sonatoki 0.2.2__py3-none-any.whl → 0.3.1__py3-none-any.whl

sonatoki/Cleaners.py

@@ -60,6 +60,13 @@ class ConsecutiveDuplicatesRe(RegexCleaner):
     replace = r"\1"
 
 
+class Lowercase(Cleaner):
+    @classmethod
+    @override
+    def clean(cls, token: str) -> str:
+        return token.lower()
+
+
 __all__ = [
     "ConsecutiveDuplicates",
 ]

sonatoki/Configs.py

@@ -2,33 +2,39 @@
 from copy import deepcopy
 from typing import List, Type, TypedDict
 
-# PDM
-from typing_extensions import NotRequired
-
 # LOCAL
 from sonatoki.Filters import (
     Filter,
     NimiPu,
     Numeric,
+    OrFilter,
     Syllabic,
-    NimiLinku,
-    NimiPuAle,
+    NimiUCSUR,
     Alphabetic,
     ProperName,
     Phonotactic,
     Punctuation,
-    NimiLinkuAle,
+    NimiLinkuCore,
+    NimiPuSynonyms,
+    OrMemberFilter,
+    NimiLinkuCommon,
+    NimiLinkuObscure,
+    NimiLinkuSandbox,
+    EnglishIgnorables,
+    NimiLinkuUncommon,
 )
 from sonatoki.Scorers import Number, Scorer, PassFail, SoftScaling, SoftPassFail
 from sonatoki.Cleaners import Cleaner, ConsecutiveDuplicates
 from sonatoki.Tokenizers import Tokenizer, WordTokenizer
 from sonatoki.Preprocessors import (
     URLs,
+    Reference,
     Preprocessor,
     DiscordEmotes,
     DiscordSpecial,
     DiscordChannels,
     DiscordMentions,
+    AngleBracketObject,
 )
 
 
@@ -42,6 +48,8 @@ class IloConfig(TypedDict):
     passing_score: Number
 
 
+# TODO: branching configs?
+
 BaseConfig: IloConfig = {
     "preprocessors": [URLs],
     "cleaners": [ConsecutiveDuplicates],
@@ -53,24 +61,75 @@ BaseConfig: IloConfig = {
 }
 
 
-PrefConfig: IloConfig = deepcopy(BaseConfig)
-PrefConfig["scoring_filters"].extend([NimiLinku, Syllabic, ProperName, Alphabetic])
-PrefConfig["scorer"] = SoftScaling
+PrefConfig: IloConfig = {
+    "preprocessors": [URLs, Reference],
+    "cleaners": [ConsecutiveDuplicates],
+    "ignoring_filters": [Numeric, Punctuation, EnglishIgnorables],
+    "scoring_filters": [
+        OrMemberFilter(NimiLinkuCore, NimiLinkuCommon, NimiUCSUR),
+        Syllabic,
+        ProperName,
+        Alphabetic,
+    ],
+    "scorer": SoftScaling,
+    "passing_score": 0.8,
+    "word_tokenizer": WordTokenizer,
+}
 
+CorpusConfig: IloConfig = {
+    "preprocessors": [URLs, AngleBracketObject, Reference],
+    "cleaners": [ConsecutiveDuplicates],
+    "ignoring_filters": [Numeric, Punctuation, EnglishIgnorables],
+    "scoring_filters": [
+        OrMemberFilter(
+            NimiLinkuCore,
+            NimiLinkuCommon,
+            NimiLinkuUncommon,
+            NimiLinkuObscure,
+            NimiLinkuSandbox,
+            NimiUCSUR,
+        ),
+        Syllabic,
+        ProperName,
+        Alphabetic,
+    ],
+    "scorer": SoftScaling,
+    "passing_score": 0.8,
+    "word_tokenizer": WordTokenizer,
+}
 
-LazyConfig: IloConfig = deepcopy(BaseConfig)
-LazyConfig["scoring_filters"].extend([Alphabetic, ProperName])
-LazyConfig["scorer"] = SoftPassFail
 
-DiscordConfig: IloConfig = deepcopy(PrefConfig)
-DiscordConfig["preprocessors"].extend(
-    [DiscordEmotes, DiscordMentions, DiscordChannels, DiscordSpecial]
-)
+LazyConfig: IloConfig = {
+    "preprocessors": [URLs],
+    "cleaners": [ConsecutiveDuplicates],
+    "ignoring_filters": [Numeric, Punctuation],
+    "scoring_filters": [Alphabetic, NimiUCSUR, ProperName],
+    "scorer": SoftPassFail,
+    "passing_score": 0.8,
+    "word_tokenizer": WordTokenizer,
+}
+
+DiscordConfig: IloConfig = {
+    "preprocessors": [URLs, AngleBracketObject, Reference],
+    "cleaners": [ConsecutiveDuplicates],
+    "ignoring_filters": [Numeric, Punctuation, EnglishIgnorables],
+    "scoring_filters": [
+        OrMemberFilter(NimiLinkuCore, NimiLinkuCommon, NimiUCSUR),
+        Syllabic,
+        ProperName,
+        Alphabetic,
+    ],
+    "scorer": SoftScaling,
+    "passing_score": 0.8,
+    "word_tokenizer": WordTokenizer,
+}
+
 TelegramConfig: IloConfig = deepcopy(PrefConfig)
 ForumConfig: IloConfig = deepcopy(PrefConfig)
 
 __all__ = [
     "BaseConfig",
+    "CorpusConfig",
     "DiscordConfig",
     "ForumConfig",
     "IloConfig",

sonatoki/Filters.py

@@ -1,7 +1,7 @@
 # STL
 import re
 from abc import ABC, abstractmethod
-from typing import Set
+from typing import Set, List, Type
 from functools import lru_cache as cache  # cache comes in 3.9
 
 # PDM
@@ -9,19 +9,26 @@ import regex
 from typing_extensions import override
 
 # LOCAL
+from sonatoki.utils import prep_dictionary
 from sonatoki.constants import (
     VOWELS,
     NIMI_PU,
     ALPHABET,
+    ALL_PUNCT,
     ALLOWABLES,
     CONSONANTS,
-    NIMI_LINKU,
-    POSIX_PUNCT,
-    UNICODE_PUNCT,
-    NIMI_LINKU_LILI,
+    IGNORABLES,
+    NIMI_UCSUR,
+    NIMI_KU_LILI,
+    NIMI_KU_SULI,
+    NIMI_LINKU_CORE,
     ALL_PUNCT_RANGES,
     NIMI_PU_SYNONYMS,
+    NIMI_LINKU_COMMON,
+    NIMI_LINKU_OBSCURE,
     NIMI_LINKU_SANDBOX,
+    UCSUR_PUNCT_RANGES,
+    NIMI_LINKU_UNCOMMON,
 )
 
 regex.DEFAULT_VERSION = regex.VERSION1
@@ -79,6 +86,10 @@ class Miscellaneous(MemberFilter):
     tokens = set(ALLOWABLES)
 
