spaCy/spacy/cli/project/remote_storage.py

206 lines
8.0 KiB
Python
Raw Normal View History

from typing import Optional, List, Dict, TYPE_CHECKING
import os
import site
import hashlib
import urllib.parse
import tarfile
from pathlib import Path
from wasabi import msg
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
2020-10-05 18:51:15 +00:00
from ...git_info import GIT_VERSION
from ... import about
from ...errors import Errors
if TYPE_CHECKING:
from pathy import FluidPath # noqa: F401
class RemoteStorage:
"""Push and pull outputs to and from a remote file storage.
Remotes can be anything that `smart-open` can support: AWS, GCS, file system,
ssh, etc.
"""
def __init__(self, project_root: Path, url: str, *, compression="gz"):
self.root = project_root
self.url = ensure_pathy(url)
self.compression = compression
def push(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
"""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.
Within the remote storage, files are addressed by their project path
(url encoded) and two user-supplied hashes, representing their creation
context and their file contents. If the URL already exists, the data is
not uploaded. Paths are archived and compressed prior to upload.
"""
loc = self.root / path
if not loc.exists():
raise IOError(f"Cannot push {loc}: does not exist.")
url = self.make_url(path, command_hash, content_hash)
if url.exists():
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167) * 🚨 Ignore all existing Mypy errors * 🏗 Add Mypy check to CI * Add types-mock and types-requests as dev requirements * Add additional type ignore directives * Add types packages to dev-only list in reqs test * Add types-dataclasses for python 3.6 * Add ignore to pretrain * 🏷 Improve type annotation on `run_command` helper The `run_command` helper previously declared that it returned an `Optional[subprocess.CompletedProcess]`, but it isn't actually possible for the function to return `None`. These changes modify the type annotation of the `run_command` helper and remove all now-unnecessary `# type: ignore` directives. * 🔧 Allow variable type redefinition in limited contexts These changes modify how Mypy is configured to allow variables to have their type automatically redefined under certain conditions. The Mypy documentation contains the following example: ```python def process(items: List[str]) -> None: # 'items' has type List[str] items = [item.split() for item in items] # 'items' now has type List[List[str]] ... ``` This configuration change is especially helpful in reducing the number of `# type: ignore` directives needed to handle the common pattern of: * Accepting a filepath as a string * Overwriting the variable using `filepath = ensure_path(filepath)` These changes enable redefinition and remove all `# type: ignore` directives rendered redundant by this change. * 🏷 Add type annotation to converters mapping * 🚨 Fix Mypy error in convert CLI argument verification * 🏷 Improve type annotation on `resolve_dot_names` helper * 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors` * 🏷 Add type annotations for more `Vocab` attributes * 🏷 Add loose type annotation for gold data compilation * 🏷 Improve `_format_labels` type annotation * 🏷 Fix `get_lang_class` type annotation * 🏷 Loosen return type of `Language.evaluate` * 🏷 Don't accept `Scorer` in `handle_scores_per_type` * 🏷 Add `string_to_list` overloads * 🏷 Fix non-Optional command-line options * 🙈 Ignore redefinition of `wandb_logger` in `loggers.py` * ➕ Install `typing_extensions` in Python 3.8+ The `typing_extensions` package states that it should be used when "writing code that must be compatible with multiple Python versions". Since SpaCy needs to support multiple Python versions, it should be used when newer `typing` module members are required. One example of this is `Literal`, which is available starting with Python 3.8. Previously SpaCy tried to import `Literal` from `typing`, falling back to `typing_extensions` if the import failed. However, Mypy doesn't seem to be able to understand what `Literal` means when the initial import means. Therefore, these changes modify how `compat` imports `Literal` by always importing it from `typing_extensions`. These changes also modify how `typing_extensions` is installed, so that it is a requirement for all Python versions, including those greater than or equal to 3.8. * 🏷 Improve type annotation for `Language.pipe` These changes add a missing overload variant to the type signature of `Language.pipe`. Additionally, the type signature is enhanced to allow type checkers to differentiate between the two overload variants based on the `as_tuple` parameter. Fixes #8772 * ➖ Don't install `typing-extensions` in Python 3.8+ After more detailed analysis of how to implement Python version-specific type annotations using SpaCy, it has been determined that by branching on a comparison against `sys.version_info` can be statically analyzed by Mypy well enough to enable us to conditionally use `typing_extensions.Literal`. This means that we no longer need to install `typing_extensions` for Python versions greater than or equal to 3.8! 