widen report

local-app/python-tools/cross-organization/assess_check_scheduling.py

@@ -1,34 +1,41 @@
-#!/usr/bin/env python
+#!/bin/env python3
+
 import json, argparse, sys, os, glob
 from collections import Counter, defaultdict
 
 # --- VERSIONING ---
-__version__ = "1.3.0"
+__version__ = "1.4.0"
 
 def find_latest_file(pattern):
     files = glob.glob(pattern)
     return max(files, key=os.path.getctime) if files else None
 
 def main():
-    parser = argparse.ArgumentParser(description="PowerSchedule Assessor - v1.3.0")
+    parser = argparse.ArgumentParser(description="PowerSchedule Assessor - v1.4.0")
     parser.add_argument("--input", help="JSON audit file")
     args = parser.parse_args()
 
     input_file = args.input or find_latest_file("audit_results.check_scheduling.*.json")
-    if not input_file: print("Error: No file found."); sys.exit(1)
+    if not input_file: 
+        print("Error: No scheduling audit file found."); sys.exit(1)
 
-    with open(input_file, 'r') as f: data = json.load(f)
+    with open(input_file, 'r') as f: 
+        data = json.load(f)
 
+    # Core Tracking
     env_matrix = defaultdict(Counter)
     env_totals = Counter()
-    type_matrix = defaultdict(Counter)
     type_totals = Counter()
 
-    # Specific group counters
-    ec2_groups = Counter({"plain": 0, "asg": 0, "eks": 0})
+    # Report 3 Matrix: resource_category -> tag_value -> env -> count
+    # Categories: "plain_ec2", "asg_ec2", "eks_ec2", "rds"
+    r3_data = defaultdict(lambda: defaultdict(lambda: defaultdict(int)))
+    category_env_totals = defaultdict(Counter)
+
     asg_names = set()
     eks_clusters = set()
     total_resources = 0
+    all_envs = set()
 
     for account in data:
         acc_id = account.get('account_id')
@@ -39,43 +46,92 @@ def main():
             tags = val.get("tags", {})
             res_type = val.get("type", "unknown")
 
-            # EKS Cluster Tracking
+            # Sub-type categorizations
+            if res_type == "eks_node": cat = "eks_ec2"
+            elif res_type == "asg_member": cat = "asg_ec2"
+            elif res_type == "rds": cat = "rds"
+            else: cat = "plain_ec2"
+
+            # EKS/ASG Metadata
             if val.get("eks_cluster") and val.get("eks_cluster") != "N/A":
                 eks_clusters.add(f"{acc_id}:{val.get('eks_cluster')}")
-
-            # EC2 Grouping Logic
-            if res_type in ["plain", "asg_member", "eks_node"]:
-                if res_type == "eks_node": ec2_groups["eks"] += 1
-                elif res_type == "asg_member": ec2_groups["asg"] += 1
-                else: ec2_groups["plain"] += 1
-                display_type = "ec2"
-            else:
-                display_type = res_type
-
-            # Metrics for reports
+            if val.get("asg_name") and val.get("asg_name") != "N/A":
+                asg_names.add(f"{acc_id}:{val.get('asg_name')}")
+
+            # Normalization
             env = tags.get('Environment') or tags.get('environment') or "Undefined"
+            all_envs.add(env)
             schedule = tags.get('PowerSchedule', "No Schedule")
+            sched_lower = schedule.lower().strip()
+
+            # Schedule Enabled Logic
+            is_enabled = sched_lower not in ["always_on", "no schedule"]
+            enabled_key = "Scheduled: True" if is_enabled else "Scheduled: False"
+
+            # Populate Matrices
             env_matrix[env][schedule] += 1
             env_totals[env] += 1
-            type_matrix[display_type][schedule] += 1
-            type_totals[display_type] += 1
+            type_totals[cat] += 1
+
+            r3_data[cat][schedule][env] += 1
+            r3_data[cat][enabled_key][env] += 1
+            category_env_totals[cat][env] += 1
+
+    sorted_envs = sorted(list(all_envs))
+    report_width = 130
 