 
+class EnglishIgnorables(MemberFilter):
+    tokens = set(IGNORABLES)
+
+
 class ProperName(Filter):
     """Determines if a given token is a valid name (also called a loan word).
     When Toki Pona is written with the Latin alphabet, names are generally
@@ -99,23 +110,43 @@ class ProperName(Filter):
 
 
 class NimiPu(MemberFilter):
-    tokens = set(NIMI_PU)
+    tokens = prep_dictionary(NIMI_PU)
+
+
+class NimiPuSynonyms(MemberFilter):
+    tokens = prep_dictionary(NIMI_PU_SYNONYMS)
+
+
+class NimiKuSuli(MemberFilter):
+    tokens = prep_dictionary(NIMI_KU_SULI)
+
+
+class NimiKuLili(MemberFilter):
+    tokens = prep_dictionary(NIMI_KU_LILI)
+
+
+class NimiLinkuCore(MemberFilter):
+    tokens = prep_dictionary(NIMI_LINKU_CORE)
 
 
-class NimiPuAle(MemberFilter):
-    tokens = set(NIMI_PU + NIMI_PU_SYNONYMS)
+class NimiLinkuCommon(MemberFilter):
+    tokens = prep_dictionary(NIMI_LINKU_COMMON)
 
 
-class NimiLinku(MemberFilter):
-    tokens = set(NIMI_LINKU)
+class NimiLinkuUncommon(MemberFilter):
+    tokens = prep_dictionary(NIMI_LINKU_UNCOMMON)
 
 
-class NimiLinkuAle(MemberFilter):
-    tokens = set(NIMI_LINKU + NIMI_LINKU_LILI)
+class NimiLinkuObscure(MemberFilter):
+    tokens = prep_dictionary(NIMI_LINKU_OBSCURE)
 
 
 class NimiLinkuSandbox(MemberFilter):
-    tokens = set(NIMI_LINKU + NIMI_LINKU_LILI + NIMI_LINKU_SANDBOX)
+    tokens = prep_dictionary(NIMI_LINKU_SANDBOX)
+
+
+class NimiUCSUR(MemberFilter):
+    tokens = prep_dictionary(NIMI_UCSUR)
 
 
 class Phonotactic(RegexFilter):
@@ -156,6 +187,11 @@ class AlphabeticRe(RegexFilter):
     pattern = re.compile(rf"[{ALPHABET}]+", flags=re.IGNORECASE)
 
 
+class TwoOrMoreAlphabetic(Filter):
+    # TODO: alphabetic implementation that ignores single characters
+    pass
+
+
 class Numeric(Filter):
     """Determine if a given token is entirely numeric.
     Covers all numeric symbols in Unicode.
@@ -175,12 +211,13 @@ class Numeric(Filter):
 class Punctuation(SubsetFilter):
     """Identify whether a token is entirely punctuation. Fastest implementation."""
 
-    tokens = set(POSIX_PUNCT + UNICODE_PUNCT)
+    tokens = set(ALL_PUNCT)
 
 
 class PunctuationRe(RegexFilter):
     """Faster implementation of `PunctuationRe1`.
-    Goes out of date compared to the `regex` library if UNICODE_PUNCT is not updated."""
+    Goes out of date compared to the `regex` library if UNICODE_PUNCT_RANGES is not updated.
+    """
 
     pattern = re.compile(rf"[{ALL_PUNCT_RANGES}]+")
 
@@ -188,17 +225,111 @@ class PunctuationRe(RegexFilter):
 class PunctuationRe1(Regex1Filter):
     """Reference implementation for identifying tokens made entirely of punctuation."""
 
-    pattern = regex.compile(r"[\p{Punctuation}\p{posix_punct}]+")
+    pattern = regex.compile(
+        rf"[\p{{Punctuation}}\p{{posix_punct}}{UCSUR_PUNCT_RANGES}]+"
+    )
+
+
+class OrFilter:
+    """Instantiate with more than one filter to compose them into one filter,
+    returning True when any individual filter matches or False otherwise.
+    Requires at least two filters.
+
+    OrFilter exists as a compromise between the need to score some filters equally,
+    while not adding custom behavior to scorers.
+    I could have allowed a position to have a list of filters instead of one filter,
+    but this would require cleaning the user's input, and nested handling of lists.
+    It also would not have been as powerful- I would need another param for the and/or switch,
+    or to not give users the choice.
+
+    Instead, the user is responsible for building an OrFilter out of their desired filters.
+    """
+
+    @staticmethod
+    def __generic_filter(*filters_: Type[Filter]) -> Type[Filter]:
+
+        class CombinedFilter(Filter):
+            filters: List[Type[Filter]] = list(filters_)  # TODO: tuple better?
+
+            @classmethod
+            @override
+            @cache(maxsize=None)
+            def filter(cls, token: str) -> bool:
+                for f in cls.filters:
+                    if f.filter(token):
+                        return True
+                return False
+
+        return CombinedFilter
+
+    def __new__(cls, *filters: Type[Filter]) -> Type[Filter]:
+        if not len(filters) >= 2:
+            raise ValueError("Provide at least two Filters to OrFilter.")
+
+        subset_filters = [f for f in filters if issubclass(f, MemberFilter)]
+        if len(subset_filters) >= 2:
+            raise Warning(
+                "Prefer OrMemberFilter for combining two or more MemberFilters."
+            )
+
+        filter = cls.__generic_filter(*filters)
+
+        return filter
+
+
+class OrMemberFilter:
+    @staticmethod
+    def __subset_filter(*filters: Type[MemberFilter]) -> Type[MemberFilter]:
+        all_token_sets: List[Set[str]] = [f.tokens for f in filters]
+        all_tokens: Set[str] = set().union(*all_token_sets)
+
+        class CombinedFilter(MemberFilter):
+            tokens = all_tokens
+
+        return CombinedFilter
+
+    def __new__(cls, *filters_: Type[MemberFilter]) -> Type[MemberFilter]:
+        if not len(filters_) >= 2:
+            raise ValueError("Provide two or more MemberFilters to OrMemberFilter.")
+        filter = cls.__subset_filter(*filters_)
+        return filter
+
+
+class AndFilter(Filter):
+    """Instantiate with more than one filter to compose them into one filter,
+    returning False when any individual filter fails to match or True otherwise.
+    Requires at least two filters."""
+
+    def __new__(cls, *filters_: Type[Filter]) -> Type[Filter]:
+        if not len(filters_) >= 2:
+            raise ValueError("Must provide at least two Filters to AndFilter.")
+
+        class AnonymousAndFilter(Filter):
+            filters: List[Type[Filter]] = list(filters_)  # TODO: tuple better?
+
+            @classmethod
+            @override
+            @cache(maxsize=None)
+            def filter(cls, token: str) -> bool:
+                for f in cls.filters:
+                    if not f.filter(token):
+                        return False
+                return True
+
+        return AnonymousAndFilter
 
 
 __all__ = [
     "Alphabetic",
-    "NimiLinku",
-    "NimiLinkuAle",
+    "AndFilter",
+    "EnglishIgnorables",
+    "NimiLinkuCore",
     "NimiLinkuSandbox",
     "NimiPu",
-    "NimiPuAle",
+    "NimiPuSynonyms",
+    "NimiUCSUR",
     "Numeric",
+    "OrFilter",
     "Phonotactic",
     "ProperName",
     "Punctuation",

sonatoki/Tokenizers.py

@@ -5,16 +5,12 @@ from typing import Set, List
 
 # PDM
 import regex
-from typing_extensions import override
+from typing_extensions import override, deprecated
 
 # LOCAL
 from sonatoki.utils import regex_escape
-from sonatoki.constants import (
-    POSIX_PUNCT,
-    UNICODE_PUNCT,
-    SENTENCE_PUNCT,
-    ALL_PUNCT_RANGES,
-)
+from sonatoki.Filters import NimiUCSUR  # seriously this sucks
+from sonatoki.constants import ALL_PUNCT, SENTENCE_PUNCT, ALL_PUNCT_RANGES
 
 regex.DEFAULT_VERSION = regex.VERSION1
 
@@ -50,7 +46,12 @@ class Regex1Tokenizer(Tokenizer):
 
 
 class WordTokenizer(SetTokenizer):
-    delimiters = set(POSIX_PUNCT + UNICODE_PUNCT)
+    delimiters = set(ALL_PUNCT)
+
+    @classmethod
+    def __helper(cls, s: str, tokens: List[str], last_match: int, i: int):
+        match = s[last_match:i].split()
+        [tokens.append(t) for t in match if t]
 
