llm-ingestion-okf/tests/test_content_accounting.py

"""Content accounting inside `okf build` -- the capability behind the gate.

`tools/okf_accounting_gate.py` is the judge and was written red first. These
tests pin what the gate cannot say on its own: the behaviour changes to the
file-level identity and to the exit code, the per-format inventory against the
independent witness, and that a real loss is FOUND rather than booked.
"""

from __future__ import annotations

import contextlib
import io
import json
import shutil
import sys
from pathlib import Path
from typing import Any

import pytest

from llm_ingestion_okf import accounting, cli, corpus
from llm_ingestion_okf.inbox import GateDecision

FIXTURES = Path(__file__).parent / "fixtures" / "accounting"
CORPUS = FIXTURES / "corpus"
REJECTED = FIXTURES / "rejected"


def _build(inbox: Path, tmp_path: Path, *extra: str, name: str = "bundle") -> tuple[int, Path, str]:
    bundle = tmp_path / name
    argv = [
        "build",
        str(inbox),
        "--bundle",
        str(bundle),
        "--bundle-id",
        "acc",
        "--okf-version",
        "0.2",
        *extra,
    ]
    err = io.StringIO()
    with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(err):
        code = cli.main(argv)
    return code, bundle, err.getvalue()


def _inbox(tmp_path: Path, source: Path) -> Path:
    target = tmp_path / "inbox"
    shutil.copytree(source, target)
    return target


# --- d: a file carried through a document is not also a rejection -----------


def test_a_file_carried_through_a_document_is_not_a_coded_rejection(tmp_path: Path) -> None:
    pytest.importorskip("pypandoc")
    report = cli.build(CORPUS, tmp_path / "b", bundle_id="acc", okf_version="0.2")
    assert report.carried_files == 2
    assert dict(report.codes).get("extractor_unknown", 0) == 0
    assert report.merged + report.carried_files + report.rejected == report.n
    assert report.unaccounted == ()


def test_an_unpointed_image_beside_a_document_stays_a_coded_rejection(tmp_path: Path) -> None:
    pytest.importorskip("pypandoc")
    inbox = _inbox(tmp_path, CORPUS)
    shutil.copy(inbox / "graphics" / "figur-7-1.png", inbox / "graphics" / "ubrukt.png")
    report = cli.build(inbox, tmp_path / "b", bundle_id="acc", okf_version="0.2")
    assert report.carried_files == 2
    assert dict(report.codes)["extractor_unknown"] == 1


def test_the_log_separates_carried_files_from_rejections(tmp_path: Path) -> None:
    pytest.importorskip("pypandoc")
    code, bundle, _ = _build(CORPUS, tmp_path)
    log = (bundle / "log.md").read_text(encoding="utf-8")
    assert code == 0
    assert "merged + files carried through a document + coded rejections = 20 + 2 + 0 = 22" in log
    assert "`extractor_unknown`" not in log


def test_a_corpus_without_carried_files_keeps_its_log_line(tmp_path: Path) -> None:
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    (inbox / "a.md").write_text("# A\n\nText.\n", encoding="utf-8")
    code, bundle, _ = _build(inbox, tmp_path)
    log = (bundle / "log.md").read_text(encoding="utf-8")
    assert code == 0
    assert "merged + coded rejections = 1 + 0 = 1; N = 1." in log


# --- exit code: extracted but nothing persisted ------------------------------


def test_a_build_that_persisted_nothing_it_extracted_does_not_exit_zero(tmp_path: Path) -> None:
    code, _, err = _build(REJECTED, tmp_path)
    assert code == 1
    assert "0 of 1 extracted document(s) persisted" in err


def test_the_library_door_still_reports_all_rejected_without_raising(tmp_path: Path) -> None:
    report = corpus.measure(
        REJECTED, tmp_path / "b", ingested_at="1970-01-01T00:00:00Z", gate="guard-trusted-source"
    )
    assert (report.extracted, report.persisted) == (1, 0)


def test_a_folder_holding_no_document_still_exits_zero(tmp_path: Path) -> None:
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    (inbox / "x.bin").write_bytes(b"x")
    code, _, _ = _build(inbox, tmp_path, "--segments", "off")
    assert code == 0


# --- the inventory equals the independent witness -----------------------------


def _witness(path: Path) -> dict[str, Any]:
    data: dict[str, Any] = json.loads(path.read_text(encoding="utf-8"))
    return data


