首次提交

tools/stats_jsonl.py

@@ -0,0 +1,73 @@
+# -*- coding: utf-8 -*-
+"""
+统计 数据.jsonl：成功条数、总条数、成功数据总秒数、全部数据总秒数。
+用法: python stats_jsonl.py [数据.jsonl路径]
+默认: python stats_jsonl.py 数据.jsonl
+"""
+import json
+import sys
+from collections import Counter
+
+JSONL_PATH = sys.argv[1] if len(sys.argv) > 1 else "数据.jsonl"
+
+
+def fmt(seconds):
+    """秒 → H时M分S秒，便于阅读"""
+    seconds = int(round(seconds))
+    h, rem = divmod(seconds, 3600)
+    m, s = divmod(rem, 60)
+    return f"{h}时{m}分{s}秒"
+
+
+def main():
+    total = 0
+    success = 0
+    total_sec = 0.0
+    success_sec = 0.0
+    status_counter = Counter()
+
+    try:
+        f = open(JSONL_PATH, encoding="utf-8")
+    except FileNotFoundError:
+        print(f"找不到文件: {JSONL_PATH}")
+        return
+
+    with f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                rec = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+
+            total += 1
+            status = rec.get("status")
+            status_counter[status] += 1
+
+            dur = rec.get("duration") or 0
+            try:
+                dur = float(dur)
+            except (TypeError, ValueError):
+                dur = 0.0
+            total_sec += dur
+
+            if status == "success":
+                success += 1
+                success_sec += dur
+
+    rate = (success / total * 100) if total else 0.0
+
+    print(f"文件: {JSONL_PATH}")
+    print("-" * 40)
+    print(f"总条数:        {total}")
+    print(f"成功条数:      {success}  ({rate:.1f}%)")
+    print(f"各状态明细:    {dict(status_counter)}")
+    print("-" * 40)
+    print(f"成功数据秒数:  {success_sec:.2f} 秒  ({fmt(success_sec)})")
+    print(f"全部数据秒数:  {total_sec:.2f} 秒  ({fmt(total_sec)})")
+
+
+if __name__ == "__main__":
+    main()