explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-02 11:20:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

Don't re-download installed models

Browse Source 
When downloading a model, this checks if the same version of the same
model is already installed. If it is then the download is skipped.

This is necessary because pip uses the final download URL for its
caching feature, but because of the way models are hosted on Github,
their URLs change every few minutes.
This commit is contained in:
Paul O'Leary McCann 2023-01-26 19:13:50 +09:00
parent de360bc981
commit ed47384da1
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/cli/download.py
View File

@ -3,11 +3,12 @@ import requests
import sys
from wasabi import msg
import typer
import srsly
from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
from .. import about
from ..util import is_package, get_minor_version, run_command
from ..util import is_prerelease_version
from ..util import is_prerelease_version, get_installed_models, get_package_path
@app.command(
@ -63,6 +64,16 @@ def download(
compatibility = get_compatibility()
version = get_version(model_name, compatibility)
# If we already have this version installed, skip downloading
installed = get_installed_models()
if model_name in installed:
model_path = get_package_path(model_name)
meta_path = model_path / "meta.json"
meta = srsly.read_json(meta_path)
if meta["version"] == version:
msg.warn(f"{model_name} v{version} already installed, skipping")
return
filename = get_model_filename(model_name, version, sdist)
download_model(filename, pip_args)