Configure isort to use the Black profile, recursively isort the `spac…

…y` module (explosion#12721)

* Use isort with Black profile

* isort all the things

* Fix import cycles as a result of import sorting

* Add DOCBIN_ALL_ATTRS type definition

* Add isort to requirements

* Remove isort from build dependencies check

* Typo

pyproject.toml

@@ -9,3 +9,6 @@ requires = [
     "numpy>=1.15.0",
 ]
 build-backend = "setuptools.build_meta"
+
+[tool.isort]
+profile = "black"

requirements.txt

@@ -38,3 +38,4 @@ types-setuptools>=57.0.0
 types-requests
 types-setuptools>=57.0.0
 black==22.3.0
+isort>=5.0,<6.0

spacy/__init__.py

@@ -1,27 +1,24 @@
-from typing import Union, Iterable, Dict, Any
-from pathlib import Path
 import sys
+from pathlib import Path
+from typing import Any, Dict, Iterable, Union
 
 # set library-specific custom warning handling before doing anything else
 from .errors import setup_default_warnings
 
 setup_default_warnings()  # noqa: E402
 
 # These are imported as part of the API
-from thinc.api import prefer_gpu, require_gpu, require_cpu  # noqa: F401
-from thinc.api import Config
+from thinc.api import Config, prefer_gpu, require_cpu, require_gpu  # noqa: F401
 
 from . import pipeline  # noqa: F401
-from .cli.info import info  # noqa: F401
-from .glossary import explain  # noqa: F401
+from . import util
 from .about import __version__  # noqa: F401
-from .util import registry, logger  # noqa: F401
-
+from .cli.info import info  # noqa: F401
 from .errors import Errors
+from .glossary import explain  # noqa: F401
 from .language import Language
+from .util import logger, registry  # noqa: F401
 from .vocab import Vocab
-from . import util
-
 
 if sys.maxunicode == 65535:
     raise SystemError(Errors.E130)

spacy/attrs.pxd

@@ -1,6 +1,7 @@
 # Reserve 64 values for flag features
 from . cimport symbols
 
+
 cdef enum attr_id_t:
     NULL_ATTR
     IS_ALPHA

spacy/cli/__init__.py

@@ -1,35 +1,35 @@
 from wasabi import msg
 
 from ._util import app, setup_cli  # noqa: F401
+from .apply import apply  # noqa: F401
+from .assemble import assemble_cli  # noqa: F401
 
 # These are the actual functions, NOT the wrapped CLI commands. The CLI commands
 # are registered automatically and won't have to be imported here.
 from .benchmark_speed import benchmark_speed_cli  # noqa: F401
-from .download import download  # noqa: F401
-from .info import info  # noqa: F401
-from .package import package  # noqa: F401
-from .profile import profile  # noqa: F401
-from .train import train_cli  # noqa: F401
-from .assemble import assemble_cli  # noqa: F401
-from .pretrain import pretrain  # noqa: F401
-from .debug_data import debug_data  # noqa: F401
+from .convert import convert  # noqa: F401
 from .debug_config import debug_config  # noqa: F401
-from .debug_model import debug_model  # noqa: F401
+from .debug_data import debug_data  # noqa: F401
 from .debug_diff import debug_diff  # noqa: F401
+from .debug_model import debug_model  # noqa: F401
+from .download import download  # noqa: F401
 from .evaluate import evaluate  # noqa: F401
-from .apply import apply  # noqa: F401
-from .convert import convert  # noqa: F401
+from .find_threshold import find_threshold  # noqa: F401
+from .info import info  # noqa: F401
+from .init_config import fill_config, init_config  # noqa: F401
 from .init_pipeline import init_pipeline_cli  # noqa: F401
-from .init_config import init_config, fill_config  # noqa: F401
-from .validate import validate  # noqa: F401
-from .project.clone import project_clone  # noqa: F401
+from .package import package  # noqa: F401
+from .pretrain import pretrain  # noqa: F401
+from .profile import profile  # noqa: F401
 from .project.assets import project_assets  # noqa: F401
-from .project.run import project_run  # noqa: F401
+from .project.clone import project_clone  # noqa: F401
+from .project.document import project_document  # noqa: F401
 from .project.dvc import project_update_dvc  # noqa: F401
-from .project.push import project_push  # noqa: F401
 from .project.pull import project_pull  # noqa: F401
-from .project.document import project_document  # noqa: F401
-from .find_threshold import find_threshold  # noqa: F401
+from .project.push import project_push  # noqa: F401
+from .project.run import project_run  # noqa: F401
+from .train import train_cli  # noqa: F401
+from .validate import validate  # noqa: F401
 
