2020-08-29 13:20:11 +00:00
|
|
|
from typing import Optional, List, Dict, Sequence, Any, Iterable
|
2020-07-08 23:42:51 +00:00
|
|
|
from pathlib import Path
|
|
|
|
from wasabi import msg
|
|
|
|
import sys
|
|
|
|
import srsly
|
|
|
|
|
2020-10-05 11:53:07 +00:00
|
|
|
from ... import about
|
|
|
|
from ...git_info import GIT_VERSION
|
2020-07-09 21:51:18 +00:00
|
|
|
from ...util import working_dir, run_command, split_command, is_cwd, join_command
|
2020-10-05 18:51:15 +00:00
|
|
|
from ...util import SimpleFrozenList, is_minor_version_match, ENV_VARS
|
|
|
|
from ...util import check_bool_env_var
|
2020-07-10 15:57:40 +00:00
|
|
|
from .._util import PROJECT_FILE, PROJECT_LOCK, load_project_config, get_hash
|
|
|
|
from .._util import get_checksum, project_cli, Arg, Opt, COMMAND
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
2020-07-09 21:51:18 +00:00
|
|
|
@project_cli.command("run")
|
2020-07-08 23:42:51 +00:00
|
|
|
def project_run_cli(
|
|
|
|
# fmt: off
|
|
|
|
subcommand: str = Arg(None, help=f"Name of command defined in the {PROJECT_FILE}"),
|
|
|
|
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
|
|
|
|
force: bool = Opt(False, "--force", "-F", help="Force re-running steps, even if nothing changed"),
|
2020-07-09 17:44:28 +00:00
|
|
|
dry: bool = Opt(False, "--dry", "-D", help="Perform a dry run and don't execute scripts"),
|
2020-07-08 23:42:51 +00:00
|
|
|
show_help: bool = Opt(False, "--help", help="Show help message and available subcommands")
|
|
|
|
# fmt: on
|
|
|
|
):
|
2020-07-09 17:44:28 +00:00
|
|
|
"""Run a named command or workflow defined in the project.yml. If a workflow
|
2020-07-08 23:42:51 +00:00
|
|
|
name is specified, all commands in the workflow are run, in order. If
|
2020-07-09 17:44:28 +00:00
|
|
|
commands define dependencies and/or outputs, they will only be re-run if
|
|
|
|
state has changed.
|
2020-09-04 10:58:50 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/cli#project-run
|
2020-07-08 23:42:51 +00:00
|
|
|
"""
|
|
|
|
if show_help or not subcommand:
|
|
|
|
print_run_help(project_dir, subcommand)
|
|
|
|
else:
|
2020-07-09 21:51:18 +00:00
|
|
|
project_run(project_dir, subcommand, force=force, dry=dry)
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
def project_run(
|
2021-02-02 02:11:15 +00:00
|
|
|
project_dir: Path,
|
|
|
|
subcommand: str,
|
|
|
|
*,
|
|
|
|
force: bool = False,
|
|
|
|
dry: bool = False,
|
|
|
|
capture: bool = False,
|
2020-07-08 23:42:51 +00:00
|
|
|
) -> None:
|
|
|
|
"""Run a named script defined in the project.yml. If the script is part
|
|
|
|
of the default pipeline (defined in the "run" section), DVC is used to
|
|
|
|
execute the command, so it can determine whether to rerun it. It then
|
|
|
|
calls into "exec" to execute it.
|
|
|
|
|
|
|
|
project_dir (Path): Path to project directory.
|
|
|
|
subcommand (str): Name of command to run.
|
|
|
|
force (bool): Force re-running, even if nothing changed.
|
|
|
|
dry (bool): Perform a dry run and don't execute commands.
|
2021-02-02 02:11:15 +00:00
|
|
|
capture (bool): Whether to capture the output and errors of individual commands.
