"""Tests for src/cmos/cli.py — end-to-end draft reformatting.

The CLI orchestrates parser → formatter → reassemble. Tests inject a fake
formatter so no API calls happen; the goal is to pin the glue logic, not the
LLM behavior.
"""

import subprocess
import sys
from pathlib import Path

import pytest

from cmos.cli import reformat_draft
from cmos.parser import NoBibliographyError


def _fake_formatter(messy: str) -> str:
    # Deterministic fake: return a cleaned-up marker string so the output is
    # recognizable.
    return f"FORMATTED({messy.strip()})"


def test_reformat_draft_rewrites_only_bibliography_section():
    draft = """\
# My Paper

Some prose with citations.

## Bibliography

yu, charles. interior chinatown. 2020.
kwon, hyeyoung. inclusion work. 2022.
"""
    output = reformat_draft(draft, formatter=_fake_formatter)
    assert "# My Paper" in output
    assert "Some prose with citations." in output
    assert "FORMATTED(yu, charles. interior chinatown. 2020.)" in output
    assert "FORMATTED(kwon, hyeyoung. inclusion work. 2022.)" in output
    # Original messy lines must not also survive.
    assert "yu, charles. interior chinatown. 2020." not in output.replace(
        "FORMATTED(yu, charles. interior chinatown. 2020.)", ""
    )


def test_reformat_draft_preserves_sections_after_bibliography():
    draft = """\
## Bibliography

one entry.

## Appendix

appendix text.
"""
    output = reformat_draft(draft, formatter=_fake_formatter)
    assert "FORMATTED(one entry.)" in output
    assert "## Appendix" in output
    assert "appendix text." in output


def test_reformat_draft_raises_when_no_bibliography():
    with pytest.raises(NoBibliographyError):
        reformat_draft("## Intro\n\nno bib here.\n", formatter=_fake_formatter)


def test_reformat_draft_bibliography_heading_preserved():
    draft = "## Bibliography\n\nentry.\n"
    output = reformat_draft(draft, formatter=_fake_formatter)
    assert "## Bibliography" in output


def test_python_dash_m_invocation_actually_runs_main():
    """Regression test: `python -m cmos.cli` must actually invoke main().

    Without an `if __name__ == "__main__"` guard at the bottom of cli.py,
    `python -m cmos.cli` imports the module body but never calls main(),
    so the process silently exits 0 with empty stdout. That looks
    indistinguishable from a successful run that produced no output —
    the worst kind of bug, since callers assume the pipeline ran. This
    test forces the guard to exist by invoking the CLI as a subprocess
    with --help and asserting argparse actually fired.
    """
    result = subprocess.run(
        [sys.executable, "-m", "cmos.cli", "--help"],
        capture_output=True,
        text=True,
        timeout=10,
    )
    # argparse --help exits 0 whether or not main() ran, so the
    # discriminator is the stdout content. Without main(), stdout is empty.
    assert result.returncode == 0, (
        f"expected exit 0, got {result.returncode}; stderr={result.stderr!r}"
    )
    assert result.stdout, (
        "stdout was empty — `python -m cmos.cli` likely silently exited "
        "without invoking main(). Check that cli.py has an "
        '`if __name__ == "__main__": sys.exit(main())` guard at the bottom.'
    )
    assert "format" in result.stdout
    assert "usage" in result.stdout.lower()


def test_reformat_draft_preserves_order_under_concurrency():
    # With concurrent execution the formatter is called on all entries in
    # parallel; the CLI must reassemble them in input order regardless of
    # which call finishes first. This test uses a fake formatter that
    # sleeps based on the entry content so earlier entries finish AFTER
    # later ones if order were naively tied to completion.
    import time

    def slow_fake(messy: str) -> str:
        # Entries with lower index sleep longer so they finish last.
        n = int(messy.split()[-1])
        time.sleep(0.05 * (5 - n))
        return f"FORMATTED({messy})"

    draft = """\
## Bibliography

entry 0
entry 1
entry 2
entry 3
entry 4
"""
    output = reformat_draft(draft, formatter=slow_fake, concurrency=4)
    # Entries must appear in input order.
    lines = [l for l in output.splitlines() if l.startswith("FORMATTED(")]
    assert lines == [
        "FORMATTED(entry 0)",
        "FORMATTED(entry 1)",
        "FORMATTED(entry 2)",
        "FORMATTED(entry 3)",
        "FORMATTED(entry 4)",
    ]