 
 @app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

spacy/cli/_util.py

@@ -1,26 +1,44 @@
-from typing import Dict, Any, Union, List, Optional, Tuple, Iterable
-from typing import TYPE_CHECKING, overload
-import sys
+import hashlib
+import os
 import shutil
+import sys
+from configparser import InterpolationError
+from contextlib import contextmanager
 from pathlib import Path
-from wasabi import msg, Printer
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Optional,
+    Tuple,
+    Union,
+    overload,
+)
+
 import srsly
-import hashlib
 import typer
 from click import NoSuchOption
 from click.parser import split_arg_string
-from typer.main import get_command
-from contextlib import contextmanager
 from thinc.api import Config, ConfigValidationError, require_gpu
 from thinc.util import gpu_is_available
-from configparser import InterpolationError
-import os
+from typer.main import get_command
+from wasabi import Printer, msg
 
+from .. import about
 from ..compat import Literal
 from ..schemas import ProjectConfigSchema, validate
-from ..util import import_file, run_command, make_tempdir, registry, logger
-from ..util import is_compatible_version, SimpleFrozenDict, ENV_VARS
-from .. import about
+from ..util import (
+    ENV_VARS,
+    SimpleFrozenDict,
+    import_file,
+    is_compatible_version,
+    logger,
+    make_tempdir,
+    registry,
+    run_command,
+)
 
 if TYPE_CHECKING:
     from pathy import FluidPath  # noqa: F401

spacy/cli/apply.py

@@ -1,18 +1,15 @@
-import tqdm
-import srsly
-
 from itertools import chain
 from pathlib import Path
-from typing import Optional, List, Iterable, cast, Union
+from typing import Iterable, List, Optional, Union, cast
 
+import srsly
+import tqdm
 from wasabi import msg
 
-from ._util import app, Arg, Opt, setup_gpu, import_code, walk_directory
-
 from ..tokens import Doc, DocBin
-from ..vocab import Vocab
 from ..util import ensure_path, load_model
-
+from ..vocab import Vocab
+from ._util import Arg, Opt, app, import_code, setup_gpu, walk_directory
 
 path_help = """Location of the documents to predict on.
 Can be a single file in .spacy format or a .jsonl file.

spacy/cli/assemble.py

@@ -1,13 +1,20 @@
-from typing import Optional
+import logging
 from pathlib import Path
-from wasabi import msg
+from typing import Optional
+
 import typer
-import logging
+from wasabi import msg
 
-from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
-from ._util import import_code
 from .. import util
 from ..util import get_sourced_components, load_model_from_config
+from ._util import (
+    Arg,
+    Opt,
+    app,
+    import_code,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 
 @app.command(

spacy/cli/benchmark_speed.py

@@ -1,11 +1,12 @@
-from typing import Iterable, List, Optional
 import random
+import time
 from itertools import islice
-import numpy
 from pathlib import Path
-import time
-from tqdm import tqdm
+from typing import Iterable, List, Optional
+
+import numpy
 import typer
+from tqdm import tqdm
 from wasabi import msg
 
 from .. import util

spacy/cli/convert.py

@@ -1,18 +1,22 @@
-from typing import Callable, Iterable, Mapping, Optional, Any, Union
+import itertools
+import re
+import sys
 from enum import Enum
 from pathlib import Path
-from wasabi import Printer
+from typing import Any, Callable, Iterable, Mapping, Optional, Union
+
 import srsly
-import re
-import sys
-import itertools
+from wasabi import Printer
 
