Merge pull request #86 from KennethEnevoldsen/package_update

Added pre-config workflows

.github/workflows/documentation.yml

@@ -16,6 +16,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install -r requirements.txt
+        pip install -e .
         sudo apt-get install pandoc
     - name: Build and Commit
       uses: sphinx-notes/pages@master

.pre-commit-config.yaml

@@ -0,0 +1,31 @@
+default_stages: [commit, push]
+
+repos:
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile", "black", "--filter-files"]
+
+  - repo: https://github.com/asottile/add-trailing-comma
+    rev: v2.2.3
+    hooks:
+      - id: add-trailing-comma
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.34.0
+    hooks:
+      - id: pyupgrade
+
+  - repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python3.8
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 4.0.1
+    hooks:
+      - id: flake8
+        args: [--config, setup.cfg]

augmenty/__init__.py

@@ -1,57 +1,52 @@
-from .about import __version__, __download_url__, __title__  # noqa
-
-from .util import augmenters, docs, texts, keyboards, load, meta  # noqa
+from .about import __download_url__, __title__, __version__  # noqa
+from .augment_utilities import set_doc_level  # noqa
+from .augment_utilities import combine, repeat, yield_original  # noqa
 
 # import augmenters
+from .character import create_char_random_augmenter_v1  # noqa
+from .character import create_char_replace_augmenter_v1  # noqa
+from .character import create_char_swap_augmenter_v1  # noqa
 from .character import (  # noqa
-    create_char_replace_augmenter_v1,
-    create_char_swap_augmenter_v1,
-    create_char_random_augmenter_v1,
     create_keystroke_error_augmenter_v1,
     create_random_casing_augmenter_v1,
     create_remove_spacing_augmenter_v1,
 )
+from .doc import create_paragraph_subset_augmenter_v1  # noqa
+from .doc import create_spongebob_augmenter_v1  # noqa
+from .doc import create_upper_casing_augmenter_v1  # noqa
+from .lang import create_da_historical_noun_casing_augmenter_v1  # noqa
+from .lang import create_da_æøå_replace_augmenter_v1  # noqa
+from .lang import create_mk  # noqa
+from .lang import (  # noqa
+    create_qwerty_da,
+    create_qwerty_de,
+    create_qwerty_el,
+    create_qwerty_en,
+    create_qwerty_es,
+    create_qwerty_fr,
+    create_qwerty_it,
+    create_qwerty_lt,
+    create_qwerty_nb,
+    create_qwerty_nl,
+    create_qwerty_pl,
+    create_qwerty_pt,
+    create_qwerty_ro,
+    create_ru,
+)
+from .span import create_ent_augmenter_v1  # noqa
+from .span import create_ent_format_augmenter_v1  # noqa
+from .span import create_per_replace_augmenter_v1  # noqa
+from .token import create_conditional_token_casing_augmenter_v1  # noqa
+from .token import create_duplicate_token_augmenter_v1  # noqa
+from .token import create_letter_spacing_augmenter_v1  # noqa
 from .token import (  # noqa
-    create_conditional_token_casing_augmenter_v1,
-    create_token_swap_augmenter_v1,
+    create_random_synonym_insertion_augmenter_v1,
     create_spacing_insertion_augmenter_v1,
-    create_letter_spacing_augmenter_v1,
-    create_wordnet_synonym_augmenter_v1,
-    create_token_replace_augmenter_v1,
     create_starting_case_augmenter_v1,
-    create_token_insert_random_augmenter_v1,
     create_token_insert_augmenter_v1,
-    create_random_synonym_insertion_augmenter_v1,
-    create_duplicate_token_augmenter_v1,
-)
-from .span import (  # noqa
-    create_per_replace_augmenter_v1,
-    create_ent_format_augmenter_v1,
-    create_ent_augmenter_v1,
-)
-from .doc import (  # noqa
-    create_upper_casing_augmenter_v1,
-    create_spongebob_augmenter_v1,
-    create_paragraph_subset_augmenter_v1,
-)
-from .lang import (  # noqa
-    create_ru,
-    create_qwerty_ro,
-    create_qwerty_pt,
-    create_qwerty_pl,
-    create_qwerty_nl,
-    create_qwerty_nb,
-    create_mk,
-    create_qwerty_lt,
-    create_qwerty_it,
-    create_qwerty_fr,
-    create_qwerty_es,
-    create_qwerty_en,
-    create_qwerty_el,
-    create_qwerty_de,
-    create_da_historical_noun_casing_augmenter_v1,
-    create_da_æøå_replace_augmenter_v1,
-    create_qwerty_da,
+    create_token_insert_random_augmenter_v1,
+    create_token_replace_augmenter_v1,
+    create_token_swap_augmenter_v1,
+    create_wordnet_synonym_augmenter_v1,
 )
-
-from .augment_utilities import combine, set_doc_level, yield_original, repeat  # noqa
+from .util import augmenters, docs, keyboards, load, meta, texts  # noqa

