"""The font reader as a RESERVE: typography only where the outline gate is empty.

Round 4 measured the font reader two ways and shipped neither as a default. On
TOP of Arm D it took `pdf` from 2 of 8 to 0 of 8, because the documents it broke
already numbered their own chapters and the second heading source could only
ADD a title page and a contents listing. INSTEAD of Arm D it scored 1 of 8 but
landed one position exactly on its reference count, which is the observation
this flag comes from: use typography only where the document does not number
itself.

The mechanism is one condition, and these tests pin the condition rather than
the outcome: the reserve reads a rendering it may not have asked for only when
`outline_runs` admits nothing at the configured minimum. Everything else --
which arm ships, whether the reserve helps -- is a measurement, and the
measurement is in `docs/2026-09-08-k3-runde5-hitat8-og-skriftakse.md`.

**The reserve is OFF by default and the measurement says it must stay off**: on
the twelve-position reference it changes not one cell, because the only
positions where it fires are a PDF whose glyphs carry no ToUnicode mapping and
four office documents the PDF reader never touches.
"""

from __future__ import annotations

import warnings
from pathlib import Path

from llm_ingestion_okf import cli
from llm_ingestion_okf.extract import extract_text
from llm_ingestion_okf.propose import build_plan, heading_reserve_applies

FIXTURES = Path(__file__).parent / "fixtures"
NUMBERED_PDF = FIXTURES / "numbered-font-krav.pdf"
FONT_PDF = FIXTURES / "font-heading-krav.pdf"


def _extract(path: Path, **kwargs: object) -> str:
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        return extract_text(path.name, path.read_bytes(), **kwargs)  # type: ignore[arg-type]


# --- the condition ----------------------------------------------------------


def test_the_reserve_is_silent_where_the_document_numbers_itself() -> None:
    """The whole point: a document with its own chapter run keeps its own run."""
    assert heading_reserve_applies(_extract(NUMBERED_PDF), outline_run=3) is False


def test_the_reserve_fires_where_the_outline_gate_admits_nothing() -> None:
    assert heading_reserve_applies(_extract(FONT_PDF), outline_run=3) is True


def test_a_run_shorter_than_the_minimum_is_not_a_run() -> None:
    """The condition reads the gate as CONFIGURED, not a fixed grammar.

    The same three-chapter document is a run at 3 and not one at 4, so raising
    the arm's minimum widens the reserve rather than leaving it behind.
    """
    text = _extract(NUMBERED_PDF)
    assert heading_reserve_applies(text, outline_run=4) is True


def test_with_arm_d_off_the_reserve_fires_everywhere() -> None:
    """`--outline-run 0` admits no run at all, so the reserve is unconditional.

    Stated rather than left to the reader: that configuration IS round 4's
    "font instead of Arm D", which measured 1 of 8. A caller combining the two
    flags gets that, and gets it deliberately.
    """
    assert heading_reserve_applies(_extract(NUMBERED_PDF), outline_run=0) is True


# --- the effect on a plan ---------------------------------------------------


def _entries(text: str) -> list[str]:
    plan = build_plan(
        Path("x.pdf"),
        text,
        b"",
        okf_type="reference",
        proposed_at="1970-01-01T00:00:00Z",
        outline_run=3,
        table_grid=True,
        unit_fold=True,
    )
    return [str(entry["title"]) for entry in plan["entries"]]


def test_the_numbered_document_is_segmented_by_its_own_numbering() -> None:
    """The reserve buys nothing here, and that is the guarantee, not a defect.

    Measured rather than assumed, and the measurement is stronger than the
    guarantee: at the build default this fixture lands on the same three units
    from BOTH renderings, because the outline arm's run wins the document and
    the fold puts the font-inferred `Forord` inside the first unit rather than
    beside it. So the reserve's silence here has two independent reasons, and
    only one of them -- the condition -- is what this flag controls. The
    condition itself is pinned above, on the extraction, where it is decided.
    """
    assert _entries(_extract(NUMBERED_PDF)) == ["Generelle krav", "Merking", "Vedlegg"]
    assert _entries(_extract(NUMBERED_PDF, pdf_headings=True)) == [
        "Generelle krav",
        "Merking",
        "Vedlegg",
    ]


# --- the flag ---------------------------------------------------------------


def test_the_build_default_does_not_reach_the_reserve() -> None:
    """Every byte-pinned golden depends on this, so it is a test and not a note."""
    assert cli.DEFAULT_PDF_HEADINGS is False
    assert cli.DEFAULT_PDF_HEADINGS_RESERVE is False


def test_the_reserve_is_reachable_from_the_build_command(tmp_path: Path) -> None:
    """`--pdf-headings font-reserve` is a third value on the same axis.

    One axis, three values, because `none`, `font` and `font-reserve` are three
    answers to one question -- how a PDF's headings are recovered -- and a
    separate boolean flag would let a caller ask for two of them at once.
    """
    base = [
        "build",
        str(tmp_path),
        "--bundle",
        str(tmp_path / "b"),
        "--bundle-id",
        "x",
        "--okf-version",
        "0.2",
    ]
    assert cli.parse_args([*base, "--pdf-headings", "font-reserve"]).pdf_headings == "font-reserve"
    assert cli.parse_args([*base, "--pdf-headings", "font"]).pdf_headings == "font"
    assert cli.parse_args(base).pdf_headings == "none"


def test_the_reserve_reaches_the_proposer_and_the_door_alike(tmp_path: Path) -> None:
    """Propose and apply must choose the SAME rendering, or nothing applies.

    A plan indexes the exact string it was proposed against (`text_sha256`), so
    a reserve that fired on one side and not the other would turn every
    document it touches into a coded rejection. The build is the test: the
    unnumbered PDF must come back segmented by its typography, and the numbered
    one by its own chapters, in ONE run with ONE flag.
    """
    inbox = tmp_path / "in"
    inbox.mkdir()
    (inbox / "numbered.pdf").write_bytes(NUMBERED_PDF.read_bytes())
    (inbox / "unnumbered.pdf").write_bytes(FONT_PDF.read_bytes())
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        report = cli.build(
            inbox,
            tmp_path / "bundle",
            bundle_id="reserve-fixture",
            okf_version="0.2",
            pdf_headings_reserve=True,
        )
    assert report.rejected == 0
    names = sorted(path.name for path in (tmp_path / "bundle").rglob("*.md"))
    # The unnumbered PDF: the default leaves it one flat concept (round 4 pins
    # that), and the reserve gives it the unit its typography names.
    assert "generelle-tekniske-krav.md" in names, names
    # The numbered PDF: its own chapters, and no `Forord` the reserve added.
    assert "generelle-krav.md" in names, names
    assert "merking.md" in names, names
    assert "vedlegg.md" in names, names
    assert "forord.md" not in names, names