mirror of
https://github.com/Stone-Red-Code/dvc.git
synced 2026-11-02 07:18:25 +01:00
Ruslan Kuprieiev
381601f4ee
* dvc: cache graph/stages/pipelines Signed-off-by: Ruslan Kuprieiev <[email protected]> * repo: check_dag: don't reset the cache https://github.com/iterative/dvc/pull/2529#discussion_r327711928 Signed-off-by: Ruslan Kuprieiev <[email protected]> * repo: rename check_dag(stages) -> check_modified_graph(new_stages) https://github.com/iterative/dvc/pull/2529#discussion_r327708439 Signed-off-by: Ruslan Kuprieiev <[email protected]> * repo: refactor "active" logic and remove it from Repo class * repo: use tree.setter to automate cache reset As noted by @Suor's , this is much less prone to errors. * repo: move graph-related staticmethods into graph.py As per @Suor's request. * dvc: remove unused from_directory https://github.com/iterative/dvc/pull/2529#discussion_r328079258 * repo: use _tree instead of __tree https://github.com/iterative/dvc/pull/2529#discussion_r328071115 * repo: add a note about cache invalidation on repo.lock release https://github.com/iterative/dvc/pull/2529#discussion_r328071635 * repo: rename reset() -> _reset() https://github.com/iterative/dvc/pull/2529#discussion_r328079899 * pipeline: use graph helpers https://github.com/iterative/dvc/pull/2529#discussion_r327502293 * repo: use list comprehension for collect() https://github.com/iterative/dvc/pull/2529#discussion_r328076651 * repo: graph: only use first cycle https://github.com/iterative/dvc/pull/2529#discussion_r328081346 * dvc: don't use G.nodes() https://github.com/iterative/dvc/pull/2529#discussion_r328089671 https://github.com/iterative/dvc/pull/2529#discussion_r328089878
73 lines
2.5 KiB
Python
73 lines
2.5 KiB
Python
from dvc.ignore import DvcIgnore
|
|
from dvc.main import main
|
|
from dvc.repo import Repo
|
|
from dvc.stage import Stage
|
|
from tests.basic_env import TestDvcGit
|
|
|
|
from dvc.scm.git import GitTree
|
|
from dvc.scm.tree import WorkingTree
|
|
|
|
|
|
class TestCollect(TestDvcGit):
|
|
def setUp(self):
|
|
super(TestCollect, self).setUp()
|
|
self.dvc.add(self.FOO)
|
|
self.dvc.run(
|
|
deps=[self.FOO],
|
|
outs=[self.BAR],
|
|
cmd="python code.py {} {}".format(self.FOO, self.BAR),
|
|
)
|
|
self.dvc.scm.add([".gitignore", self.FOO + ".dvc", self.BAR + ".dvc"])
|
|
self.dvc.scm.commit("foo.dvc and bar.dvc")
|
|
self.dvc.scm.checkout("new_branch", True)
|
|
self.dvc.run(
|
|
deps=[self.BAR],
|
|
outs=["buzz"],
|
|
cmd="python code.py {} {}".format(self.BAR, "buzz"),
|
|
)
|
|
self.dvc.scm.add([".gitignore", "buzz.dvc"])
|
|
self.dvc.scm.commit("add buzz")
|
|
self.dvc.scm.checkout("master")
|
|
|
|
def _check(self, branch, target, with_deps, expected):
|
|
if branch:
|
|
self.dvc.tree = GitTree(self.dvc.scm.repo, branch)
|
|
else:
|
|
self.dvc.tree = WorkingTree()
|
|
result = self.dvc.collect(target + ".dvc", with_deps=with_deps)
|
|
self.assertEqual([[str(j) for j in i.outs] for i in result], expected)
|
|
return result
|
|
|
|
def test(self):
|
|
self._check("", self.BAR, True, [[self.FOO], [self.BAR]])
|
|
self._check("master", self.BAR, True, [[self.FOO], [self.BAR]])
|
|
self._check(
|
|
"new_branch", "buzz", True, [[self.FOO], [self.BAR], ["buzz"]]
|
|
)
|
|
result = self._check("new_branch", "buzz", False, [["buzz"]])
|
|
self.assertEqual([str(i) for i in result[0].deps], ["bar"])
|
|
|
|
|
|
class TestIgnore(TestDvcGit):
|
|
def _stage_name(self, file):
|
|
return file + Stage.STAGE_FILE_SUFFIX
|
|
|
|
def test_should_not_gather_stage_files_from_ignored_dir(self):
|
|
ret = main(["add", self.FOO, self.BAR, self.DATA, self.DATA_SUB])
|
|
self.assertEqual(0, ret)
|
|
|
|
stages = self.dvc.stages
|
|
self.assertEqual(4, len(stages))
|
|
|
|
self.create(DvcIgnore.DVCIGNORE_FILE, self.DATA_DIR)
|
|
|
|
self.dvc = Repo(self.dvc.root_dir)
|
|
stages = self.dvc.stages
|
|
self.assertEqual(2, len(stages))
|
|
|
|
stagenames = [s.relpath for s in stages]
|
|
self.assertIn(self._stage_name(self.FOO), stagenames)
|
|
self.assertIn(self._stage_name(self.BAR), stagenames)
|
|
self.assertNotIn(self._stage_name(self.DATA), stagenames)
|
|
self.assertNotIn(self._stage_name(self.DATA_SUB), stagenames)
|