"""Clause 1 asks whether a title NAMES something, not whether a number ends it.

`_TRAILING_PAGE_NUMBER` reads a run of consecutive titles ending in an integer
as a contents listing and discards it. That predicate cannot tell a contents
entry from a run of DATA ROWS, because a drawing's dimension chain, a P&ID's
schematic labels, a door schedule and a borehole log's coordinate column all
end in integers too. Measured on the 43-document corpus, clause 1 dropped 68
candidates over 11 of 39 readable documents, and 19 of those 68 over 5 of the
11 were data rows whose titles -- `40.23`, `300 1`, `3000 V 1`, `619649.097`
-- name nothing at all.

Round 8 removed the DAMAGE (`--close-span-gaps` carries a removed mark's text
on the mark above), so what is left is classification. The repair is one
clause: a title is a contents entry only if a NAME survives stripping the page
number.

WHERE THE THRESHOLD SITS IS MEASURED, NOT CHOSEN. Swept over the corpus at an
alphabetic run of >= 1, >= 2 and >= 3 characters, and it collapses at both
ends: at >= 1 three data rows keep a stray single letter (`3000 V`) and stay
misclassified (13 of 19 rescued); at >= 3 a real contents list breaks, because
`VA` is a two-letter section name and dropping it out of run membership takes
`RIB`, `MMI` and `Tittelfelt` below `CONTENTS_RUN` with it -- one acronym
costing four real entries. At >= 2 the rescue is 16 of 19 and the regression 0
of 49 real entries. This file holds BOTH sides, and the second is the one that
matters: a rule that rescues a table by also rescuing contents lists has moved
the defect rather than fixed it.
"""

from __future__ import annotations

from llm_ingestion_okf import cli
from llm_ingestion_okf.propose import find_candidates

DEFAULT = dict(
    outline_run=cli.DEFAULT_OUTLINE_RUN,
    table_grid=cli.DEFAULT_TABLE_GRID,
    unit_fold=cli.DEFAULT_UNIT_FOLD,
    keep_table_heading=cli.DEFAULT_KEEP_TABLE_HEADING,
    sheet_section_rows=cli.DEFAULT_SHEET_SECTION_ROWS,
    drop_wrapped_outline=cli.DEFAULT_DROP_WRAPPED_OUTLINE,
    outline_gate=cli.DEFAULT_OUTLINE_GATE,
    first_span_from_zero=cli.DEFAULT_FIRST_SPAN_FROM_ZERO,
    close_span_gaps=cli.DEFAULT_CLOSE_SPAN_GAPS,
    contents_name=cli.DEFAULT_CONTENTS_NAME,
)

#: The borehole-log shape, rebuilt from the corpus document's geometry: a
#: coordinate column whose rows are `<northing>.<decimals>` and end in digits.
#: Five consecutive rows, comfortably over `CONTENTS_RUN`, each with a body so
#: the orphan check does not remove them first.
DATA_ROWS = """# Geoteknisk borelogg Testdokument

Dette dokumentet har en kjent struktur: en koordinatkolonne der hver rad er
et tall, og ingen av dem navngir noe som helst.

## 619482.244

Proevepunkt P20, naverboring, fire proever i sjiktet 0-4 meter.

## 619551.473

Proevepunkt P21, naverboring, tre proever i sjiktet 0-3 meter.

## 619575.846

Proevepunkt P22, naverboring, fem proever i sjiktet 0-5 meter.

## 619649.097

Proevepunkt P23, naverboring, to proever i sjiktet 0-2 meter.

## 619712.518

Proevepunkt P24, naverboring, seks proever i sjiktet 0-6 meter.
"""

#: The known-negative, and it carries the exact boundary the sweep found: a
#: real contents listing whose shortest entry is a TWO-letter section name.
#: Every one of these must still be discarded.
REAL_CONTENTS = """# Modellansvar Testdokument

Innhold

## Ansvar fagmodellansvarlig 5

## Kontaktpersoner 7

## RIB 9

## VA 11

## MMI 13

## Tittelfelt 15

Dette avsnittet staar under listen og gir den en kropp.
"""


def _titles(document: str) -> list[str]:
    return [candidate.title for candidate in find_candidates(document, **DEFAULT)]


def test_a_run_of_numeric_data_rows_is_not_a_contents_listing() -> None:
    """The known-positive: nothing survives stripping, so nothing is a name."""
    titles = _titles(DATA_ROWS)
    for row in ("619482.244", "619551.473", "619575.846", "619649.097", "619712.518"):
        assert row in titles, f"clause 1 discarded the data row {row!r} as a contents entry"


def test_a_real_contents_listing_is_still_discarded() -> None:
    """The known-negative, and the reason the threshold is 2 and not 3.

    `VA` is two letters. At an alphabetic run of >= 3 it stops being a name,
    falls out of run membership, and the run around it drops below
    `CONTENTS_RUN` -- so the whole listing survives and four real entries are
    emitted as concepts. Measured on the corpus, that is exactly what happened.
    """
    titles = _titles(REAL_CONTENTS)
    for entry in ("Ansvar fagmodellansvarlig", "Kontaktpersoner", "RIB", "VA", "MMI", "Tittelfelt"):
        assert not any(title.startswith(entry) for title in titles), (
            f"clause 1 emitted the contents entry {entry!r} as a concept"
        )