Add a way to get the URL to download a pipeline to the CLI (#11175)

* Add a dry run flag to download

* Remove --dry-run, add --url option to `spacy info` instead

* Make mypy happy

* Print only the URL, so it's easier to use in scripts

* Don't add the egg hash unless downloading an sdist

* Update spacy/cli/info.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Add two implementations of requirements

* Clean up requirements sample slightly

This should make mypy happy

* Update URL help string

* Remove requirements option

* Add url option to docs

* Add URL to spacy info model output, when available

* Add types-setuptools to testing reqs

* Add types-setuptools to requirements

* Add "compatible", expand docstring

* Update spacy/cli/info.py

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Run prettier on CLI docs

* Update docs

Add a sidebar about finding download URLs, with some examples of the new
command.

* Add download URLs to table on model page

* Apply suggestions from code review

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Updates from review

* download url -> download link

* Update docs

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

requirements.txt

@@ -34,4 +34,5 @@ mypy>=0.910,<0.970; platform_machine!='aarch64'
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-requests
+types-setuptools>=57.0.0
 black>=22.0,<23.0

spacy/cli/download.py

@@ -20,7 +20,7 @@ def download_cli(
     ctx: typer.Context,
     model: str = Arg(..., help="Name of pipeline package to download"),
     direct: bool = Opt(False, "--direct", "-d", "-D", help="Force direct download of name + version"),
-    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel")
+    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel"),
     # fmt: on
 ):
     """
@@ -36,7 +36,12 @@ def download_cli(
     download(model, direct, sdist, *ctx.args)
 
 
-def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -> None:
+def download(
+    model: str,
+    direct: bool = False,
+    sdist: bool = False,
+    *pip_args,
+) -> None:
     if (
         not (is_package("spacy") or is_package("spacy-nightly"))
         and "--no-deps" not in pip_args
@@ -50,13 +55,10 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
             "dependencies, you'll have to install them manually."
         )
         pip_args = pip_args + ("--no-deps",)
-    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
-    dl_tpl = "{m}-{v}/{m}-{v}{s}#egg={m}=={v}"
     if direct:
         components = model.split("-")
         model_name = "".join(components[:-1])
         version = components[-1]
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
     else:
         model_name = model
         if model in OLD_MODEL_SHORTCUTS:
@@ -67,13 +69,26 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
             model_name = OLD_MODEL_SHORTCUTS[model]
         compatibility = get_compatibility()
         version = get_version(model_name, compatibility)
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
+
+    filename = get_model_filename(model_name, version, sdist)
+
+    download_model(filename, pip_args)
     msg.good(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
     )
 
 
+def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:
+    dl_tpl = "{m}-{v}/{m}-{v}{s}"
+    egg_tpl = "#egg={m}=={v}"
+    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
+    filename = dl_tpl.format(m=model_name, v=version, s=suffix)
+    if sdist:
+        filename += egg_tpl.format(m=model_name, v=version)
+    return filename
+
+
 def get_compatibility() -> dict:
     if is_prerelease_version(about.__version__):
         version: Optional[str] = about.__version__
@@ -105,6 +120,11 @@ def get_version(model: str, comp: dict) -> str:
     return comp[model][0]
 
 
+def get_latest_version(model: str) -> str:
+    comp = get_compatibility()
+    return get_version(model, comp)
+
+
 def download_model(
     filename: str, user_pip_args: Optional[Sequence[str]] = None
 ) -> None:

spacy/cli/info.py

@@ -1,10 +1,13 @@
 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
 
@@ -16,6 +19,7 @@ def info_cli(
     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
 ):
     """
@@ -23,10 +27,19 @@ def info_cli(
     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)
+    info(
+        model,
+        markdown=markdown,
+        silent=silent,
+        exclude=exclude,
+        url=url,
+    )
 
 
 def info(
@@ -35,11 +48,20 @@ def info(
     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 model:
+    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:
@@ -99,11 +121,43 @@ def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
         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,

spacy/tests/package/test_requirements.py

@@ -17,6 +17,7 @@ def test_build_dependencies():
         "types-dataclasses",
         "types-mock",
         "types-requests",
+        "types-setuptools",
     ]
     # ignore language-specific packages that shouldn't be installed by all
     libs_ignore_setup = [

