Update project CLI

spacy/cli/project.py

@@ -7,15 +7,26 @@ import subprocess
 import shlex
 import os
 import re
+import shutil
 
-from ._app import app, Arg, Opt
+from ._app import app, Arg, Opt, COMMAND
 from .. import about
 from ..schemas import ProjectConfigSchema, validate
-from ..util import ensure_path, run_command
+from ..util import ensure_path, run_command, make_tempdir, working_dir
 
 
 CONFIG_FILE = "project.yml"
-DIRS = ["assets", "configs", "packages", "metrics", "scripts", "notebooks", "training"]
+DIRS = [
+    "assets",
+    "metas",
+    "configs",
+    "packages",
+    "metrics",
+    "scripts",
+    "notebooks",
+    "training",
+    "corpus",
+]
 CACHES = [
     Path.home() / ".torch",
     Path.home() / ".caches" / "torch",
@@ -45,28 +56,37 @@ def callback():
 def project_clone_cli(
     # fmt: off
     name: str = Arg(..., help="The name of the template to fetch"),
-    dest: Path = Arg(Path.cwd(), help="Where to download and work. Defaults to current working directory.", exists=True, file_okay=False),
+    dest: Path = Arg(Path.cwd(), help="Where to download and work. Defaults to current working directory.", exists=False),
     repo: str = Opt(about.__projects__, "--repo", "-r", help="The repository to look in."),
+    verbose: bool = Opt(False, "--verbose", "-V", help="Show detailed information")
     # fmt: on
 ):
     """Clone a project template from a repository."""
-    project_clone(name, dest, repo=repo)
+    project_clone(name, dest, repo=repo, verbose=verbose)
 
 
-def project_clone(name: str, dest: Path, repo: str = about.__projects__) -> None:
+def project_clone(
+    name: str, dest: Path, *, repo: str = about.__projects__, verbose: bool = False
+) -> None:
     dest = ensure_path(dest)
-    if not dest or not dest.exists() or not dest.is_dir():
-        msg.fail("Not a valid directory to clone project", dest, exits=1)
-    cmd = ["dvc", "get", repo, name, "-o", str(dest)]
-    msg.info(" ".join(cmd))
+    check_clone_dest(dest)
+    # When cloning a subdirectory with DVC, it will create a folder of that name
+    # within the destination dir, so we use a tempdir and then copy it into the
+    # parent directory to create the cloned directory
+    with make_tempdir() as tmp_dir:
+        cmd = ["dvc", "get", repo, name, "-o", str(tmp_dir)]
+        if verbose:
+            cmd.append("-v")
+        print(" ".join(cmd))
         run_command(cmd)
+        shutil.move(str(tmp_dir / Path(name).name), str(dest))
     msg.good(f"Cloned project '{name}' from {repo}")
-    with msg.loading("Setting up directories..."):
     for sub_dir in DIRS:
         dir_path = dest / sub_dir
         if not dir_path.exists():
             dir_path.mkdir(parents=True)
     msg.good(f"Your project is now ready!", dest.resolve())
+    print(f"To get the assets, run:\npython -m spacy project get-assets {dest}")
 
 
 @project_cli.command("get-assets")
@@ -91,7 +111,6 @@ def project_get_assets(project_path: Path) -> None:
         dest_path = project_path / dest
         check_asset(url)
         cmd = ["dvc", "get-url", url, str(dest_path)]
-        msg.info(" ".join(cmd))
         run_command(cmd)
         msg.good(f"Got asset {dest}")
 
@@ -100,18 +119,43 @@ def project_get_assets(project_path: Path) -> None:
 def project_run_cli(
     # fmt: off
     project_dir: Path = Arg(..., help="Location of project directory", exists=True, file_okay=False),
-    subcommand: str = Arg(None, help="Name of command defined in project config")
+    subcommand: str = Arg(None, help="Name of command defined in project config"),
+    show_help: bool = Opt(False, "--help", help="Show help message and available subcommands")
     # fmt: on
 ):
     """Run scripts defined in the project."""
+    if show_help:
+        print_run_help(project_dir, subcommand)
+    else:
         project_run(project_dir, subcommand)
 
