from typing import Optional import shutil from pathlib import Path from wasabi import msg, get_raw_input import srsly from ._app import app, Arg, Opt from .. import util from .. import about @app.command("package") def package( # fmt: off input_dir: str = Arg(..., help="Directory with model data"), output_dir: str = Arg(..., help="Output parent directory"), meta_path: Optional[str] = Opt(None, "--meta-path", "-m", help="Path to meta.json"), create_meta: bool = Opt(False, "--create-meta", "-c", help="Create meta.json, even if one exists"), force: bool = Opt(False, "--force", "-f", help="Force overwriting existing model in output directory"), # fmt: on ): """ 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. If --create-meta is set and a meta.json already exists in the output directory, the existing values will be used as the defaults in the command-line prompt. """ input_path = util.ensure_path(input_dir) output_path = util.ensure_path(output_dir) meta_path = util.ensure_path(meta_path) if not input_path or not input_path.exists(): msg.fail("Can't locate model data", input_path, exits=1) if not output_path or not output_path.exists(): msg.fail("Output directory not found", output_path, exits=1) if meta_path and not meta_path.exists(): msg.fail("Can't find model meta.json", meta_path, exits=1) meta_path = meta_path or input_path / "meta.json" if meta_path.is_file(): meta = srsly.read_json(meta_path) if not create_meta: # only print if user doesn't want to overwrite msg.good("Loaded meta.json from file", meta_path) else: meta = generate_meta(input_dir, meta, msg) for key in ("lang", "name", "version"): if key not in meta or meta[key] == "": msg.fail( f"No '{key}' setting found in meta.json", "This setting is required to build your package.", exits=1, ) 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 if package_path.exists(): if force: shutil.rmtree(str(package_path)) else: msg.fail( "Package directory already exists", "Please delete the directory and try again, or use the " "`--force` flag to overwrite existing directories.", exits=1, ) Path.mkdir(package_path, parents=True) shutil.copytree(str(input_path), str(package_path / model_name_v)) create_file(main_path / "meta.json", srsly.json_dumps(meta, indent=2)) create_file(main_path / "setup.py", TEMPLATE_SETUP) create_file(main_path / "MANIFEST.in", TEMPLATE_MANIFEST) create_file(package_path / "__init__.py", TEMPLATE_INIT) msg.good(f"Successfully created package '{model_name_v}'", main_path) msg.text("To build the package, run `python setup.py sdist` in this directory.") def create_file(file_path, contents): file_path.touch() file_path.open("w", encoding="utf-8").write(contents) def generate_meta(model_path, existing_meta, msg): meta = existing_meta or {} settings = [ ("lang", "Model language", meta.get("lang", "en")), ("name", "Model name", meta.get("name", "model")), ("version", "Model version", meta.get("version", "0.0.0")), ("description", "Model description", meta.get("description", False)), ("author", "Author", meta.get("author", False)), ("email", "Author email", meta.get("email", False)), ("url", "Author website", meta.get("url", False)), ("license", "License", meta.get("license", "MIT")), ] nlp = util.load_model_from_path(Path(model_path)) meta["spacy_version"] = util.get_model_version_range(about.__version__) meta["pipeline"] = nlp.pipe_names meta["vectors"] = { "width": nlp.vocab.vectors_length, "vectors": len(nlp.vocab.vectors), "keys": nlp.vocab.vectors.n_keys, "name": nlp.vocab.vectors.name, } msg.divider("Generating meta.json") msg.text( "Enter the package settings for your model. The following information " "will be read from your model data: pipeline, vectors." ) for setting, desc, default in settings: response = 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 TEMPLATE_SETUP = """ #!/usr/bin/env python import io import json from os import path, walk from shutil import copy from setuptools import setup def load_meta(fp): with io.open(fp, encoding='utf8') as f: return json.load(f) def list_files(data_dir): output = [] for root, _, filenames in walk(data_dir): for filename in filenames: if not filename.startswith('.'): output.append(path.join(root, filename)) output = [path.relpath(p, path.dirname(data_dir)) for p in output] output.append('meta.json') return output def list_requirements(meta): parent_package = meta.get('parent_package', 'spacy') requirements = [parent_package + meta['spacy_version']] if 'setup_requires' in meta: requirements += meta['setup_requires'] if 'requirements' in meta: requirements += meta['requirements'] return requirements def setup_package(): root = path.abspath(path.dirname(__file__)) meta_path = path.join(root, 'meta.json') meta = load_meta(meta_path) model_name = str(meta['lang'] + '_' + meta['name']) model_dir = path.join(model_name, model_name + '-' + meta['version']) copy(meta_path, path.join(model_name)) copy(meta_path, model_dir) setup( name=model_name, description=meta['description'], author=meta['author'], author_email=meta['email'], url=meta['url'], version=meta['version'], license=meta['license'], packages=[model_name], package_data={model_name: list_files(model_dir)}, install_requires=list_requirements(meta), zip_safe=False, entry_points={'spacy_models': ['{m} = {m}'.format(m=model_name)]} ) if __name__ == '__main__': setup_package() """.strip() TEMPLATE_MANIFEST = """ include meta.json """.strip() TEMPLATE_INIT = """ from pathlib import Path from spacy.util import load_model_from_init_py, get_model_meta __version__ = get_model_meta(Path(__file__).parent)['version'] def load(**overrides): return load_model_from_init_py(__file__, **overrides) """.strip()