augmenty/augment_utilities.py

@@ -2,15 +2,14 @@
 
 import random
 from functools import partial
-from typing import Callable, Iterable, Iterator, List
+from typing import Callable, Iterable, Iterator
 
 from spacy.language import Language
-from spacy.tokens import Doc
 from spacy.training import Example
 
 
 def combine(
-    augmenters: Iterable[Callable[[Language, Example], Iterator[Example]]]
+    augmenters: Iterable[Callable[[Language, Example], Iterator[Example]]],
 ) -> Callable[[Language, Example], Iterator[Example]]:
     """Combines a series of spaCy style augmenters.
 
@@ -84,7 +83,8 @@ def __augment(nlp: Language, example: Example):
 
 
 def yield_original(
-    augmenter: Callable[[Language, Example], Iterator[Example]], doc_level: float = 1.0
+    augmenter: Callable[[Language, Example], Iterator[Example]],
+    doc_level: float = 1.0,
 ) -> Callable[[Language, Example], Iterator[Example]]:
     """Wraps and augmented such that it yields both the original and augmented example.
 

augmenty/character/__init__.py

@@ -1,6 +1,6 @@
 from .casing import create_random_casing_augmenter_v1  # noqa
+from .replace import create_char_random_augmenter_v1  # noqa
 from .replace import (  # noqa
-    create_char_random_augmenter_v1,
     create_char_replace_augmenter_v1,
     create_keystroke_error_augmenter_v1,
 )

augmenty/character/casing.py

@@ -1,6 +1,6 @@
 import random
 from functools import partial
-from typing import Iterator, Callable
+from typing import Callable, Iterator
 
 import spacy
 from spacy.language import Language
@@ -34,7 +34,9 @@ def create_random_casing_augmenter_v1(
 
 
 def random_casing_augmenter_v1(
-    nlp: Language, example: Example, level: float
+    nlp: Language,
+    example: Example,
+    level: float,
 ) -> Iterator[Example]:
     def __casing(c):
         if random.random() < level:

augmenty/character/replace.py

@@ -50,7 +50,8 @@ def create_char_random_augmenter_v1(
 
 @spacy.registry.augmenters("char_replace.v1")
 def create_char_replace_augmenter_v1(
-    level: float, replace: dict
+    level: float,
+    replace: dict,
 ) -> Callable[[Language, Example], Iterator[Example]]:
     """Creates an augmenter that replaces a character with a random character from
     replace dict

augmenty/character/spacing.py

@@ -2,10 +2,9 @@
 Augmenters for modyfing spacing
 """
 
-from typing import Callable, Iterator
-
-from functools import partial
 import random
+from functools import partial
+from typing import Callable, Iterator
 
 import spacy
 from spacy.language import Language

augmenty/character/swap.py

@@ -3,10 +3,9 @@
 """
 
 
-from typing import Callable, Iterator
-
-from functools import partial
 import random
+from functools import partial
+from typing import Callable, Iterator
 
 import spacy
 from spacy.language import Language

augmenty/doc/__init__.py

@@ -1,5 +1,3 @@
-from .casing import (
-    create_spongebob_augmenter_v1,
-    create_upper_casing_augmenter_v1,
-)  # noqa
+from .casing import create_spongebob_augmenter_v1  # noqa
+from .casing import create_upper_casing_augmenter_v1  # noqa
 from .subset import create_paragraph_subset_augmenter_v1  # noqa

augmenty/doc/casing.py

@@ -1,6 +1,6 @@
 import random
 from functools import partial
-from typing import Iterator, Callable
+from typing import Callable, Iterator
 
 import spacy
 from spacy.language import Language

augmenty/doc/subset.py

@@ -1,12 +1,13 @@
 import random
 from functools import partial
-from typing import Iterator, Callable, Union
+from typing import Callable, Iterator, Union
 
+import numpy as np
 import spacy
 from spacy.language import Language
 from spacy.training import Example
+
 from augmenty.augment_utilities import make_text_from_orth
-import numpy as np
 