|
|
|
|
If False, the stdout and stderr will not be redirected, and if there's an error,
|
|
|
|
sys.exit will be called with the return code. You should use capture=False
|
|
|
|
when you want to turn over execution to the command, and capture=True
|
|
|
|
when you want to run the command more like a function.
|
2020-07-08 23:42:51 +00:00
|
|
|
"""
|
|
|
|
config = load_project_config(project_dir)
|
|
|
|
commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
|
|
|
|
workflows = config.get("workflows", {})
|
|
|
|
validate_subcommand(commands.keys(), workflows.keys(), subcommand)
|
|
|
|
if subcommand in workflows:
|
|
|
|
msg.info(f"Running workflow '{subcommand}'")
|
|
|
|
for cmd in workflows[subcommand]:
|
|
|
|
project_run(project_dir, cmd, force=force, dry=dry)
|
|
|
|
else:
|
|
|
|
cmd = commands[subcommand]
|
|
|
|
for dep in cmd.get("deps", []):
|
|
|
|
if not (project_dir / dep).exists():
|
|
|
|
err = f"Missing dependency specified by command '{subcommand}': {dep}"
|
2020-09-22 07:45:34 +00:00
|
|
|
err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
|
2020-07-08 23:42:51 +00:00
|
|
|
err_kwargs = {"exits": 1} if not dry else {}
|
2020-09-20 15:44:51 +00:00
|
|
|
msg.fail(err, err_help, **err_kwargs)
|
2020-10-05 18:51:15 +00:00
|
|
|
check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
|
2020-07-08 23:42:51 +00:00
|
|
|
with working_dir(project_dir) as current_dir:
|
2020-10-05 11:53:07 +00:00
|
|
|
msg.divider(subcommand)
|
2020-10-05 18:51:15 +00:00
|
|
|
rerun = check_rerun(current_dir, cmd, check_spacy_commit=check_spacy_commit)
|
2020-07-08 23:42:51 +00:00
|
|
|
if not rerun and not force:
|
|
|
|
msg.info(f"Skipping '{cmd['name']}': nothing changed")
|
|
|
|
else:
|
2021-02-02 02:11:15 +00:00
|
|
|
run_commands(cmd["script"], dry=dry, capture=capture)
|
2020-07-09 21:51:18 +00:00
|
|
|
if not dry:
|
2020-08-23 16:32:09 +00:00
|
|
|
update_lockfile(current_dir, cmd)
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
def print_run_help(project_dir: Path, subcommand: Optional[str] = None) -> None:
|
|
|
|
"""Simulate a CLI help prompt using the info available in the project.yml.
|
|
|
|
|
|
|
|
project_dir (Path): The project directory.
|
|
|
|
subcommand (Optional[str]): The subcommand or None. If a subcommand is
|
|
|
|
provided, the subcommand help is shown. Otherwise, the top-level help
|
|
|
|
and a list of available commands is printed.
