"""Characterization tests for the legacy logreport script.

These tests pin what the script DOES today, including its quirks and one latent
bug, following Michael Feathers' method: write the test, run it, paste the actual
output in as the expectation, then name the test after what you learned.

Run:  python -m unittest add-tests-to-a-legacy-script-with-an-agent_test.py
Python 3.13, standard library only.
"""
from __future__ import annotations

import importlib.util
import io
import os
import unittest

HERE = os.path.dirname(os.path.abspath(__file__))
_spec = importlib.util.spec_from_file_location(
    "logreport", os.path.join(HERE, "add-tests-to-a-legacy-script-with-an-agent.py"))
logreport = importlib.util.module_from_spec(_spec)
_spec.loader.exec_module(logreport)

LINES = [
    "2026-09-05 14:03:11 ERROR auth: token expired user=42\n",
    "2026-09-05 14:03:12 INFO auth: refreshed user=42\n",
    "garbage line without a timestamp\n",
    "2026-09-05 14:04:00 INFO web: GET /health 200\n",
    "2026-09-05 14:05:30 WARN db: slow query 1.2s\n",
]


def run(lines):
    out = io.StringIO()
    logreport.run(lines, out)
    return out.getvalue()


class ReportCharacterization(unittest.TestCase):
    def test_report_for_five_lines_is_exactly_this(self):
        # Pasted from the first run; every character is intentional.
        self.assertEqual(run(LINES),
                         "WARN skipping line 3: 'garbage line without a timestamp'\n"
                         "lines: 5 (skipped 1)\n"
                         "  INFO     2\n"
                         "  ERROR    1\n"
                         "  WARN     1\n"
                         "first: 05/09/26 14:03:11\n"
                         "last:  05/09/26 14:05:30\n")

    def test_empty_input_prints_only_the_line_count(self):
        self.assertEqual(run([]), "lines: 0 (skipped 0)\n")

    def test_levels_sort_by_count_then_name(self):
        out = run(["2026-01-01 00:00:00 B x\n", "2026-01-01 00:00:00 A x\n",
                   "2026-01-01 00:00:00 A x\n", "2026-01-01 00:00:00 C x\n"])
        self.assertEqual(out.splitlines()[1:4], ["  A        2", "  B        1", "  C        1"])

    def test_level_match_is_case_sensitive(self):
        out = run(["2026-01-01 00:00:00 error x\n", "2026-01-01 00:00:00 ERROR x\n"])
        self.assertIn("  ERROR    1\n", out)
        self.assertIn("  error    1\n", out)

    def test_short_or_malformed_stamps_are_skipped_with_a_warning(self):
        cases = {
            "2026-9-5 14:03:11 INFO x\n": "WARN skipping line 1: '2026-9-5 14:03:11 INFO x'",
            "2026-09-05 14:03 INFO x\n": "WARN skipping line 1: '2026-09-05 14:03 INFO x'",
            "2026-09-05 14:03:11 INFO\n": "WARN skipping line 1: '2026-09-05 14:03:11 INFO'",
        }
        for line, expected in cases.items():
            with self.subTest(line=line):
                self.assertEqual(run([line]).splitlines()[0], expected)

    def test_run_resets_state_between_calls(self):
        run(LINES)
        self.assertEqual(run([]), "lines: 0 (skipped 0)\n")


class DateQuirks(unittest.TestCase):
    def test_dates_are_reformatted_to_dd_mm_yy(self):
        for iso, expected in {"2026-09-05": "05/09/26", "1999-12-31": "31/12/99",
                              "2000-01-01": "01/01/00"}.items():
            with self.subTest(iso=iso):
                self.assertEqual(logreport.fmt_date(iso), expected)

    def test_last_seen_is_wrong_across_a_month_boundary_documented_bug(self):
        # 1 September sorts before 31 August once both are DD/MM/YY strings.
        out = run(["2026-08-31 23:59:59 INFO x\n", "2026-09-01 00:00:01 INFO y\n"])
        self.assertIn("first: 01/09/26 00:00:01\n", out)   # wrong, pinned on purpose
        self.assertIn("last:  31/08/26 23:59:59\n", out)   # wrong, pinned on purpose


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