spaCy/spacy/cli/project/util.py
Ines Montani a60562f208
Update project CLI hashes, directories, skipping (#5741)
* Update project CLI hashes, directories, skipping

* Improve clone success message

* Remove unused context args

* Move project-specific utils to project utils

The hashing/checksum functions may not end up being general-purpose functions and are more designed for the projects, so they shouldn't live in spacy.util

* Improve run help and add workflows

* Add note re: directory checksum speed

* Fix cloning from subdirectories and output messages

* Remove hard-coded dirs
2020-07-09 23:51:18 +02:00

94 lines
3.4 KiB
Python

from typing import Dict, Any, Union
from pathlib import Path
from wasabi import msg
import srsly
import hashlib
from ...schemas import ProjectConfigSchema, validate
PROJECT_FILE = "project.yml"
PROJECT_LOCK = "project.lock"
def load_project_config(path: Path) -> Dict[str, Any]:
"""Load the project.yml file from a directory and validate it. Also make
sure that all directories defined in the config exist.
path (Path): The path to the project directory.
RETURNS (Dict[str, Any]): The loaded project.yml.
"""
config_path = path / PROJECT_FILE
if not config_path.exists():
msg.fail(f"Can't find {PROJECT_FILE}", config_path, exits=1)
invalid_err = f"Invalid {PROJECT_FILE}. Double-check that the YAML is correct."
try:
config = srsly.read_yaml(config_path)
except ValueError as e:
msg.fail(invalid_err, e, exits=1)
errors = validate(ProjectConfigSchema, config)
if errors:
msg.fail(invalid_err, "\n".join(errors), exits=1)
validate_project_commands(config)
# Make sure directories defined in config exist
for subdir in config.get("directories", []):
dir_path = path / subdir
if not dir_path.exists():
dir_path.mkdir(parents=True)
return config
def validate_project_commands(config: Dict[str, Any]) -> None:
"""Check that project commands and workflows are valid, don't contain
duplicates, don't clash and only refer to commands that exist.
config (Dict[str, Any]): The loaded config.
"""
command_names = [cmd["name"] for cmd in config.get("commands", [])]
workflows = config.get("workflows", {})
duplicates = set([cmd for cmd in command_names if command_names.count(cmd) > 1])
if duplicates:
err = f"Duplicate commands defined in {PROJECT_FILE}: {', '.join(duplicates)}"
msg.fail(err, exits=1)
for workflow_name, workflow_steps in workflows.items():
if workflow_name in command_names:
err = f"Can't use workflow name '{workflow_name}': name already exists as a command"
msg.fail(err, exits=1)
for step in workflow_steps:
if step not in command_names:
msg.fail(
f"Unknown command specified in workflow '{workflow_name}': {step}",
f"Workflows can only refer to commands defined in the 'commands' "
f"section of the {PROJECT_FILE}.",
exits=1,
)
def get_hash(data) -> str:
"""Get the hash for a JSON-serializable object.
data: The data to hash.
RETURNS (str): The hash.
"""
data_str = srsly.json_dumps(data, sort_keys=True).encode("utf8")
return hashlib.md5(data_str).hexdigest()
def get_checksum(path: Union[Path, str]) -> str:
"""Get the checksum for a file or directory given its file path. If a
directory path is provided, this uses all files in that directory.
path (Union[Path, str]): The file or directory path.
RETURNS (str): The checksum.
"""
path = Path(path)
if path.is_file():
return hashlib.md5(Path(path).read_bytes()).hexdigest()
if path.is_dir():
# TODO: this is currently pretty slow
dir_checksum = hashlib.md5()
for sub_file in sorted(fp for fp in path.rglob("*") if fp.is_file()):
dir_checksum.update(sub_file.read_bytes())
return dir_checksum.hexdigest()
raise ValueError(f"Can't get checksum for {path}: not a file or directory")