Demo: Switch from pathy to cloudpathlib

This commit is contained in:
Adriane Boyd 2022-11-04 15:44:45 +01:00
parent 40e1000db0
commit 4b64c1bbcc
5 changed files with 78 additions and 27 deletions

View File

@ -10,7 +10,7 @@ wasabi>=0.9.1,<1.1.0
srsly>=2.4.3,<3.0.0
catalogue>=2.0.6,<2.1.0
typer>=0.3.0,<0.5.0
pathy>=0.3.5
cloudpathlib>=0.7.0,<0.11.0
# Third party dependencies
numpy>=1.15.0
requests>=2.13.0,<3.0.0

View File

@ -52,7 +52,7 @@ install_requires =
catalogue>=2.0.6,<2.1.0
# Third-party dependencies
typer>=0.3.0,<0.5.0
pathy>=0.3.5
cloudpathlib>=0.7.0,<0.11.0
tqdm>=4.38.0,<5.0.0
numpy>=1.15.0
requests>=2.13.0,<3.0.0

View File

@ -23,7 +23,7 @@ from ..util import is_compatible_version, SimpleFrozenDict, ENV_VARS
from .. import about
if TYPE_CHECKING:
from pathy import Pathy # noqa: F401
from cloudpathlib import CloudPath # noqa: F401
SDIST_SUFFIX = ".tar.gz"
@ -331,21 +331,25 @@ def import_code(code_path: Optional[Union[Path, str]]) -> None:
msg.fail(f"Couldn't load Python code: {code_path}", e, exits=1)
def upload_file(src: Path, dest: Union[str, "Pathy"]) -> None:
def upload_file(src: Path, dest: Union[str, Path, "CloudPath"]) -> None:
"""Upload a file.
src (Path): The source path.
url (str): The destination URL to upload to.
"""
import smart_open
# Create parent directories for local paths
if isinstance(dest, Path):
if not dest.parent.exists():
dest.parent.mkdir(parents=True)
dest = str(dest)
with smart_open.open(dest, mode="wb") as output_file:
with dest.open(mode="wb") as output_file:
with src.open(mode="rb") as input_file:
output_file.write(input_file.read())
def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False) -> None:
def download_file(
src: Union[str, Path, "CloudPath"], dest: Path, *, force: bool = False
) -> None:
"""Download a file using smart_open.
url (str): The URL of the file.
@ -353,22 +357,19 @@ def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False)
force (bool): Whether to force download even if file exists.
If False, the download will be skipped.
"""
import smart_open
if dest.exists() and not force:
return None
src = str(src)
with smart_open.open(src, mode="rb", ignore_ext=True) as input_file:
with src.open(mode="rb") as input_file:
with dest.open(mode="wb") as output_file:
shutil.copyfileobj(input_file, output_file)
def ensure_pathy(path):
"""Temporary helper to prevent importing Pathy globally (which can cause
"""Temporary helper to prevent importing globally (which can cause
slow and annoying Google Cloud warning)."""
from pathy import Pathy # noqa: F811
from cloudpathlib import AnyPath # noqa: F811
return Pathy(path)
return AnyPath(path)
def git_checkout(

View File

@ -1,18 +1,20 @@
from typing import Optional, List, Dict, TYPE_CHECKING
from typing import Optional, List, Dict, TYPE_CHECKING, Union
import os
import site
import hashlib
import urllib.parse
import tarfile
import warnings
from pathlib import Path
from .._util import get_hash, get_checksum, download_file, ensure_pathy
from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var
from .._util import get_hash, get_checksum, upload_file, download_file
from .._util import ensure_pathy, make_tempdir
from ...util import get_minor_version, ENV_VARS, check_bool_env_var
from ...git_info import GIT_VERSION
from ... import about
if TYPE_CHECKING:
from pathy import Pathy # noqa: F401
from cloudpathlib import CloudPath # noqa: F401
class RemoteStorage:
@ -27,7 +29,7 @@ class RemoteStorage:
self.url = ensure_pathy(url)
self.compression = compression
def push(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
def push(self, path: Path, command_hash: str, content_hash: str) -> Union[Path, "CloudPath"]:
"""Compress a file or directory within a project and upload it to a remote
storage. If an object exists at the full URL, nothing is done.
@ -48,9 +50,7 @@ class RemoteStorage:
mode_string = f"w:{self.compression}" if self.compression else "w"
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
tar_file.add(str(loc), arcname=str(path))
with tar_loc.open(mode="rb") as input_file:
with url.open(mode="wb") as output_file:
output_file.write(input_file.read())
upload_file(tar_loc, url)
return url
def pull(
@ -59,7 +59,7 @@ class RemoteStorage:
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["Pathy"]:
) -> Optional[Union[Path, "CloudPath"]]:
"""Retrieve a file from the remote cache. If the file already exists,
nothing is done.
@ -93,7 +93,7 @@ class RemoteStorage:
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["Pathy"]:
) -> Optional[Union[Path, "CloudPath"]]:
"""Find the best matching version of a file within the storage,
or `None` if no match can be found. If both the creation and content hash
are specified, only exact matches will be returned. Otherwise, the most
@ -106,12 +106,22 @@ class RemoteStorage:
elif command_hash is not None:
urls = list((self.url / name / command_hash).iterdir())
else:
urls = list((self.url / name).iterdir())
urls = []
for sub_dir in (self.url / name).iterdir():
urls.extend(sub_dir.iterdir())
if content_hash is not None:
urls = [url for url in urls if url.parts[-1] == content_hash]
if len(urls) > 1:
try:
urls.sort(key=lambda x: x.stat().st_mtime) # type: ignore
except Exception:
warnings.warn(
"Unable to sort remote files by last modified. The file(s) "
"pulled from the cache may not be the most recent."
)
return urls[-1] if urls else None
def make_url(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
def make_url(self, path: Path, command_hash: str, content_hash: str) -> Union[Path, "CloudPath"]:
"""Construct a URL from a subpath, a creation hash and a content hash."""
return self.url / self.encode_name(str(path)) / command_hash / content_hash

View File

@ -25,6 +25,7 @@ from spacy.cli.download import get_compatibility, get_version
from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
from spacy.cli.package import get_third_party_dependencies
from spacy.cli.package import _is_permitted_package_name
from spacy.cli.project.remote_storage import RemoteStorage
from spacy.cli.validate import get_model_pkgs
from spacy.lang.en import English
from spacy.lang.nl import Dutch
@ -855,3 +856,42 @@ def test_span_length_freq_dist_output_must_be_correct():
span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold)
assert sum(span_freqs.values()) >= threshold
assert list(span_freqs.keys()) == [3, 1, 4, 5, 2]
def test_local_remote_storage():
with make_tempdir() as d:
filename = "a.txt"
content = "a"
loc_file = d / "root" / filename
loc_file.parent.mkdir(parents=True)
with loc_file.open(mode="w") as file_:
file_.write(content)
# push to remote storage
remote = RemoteStorage(d / "root", str(d / "remote"))
remote.push(filename, "aaaa", "bbbb")
# retrieve with full hashes
loc_file.unlink()
remote.pull(filename, command_hash="aaaa", content_hash="bbbb")
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with command hash
loc_file.unlink()
remote.pull(filename, command_hash="aaaa")
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with content hash
loc_file.unlink()
remote.pull(filename, content_hash="bbbb")
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with no hashes
loc_file.unlink()
remote.pull(filename)
with loc_file.open(mode="r") as file_:
assert file_.read() == content