     @classmethod
     @override
@@ -60,32 +61,47 @@ class WordTokenizer(SetTokenizer):
 
         tokens: List[str] = []
 
+        i = 0  # ensure i is bound
         last_match = 0
         last_membership = s[0] in cls.delimiters
         for i, char in enumerate(s):
             mem = char in cls.delimiters
-            if mem == last_membership:
+            ucsur = NimiUCSUR.filter(char)  # always "changed" means
+            changed = (mem != last_membership) or ucsur
+            # this keeps contiguous words together, but splits UCSUR
+            if not changed:
+                continue
+
+            if ucsur:
+                if i > last_match:
+                    # Add the token before UCSUR character
+                    cls.__helper(s, tokens, last_match, i)
+                # Add UCSUR character itself as a token
+                tokens.append(char)
+                last_match = i + 1
+                last_membership = mem
                 continue
 
-            match = s[last_match:i].split()
-            # TODO: kinda sucks? what about unicode whitespace?
+            cls.__helper(s, tokens, last_match, i)
             last_match = i
             last_membership = mem
-            [tokens.append(t) for t in match if t]
-
-        match = s[last_match:].strip().split()
-        if match:
-            tokens.extend(match)
 
+        cls.__helper(s, tokens, last_match, i + 1)
         return tokens
 
 
+@deprecated(
+    "WordTokenizerRe is a previous reference implementation. Its behavior has diverged from WordTokenizer and it may not be restored."
+)
 class WordTokenizerRe(RegexTokenizer):
     pattern = re.compile(rf"""([{ALL_PUNCT_RANGES}]+|\s+)""")
 
 
+@deprecated(
+    "WordTokenizerRe1 is a previous reference implementation. Its behavior has diverged from WordTokenizer and it may not be restored."
+)
 class WordTokenizerRe1(Regex1Tokenizer):
-    """Reference implementation for WorkTokenizer."""
+    """Reference implementation for WordTokenizer."""
 
     pattern = regex.compile(r"""([\p{posix_punct}\p{Punctuation}]+|\s+)""")
 

sonatoki/constants.py

@@ -4,16 +4,371 @@ from typing import Dict, List
 from pathlib import Path
 
 # LOCAL
-from sonatoki.utils import find_unicode_ranges
+from sonatoki.utils import find_unicode_chars, find_unicode_ranges
 
