From a3aed444c16dfe699548e7bcd1387caad5f811b2 Mon Sep 17 00:00:00 2001
From: Kristen Newbury <knewbury01@github.com>
Date: Mon, 29 May 2023 08:58:29 -0400
Subject: [PATCH] Add explicit column ordering to to_csv writes

in interfaces:
sarif-pad-aggregates
sarif-extract-scans
---
 bin/sarif-extract-scans |  3 +-
 bin/sarif-pad-aggregate |  3 +-
 sarif_cli/columns.py    | 62 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+), 2 deletions(-)
 create mode 100644 sarif_cli/columns.py

diff --git a/bin/sarif-extract-scans b/bin/sarif-extract-scans
index 7cf6376..2b7e371 100755
--- a/bin/sarif-extract-scans
+++ b/bin/sarif-extract-scans
@@ -16,6 +16,7 @@ import pathlib
 import sarif_cli.table_joins as tj
 import sarif_cli.table_joins_CLI as tj_CLI
 import sarif_cli.scan_tables as st
+from sarif_cli import columns
 import sys
 
 #
@@ -253,7 +254,7 @@ p.mkdir(exist_ok=True)
 
 def write(path, frame):
     with p.joinpath(path + ".csv").open(mode='wb') as fh:
-        frame.to_csv(fh, index=False, quoting=csv.QUOTE_NONNUMERIC)
+        frame.to_csv(fh, index=False, columns=columns.columns[path] , quoting=csv.QUOTE_NONNUMERIC)
 
 def _write_dataframes_of(tables_dataclass):
     for field in dc.fields(tables_dataclass):
diff --git a/bin/sarif-pad-aggregate b/bin/sarif-pad-aggregate
index b9c9796..4cc0385 100755
--- a/bin/sarif-pad-aggregate
+++ b/bin/sarif-pad-aggregate
@@ -11,6 +11,7 @@ import random
 
 from sarif_cli import scan_tables
 from sarif_cli import table_joins
+from sarif_cli import columns
 
 #
 # Handle arguments
@@ -133,4 +134,4 @@ for file_prefix in _extract_scans_tables.keys():
     frame = (_extract_scans_tables[file_prefix][0]
              .astype(_table_output_dtypes[file_prefix]))
     with open(csv_fname, 'w') as fh:
-        frame.to_csv(fh, index=False, quoting=csv.QUOTE_NONNUMERIC)
+        frame.to_csv(fh, index=False, columns=columns.columns[file_prefix], quoting=csv.QUOTE_NONNUMERIC)
diff --git a/sarif_cli/columns.py b/sarif_cli/columns.py
new file mode 100644
index 0000000..76634c3
--- /dev/null
+++ b/sarif_cli/columns.py
@@ -0,0 +1,62 @@
+columns = {
+    "scans" : [
+        "id",               
+        "commit_id",           
+        "project_id",          
+        "db_create_start",     
+        "db_create_stop",       
+        "scan_start_date",     
+        "scan_stop_date",       
+        "tool_name" ,           
+        "tool_version" ,        
+        "tool_query_commit_id",
+        "sarif_file_name" ,    
+        "results_count" ,      
+        "rules_count"  ,       
+],
+"results" : [
+        'id',               
+        'scan_id',          
+        'query_id',         
+        'query_kind',       
+        'query_precision',  
+        'query_severity',  
+        'query_tags',    
+        'codeFlow_id',      
+        'message'  ,        
+        'message_object'  , 
+        'location' , 
+        'source_startLine', 
+        'source_startCol',
+        'source_endLine' ,  
+        'source_endCol' , 
+        'sink_startLine' , 
+        'sink_startCol',   
+        'sink_endLine' ,   
+        'sink_endCol' ,
+        'source_object' ,  
+        'sink_object'     
+],
+"projects" : [
+        "id"     ,            
+        "project_name" ,     
+        "creation_date",     
+        "repo_url" ,          
+        "primary_language"  , 
+        "languages_analyzed" 
+],
+"codeflows" : [
+"codeflow_id",
+"codeflow_index",
+"threadflow_index",
+"location_index",
+"endColumn",
+"endLine",
+"startColumn",
+"startLine",
+"artifact_index",
+"uri",
+"uriBaseId",
+"message"
+]
+}
\ No newline at end of file