 
 @spacy.registry.augmenters("paragraph_subset_augmenter.v1")
@@ -42,7 +43,8 @@ def create_paragraph_subset_augmenter_v1(
         >>>   "It have tons of different augmenters. " +
         >>>   " Augmenty is developed using spaCy."
         >>> list(augmenty.texts([text], upper_case_augmenter, nlp))
-        ["Augmenty is a wonderful tool for augmentation. Augmenty is developed using spaCy."]
+        ["Augmenty is a wonderful tool for augmentation. Augmenty is developed using
+        spaCy."]
     """
     return partial(
         paragraph_subset_augmenter_v1,

augmenty/lang/__init__.py

@@ -1,9 +1,6 @@
 # import keyboard and augmenters
-from .da import (  # noqa
-    create_qwerty_da,
-    create_da_æøå_replace_augmenter_v1,
-    create_da_historical_noun_casing_augmenter_v1,
-)
+from .da import create_da_historical_noun_casing_augmenter_v1  # noqa
+from .da import create_da_æøå_replace_augmenter_v1, create_qwerty_da  # noqa
 from .de import create_qwerty_de  # noqa
 from .el import create_qwerty_el  # noqa
 from .en import create_qwerty_en  # noqa

augmenty/lang/da/__init__.py

@@ -1,6 +1,3 @@
-from .augmenters import (  # noqa
-    create_da_historical_noun_casing_augmenter_v1,
-    create_da_æøå_replace_augmenter_v1,
-)
-
+from .augmenters import create_da_historical_noun_casing_augmenter_v1  # noqa
+from .augmenters import create_da_æøå_replace_augmenter_v1  # noqa
 from .keyboard import create_qwerty_da  # noqa

augmenty/lang/da/augmenters.py

@@ -60,5 +60,7 @@ def conditional(token):
         return False
 
     return create_conditional_token_casing_augmenter_v1(
-        conditional=conditional, upper=True, level=level
+        conditional=conditional,
+        upper=True,
+        level=level,
     )

augmenty/span/__init__.py

@@ -1,5 +1,3 @@
-from .entities import (  # noqa
-    create_ent_augmenter_v1,
-    create_ent_format_augmenter_v1,
-    create_per_replace_augmenter_v1,
-)
+from .entities import create_ent_augmenter_v1  # noqa
+from .entities import create_ent_format_augmenter_v1  # noqa
+from .entities import create_per_replace_augmenter_v1  # noqa

augmenty/span/entities.py

@@ -1,13 +1,12 @@
 import random
 from functools import partial
-from typing import Callable, Dict, Iterable, Iterator, List, Optional, Union, Generator
+from typing import Callable, Dict, Generator, Iterable, Iterator, List, Optional, Union
 
 import numpy as np
-
 import spacy
 from spacy.language import Language
-from spacy.training import Example
 from spacy.tokens import Token
+from spacy.training import Example
 
 from ..augment_utilities import make_text_from_orth
 
@@ -111,10 +110,10 @@ def ent_augmenter_v1(
                         np.array(head[: ent.start + offset]),  # before
                         np.array(
                             [head[ent.root.i + offset]]
-                            + [ent.start + offset] * (len_ent - 1)
+                            + [ent.start + offset] * (len_ent - 1),
                         ),  # the entity
                         np.array(head[ent.end + offset :]),  # after
-                    ]
+                    ],
                 )
                 offset += offset_
 
@@ -142,7 +141,8 @@ def ent_augmenter_v1(
 @spacy.registry.augmenters("per_replace.v1")
 def create_per_replace_augmenter_v1(
     names: Dict[
-        str, List[str]
+        str,
+        List[str],
     ],  # {"firstname": ["Kenneth", "Lasse"], "lastname": ["Enevoldsen", "Hansen"]}
     patterns: List[List[str]],  # ["firstname", "firstname", "lastname"]
     level: float,

augmenty/tests/fixtures.py

@@ -1,12 +1,11 @@
 import pytest
-
 import spacy
-from spacy.training import Example
-
 from dacy.datasets import dane
+from spacy.training import Example
 
 from .books import BOOKS
 
+
 # pipelines
 @pytest.fixture()
 def nlp_en():

augmenty/tests/lang/test_da.py

@@ -1,12 +1,12 @@
-from augmenty.lang.da import create_da_æøå_replace_augmenter_v1
-from augmenty.lang.da import create_da_historical_noun_casing_augmenter_v1
-
-import augmenty
-
+import pytest
 from spacy.lang.da import Danish
 from spacy.tokens import Doc
 
-import pytest
+import augmenty
+from augmenty.lang.da import (
+    create_da_historical_noun_casing_augmenter_v1,
+    create_da_æøå_replace_augmenter_v1,
+)
 
 
 @pytest.fixture()