spaCy/spacy/cli/package.py

126 lines
4.9 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
import plac
2017-03-21 04:06:29 +03:00
import shutil
import requests
from pathlib import Path
2017-05-08 00:25:29 +03:00
from ..compat import path2str, json_dumps
from ..util import prints
from .. import util
2017-05-08 00:25:29 +03:00
from .. import about
@plac.annotations(
input_dir=("directory with model data", "positional", None, str),
output_dir=("output parent directory", "positional", None, str),
meta_path=("path to meta.json", "option", "m", str),
2017-10-27 15:38:39 +03:00
create_meta=("create meta.json, even if one exists in directory", "flag",
"c", bool),
force=("force overwriting of existing folder in output directory", "flag",
"f", bool))
def package(cmd, input_dir, output_dir, meta_path=None, create_meta=False,
force=False):
"""
Generate Python package for model data, including meta and required
installation files. A new directory will be created in the specified
output directory, and model data will be copied over.
"""
2017-05-08 00:25:29 +03:00
input_path = util.ensure_path(input_dir)
output_path = util.ensure_path(output_dir)
meta_path = util.ensure_path(meta_path)
2017-05-08 00:25:29 +03:00
if not input_path or not input_path.exists():
prints(input_path, title="Model directory not found", exits=1)
2017-05-08 00:25:29 +03:00
if not output_path or not output_path.exists():
prints(output_path, title="Output directory not found", exits=1)
2017-05-08 00:25:29 +03:00
if meta_path and not meta_path.exists():
prints(meta_path, title="meta.json not found", exits=1)
template_setup = get_template('setup.py')
2017-03-21 13:32:38 +03:00
template_manifest = get_template('MANIFEST.in')
2017-05-29 16:27:24 +03:00
template_init = get_template('xx_model_name/__init__.py')
meta_path = meta_path or input_path / 'meta.json'
if not create_meta and meta_path.is_file():
2017-05-08 00:25:29 +03:00
prints(meta_path, title="Reading meta.json from file")
meta = util.read_json(meta_path)
else:
meta = generate_meta(input_dir)
meta = validate_meta(meta, ['lang', 'name', 'version'])
2017-05-08 00:25:29 +03:00
model_name = meta['lang'] + '_' + meta['name']
model_name_v = model_name + '-' + meta['version']
main_path = output_path / model_name_v
package_path = main_path / model_name
create_dirs(package_path, force)
2017-10-27 15:38:39 +03:00
shutil.copytree(path2str(input_path),
path2str(package_path / model_name_v))
create_file(main_path / 'meta.json', json_dumps(meta))
create_file(main_path / 'setup.py', template_setup)
create_file(main_path / 'MANIFEST.in', template_manifest)
create_file(package_path / '__init__.py', template_init)
2017-10-27 15:38:39 +03:00
prints(main_path, "To build the package, run `python setup.py sdist` in "
"this directory.",
title="Successfully created package '%s'" % model_name_v)
def create_dirs(package_path, force):
if package_path.exists():
if force:
2017-05-08 00:25:29 +03:00
shutil.rmtree(path2str(package_path))
else:
2017-10-27 15:38:39 +03:00
prints(package_path, "Please delete the directory and try again, "
"or use the --force flag to overwrite existing "
"directories.", title="Package directory already exists",
exits=1)
Path.mkdir(package_path, parents=True)
def create_file(file_path, contents):
file_path.touch()
file_path.open('w', encoding='utf-8').write(contents)
def generate_meta(model_path):
meta = {}
settings = [('lang', 'Model language', 'en'),
('name', 'Model name', 'model'),
('version', 'Model version', '0.0.0'),
2017-10-27 15:38:39 +03:00
('spacy_version', 'Required spaCy version',
'>=%s,<3.0.0' % about.__version__),
('description', 'Model description', False),
('author', 'Author', False),
('email', 'Author email', False),
('url', 'Author website', False),
2017-03-21 14:24:43 +03:00
('license', 'License', 'CC BY-NC 3.0')]
nlp = util.load_model_from_path(Path(model_path))
meta['pipeline'] = nlp.pipe_names
meta['vectors'] = {'width': nlp.vocab.vectors_length,
'entries': len(nlp.vocab.vectors)}
prints("Enter the package settings for your model. The following "
"information will be read from your model data: pipeline, vectors.",
title="Generating meta.json")
for setting, desc, default in settings:
response = util.get_raw_input(desc, default)
meta[setting] = default if response == '' and default else response
if about.__title__ != 'spacy':
meta['parent_package'] = about.__title__
return meta
def validate_meta(meta, keys):
for key in keys:
if key not in meta or meta[key] == '':
2017-05-08 00:25:29 +03:00
prints("This setting is required to build your package.",
title='No "%s" setting found in meta.json' % key, exits=1)
return meta
def get_template(filepath):
2017-05-08 00:25:29 +03:00
r = requests.get(about.__model_files__ + filepath)
if r.status_code != 200:
2017-05-08 00:25:29 +03:00
prints("Couldn't fetch template files from GitHub.",
title="Server error (%d)" % r.status_code, exits=1)
return r.text