 # `\p{Punctuation}` character class
-UNICODE_PUNCT = r"""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~¡¢£¤¥¦§¨©«¬®¯°±´¶·¸»¿×÷˂˃˄˅˒˓˔˕˖˗˘˙˚˛˜˝˞˟˥˦˧˨˩˪˫˭˯˰˱˲˳˴˵˶˷˸˹˺˻˼˽˾˿͵;΄΅·϶҂՚՛՜՝՞՟։֊֍֎֏־׀׃׆׳״؆؇؈؉؊؋،؍؎؏؛؝؞؟٪٫٬٭۔۞۩۽۾܀܁܂܃܄܅܆܇܈܉܊܋܌܍߶߷߸߹߾߿࠰࠱࠲࠳࠴࠵࠶࠷࠸࠹࠺࠻࠼࠽࠾࡞࢈।॥॰৲৳৺৻৽੶૰૱୰௳௴௵௶௷௸௹௺౷౿಄൏൹෴฿๏๚๛༁༂༃༄༅༆༇༈༉༊་༌།༎༏༐༑༒༓༔༕༖༗༚༛༜༝༞༟༴༶༸༺༻༼༽྅྾྿࿀࿁࿂࿃࿄࿅࿇࿈࿉࿊࿋࿌࿎࿏࿐࿑࿒࿓࿔࿕࿖࿗࿘࿙࿚၊။၌၍၎၏႞႟჻፠፡።፣፤፥፦፧፨᎐᎑᎒᎓᎔᎕᎖᎗᎘᎙᐀᙭᙮᚛᚜᛫᛬᛭᜵᜶។៕៖៘៙៚៛᠀᠁᠂᠃᠄᠅᠆᠇᠈᠉᠊᥀᥄᥅᧞᧟᧠᧡᧢᧣᧤᧥᧦᧧᧨᧩᧪᧫᧬᧭᧮᧯᧰᧱᧲᧳᧴᧵᧶᧷᧸᧹᧺᧻᧼᧽᧾᧿᨞᨟᪠᪡᪢᪣᪤᪥᪦᪨᪩᪪᪫᪬᪭᭚᭛᭜᭝᭞᭟᭠᭡᭢᭣᭤᭥᭦᭧᭨᭩᭪᭴᭵᭶᭷᭸᭹᭺᭻᭼᭽᭾᯼᯽᯾᯿᰻᰼᰽᰾᰿᱾᱿᳀᳁᳂᳃᳄᳅᳆᳇᳓᾽᾿῀῁῍῎῏῝῞῟῭΅`´῾‐‑‒–—―‖‗‘’‚‛“”„‟†‡•‣․‥…‧‰‱′″‴‵‶‷‸‹›※‼‽‾‿⁀⁁⁂⁃⁄⁅⁆⁇⁈⁉⁊⁋⁌⁍⁎⁏⁐⁑⁒⁓⁔⁕⁖⁗⁘⁙⁚⁛⁜⁝⁞⁺⁻⁼⁽⁾₊₋₌₍₎₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵₶₷₸₹₺₻₼₽₾₿⃀℀℁℃℄℅℆℈℉℔№℗℘℞℟℠℡™℣℥℧℩℮℺℻⅀⅁⅂⅃⅄⅊⅋⅌⅍⅏↊↋←↑→↓↔↕↖↗↘↙↚↛↜↝↞↟↠↡↢↣↤↥↦↧↨↩↪↫↬↭↮↯↰↱↲↳↴↵↶↷↸↹↺↻↼↽↾↿⇀⇁⇂⇃⇄⇅⇆⇇⇈⇉⇊⇋⇌⇍⇎⇏⇐⇑⇒⇓⇔⇕⇖⇗⇘⇙⇚⇛⇜⇝⇞⇟⇠⇡⇢⇣⇤⇥⇦⇧⇨⇩⇪⇫⇬⇭⇮⇯⇰⇱⇲⇳⇴⇵⇶⇷⇸⇹⇺⇻⇼⇽⇾⇿∀∁∂∃∄∅∆∇∈∉∊∋∌∍∎∏∐∑−∓∔∕∖∗∘∙√∛∜∝∞∟∠∡∢∣∤∥∦∧∨∩∪∫∬∭∮∯∰∱∲∳∴∵∶∷∸∹∺∻∼∽∾∿≀≁≂≃≄≅≆≇≈≉≊≋≌≍≎≏≐≑≒≓≔≕≖≗≘≙≚≛≜≝≞≟≠≡≢≣≤≥≦≧≨≩≪≫≬≭≮≯≰≱≲≳≴≵≶≷≸≹≺≻≼≽≾≿⊀⊁⊂⊃⊄⊅⊆⊇⊈⊉⊊⊋⊌⊍⊎⊏⊐⊑⊒⊓⊔⊕⊖⊗⊘⊙⊚⊛⊜⊝⊞⊟⊠⊡⊢⊣⊤⊥⊦⊧⊨⊩⊪⊫⊬⊭⊮⊯⊰⊱⊲⊳⊴⊵⊶⊷⊸⊹⊺⊻⊼⊽⊾⊿⋀⋁⋂⋃⋄⋅⋆⋇⋈⋉⋊⋋⋌⋍⋎⋏⋐⋑⋒⋓⋔⋕⋖⋗⋘⋙⋚⋛⋜⋝⋞⋟⋠⋡⋢⋣⋤⋥⋦⋧⋨⋩⋪⋫⋬⋭⋮⋯⋰⋱⋲⋳⋴⋵⋶⋷⋸⋹⋺⋻⋼⋽⋾⋿⌀⌁⌂⌃⌄⌅⌆⌇⌈⌉⌊⌋⌌⌍⌎⌏⌐⌑⌒⌓⌔⌕⌖⌗⌘⌙⌚⌛⌜⌝⌞⌟⌠⌡⌢⌣⌤⌥⌦⌧⌨〈〉⌫⌬⌭⌮⌯⌰⌱⌲⌳⌴⌵⌶⌷⌸⌹⌺⌻⌼⌽⌾⌿⍀⍁⍂⍃⍄