"""No character stands before the first concept.

Round 3 recorded it as a footnote about ONE position: under
`--drop-wrapped-outline` that document's surviving concept starts at line 18 of
302, so 940 characters of the note's opening sit in no segment. Measured across
the whole 39-document corpus it is not one position -- it is **32 of the 32
documents that get a plan at all, 159 704 characters, 9.18 % of the corpus**,
with 45 841 characters lost from a single document. A concept boundary is a
statement about where a unit BEGINS; it was never a statement that the text
above the first one belongs nowhere.

The rule: when nothing precedes the first concept, the first concept starts at
0. It adds no boundary and removes none -- only the first span's `start` moves
-- so a plan's entry count is identical either way.

OFF by default, and the reason is the round's own acceptance criterion rather
than doubt about the defect: it moves the first span of essentially every
segmented bundle, and the round budget held one K2 build, which measured the
outline gate. A default that changes every bundle's first concept without a
hit@8 measurement behind it would be exactly the move this round refused to
make elsewhere. The measured cost and the outstanding measurement are in
`docs/2026-09-09-k3-runde6-outline-gaten-og-prioren.md`.
"""

from __future__ import annotations

from llm_ingestion_okf import cli
from llm_ingestion_okf.propose import find_candidates

ARMS = dict(outline_run=3, table_grid=True, unit_fold=True)

WITH_PREAMBLE = (
    "En tittelside og et forord som ingen overskrift star foran.\n"
    "Enda en linje av det samme.\n"
    "\n"
    "## Forste avsnitt\nInnhold under.\n"
    "## Andre avsnitt\nInnhold under.\n"
)

NO_PREAMBLE = "## Forste avsnitt\nInnhold under.\n## Andre avsnitt\nInnhold under.\n"


def test_the_default_still_loses_the_preamble() -> None:
    """The defect, kept as a test so the flag's reason stays visible."""
    first = find_candidates(WITH_PREAMBLE, **ARMS)[0]
    assert first.start > 0


def test_the_first_concept_starts_at_zero() -> None:
    candidates = find_candidates(WITH_PREAMBLE, **ARMS, first_span_from_zero=True)
    assert candidates[0].start == 0
    assert WITH_PREAMBLE[candidates[0].start : candidates[0].end].startswith("En tittelside")


def test_a_document_with_no_preamble_is_untouched() -> None:
    """The known-negative, as IDENTICAL objects rather than an equal count."""
    before = find_candidates(NO_PREAMBLE, **ARMS)
    after = find_candidates(NO_PREAMBLE, **ARMS, first_span_from_zero=True)
    assert before == after
    assert before[0].start == 0


def test_the_rule_adds_and_removes_no_boundary() -> None:
    plain = find_candidates(WITH_PREAMBLE, **ARMS)
    moved = find_candidates(WITH_PREAMBLE, **ARMS, first_span_from_zero=True)
    assert [c.title for c in plain] == [c.title for c in moved]
    assert [c.end for c in plain] == [c.end for c in moved]
    assert [c.start for c in plain][1:] == [c.start for c in moved][1:]


def test_it_is_on_by_default_in_the_build_command() -> None:
    """Moved 2026-09-10, once the hit@8 number round 6 lacked was measured.

    The opt-out is asserted in `tests/test_round7_defaults.py`; here the point
    is only that the rule below is what a caller gets without saying anything.
    """
    assert cli.DEFAULT_FIRST_SPAN_FROM_ZERO is True