"""logreport — a deliberately legacy log summariser, kept as the subject of a tutorial.

What it does
    Reads log lines shaped like
        2026-09-05 14:03:11 ERROR auth: token expired user=42
    counts lines per level, remembers the first and last timestamp seen, warns on
    malformed lines, and prints a short report.

Inputs
    python add-tests-to-a-legacy-script-with-an-agent.py <logfile>
    or, from Python, run(lines, out) where `lines` is any iterable of strings and
    `out` is a text stream. run() is the seam added for testing; the module-level
    globals it resets are the original design.

Known quirks (deliberately preserved; the characterization tests pin them)
    * Dates are re-formatted to DD/MM/YY by string slicing.
    * "first" and "last" are chosen by comparing the DD/MM/YY strings, so the
      answer is wrong whenever the log crosses a month or year boundary.
      This is the latent bug the tutorial leaves in place.
    * Level names are matched case-sensitively; "error" and "ERROR" count apart.

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

COUNTS = {}
FIRST = None
LAST = None
BAD = 0
TOTAL = 0


def fmt_date(iso):
    # 2026-09-05 -> 05/09/26
    return iso[8:10] + "/" + iso[5:7] + "/" + iso[2:4]


def parse_line(line, out=sys.stdout):
    global FIRST, LAST, BAD, TOTAL
    TOTAL += 1
    parts = line.rstrip("\n").split(" ", 3)
    if len(parts) < 4 or len(parts[0]) != 10 or len(parts[1]) != 8:
        BAD += 1
        print("WARN skipping line %d: %r" % (TOTAL, line.rstrip("\n")), file=out)
        return
    stamp = fmt_date(parts[0]) + " " + parts[1]
    level = parts[2]
    COUNTS[level] = COUNTS.get(level, 0) + 1
    if FIRST is None or stamp < FIRST:
        FIRST = stamp
    if LAST is None or stamp > LAST:
        LAST = stamp


def report(out=sys.stdout):
    print("lines: %d (skipped %d)" % (TOTAL, BAD), file=out)
    for level in sorted(COUNTS, key=lambda k: (-COUNTS[k], k)):
        print("  %-8s %d" % (level, COUNTS[level]), file=out)
    if FIRST is not None:
        print("first: " + FIRST, file=out)
        print("last:  " + LAST, file=out)


def reset():
    global COUNTS, FIRST, LAST, BAD, TOTAL
    COUNTS = {}
    FIRST = None
    LAST = None
    BAD = 0
    TOTAL = 0


def run(lines, out=sys.stdout):
    """Seam: process `lines` and write the report to `out`. Resets the globals first."""
    reset()
    for line in lines:
        parse_line(line, out)
    report(out)


def main(argv):
    if len(argv) != 2:
        print("usage: logreport <logfile>", file=sys.stderr)
        return 1
    with open(argv[1], encoding="utf-8") as fh:
        run(fh)
    return 0


if __name__ == "__main__":
    sys.exit(main(sys.argv))