Merge pull request #164 from SynBioDex/test-branch

Fixed pytests

Author: CarolusVitalis

.github/workflows/python-package.yml

@@ -41,4 +41,4 @@ jobs:
       run: |
         python -m pip install -e .
         python -m pytest -vv -s
-      # python -m unittest discover -s tests
+        python -m unittest discover -s tests

README.md

@@ -1,6 +1,6 @@
 # Excel-to-SBOL
 
-**Excel-to-SBOL** is an open source python library that converts [Excel Templates](https://github.com/SynBioDex/Excel-to-SBOL/tree/master/excel2sbol/resources/templates) to [SBOL](https://sbolstandard.org/) documents.
+**Excel-to-SBOL** is an open source python library that converts [Excel Templates](https://github.com/SynBioDex/Excel-to-SBOL/tree/master/resources/templates) to [SBOL](https://sbolstandard.org/) documents.
 
 A similar utility developed for SBOL3 support (developed by Jake Beal) is in [SBOL-utilities](https://github.com/SynBioDex/SBOL-utilities).
 
@@ -31,7 +31,7 @@ To get the latest version you can use `git clone https://github.com/SynBioDex/Ex
 ## How to use
 
 **1) Choose an Excel Template**
-Choose an excel template from the [templates folder](https://github.com/SynBioDex/Excel-to-SBOL/tree/master/excel2sbol/resources/templates).
+Choose an excel template from the [templates folder](https://github.com/SynBioDex/Excel-to-SBOL/tree/master/resources/templates).
 We suggest choosing the latest version. Fill out the template as the instructions indicate. 
 
 **2) Install the Converter**
@@ -43,7 +43,7 @@ The following script asks the user for the name of the input file, version of SB
 
 If you want to use the tool in offline mode for a custom SynBioHub instance, leave the "Domain" field empty on the spreadsheet "Welcome page".
 
-[Converter File](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/excel2sbol/tests/test_files/Excel2SBOLConverter.py)
+[Converter File](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/resources/Excel2SBOLConverter.py)
 
 Tip: the use of `os.getcwd()` and `os.path.join` is recommended for the creation of the file paths. This is safer from a cybersecurity stand point and provide better operating system interoperability.
 
@@ -52,7 +52,7 @@ The SBOL file that is output can then be used by further [SBOL tools](https://sb
 
 # Example Conversion
 
-A data-filled [spreadsheet](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/excel2sbol/resources/templates/Sample_template_Excel2SBOL.xlsm) was converted to an [SBOL file](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/excel2sbol/resources/templates/Sample_template_Excel2SBOL.xml).
+A data-filled [spreadsheet](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/resources/templates/Sample_template_Excel2SBOL.xlsm) was converted to an [SBOL file](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/resources/templates/Sample_template_Excel2SBOL.xml).
 
 **Example Spreadsheet**
 ![Example Spreadsheet](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/images/sample_template.png)
@@ -74,6 +74,10 @@ Alternatively you can also make changes to the package and then use it locally:
 1. Clone the directory: `git clone https://github.com/SynBioDex/Excel-to-SBOL`
 2. Change to the excel2sbol folder: 
 
-cd ./Excel_to_SBOL/excel2sbol
+cd ./Excel_to_SBOL/src/excel2sbol
 
 3. Install an editable version of the package: `python -m pip install -e .` (will overwrite the directory in site-packages with a symbolic link to the locations repository). If a virtual environment is being used the python -m can be left off.
+
+# Excel2SBOL Paper
+
+An updated version of the Excel template referenced in the paper [Excel–SBOL Converter: Creating SBOL from Excel Templates and Vice Versa](https://pubs.acs.org/doi/full/10.1021/acssynbio.2c00521) can be found [here](https://github.com/SynBioDex/Excel-to-SBOL/blob/master/tests/test_files/sb2c00521_si_001.xlsx).

src/excel2sbol/compiler.py

@@ -130,6 +130,7 @@ def initialise(file_path_in):
         lib_df = pd.read_excel(file_path_in, sheet_name=sheet_name,
                                header=0, skiprows=skipval,
                                engine='openpyxl').fillna("")
+       
         sheet_dict['library'] = lib_df.applymap(lambda x: x.strip() if isinstance(x, str) else x).to_dict('list')
 
         # need dicitonary with as keys every column name and as values a list of values (note ordered list and need place holder empty values)
@@ -182,7 +183,10 @@ def parse_objects(col_read_df, to_convert, compiled_sheets,
 
     sbol2.Config.setOption(sbol2.ConfigOptions.SBOL_COMPLIANT_URIS, True)
     sbol2.Config.setOption(sbol2.ConfigOptions.SBOL_TYPED_URIS, False)
-
+    # print("[DEBUG]")
+    # print(compiled_sheets)
+    
+    
     for sht in to_convert:
         sht_df = col_read_df.loc[col_read_df['Sheet Name'] == sht]
 