#: What the witness counts and this package does not, per file type. Added
#: 2026-09-18 when the gate's witnesses were widened: rows 2 and 3 of the gate
#: are RED on exactly these, and that is the finding rather than a regression.
#: Closing one here turns this test red, which is the point -- the list is the
#: standing statement of what a bundle built by this package leaves behind.
NOT_IN_THIS_PACKAGES_VOCABULARY = {
    "comment",
    "endnote",
    "header_footer",
    "text_box",
    "note",
    "hidden_slide",
    "formula",
    "hidden_sheet",
    "annotation",
    "citation",
    "math",
    "figure",
    "figure_caption",
}


#: Shared element names on which the two now DISAGREE, with the cause of each.
#: Three are reclassifications -- the witness gives the element its own role
#: and this package still calls it the ordinary one -- and the fourth is a
#: double count this package makes. Measured 2026-09-18.
VOCABULARY_SHIFTS: dict[tuple[str, str], tuple[int, int, str]] = {
    ("notater-og-skjult.pptx", "slide"): (2, 1, "a hidden slide counts as an ordinary slide"),
    ("skjult-ark-og-formel.xlsx", "sheet"): (2, 1, "a hidden sheet counts as an ordinary sheet"),
    ("liste-og-bilde.odt", "paragraph"): (5, 4, "an annotation counts as prose"),
    (
        "topptekst-og-kommentar.docx",
        "paragraph",
    ): (
        5,
        3,
        "a text box's paragraph is counted TWICE: inside the box, and again in the "
        "paragraph that carries the box",
    ),
}


@pytest.mark.parametrize("name", sorted(_witness(FIXTURES / "inventory.json")["documents"]))
def test_the_inventory_equals_the_witness_on_every_shared_element(name: str) -> None:
    """The coupling is unchanged where the two vocabularies meet: one number
    off on a shared element is a red test unless it is in the table above,
    with its cause written down."""
    pytest.importorskip("pdfplumber")
    want = _witness(FIXTURES / "inventory.json")["documents"][name]["elements"]
    got = accounting.inventory(CORPUS, CORPUS / name).counts()
    shared = {k: v for k, v in want.items() if k not in NOT_IN_THIS_PACKAGES_VOCABULARY}
    differences = {k: (got[k], v) for k, v in shared.items() if got.get(k) != v}
    expected = {
        element: (mine, theirs)
        for (document, element), (mine, theirs, _) in VOCABULARY_SHIFTS.items()
        if document == name
    }
    assert differences == expected


@pytest.mark.parametrize("name", sorted(_witness(FIXTURES / "inventory.json")["documents"]))
def test_the_classes_this_package_does_not_count_are_named(name: str) -> None:
    """A known-negative: every element the witness counts and this package
    does not is on the list above, by name. Nothing is missing quietly."""
    pytest.importorskip("pdfplumber")
    want = _witness(FIXTURES / "inventory.json")["documents"][name]["elements"]
    got = accounting.inventory(CORPUS, CORPUS / name).counts()
    assert set(want) - set(got) <= NOT_IN_THIS_PACKAGES_VOCABULARY
    assert not set(got) - set(want), "this package counts something no witness does"


def test_the_inventory_resolves_the_files_a_document_points_at() -> None:
    got = accounting.inventory(CORPUS, CORPUS / "kapittel-7-sts.xml")
    assert got.pointed_files() == {"graphics/tabell-7-2.png", "graphics/figur-7-1.png"}


def test_the_inventory_of_an_unread_type_is_empty() -> None:
    got = accounting.inventory(CORPUS, CORPUS / "graphics" / "figur-7-1.png")
    assert got.counts() == {}


