"""L0: db/sampling against known data (testcontainers).
Verifies unique_values_for_lsh returns the expected most-frequent values for text
columns, and that wide_text / non-text columns are excluded.
"""
import pytest

from tht.config import LshConfig
from tht.db.introspect import introspect
from tht.db.sampling import is_text_type, unique_values_for_lsh

pytestmark = [pytest.mark.l0]


def test_is_text_type():
    assert is_text_type("text")
    assert is_text_type("varchar(100)")
    assert is_text_type("character varying")
    assert not is_text_type("integer")
    assert not is_text_type("bigint")
    assert not is_text_type("timestamp without time zone")


def test_unique_values_for_lsh_returns_most_frequent(admin_engine):
    schema = introspect(admin_engine, "testdb", "dw")
    # Before classify_all, all text columns are eligible=True by default. Sampling
    # only touches text types regardless.
    values, skipped, truncated = unique_values_for_lsh(
        admin_engine, schema, LshConfig(max_values_per_column=100)
    )
    # dim_pazienti.citta: Milano, Bergamo, Brescia (3 distinct, all eligible text)
    citta = values.get("dim_pazienti", {}).get("citta")
    assert citta is not None
    assert set(citta) == {"Milano", "Bergamo", "Brescia"}


def test_unique_values_for_lsh_excludes_non_text(admin_engine):
    schema = introspect(admin_engine, "testdb", "dw")
    values, _, _ = unique_values_for_lsh(
        admin_engine, schema, LshConfig(max_values_per_column=100)
    )
    # id_paziente is bigint — must never appear in the LSH values.
    assert "id_paziente" not in values.get("dim_pazienti", {})


def test_unique_values_for_lsh_truncation_reported(admin_engine):
    schema = introspect(admin_engine, "testdb", "dw")
    # Force a tiny cap so procedura/diagnosi columns (which have >2 distinct values)
    # are reported as truncated rather than silently cut.
    _, _, truncated = unique_values_for_lsh(
        admin_engine, schema, LshConfig(max_values_per_column=1)
    )
    truncated_cols = {(t.table, t.column) for t in truncated}
    # fct_ricoveri has several eligible text columns with distinct values
    assert any(t[0] == "fct_ricoveri" for t in truncated_cols)