o ante e nimi ilo :(

README.md

@@ -1,8 +1,8 @@
-# o toki pona
+# sona toki
 
-## What is __o toki pona__?
+## What is **sona toki**?
 
-This library, "Speak Toki Pona," helps you identify whether a message is in Toki Pona. No grammar checking, yet, which means this more checks whether a given message has enough Toki Pona words.
+This library, "Language Knowledge," helps you identify whether a message is in Toki Pona. No grammar checking, yet, which means this more checks whether a given message has enough Toki Pona words.
 
 I wrote it with a variety of scraps and lessons learned from a prior project, [ilo pi toki pona taso, "toki-pona-only tool"](https://github.com/gregdan3/ilo-pi-toki-pona-taso). That tool will be rewritten to use this library shortly.
 
@@ -16,24 +16,24 @@ Install with your preferred Python package manager. Example:
 
 ```sh
 pdm init  # if your pyproject.toml doesn't exist yet
-pdm add otokipona
+pdm add sonatoki
 ```
 
 Then get started with a script along these lines:
 
 ```py
-from otokipona.Filters import (
+from sonatoki.Filters import (
     Numerics,
     Syllabic,
     NimiLinku,
     Alphabetic,
     ProperName,
     Punctuations,
 )
-from otokipona.Scorers import Scaling
-from otokipona.Cleaners import ConsecutiveDuplicates
-from otokipona.Tokenizers import word_tokenize_tok
-from otokipona.Preprocessors import URLs, DiscordEmotes
+from sonatoki.Scorers import Scaling
+from sonatoki.Cleaners import ConsecutiveDuplicates
+from sonatoki.Tokenizers import word_tokenize_tok
+from sonatoki.Preprocessors import URLs, DiscordEmotes
 
 def main():
     ilo = Ilo(
@@ -67,4 +67,4 @@ The intent is to show our methodology to the Unicode Consortium, particularly to
 
 After our proposal has been examined and a result given by the committee, I will translate this file and library into Toki Pona, with a note left behind for those who do not understand it.
 
-### Why aren't any of the specific 
+### Why aren't any of the specific

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "otokipona"
+name = "sonatoki"
 version = "0.1.0"
 description = "ilo li moku e toki li pana e sona ni: ni li toki ala toki pona?"
 authors = [
@@ -76,9 +76,9 @@ src = ["src"]
 
 [tool.coverage.run]
 branch = true
-source = ["src/otokipona/"]
+source = ["src/sonatoki/"]
 omit = [
-    "src/otokipona/__main__.py"
+    "src/sonatoki/__main__.py"
 ]
 
 [tool.coverage.report]

src/otokipona/Filters.py → src/sonatoki/Filters.py

@@ -8,7 +8,7 @@
 from typing_extensions import override
 
 # LOCAL
-from otokipona.constants import (
+from sonatoki.constants import (
     VOWELS,
     CONSONANTS,
     NIMI_PU_SET,

src/otokipona/Scorers.py → src/sonatoki/Scorers.py

@@ -7,7 +7,7 @@
 from typing_extensions import override
 
 # LOCAL
-from otokipona.Filters import Filter
+from sonatoki.Filters import Filter
 
 Number = Union[int, float]
 Weights = Dict[str, Number]
@@ -83,6 +83,7 @@ def score(cls, tokens: List[str], filters: List[Type[Filter]]) -> Number:
             total_score += cls.score_token(token, filters, len_filters)
         return total_score / max_score if max_score else 0
 
+
 class SoftScaling(Scaling):
     """Shorter messages are subject to less harsh scoring
     by mapping the token count to [0.5, 1.0] via the sigmoid function,
@@ -92,7 +93,7 @@ class SoftScaling(Scaling):
 
     @staticmethod
     def sigmoid(n: int) -> Number:
-        return (1 / (1 + math.exp(-(0.30 * (n-1)) )))
+        return 1 / (1 + math.exp(-(0.30 * (n - 1))))
         # n-1 makes sigmoid(1) == 0.5
         # 0.30 softens scaling against input
         # return n / (1+abs(n))   # too weak in 0.7+
@@ -112,11 +113,10 @@ def score(cls, tokens: List[str], filters: List[Type[Filter]]) -> Number:
             total_score += cls.score_token(token, filters, len_filters)
 
         percentage = total_score / max_score if max_score else 0
-        percentage **= cls.sigmoid(len_tokens) 
+        percentage **= cls.sigmoid(len_tokens)
         return percentage
 
 
-
 class Logarithmic(Scorer): ...
 
 

src/otokipona/ilo.py → src/sonatoki/ilo.py

@@ -2,11 +2,11 @@
 from typing import List, Type
 
 # LOCAL
-from otokipona.Filters import Filter
-from otokipona.Scorers import Number, Scorer
-from otokipona.Cleaners import Cleaner
-from otokipona.Tokenizers import Tokenizer
-from otokipona.Preprocessors import Preprocessor
