chore: add Playwright test screenshots, mass test generator, update gitignore

scripts/gen_massive_test.py

@@ -0,0 +1,81 @@
+"""Generate 100 TLS flow CSV files (10000 rows each) matching TlsDB.csv column spec.
+
+Usage:
+    runtime\\python\\python.exe scripts\\gen_massive_test.py [--files 100] [--rows 10000] [--output-dir data/test_csvs]
+"""
+import sys
+import argparse
+from pathlib import Path
+
+# Allow importing from project root
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from scripts.gen_test_data import generate_row, COLUMNS, COVERAGE
+import random
+import csv
+from datetime import datetime
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Generate 100 massive TLS flow CSV files (10,000 rows each)'
+    )
+    parser.add_argument('--files', type=int, default=100,
+                        help='Number of CSV files (default: 100)')
+    parser.add_argument('--rows', type=int, default=10000,
+                        help='Rows per file (default: 10000)')
+    parser.add_argument('--output-dir', type=str, default='data/test_csvs',
+                        help='Output directory (default: data/test_csvs)')
+    parser.add_argument('--seed', type=int, default=42,
+                        help='Random seed for reproducibility (default: 42)')
+    args = parser.parse_args()
+
+    random.seed(args.seed)
+    out_dir = Path(args.output_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+    base_time = datetime(2026, 6, 1, 0, 0, 0)
+
+    total_rows = 0
+    for file_idx in range(args.files):
+        file_seed = args.seed + file_idx
+        file_rng = random.Random(file_seed)
+
+        # Generate all rows for this file
+        rows = []
+        for row_i in range(args.rows):
+            row = generate_row(total_rows + row_i, base_time)
+            rows.append(row)
+
+        # Auto-drop columns that are ALL blank
+        non_blank_cols = set()
+        for row in rows:
+            for col in COLUMNS:
+                val = row.get(col, '')
+                if val != '' and val != '+':
+                    non_blank_cols.add(col)
+        file_columns = [c for c in COLUMNS if c in non_blank_cols]
+
+        # Randomize column order per file
+        shuffled = file_columns[:]
+        file_rng.shuffle(shuffled)
+
+        # Write: test_0000.csv .. test_0099.csv
+        out_path = out_dir / f'test_{file_idx:04d}.csv'
+        with open(out_path, 'w', newline='', encoding='utf-8') as f:
+            writer = csv.DictWriter(f, fieldnames=shuffled, extrasaction='ignore')
+            writer.writeheader()
+            for row in rows:
+                writer.writerow(row)
+
+        total_rows += args.rows
+
+        if (file_idx + 1) % 10 == 0 or file_idx == 0 or file_idx == args.files - 1:
+            print(f'  [{file_idx + 1}/{args.files}] {total_rows} rows, '
+                  f'{len(shuffled)} cols, seed={file_seed}')
+
+    print(f'\nDone: {args.files} files x {args.rows} rows = {total_rows} total rows')
+    print(f'Output: {out_dir.resolve()}')
+
+
+if __name__ == '__main__':
+    main()