@@ -106,26 +106,29 @@ def build_summary(self,
106106 for task in self .tasks_summary [task_name ]:
107107 runtime_list .append (task .runtime )
108108
109-
110109 # For each input_file and output_file, append the file size to the dictionary
111110 for infile in task .input_files :
112111 extension : str = path .splitext (infile .file_id )[1 ] if '.' in infile .file_id else infile .file_id
112+ # print(f"file {infile.file_id} extension: {extension}")
113113 if extension [1 :].isnumeric ():
114114 extension = path .splitext (infile .file_id .replace (extension , '' ))[1 ]
115115
116116 # Check if the file is definetly an input
117117 assert infile .link == FileLink .INPUT , f"{ infile .file_id } is not set as input"
118118 _append_file_to_dict (extension , inputs_dict , infile .size )
119+
119120
120121 for outfile in task .output_files :
121122 extension : str = path .splitext (outfile .file_id )[1 ] if '.' in outfile .file_id else outfile .file_id
123+ # print(f"file {outfile.file_id} extension: {extension}")
122124 if extension [1 :].isnumeric ():
123125 extension = path .splitext (outfile .file_id .replace (extension , '' ))[1 ]
124126
125127 # Check if the file is definetly an output
126128 assert outfile .link == FileLink .OUTPUT , f"{ outfile .file_id } is not set as output"
127129 _append_file_to_dict (extension , outputs_dict , outfile .size )
128130
131+
129132 # Find the best fit distribution for each file type
130133 _best_fit_distribution_for_file (inputs_dict , include_raw_data )
131134 _best_fit_distribution_for_file (outputs_dict , include_raw_data )
@@ -198,7 +201,6 @@ def _append_file_to_dict(extension: str, dict_obj: Dict[str, Any], file_size: in
198201 dict_obj [extension ] = {'data' : [], 'distribution' : None }
199202 dict_obj [extension ]['data' ].append (file_size )
200203
201-
202204def _best_fit_distribution_for_file (dict_obj , include_raw_data ) -> None :
203205 """
204206 Find the best fit distribution for a file.
0 commit comments