fix: Enhance error handling and logging across multiple evaluators

- Added logging for file retrieval and error handling in file.py, improving robustness during file operations.
- Implemented checks for file existence and parsing errors in general.py, enhancing reliability in JSON/YAML processing.
- Improved table comparison logic in table.py with detailed error logging for sheet loading and cell value reading.
- Enhanced metrics evaluation in slides.py with additional checks for paragraph and run counts, ensuring thorough comparison.
- Updated utils.py to include file existence checks and detailed error logging during cell value reading.

desktop_env/evaluators/metrics/general.py

@@ -298,34 +298,84 @@ def check_json(result: str, rules: Dict[str, List[Dict[str, Union[List[str], str
     """
 
     if result is None:
+        logger.warning("Result file path is None, returning 0.0")
+        return 0.
+        
+    # Check if file exists
+    if not os.path.exists(result):
+        logger.warning(f"Result file does not exist: {result}, returning 0.0")
+        return 0.
+    
+    try:
+        with open(result, 'r', encoding='utf-8') as f:
+            if is_yaml:
+                try:
+                    # Use SafeLoader instead of Loader for better security and error handling
+                    result_data: Dict[str, Any] = yaml.safe_load(f)
+                    if result_data is None:
+                        logger.warning(f"YAML file {result} is empty or contains only null values, returning 0.0")
+                        return 0.
+                except yaml.YAMLError as e:
+                    logger.error(f"YAML parsing error in file {result}: {e}")
+                    logger.error(f"File content might be corrupted or have invalid YAML syntax")
+                    return 0.
+                except Exception as e:
+                    logger.error(f"Unexpected error parsing YAML file {result}: {e}")
+                    return 0.
+            else:
+                try:
+                    result_data: Dict[str, Any] = json.load(f)
+                except json.JSONDecodeError as e:
+                    logger.error(f"JSON parsing error in file {result}: {e}")
+                    return 0.
+                except Exception as e:
+                    logger.error(f"Unexpected error parsing JSON file {result}: {e}")
+                    return 0.
+    except IOError as e:
+        logger.error(f"IO error reading file {result}: {e}")
+        return 0.
+    except Exception as e:
+        logger.error(f"Unexpected error reading file {result}: {e}")
         return 0.
-    with open(result) as f:
-        if is_yaml:
-            result: Dict[str, Any] = yaml.load(f, Loader=yaml.Loader)
-        else:
-            result: Dict[str, Any] = json.load(f)
 
     expect_rules = rules.get("expect", {})
     unexpect_rules = rules.get("unexpect", {})
 
     metric = True
     for r in expect_rules:
-        value = result
-        for k in r["key"]:
-            try:
-                value = value[k]
-            except KeyError:
-                return 0.
-        metric = metric and _match_value_to_rule(value, r)
+        value = result_data
+        try:
+            for k in r["key"]:
+                try:
+                    value = value[k]
+                except KeyError:
+                    logger.debug(f"Key '{k}' not found in result data, returning 0.0")
+                    return 0.
+                except TypeError:
+                    logger.debug(f"Cannot access key '{k}' - value is not a dictionary, returning 0.0")
+                    return 0.
+            metric = metric and _match_value_to_rule(value, r)
+        except Exception as e:
+            logger.error(f"Error processing expect rule {r}: {e}")
+            return 0.
+            
     for r in unexpect_rules:
-        value = result
-        for k in r["key"]:
-            try:
-                value = value[k]
-            except KeyError:
-                value = None
-                break
-        metric = metric and not _match_value_to_rule(value, r)
+        value = result_data
+        try:
+            for k in r["key"]:
+                try:
+                    value = value[k]
+                except KeyError:
+                    value = None
+                    break
+                except TypeError:
+                    value = None
+                    break
+            metric = metric and not _match_value_to_rule(value, r)
+        except Exception as e:
+            logger.error(f"Error processing unexpect rule {r}: {e}")
+            return 0.
+            
     return float(metric)