# --- the door ----------------------------------------------------------------


#: The elements this package loses from the fixture corpus, in its OWN
#: vocabulary, measured 2026-09-18 on the widened corpus. Each is a real loss
#: with a named cause, and the door exits 1 because of them -- which is the
#: behaviour the flag was built for, exercised for the first time by fixtures
#: that actually carry the constructs.
KNOWN_LOSSES = {
    ("liste-og-bilde.odt", "image"): (0, 1),
    ("liste-og-bilde.odt", "paragraph"): (4, 5),
    ("skjult-ark-og-formel.xlsx", "image"): (0, 1),
    ("topptekst-og-kommentar.docx", "footnote"): (0, 1),
    ("topptekst-og-kommentar.docx", "paragraph"): (3, 5),
}


def test_the_door_books_every_element_of_the_fixture_corpus_but_the_known_losses(
    tmp_path: Path,
) -> None:
    pytest.importorskip("pdfplumber")
    path = tmp_path / "accounting.json"
    code, _, err = _build(CORPUS, tmp_path, "--accounting", str(path))
    data = json.loads(path.read_text(encoding="utf-8"))
    assert data["accounting_version"] == 1
    assert data["double_booked"] == 0
    assert data["unaccounted"] == 6, err
    assert code == 1, "a run that loses content does not exit zero"
    found = {}
    for document in data["documents"]:
        for kind, number in document["inventory"].items():
            fate = document.get("fates", {}).get(kind, {})
            booked = (
                fate.get("carried", 0)
                + fate.get("pointer", 0)
                + sum(fate.get("rejected", {}).values())
            )
            if booked != number:
                found[(document["source_file"], kind)] = (booked, number)
    assert found == KNOWN_LOSSES
    files = {entry["source_file"]: entry["fate"] for entry in data["files"]}
    assert files == {"graphics/figur-7-1.png": "carried", "graphics/tabell-7-2.png": "carried"}
    web = next(d for d in data["documents"] if d["source_file"] == "kapittel-7-web.html")
    assert web["fates"]["image"] == {"carried": 2, "pointer": 1, "rejected": {}}


def test_the_door_writes_the_accounting_into_the_log(tmp_path: Path) -> None:
    pytest.importorskip("pdfplumber")
    _, bundle, _ = _build(CORPUS, tmp_path, "--accounting", str(tmp_path / "a.json"))
    log = (bundle / "log.md").read_text(encoding="utf-8")
    assert "* **Accounting**: 20 document(s) and 2 other file(s);" in log
    assert "6 unaccounted, 0 double-booked; 0 of 20 document(s) refused whole." in log


def test_a_rejected_document_is_logged_with_what_its_source_held(tmp_path: Path) -> None:
    code, bundle, _ = _build(REJECTED, tmp_path, "--accounting", str(tmp_path / "a.json"))
    log = (bundle / "log.md").read_text(encoding="utf-8")
    assert code == 1
    assert (
        "avvist.html: 3 elements found in the source, 0 carried: document rejected `fail_secure`"
        in log
    )
    assert "**Images**: 0 carried of 1 found" in log


def test_a_rejected_documents_elements_carry_its_code(tmp_path: Path) -> None:
    path = tmp_path / "a.json"
    _build(REJECTED, tmp_path, "--accounting", str(path))
    data = json.loads(path.read_text(encoding="utf-8"))
    (doc,) = data["documents"]
    assert (doc["status"], doc["code"]) == ("rejected", "fail_secure")
    assert doc["fates"]["paragraph"] == {"carried": 0, "pointer": 0, "rejected": {"fail_secure": 1}}
    assert data["files"] == [
        {"source_file": "graphics/figur.png", "fate": "rejected", "code": "extractor_unknown"}
    ]


def test_a_partly_refused_corpus_says_how_many_sources_it_lost(tmp_path: Path) -> None:
    """H1's other half. The gate judges the report; this pins what the report
    SAYS. One refused source beside an accepted one exits 0 -- the exit code
    belongs to the whole run and a corpus with an unreadable file in it is the
    ordinary case -- so the count has to stand in the accounting and the log,
    or the loss is silent."""
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    shutil.copy(REJECTED / "avvist.html", inbox / "avvist.html")
    shutil.copy(CORPUS / "notat.md", inbox / "notat.md")
    path = tmp_path / "a.json"
    code, bundle, _ = _build(inbox, tmp_path, "--accounting", str(path))
    data = json.loads(path.read_text(encoding="utf-8"))
    log = (bundle / "log.md").read_text(encoding="utf-8")
    assert code == 0, "the build persisted a document; the exit code is the run's"
    assert data["refused"] == 1
    assert "1 of 2 document(s) refused whole" in log


def test_a_lost_paragraph_is_found_and_fails_the_build(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """The known-positive: a gate that drops one line of text. Every file is
    still merged, K1b holds -- and the paragraph is gone."""