+from sonatoki.Filters import Filter
+from sonatoki.Scorers import Number, Scorer
+from sonatoki.Cleaners import Cleaner
+from sonatoki.Tokenizers import Tokenizer
+from sonatoki.Preprocessors import Preprocessor
 
 
 class Ilo:
@@ -98,5 +98,4 @@ def is_toki_pona(self, message: str) -> bool:
             print("Cleaned:   %s" % cleaned)
             print()
 
-
         return score >= self.__passing_score

tests/test_cleaners.py

@@ -5,7 +5,7 @@
 from hypothesis import assume, given, example, reproduce_failure
 
 # LOCAL
-from otokipona.Cleaners import ConsecutiveDuplicates
+from sonatoki.Cleaners import ConsecutiveDuplicates
 
 # FILESYSTEM
 from .test_utils import overlapping_pairs
@@ -16,7 +16,9 @@
 @example("muuuuuu")
 @example("nnn")
 @example("")
-@example("manna")  # syllabically valid, but not phonotactically valid; errantly matches phonotactic filter after this cleaner
+@example(
+    "manna"
+)  # syllabically valid, but not phonotactically valid; errantly matches phonotactic filter after this cleaner
 def test_ConsecutiveDuplicates(s: str):
     _ = assume("\n" not in s)
     res = ConsecutiveDuplicates.clean(s)

tests/test_filters.py

@@ -7,7 +7,7 @@
 from hypothesis import HealthCheck, given, assume, example, settings
 
 # LOCAL
-from otokipona.Filters import (
+from sonatoki.Filters import (
     NimiPu,
     Numerics,
     Syllabic,
@@ -17,8 +17,8 @@
     Phonotactic,
     Punctuations,
 )
-from otokipona.Cleaners import ConsecutiveDuplicates
-from otokipona.constants import NIMI_PU, NIMI_LINKU
+from sonatoki.Cleaners import ConsecutiveDuplicates
+from sonatoki.constants import NIMI_PU, NIMI_LINKU
 
 # FILESYSTEM
 from .test_utils import ALPHABETIC_RE, PROPER_NAME_RE

tests/test_ilo.py

@@ -1,17 +1,17 @@
 # LOCAL
-from otokipona.ilo import Ilo
-from otokipona.Filters import (
+from sonatoki.ilo import Ilo
+from sonatoki.Filters import (
     Numerics,
     Syllabic,
     NimiLinku,
     Alphabetic,
     ProperName,
     Punctuations,
 )
-from otokipona.Scorers import Scaling, SoftScaling
-from otokipona.Cleaners import ConsecutiveDuplicates
-from otokipona.Tokenizers import word_tokenize_tok
-from otokipona.Preprocessors import (
+from sonatoki.Scorers import Scaling, SoftScaling
+from sonatoki.Cleaners import ConsecutiveDuplicates
+from sonatoki.Tokenizers import word_tokenize_tok
+from sonatoki.Preprocessors import (
     URLs,
     DiscordEmotes,
     DiscordSpecial,
@@ -47,5 +47,7 @@ def test_constructor():
     assert ilo.is_toki_pona("ni li tptpt")
 
     assert not ilo.is_toki_pona("I'm Trying To Evade The Filter")
-    assert not ilo.is_toki_pona("""aaa i non-saw usa's most multiple element-set
-it's as asinine as in `e`-less speak""")
+    assert not ilo.is_toki_pona(
+        """aaa i non-saw usa's most multiple element-set
+it's as asinine as in `e`-less speak"""
+    )

tests/test_preprocessors.py

@@ -3,7 +3,7 @@
 from hypothesis import given, example
 
 # LOCAL
-from otokipona.Preprocessors import (
+from sonatoki.Preprocessors import (
     URLs,
     Spoilers,
     Backticks,

tests/test_scorers.py

@@ -7,7 +7,7 @@
 from hypothesis import given
 
 # LOCAL
-from otokipona.Filters import (
+from sonatoki.Filters import (
     Filter,
     NimiPu,
     Numerics,
@@ -18,7 +18,7 @@
     Phonotactic,
     Punctuations,
 )
-from otokipona.Scorers import Scorer, Scaling, PassFail, SoftScaling
+from sonatoki.Scorers import Scorer, Scaling, PassFail, SoftScaling
 
 # FILESYSTEM
 from .test_utils import token_strategy

tests/test_tokenize.py

@@ -6,7 +6,7 @@
 import pytest
 
 # LOCAL
-from otokipona.Tokenizers import (
+from sonatoki.Tokenizers import (
     sent_tokenize_re,
     word_tokenize_re,
     sent_tokenize_tok,
@@ -18,7 +18,7 @@
     import nltk
 
     # LOCAL
-    from otokipona.Tokenizers import sent_tokenize_nltk, word_tokenize_nltk
+    from sonatoki.Tokenizers import sent_tokenize_nltk, word_tokenize_nltk
 
 except ImportError as e:
     nltk = e

tests/test_utils.py

@@ -5,8 +5,8 @@
 import hypothesis.strategies as st
 
 # LOCAL
-from otokipona.Filters import Syllabic, Phonotactic
-from otokipona.constants import ALPHABET, NIMI_LINKU_ALE
+from sonatoki.Filters import Syllabic, Phonotactic
+from sonatoki.constants import ALPHABET, NIMI_LINKU_ALE
 
 PROPER_NAME_RE = r"[A-Z][a-z]*"
 ALPHABETIC_RE = rf"[{ALPHABET}{ALPHABET.upper()}]+"