|
|
|
|
"""
|
|
|
|
config = load_project_config(project_dir)
|
|
|
|
config_commands = config.get("commands", [])
|
|
|
|
commands = {cmd["name"]: cmd for cmd in config_commands}
|
2020-07-09 21:51:18 +00:00
|
|
|
workflows = config.get("workflows", {})
|
2020-07-08 23:42:51 +00:00
|
|
|
project_loc = "" if is_cwd(project_dir) else project_dir
|
|
|
|
if subcommand:
|
2020-07-09 21:51:18 +00:00
|
|
|
validate_subcommand(commands.keys(), workflows.keys(), subcommand)
|
2020-07-08 23:42:51 +00:00
|
|
|
print(f"Usage: {COMMAND} project run {subcommand} {project_loc}")
|
2020-07-09 21:51:18 +00:00
|
|
|
if subcommand in commands:
|
|
|
|
help_text = commands[subcommand].get("help")
|
|
|
|
if help_text:
|
|
|
|
print(f"\n{help_text}\n")
|
|
|
|
elif subcommand in workflows:
|
|
|
|
steps = workflows[subcommand]
|
|
|
|
print(f"\nWorkflow consisting of {len(steps)} commands:")
|
|
|
|
steps_data = [
|
|
|
|
(f"{i + 1}. {step}", commands[step].get("help", ""))
|
|
|
|
for i, step in enumerate(steps)
|
|
|
|
]
|
|
|
|
msg.table(steps_data)
|
|
|
|
help_cmd = f"{COMMAND} project run [COMMAND] {project_loc} --help"
|
|
|
|
print(f"For command details, run: {help_cmd}")
|
2020-07-08 23:42:51 +00:00
|
|
|
else:
|
2020-07-09 21:51:18 +00:00
|
|
|
print("")
|
2020-08-26 08:26:57 +00:00
|
|
|
title = config.get("title")
|
|
|
|
if title:
|
|
|
|
print(f"{title}\n")
|
2020-07-09 21:51:18 +00:00
|
|
|
if config_commands:
|
|
|
|
print(f"Available commands in {PROJECT_FILE}")
|
|
|
|
print(f"Usage: {COMMAND} project run [COMMAND] {project_loc}")
|
|
|
|
msg.table([(cmd["name"], cmd.get("help", "")) for cmd in config_commands])
|
|
|
|
if workflows:
|
|
|
|
print(f"Available workflows in {PROJECT_FILE}")
|
|
|
|
print(f"Usage: {COMMAND} project run [WORKFLOW] {project_loc}")
|
|
|
|
msg.table([(name, " -> ".join(steps)) for name, steps in workflows.items()])
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
def run_commands(
|
2020-08-29 13:20:11 +00:00
|
|
|
commands: Iterable[str] = SimpleFrozenList(),
|
|
|
|
silent: bool = False,
|
|
|
|
dry: bool = False,
|
2021-02-02 02:11:15 +00:00
|
|
|
capture: bool = False,
|
2020-07-08 23:42:51 +00:00
|
|
|
) -> None:
|
|
|
|
"""Run a sequence of commands in a subprocess, in order.
|
|
|
|
|
|
|
|
commands (List[str]): The string commands.
|
|
|
|
silent (bool): Don't print the commands.
|
|
|
|
dry (bool): Perform a dry run and don't execut anything.
|
2021-02-02 02:11:15 +00:00
|
|
|
capture (bool): Whether to capture the output and errors of individual commands.
|
|
|
|
If False, the stdout and stderr will not be redirected, and if there's an error,
|
|
|
|
sys.exit will be called with the return code. You should use capture=False
|
|
|
|
when you want to turn over execution to the command, and capture=True
|
|
|
|
when you want to run the command more like a function.
|
2020-07-08 23:42:51 +00:00
|
|
|
"""
|
|
|
|
for command in commands:
|
|
|
|
command = split_command(command)
|
|
|
|
# Not sure if this is needed or a good idea. Motivation: users may often
|
|
|
|
# use commands in their config that reference "python" and we want to
|
|
|
|
# make sure that it's always executing the same Python that spaCy is
|
|
|
|
# executed with and the pip in the same env, not some other Python/pip.
|
|
|
|
# Also ensures cross-compatibility if user 1 writes "python3" (because
|
|
|
|
# that's how it's set up on their system), and user 2 without the
|
|
|
|
# shortcut tries to re-run the command.
|
|
|
|
if len(command) and command[0] in ("python", "python3"):
|
|
|
|
command[0] = sys.executable
|
|
|
|
elif len(command) and command[0] in ("pip", "pip3"):
|
|
|
|
command = [sys.executable, "-m", "pip", *command[1:]]
|
|
|
|
if not silent:
|
|
|
|
print(f"Running command: {join_command(command)}")
|
|
|
|
if not dry:
|
2021-02-02 02:11:15 +00:00
|
|
|
run_command(command, capture=capture)
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
def validate_subcommand(
|
|
|
|
commands: Sequence[str], workflows: Sequence[str], subcommand: str
|
|
|
|
) -> None:
|
|
|
|
"""Check that a subcommand is valid and defined. Raises an error otherwise.