    def dropping_gate(text: str) -> GateDecision:
        kept = "\n".join(line for line in text.split("\n") if "Vask skjer" not in line)
        return GateDecision(sanitized_text=kept, disposition="warn", reasons=())

    monkeypatch.setattr(corpus, "resolve_gate", lambda name: dropping_gate)
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    shutil.copy(CORPUS / "notat.md", inbox / "notat.md")
    path = tmp_path / "a.json"
    code, bundle, err = _build(inbox, tmp_path, "--accounting", str(path))
    data = json.loads(path.read_text(encoding="utf-8"))
    assert code == 1
    assert data["unaccounted"] == 1
    (doc,) = data["documents"]
    assert doc["fates"]["paragraph"]["carried"] == 1
    assert "accounting FAILED" in err
    assert "notat.md: paragraph 1 unaccounted" in (bundle / "log.md").read_text(encoding="utf-8")


def test_without_the_door_the_log_has_no_accounting(tmp_path: Path) -> None:
    pytest.importorskip("pypandoc")
    _, bundle, _ = _build(CORPUS, tmp_path)
    assert "**Accounting**" not in (bundle / "log.md").read_text(encoding="utf-8")


def test_the_door_is_a_build_flag(tmp_path: Path) -> None:
    parsed = cli.parse_args(
        ["build", "f", "--bundle", "b", "--okf-version", "0.2", "--accounting", "a.json"]
    )
    assert parsed.accounting == Path("a.json")
    assert "accounting" in sys.modules["llm_ingestion_okf.accounting"].__name__


def test_a_proposed_exception_is_not_applied(tmp_path: Path) -> None:
    """An image inside a workbook is one of the three PROPOSED exceptions: the
    reader does not carry it. Until the operator approves the exception, it is
    unaccounted and the build says so -- it is never booked away silently."""
    import zipfile

    inbox = tmp_path / "inbox"
    inbox.mkdir()
    with (
        zipfile.ZipFile(Path(__file__).parent / "fixtures" / "prisark.xlsx") as source,
        zipfile.ZipFile(inbox / "bilde.xlsx", "w") as target,
    ):
        for name in source.namelist():
            target.writestr(name, source.read(name))
        target.writestr(
            "xl/drawings/drawing1.xml",
            '<xdr:wsDr xmlns:xdr="http://schemas.openxmlformats.org/drawingml/2006/'
            'spreadsheetDrawing"><xdr:twoCellAnchor><xdr:pic/></xdr:twoCellAnchor></xdr:wsDr>',
        )
    pytest.importorskip("pypandoc")
    path = tmp_path / "a.json"
    code, bundle, _ = _build(inbox, tmp_path, "--accounting", str(path))
    assert code == 1
    assert json.loads(path.read_text(encoding="utf-8"))["unaccounted"] == 1
    assert "bilde.xlsx: image 1 unaccounted." in (bundle / "log.md").read_text(encoding="utf-8")


def test_a_converter_attribute_inside_carried_text_is_not_a_loss() -> None:
    """Measured on K2: the converter writes `\\[[Sted]{.mark}, [dd.mm.åååå]{.mark}\\]`
    for a highlighted `[Sted, dd.mm.åååå]`. The text is carried; the attribute
    letters between its words must not make it look lost."""
    find = accounting._Finder("\\[[Sted]{.mark}, [dd.mm.åååå]{.mark}\\]\n")
    assert find("[Sted, dd.mm.åååå]")


def test_a_line_break_inside_a_paragraph_splits_its_text(tmp_path: Path) -> None:
    """Measured on K2: `Ref.nr i <w:br/>tilbudet` in a table cell is written on two
    rows of a grid table, with other cells' text between the halves."""
    import zipfile

    document = (
        '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
        "<w:body><w:p><w:r><w:t>Ref.nr i </w:t></w:r><w:r><w:br/><w:t>tilbudet</w:t></w:r>"
        "</w:p></w:body></w:document>"
    )
    path = tmp_path / "a.docx"
    with zipfile.ZipFile(path, "w") as archive:
        archive.writestr("word/document.xml", document)
    inv = accounting.inventory(tmp_path, path)
    assert inv.counts()["paragraph"] == 1
    assert inv.chunks == ["Ref.nr i ", "tilbudet"]