-from ._util import app, Arg, Opt, walk_directory
-from ..training import docs_to_json
 from ..tokens import Doc, DocBin
-from ..training.converters import iob_to_docs, conll_ner_to_docs, json_to_docs
-from ..training.converters import conllu_to_docs
-
+from ..training import docs_to_json
+from ..training.converters import (
+    conll_ner_to_docs,
+    conllu_to_docs,
+    iob_to_docs,
+    json_to_docs,
+)
+from ._util import Arg, Opt, app, walk_directory
 
 # Converters are matched by file extension except for ner/iob, which are
 # matched by file extension and content. To add a converter, add a new

spacy/cli/debug_config.py

@@ -1,15 +1,22 @@
-from typing import Optional, Dict, Any, Union, List
 from pathlib import Path
-from wasabi import msg, table
+from typing import Any, Dict, List, Optional, Union
+
+import typer
 from thinc.api import Config
 from thinc.config import VARIABLE_RE
-import typer
+from wasabi import msg, table
 
-from ._util import Arg, Opt, show_validation_error, parse_config_overrides
-from ._util import import_code, debug_cli
+from .. import util
 from ..schemas import ConfigSchemaInit, ConfigSchemaTraining
 from ..util import registry
-from .. import util
+from ._util import (
+    Arg,
+    Opt,
+    debug_cli,
+    import_code,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 
 @debug_cli.command(

spacy/cli/debug_data.py

@@ -1,31 +1,49 @@
-from typing import Any, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union
-from typing import cast, overload
-from pathlib import Path
-from collections import Counter
+import math
 import sys
+from collections import Counter
+from pathlib import Path
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Optional,
+    Sequence,
+    Set,
+    Tuple,
+    Union,
+    cast,
+    overload,
+)
+
+import numpy
 import srsly
-from wasabi import Printer, MESSAGES, msg
 import typer
-import math
-import numpy
+from wasabi import MESSAGES, Printer, msg
 
-from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides
-from ._util import import_code, debug_cli, _format_number
-from ..training import Example, remove_bilu_prefix
-from ..training.initialize import get_sourced_components
-from ..schemas import ConfigSchemaTraining
-from ..pipeline import TrainablePipe
+from .. import util
+from ..compat import Literal
+from ..language import Language
+from ..morphology import Morphology
+from ..pipeline import Morphologizer, SpanCategorizer, TrainablePipe
+from ..pipeline._edit_tree_internals.edit_trees import EditTrees
 from ..pipeline._parser_internals import nonproj
 from ..pipeline._parser_internals.nonproj import DELIMITER
-from ..pipeline import Morphologizer, SpanCategorizer
-from ..pipeline._edit_tree_internals.edit_trees import EditTrees
-from ..morphology import Morphology
-from ..language import Language
+from ..schemas import ConfigSchemaTraining
+from ..training import Example, remove_bilu_prefix
+from ..training.initialize import get_sourced_components
 from ..util import registry, resolve_dot_names
-from ..compat import Literal
 from ..vectors import Mode as VectorsMode
-from .. import util
-
+from ._util import (
+    Arg,
+    Opt,
+    _format_number,
+    app,
+    debug_cli,
+    import_code,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 # Minimum number of expected occurrences of NER label in data to train new label
 NEW_LABEL_THRESHOLD = 50

spacy/cli/debug_diff.py

@@ -1,13 +1,13 @@
+from pathlib import Path
 from typing import Optional
 
 import typer
-from wasabi import Printer, diff_strings, MarkdownRenderer
-from pathlib import Path
 from thinc.api import Config
+from wasabi import MarkdownRenderer, Printer, diff_strings
 
-from ._util import debug_cli, Arg, Opt, show_validation_error, parse_config_overrides
 from ..util import load_config
-from .init_config import init_config, Optimizations
+from ._util import Arg, Opt, debug_cli, parse_config_overrides, show_validation_error
+from .init_config import Optimizations, init_config
 
 
 @debug_cli.command(