"""A declared section below markdown's sixth level keeps its own level in the plan.

K3-21 D. The NISO-STS reader wrote ONE clipped level into two places: the ATX
heading it emits, where markdown has six levels and the clip is the grammar's,
and the `OutlineMark` the declared route builds its plan from, where nothing
clips and the source's own depth is the point (`OutlineMark`'s docstring:
the level is what the tree declares, "reported rather than fixed up"). On one
standard 9 of 2 761 titled sections sit at depth 7, and the plan read them at
6 -- so `--shell-parent` gave its two depth-7 shells the ancestor one level
too high.

The heading stays clipped: `#######` matches nothing, and the extracted TEXT
does not move one character. Only the mark's level does.

`sts-deep.xml` is hand-written in an invented setting and carries no sentence
from any source.
"""

from __future__ import annotations

from pathlib import Path

from llm_ingestion_okf import extract, propose

FIXTURE = Path(__file__).parent / "fixtures" / "sts-deep.xml"

#: Every flag `okf build` turns on by default.
BUILD_DEFAULTS = dict(
    outline_run=3,
    table_grid=True,
    unit_fold=True,
    keep_table_heading=True,
    sheet_section_rows=True,
    drop_wrapped_outline=True,
    outline_gate=True,
    first_span_from_zero=True,
    close_span_gaps=True,
    contents_name=True,
)

#: The extracted headings, as they were before this rule and after it.
HEADINGS = [
    "# 1 Nivaa en",
    "## 1.1 Nivaa to",
    "### 1.11 Nivaa tre",
    "#### 1.111 Nivaa fire",
    "##### 1.1111 Nivaa fem",
    "###### 1.11111 Nivaa seks",
    "###### 1.111111 Nivaa sju foerste",
    "###### 1.111112 Nivaa sju andre",
]


def test_the_mark_carries_the_declared_depth() -> None:
    marks = extract.xml_outline(FIXTURE.name, FIXTURE.read_bytes())
    assert [mark.level for mark in marks] == [1, 2, 3, 4, 5, 6, 7, 7]


def test_the_heading_stays_markdown_and_the_text_does_not_move() -> None:
    data = FIXTURE.read_bytes()
    text = extract.extract_text(FIXTURE.name, data)
    lines = text.split("\n")
    assert [line for line in lines if line.startswith("#")] == HEADINGS
    for mark in extract.xml_outline(FIXTURE.name, data):
        assert lines[mark.line] == "#" * min(mark.level, 6) + " " + mark.title


def test_a_depth_seven_shell_points_at_its_depth_six_ancestor() -> None:
    data = FIXTURE.read_bytes()
    text = extract.extract_text(FIXTURE.name, data)
    plan = propose.build_plan(
        FIXTURE,
        text,
        data,
        okf_type="reference",
        proposed_at="2026-01-01T00:00:00Z",
        shell_parent=True,
        **BUILD_DEFAULTS,  # type: ignore[arg-type]
    )
    titles = {entry["segment_id"]: entry["title"] for entry in plan["entries"]}
    parents = {entry["title"]: titles.get(entry.get("parent_id", "")) for entry in plan["entries"]}
    assert parents["Nivaa sju foerste"] == "Nivaa seks"
    assert parents["Nivaa sju andre"] == "Nivaa seks"