add --bucket-name regex filter

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

@@ -9,9 +9,8 @@
 from collections import defaultdict
 
 # --- VERSIONING ---
-__version__ = "1.1.0"
+__version__ = "1.2.0"
 
-# Strict binary byte scaling dictionary
 UNIT_CONVERSION_MAP = {
     "B":  {"divisor": 1, "label": "Bytes"},
     "MB": {"divisor": 1024**2, "label": "MB"},
@@ -25,13 +24,13 @@ 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 Unit-Normalized Assessor Suite v1.1.0")
+    parser = argparse.ArgumentParser(description="AWS S3 Fleet Storage Filtered Assessor Suite v1.2.0")
     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)")
+    parser.add_argument("--bucket-name", help="Optional regular expression pattern to filter bucket names (e.g., '^prod-.*')")
     args = parser.parse_args()
 
-    # Locate and resolve input data paths
     input_file = args.input or find_latest_file("audit_results.check_s3_buckets.*.json")
     if not input_file:
         print("Error: No input file located."); sys.exit(1)
@@ -46,7 +45,15 @@ def main():
     txt_filename = f"{os.path.splitext(input_file)[0]}.txt"
     csv_filename = f"s3_global_inventory_{timestamp_suffix}.csv"
 
-    # Setup the requested unit variables
+    # Compile the bucket filter regex if provided
+    bucket_regex = None
+    if args.bucket_name:
+        try:
+            bucket_regex = re.compile(args.bucket_name)
+        except Exception as e:
+            print(f"Error: Invalid regular expression pattern supplied for --bucket-name: {e}")
+            sys.exit(1)
+
     target_unit = args.size_units.upper()
     scale_spec = UNIT_CONVERSION_MAP[target_unit]
     divisor = scale_spec["divisor"]
@@ -72,6 +79,10 @@ def main():
         max_alias_w = max(max_alias_w, len(str(alias)))
 
         for b in buckets:
+            # --- NEW FEATURE: Apply bucket name regex filter block ---
+            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)
@@ -92,7 +103,7 @@ def main():
                 b["versioning_status"], b["kms_key_id"], b["has_lifecycle"]
             ])
 
-    # Write Master Baseline Inventory CSV File
+    # 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"])
@@ -108,6 +119,8 @@ def main():
 
         # Section 1
         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)
@@ -136,11 +149,9 @@ def main():
         tf.write("[SECTION 4: GRANULAR BUCKET METADATA INVENTORY MATRIX]\n")
         size_header_str = f"Size ({target_unit})"
 
-        # Build dynamic padding with right-aligned floating precision parameters
         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{',d' if target_unit == 'B' else ',.2f'}}} | {{:>12,}} | {{:<10}} | {{:<13}}\n"
 
-        # Inject column widths into format strings
         f_header = fmt_row_header.format("Account ID", size_header_str, "Version", "Lifecycle", max_alias_w=max_alias_w, max_bucket_w=max_bucket_w)
         tf.write(f_header.format("Account ID", "Account Alias", "Bucket Name", "Region", size_header_str, "Objects", "Version", "Lifecycle"))
 
@@ -150,7 +161,7 @@ def main():
             f_data = fmt_row_data.format(max_alias_w=max_alias_w, max_bucket_w=max_bucket_w)
             tf.write(f_data.format(r[0], r[1], r[2], r[3], scaled_bucket_size, r[6], r[7], r[9]))
 
-    print(f"[+] Output unit normalization target mapped successfully to: {target_unit}")
+    print(f"[+] Successfully evaluated total data subset across {total_buckets} matching buckets.")
     print(f"[+] Multi-Account Analytical Dashboard Saved: {txt_filename}")
     print(f"[+] Tabular Base Inventory Shared Asset Generated: {csv_filename}")