⍅⍆⍇⍈⍉⍊⍋⍌⍍⍎⍏⍐⍑⍒⍓⍔⍕⍖⍗⍘⍙⍚⍛⍜⍝⍞⍟⍠⍡⍢⍣⍤⍥⍦⍧⍨⍩⍪⍫⍬⍭⍮⍯⍰⍱⍲⍳⍴⍵⍶⍷⍸⍹⍺⍻⍼⍽⍾⍿⎀⎁⎂⎃⎄⎅⎆⎇⎈⎉⎊⎋⎌⎍⎎⎏⎐⎑⎒⎓⎔⎕⎖⎗⎘⎙⎚⎛⎜⎝⎞⎟⎠⎡⎢⎣⎤⎥⎦⎧⎨⎩⎪⎫⎬⎭⎮⎯⎰⎱⎲⎳⎴⎵⎶⎷⎸⎹⎺⎻⎼⎽⎾⎿⏀⏁⏂⏃⏄⏅⏆⏇⏈⏉⏊⏋⏌⏍⏎⏏⏐⏑⏒⏓⏔⏕⏖⏗⏘⏙⏚⏛⏜⏝⏞⏟⏠⏡⏢⏣⏤⏥⏦⏧⏨⏩⏪⏫⏬⏭⏮⏯⏰⏱⏲⏳⏴⏵⏶⏷⏸⏹⏺⏻⏼⏽⏾⏿␀␁␂␃␄␅␆␇␈␉␊␋␌␍␎␏␐␑␒␓␔␕␖␗␘␙␚␛␜␝␞␟␠␡␢␣␤␥␦⑀⑁⑂⑃⑄⑅⑆⑇⑈⑉⑊⒜⒝⒞⒟⒠⒡⒢⒣⒤⒥⒦⒧⒨⒩⒪⒫⒬⒭⒮⒯⒰⒱⒲⒳⒴⒵─━│┃┄┅┆┇┈┉┊┋┌┍┎┏┐┑┒┓└┕┖┗┘┙┚┛├┝┞┟┠┡┢┣┤┥┦┧┨┩┪┫┬┭┮┯┰┱┲┳┴┵┶┷┸┹┺┻┼┽┾┿╀╁╂╃╄╅╆╇╈╉╊╋╌╍╎╏═║╒╓╔╕╖╗╘╙╚╛╜╝╞╟╠╡╢╣╤╥╦╧╨╩╪╫╬╭╮╯╰╱╲╳╴╵╶╷╸╹╺╻╼╽╾╿▀▁▂▃▄▅▆▇█▉▊▋▌▍▎▏▐░▒▓▔▕▖▗▘▙▚▛▜▝▞▟■□▢▣▤▥▦▧▨▩▪▫▬▭▮▯▰▱▲△▴▵▶▷▸▹►▻▼▽▾▿◀◁◂◃◄◅◆◇◈◉◊○◌◍◎●◐◑◒◓◔◕◖◗◘◙◚◛◜◝◞◟◠◡◢◣◤◥◦◧◨◩◪◫◬◭◮◯◰◱◲◳◴◵◶◷◸◹◺◻◼◽◾◿☀☁☂☃☄★☆☇☈☉☊☋☌☍☎☏☐☑☒☓☔☕☖☗☘☙☚☛☜☝☞☟☠☡☢☣☤☥☦☧☨☩☪☫☬☭☮☯☰☱☲☳☴☵☶☷☸☹☺☻☼☽☾☿♀♁♂♃♄♅♆♇♈♉♊♋♌♍♎♏♐♑♒♓♔♕♖♗♘♙♚♛♜♝♞♟♠♡♢♣♤♥♦♧♨♩♪♫♬♭♮♯♰♱♲♳♴♵♶♷♸♹♺♻♼♽♾♿⚀⚁⚂⚃⚄⚅⚆⚇⚈⚉⚊⚋⚌⚍⚎⚏⚐⚑⚒⚓⚔⚕⚖⚗⚘⚙⚚⚛⚜⚝⚞⚟⚠⚡⚢⚣⚤⚥⚦⚧⚨⚩⚪⚫⚬⚭⚮⚯⚰⚱⚲⚳⚴⚵⚶⚷⚸⚹⚺⚻⚼⚽⚾⚿⛀⛁⛂⛃⛄⛅⛆⛇⛈⛉⛊⛋⛌⛍⛎⛏⛐⛑⛒⛓⛔⛕⛖⛗⛘⛙⛚⛛⛜⛝⛞⛟⛠⛡⛢⛣⛤⛥⛦⛧⛨⛩⛪⛫⛬⛭⛮⛯⛰⛱⛲⛳⛴⛵⛶⛷⛸⛹⛺⛻⛼⛽⛾⛿✀✁✂✃✄✅✆✇✈✉✊✋✌✍✎✏✐✑✒✓✔✕✖✗✘✙✚✛✜✝✞✟✠✡✢✣✤✥✦✧✨✩✪✫✬✭✮✯✰✱✲✳✴✵✶✷✸✹✺✻✼✽✾✿❀❁❂❃❄❅❆❇❈❉❊❋❌❍❎❏❐❑❒❓❔❕❖❗❘❙❚❛❜❝❞❟❠❡❢❣❤❥❦❧❨❩❪❫❬❭❮❯❰❱❲❳❴❵➔➕➖➗➘➙➚➛➜➝➞➟➠➡➢➣➤➥➦➧➨➩➪➫➬➭➮➯➰➱➲➳➴➵➶➷➸➹➺➻➼➽➾➿⟀⟁⟂⟃⟄⟅⟆⟇⟈⟉⟊⟋⟌⟍⟎⟏⟐⟑⟒⟓⟔⟕⟖⟗⟘⟙⟚⟛⟜⟝⟞⟟⟠⟡⟢⟣⟤⟥⟦⟧⟨⟩⟪⟫⟬⟭⟮⟯⟰⟱⟲⟳⟴⟵⟶⟷⟸⟹⟺⟻⟼⟽⟾⟿⠀⠁⠂⠃⠄⠅⠆⠇⠈⠉⠊⠋⠌⠍⠎⠏⠐⠑⠒⠓⠔⠕⠖⠗⠘⠙⠚⠛⠜⠝⠞⠟⠠⠡⠢⠣⠤⠥⠦⠧⠨⠩⠪⠫⠬⠭⠮⠯⠰⠱⠲⠳⠴⠵⠶⠷⠸⠹⠺⠻⠼⠽⠾⠿⡀⡁⡂⡃⡄⡅⡆⡇⡈⡉⡊⡋⡌⡍⡎⡏⡐⡑⡒⡓⡔⡕⡖⡗⡘⡙⡚⡛⡜⡝⡞⡟⡠⡡⡢⡣⡤⡥⡦⡧⡨⡩⡪⡫⡬⡭⡮⡯⡰⡱⡲⡳⡴⡵⡶⡷⡸⡹⡺⡻⡼⡽⡾⡿⢀⢁⢂⢃⢄⢅⢆⢇⢈⢉⢊⢋⢌⢍⢎⢏⢐⢑⢒