"""Door B writes the images beside the text, and says how many (0.10.0).

The gate (`test_asset_gate.py`) asks whether the bytes arrive. This file pins
the four properties that decide whether their arrival is trustworthy.

- **A concept says how many images it carries.** `images: N`, conditional, so a
  document without figures pays nothing and every bundle built before this
  existed is byte-identical. Without the count a consumer cannot tell "this
  document had no figures" from "this build dropped them", which is the
  distinction the whole capability exists to restore.
- **The key belongs to the profiles this repository owns.** `DEFAULT` states
  commons' ingest-spec SS 5 layer and `STRICT_V1` the wiki's ratified contract;
  naming a key in either from here is this repository editing someone else's
  contract (O2), the same reason `sources` sits on the segmented v0.2 profile
  alone. Under those profiles the images are still CARRIED and still POINTED
  at -- only the count is absent.
- **`--no-assets` reproduces the pre-move bytes.** Every default this package
  has ever moved carries an opt-out that does, and the claim is measured on a
  whole bundle rather than asserted.
- **The run log states the denominator.** SS 9's `log.md` already carries the
  gate's name and the file counts because they are the facts about a run that
  the bundle cannot otherwise recover. "51 images carried of 53 found" is the
  same class of fact, and without it a bundle whose figures were all refused
  looks exactly like a bundle of documents that had none.
"""

from __future__ import annotations

import filecmp
import warnings
from pathlib import Path

import pytest

from llm_ingestion_okf import cli, corpus
from llm_ingestion_okf.assets import ASSETS_DIR
from llm_ingestion_okf.profiles import DEFAULT, SEGMENTED_OKF_V0_2, STRICT_V1, STRUCTURED_V1

FIXTURES = Path(__file__).parent / "fixtures" / "image-inbox"
BUNDLE_ID = "asset-bundle-fixture"
OKF_VERSION = "0.2"


def _inbox(root: Path) -> Path:
    inbox = root / "inbox"
    (inbox / "graphics").mkdir(parents=True)
    for source in sorted(FIXTURES.rglob("*")):
        if source.is_file():
            (inbox / source.relative_to(FIXTURES)).write_bytes(source.read_bytes())
    return inbox


def _build(inbox: Path, bundle: Path, *extra: str) -> int:
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        return cli.main(
            [
                "build",
                str(inbox),
                "--bundle",
                str(bundle),
                "--bundle-id",
                BUNDLE_ID,
                "--okf-version",
                OKF_VERSION,
                *extra,
            ]
        )


def _concepts(bundle: Path) -> list[Path]:
    return [
        path
        for path in sorted(bundle.rglob("*.md"))
        if path.name not in {"index.md", corpus.LOG_NAME}
    ]


# --- the count -------------------------------------------------------------


def test_a_concept_that_carries_images_counts_them(tmp_path: Path) -> None:
    pytest.importorskip("pdfplumber")
    pytest.importorskip("llm_ingestion_guard")
    bundle = tmp_path / "bundle"
    assert _build(_inbox(tmp_path), bundle) == 0
    counted = [path for path in _concepts(bundle) if "\nimages: " in path.read_text("utf-8")]
    assert counted, "no concept declared an image count"
    for path in counted:
        text = path.read_text("utf-8")
        line = next(row for row in text.splitlines() if row.startswith("images: "))
        assert int(line.split(":", 1)[1]) == text.count("](/assets/")


def test_a_concept_without_images_declares_no_count(tmp_path: Path) -> None:
    """Conditional, like `req_number`: absent is the document saying nothing."""
    pytest.importorskip("llm_ingestion_guard")
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    (inbox / "ren.md").write_text("# Kostnader\n\nIngen figurer her.\n", encoding="utf-8")
    bundle = tmp_path / "bundle"
    assert _build(inbox, bundle) == 0
    for path in _concepts(bundle):
        assert "images:" not in path.read_text("utf-8")


def test_the_key_is_named_by_the_profiles_this_repository_owns() -> None:
    assert "images" in STRUCTURED_V1.frontmatter.order
    assert "images" in SEGMENTED_OKF_V0_2.frontmatter.order
    # O2: naming a key in either of these is editing a contract owned elsewhere.
    assert "images" not in DEFAULT.frontmatter.order
    assert "images" not in STRICT_V1.frontmatter.order


# --- the opt-out reproduces the pre-move bytes -----------------------------


def test_no_assets_writes_no_assets_directory(tmp_path: Path) -> None:
    pytest.importorskip("pdfplumber")
    pytest.importorskip("llm_ingestion_guard")
    bundle = tmp_path / "bundle"
    assert _build(_inbox(tmp_path), bundle, "--no-assets") == 0
    assert not (bundle / ASSETS_DIR).exists()
    for path in _concepts(bundle):
        assert "](/assets/" not in path.read_text("utf-8")


def test_the_two_runs_differ_in_the_asset_layer_and_nowhere_else(tmp_path: Path) -> None:
    """A document with NO images is byte-identical under both settings.

    The measurement that matters for every consumer who has already built a
    bundle: turning the capability on must move nothing in a corpus that has no
    pictures in it. Asserted on files rather than on a count, because a count is
    insensitive to exactly the change this would hide.
    """
    pytest.importorskip("llm_ingestion_guard")
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    (inbox / "ren.md").write_text(
        "# Kostnader\n\nIngen figurer.\n\n## Pris\n\nEn tabell uten bilde.\n", encoding="utf-8"
    )
    on, off = tmp_path / "on", tmp_path / "off"
    assert _build(inbox, on) == 0
    assert _build(inbox, off, "--no-assets") == 0
    names = sorted(path.relative_to(on) for path in on.rglob("*") if path.is_file())
    assert names == sorted(path.relative_to(off) for path in off.rglob("*") if path.is_file())
    for name in names:
        if name.name == corpus.LOG_NAME:
            continue  # the log names the setting on purpose
        assert filecmp.cmp(on / name, off / name, shallow=False), name


# --- the log states the denominator ----------------------------------------


def test_the_log_carries_images_found_and_carried(tmp_path: Path) -> None:
    pytest.importorskip("pdfplumber")
    pytest.importorskip("llm_ingestion_guard")
    bundle = tmp_path / "bundle"
    assert _build(_inbox(tmp_path), bundle) == 0
    log = (bundle / corpus.LOG_NAME).read_text("utf-8")
    assert "**Images**:" in log
    assert " of " in log.split("**Images**:", 1)[1].splitlines()[0]


def test_the_log_names_the_capability_as_off_when_it_is(tmp_path: Path) -> None:
    """`--no-assets` is stated, never implied by a missing line.

    The same rule `--gate none` follows: a bundle built without screening says
    `NOTHING WAS SCREENED` rather than leaving a reader to infer it from an
    absent bullet. A bundle whose figures were never looked for must not read
    as a bundle of documents that had none.
    """
    pytest.importorskip("llm_ingestion_guard")
    inbox = tmp_path / "inbox"
    inbox.mkdir()
    (inbox / "ren.md").write_text("# Kostnader\n\nIngen figurer.\n", encoding="utf-8")
    bundle = tmp_path / "bundle"
    assert _build(inbox, bundle, "--no-assets") == 0
    log = (bundle / corpus.LOG_NAME).read_text("utf-8")
    assert "NOT CARRIED" in log