 
+def print_run_help(project_dir: Path, subcommand: str) -> None:
+    """Simulate a CLI help prompt using the info available in the project config."""
+    config = load_project_config(project_dir)
+    config_commands = config.get("commands", [])
+    commands = {cmd["name"]: cmd for cmd in config_commands}
+    if subcommand:
+        if subcommand not in commands:
+            msg.fail(f"Can't find command '{subcommand}' in project config", exits=1)
+        print(f"Usage: {COMMAND} project run {project_dir} {subcommand}")
+        help_text = commands[subcommand].get("help")
+        if help_text:
+            msg.text(f"\n{help_text}\n")
+    else:
+        print(f"\nAvailable commands in {CONFIG_FILE}")
+        print(f"Usage: {COMMAND} project run {project_dir} [COMMAND]")
+        msg.table([(cmd["name"], cmd.get("help", "")) for cmd in config_commands])
+
+
 def project_run(project_dir: Path, subcommand: str) -> None:
     config = load_project_config(project_dir)
     config_commands = config.get("commands", [])
     variables = config.get("variables", {})
     commands = {cmd["name"]: cmd for cmd in config_commands}
+    if subcommand and subcommand not in commands:
+        msg.fail(f"Can't find command '{subcommand}' in project config", exits=1)
+    with working_dir(project_dir):
         if subcommand is None:
             all_commands = config.get("run", [])
             if not all_commands:
@@ -119,12 +163,12 @@ def project_run(project_dir: Path, subcommand: str) -> None:
             msg.table([(cmd["name"], cmd.get("help", "")) for cmd in config_commands])
             for command in all_commands:
                 if command not in commands:
-                msg.fail(f"Can't find command '{command}' in project config", exits=1)
+                    msg.fail(
+                        f"Can't find command '{command}' in project config", exits=1
+                    )
                 msg.divider(command)
                 run_commands(commands[command]["script"], variables)
-        return
-    if subcommand not in commands:
-        msg.fail(f"Can't find command '{subcommand}' in project config", exits=1)
+        else:
             run_commands(commands[subcommand]["script"], variables)
 
 
@@ -146,7 +190,7 @@ def run_commands(commands: List[str] = tuple(), variables: Dict[str, str] = {})
     for command in commands:
         # Substitute variables, e.g. "./{NAME}.json"
         command = command.format(**variables)
-        msg.info(command)
+        print(command)
         run_command(shlex.split(command))
 
 
@@ -160,3 +204,19 @@ def check_asset(url: str) -> None:
             "download the raw file, click on 'Download' on the GitHub page "
             "and copy the raw.githubusercontent.com URL instead."
         )
+        # url.replace("github.com", "raw.githubusercontent.com").replace("/blob/", "/").replace("/tree/", "/")
+
+
+def check_clone_dest(dest: Path) -> None:
+    """Check and validate that the destination path can be used to clone."""
+    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,
+        )

spacy/schemas.py

@@ -229,11 +229,15 @@ class ProjectConfigCommand(BaseModel):
     name: StrictStr = Field(..., title="Name of command")
     help: Optional[StrictStr] = Field(None, title="Command description")
     script: List[StrictStr] = Field([], title="List of CLI commands to run, in order")
-    dvc_deps: List[StrictStr] = Field([], title="Data Version Control dependencies")
-    dvc_outputs: List[StrictStr] = Field([], title="Data Version Control outputs")
-    dvc_outputs_no_cache: List[StrictStr] = Field([], title="Data Version Control outputs (no cache)")
+    deps: List[StrictStr] = Field([], title="Data Version Control dependencies")
+    outputs: List[StrictStr] = Field([], title="Data Version Control outputs")
+    outputs_no_cache: List[StrictStr] = Field([], title="Data Version Control outputs (no cache)")
     # fmt: on
 
+    class Config:
+        title = "A single named command specified in a project config"
+        extra = "forbid"
+
 
 class ProjectConfigSchema(BaseModel):
     # fmt: off

spacy/tests/util.py

@@ -8,8 +8,8 @@ from pathlib import Path
 from spacy import Errors
 from spacy.tokens import Doc, Span
 from spacy.attrs import POS, TAG, HEAD, DEP, LEMMA
-
 from spacy.vocab import Vocab
+from spacy.util import make_tempdir
 
 
 @contextlib.contextmanager
@@ -19,13 +19,6 @@ def make_tempfile(mode="r"):
     f.close()
 
 
-@contextlib.contextmanager
-def make_tempdir():
-    d = Path(tempfile.mkdtemp())
-    yield d
-    shutil.rmtree(str(d))
-
-
 def get_doc(
     vocab, words=[], pos=None, heads=None, deps=None, tags=None, ents=None, lemmas=None
 ):

spacy/util.py

@@ -19,6 +19,8 @@ from packaging.specifiers import SpecifierSet, InvalidSpecifier
 from packaging.version import Version, InvalidVersion
 import subprocess
 from contextlib import contextmanager
+import tempfile
+import shutil
 
 
 try:
@@ -453,6 +455,13 @@ def working_dir(path: Union[str, Path]) -> None:
         os.chdir(prev_cwd)
 
 
+@contextmanager
+def make_tempdir():
+    d = Path(tempfile.mkdtemp())
+    yield d
+    shutil.rmtree(str(d))
+
+
 def is_in_jupyter():
     """Check if user is running spaCy from a Jupyter notebook by detecting the
     IPython kernel. Mainly used for the displaCy visualizer.