🎉 These changes revert previous changes installing `typing-extensions` regardless of Python version and modify how we import the `Literal` type to ensure that Mypy treats it properly. * resolve mypy errors for Strict pydantic types * refactor code to avoid missing return statement * fix types of convert CLI command * avoid list-set confustion in debug_data * fix typo and formatting * small fixes to avoid type ignores * fix types in profile CLI command and make it more efficient * type fixes in projects CLI * put one ignore back * type fixes for render * fix render types - the sequel * fix BaseDefault in language definitions * fix type of noun_chunks iterator - yields tuple instead of span * fix types in language-specific modules * 🏷 Expand accepted inputs of `get_string_id` `get_string_id` accepts either a string (in which case it returns its ID) or an ID (in which case it immediately returns the ID). These changes extend the type annotation of `get_string_id` to indicate that it can accept either strings or IDs. * 🏷 Handle override types in `combine_score_weights` The `combine_score_weights` function allows users to pass an `overrides` mapping to override data extracted from the `weights` argument. Since it allows `Optional` dictionary values, the return value may also include `Optional` dictionary values. These changes update the type annotations for `combine_score_weights` to reflect this fact. * 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer` * 🏷 Fix redefinition of `wandb_logger` These changes fix the redefinition of `wandb_logger` by giving a separate name to each `WandbLogger` version. For backwards-compatibility, `spacy.train` still exports `wandb_logger_v3` as `wandb_logger` for now. * more fixes for typing in language * type fixes in model definitions * 🏷 Annotate `_RandomWords.probs` as `NDArray` * 🏷 Annotate `tok2vec` layers to help Mypy * 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6 Also remove an import that I forgot to move to the top of the module 😅 * more fixes for matchers and other pipeline components * quick fix for entity linker * fixing types for spancat, textcat, etc * bugfix for tok2vec * type annotations for scorer * add runtime_checkable for Protocol * type and import fixes in tests * mypy fixes for training utilities * few fixes in util * fix import * 🐵 Remove unused `# type: ignore` directives * 🏷 Annotate `Language._components` * 🏷 Annotate `spacy.pipeline.Pipe` * add doc as property to span.pyi * small fixes and cleanup * explicit type annotations instead of via comment Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
return url
tmp: Path
with make_tempdir() as tmp:
tar_loc = tmp / self.encode_name(str(path))
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))
upload_file(tar_loc, url)
return url
def pull(
self,
path: Path,
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["FluidPath"]:
"""Retrieve a file from the remote cache. If the file already exists,
nothing is done.
If the command_hash and/or content_hash are specified, only matching
results are returned. If no results are available, an error is raised.
"""
dest = self.root / path
if dest.exists():
return None
url = self.find(path, command_hash=command_hash, content_hash=content_hash)
if url is None:
return url
else:
# Make sure the destination exists
if not dest.parent.exists():
dest.parent.mkdir(parents=True)
tmp: Path
with make_tempdir() as tmp:
tar_loc = tmp / url.parts[-1]
download_file(url, tar_loc)
mode_string = f"r:{self.compression}" if self.compression else "r"
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
# This requires that the path is added correctly, relative
# to root. This is how we set things up in push()
# Disallow paths outside the current directory for the tar
# file (CVE-2007-4559, directory traversal vulnerability)
def is_within_directory(directory, target):
abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)
prefix = os.path.commonprefix([abs_directory, abs_target])
return prefix == abs_directory
def safe_extract(tar, path):
for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise ValueError(Errors.E852)
tar.extractall(path)
safe_extract(tar_file, self.root)
return url
def find(
self,
path: Path,
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["FluidPath"]:
"""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
recent matching file is preferred.
