from __future__ import annotations

import sys
import unittest
from contextlib import contextmanager
from datetime import datetime, timedelta, timezone
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import patch

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

import core.toolfail as tf  # noqa: E402

NOW = datetime.now(timezone.utc)


class _FakeSession:
    """按 SQL 关键字分流两段查询:messages 段与 usage_events(tool_malformed)段。"""

    def __init__(self, msg_rows, malformed_rows):
        self._msg_rows = msg_rows
        self._malformed_rows = malformed_rows

    def execute(self, clause, params=None):
        sql = str(clause)
        rows = self._malformed_rows if "tool_malformed" in sql else self._msg_rows
        return SimpleNamespace(fetchall=lambda: rows)


def _scan(msg_rows, malformed_rows, **kw):
    @contextmanager
    def fake_scope():
        yield _FakeSession(msg_rows, malformed_rows)

    with patch.object(tf, "session_scope", fake_scope):
        return tf.scan_tool_failures(**kw)


class TestToolfailMalformed(unittest.TestCase):
    def test_malformed_rows_cluster(self):
        """usage_events 的 tool_malformed 行聚成 kind=malformed 的 cluster。"""
        err = "Expecting value: line 1 column 1 (char 0)"
        rows = [
            ("t1", "u1", NOW - timedelta(hours=1), "write", err, "].cells[1]", '"}'),
            ("t2", "u1", NOW - timedelta(hours=2), "write", err, "].merge(", '"}'),
        ]
        out = _scan([], rows, days=7, min_count=2, min_tasks=2)
        self.assertEqual(len(out), 1)
        c = out[0]
        self.assertEqual(c["tool"], "write")
        self.assertEqual(c["kind"], "malformed")
        self.assertEqual(c["count"], 2)
        self.assertEqual(c["count_24h"], 2)
        self.assertEqual(c["task_count"], 2)
        self.assertIn("…", c["sample"])  # sample = head … tail

    def test_err_signature_normalized(self):
        """报错里的行号/列号数字被归一,不同位置的同类报错聚成一条。"""
        rows = [
            ("t1", "u1", NOW, "write", "Expecting ',' delimiter: line 1 column 57 (char 56)", "h", "t"),
            ("t2", "u2", NOW, "write", "Expecting ',' delimiter: line 3 column 9 (char 88)", "h", "t"),
        ]
        out = _scan([], rows, days=7, min_count=2, min_tasks=2)
        self.assertEqual(len(out), 1)

    def test_merges_with_message_clusters(self):
        """两段数据源并存互不干扰:messages 报错与 malformed 各出各的 cluster。"""
        msg_rows = [
            ("t1", "u1", NOW, "glob", "[Error] base path not found"),
            ("t2", "u2", NOW, "glob", "[Error] base path not found"),
        ]
        mal_rows = [
            ("t3", "u1", NOW, "write", "Expecting value", "h", "t"),
            ("t4", "u2", NOW, "write", "Expecting value", "h", "t"),
        ]
        out = _scan(msg_rows, mal_rows, days=7, min_count=2, min_tasks=2)
        kinds = sorted(c["kind"] for c in out)
        self.assertEqual(kinds, ["error", "malformed"])

    def test_quiet_cluster_daily_bucket(self):
        """3 天前的畸形记录:count_24h=0(已安静),落在对应历史桶。"""
        rows = [
            ("t1", "u1", NOW - timedelta(days=3, hours=1), "write", "Expecting value", "h", "t"),
            ("t2", "u2", NOW - timedelta(days=3, hours=2), "write", "Expecting value", "h", "t"),
        ]
        out = _scan([], rows, days=7, min_count=2, min_tasks=2)
        c = out[0]
        self.assertEqual(c["count_24h"], 0)
        self.assertEqual(sum(c["daily"]), 2)
        self.assertEqual(c["daily"][-4], 2)  # 尾桶=近24h,往前退 3 桶


if __name__ == "__main__":
    unittest.main()