|
|
|
|
|
|
|
|
commands (Sequence[str]): The available commands.
|
|
|
|
subcommand (str): The subcommand.
|
|
|
|
"""
|
|
|
|
if not commands and not workflows:
|
|
|
|
msg.fail(f"No commands or workflows defined in {PROJECT_FILE}", exits=1)
|
|
|
|
if subcommand not in commands and subcommand not in workflows:
|
|
|
|
help_msg = []
|
|
|
|
if commands:
|
|
|
|
help_msg.append(f"Available commands: {', '.join(commands)}")
|
|
|
|
if workflows:
|
|
|
|
help_msg.append(f"Available workflows: {', '.join(workflows)}")
|
|
|
|
msg.fail(
|
|
|
|
f"Can't find command or workflow '{subcommand}' in {PROJECT_FILE}",
|
|
|
|
". ".join(help_msg),
|
|
|
|
exits=1,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
2020-10-05 11:53:07 +00:00
|
|
|
def check_rerun(
|
|
|
|
project_dir: Path,
|
|
|
|
command: Dict[str, Any],
|
2020-10-05 15:07:35 +00:00
|
|
|
*,
|
2020-10-05 11:53:07 +00:00
|
|
|
check_spacy_version: bool = True,
|
|
|
|
check_spacy_commit: bool = False,
|
|
|
|
) -> bool:
|
2020-07-08 23:42:51 +00:00
|
|
|
"""Check if a command should be rerun because its settings or inputs/outputs
|
|
|
|
changed.
|
|
|
|
|
|
|
|
project_dir (Path): The current project directory.
|
|
|
|
command (Dict[str, Any]): The command, as defined in the project.yml.
|
2020-10-05 11:53:07 +00:00
|
|
|
strict_version (bool):
|
2020-07-08 23:42:51 +00:00
|
|
|
RETURNS (bool): Whether to re-run the command.
|
|
|
|
"""
|
|
|
|
lock_path = project_dir / PROJECT_LOCK
|
|
|
|
if not lock_path.exists(): # We don't have a lockfile, run command
|
|
|
|
return True
|
|
|
|
data = srsly.read_yaml(lock_path)
|
|
|
|
if command["name"] not in data: # We don't have info about this command
|
|
|
|
return True
|
|
|
|
entry = data[command["name"]]
|
2020-07-09 21:51:18 +00:00
|
|
|
# Always run commands with no outputs (otherwise they'd always be skipped)
|
|
|
|
if not entry.get("outs", []):
|
|
|
|
return True
|
2020-10-05 11:53:07 +00:00
|
|
|
# Always rerun if spaCy version or commit hash changed
|
|
|
|
spacy_v = entry.get("spacy_version")
|
|
|
|
commit = entry.get("spacy_git_version")
|
|
|
|
if check_spacy_version and not is_minor_version_match(spacy_v, about.__version__):
|
|
|
|
info = f"({spacy_v} in {PROJECT_LOCK}, {about.__version__} current)"
|
|
|
|
msg.info(f"Re-running '{command['name']}': spaCy minor version changed {info}")
|
|
|
|
return True
|
|
|
|
if check_spacy_commit and commit != GIT_VERSION:
|
|
|
|
info = f"({commit} in {PROJECT_LOCK}, {GIT_VERSION} current)"
|
|
|
|
msg.info(f"Re-running '{command['name']}': spaCy commit changed {info}")
|
|
|
|
return True
|
2020-07-08 23:42:51 +00:00
|
|
|
# If the entry in the lockfile matches the lockfile entry that would be
|
|
|
|
# generated from the current command, we don't rerun because it means that
|
|
|
|
# all inputs/outputs, hashes and scripts are the same and nothing changed
|
2020-10-05 11:53:07 +00:00
|
|
|
lock_entry = get_lock_entry(project_dir, command)
|
|
|
|
exclude = ["spacy_version", "spacy_git_version"]
|
|
|
|
return get_hash(lock_entry, exclude=exclude) != get_hash(entry, exclude=exclude)
|
2020-07-08 23:42:51 +00:00
|
|
|
|
|
|
|
|
2020-08-23 16:32:09 +00:00
|
|
|
def update_lockfile(project_dir: Path, command: Dict[str, Any]) -> None:
|
2020-07-08 23:42:51 +00:00
|
|
|
"""Update the lockfile after running a command. Will create a lockfile if
|
|
|
|
it doesn't yet exist and will add an entry for the current command, its
|
|
|
|
script and dependencies/outputs.