"""
name = self.encode_name(str(path))
urls = []
if command_hash is not None and content_hash is not None:
url = self.url / name / command_hash / content_hash
urls = [url] if url.exists() else []
elif command_hash is not None:
if (self.url / name / command_hash).exists():
urls = list((self.url / name / command_hash).iterdir())
else:
if (self.url / name).exists():
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) >= 2:
try:
urls.sort(key=lambda x: x.stat().last_modified) # type: ignore
except Exception:
msg.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) -> "FluidPath":
"""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
def encode_name(self, name: str) -> str:
"""Encode a subpath into a URL-safe name."""
return urllib.parse.quote_plus(name)
def get_content_hash(loc: Path) -> str:
return get_checksum(loc)
def get_command_hash(
site_hash: str, env_hash: str, deps: List[Path], cmd: List[str]
) -> str:
"""Create a hash representing the execution of a command. This includes the
currently installed packages, whatever environment variables have been marked
as relevant, and the command.
"""
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167) * 🚨 Ignore all existing Mypy errors * 🏗 Add Mypy check to CI * Add types-mock and types-requests as dev requirements * Add additional type ignore directives * Add types packages to dev-only list in reqs test * Add types-dataclasses for python 3.6 * Add ignore to pretrain * 🏷 Improve type annotation on `run_command` helper The `run_command` helper previously declared that it returned an `Optional[subprocess.CompletedProcess]`, but it isn't actually possible for the function to return `None`. These changes modify the type annotation of the `run_command` helper and remove all now-unnecessary `# type: ignore` directives. * 🔧 Allow variable type redefinition in limited contexts These changes modify how Mypy is configured to allow variables to have their type automatically redefined under certain conditions. The Mypy documentation contains the following example: ```python def process(items: List[str]) -> None: # 'items' has type List[str] items = [item.split() for item in items] # 'items' now has type List[List[str]] ... ``` This configuration change is especially helpful in reducing the number of `# type: ignore` directives needed to handle the common pattern of: * Accepting a filepath as a string * Overwriting the variable using `filepath = ensure_path(filepath)` These changes enable redefinition and remove all `# type: ignore` directives rendered redundant by this change. * 🏷 Add type annotation to converters mapping * 🚨 Fix Mypy error in convert CLI argument verification * 🏷 Improve type annotation on `resolve_dot_names` helper * 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors` * 🏷 Add type annotations for more `Vocab` attributes * 🏷 Add loose type annotation for gold data compilation * 🏷 Improve `_format_labels` type annotation * 🏷 Fix `get_lang_class` type annotation * 🏷 Loosen return type of `Language.evaluate` * 🏷 Don't accept `Scorer` in `handle_scores_per_type` * 🏷 Add `string_to_list` overloads * 🏷 Fix non-Optional command-line options * 🙈 Ignore redefinition of `wandb_logger` in `loggers.py` * ➕ Install `typing_extensions` in Python 3.8+ The `typing_extensions` package states that it should be used when "writing code that must be compatible with multiple Python versions". Since SpaCy needs to support multiple Python versions, it should be used when newer `typing` module members are required. One example of this is `Literal`, which is available starting with Python 3.8. Previously SpaCy tried to import `Literal` from `typing`, falling back to `typing_extensions` if the import failed. However, Mypy doesn't seem to be able to understand what `Literal` means when the initial import means. Therefore, these changes modify how `compat` imports `Literal` by always importing it from `typing_extensions`. These changes also modify how `typing_extensions` is installed, so that it is a requirement for all Python versions, including those greater than or equal to 3.8. * 🏷 Improve type annotation for `Language.pipe` These changes add a missing overload variant to the type signature of `Language.pipe`. Additionally, the type signature is enhanced to allow type checkers to differentiate between the two overload variants based on the `as_tuple` parameter. Fixes #8772 * ➖ Don't install `typing-extensions` in Python 3.8+ After more detailed analysis of how to implement Python version-specific type annotations using SpaCy, it has been determined that by branching on a comparison against `sys.version_info` can be statically analyzed by Mypy well enough to enable us to conditionally use `typing_extensions.Literal`. This means that we no longer need to install `typing_extensions` for Python versions greater than or equal to 3.8! 