Unify dataset/tooling scripts into a single dwarf Typer CLI
Replace the five separately-hyphenated uv entry points (steps-to-parquet, steps-to-parquet-parallel, migrate-geant-steps, bump-dataset-version, create-root-files) plus the unregistered hparam_scan.py with one `dwarf` command exposing convert/migrate/bump-gen/bump-schema/status/ update-manifest/create-manifest/make-root/hparam-scan as subcommands. Each scripts/*.py module now only holds argparse-free business logic; scripts/dwarf.py wires it up with Typer, matching giant/cli.py's style. `dwarf convert` merges the old serial/parallel conversion scripts behind a --jobs flag (default 1: sequential with plain -o; >1: dataset-layout fan-out via subprocess). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,68 @@
|
||||
from typer.testing import CliRunner
|
||||
|
||||
from scripts.dwarf import app
|
||||
|
||||
runner = CliRunner()
|
||||
|
||||
|
||||
def test_convert_rejects_jobs_below_one(tmp_path):
|
||||
root_file = tmp_path / "shard.root"
|
||||
root_file.touch()
|
||||
result = runner.invoke(app, ["convert", str(root_file), "--jobs", "0"])
|
||||
assert result.exit_code != 0
|
||||
assert "--jobs must be >= 1" in result.output
|
||||
|
||||
|
||||
def test_convert_rejects_output_with_multiple_files(tmp_path):
|
||||
a = tmp_path / "a.root"
|
||||
b = tmp_path / "b.root"
|
||||
a.touch()
|
||||
b.touch()
|
||||
result = runner.invoke(app, ["convert", str(a), str(b), "--output", "out.parquet"])
|
||||
assert result.exit_code != 0
|
||||
assert "--output can only be used with a single input file" in result.output
|
||||
|
||||
|
||||
def test_convert_rejects_output_with_parallel_jobs(tmp_path):
|
||||
root_file = tmp_path / "shard.root"
|
||||
root_file.touch()
|
||||
result = runner.invoke(
|
||||
app, ["convert", str(root_file), "--output", "out.parquet", "--jobs", "2"]
|
||||
)
|
||||
assert result.exit_code != 0
|
||||
assert "--output cannot be combined with --jobs > 1" in result.output
|
||||
|
||||
|
||||
def test_convert_default_jobs_is_one():
|
||||
result = runner.invoke(app, ["convert", "--help"])
|
||||
assert result.exit_code == 0
|
||||
assert "default: 1" in result.output
|
||||
|
||||
|
||||
def test_bump_gen_requires_reason():
|
||||
result = runner.invoke(app, ["bump-gen"])
|
||||
assert result.exit_code != 0
|
||||
assert "reason" in result.output.lower()
|
||||
|
||||
|
||||
def test_create_manifest_requires_exactly_one_of_output_or_pool(tmp_path):
|
||||
f = tmp_path / "a.parquet"
|
||||
f.touch()
|
||||
result = runner.invoke(app, ["create-manifest", str(f)])
|
||||
assert result.exit_code != 0
|
||||
assert "exactly one of --output or --pool is required" in result.output
|
||||
|
||||
|
||||
def test_create_manifest_requires_type_with_pool(tmp_path):
|
||||
f = tmp_path / "a.parquet"
|
||||
f.touch()
|
||||
result = runner.invoke(app, ["create-manifest", "--pool", "pbwo4", str(f)])
|
||||
assert result.exit_code != 0
|
||||
assert "--type is required when --pool is given" in result.output
|
||||
|
||||
|
||||
def test_status_reports_missing_root(tmp_path):
|
||||
missing = tmp_path / "does-not-exist"
|
||||
result = runner.invoke(app, ["status", "--root", str(missing)])
|
||||
assert result.exit_code != 0
|
||||
assert "is not a directory" in result.output
|
||||
Reference in New Issue
Block a user