better reportign

local-app/python-tools/cross-organization/assess_check_s3_buckets.py

@@ -9,7 +9,7 @@
 from collections import defaultdict
 
 # --- VERSIONING ---
-__version__ = "1.3.1"
+__version__ = "1.4.0"
 
 UNIT_CONVERSION_MAP = {
     "B":  {"divisor": 1, "label": "Bytes"},
@@ -24,7 +24,7 @@ def find_latest_file(pattern):
     return max(files, key=os.path.getctime) if files else None
 
 def main():
-    parser = argparse.ArgumentParser(description="AWS S3 Fleet Storage Filtered Assessor Suite v1.3.1")
+    parser = argparse.ArgumentParser(description="AWS S3 Fleet Storage Segmented Filter Assessor Suite v1.4.0")
     parser.add_argument("--input", help="JSON file (default: latest audit_results.check_s3_buckets.*.json)")
     parser.add_argument("--size-units", default="GB", choices=["B", "MB", "GB", "TB", "PB"], 
                         help="Target size scale unit representation to output in reports (Default: GB)")
@@ -58,9 +58,15 @@ def main():
     divisor = scale_spec["divisor"]
     unit_label = scale_spec["label"]
 
-    total_buckets = 0
-    total_global_bytes = 0
-    total_global_objects = 0
+    # Global Footprint Accumulators
+    global_total_buckets = 0
+    global_total_bytes = 0
+    global_total_objects = 0
+
+    # Filtered Footprint Accumulators
+    filtered_total_buckets = 0
+    filtered_total_bytes = 0
+    filtered_total_objects = 0
 
     account_summary = defaultdict(lambda: {"count": 0, "bytes": 0, "objects": 0})
     storage_class_summary = defaultdict(int)
@@ -78,15 +84,23 @@ def main():
         max_alias_w = max(max_alias_w, len(str(alias)))
 
         for b in buckets:
+            b_bytes = b.get("size_bytes", 0)
+            b_objects = b.get("object_count", 0)
+
+            # 1. Unconditionally tally raw global metric layers
+            global_total_buckets += 1
+            global_total_bytes += b_bytes
+            global_total_objects += b_objects
+
+            # 2. Evaluate Regex filter threshold criteria
             if bucket_regex and not bucket_regex.search(b["name"]):
                 continue
 
-            total_buckets += 1
-            b_bytes = b.get("size_bytes", 0)
-            b_objects = b.get("object_count", 0)
+            # 3. Populate downstream metrics for matching resources only
+            filtered_total_buckets += 1
+            filtered_total_bytes += b_bytes
+            filtered_total_objects += b_objects
 
-            total_global_bytes += b_bytes
-            total_global_objects += b_objects
             max_bucket_w = max(max_bucket_w, len(b["name"]))
 
             account_summary[f"{alias} ({acc_id})"]["count"] += 1
@@ -101,6 +115,7 @@ def main():
                 b["versioning_status"], b["kms_key_id"], b["has_lifecycle"]
             ])
 
+    # Write Filtered Inventory CSV File
     with open(csv_filename, "w", newline="", encoding="utf-8") as cf:
         writer = csv.writer(cf)
         writer.writerow(["Account ID", "Account Alias", "Bucket Name", "Region", "ARN", f"Size ({target_unit})", "Object Count", "Versioning Status", "KMS Key ID", "Has Lifecycle"])
@@ -113,16 +128,25 @@ def main():
         tf.write(f"AWS ORGANIZATIONAL S3 METRICS STORAGE OPTIMIZATION REPORT | Source: {input_base_name}\n")
         tf.write("=" * 155 + "\n\n")
 
-        # Section 1
+        # --- SECTION 1: EXPANDED DUAL SEGMENT FOOTPRINT MATRIX ---
         tf.write("[SECTION 1: FLEET METRICS PROFILE OVERVIEW]\n")
-        if bucket_regex:
-            tf.write(f"  [FILTER ACTIVE] Target Bucket Name Regex Match Pattern: '{args.bucket_name}'\n")
-        tf.write(f"  ▶ Total Corporate S3 Buckets Managed : {total_buckets}\n")
 
