mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
8038b87f04
* Fix up/download of http and local paths * Support git_sparse_checkout for assets * Fix scorer * Handle already-present directories for git assets * Improve convert command * Fix support for existant files in git assets * Support branches in git sparse checkout * Format * Fix git assets * Document git block in assets * Fix test * Fix test * Revert "Fix test" This reverts commitcf3097260f. * Revert "Fix test" This reverts commit964d636e27. * Dont multiply p/r/f by 100 * Display scores * 100 during training
85 lines
3.2 KiB
Python
85 lines
3.2 KiB
Python
from typing import Optional
|
|
from pathlib import Path
|
|
from wasabi import msg
|
|
import subprocess
|
|
import shutil
|
|
import re
|
|
|
|
from ... import about
|
|
from ...util import ensure_path
|
|
from .._util import project_cli, Arg, Opt, COMMAND, PROJECT_FILE
|
|
from .._util import git_sparse_checkout
|
|
|
|
|
|
@project_cli.command("clone")
|
|
def project_clone_cli(
|
|
# fmt: off
|
|
name: str = Arg(..., help="The name of the template to clone"),
|
|
dest: Optional[Path] = Arg(None, help="Where to clone the project. Defaults to current working directory", exists=False),
|
|
repo: str = Opt(about.__projects__, "--repo", "-r", help="The repository to clone from"),
|
|
# fmt: on
|
|
):
|
|
"""Clone a project template from a repository. Calls into "git" and will
|
|
only download the files from the given subdirectory. The GitHub repo
|
|
defaults to the official spaCy template repo, but can be customized
|
|
(including using a private repo).
|
|
"""
|
|
if dest is None:
|
|
dest = Path.cwd() / name
|
|
project_clone(name, dest, repo=repo)
|
|
|
|
|
|
def project_clone(name: str, dest: Path, *, repo: str = about.__projects__) -> None:
|
|
"""Clone a project template from a repository.
|
|
|
|
name (str): Name of subdirectory to clone.
|
|
dest (Path): Destination path of cloned project.
|
|
repo (str): URL of Git repo containing project templates.
|
|
"""
|
|
dest = ensure_path(dest)
|
|
check_clone(name, dest, repo)
|
|
project_dir = dest.resolve()
|
|
repo_name = re.sub(r"(http(s?)):\/\/github.com/", "", repo)
|
|
try:
|
|
git_sparse_checkout(repo, name, dest)
|
|
except subprocess.CalledProcessError:
|
|
err = f"Could not clone '{name}' from repo '{repo_name}'"
|
|
msg.fail(err)
|
|
msg.good(f"Cloned '{name}' from {repo_name}", project_dir)
|
|
if not (project_dir / PROJECT_FILE).exists():
|
|
msg.warn(f"No {PROJECT_FILE} found in directory")
|
|
else:
|
|
msg.good(f"Your project is now ready!")
|
|
print(f"To fetch the assets, run:\n{COMMAND} project assets {dest}")
|
|
|
|
|
|
def check_clone(name: str, dest: Path, repo: str) -> None:
|
|
"""Check and validate that the destination path can be used to clone. Will
|
|
check that Git is available and that the destination path is suitable.
|
|
|
|
name (str): Name of the directory to clone from the repo.
|
|
dest (Path): Local destination of cloned directory.
|
|
repo (str): URL of the repo to clone from.
|
|
"""
|
|
try:
|
|
subprocess.run(["git", "--version"], stdout=subprocess.DEVNULL)
|
|
except Exception:
|
|
msg.fail(
|
|
f"Cloning spaCy project templates requires Git and the 'git' command. ",
|
|
f"To clone a project without Git, copy the files from the '{name}' "
|
|
f"directory in the {repo} to {dest} manually and then run:",
|
|
f"{COMMAND} project init {dest}",
|
|
exits=1,
|
|
)
|
|
if not dest:
|
|
msg.fail(f"Not a valid directory to clone project: {dest}", exits=1)
|
|
if dest.exists():
|
|
# Directory already exists (not allowed, clone needs to create it)
|
|
msg.fail(f"Can't clone project, directory already exists: {dest}", exits=1)
|
|
if not dest.parent.exists():
|
|
# We're not creating parents, parent dir should exist
|
|
msg.fail(
|
|
f"Can't clone project, parent directory doesn't exist: {dest.parent}",
|
|
exits=1,
|
|
)
|