Add capability to read sourceLanguage if exists in CLI sarif

otherwise dummy val
previously assumed never present in CLI sarif

sarif_cli/scan_tables.py

@@ -101,21 +101,14 @@ def joins_for_projects(basetables, external_info):
     else:
         repo_url = "unknown"
         project_name = pd.NA
-
-    if 'semmle.sourceLanguage' in b.project:
-        srcLang = b.project['semmle.sourceLanguage'][0]
-        allLang = ",".join(list(b.project['semmle.sourceLanguage']))
-    else: 
-        srcLang = "unknown"
-        allLang = "unknown"
     
     res = pd.DataFrame(data={
         "id"                 : e.project_id,
         "project_name"       : project_name,
         "creation_date"      : pd.Timestamp(0.0, unit='s'), # TODO: external info 
         "repo_url"           : repo_url, 
-        "primary_language"   : srcLang, # TODO: external info if CLI sarif
-        "languages_analyzed" : allLang  # TODO: external info if CLI sarif
+        "primary_language"   : b.project['semmle.sourceLanguage'][0],
+        "languages_analyzed" : ",".join(list(b.project['semmle.sourceLanguage']))
     }, index=[0])
 
     # Force all column types to ensure appropriate formatting

sarif_cli/signature.py

@@ -235,6 +235,8 @@ dummy_relatedLocations_entry = [
 
 dummy_message_entry = {'text': 'scli-dyys dummy value'}
 
+dummy_sourceLanguage = 'unknown'
+
 def fillsig_dict(args, elem, context):
     """ Fill in the missing fields in dictionary signatures.
     """
@@ -286,6 +288,10 @@ def fillsig_dict(args, elem, context):
     if 'level' in elem.keys():
         full_elem['enabled'] = elem.get('enabled', True)
 
+    if 'semmle.formatSpecifier' in elem.keys():
+        # Ensure semmle.sourceLanguage is present at least in dummy form
+        full_elem['semmle.sourceLanguage'] = elem.get('semmle.sourceLanguage', dummy_sourceLanguage)
+
     if 'versionControlProvenance' in elem.keys():
         # Ensure newlineSequences is present when versionControlProvenance is
         full_elem['newlineSequences'] = elem.get('newlineSequences', dummy_newlineSequences)

sarif_cli/signature_single_CLI.py

@@ -28,7 +28,7 @@ struct_graph_CLI = (
     ('Struct3497', ('struct', ('index', 'Int'), ('uri', 'String'))),
     ('Struct9567', ('struct', ('location', 'Struct3497'))),
     ('Array6920', ('array', (0, 'Struct5277'), (1, 'Struct9567'))),
-    ('Struct1509', ('struct', ('semmle.formatSpecifier', 'String'))),
+    ('Struct1509', ('struct', ('semmle.formatSpecifier', 'String'), ('semmle.sourceLanguage', 'String'))),
     ('Struct2774', ('struct', ('text', 'String'))),
     (   'Struct6299',
         (   'struct',