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/utils.py

@@ -4,6 +4,7 @@ import functools
 import itertools
 import logging
 import operator
+import os
 import re
 import zipfile
 #import pandas as pd
@@ -33,10 +34,11 @@ V = TypeVar("Value")
 
 logger = logging.getLogger("desktopenv.metrics.utils")
 
-_xlsx_namespaces = [("oo", "http://schemas.openxmlformats.org/spreadsheetml/2006/main")
-    , ("x14", "http://schemas.microsoft.com/office/spreadsheetml/2009/9/main")
-    , ("xm", "http://schemas.microsoft.com/office/excel/2006/main")
-                    ]
+_xlsx_namespaces = [
+    ("oo", "http://schemas.openxmlformats.org/spreadsheetml/2006/main"),
+    ("x14", "http://schemas.microsoft.com/office/spreadsheetml/2009/9/main"),
+    ("xm", "http://schemas.microsoft.com/office/excel/2006/main")
+]
 _xlsx_ns_mapping = dict(_xlsx_namespaces)
 _xlsx_ns_imapping = dict(map(lambda itm: (itm[1], itm[0]), _xlsx_namespaces))
 _xlsx_ns_imapping["http://schemas.openxmlformats.org/spreadsheetml/2006/main"] = None
@@ -282,6 +284,13 @@ _shared_str_value_selector = lxml.cssselect.CSSSelector("oo|t", namespaces=_xlsx
 
 def read_cell_value(xlsx_file: str, sheet_name: str, coordinate: str) -> Any:
     #  read_cell_value {{{ # 
+    logger.debug(f"Reading cell value from {xlsx_file}, sheet: {sheet_name}, coordinate: {coordinate}")
+    
+    # Check if file exists
+    if not os.path.exists(xlsx_file):
+        logger.error(f"Excel file not found: {xlsx_file}")
+        return None
+    
     try:
         with zipfile.ZipFile(xlsx_file, "r") as z_f:
             try:
@@ -308,9 +317,17 @@ def read_cell_value(xlsx_file: str, sheet_name: str, coordinate: str) -> Any:
                                                , namespaces=_xlsx_ns_mapping
                                                )(sheet)
                 if len(cells) == 0:
+                    logger.debug(f"Cell {coordinate} not found in sheet {sheet_name}")
                     return None
                 cell: _Element = cells[0]
-    except zipfile.BadZipFile:
+    except zipfile.BadZipFile as e:
+        logger.error(f"Bad zip file {xlsx_file}: {e}")
+        return None
+    except KeyError as e:
+        logger.error(f"Sheet {sheet_name} not found in {xlsx_file}: {e}")
+        return None
+    except Exception as e:
+        logger.error(f"Error reading {xlsx_file}: {e}")
         return None
 
     cell: Dict[str, str] = xmltodict.parse(lxml.etree.tostring(cell, encoding="unicode")