mirror of
https://github.com/Stone-Red-Code/dvc.git
synced 2026-11-07 15:28:28 +01:00
Saugat PachhaiandRuslan Kuprieiev
1937527249
* dvc: use lockfile as yaml instead of json * refactor Dvcfile into Pipeline file and Single stage file * fix tests * dvc: fix outputs * add more tests for collection of outputs * add tests for data cloud/get/import/ls * tests: test for checkouts * Allow other checksums other than md5 * tests: use iterdir instead of os.listdir * cleanup errors reported by cc and ds * utils: throw DvcException instead of plain Exception * tests: use yaml.load instead of json.load * run: split assignments * Update dvc/stage/exceptions.py Co-authored-by: Ruslan Kuprieiev <[email protected]>
85 lines
2.5 KiB
Python
85 lines
2.5 KiB
Python
from dvc.stage import PipelineStage
|
|
from dvc.dvcfile import Lockfile, LockfileCorruptedError
|
|
import yaml
|
|
import pytest
|
|
|
|
|
|
def test_stage_dump_no_outs_deps(tmp_dir, dvc):
|
|
stage = PipelineStage(name="s1", repo=dvc, path="path", cmd="command")
|
|
lockfile = Lockfile(dvc, "path.lock")
|
|
lockfile.dump(stage)
|
|
assert lockfile.load() == {"s1": {"cmd": "command"}}
|
|
|
|
|
|
def test_stage_dump_when_already_exists(tmp_dir, dvc):
|
|
data = {"s1": {"cmd": "command", "deps": [], "outs": []}}
|
|
with open("path.lock", "w+") as f:
|
|
yaml.dump(data, f)
|
|
stage = PipelineStage(name="s2", repo=dvc, path="path", cmd="command2")
|
|
lockfile = Lockfile(dvc, "path.lock")
|
|
lockfile.dump(stage)
|
|
assert lockfile.load() == {
|
|
**data,
|
|
"s2": {"cmd": "command2"},
|
|
}
|
|
|
|
|
|
def test_stage_dump_with_deps_and_outs(tmp_dir, dvc):
|
|
data = {
|
|
"s1": {
|
|
"cmd": "command",
|
|
"deps": [{"md5": "1.txt", "path": "checksum"}],
|
|
"outs": [{"md5": "2.txt", "path": "checksum"}],
|
|
}
|
|
}
|
|
with open("path.lock", "w+") as f:
|
|
yaml.dump(data, f)
|
|
|
|
lockfile = Lockfile(dvc, "path.lock")
|
|
stage = PipelineStage(name="s2", repo=dvc, path="path", cmd="command2")
|
|
lockfile.dump(stage)
|
|
assert lockfile.load() == {
|
|
**data,
|
|
"s2": {"cmd": "command2"},
|
|
}
|
|
|
|
|
|
def test_stage_overwrites_if_already_exists(tmp_dir, dvc):
|
|
lockfile = Lockfile(dvc, "path.lock",)
|
|
stage = PipelineStage(name="s2", repo=dvc, path="path", cmd="command2")
|
|
lockfile.dump(stage)
|
|
stage = PipelineStage(name="s2", repo=dvc, path="path", cmd="command3")
|
|
lockfile.dump(stage)
|
|
assert lockfile.load() == {
|
|
"s2": {"cmd": "command3"},
|
|
}
|
|
|
|
|
|
def test_load_when_lockfile_does_not_exist(tmp_dir, dvc):
|
|
assert {} == Lockfile(dvc, "pipelines.lock").load()
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"corrupt_data",
|
|
[
|
|
{"s1": {"outs": []}},
|
|
{"s1": {}},
|
|
{
|
|
"s1": {
|
|
"cmd": "command",
|
|
"outs": [
|
|
{"md5": "checksum", "path": "path", "random": "value"}
|
|
],
|
|
}
|
|
},
|
|
{"s1": {"cmd": "command", "deps": [{"md5": "checksum"}]}},
|
|
],
|
|
)
|
|
def test_load_when_lockfile_is_corrupted(tmp_dir, dvc, corrupt_data):
|
|
with open("Dvcfile.lock", "w+") as f:
|
|
yaml.dump(corrupt_data, f)
|
|
lockfile = Lockfile(dvc, "Dvcfile.lock")
|
|
with pytest.raises(LockfileCorruptedError) as exc_info:
|
|
lockfile.load()
|
|
assert "Dvcfile.lock" in str(exc_info.value)
|