|
|
|
|
|
|
|
|
project_dir (Path): The current project directory.
|
|
|
|
command (Dict[str, Any]): The command, as defined in the project.yml.
|
|
|
|
"""
|
|
|
|
lock_path = project_dir / PROJECT_LOCK
|
|
|
|
if not lock_path.exists():
|
|
|
|
srsly.write_yaml(lock_path, {})
|
|
|
|
data = {}
|
|
|
|
else:
|
|
|
|
data = srsly.read_yaml(lock_path)
|
2020-08-23 16:32:09 +00:00
|
|
|
data[command["name"]] = get_lock_entry(project_dir, command)
|
2020-07-08 23:42:51 +00:00
|
|
|
srsly.write_yaml(lock_path, data)
|
|
|
|
|
|
|
|
|
2020-08-23 16:32:09 +00:00
|
|
|
def get_lock_entry(project_dir: Path, command: Dict[str, Any]) -> Dict[str, Any]:
|
2020-07-08 23:42:51 +00:00
|
|
|
"""Get a lockfile entry for a given command. An entry includes the command,
|
|
|
|
the script (command steps) and a list of dependencies and outputs with
|
|
|
|
their paths and file hashes, if available. The format is based on the
|
|
|
|
dvc.lock files, to keep things consistent.
|
|
|
|
|
|
|
|
project_dir (Path): The current project directory.
|
|
|
|
command (Dict[str, Any]): The command, as defined in the project.yml.
|
|
|
|
RETURNS (Dict[str, Any]): The lockfile entry.
|
|
|
|
"""
|
2020-08-23 16:32:09 +00:00
|
|
|
deps = get_fileinfo(project_dir, command.get("deps", []))
|
|
|
|
outs = get_fileinfo(project_dir, command.get("outputs", []))
|
|
|
|
outs_nc = get_fileinfo(project_dir, command.get("outputs_no_cache", []))
|
2020-07-08 23:42:51 +00:00
|
|
|
return {
|
|
|
|
"cmd": f"{COMMAND} run {command['name']}",
|
|
|
|
"script": command["script"],
|
|
|
|
"deps": deps,
|
|
|
|
"outs": [*outs, *outs_nc],
|
2020-10-05 11:53:07 +00:00
|
|
|
"spacy_version": about.__version__,
|
|
|
|
"spacy_git_version": GIT_VERSION,
|
2020-07-08 23:42:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2020-08-23 16:32:09 +00:00
|
|
|
def get_fileinfo(project_dir: Path, paths: List[str]) -> List[Dict[str, str]]:
|
2020-07-08 23:42:51 +00:00
|
|
|
"""Generate the file information for a list of paths (dependencies, outputs).
|
|
|
|
Includes the file path and the file's checksum.
|
|
|
|
|
|
|
|
project_dir (Path): The current project directory.
|
|
|
|
paths (List[str]): The file paths.
|
|
|
|
RETURNS (List[Dict[str, str]]): The lockfile entry for a file.
|
|
|
|
"""
|
|
|
|
data = []
|
|
|
|
for path in paths:
|
|
|
|
file_path = project_dir / path
|
|
|
|
md5 = get_checksum(file_path) if file_path.exists() else None
|
|
|
|
data.append({"path": path, "md5": md5})
|
|
|
|
return data
|