website/docs/api/cli.md

@@ -77,14 +77,15 @@ $ python -m spacy info [--markdown] [--silent] [--exclude]
 $ python -m spacy info [model] [--markdown] [--silent] [--exclude]
 ```
 
-| Name                                             | Description                                                                                   |
+| Name                                             | Description                                                                                                             |
-| ------------------------------------------------ | --------------------------------------------------------------------------------------------- |
+| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------- |
-| `model`                                          | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~         |
+| `model`                                          | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~                                   |
-| `--markdown`, `-md`                              | Print information as Markdown. ~~bool (flag)~~                                                |
+| `--markdown`, `-md`                              | Print information as Markdown. ~~bool (flag)~~                                                                          |
-| `--silent`, `-s` <Tag variant="new">2.0.12</Tag> | Don't print anything, just return the values. ~~bool (flag)~~                                 |
+| `--silent`, `-s` <Tag variant="new">2.0.12</Tag> | Don't print anything, just return the values. ~~bool (flag)~~                                                           |
-| `--exclude`, `-e`                                | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~ |
+| `--exclude`, `-e`                                | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~                           |
-| `--help`, `-h`                                   | Show help message and available arguments. ~~bool (flag)~~                                    |
+| `--url`, `-u` <Tag variant="new">3.5.0</Tag>     | Print the URL to download the most recent compatible version of the pipeline. Requires a pipeline name. ~~bool (flag)~~ |
-| **PRINTS**                                       | Information about your spaCy installation.                                                    |
+| `--help`, `-h`                                   | Show help message and available arguments. ~~bool (flag)~~                                                              |
+| **PRINTS**                                       | Information about your spaCy installation.                                                                              |
 
 ## validate {#validate new="2" tag="command"}
 

website/docs/usage/models.md

@@ -365,15 +365,32 @@ pipeline package can be found.
 To download a trained pipeline directly using
 [pip](https://pypi.python.org/pypi/pip), point `pip install` to the URL or local
 path of the wheel file or archive. Installing the wheel is usually more
-efficient. To find the direct link to a package, head over to the
+efficient.
-[releases](https://github.com/explosion/spacy-models/releases), right click on
+
-the archive link and copy it to your clipboard.
+> #### Pipeline Package URLs {#pipeline-urls}
+>
+> Pretrained pipeline distributions are hosted on
+> [Github Releases](https://github.com/explosion/spacy-models/releases), and you
+> can find download links there, as well as on the model page. You can also get
+> URLs directly from the command line by using `spacy info` with the `--url`
+> flag, which may be useful for automation.
+>
+> ```bash
+> spacy info en_core_web_sm --url
+> ```
+>
+> This command will print the URL for the latest version of a pipeline
+> compatible with the version of spaCy you're using. Note that in order to look
+> up the compatibility information an internet connection is required.
 
 ```bash
 # With external URL
 $ pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0-py3-none-any.whl
 $ pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz
 
+# Using spacy info to get the external URL
+$ pip install $(spacy info en_core_web_sm --url)
+
 # With local file
 $ pip install /Users/you/en_core_web_sm-3.0.0-py3-none-any.whl
 $ pip install /Users/you/en_core_web_sm-3.0.0.tar.gz
@@ -514,21 +531,16 @@ should be specifying them directly.
 Because pipeline packages are valid Python packages, you can add them to your
 application's `requirements.txt`. If you're running your own internal PyPi
 installation, you can upload the pipeline packages there. pip's
-[requirements file format](https://pip.pypa.io/en/latest/reference/pip_install/#requirements-file-format)
+[requirements file format](https://pip.pypa.io/en/latest/reference/requirements-file-format/)
-supports both package names to download via a PyPi server, as well as direct
+supports both package names to download via a PyPi server, as well as
-URLs.
+[direct URLs](#pipeline-urls).
 
 ```text
 ### requirements.txt
 spacy>=3.0.0,<4.0.0
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz#egg=en_core_web_sm
+en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.0/en_core_web_sm-3.4.0-py3-none-any.whl
 ```
 
-Specifying `#egg=` with the package name tells pip which package to expect from
-the download URL. This way, the package won't be re-downloaded and overwritten
-if it's already installed - just like when you're downloading a package from
-PyPi.
-
 All pipeline packages are versioned and specify their spaCy dependency. This
 ensures cross-compatibility and lets you specify exact version requirements for
 each pipeline. If you've [trained](/usage/training) your own pipeline, you can

website/src/templates/models.js

@@ -76,6 +76,7 @@ const MODEL_META = {
     benchmark_ner: 'NER accuracy',
     benchmark_speed: 'Speed',
     compat: 'Latest compatible package version for your spaCy installation',
+    download_link: 'Download link for the pipeline',
 }
 
 const LABEL_SCHEME_META = {
@@ -138,6 +139,13 @@ function formatAccuracy(data, lang) {
         .filter(item => item)
 }
 
+function formatDownloadLink(lang, name, version) {
+  const fullName = `${lang}_${name}-${version}`
+  const filename = `${fullName}-py3-none-any.whl`
+  const url = `https://github.com/explosion/spacy-models/releases/download/${fullName}/${filename}`
+  return <Link to={url} hideIcon>{filename}</Link>
+}
+
 function formatModelMeta(data) {
     return {
         fullName: `${data.lang}_${data.name}-${data.version}`,
@@ -154,6 +162,7 @@ function formatModelMeta(data) {
         labels: isEmptyObj(data.labels) ? null : data.labels,
         vectors: formatVectors(data.vectors),
         accuracy: formatAccuracy(data.performance, data.lang),
+        download_link: formatDownloadLink(data.lang, data.name, data.version),
     }
 }
 
@@ -244,6 +253,7 @@ const Model = ({
         { label: 'Components', content: components, help: MODEL_META.components },
         { label: 'Pipeline', content: pipeline, help: MODEL_META.pipeline },
         { label: 'Vectors', content: meta.vectors, help: MODEL_META.vecs },
+        { label: 'Download Link', content: meta.download_link, help: MODEL_META.download_link },
         { label: 'Sources', content: sources, help: MODEL_META.sources },
         { label: 'Author', content: author },
         { label: 'License', content: license },