🎉 These changes revert previous changes installing `typing-extensions` regardless of Python version and modify how we import the `Literal` type to ensure that Mypy treats it properly. * resolve mypy errors for Strict pydantic types * refactor code to avoid missing return statement * fix types of convert CLI command * avoid list-set confustion in debug_data * fix typo and formatting * small fixes to avoid type ignores * fix types in profile CLI command and make it more efficient * type fixes in projects CLI * put one ignore back * type fixes for render * fix render types - the sequel * fix BaseDefault in language definitions * fix type of noun_chunks iterator - yields tuple instead of span * fix types in language-specific modules * 🏷 Expand accepted inputs of `get_string_id` `get_string_id` accepts either a string (in which case it returns its ID) or an ID (in which case it immediately returns the ID). These changes extend the type annotation of `get_string_id` to indicate that it can accept either strings or IDs. * 🏷 Handle override types in `combine_score_weights` The `combine_score_weights` function allows users to pass an `overrides` mapping to override data extracted from the `weights` argument. Since it allows `Optional` dictionary values, the return value may also include `Optional` dictionary values. These changes update the type annotations for `combine_score_weights` to reflect this fact. * 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer` * 🏷 Fix redefinition of `wandb_logger` These changes fix the redefinition of `wandb_logger` by giving a separate name to each `WandbLogger` version. For backwards-compatibility, `spacy.train` still exports `wandb_logger_v3` as `wandb_logger` for now. * more fixes for typing in language * type fixes in model definitions * 🏷 Annotate `_RandomWords.probs` as `NDArray` * 🏷 Annotate `tok2vec` layers to help Mypy * 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6 Also remove an import that I forgot to move to the top of the module 😅 * more fixes for matchers and other pipeline components * quick fix for entity linker * fixing types for spancat, textcat, etc * bugfix for tok2vec * type annotations for scorer * add runtime_checkable for Protocol * type and import fixes in tests * mypy fixes for training utilities * few fixes in util * fix import * 🐵 Remove unused `# type: ignore` directives * 🏷 Annotate `Language._components` * 🏷 Annotate `spacy.pipeline.Pipe` * add doc as property to span.pyi * small fixes and cleanup * explicit type annotations instead of via comment Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
if check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION):
spacy_v = GIT_VERSION
else:
spacy_v = str(get_minor_version(about.__version__) or "")
dep_checksums = [get_checksum(dep) for dep in sorted(deps)]
hashes = [spacy_v, site_hash, env_hash] + dep_checksums
hashes.extend(cmd)
creation_bytes = "".join(hashes).encode("utf8")
return hashlib.md5(creation_bytes).hexdigest()
def get_site_hash():
"""Hash the current Python environment's site-packages contents, including
the name and version of the libraries. The list we're hashing is what
`pip freeze` would output.
"""
site_dirs = site.getsitepackages()
if site.ENABLE_USER_SITE:
site_dirs.extend(site.getusersitepackages())
packages = set()
for site_dir in site_dirs:
site_dir = Path(site_dir)
for subpath in site_dir.iterdir():
if subpath.parts[-1].endswith("dist-info"):
packages.add(subpath.parts[-1].replace(".dist-info", ""))
package_bytes = "".join(sorted(packages)).encode("utf8")
return hashlib.md5sum(package_bytes).hexdigest()
def get_env_hash(env: Dict[str, str]) -> str:
"""Construct a hash of the environment variables that will be passed into
the commands.
Values in the env dict may be references to the current os.environ, using
the syntax $ENV_VAR to mean os.environ[ENV_VAR]
"""
env_vars = {}
for key, value in env.items():
if value.startswith("$"):
env_vars[key] = os.environ.get(value[1:], "")
else:
env_vars[key] = value
return get_hash(env_vars)