-    # ... [Report 1 output logic preserved from v1.2.1] ...
+    # --- REPORT 1: ENVIRONMENT SUMMARY ---
+    print(f"\nREPORT 1: BREAKDOWN BY ENVIRONMENT")
+    print("-" * report_width)
+    for env in sorted_envs:
+        print(f"\nEnvironment: {env} (Total: {env_totals[env]})")
+        for sched, count in sorted(env_matrix[env].items()):
+            pct = (count / env_totals[env]) * 100
+            print(f"  {sched:<30} | {count:<5} | {pct:>5.1f}%")
 
+    # --- REPORT 2: RESOURCE TYPE SUMMARY ---
     print(f"\n\nREPORT 2: BREAKDOWN BY RESOURCE TYPE")
-    print("=" * 40)
-    for r_type in sorted(type_matrix.keys()):
-        print(f"\nResource Type: {r_type.upper()} (Total: {type_totals[r_type]})")
-        if r_type == "ec2":
-            print(f"  -> Plain: {ec2_groups['plain']} | ASG: {ec2_groups['asg']} | EKS: {ec2_groups['eks']}")
-        # ... [Matrix output logic preserved from v1.2.1] ...
-
-    print("\n" + "=" * 120)
+    print("-" * report_width)
+    for cat in sorted(type_totals.keys()):
+        print(f"Resource Group: {cat.upper():<10} | Total: {type_totals[cat]}")
+
+    # --- REPORT 3: CROSS-ENVIRONMENT MATRIX ---
+    print(f"\n\nREPORT 3: SCHEDULING MATRIX BY CATEGORY")
+    for cat in ["plain_ec2", "asg_ec2", "eks_ec2", "rds"]:
+        cat_total = type_totals[cat]
+        if cat_total == 0: continue
+
+        print(f"\n{cat.upper()} SCHEDULING DETAIL")
+        header = f"{'PowerSchedule Tag':<25} | {'Org Total':<12}"
+        for env in sorted_envs: header += f" | {env[:10]:<12}"
+        print("-" * len(header))
+        print(header)
+        print("-" * len(header))
+
+        # Sort tags so 'Scheduled: True/False' are at the bottom
+        all_tags = sorted([t for t in r3_data[cat].keys() if not t.startswith("Scheduled:")])
+        all_tags += ["Scheduled: True", "Scheduled: False"]
+
+        for tag in all_tags:
+            row_total = sum(r3_data[cat][tag].values())
+            row_pct = (row_total / cat_total) * 100
+            line = f"{tag[:25]:<25} | {row_total:<4} ({row_pct:>3.0f}%)"
+
+            for env in sorted_envs:
+                count = r3_data[cat][tag][env]
+                env_total = category_env_totals[cat][env]
+                env_pct = (count / env_total * 100) if env_total > 0 else 0
+                line += f" | {count:<3} ({env_pct:>3.0f}%)"
+            print(line)
+
+    # --- ORG SUMMARY ---
+    print("\n" + "=" * report_width)
     print(f"ORGANIZATION SUMMARY")
-    print(f"  Total Resources:         {total_resources}")
-    print(f"  Total ASGs Identified:   {len(asg_names)}")
-    print(f"  Total EKS Clusters:      {len(eks_clusters)}") # NEW
-    print(f"  Total EKS Nodes:         {ec2_groups['eks']}")  # NEW
-    print("=" * 120)
+    print(f"  Accounts Checked:    {len(data)}")
+    print(f"  Total Resources:     {total_resources}")
+    print(f"  Total ASGs:          {len(asg_names)}")
+    print(f"  Total EKS Clusters:  {len(eks_clusters)}")
+    print(f"  Total EKS Nodes:     {type_totals['eks_ec2']}")
+    print("=" * report_width)
 
 if __name__ == "__main__": main()