spaCy/spacy/tests/test_cli_app.py

import os
from pathlib import Path
from typer.testing import CliRunner
from spacy.tokens import DocBin, Doc

from spacy.cli._util import app
from .util import make_tempdir, normalize_whitespace


def test_convert_auto():
    with make_tempdir() as d_in, make_tempdir() as d_out:
        for f in ["data1.iob", "data2.iob", "data3.iob"]:
            Path(d_in / f).touch()

        # ensure that "automatic" suffix detection works
        result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
        assert "Generated output file" in result.stdout
        out_files = os.listdir(d_out)
        assert len(out_files) == 3
        assert "data1.spacy" in out_files
        assert "data2.spacy" in out_files
        assert "data3.spacy" in out_files


def test_convert_auto_conflict():
    with make_tempdir() as d_in, make_tempdir() as d_out:
        for f in ["data1.iob", "data2.iob", "data3.json"]:
            Path(d_in / f).touch()

        # ensure that "automatic" suffix detection warns when there are different file types
        result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
        assert "All input files must be same type" in result.stdout
        out_files = os.listdir(d_out)
        assert len(out_files) == 0


def test_benchmark_accuracy_alias():
    # Verify that the `evaluate` alias works correctly.
    result_benchmark = CliRunner().invoke(app, ["benchmark", "accuracy", "--help"])
    result_evaluate = CliRunner().invoke(app, ["evaluate", "--help"])
    assert normalize_whitespace(result_benchmark.stdout) == normalize_whitespace(
        result_evaluate.stdout.replace("spacy evaluate", "spacy benchmark accuracy")
    )


def test_debug_data_trainable_lemmatizer_cli(en_vocab):
    train_docs = [
        Doc(en_vocab, words=["I", "like", "cats"], lemmas=["I", "like", "cat"]),
        Doc(
            en_vocab,
            words=["Dogs", "are", "great", "too"],
            lemmas=["dog", "be", "great", "too"],
        ),
    ]
    dev_docs = [
        Doc(en_vocab, words=["Cats", "are", "cute"], lemmas=["cat", "be", "cute"]),
        Doc(en_vocab, words=["Pets", "are", "great"], lemmas=["pet", "be", "great"]),
    ]
    with make_tempdir() as d_in:
        train_bin = DocBin(docs=train_docs)
        train_bin.to_disk(d_in / "train.spacy")
        dev_bin = DocBin(docs=dev_docs)
        dev_bin.to_disk(d_in / "dev.spacy")
        # `debug data` requires an input pipeline config
        CliRunner().invoke(
            app,
            [
                "init",
                "config",
                f"{d_in}/config.cfg",
                "--lang",
                "en",
                "--pipeline",
                "trainable_lemmatizer",
            ],
        )
        result_debug_data = CliRunner().invoke(
            app,
            [
                "debug",
                "data",
                f"{d_in}/config.cfg",
                "--paths.train",
                f"{d_in}/train.spacy",
                "--paths.dev",
                f"{d_in}/dev.spacy",
            ],
        )
        # Instead of checking specific wording of the output, which may change,
        # we'll check that this section of the debug output is present.
        assert "= Trainable Lemmatizer =" in result_debug_data.stdout