fix: cleaning up unn. type ignores

src/augmenty/character/casing.py

@@ -6,14 +6,16 @@
 from spacy.language import Language
 from spacy.training import Example
 
+from augmenty.util import Augmenter
+
 from ..augment_utilities import make_text_from_orth
 
 
 def random_casing_augmenter_v1(
     nlp: Language,
     example: Example,
     level: float,
-) -> Iterator[Example]:  # type: ignore
+) -> Iterator[Example]:
     def __casing(c):
         if random.random() < level:
             return c.lower() if random.random() < 0.5 else c.upper()
@@ -31,14 +33,14 @@ def __casing(c):
 @spacy.registry.augmenters("random_casing_v1")  # type: ignore
 def create_random_casing_augmenter_v1(
     level: float,
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Create an augment that randomly changes the casing of the document.
 
     Args:
-        level (float): The percentage of character that will have its casing changed.
+        level: The percentage of character that will have its casing changed.
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmenter.
+        The augmenter.
 
     Example:
         >>> import augmenty

src/augmenty/character/replace.py

@@ -7,8 +7,11 @@
 
 import spacy
 from spacy.language import Language
+from spacy.tokens import Token
 from spacy.training import Example
 
+from augmenty.util import Augmenter
+
 from ..augment_utilities import make_text_from_orth
 from ..keyboard import Keyboard
 
@@ -18,10 +21,10 @@ def char_replace_augmenter_v1(
     example: Example,
     level: float,
     replace: dict,
-) -> Iterator[Example]:  # type: ignore
-    def __replace(t):
+) -> Iterator[Example]:
+    def __replace(t: Token) -> str:
         t_ = []
-        for i, c in enumerate(t.text):
+        for c in t.text:
             if random.random() < level and c in replace:
                 c = random.choice(replace[c])
             t_.append(c)
@@ -38,19 +41,17 @@ def __replace(t):
 def create_char_random_augmenter_v1(
     level: float,
     keyboard: str = "en_qwerty_v1",
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Creates an augmenter that replaces a character with a random character
     from the keyboard.
 
     Args:
-        level (float): The probability to replace a character with a neightbouring
-            character.
-        keyboard (str, optional): A defined keyboard in the keyboard registry. To see a
-            list of all keyboard you can run `augmenty,keyboards()`. Defaults
+        level: The probability to replace a character with a neightbouring character.
+        keyboard: A defined keyboard in the keyboard registry. To see a list of all keyboard you can run `augmenty,keyboards()`. Defaults
             to "en_qwerty_v1".
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmenter function.
+        The augmenter.
 
     Example:
         >>> import augmenty
@@ -71,17 +72,17 @@ def create_char_random_augmenter_v1(
 def create_char_replace_augmenter_v1(
     level: float,
     replace: dict,
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Creates an augmenter that replaces a character with a random character
     from replace dict.
 
     Args:
-        level (float): probability to augment character, if document is augmented.
-        replace (dict): A dictionary denoting which characters denote potentials
+        level: probability to augment character, if document is augmented.
+        replace: A dictionary denoting which characters denote potentials
             replace for each character.
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmenter function.
+        The augmenter function.
 
     Example:
         >>> create_char_replace_augmenter_v1(level=0.02,
@@ -99,21 +100,18 @@ def create_keystroke_error_augmenter_v1(
     level: float,
     distance: float = 1.5,
     keyboard: str = "en_qwerty_v1",
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Creates a augmenter which augments a text with plausible typos based on
     keyboard distance.
 
     Args:
-        level (float): The probability to replace a character with a neightbouring
-            character.
-        distance (float, optional): keyboard distance. Defaults to 1.5 corresponding to
-            neighbouring keys including diagonals.
-        keyboard (str, optional): A defined keyboard in the keyboard registry. To see a
-            list of all keyboard you can run `augmenty,keyboards.get_all()`. Defaults
+        level: The probability to replace a character with a neightbouring character.
+        distance: keyboard distance. Defaults to 1.5 corresponding to neighbouring keys including diagonals.
+        keyboard: A defined keyboard in the keyboard registry. To see a list of all keyboard you can run `augmenty,keyboards.get_all()`. Defaults
             to "en_qwerty_v1".
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmentation function
+        The augmenter.
 
     Example:
         >>> import augmenty

src/augmenty/character/spacing.py

@@ -8,14 +8,16 @@
 from spacy.language import Language
 from spacy.training import Example
 
+from augmenty.util import Augmenter
+
 from ..augment_utilities import make_text_from_orth
 
 
 def remove_spacing_augmenter_v1(
     nlp: Language,
     example: Example,
     level: float,
-) -> Iterator[Example]:  # type: ignore
+) -> Iterator[Example]:
     def __replace(s):
         if random.random() < level and (s is True):
             return False
@@ -33,14 +35,14 @@ def __replace(s):
 @spacy.registry.augmenters("remove_spacing_v1")  # type: ignore
 def create_remove_spacing_augmenter_v1(
     level: float,
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Creates an augmenter that removes spacing with a given probability.
 
     Args:
-        level (float): The probability to remove a space.
+        level: The probability to remove a space.
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmenter.
+        The augmenter.
 
     Example:
         >>> import augmenty

src/augmenty/character/swap.py

@@ -9,10 +9,14 @@
 from spacy.language import Language
 from spacy.training import Example
 
+from augmenty.util import Augmenter
+
 from ..augment_utilities import make_text_from_orth
 
 
-def char_swap_augmenter_v1(nlp: Language, example: Example, level) -> Iterator[Example]:  # type: ignore
+def char_swap_augmenter_v1(
+    nlp: Language, example: Example, level: float
+) -> Iterator[Example]:
     def __replace(t):
         for i, c in enumerate(t.text[:-1]):
             if random.random() < level:
@@ -29,15 +33,15 @@ def __replace(t):
 @spacy.registry.augmenters("char_swap_v1")  # type: ignore
 def create_char_swap_augmenter_v1(
     level: float,
-) -> Callable[[Language, Example], Iterator[Example]]:  # type: ignore
+) -> Augmenter:
     """Creates an augmenter that swaps two neighbouring characters in a token
     with a given probability.
 
     Args:
-        level (float): probability to replace a character.
+        level: probability to replace a character.
 
     Returns:
-        Callable[[Language, Example], Iterator[Example]]: The augmenter.
+         The augmenter.
 
     Example:
         >>> import augmenty

src/augmenty/doc/subset.py

@@ -50,10 +50,26 @@ def paragraph_subset_augmenter_v1(
         start, end = start_n, end_n
 
     # Respect entity spans
-    while start != 0 and example.y[start].ent_iob_ not in {"O", "B", ""}:
+    start_is_in_entity = start != 0 and example.y[start].ent_iob_ not in {"O", "B", ""}
+    end_is_in_entity = end < doc_len - 1 and example.y[end].ent_iob_ not in {
+        "O",
+        "B",
+        "",
+    }
+    while start_is_in_entity:
         start -= 1
-    while end < doc_len - 1 and example.y[end - 1].ent_iob_ not in {"O", "B", ""}:
+        start_is_in_entity = start != 0 and example.y[start].ent_iob_ not in {
+            "O",
+            "B",
+            "",
+        }
+    while end_is_in_entity:
         end += 1
+        end_is_in_entity = end < doc_len - 1 and example.y[end].ent_iob_ not in {
+            "O",
+            "B",
+            "",
+        }
 
     for k in token_anno:
         token_anno[k] = token_anno[k][start:end]