test_parse_bio.py

# -*- coding: utf-8 -*-
from pathlib import Path

import pytest

from nerval import evaluate
from nerval.parse import parse_line

expected_parsed_annot = {
    "entity_count": {"All": 3, "DAT": 1, "LOC": 1, "PER": 1},
    "labels": [
        "B-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "B-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "O",
        "O",
        "O",
        "O",
        "B-DAT",
        "I-DAT",
        "I-DAT",
        "I-DAT",
        "O",
        "O",
    ],
    "words": "Gérard de Nerval was born in Paris in 1808 .",
}

expected_parsed_predict = {
    "entity_count": {"All": 3, "DAT": 1, "***": 1, "PER": 1},
    "labels": [
        "B-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "O",
        "B-***",
        "I-***",
        "I-***",
        "I-***",
        "I-***",
        "O",
        "O",
        "O",
        "O",
        "B-DAT",
        "I-DAT",
        "I-DAT",
        "I-DAT",
        "O",
        "O",
        "O",
    ],
    "words": "G*rard de *N*erval bo*rn in Paris in 1833 *.",
}

expected_parsed_end_of_file = {
    "entity_count": {"All": 3, "LOC": 2, "PER": 1},
    "labels": [
        "B-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "B-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "I-PER",
        "O",
        "B-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
        "I-LOC",
    ],
    "words": "Louis par la grâce de Dieu roy de France et de Navarre",
}


@pytest.mark.parametrize(
    "test_input, expected",
    [
        (pytest.lazy_fixture("fake_annot_bio"), expected_parsed_annot),
        (pytest.lazy_fixture("fake_predict_bio"), expected_parsed_predict),
        (pytest.lazy_fixture("empty_bio"), None),
        (pytest.lazy_fixture("bioeslu_bio"), expected_parsed_annot),
        (pytest.lazy_fixture("end_of_file_bio"), expected_parsed_end_of_file),
    ],
)
def test_parse_bio(test_input, expected):
    assert evaluate.parse_bio(test_input) == expected


def test_parse_bio_bad_input(bad_bio):
    with pytest.raises(Exception):
        evaluate.parse_bio(bad_bio)


def test_parse_bio_no_input():
    with pytest.raises(AssertionError):
        evaluate.parse_bio(Path("not_a_bio"))


@pytest.mark.parametrize(
    "line, word, label",
    (
        ("Hi B-ORG", "Hi", "B-ORG"),
        ("Hi B-Org or maybe not org", "Hi", "B-Org or maybe not org"),
    ),
)
def test_parse_line(line, word, label):
    assert parse_line(index=0, line=line, path=Path("")) == (word, label)


@pytest.mark.parametrize(
    "line",
    (
        ("HiB-ORG"),
        ("HiB-ORG or maybe not"),
    ),
)
def test_parse_line_crash(line):
    with pytest.raises(Exception):
        parse_line(index=0, line=line, path=Path(""))