⢓⢔⢕⢖⢗⢘⢙⢚⢛⢜⢝⢞⢟⢠⢡⢢⢣⢤⢥⢦⢧⢨⢩⢪⢫⢬⢭⢮⢯⢰⢱⢲⢳⢴⢵⢶⢷⢸⢹⢺⢻⢼⢽⢾⢿⣀⣁⣂⣃⣄⣅⣆⣇⣈⣉⣊⣋⣌⣍⣎⣏⣐⣑⣒⣓⣔⣕⣖⣗⣘⣙⣚⣛⣜⣝⣞⣟⣠⣡⣢⣣⣤⣥⣦⣧⣨⣩⣪⣫⣬⣭⣮⣯⣰⣱⣲⣳⣴⣵⣶⣷⣸⣹⣺⣻⣼⣽⣾⣿⤀⤁⤂⤃⤄⤅⤆⤇⤈⤉⤊⤋⤌⤍⤎⤏⤐⤑⤒⤓⤔⤕⤖⤗⤘⤙⤚⤛⤜⤝⤞⤟⤠⤡⤢⤣⤤⤥⤦⤧⤨⤩⤪⤫⤬⤭⤮⤯⤰⤱⤲⤳⤴⤵⤶⤷⤸⤹⤺⤻⤼⤽⤾⤿⥀⥁⥂⥃⥄⥅⥆⥇⥈⥉⥊⥋⥌⥍⥎⥏⥐⥑⥒⥓⥔⥕⥖⥗⥘⥙⥚⥛⥜⥝⥞⥟⥠⥡⥢⥣⥤⥥⥦⥧⥨⥩⥪⥫⥬⥭⥮⥯⥰⥱⥲⥳⥴⥵⥶⥷⥸⥹⥺⥻⥼⥽⥾⥿⦀⦁⦂⦃⦄⦅⦆⦇⦈⦉⦊⦋⦌⦍⦎⦏⦐⦑⦒⦓⦔⦕⦖⦗⦘⦙⦚⦛⦜⦝⦞⦟⦠⦡⦢⦣⦤⦥⦦⦧⦨⦩⦪⦫⦬⦭⦮⦯⦰⦱⦲⦳⦴⦵⦶⦷⦸⦹⦺⦻⦼⦽⦾⦿⧀⧁⧂⧃⧄⧅⧆⧇⧈⧉⧊⧋⧌⧍⧎⧏⧐⧑⧒⧓⧔⧕⧖⧗⧘⧙⧚⧛⧜⧝⧞⧟⧠⧡⧢⧣⧤⧥⧦⧧⧨⧩⧪⧫⧬⧭⧮⧯⧰⧱⧲⧳⧴⧵⧶⧷⧸⧹⧺⧻⧼⧽⧾⧿⨀⨁⨂⨃⨄⨅⨆⨇⨈⨉⨊⨋⨌⨍⨎⨏⨐⨑⨒⨓⨔⨕⨖⨗⨘⨙⨚⨛⨜⨝⨞⨟⨠⨡⨢⨣⨤⨥⨦⨧⨨⨩⨪⨫⨬⨭⨮⨯⨰⨱⨲⨳⨴⨵⨶⨷⨸⨹⨺⨻⨼⨽⨾⨿⩀⩁⩂⩃⩄⩅⩆⩇⩈⩉⩊⩋⩌⩍⩎⩏⩐⩑⩒⩓⩔⩕⩖⩗⩘⩙⩚⩛⩜⩝⩞⩟⩠⩡⩢⩣⩤⩥⩦⩧⩨⩩⩪⩫⩬⩭⩮⩯⩰⩱⩲⩳⩴⩵⩶⩷⩸⩹⩺⩻⩼⩽⩾⩿⪀⪁⪂⪃⪄⪅⪆⪇⪈⪉⪊⪋⪌⪍⪎⪏⪐⪑⪒⪓⪔⪕⪖⪗⪘⪙⪚⪛⪜⪝⪞⪟⪠⪡⪢⪣⪤⪥⪦⪧⪨⪩⪪⪫⪬⪭⪮⪯⪰⪱⪲⪳⪴⪵⪶⪷⪸⪹⪺⪻⪼⪽⪾⪿⫀⫁⫂⫃⫄⫅⫆⫇⫈⫉⫊⫋⫌⫍⫎⫏⫐⫑⫒⫓⫔⫕⫖⫗⫘⫙⫚⫛⫝̸⫝⫞⫟⫠⫡⫢⫣⫤⫥⫦⫧⫨⫩⫪⫫⫬⫭⫮⫯⫰⫱⫲⫳⫴⫵⫶⫷⫸⫹⫺⫻⫼⫽⫾⫿⬀⬁⬂⬃⬄⬅⬆⬇⬈⬉⬊⬋⬌⬍⬎⬏⬐⬑⬒⬓⬔⬕⬖⬗⬘⬙⬚⬛⬜⬝⬞⬟⬠⬡⬢⬣⬤⬥⬦⬧⬨⬩⬪⬫⬬⬭⬮⬯⬰⬱⬲⬳⬴⬵⬶⬷⬸⬹⬺⬻⬼⬽⬾⬿⭀⭁⭂⭃⭄⭅⭆⭇⭈⭉⭊⭋⭌⭍⭎⭏⭐⭑⭒⭓⭔⭕⭖⭗⭘⭙⭚⭛⭜⭝⭞⭟⭠⭡⭢⭣⭤⭥⭦⭧⭨⭩⭪⭫⭬⭭⭮⭯⭰⭱⭲⭳⭶⭷⭸⭹⭺⭻⭼⭽⭾⭿⮀⮁⮂⮃⮄⮅⮆⮇⮈⮉⮊⮋⮌⮍⮎⮏⮐⮑⮒⮓⮔⮕⮗⮘⮙⮚⮛⮜⮝⮞⮟⮠⮡⮢⮣⮤⮥⮦⮧⮨⮩⮪⮫⮬⮭⮮⮯⮰⮱⮲⮳⮴⮵⮶⮷⮸⮹⮺⮻⮼⮽⮾⮿⯀⯁⯂⯃⯄⯅⯆⯇⯈⯉⯊⯋⯌⯍⯎⯏⯐⯑⯒⯓⯔⯕⯖⯗⯘⯙⯚⯛⯜⯝⯞⯟⯠⯡⯢⯣⯤⯥⯦⯧⯨⯩⯪⯫⯬⯭⯮⯯⯰⯱⯲⯳⯴⯵⯶⯷⯸⯹⯺⯻⯼⯽⯾⯿⳥⳦⳧⳨⳩⳪⳹⳺⳻⳼⳾⳿⵰⸀⸁⸂⸃⸄⸅⸆⸇⸈⸉⸊⸋⸌⸍⸎⸏⸐⸑⸒⸓⸔⸕⸖⸗⸘⸙⸚⸛⸜⸝⸞⸟⸠⸡⸢⸣⸤⸥⸦⸧⸨⸩⸪⸫⸬⸭⸮⸰⸱⸲⸳⸴⸵⸶⸷⸸⸹⸺⸻⸼⸽⸾⸿⹀⹁⹂⹃⹄⹅⹆⹇⹈⹉⹊⹋⹌⹍⹎⹏⹐⹑⹒⹓⹔⹕⹖⹗⹘⹙⹚⹛⹜⹝⺀⺁⺂⺃⺄⺅⺆⺇⺈⺉⺊⺋⺌⺍⺎⺏⺐⺑⺒⺓⺔⺕⺖⺗⺘⺙⺛⺜⺝⺞⺟⺠⺡⺢⺣⺤⺥⺦⺧⺨⺩⺪⺫⺬⺭⺮⺯⺰⺱⺲⺳⺴⺵⺶⺷⺸⺹⺺⺻⺼⺽⺾⺿⻀⻁⻂⻃⻄⻅⻆⻇⻈⻉⻊⻋⻌⻍⻎⻏⻐⻑⻒⻓⻔⻕⻖⻗⻘⻙⻚⻛⻜⻝⻞⻟⻠⻡⻢⻣⻤⻥⻦⻧⻨⻩⻪⻫⻬⻭⻮⻯⻰⻱⻲⻳⼀⼁⼂⼃⼄⼅⼆⼇⼈⼉⼊⼋⼌⼍⼎⼏⼐⼑⼒⼓⼔⼕⼖⼗⼘⼙⼚⼛⼜⼝⼞⼟⼠⼡⼢⼣⼤⼥⼦⼧⼨⼩⼪⼫⼬⼭⼮⼯⼰⼱⼲