-        scaled_global_size = total_global_bytes if target_unit == "B" else (total_global_bytes / divisor)
+        # Format specifiers logic map block
         fmt_spec = ",d" if target_unit == "B" else ",.2f"
-        tf.write(f"  ▶ Total Global Footprint Aggregation : {scaled_global_size:{fmt_spec}} {unit_label}\n")
-        tf.write(f"  ▶ Total Allocated Object Count       : {total_global_objects:,} Objects\n\n")
+        scaled_global_size = global_total_bytes if target_unit == "B" else (global_total_bytes / divisor)
+
+        tf.write(f"  ▶ Global Unfiltered Footprint:\n")
+        tf.write(f"     • Total S3 Buckets Managed       : {global_total_buckets} Buckets\n")
+        tf.write(f"     • Cumulative Raw Storage Volume  : {scaled_global_size:{fmt_spec}} {unit_label}\n")
+        tf.write(f"     • Aggregate Object Count         : {global_total_objects:,} Objects\n")
+
+        if bucket_regex:
+            scaled_filtered_size = filtered_total_bytes if target_unit == "B" else (filtered_total_bytes / divisor)
+            tf.write(f"\n  ▶ Filtered Subset Footprint (Match Pattern: '{args.bucket_name}'):\n")
+            tf.write(f"     • Total Matching S3 Buckets      : {filtered_total_buckets} Buckets\n")
+            tf.write(f"     • Cumulative Subset Storage Vol  : {scaled_filtered_size:{fmt_spec}} {unit_label}\n")
+            tf.write(f"     • Subset Target Object Count     : {filtered_total_objects:,} Objects\n")
+        tf.write("\n")
 
         # Section 2
         tf.write("[SECTION 2: ACCOUNT BILLING SECTOR SUMMARY BREAKDOWN]\n")
@@ -144,12 +168,12 @@ def main():
             fmt_tier = f"     • Storage Tier: {{:<30}} | Footprint ({target_unit}): {{:>17,.3f}} | Share %: {{:>8.2f}}\n"
 
         for s_tier, t_bytes in sorted(storage_class_summary.items(), key=lambda x: x[1], reverse=True):
-            share = (t_bytes / total_global_bytes * 100) if total_global_bytes > 0 else 0.0
+            share = (t_bytes / filtered_total_bytes * 100) if filtered_total_bytes > 0 else 0.0
             scaled_tier_size = t_bytes if target_unit == "B" else (t_bytes / divisor)
             tf.write(fmt_tier.format(s_tier, scaled_tier_size, share))
         tf.write("\n")
 
-        # --- RE-ORDERED SECTION 4: TOP 20 LARGEST BUCKETS ---
+        # Section 4: Top 20 Largest Buckets
         tf.write("[SECTION 4: TOP 20 LARGEST BUCKETS BY INSTALLED VOLUME FOOTPRINT]\n")
         size_data_spec = ",d" if target_unit == "B" else ",.2f"
         fmt_top_size_header = f"  {{:<4}} | {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18}} | {{:>12}}\n"
@@ -165,7 +189,7 @@ def main():
             tf.write(fmt_top_size_data.format(idx, r[0], r[1], r[2], r[3], scaled_bucket_size, r[6]))
         tf.write("\n")
 
-        # --- RE-ORDERED SECTION 5: TOP 20 BUCKETS BY TOTAL OBJECT COUNT ---
+        # Section 5: Top 20 Most Populated Buckets
         tf.write("[SECTION 5: TOP 20 MOST POPULATED BUCKETS BY ALLOCATED OBJECT DENSITY]\n")
         fmt_top_obj_header = f"  {{:<4}} | {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18}} | {{:>12}}\n"
         fmt_top_obj_data   = f"  #{{:<3}} | {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18{size_data_spec}}} | {{:>12,}}\n"
@@ -179,7 +203,7 @@ def main():
             tf.write(fmt_top_obj_data.format(idx, r[0], r[1], r[2], r[3], scaled_bucket_size, r[6]))
         tf.write("\n")
 
-        # --- RE-ORDERED SECTION 6: MASTER MATRIX TABLE ---
+        # Section 6: Master Matrix Table
         tf.write("[SECTION 6: GRANULAR BUCKET METADATA INVENTORY MATRIX]\n")
         fmt_row_header = f"  {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18}} | {{:>12}} | {{:<10}} | {{:<13}}\n"
         fmt_row_data   = f"  {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18{size_data_spec}}} | {{:>12,}} | {{:<10}} | {{:<13}}\n"