Make stable private modules public and adjust names (#11353)

* Make stable private modules public and adjust names

* `spacy.ml._character_embed` -> `spacy.ml.character_embed`
* `spacy.ml._precomputable_affine` -> `spacy.ml.precomputable_affine`
* `spacy.tokens._serialize` -> `spacy.tokens.doc_bin`
* `spacy.tokens._retokenize` -> `spacy.tokens.retokenize`
* `spacy.tokens._dict_proxies` -> `spacy.tokens.span_groups`

* Skip _precomputable_affine

* retokenize -> retokenizer

* Fix imports

setup.py

@@ -60,7 +60,7 @@ MOD_NAMES = [
     "spacy.tokens.span_group",
     "spacy.tokens.graph",
     "spacy.tokens.morphanalysis",
-    "spacy.tokens._retokenize",
+    "spacy.tokens.retokenizer",
     "spacy.matcher.matcher",
     "spacy.matcher.phrasematcher",
     "spacy.matcher.dependencymatcher",

spacy/ml/models/tok2vec.py

@@ -7,7 +7,7 @@ from thinc.api import expand_window, residual, Maxout, Mish, PyTorchLSTM
 from ...tokens import Doc
 from ...util import registry
 from ...errors import Errors
-from ...ml import _character_embed
+from ...ml import character_embed
 from ..staticvectors import StaticVectors
 from ..featureextractor import FeatureExtractor
 from ...pipeline.tok2vec import Tok2VecListener
@@ -226,7 +226,7 @@ def CharacterEmbed(
     if feature is None:
         raise ValueError(Errors.E911.format(feat=feature))
     char_embed = chain(
-        _character_embed.CharacterEmbed(nM=nM, nC=nC),
+        character_embed.CharacterEmbed(nM=nM, nC=nC),
         cast(Model[List[Floats2d], Ragged], list2ragged()),
     )
     feature_extractor: Model[List[Doc], Ragged] = chain(

spacy/pipeline/attribute_ruler.py

@@ -11,7 +11,7 @@ from ..matcher import Matcher
 from ..scorer import Scorer
 from ..symbols import IDS
 from ..tokens import Doc, Span
-from ..tokens._retokenize import normalize_token_attrs, set_token_attrs
+from ..tokens.retokenizer import normalize_token_attrs, set_token_attrs
 from ..vocab import Vocab
 from ..util import SimpleFrozenList, registry
 from .. import util

spacy/tests/pipeline/test_models.py

@@ -9,7 +9,7 @@ from thinc.types import Array2d, Ragged
 
 from spacy.lang.en import English
 from spacy.ml import FeatureExtractor, StaticVectors
-from spacy.ml._character_embed import CharacterEmbed
+from spacy.ml.character_embed import CharacterEmbed
 from spacy.tokens import Doc
 
 

spacy/tests/pipeline/test_spancat.py

@@ -7,7 +7,7 @@ from spacy import util
 from spacy.lang.en import English
 from spacy.language import Language
 from spacy.tokens import SpanGroup
-from spacy.tokens._dict_proxies import SpanGroups
+from spacy.tokens.span_groups import SpanGroups
 from spacy.training import Example
 from spacy.util import fix_random_seed, registry, make_tempdir
 

spacy/tests/serialize/test_serialize_span_groups.py

@@ -1,7 +1,7 @@
 import pytest
 
 from spacy.tokens import Span, SpanGroup
-from spacy.tokens._dict_proxies import SpanGroups
+from spacy.tokens.span_groups import SpanGroups
 
 
 @pytest.mark.issue(10685)

spacy/tokens/__init__.py

@@ -2,7 +2,7 @@ from .doc import Doc
 from .token import Token
 from .span import Span
 from .span_group import SpanGroup
-from ._serialize import DocBin
+from .doc_bin import DocBin
 from .morphanalysis import MorphAnalysis
 
 __all__ = ["Doc", "Token", "Span", "SpanGroup", "DocBin", "MorphAnalysis"]

spacy/tokens/doc.pyi

@@ -4,8 +4,8 @@ from cymem.cymem import Pool
 from thinc.types import Floats1d, Floats2d, Ints2d
 from .span import Span
 from .token import Token
-from ._dict_proxies import SpanGroups
+from .span_groups import SpanGroups
-from ._retokenize import Retokenizer
+from .retokenizer import Retokenizer
 from ..lexeme import Lexeme
 from ..vocab import Vocab
 from .underscore import Underscore

spacy/tokens/doc.pyx

@@ -19,7 +19,7 @@ import warnings
 
 from .span cimport Span
 from .token cimport MISSING_DEP
-from ._dict_proxies import SpanGroups
+from .span_groups import SpanGroups
 from .token cimport Token
 from ..lexeme cimport Lexeme, EMPTY_LEXEME
 from ..typedefs cimport attr_t, flags_t
@@ -35,8 +35,8 @@ from .. import util
 from .. import parts_of_speech
 from .. import schemas
 from .underscore import Underscore, get_ext_args
-from ._retokenize import Retokenizer
+from .retokenizer import Retokenizer
-from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
+from .doc_bin import ALL_ATTRS as DOCBIN_ALL_ATTRS
 from ..util import get_words_and_spaces
 
 DEF PADDING = 5

spacy/tokens/doc_bin.py

@@ -12,7 +12,7 @@ from ..compat import copy_reg
 from ..attrs import SPACY, ORTH, intify_attr, IDS
 from ..errors import Errors
 from ..util import ensure_path, SimpleFrozenList
-from ._dict_proxies import SpanGroups
+from .span_groups import SpanGroups
 
 # fmt: off
 ALL_ATTRS = ("ORTH", "NORM", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "ENT_KB_ID", "ENT_ID", "LEMMA", "MORPH", "POS", "SENT_START")