⼳⼴⼵⼶⼷⼸⼹⼺⼻⼼⼽⼾⼿⽀⽁⽂⽃⽄⽅⽆⽇⽈⽉⽊⽋⽌⽍⽎⽏⽐⽑⽒⽓⽔⽕⽖⽗⽘⽙⽚⽛⽜⽝⽞⽟⽠⽡⽢⽣⽤⽥⽦⽧⽨⽩⽪⽫⽬⽭⽮⽯⽰⽱⽲⽳⽴⽵⽶⽷⽸⽹⽺⽻⽼⽽⽾⽿⾀⾁⾂⾃⾄⾅⾆⾇⾈⾉⾊⾋⾌⾍⾎⾏⾐⾑⾒⾓⾔⾕⾖⾗⾘⾙⾚⾛⾜⾝⾞⾟⾠⾡⾢⾣⾤⾥⾦⾧⾨⾩⾪⾫⾬⾭⾮⾯⾰⾱⾲⾳⾴⾵⾶⾷⾸⾹⾺⾻⾼⾽⾾⾿⿀⿁⿂⿃⿄⿅⿆⿇⿈⿉⿊⿋⿌⿍⿎⿏⿐⿑⿒⿓⿔⿕⿰⿱⿲⿳⿴⿵⿶⿷⿸⿹⿺⿻⿼⿽⿾⿿、。〃〄〈〉《》「」『』【】〒〓〔〕〖〗〘〙〚〛〜〝〞〟〠〰〶〷〽〾〿゛゜゠・㆐㆑㆖㆗㆘㆙㆚㆛㆜㆝㆞㆟㇀㇁㇂㇃㇄㇅㇆㇇㇈㇉㇊㇋㇌㇍㇎㇏㇐㇑㇒㇓㇔㇕㇖㇗㇘㇙㇚㇛㇜㇝㇞㇟㇠㇡㇢㇣㇯㈀㈁㈂㈃㈄㈅㈆㈇㈈㈉㈊㈋㈌㈍㈎㈏㈐㈑㈒㈓㈔㈕㈖㈗㈘㈙㈚㈛㈜㈝㈞㈪㈫㈬㈭㈮㈯㈰㈱㈲㈳㈴㈵㈶㈷㈸㈹㈺㈻㈼㈽㈾㈿㉀㉁㉂㉃㉄㉅㉆㉇㉐㉠㉡㉢㉣㉤㉥㉦㉧㉨㉩㉪㉫㉬㉭㉮㉯㉰㉱㉲㉳㉴㉵㉶㉷㉸㉹㉺㉻㉼㉽㉾㉿㊊㊋㊌㊍㊎㊏㊐㊑㊒㊓㊔㊕㊖㊗㊘㊙㊚㊛㊜㊝㊞㊟㊠㊡㊢㊣㊤㊥㊦㊧㊨㊩㊪㊫㊬㊭㊮㊯㊰㋀㋁㋂㋃㋄㋅㋆㋇㋈㋉㋊㋋㋌㋍㋎㋏㋐㋑㋒㋓㋔㋕㋖㋗㋘㋙㋚㋛㋜㋝㋞㋟㋠㋡㋢㋣㋤㋥㋦㋧㋨㋩㋪㋫㋬㋭㋮㋯㋰㋱㋲㋳㋴㋵㋶㋷㋸㋹㋺㋻㋼㋽㋾㋿㌀㌁㌂㌃㌄㌅㌆㌇㌈㌉㌊㌋㌌㌍㌎㌏㌐㌑㌒㌓㌔㌕㌖㌗㌘㌙㌚㌛㌜㌝㌞㌟㌠㌡㌢㌣㌤㌥㌦㌧㌨㌩㌪㌫㌬㌭㌮㌯㌰㌱㌲㌳㌴㌵㌶㌷㌸㌹㌺㌻㌼㌽㌾㌿㍀㍁㍂㍃㍄㍅㍆㍇㍈㍉㍊㍋㍌㍍㍎㍏㍐㍑㍒㍓㍔㍕㍖㍗㍘㍙㍚㍛㍜㍝㍞㍟㍠㍡㍢㍣㍤㍥㍦㍧㍨㍩㍪㍫㍬㍭㍮㍯㍰㍱㍲㍳㍴㍵㍶㍷㍸㍹㍺㍻㍼㍽㍾㍿㎀㎁㎂㎃㎄㎅㎆㎇㎈㎉㎊㎋㎌㎍㎎㎏㎐㎑㎒㎓㎔㎕㎖㎗㎘㎙㎚㎛㎜㎝㎞㎟㎠㎡㎢㎣㎤㎥㎦㎧㎨㎩㎪㎫㎬㎭㎮㎯㎰㎱㎲㎳㎴㎵㎶㎷㎸㎹㎺㎻㎼㎽㎾㎿㏀㏁㏂㏃㏄㏅㏆㏇㏈㏉㏊㏋㏌㏍㏎㏏㏐㏑㏒㏓㏔㏕㏖㏗㏘㏙㏚㏛㏜㏝㏞㏟㏠㏡㏢㏣㏤㏥㏦㏧㏨㏩㏪㏫㏬㏭㏮㏯㏰㏱㏲㏳㏴㏵㏶㏷㏸㏹㏺㏻㏼㏽㏾㏿䷀䷁䷂䷃䷄䷅䷆䷇䷈䷉䷊䷋䷌䷍䷎䷏䷐䷑䷒䷓䷔䷕䷖䷗䷘䷙䷚䷛䷜䷝䷞䷟䷠䷡䷢䷣䷤䷥䷦䷧䷨䷩䷪䷫䷬䷭䷮䷯䷰䷱䷲䷳䷴䷵䷶䷷䷸䷹䷺䷻䷼䷽䷾䷿꒐꒑꒒꒓꒔꒕꒖꒗꒘꒙꒚꒛꒜꒝꒞꒟꒠꒡꒢꒣꒤꒥꒦꒧꒨꒩꒪꒫꒬꒭꒮꒯꒰꒱꒲꒳꒴꒵꒶꒷꒸꒹꒺꒻꒼꒽꒾꒿꓀꓁꓂꓃꓄꓅꓆꓾꓿꘍꘎꘏꙳꙾꛲꛳꛴꛵꛶꛷꜀꜁꜂꜃꜄꜅꜆꜇꜈꜉꜊꜋꜌꜍꜎꜏꜐꜑꜒꜓꜔꜕꜖꜠꜡꞉꞊꠨꠩꠪꠫꠶꠷꠸꠹꡴꡵꡶꡷꣎꣏꣸꣹꣺꣼꤮꤯꥟꧁꧂꧃꧄꧅꧆꧇꧈꧉꧊꧋꧌꧍꧞꧟꩜꩝꩞꩟꩷꩸꩹꫞꫟꫰꫱꭛꭪꭫꯫﬩﮲﮳﮴﮵﮶﮷﮸﮹﮺﮻﮼﮽﮾﮿﯀﯁﯂﴾﴿﵀﵁﵂﵃﵄﵅﵆﵇﵈﵉﵊﵋﵌﵍﵎﵏﷏﷼﷽﷾﷿︐︑︒︓︔︕︖︗︘︙︰︱︲︳︴︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄﹅﹆﹇﹈﹉﹊﹋﹌﹍﹎﹏﹐﹑﹒﹔﹕﹖﹗﹘﹙﹚﹛﹜﹝﹞﹟﹠﹡﹢﹣﹤﹥﹦﹨﹩﹪﹫！＂＃＄％＆＇（）＊＋，－．／：；＜＝＞？＠［＼］＾＿｀｛｜｝～｟｠｡