Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Make project pull order insensitive (#6131)

This commit is contained in:
Matthew Honnibal 2020-09-24 10:30:42 +02:00 committed by GitHub
parent e2ffe51fb5
commit 17a6b0a173
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 24 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
spacy/cli/project/pull.py
View File

@ -27,19 +27,32 @@ def project_pull_cli(
def project_pull(project_dir: Path, remote: str, *, verbose: bool = False): def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
# TODO: We don't have tests for this :(. It would take a bit of mockery to
# set up. I guess see if it breaks first?
config = load_project_config(project_dir) config = load_project_config(project_dir)
if remote in config.get("remotes", {}): if remote in config.get("remotes", {}):
remote = config["remotes"][remote] remote = config["remotes"][remote]
storage = RemoteStorage(project_dir, remote) storage = RemoteStorage(project_dir, remote)
for cmd in config.get("commands", []): commands = list(config.get("commands", []))
deps = [project_dir / dep for dep in cmd.get("deps", [])] # We use a while loop here because we don't know how the commands
if any(not dep.exists() for dep in deps): # will be ordered. A command might need dependencies from one that's later
continue # in the list.
cmd_hash = get_command_hash("", "", deps, cmd["script"]) while commands:
for output_path in cmd.get("outputs", []): for i, cmd in enumerate(list(commands)):
url = storage.pull(output_path, command_hash=cmd_hash) deps = [project_dir / dep for dep in cmd.get("deps", [])]
yield url, output_path if all(dep.exists() for dep in deps):
cmd_hash = get_command_hash("", "", deps, cmd["script"])
for output_path in cmd.get("outputs", []):
url = storage.pull(output_path, command_hash=cmd_hash)
yield url, output_path
out_locs = [project_dir / out for out in cmd.get("outputs", [])] out_locs = [project_dir / out for out in cmd.get("outputs", [])]
if all(loc.exists() for loc in out_locs): if all(loc.exists() for loc in out_locs):
update_lockfile(project_dir, cmd) update_lockfile(project_dir, cmd)
# We remove the command from the list here, and break, so that
# we iterate over the loop again.
commands.remove(i)
break
else:
# If we didn't break the for loop, break the while loop.
break