llm-ingestion-okf/tests/test_multi_source_provenance.py

"""SPEC 5.1 `sources` with more than one entry, and the form it is emitted in.

PM decision B6 asked for a list-taking `_render_sources` so a concept can
record more than one source. It also prescribed the BLOCK list as the emitted
form. The list is delivered; the block form is not, and this file carries the
measurement rather than the argument.

Three facts, each pinned by a test below:

- **Our own parser loses a block list entirely.** `parse_frontmatter` is
  line-oriented and skips indented lines, so `sources:` followed by `  - id: a`
  round-trips to an EMPTY value with every entry gone -- silently. A provenance
  record we cannot read back is worse than one we never wrote.
- **The consumer's decoder reads the flow sequence and refuses the block one.**
  `portfolio-optimiser`'s `decode_flow_value` accepts `[{ k: v }, { k: v }]` --
  plural -- and classifies a block sequence as `UnreadableProvenance`. Emitting
  block would hand the consumer that asked for multi-source exactly the state it
  reports as unreadable.
- **The order's own acceptance test settles it.** It asks for a round trip
  through our `parse_frontmatter` equivalent. No block form can pass that.

So the goal is delivered in the form that reaches a reader: one flow sequence of
N flow mappings, on one line. A single source stays byte-identical, which is
what keeps all six goldens unmoved.
"""

from __future__ import annotations

from pathlib import Path

import pytest

from llm_ingestion_okf.errors import MaterializationError
from llm_ingestion_okf.manifest import FileSource, HttpSource, Source, SqlSource
from llm_ingestion_okf.materialize import _render_sources, parse_frontmatter

CATALOGUE = FileSource(id="golden-catalogue", root="fixture")
DATABASE = SqlSource(id="golden-db", connection_ref="OKF_GOLDEN_SQL_DB")
API = HttpSource(id="golden-api", base_url="https://golden.example.test")


def _document(sources: str) -> str:
    return (
        "---\n"
        "type: dataset\n"
        "title: Orders\n"
        "generated: { by: process:okf-ingest, at: 2026-01-01T00:00:00Z }\n"
        f"sources: {sources}\n"
        "---\n"
        "\nBody.\n"
    )


# --- the rendered form ------------------------------------------------------


def test_one_source_renders_the_byte_identical_single_form() -> None:
    """The additivity arm. Every golden in the suite reads this line."""
    assert _render_sources([CATALOGUE]) == "[{ id: golden-catalogue, resource: fixture }]"


def test_two_sources_render_as_one_flow_sequence_on_one_line() -> None:
    assert _render_sources([CATALOGUE, DATABASE]) == (
        "[{ id: golden-catalogue, resource: fixture }, "
        "{ id: golden-db, resource: OKF_GOLDEN_SQL_DB }]"
    )
    assert "\n" not in _render_sources([CATALOGUE, DATABASE])


def test_sources_keep_the_order_they_were_given() -> None:
    """No sort. The order a manifest names its sources in is the manifest's
    statement, and nothing here can recover it once reordered."""
    forward = _render_sources([CATALOGUE, DATABASE, API])
    reverse = _render_sources([API, DATABASE, CATALOGUE])

    assert forward.index("golden-catalogue") < forward.index("golden-api")
    assert reverse.index("golden-api") < reverse.index("golden-catalogue")


def test_an_empty_source_list_is_refused() -> None:
    """`sources: []` is a provenance record naming no source: it reads as a
    measured absence when it is the absence of a measurement."""
    with pytest.raises(MaterializationError) as excinfo:
        _render_sources([])

    assert excinfo.value.code == "sources_empty"


# --- the round trip, which is the acceptance test ---------------------------


def test_two_sources_round_trip_through_our_own_parser(tmp_path: Path) -> None:
    rendered = _render_sources([CATALOGUE, DATABASE])
    path = tmp_path / "concept.md"
    path.write_text(_document(rendered), encoding="utf-8")

    frontmatter = parse_frontmatter(path)

    assert frontmatter["sources"] == rendered
    assert sorted(frontmatter) == ["generated", "sources", "title", "type"]


def test_the_block_form_round_trips_to_nothing(tmp_path: Path) -> None:
    """The NEGATIVE CONTROL, and the measured reason the block form is not
    emitted. Two entries go in; an empty string comes back, and no error is
    raised anywhere. This test must stay green: it is the evidence, not a
    regression guard."""
    path = tmp_path / "concept.md"
    path.write_text(
        "---\n"
        "type: dataset\n"
        "sources:\n"
        "  - id: golden-catalogue\n"
        "    resource: fixture\n"
        "  - id: golden-db\n"
        "    resource: OKF_GOLDEN_SQL_DB\n"
        "---\n"
        "\nBody.\n",
        encoding="utf-8",
    )

    frontmatter = parse_frontmatter(path)

    assert frontmatter["sources"] == ""
    assert "golden-db" not in "".join(frontmatter.values())


# --- the refusal applies to every entry, not only the first -----------------


@pytest.mark.parametrize("position", [0, 1, 2], ids=["first", "middle", "last"])
def test_an_unquotable_locator_is_refused_in_any_position(position: int) -> None:
    """A gate that only reads the head of a list is a gate the second entry
    walks past."""
    sources: list[Source] = [CATALOGUE, DATABASE, API]
    sources[position] = FileSource(id="broken", root="data, backup")

    with pytest.raises(MaterializationError) as excinfo:
        _render_sources(sources)

    assert excinfo.value.code == "source_reference_unquotable"


@pytest.mark.parametrize("position", [0, 1], ids=["first", "last"])
def test_an_unquotable_id_is_refused_in_any_position(position: int) -> None:
    sources: list[Source] = [CATALOGUE, DATABASE]
    sources[position] = FileSource(id="a{1}", root="fixture")

    with pytest.raises(MaterializationError) as excinfo:
        _render_sources(sources)

    assert excinfo.value.code == "source_reference_unquotable"