"""#232 — the source_kind selector must not silently hide a corpus.

`search_precedent_library` defaulted to source_kind='external_upload' all the
way down the stack, so 104 appeals-committee decisions (29% of the corpus)
were unreachable through the entry point the writing agents actually call.
These tests pin the selector semantics; the end-to-end retrieval check lives
in scripts/test_retrieval_by_name.py (needs a live DB).
"""

import pytest

from legal_mcp.services.db import _source_kind_clause


def test_empty_selector_means_no_filter():
    """'' and 'all' must produce no predicate — the whole corpus."""
    assert _source_kind_clause("") == ""
    assert _source_kind_clause("all") == ""
    assert _source_kind_clause("  ") == ""


def test_named_kinds_produce_equality_predicate():
    assert _source_kind_clause("internal_committee", "cl.") == (
        "cl.source_kind = 'internal_committee'"
    )
    assert _source_kind_clause("external_upload") == "source_kind = 'external_upload'"


def test_all_committees_expands_to_both_shapes():
    """Committee decisions live under two historical shapes — cover both."""
    clause = _source_kind_clause("all_committees", "cl.")
    assert "cl.source_kind = 'internal_committee'" in clause
    assert "cl.source_type = 'appeals_committee'" in clause
    assert clause.startswith("(") and clause.endswith(")")


def test_unknown_selector_raises_rather_than_reaching_sql():
    """The value is f-string-interpolated, so the whitelist is the guard."""
    with pytest.raises(ValueError, match="source_kind"):
        _source_kind_clause("'; DROP TABLE case_law; --")
    with pytest.raises(ValueError):
        _source_kind_clause("internal")


def test_default_of_the_search_entry_points_is_whole_corpus():
    """A regression guard on the defaults themselves — this is the bug."""
    import inspect

    from legal_mcp.services import hybrid_search, precedent_library
    from legal_mcp.services import db as db_mod
    from legal_mcp.tools import precedent_library as plib_tool

    for fn in (
        db_mod.search_precedent_library_semantic,
        db_mod.search_precedent_library_lexical,
        db_mod.list_external_case_law,
        hybrid_search.search_precedent_library_hybrid,
        precedent_library.search_library,
        precedent_library.list_precedents,
        plib_tool.search_precedent_library,
        plib_tool.precedent_library_list,
    ):
        default = inspect.signature(fn).parameters["source_kind"].default
        assert default == "", (
            f"{fn.__module__}.{fn.__qualname__} defaults source_kind to "
            f"{default!r} — that hides a corpus from every caller (#232)"
        )