Break apart codebase

src/imsosorry/uwuification/__init__.py

@@ -0,0 +1,7 @@
+"""UwU-ification of text."""
+
+from .uwuifier import uwuify
+
+__all__ = [
+    "uwuify",
+]

src/imsosorry/uwuification/constants.py

@@ -0,0 +1,69 @@
+"""Regex and map constants for uwuification."""
+
+import re
+
+REGEX_WORD_REPLACE = re.compile(r"(?<!w)[lr](?!w)")
+"""A regex that to detect certain characters to change to "w"s."""
+
+REGEX_PUNCTUATION = re.compile(r"[.!?\r\n\t]")
+"""A regex to detect certain punctuation characters to emotify /(^•ω•^)"""
+
+REGEX_TILDE = re.compile(r"(?![^ ])(?<!\B)")
+"""A regex to find places to add tildes (~) to."""
+
+REGEX_STUTTER = re.compile(r"(\s)([a-zA-Z])")
+"""A regex to find words to stutter."""
+
+REGEX_NYA = re.compile(r"n([aeou][^aeiou])")
+"""A regex to detect words with an n before a vowel to nyaify."""
+SUBSTITUTE_NYA = r"ny\1"
+"""A regex to to nyaify words."""
+
+WORD_REPLACE = {
+    "small": "smol",
+    "cute": "kawaii~",
+    "fluff": "floof",
+    "love": "luv",
+    "stupid": "baka",
+    "idiot": "baka",
+    "what": "nani",
+    "meow": "nya~",
+    "roar": "rawrr~",
+}
+"""A dict to match certain words for replacement words"""
+
+EMOJIS = [
+    "rawr x3",
+    "OwO",
+    "UwU",
+    "o.O",
+    "-.-",
+    ">w<",
+    "(⑅˘꒳˘)",
+    "(ꈍᴗꈍ)",
+    "(˘ω˘)",
+    "(U ᵕ U❁)",
+    "σωσ",
+    "òωó",
+    "(///ˬ///✿)",
+    "(U ﹏ U)",  # noqa: RUF001 - literally the point...
+    "( ͡o ω ͡o )",
+    "ʘwʘ",
+    ":3",
+    ":3",  # important enough to have twice
+    "XD",
+    "nyaa~~",
+    "mya",
+    ">_<",
+    "😳",
+    "🥺",
+    "😳😳😳",
+    "rawr",
+    "^^",
+    "^^;;",
+    "(ˆ ﻌ ˆ)♡",  # noqa: RUF001 - literally the point...
+    "^•ﻌ•^",
+    "/(^•ω•^)",
+    "(✿oωo)",
+]
+"""A list of emojis/emoticons to add."""

src/imsosorry/uwuification/replacers/__init__.py

@@ -0,0 +1 @@
+"""Replacers."""

src/imsosorry/uwuification/replacers/regex.py

@@ -0,0 +1,29 @@
+"""Regex replacers."""
+
+from __future__ import annotations
+
+import random
+from functools import partial
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    import re
+    from collections.abc import Callable
+
+
+def re_sub_maybe(
+    text: str,
+    pattern: re.Pattern[str],
+    text_getter: Callable[[str], str],
+    strength: float = 0.0,
+) -> str:
+    """Replace pattern in string randomly."""
+
+    def inner(match: re.Match[str], strength: float) -> str:
+        """Replace text randomly."""
+        match_string = match.group()
+        if random.random() < strength:
+            return text_getter(match_string)
+        return match_string
+
+    return pattern.sub(partial(inner, strength=strength), text)

src/imsosorry/uwuification/uwuifier.py

@@ -0,0 +1,107 @@
+"""Uwuification of text."""
+
+from __future__ import annotations
+
+import random
+from copy import copy
+from functools import partial
+
+from imsosorry.uwuification.replacers.regex import re_sub_maybe
+
+from .constants import (
+    EMOJIS,
+    REGEX_NYA,
+    REGEX_PUNCTUATION,
+    REGEX_STUTTER,
+    REGEX_TILDE,
+    REGEX_WORD_REPLACE,
+    SUBSTITUTE_NYA,
+    WORD_REPLACE,
+)
+
+
+def _stutter_string(text: str) -> str:
+    """Repeat the last character in a string."""
+    return f"{text}-{text[-1]}"
+
+
+def _emoji_string(_text: str) -> str:
+    """Return a random emoji."""
+    return f" {random.choice(EMOJIS)} "
+
+
+def _tildify_string(_text: str) -> str:
+    """Repeat the last character in a string."""
+    return "~"
+
+
+def word_replace(text: str) -> str:
+    """Replace words that are keys in the word replacement hash to the values specified."""
+    for word, replacement in WORD_REPLACE.items():
+        text = text.replace(word, replacement)
+    return text
+
+
+def nyaify(text: str) -> str:
+    """Nyaify a string by adding a 'y' between an 'n' and a vowel."""
+    return REGEX_NYA.sub(SUBSTITUTE_NYA, text)
+
+
+def char_replace(text: str) -> str:
+    """Replace certain characters with 'w'."""
+    return REGEX_WORD_REPLACE.sub("w", text)
+
+
+def stutter(text: str, strength: float) -> str:
+    """Add stuttering to a string."""
+    return re_sub_maybe(text=text, pattern=REGEX_STUTTER, text_getter=_stutter_string, strength=strength)
+
+
+def emoji(text: str, strength: float) -> str:
+    """Replace some punctuation with emoticons."""
+    return re_sub_maybe(text=text, pattern=REGEX_PUNCTUATION, text_getter=_emoji_string, strength=strength)
+
+
+def tildify(text: str, strength: float) -> str:
+    """Add some tildes to spaces."""
+    return re_sub_maybe(text=text, pattern=REGEX_TILDE, text_getter=_tildify_string, strength=strength)
+
+
+def uwuify(
+    text: str,
+    *,
+    stutter_strength: float = 0.2,
+    emoji_strength: float = 0.1,
+    tilde_strength: float = 0.1,
+    minimun_processable_length: int = 2,
+) -> str:
+    """Uwuify a string."""
+    contains_alpha = any(char.isalpha() for char in text)
+
+    if len(text) < minimun_processable_length and not contains_alpha:
+        return random.choice(EMOJIS)
+
+    text = text.lower()
+    original_text = copy(text)
+
+    transforms = [
+        word_replace,
+        nyaify,
+        char_replace,
+        stutter,
+        partial(stutter, strength=stutter_strength),
+        partial(emoji, strength=emoji_strength),
+        partial(tildify, strength=tilde_strength),
+    ]
+    for transform in transforms:
+        text = transform(text)  # type: ignore[operator]
+
+    if text == original_text and contains_alpha:
+        return uwuify(
+            text,
+            stutter_strength=stutter_strength + 0.225,
+            emoji_strength=emoji_strength + 0.075,
+            tilde_strength=tilde_strength + 0.175,
+        )
+
+    return text