@@ -197,6 +201,7 @@ def parse_objects(col_read_df, to_convert, compiled_sheets,
             raise KeyError(f'The sheet "{sht}" has no column with sbol_objectType as type. Thus the following error was raised: {e}')
 
         sht_convert_dict[sht] = dis_name_col
+
         ids = compiled_sheets[sht]['library'][dis_name_col]
         types = compiled_sheets[sht]['library'][obj_type_col]
 
@@ -272,7 +277,10 @@ def parse_objects3(col_read_df, to_convert, compiled_sheets,
             mol_types = None
 
         sht_convert_dict[sht] = dis_name_col
+        
         ids = compiled_sheets[sht]['library'][dis_name_col]
+
+
         obj_types = compiled_sheets[sht]['library'][obj_type_col]
 
         for ind, id in enumerate(ids):
@@ -400,7 +408,9 @@ def column_parse(to_convert, compiled_sheets, sht_convert_dict, dict_of_objs,
                     # the sbol_term of the column
                     # This creates an object with the converted cell values
                     # hierarchy: sbol term, multicolumn, column name, cell val
+                    
                     mcol = col_convert_df['Multicolumn'].values[0]
+
                     sbol_term = col_convert_df['SBOL Term'].values[0]
 
                     if hasattr(term_dict, sbol_term):

src/excel2sbol/converter.py

@@ -20,10 +20,13 @@ def converter(file_path_in, file_path_out, sbol_version=3, homespace="http://exa
 
     col_read_df, to_convert, compiled_sheets, version_info, homespace2 = e2s.initialise(file_path_in)
     dict = e2s.initialise_welcome(file_path_in)
-    for key, value in dict.items():
-        if isinstance(value, datetime):
-            dict[key] = value.isoformat()
+    # for key, value in dict.items():
+    #     if isinstance(value, datetime):
+    #         dict[key] = value.isoformat()
     if dict is not None:
+        for key, value in dict.items():
+            if isinstance(value, datetime):
+                dict[key] = value.isoformat()
         os.environ["SBOL_DICTIONARY"] = json.dumps(dict)
     # print(dict)
 

src/excel2sbol/library2.py

@@ -216,6 +216,9 @@ def displayId(rowobj):
 	password = os.getenv("SBOL_PASSWORD")
 
 	dict = os.getenv("SBOL_DICTIONARY")
+	if dict is None:
+		# print("No welcome page provided. Returning")
+		return
 	data = json.loads(dict)
 	url = data["Domain"].strip()
 	if url.endswith('/'):
@@ -496,8 +499,8 @@ def encodesFor(rowobj):
     password = os.getenv("SBOL_PASSWORD")
     url = os.getenv("SBOL_URL")
     # print(rowobj.col_cell_dict)
-    dict = os.getenv("SBOL_DICTIONARY")
-    data = json.loads(dict)
+    # dict = os.getenv("SBOL_DICTIONARY")
+    # data = json.loads(dict)
 
 
     for col in rowobj.col_cell_dict.keys():
@@ -928,8 +931,11 @@ def sequence(rowobj):
 		username = os.getenv("SBOL_USERNAME")
 		password = os.getenv("SBOL_PASSWORD")
 		url = os.getenv("SBOL_URL")
-		dict = os.getenv("SBOL_DICTIONARY")
-		data = json.loads(dict)
+		dict_env = os.getenv("SBOL_DICTIONARY")
+		data = None
+		if dict_env is not None:
+			data = json.loads(dict_env)
+		
 
 		if isinstance(val, str):
 			# might need to be careful if the object type is sequence!
@@ -957,7 +963,7 @@ def sequence(rowobj):
 				# if data["Domain"].strip() == "":
 				# 	# print("Domain not provided. Proceding without checking the domain for duplicate sequences.")
 				# 	return
-				if data["Domain"].strip() != "":
+				if data and data["Domain"].strip() != "":
 					# print("Domain provided. Proceeding with checking the domain for duplicate sequences.")
 					valid_uri = sequence_authentication(username, password, url,uri)
 					if not valid_uri:
@@ -994,8 +1000,12 @@ def proteinSequence(rowobj):
 		username = os.getenv("SBOL_USERNAME")
 		password = os.getenv("SBOL_PASSWORD")
 		url = os.getenv("SBOL_URL")
-		dict = os.getenv("SBOL_DICTIONARY")
-		data = json.loads(dict)
+		dict_env = os.getenv("SBOL_DICTIONARY")
+
+		data = None
+		if dict_env is not None:
+			data = json.loads(dict_env)
+
 		if isinstance(val, str):
 			# might need to be careful if the object type is sequence!
 			# THIS MIGHT HAVE BUGS IF MULTIPLE SEQUENCES ARE PROVIDED FOR
@@ -1023,7 +1033,7 @@ def proteinSequence(rowobj):
 				# if data["Domain"].strip() == "":
 				# 	# print("Domain not provided. Proceding without checking the domain for duplicate sequences.")
 				# 	return
-				if data["Domain"].strip() != "":
+				if data and data["Domain"].strip() != "":
 					# print("Domain provided. Proceeding with checking the domain for duplicate sequences.")
 					valid_uri = sequence_authentication(username, password, url,uri)
 					if not valid_uri: