spaCy/spacy/cli/info.py

192 lines
6.3 KiB
Python

from typing import Optional, Dict, Any, Union, List
import platform
import pkg_resources
import json
from pathlib import Path
from wasabi import Printer, MarkdownRenderer
import srsly
from ._util import app, Arg, Opt, string_to_list
from .download import get_model_filename, get_latest_version
from .. import util
from .. import about
@app.command("info")
def info_cli(
# fmt: off
model: Optional[str] = Arg(None, help="Optional loadable spaCy pipeline"),
markdown: bool = Opt(False, "--markdown", "-md", help="Generate Markdown for GitHub issues"),
silent: bool = Opt(False, "--silent", "-s", "-S", help="Don't print anything (just return)"),
exclude: str = Opt("labels", "--exclude", "-e", help="Comma-separated keys to exclude from the print-out"),
url: bool = Opt(False, "--url", "-u", help="Print the URL to download the most recent compatible version of the pipeline"),
# fmt: on
):
"""
Print info about spaCy installation. If a pipeline is specified as an argument,
print its meta information. Flag --markdown prints details in Markdown for easy
copy-pasting to GitHub issues.
Flag --url prints only the download URL of the most recent compatible
version of the pipeline.
DOCS: https://spacy.io/api/cli#info
"""
exclude = string_to_list(exclude)
info(
model,
markdown=markdown,
silent=silent,
exclude=exclude,
url=url,
)
def info(
model: Optional[str] = None,
*,
markdown: bool = False,
silent: bool = True,
exclude: Optional[List[str]] = None,
url: bool = False,
) -> Union[str, dict]:
msg = Printer(no_print=silent, pretty=not silent)
if not exclude:
exclude = []
if url:
if model is not None:
title = f"Download info for pipeline '{model}'"
data = info_model_url(model)
print(data["download_url"])
return data
else:
msg.fail("--url option requires a pipeline name", exits=1)
elif model:
title = f"Info about pipeline '{model}'"
data = info_model(model, silent=silent)
else:
title = "Info about spaCy"
data = info_spacy()
raw_data = {k.lower().replace(" ", "_"): v for k, v in data.items()}
if "Pipelines" in data and isinstance(data["Pipelines"], dict):
data["Pipelines"] = ", ".join(
f"{n} ({v})" for n, v in data["Pipelines"].items()
)
markdown_data = get_markdown(data, title=title, exclude=exclude)
if markdown:
if not silent:
print(markdown_data)
return markdown_data
if not silent:
table_data = {k: v for k, v in data.items() if k not in exclude}
msg.table(table_data, title=title)
return raw_data
def info_spacy() -> Dict[str, Any]:
"""Generate info about the current spaCy intallation.
RETURNS (dict): The spaCy info.
"""
all_models = {}
for pkg_name in util.get_installed_models():
package = pkg_name.replace("-", "_")
all_models[package] = util.get_package_version(pkg_name)
return {
"spaCy version": about.__version__,
"Location": str(Path(__file__).parent.parent),
"Platform": platform.platform(),
"Python version": platform.python_version(),
"Pipelines": all_models,
}
def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
"""Generate info about a specific model.
model (str): Model name of path.
silent (bool): Don't print anything, just return.
RETURNS (dict): The model meta.
"""
msg = Printer(no_print=silent, pretty=not silent)
if util.is_package(model):
model_path = util.get_package_path(model)
else:
model_path = Path(model)
meta_path = model_path / "meta.json"
if not meta_path.is_file():
msg.fail("Can't find pipeline meta.json", meta_path, exits=1)
meta = srsly.read_json(meta_path)
if model_path.resolve() != model_path:
meta["source"] = str(model_path.resolve())
else:
meta["source"] = str(model_path)
download_url = info_installed_model_url(model)
if download_url:
meta["download_url"] = download_url
return {
k: v for k, v in meta.items() if k not in ("accuracy", "performance", "speed")
}
def info_installed_model_url(model: str) -> Optional[str]:
"""Given a pipeline name, get the download URL if available, otherwise
return None.
This is only available for pipelines installed as modules that have
dist-info available.
"""
try:
dist = pkg_resources.get_distribution(model)
data = json.loads(dist.get_metadata("direct_url.json"))
return data["url"]
except pkg_resources.DistributionNotFound:
# no such package
return None
except Exception:
# something else, like no file or invalid JSON
return None
def info_model_url(model: str) -> Dict[str, Any]:
"""Return the download URL for the latest version of a pipeline."""
version = get_latest_version(model)
filename = get_model_filename(model, version)
download_url = about.__download_url__ + "/" + filename
release_tpl = "https://github.com/explosion/spacy-models/releases/tag/{m}-{v}"
release_url = release_tpl.format(m=model, v=version)
return {"download_url": download_url, "release_url": release_url}
def get_markdown(
data: Dict[str, Any],
title: Optional[str] = None,
exclude: Optional[List[str]] = None,
) -> str:
"""Get data in GitHub-flavoured Markdown format for issues etc.
data (Dict[str, Any]): Label/value pairs.
title (str): Optional title, will be rendered as headline 2.
exclude (List[str]): Names of keys to exclude.
RETURNS (str): The Markdown string.
"""
md = MarkdownRenderer()
if title:
md.add(md.title(2, title))
items = []
for key, value in data.items():
if exclude and key in exclude:
continue
if isinstance(value, str):
try:
existing_path = Path(value).exists()
except Exception:
# invalid Path, like a URL string
existing_path = False
if existing_path:
continue
items.append(f"{md.bold(f'{key}:')} {value}")
md.add(md.list(items))
return f"\n{md.text}\n"