#!/bin/bash
# 分析 relay-stability 的 2 小时健康长测数据（只读）
set -u

F=/root/long2h_health.tsv
[ -f "$F" ] || { echo "  数据文件不存在: $F"; exit 0; }

echo "  文件: $F   行数: $(wc -l < "$F")"
echo "  前 3 行（看格式）:"
head -3 "$F" | sed 's/^/    /'
echo

python3 - "$F" <<'PYEOF'
import sys
from collections import Counter
from pathlib import Path

path = Path(sys.argv[1])
lines = [l.strip() for l in path.read_text(encoding="utf-8",
                                           errors="replace").splitlines()
         if l.strip()]
if not lines:
    print("  没有数据")
    raise SystemExit(0)

# 猜列：先看表头，没有表头就按 tab 切
head = lines[0].lower()
has_header = any(k in head for k in ("time", "code", "ms", "http"))
rows = lines[1:] if has_header else lines
if has_header:
    print("  表头: %s" % lines[0])
print("  样本数: %d" % len(rows))

codes = Counter()
times = []
conns = []
fails = []
for i, line in enumerate(rows, 1):
    parts = line.split("\t")
    code = None
    ms = None
    for p in parts:
        p = p.strip()
        if p.isdigit() and len(p) == 3:
            code = p
        if p.replace(".", "").isdigit() and "." in p:
            try:
                v = float(p)
                if ms is None and v < 300000:
                    ms = v
            except ValueError:
                pass
    if code:
        codes[code] += 1
        if code != "200":
            fails.append((i, line[:100]))
    if ms:
        times.append(ms)
    # 连接数：找形如 quic=N h2=M 或者单独的数字
    for p in parts:
        if "quic=" in p:
            conns.append(p.strip())

total = sum(codes.values())
ok = codes.get("200", 0)
print()
print("  ── HTTP 结果分布 ──")
for c, n in codes.most_common():
    pct = n * 100.0 / total if total else 0
    print("    %-6s %4d 次  %.1f%%" % (c, n, pct))
print("    --------")
print("    可用率: %d/%d = %.1f%%" % (ok, total, ok * 100.0 / total if total else 0))

if times:
    s = sorted(times)
    def pct(q):
        return s[min(int(len(s) * q), len(s) - 1)]
    print()
    print("  ── 耗时分布（毫秒）──")
    print("    最小 %.0f   中位 %.0f   P90 %.0f   P99 %.0f   最大 %.0f"
          % (s[0], s[len(s)//2], pct(0.9), pct(0.99), s[-1]))

if conns:
    c = Counter(conns)
    print()
    print("  ── 连接数分布（前 8）──")
    for k, n in c.most_common(8):
        print("    %-28s %d 次" % (k, n))

if fails:
    print()
    print("  ── 失败样本（最多 12 条）──")
    for i, line in fails[:12]:
        print("    第 %d 行: %s" % (i, line))
else:
    print()
    print("  ✓ 全程没有非 200")
PYEOF