Add admin page overhaul and compliance schema drift check specs, compliance upload improvements, drift checker helper

backend/scripts/compliance_config.json

@@ -0,0 +1,44 @@
+{
+  "metric_categories": {
+    "1.1.1": "Logging & Monitoring",
+    "1.1.3": "Logging & Monitoring",
+    "1.4.1": "Logging & Monitoring",
+    "2.3.4i": "Vulnerability Management",
+    "2.3.6i": "Vulnerability Management",
+    "2.3.8i": "Vulnerability Management",
+    "5.2.4": "Access & MFA",
+    "5.2.5": "Access & MFA",
+    "5.2.6": "Access & MFA",
+    "5.2.7": "Access & MFA",
+    "5.2.8": "Access & MFA",
+    "5.3.4": "Endpoint Protection",
+    "5.5.4i": "Vulnerability Management",
+    "5.5.5": "Decommissioned Assets",
+    "5.8.1": "Application Security",
+    "7.1.1": "Logging & Monitoring",
+    "7.1.4": "Logging & Monitoring",
+    "7.6.13": "Disaster Recovery",
+    "7.6.16": "Disaster Recovery",
+    "Missing_AppID": "Asset Data Quality",
+    "Missing_DF": "Asset Data Quality",
+    "Missing_OS": "Asset Data Quality",
+    "5.5.2": "Other"
+  },
+  "core_cols": [
+    "Preferred - Hostname",
+    "GRANITE - IPv4_Address",
+    "GRANITE - Type",
+    "Team",
+    "Compliant",
+    "Source_Network",
+    "Vertical",
+    "GRANITE - Equip_Inst_ID",
+    "GRANITE - RESPONSIBLE_TEAM"
+  ],
+  "skip_sheets": [
+    "Summary",
+    "CMDB_9box",
+    "Vulns",
+    "Aging Dashboard"
+  ]
+}

backend/scripts/extract_xlsx_schema.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+"""
+Extract the structural schema of a compliance xlsx file as JSON.
+Usage: python3 extract_xlsx_schema.py <path_to_xlsx>
+
+Output:
+{
+  "sheets": [
+    {
+      "name": "Summary",
+      "columns": ["Metric", "Non-Compliant", "..."],
+      "metric_values": ["2.3.4i", "5.2.4", "..."]
+    },
+    {
+      "name": "2.3.4i",
+      "columns": ["Preferred - Hostname", "GRANITE - IPv4_Address", "..."]
+    }
+  ]
+}
+
+- Uses openpyxl in read-only mode.
+- Extracts sheet names, first-row column headers per sheet, and unique metric
+  values from the Summary sheet (header at row 4, data from row 5 onward).
+- On error, returns { "error": "..." } on stdout and exits with non-zero code.
+
+Dependencies: openpyxl (already in requirements.txt)
+"""
+import sys
+import json
+from openpyxl import load_workbook
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(json.dumps({"error": "No file path provided"}))
+        sys.exit(1)
+
+    filepath = sys.argv[1]
+
+    try:
+        wb = load_workbook(filepath, read_only=True, data_only=True)
+    except Exception as e:
+        print(json.dumps({"error": f"Cannot open file: {str(e)}"}))
+        sys.exit(1)
+
+    if not wb.sheetnames:
+        print(json.dumps({"error": "Workbook contains no sheets"}))
+        wb.close()
+        sys.exit(1)
+
+    sheets = []
+    for sheet_name in wb.sheetnames:
+        ws = wb[sheet_name]
+
+        # Extract first-row column headers
+        rows = list(ws.iter_rows(max_row=1, values_only=True))
+        columns = [str(c).strip() for c in rows[0] if c is not None] if rows else []
+
+        entry = {
+            "name": sheet_name,
+            "columns": columns,
+        }
+
+        # Extract metric values from the Summary sheet
+        # Summary has header at row 4, data from row 5 onward
+        if sheet_name == "Summary":
+            metric_values = []
+            header_rows = list(ws.iter_rows(min_row=4, max_row=4, values_only=True))
+            if header_rows:
+                summary_cols = [str(c).strip() if c else "" for c in header_rows[0]]
+                metric_idx = None
+                for i, col in enumerate(summary_cols):
+                    if col == "Metric":
+                        metric_idx = i
+                        break
+                if metric_idx is not None:
+                    for row in ws.iter_rows(min_row=5, values_only=True):
+                        if row[metric_idx] is not None:
+                            val = str(row[metric_idx]).strip()
+                            if val and val != "Metric":
+                                metric_values.append(val)
+            entry["metric_values"] = sorted(set(metric_values))
+
+        sheets.append(entry)
+
+    wb.close()
+    print(json.dumps({"sheets": sheets}))
+
+
+if __name__ == "__main__":
+    main()

backend/scripts/parse_compliance_xlsx.py

@@ -12,45 +12,35 @@ Output:
 }
 """
 import sys
+import os
 import json
 import re
 import pandas as pd
 from pathlib import Path
 
-METRIC_CATEGORIES = {
-    '2.3.4i':  'Vulnerability Management',
-    '2.3.6i':  'Vulnerability Management',
-    '2.3.8i':  'Vulnerability Management',
-    '5.2.4':   'Access & MFA',
-    '5.2.5':   'Access & MFA',
-    '5.2.6':   'Access & MFA',
-    '5.3.4':   'Endpoint Protection',
-    '5.5.2':   'End-of-Life OS',
-    '5.5.4i':  'Vulnerability Management',
-    '5.5.5':   'Decommissioned Assets',
-    '5.8.1':   'Application Security',
-    '7.1.1':   'Logging & Monitoring',
-    '7.6.13':  'Disaster Recovery',
-    '7.6.16':  'Disaster Recovery',
-    '1.1.1':   'Logging & Monitoring',
-    '1.1.3':   'Logging & Monitoring',
-    '1.4.1':   'Logging & Monitoring',
-    '5.2.7':   'Access & MFA',
-    '5.2.8':   'Access & MFA',
-    '7.1.4':   'Logging & Monitoring',
-    'Missing_AppID': 'Asset Data Quality',
-    'Missing_DF':    'Asset Data Quality',
-    'Missing_OS':    'Asset Data Quality',
-}
 
-# Columns that go into the main item fields — everything else becomes extra_json
-CORE_COLS = {
-    'Preferred - Hostname', 'GRANITE - IPv4_Address', 'GRANITE - Type',
-    'Team', 'Compliant', 'Source_Network', 'Vertical',
-    'GRANITE - Equip_Inst_ID', 'GRANITE - RESPONSIBLE_TEAM',
-}
+def load_config():
+    """Load parser configuration from compliance_config.json."""
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    config_path = os.path.join(script_dir, 'compliance_config.json')
 
-SKIP_SHEETS = {'Summary', 'CMDB_9box', 'Vulns', 'Aging Dashboard'}
+    try:
+        with open(config_path, 'r') as f:
+            config = json.load(f)
+    except FileNotFoundError:
+        print(f"Error: Configuration file not found: {config_path}", file=sys.stderr)
+        sys.exit(1)
+    except json.JSONDecodeError as e:
+        print(f"Error: Invalid JSON in configuration file {config_path}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    return config
+
+
+_config = load_config()
+METRIC_CATEGORIES = _config['metric_categories']
+CORE_COLS = set(_config['core_cols'])
+SKIP_SHEETS = set(_config['skip_sheets'])
 
 
 def safe_str(val):