add top 20

terraform · Jul 17, 2026 · c5179bf · c5179bf
1 parent ef39e3f
commit c5179bf
Showing 1 changed file with 32 additions and 6 deletions.
diff --git a/local-app/python-tools/cross-organization/assess_check_s3_buckets.py b/local-app/python-tools/cross-organization/assess_check_s3_buckets.py
@@ -9,7 +9,7 @@
 from collections import defaultdict
 
 # --- VERSIONING ---
-__version__ = "1.2.2"
+__version__ = "1.3.0"
 
 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 v1.2.2")
+    parser = argparse.ArgumentParser(description="AWS S3 Fleet Storage Filtered Assessor Suite v1.3.0")
     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)")
@@ -149,13 +149,39 @@ def main():
             tf.write(fmt_tier.format(s_tier, scaled_tier_size, share))
         tf.write("\n")
 
-        # --- FIXED: Use clean pre-compiled f-string masks to inject tracking widths safely ---
-        tf.write("[SECTION 4: GRANULAR BUCKET METADATA INVENTORY MATRIX]\n")
+        # --- NEW SECTION 5: TOP 20 LARGEST BUCKETS ---
+        tf.write("[SECTION 5: 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"
+        fmt_top_size_data   = f"  #{{:<3}} | {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18{size_data_spec}}} | {{:>12,}}\n"
+
         size_header_str = f"Size ({target_unit})"
+        tf.write(fmt_top_size_header.format("Idx", "Account ID", "Account Alias", "Bucket Name", "Region", size_header_str, "Objects"))
+        tf.write("  " + "-" * (max_alias_w + max_bucket_w + 65) + "\n")
 
-        fmt_row_header = f"  {{:<12}} | {{:<{max_alias_w}}} | {{:<{max_bucket_w}}} | {{:<12}} | {{:>18}} | {{:>12}} | {{:<10}} | {{:<13}}\n"
+        largest_buckets = sorted(flat_rows, key=lambda x: x[5], reverse=True)[:20]
+        for idx, r in enumerate(largest_buckets, start=1):
+            scaled_bucket_size = r[5] if target_unit == "B" else (r[5] / divisor)
+            tf.write(fmt_top_size_data.format(idx, r[0], r[1], r[2], r[3], scaled_bucket_size, r[6]))
+        tf.write("\n")
+
+        # --- NEW SECTION 6: TOP 20 BUCKETS BY TOTAL OBJECT COUNT ---
+        tf.write("[SECTION 6: 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"
 
-        size_data_spec = ",d" if target_unit == "B" else ",.2f"
+        tf.write(fmt_top_obj_header.format("Idx", "Account ID", "Account Alias", "Bucket Name", "Region", size_header_str, "Objects"))
+        tf.write("  " + "-" * (max_alias_w + max_bucket_w + 65) + "\n")
+
+        most_populated = sorted(flat_rows, key=lambda x: x[6], reverse=True)[:20]
+        for idx, r in enumerate(most_populated, start=1):
+            scaled_bucket_size = r[5] if target_unit == "B" else (r[5] / divisor)
+            tf.write(fmt_top_obj_data.format(idx, r[0], r[1], r[2], r[3], scaled_bucket_size, r[6]))
+        tf.write("\n")
+
+        # Section 4: Master Matrix Table
+        tf.write("[SECTION 4: 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"
 
         tf.write(fmt_row_header.format("Account ID", "Account Alias", "Bucket Name", "Region", size_header_str, "Objects", "Version", "Lifecycle"))