try a reduced signature for better compatibility with sarif variations

This doesn't help; sarif is just too dynamic.  Try a pull parser instead.

bin/sarif-extract-scans

@@ -2,7 +2,8 @@
 """ Extract scan data from multiple sarif files in table form.
 """
 from dataclasses import dataclass
-from sarif_cli import signature, signature_single, signature_single_CLI
+from sarif_cli import signature, signature_single, signature_single_CLI, \
+    signature_table_joins_CLI
 from sarif_cli import typegraph
 from sarif_cli import snowflake_id
 from sarif_cli import status_writer
@@ -128,9 +129,12 @@ if args.input_signature == "LGTM":
     signature_to_use = signature_single.struct_graph_LGTM
     start_node = signature_single.start_node_LGTM
 else:
-    #signature_to_use = signature_single.struct_graph_CLI
-    signature_to_use = signature_single_CLI.struct_graph_CLI
+    # #signature_to_use = signature_single.struct_graph_CLI
+    # signature_to_use = signature_single_CLI.struct_graph_CLI
+    # start_node = signature_single_CLI.start_node_CLI
+    signature_to_use = signature_table_joins_CLI.struct_graph_CLI
     start_node = signature_single_CLI.start_node_CLI
+
 #
 # Use reference type graph (signature) to traverse sarif and attach values to tables
 try:

sarif_cli/signature_table_joins_CLI.py

@@ -0,0 +1,122 @@
+"""Reduced signature graph limited to the types used by table_joins_CLI.
+
+This is derived from signature_single_CLI.struct_graph_CLI by keeping only the
+fields that are reachable from the joins implemented in table_joins_CLI.
+"""
+
+start_node_CLI = 'Struct5521'
+
+struct_graph_CLI = (
+    [   ('String', 'string'),
+        ('Int', 'int'),
+        ('Bool', 'bool'),
+        ('Array7069', ('array', (0, 'String'))),
+        (   'Struct2685',
+            (   'struct',
+                ('index', 'Int'),
+                ('uri', 'String'),
+                ('uriBaseId', 'String'))),
+        ('Struct5277', ('struct', ('location', 'Struct2685'))),
+        (   'Struct3497',
+            ('struct', ('index', 'Int'), ('uri', 'String'))),
+        ('Struct9567', ('struct', ('location', 'Struct3497'))),
+        ('Array6920', ('array', (0, 'Struct5277'), (1, 'Struct9567'))),
+        (   'Struct6299',
+            (   'struct',
+                ('endColumn', 'Int'),
+                ('endLine', 'Int'),
+                ('startColumn', 'Int'),
+                ('startLine', 'Int'))),
+        (   'Struct4963',
+            (   'struct',
+                ('artifactLocation', 'Struct2685'),
+                ('region', 'Struct6299'))),
+        ('Struct2774', ('struct', ('text', 'String'))),
+        (   'Struct2683',
+            (   'struct',
+                ('id', 'Int'),
+                ('message', 'Struct2774'),
+                ('physicalLocation', 'Struct4963'))),
+        ('Array0350', ('array', (0, 'Struct2683'))),
+        (   'Struct4199',
+            (   'struct',
+                ('primaryLocationLineHash', 'String'),
+                ('primaryLocationStartColumnFingerprint', 'String'))),
+        ('Struct3942', ('struct', ('id', 'String'), ('index', 'Int'))),
+        (   'Struct4055',
+            (   'struct',
+                ('locations', 'Array0350'),
+                ('message', 'Struct2774'),
+                ('partialFingerprints', 'Struct4199'),
+                ('relatedLocations', 'Array0350'),
+                ('rule', 'Struct3942'),
+                ('ruleId', 'String'),
+                ('ruleIndex', 'Int'))),
+        ('Struct0987', ('struct', ('location', 'Struct2683'))),
+        ('Array1075', ('array', (0, 'Struct0987'))),
+        ('Struct4194', ('struct', ('locations', 'Array1075'))),
+        ('Array1597', ('array', (0, 'Struct4194'))),
+        ('Struct7122', ('struct', ('threadFlows', 'Array1597'))),
+        ('Array9799', ('array', (0, 'Struct7122'))),
+        (   'Struct9699',
+            (   'struct',
+                ('codeFlows', 'Array9799'),
+                ('locations', 'Array0350'),
+                ('message', 'Struct2774'),
+                ('partialFingerprints', 'Struct4199'),
+                ('relatedLocations', 'Array0350'),
+                ('rule', 'Struct3942'),
+                ('ruleId', 'String'),
+                ('ruleIndex', 'Int'))),
+        ('Array1768', ('array', (2, 'Struct9699'), (1, 'Struct4055'))),
+        ('Struct1111', ('struct', ('id', 'String'))),
+        (   'Struct1509',
+            (   'struct',
+                ('semmle.formatSpecifier', 'String'),
+                ('semmle.sourceLanguage', 'String'))),
+        ('Struct8581', ('struct', ('enabled', 'Bool'), ('level', 'String'))),
+        (   'Struct6853',
+            (   'struct',
+                ('description', 'String'),
+                ('id', 'String'),
+                ('kind', 'String'),
+                ('name', 'String'),
+                ('precision', 'String'),
+                ('problem.severity', 'String'),
+                ('security-severity', 'String'),
+                ('sub-severity', 'String'),
+                ('tags', 'Array7069'))),
+        (   'Struct7100',
+            (   'struct',
+                ('defaultConfiguration', 'Struct8581'),
+                ('fullDescription', 'Struct2774'),
+                ('id', 'String'),
+                ('name', 'String'),
+                ('properties', 'Struct6853'),
+                ('shortDescription', 'Struct2774'))),
+        ('Array0147', ('array', (0, 'Struct7100'))),
+        (   'Struct7828',
+            (   'struct',
+                ('name', 'String'),
+                ('organization', 'String'),
+                ('rules', 'Array0147'),
+                ('semanticVersion', 'String'))),
+        ('Struct0032', ('struct', ('driver', 'Struct7828'))),
+        ('Struct3081', ('struct', ('repositoryUri', 'String'), ('revisionId', 'String'))),
+        ('Array5511', ('array', (0, 'Struct3081'))),
+        (   'Struct9786',
+            (   'struct',
+                ('artifacts', 'Array6920'),
+                ('automationDetails', 'Struct1111'),
+                ('columnKind', 'String'),
+                ('newlineSequences', 'Array7069'),
+                ('properties', 'Struct1509'),
+                ('results', 'Array1768'),
+                ('tool', 'Struct0032'),
+                ('versionControlProvenance', 'Array5511'))),
+        ('Array1273', ('array', (0, 'Struct9786'))),
+        (   'Struct5521',
+            (   'struct',
+                ('$schema', 'String'),
+                ('runs', 'Array1273'),
+                ('version', 'String')))] )