fn_registry/python/functions/infra/pg_upsert_test.py

"""Tests para pg_upsert.

Requieren un PostgreSQL real. Si PG_TEST_DSN no esta definida, los tests que tocan
la DB se saltan con skip elegante. Cada test crea y limpia su propia tabla con un
nombre aleatorio.

    PG_TEST_DSN="postgresql://user:pass@localhost:5433/trends" \
        python/.venv/bin/python3 -m pytest python/functions/infra/pg_upsert_test.py
"""

import os
import sys
import uuid

import pytest

sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
from infra.pg_upsert import pg_upsert  # noqa: E402

PG_TEST_DSN = os.environ.get("PG_TEST_DSN")
requires_pg = pytest.mark.skipif(
    not PG_TEST_DSN, reason="PG_TEST_DSN no definido: se omiten los tests de Postgres"
)


@pytest.fixture
def temp_table():
    """Crea leads(email PRIMARY KEY, name TEXT, score INT) y la elimina al final."""
    import psycopg2

    name = "pg_upsert_t_" + uuid.uuid4().hex[:12]
    conn = psycopg2.connect(PG_TEST_DSN)
    try:
        with conn.cursor() as cur:
            cur.execute(
                f"CREATE TABLE {name} "
                f"(email TEXT PRIMARY KEY, name TEXT, score INTEGER)"
            )
        conn.commit()
    finally:
        conn.close()

    yield name

    conn = psycopg2.connect(PG_TEST_DSN)
    try:
        with conn.cursor() as cur:
            cur.execute(f"DROP TABLE IF EXISTS {name}")
        conn.commit()
    finally:
        conn.close()


def _read(table, email):
    import psycopg2

    conn = psycopg2.connect(PG_TEST_DSN)
    try:
        with conn.cursor() as cur:
            cur.execute(
                f"SELECT name, score FROM {table} WHERE email = %s", (email,)
            )
            return cur.fetchone()
    finally:
        conn.close()


def test_skip_sin_pg_test_dsn():
    """skip sin PG_TEST_DSN."""
    if not PG_TEST_DSN:
        pytest.skip("PG_TEST_DSN no definido")
    assert PG_TEST_DSN


def test_identificador_invalido_devuelve_status_error():
    """identificador invalido devuelve status error sin tocar DB."""
    res = pg_upsert(
        "postgresql://x/y",
        "tabla mala; DROP TABLE foo",
        [{"email": "a@x.com"}],
        key_cols=["email"],
    )
    assert res["status"] == "error"


@requires_pg
def test_inserta_filas_nuevas_cuenta_inserted(temp_table):
    """inserta filas nuevas cuenta inserted."""
    res = pg_upsert(
        PG_TEST_DSN,
        temp_table,
        [
            {"email": "ana@x.com", "name": "Ana", "score": 0},
            {"email": "bob@x.com", "name": "Bob", "score": 5},
        ],
        key_cols=["email"],
    )
    assert res["status"] == "ok"
    assert res["inserted"] == 2
    assert res["updated"] == 0


@requires_pg
def test_conflicto_actualiza_y_cuenta_updated(temp_table):
    """conflicto actualiza columnas y cuenta updated."""
    pg_upsert(
        PG_TEST_DSN, temp_table,
        [{"email": "ana@x.com", "name": "Ana", "score": 0}], key_cols=["email"],
    )
    res = pg_upsert(
        PG_TEST_DSN, temp_table,
        [{"email": "ana@x.com", "name": "Ana Lopez", "score": 9}], key_cols=["email"],
    )
    assert res["status"] == "ok"
    assert res["inserted"] == 0
    assert res["updated"] == 1
    assert _read(temp_table, "ana@x.com") == ("Ana Lopez", 9)


@requires_pg
def test_ownership_selectivo_no_pisa_columna_excluida(temp_table):
    """ownership selectivo no pisa columna excluida."""
    pg_upsert(
        PG_TEST_DSN, temp_table,
        [{"email": "ana@x.com", "name": "Ana", "score": 0}], key_cols=["email"],
    )
    # La DB es duena de score (otro proceso lo subio a 87).
    import psycopg2

    conn = psycopg2.connect(PG_TEST_DSN)
    with conn.cursor() as cur:
        cur.execute(f"UPDATE {temp_table} SET score = 87 WHERE email = 'ana@x.com'")
    conn.commit()
    conn.close()

    # El feed trae score=0 pero solo autorizamos actualizar name.
    res = pg_upsert(
        PG_TEST_DSN, temp_table,
        [{"email": "ana@x.com", "name": "Ana Lopez", "score": 0}],
        key_cols=["email"], update_cols=["name"],
    )
    assert res["status"] == "ok"
    assert res["updated"] == 1
    assert _read(temp_table, "ana@x.com") == ("Ana Lopez", 87)


@requires_pg
def test_do_nothing_no_actualiza(temp_table):
    """do nothing no actualiza: update_cols=[] inserta solo nuevas."""
    pg_upsert(
        PG_TEST_DSN, temp_table,
        [{"email": "ana@x.com", "name": "Ana", "score": 1}], key_cols=["email"],
    )
    res = pg_upsert(
        PG_TEST_DSN, temp_table,
        [
            {"email": "ana@x.com", "name": "PISADO", "score": 99},  # conflicto
            {"email": "new@x.com", "name": "Nuevo", "score": 2},    # nuevo
        ],
        key_cols=["email"], update_cols=[],
    )
    assert res["status"] == "ok"
    # La fila en conflicto no se devuelve por RETURNING (DO NOTHING).
    assert res["inserted"] == 1
    assert res["updated"] == 0
    # La existente NO se pisa.
    assert _read(temp_table, "ana@x.com") == ("Ana", 1)