Merged in feature/print_string_when_failed_json_load (pull request #489)

Enhance universal_json_load function with detailed error handling and traceback logging

* Enhance universal_json_load function with detailed error handling and traceback logging

* Add type hint for string_dict parameter in universal_json_load function

* Update return type annotation for universal_json_load function to reflect possible return values


Approved-by: Katon Minhas

fieldExtraction/src/utils/string_utils.py

@@ -5,6 +5,7 @@ import warnings
 
 import numpy as np
 import pandas as pd
+import traceback
 
 from src.prompts import preprocessing_prompts
 import src.utils.llm_utils as llm_utils
@@ -224,15 +225,28 @@ def primary_string_to_dict(string_dict, filename):
             data.append(dict_)
     return data
 
-def universal_json_load(string_dict):
-    """Matches json dicts and list of dicts - NOT simple lists"""
+def universal_json_load(string_dict: str):
+    """Matches json dicts and list of dicts - NOT simple lists
+    Args:
+        string_dict (str): The string containing the JSON-like content.
+    Returns:
+        list[dict] | dict: The dictionary or list of dictionaries obtained from parsing the cleaned and corrected string.
+    Raises:
+        ValueError: If no valid JSON object is found in the input string. In addition,
+        the traceback as well as the offending string are printed.
+    
+    """
     match = re.search(r'\{.*\}|\[\s*?\{.*\}\s*?\]', string_dict, re.DOTALL) # Updated regex
     if match:
+        matched_str = match.group()
         try:
-            return json.loads(match.group())
-        except json.JSONDecodeError:
-            pass
-        raise ValueError("No valid JSON object found in the input string")
+            return json.loads(matched_str)
+        except json.JSONDecodeError as e:
+            print(f"Failed to parse JSON: {e}")
+            print(f"Problematic JSON string: {matched_str}")
+            print(f"Original string: {string_dict[:200]}{'...' if len(string_dict) > 200 else ''}") # Print first 200 chars
+            print(f"Traceback: {traceback.format_exc()}")
+            raise ValueError(f"JSON parsing failed: {e.msg} at position {e.pos}") from e
     else:
         return {}