glowtables/glowtables/tests/table_test.py

# This file is part of the Glowtables software
# Copyright (C) 2023  Valentin Lorentz
#
# This program is free software: you can redistribute it and/or modify it under the
# terms of the GNU Affero General Public License version 3, as published by the
# Free Software Foundation.
#
# This program is distributed in the hope that it will be useful, but WITHOUT ANY
# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
# PARTICULAR PURPOSE.  See the GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License along with
# this program.  If not, see <http://www.gnu.org/licenses/>.

"""Tests :mod:`glowtables.table`.

Test cases use a graph containing a few CPUs, with names and clock frequencies.
"""

import textwrap
from decimal import Decimal

import pytest
import rdflib

from glowtables.sparql import SparqlBackend
from glowtables.table import Language, LiteralField, Table

CPU1_URI = rdflib.URIRef("http://example.org/grown-1700")
CPU2_URI = rdflib.URIRef("http://example.org/grown-3600")
CPU3_URI = rdflib.URIRef("http://example.org/secret-project")
CG_URI = rdflib.URIRef("http://example.org/likestone-underdog")
CPU = rdflib.URIRef("http://example.org/CPU")
DISPLAY_NAME = rdflib.URIRef("http://example.org/display-name")
FREQUENCY = rdflib.URIRef("http://example.org/clock-frequency")
TYPE = rdflib.URIRef("http://example.org/type")


@pytest.fixture()
def rdflib_graph() -> rdflib.Graph:
    graph = rdflib.Graph()

    # A CPU with all the properties
    graph.add((CPU1_URI, DISPLAY_NAME, rdflib.Literal("Grown 1700")))
    graph.add((CPU1_URI, TYPE, CPU))
    graph.add((CPU1_URI, FREQUENCY, rdflib.Literal(3000)))

    # Another CPU, without a frequency
    graph.add((CPU2_URI, DISPLAY_NAME, rdflib.Literal("Grown 3600")))
    graph.add((CPU2_URI, TYPE, CPU))

    # Another CPU, without a name
    graph.add((CPU3_URI, TYPE, CPU))
    graph.add((CPU3_URI, FREQUENCY, rdflib.Literal(9000)))

    # Add a graphics card; which should be excluded from CPU searches
    graph.add((CG_URI, DISPLAY_NAME, rdflib.Literal("LikeStone Underdog")))
    graph.add((CG_URI, FREQUENCY, rdflib.Literal(1626)))
    graph.add((CG_URI, TYPE, rdflib.URIRef("http://example.org/graphics-card")))

    return graph


def test_single_literal(rdflib_sparql: SparqlBackend) -> None:
    name_field = LiteralField(
        "display_name",
        {Language("en"): "Name"},
        str,
        rdflib.URIRef("http://example.org/display-name"),
    )
    table = Table(
        id="test-table",
        fields=[name_field],
        constraints="?subject <http://example.org/type> <http://example.org/CPU>.",
    )

    assert table.sparql() == textwrap.dedent(
        """
        SELECT ?display_name
        WHERE {
            ?subject <http://example.org/type> <http://example.org/CPU>.
            ?subject <http://example.org/display-name> ?display_name.
        }
        """
    )

    assert set(table.query(rdflib_sparql)) == {
        ("Grown 1700",),
        ("Grown 3600",),
    }


def test_two_literals(rdflib_sparql: SparqlBackend) -> None:
    name_field = LiteralField(
        "display_name",
        {Language("en"): "Name"},
        str,
        rdflib.URIRef("http://example.org/display-name"),
    )
    frequency_field = LiteralField(
        "frequency",
        {Language("en"): "Clock frequency"},
        Decimal,
        rdflib.URIRef("http://example.org/clock-frequency"),
    )
    table = Table(
        id="test-table",
        fields=[name_field, frequency_field],
        constraints="?subject <http://example.org/type> <http://example.org/CPU>.",
    )

    assert table.sparql() == textwrap.dedent(
        """
        SELECT ?display_name ?frequency
        WHERE {
            ?subject <http://example.org/type> <http://example.org/CPU>.
            ?subject <http://example.org/display-name> ?display_name.
            ?subject <http://example.org/clock-frequency> ?frequency.
        }
        """
    )

    assert set(table.query(rdflib_sparql)) == {
        ("Grown 1700", 3000),
    }


def test_default_value(rdflib_sparql: SparqlBackend) -> None:
    name_field = LiteralField(
        "display_name",
        {Language("en"): "Name"},
        str,
        rdflib.URIRef("http://example.org/display-name"),
        default="Anonymous CPU",
    )
    frequency_field = LiteralField(
        "frequency",
        {Language("en"): "Clock frequency"},
        Decimal,
        rdflib.URIRef("http://example.org/clock-frequency"),
        default=Decimal(0),
    )
    table = Table(
        id="test-table",
        fields=[name_field, frequency_field],
        constraints="?subject <http://example.org/type> <http://example.org/CPU>.",
    )

    assert table.sparql() == textwrap.dedent(
        """
        SELECT ?display_name ?frequency
        WHERE {
            ?subject <http://example.org/type> <http://example.org/CPU>.
            OPTIONAL { ?subject <http://example.org/display-name> ?display_name. }.
            OPTIONAL { ?subject <http://example.org/clock-frequency> ?frequency. }.
        }
        """
    )

    assert set(table.query(rdflib_sparql)) == {
        ("Grown 1700", 3000),
        ("Grown 3600", None),
        (None, 9000),
    }


def test_field_id_subject() -> None:
    name_field = LiteralField(
        "subject",
        {Language("en"): "Name"},
        str,
        rdflib.URIRef("http://example.org/display-name"),
    )
    with pytest.raises(ValueError, match="both subject and a field id"):
        Table(
            id="test-table",
            fields=[name_field],
            constraints="",
        )


def test_field_id_clash() -> None:
    name_field = LiteralField(
        "name",
        {Language("en"): "Name"},
        str,
        rdflib.URIRef("http://example.org/name"),
    )
    display_name_field = LiteralField(
        "name",
        {Language("en"): "Display Name"},
        str,
        rdflib.URIRef("http://example.org/display-name"),
    )
    with pytest.raises(ValueError, match="has duplicate field ids: name"):
        Table(
            id="test-table",
            fields=[name_field, display_name_field],
            constraints="",
        )