README.md

@@ -63,6 +63,7 @@ Once the JSON is converted using the formatting function, pass the `dataset_text
 
 2.  #### Format JSON/JSONL on the fly
    Pass a JSON/JSONL and a `data_formatter_template` to use the formatting function on the fly while tuning. The template should specify fields of JSON with `{{field}}`. While tuning, the data will be converted to a single sequence using the template.  
+   JSON fields can contain alpha-numeric characters, spaces and the following special symbols - "." , "_", "-".  
 
 Example: Train.json
 `[{ "input" : <text>,

tuning/utils/data_utils.py

@@ -31,6 +31,10 @@ def replace_text(match_obj):
 
             return element[index_object]
 
-        return {formatted_dataset_field: re.sub(r"{{(.+)}}", replace_text, template)}
+        return {
+            formatted_dataset_field: re.sub(
+                r"{{([\s0-9a-zA-Z_\-\.]+)}}", replace_text, template
+            )
+        }
 
     return dataset.map(formatter), formatted_dataset_field