｢｣､･￠￡￢￣￤￥￦￨￩￪￫￬￭￮�𐄀𐄁𐄂𐄷𐄸𐄹𐄺𐄻𐄼𐄽𐄾𐄿𐅹𐅺𐅻𐅼𐅽𐅾𐅿𐆀𐆁𐆂𐆃𐆄𐆅𐆆𐆇𐆈𐆉𐆌𐆍𐆎𐆐𐆑𐆒𐆓𐆔𐆕𐆖𐆗𐆘𐆙𐆚𐆛𐆜𐆠𐇐𐇑𐇒𐇓𐇔𐇕𐇖𐇗𐇘𐇙𐇚𐇛𐇜𐇝𐇞𐇟𐇠𐇡𐇢𐇣𐇤𐇥𐇦𐇧𐇨𐇩𐇪𐇫𐇬𐇭𐇮𐇯𐇰𐇱𐇲𐇳𐇴𐇵𐇶𐇷𐇸𐇹𐇺𐇻𐇼𐎟𐏐𐕯𐡗𐡷𐡸𐤟𐤿𐩐𐩑𐩒𐩓𐩔𐩕𐩖𐩗𐩘𐩿𐫈𐫰𐫱𐫲𐫳𐫴𐫵𐫶𐬹𐬺𐬻𐬼𐬽𐬾𐬿𐮙𐮚𐮛𐮜𐺭𐽕𐽖𐽗𐽘𐽙𐾆𐾇𐾈𐾉𑁇𑁈𑁉𑁊𑁋𑁌𑁍𑂻𑂼𑂾𑂿𑃀𑃁𑅀𑅁𑅂𑅃𑅴𑅵𑇅𑇆𑇇𑇈𑇍𑇛𑇝𑇞𑇟𑈸𑈹𑈺𑈻𑈼𑈽𑊩𑑋𑑌𑑍𑑎𑑏𑑚𑑛𑑝𑓆𑗁𑗂𑗃𑗄𑗅𑗆𑗇𑗈𑗉𑗊𑗋𑗌𑗍𑗎𑗏𑗐𑗑𑗒𑗓𑗔𑗕𑗖𑗗𑙁𑙂𑙃𑙠𑙡𑙢𑙣𑙤𑙥𑙦𑙧𑙨𑙩𑙪𑙫𑙬𑚹𑜼𑜽𑜾𑜿𑠻𑥄𑥅𑥆𑧢𑨿𑩀𑩁𑩂𑩃𑩄𑩅𑩆𑪚𑪛𑪜𑪞𑪟𑪠𑪡𑪢𑬀𑬁𑬂𑬃𑬄𑬅𑬆𑬇𑬈𑬉𑱁𑱂𑱃𑱄𑱅𑱰𑱱𑻷𑻸𑽃𑽄𑽅𑽆𑽇𑽈𑽉𑽊𑽋𑽌𑽍𑽎𑽏𑿕𑿖𑿗𑿘𑿙𑿚𑿛𑿜𑿝𑿞𑿟𑿠𑿡𑿢𑿣𑿤𑿥𑿦𑿧𑿨𑿩𑿪𑿫𑿬𑿭𑿮𑿯𑿰𑿱𑿿𒑰𒑱𒑲𒑳𒑴𒿱𒿲𖩮𖩯𖫵𖬷𖬸𖬹𖬺𖬻𖬼𖬽𖬾𖬿𖭄𖭅𖺗𖺘𖺙𖺚𖿢𛲜𛲟𜽐𜽑𜽒𜽓𜽔𜽕𜽖𜽗𜽘𜽙𜽚𜽛𜽜𜽝𜽞𜽟𜽠𜽡𜽢𜽣𜽤𜽥𜽦𜽧𜽨𜽩𜽪𜽫𜽬𜽭𜽮𜽯𜽰𜽱𜽲𜽳𜽴𜽵𜽶𜽷𜽸𜽹𜽺𜽻𜽼𜽽𜽾𜽿𜾀𜾁𜾂𜾃𜾄𜾅𜾆𜾇𜾈𜾉𜾊𜾋𜾌𜾍𜾎𜾏𜾐𜾑𜾒𜾓𜾔𜾕𜾖𜾗𜾘𜾙𜾚𜾛𜾜𜾝𜾞𜾟𜾠𜾡𜾢𜾣𜾤𜾥𜾦𜾧𜾨𜾩𜾪𜾫𜾬𜾭𜾮𜾯𜾰𜾱𜾲𜾳𜾴𜾵𜾶𜾷𜾸𜾹𜾺𜾻𜾼𜾽𜾾𜾿𜿀𜿁𜿂𜿃𝀀𝀁𝀂𝀃𝀄𝀅𝀆𝀇𝀈𝀉𝀊𝀋𝀌𝀍𝀎𝀏𝀐𝀑𝀒𝀓𝀔𝀕𝀖𝀗𝀘𝀙𝀚𝀛𝀜𝀝𝀞𝀟𝀠𝀡𝀢𝀣𝀤𝀥𝀦𝀧𝀨𝀩𝀪𝀫𝀬𝀭𝀮𝀯𝀰𝀱𝀲𝀳𝀴𝀵𝀶𝀷𝀸𝀹𝀺𝀻𝀼𝀽𝀾𝀿𝁀𝁁𝁂𝁃𝁄𝁅𝁆𝁇𝁈𝁉𝁊𝁋𝁌𝁍𝁎𝁏𝁐𝁑𝁒𝁓𝁔𝁕𝁖𝁗𝁘𝁙𝁚𝁛𝁜𝁝𝁞𝁟𝁠𝁡𝁢𝁣𝁤𝁥𝁦𝁧𝁨𝁩𝁪𝁫𝁬𝁭𝁮𝁯𝁰𝁱𝁲𝁳𝁴𝁵𝁶𝁷𝁸𝁹𝁺𝁻𝁼𝁽𝁾𝁿𝂀𝂁𝂂𝂃𝂄𝂅𝂆𝂇𝂈𝂉𝂊𝂋𝂌𝂍𝂎𝂏𝂐𝂑𝂒𝂓𝂔𝂕𝂖𝂗𝂘𝂙𝂚𝂛𝂜𝂝𝂞𝂟𝂠𝂡𝂢𝂣𝂤𝂥𝂦𝂧𝂨𝂩𝂪𝂫𝂬𝂭𝂮𝂯𝂰𝂱𝂲𝂳𝂴𝂵𝂶𝂷𝂸𝂹𝂺𝂻𝂼𝂽𝂾𝂿𝃀𝃁𝃂𝃃𝃄𝃅𝃆𝃇𝃈𝃉𝃊𝃋𝃌𝃍𝃎𝃏𝃐𝃑𝃒𝃓𝃔𝃕𝃖𝃗𝃘𝃙𝃚𝃛𝃜𝃝𝃞𝃟𝃠𝃡𝃢𝃣𝃤𝃥𝃦𝃧𝃨𝃩𝃪𝃫𝃬𝃭𝃮𝃯𝃰𝃱𝃲𝃳𝃴𝃵𝄀𝄁𝄂𝄃𝄄𝄅𝄆𝄇𝄈𝄉𝄊𝄋𝄌𝄍𝄎𝄏𝄐𝄑𝄒𝄓𝄔𝄕𝄖𝄗𝄘𝄙𝄚𝄛𝄜𝄝𝄞𝄟𝄠𝄡𝄢𝄣𝄤𝄥𝄦𝄩𝄪𝄫𝄬𝄭𝄮𝄯𝄰𝄱𝄲𝄳𝄴𝄵𝄶𝄷𝄸𝄹𝄺𝄻𝄼𝄽𝄾𝄿𝅀𝅁𝅂𝅃𝅄𝅅𝅆𝅇𝅈𝅉𝅊𝅋𝅌𝅍𝅎𝅏𝅐𝅑𝅒𝅓𝅔𝅕𝅖𝅗𝅘𝅙𝅚𝅛𝅜𝅝𝅗𝅥𝅘𝅥𝅘𝅥𝅮𝅘𝅥𝅯𝅘𝅥𝅰𝅘𝅥𝅱𝅘𝅥𝅲𝅪𝅫𝅬𝆃𝆄𝆌𝆍𝆎𝆏𝆐𝆑𝆒𝆓𝆔𝆕𝆖𝆗𝆘𝆙𝆚𝆛𝆜𝆝𝆞𝆟𝆠𝆡𝆢𝆣𝆤𝆥𝆦𝆧𝆨𝆩𝆮𝆯𝆰𝆱𝆲𝆳𝆴𝆵𝆶𝆷𝆸𝆹𝆺𝆹𝅥𝆺𝅥𝆹𝅥𝅮𝆺𝅥𝅮𝆹𝅥𝅯𝆺𝅥𝅯𝇁𝇂𝇃𝇄𝇅𝇆𝇇𝇈𝇉𝇊𝇋𝇌𝇍𝇎𝇏𝇐𝇑𝇒𝇓𝇔𝇕𝇖𝇗𝇘𝇙𝇚𝇛𝇜𝇝𝇞𝇟𝇠𝇡𝇢𝇣𝇤𝇥𝇦𝇧𝇨𝇩𝇪𝈀𝈁𝈂𝈃𝈄𝈅𝈆𝈇𝈈𝈉𝈊𝈋𝈌𝈍𝈎𝈏𝈐𝈑𝈒𝈓𝈔𝈕𝈖𝈗𝈘𝈙𝈚𝈛𝈜𝈝𝈞𝈟𝈠𝈡𝈢𝈣𝈤𝈥𝈦𝈧𝈨𝈩𝈪𝈫𝈬𝈭𝈮𝈯𝈰𝈱𝈲𝈳𝈴𝈵𝈶𝈷𝈸𝈹𝈺𝈻𝈼𝈽𝈾𝈿𝉀𝉁𝉅𝌀𝌁𝌂𝌃𝌄𝌅𝌆𝌇𝌈𝌉𝌊𝌋𝌌𝌍𝌎𝌏𝌐𝌑𝌒𝌓𝌔𝌕𝌖𝌗𝌘𝌙𝌚𝌛𝌜𝌝𝌞𝌟𝌠𝌡𝌢𝌣𝌤𝌥𝌦𝌧𝌨𝌩𝌪𝌫𝌬𝌭𝌮𝌯𝌰𝌱𝌲𝌳𝌴𝌵𝌶𝌷𝌸𝌹𝌺𝌻𝌼𝌽𝌾𝌿𝍀𝍁𝍂𝍃𝍄𝍅𝍆𝍇𝍈𝍉𝍊𝍋𝍌𝍍𝍎𝍏𝍐𝍑𝍒𝍓𝍔𝍕𝍖𝛁𝛛𝛻𝜕𝜵𝝏𝝯𝞉𝞩𝟃𝠀𝠁𝠂𝠃𝠄𝠅𝠆𝠇𝠈𝠉𝠊𝠋𝠌𝠍𝠎𝠏𝠐𝠑𝠒𝠓𝠔𝠕𝠖𝠗𝠘𝠙𝠚𝠛𝠜𝠝𝠞𝠟𝠠𝠡𝠢𝠣𝠤𝠥𝠦𝠧𝠨𝠩𝠪𝠫𝠬𝠭𝠮𝠯𝠰𝠱𝠲𝠳𝠴𝠵𝠶𝠷𝠸𝠹𝠺𝠻𝠼𝠽𝠾𝠿𝡀𝡁𝡂𝡃𝡄𝡅𝡆𝡇𝡈𝡉𝡊𝡋𝡌𝡍𝡎𝡏𝡐𝡑𝡒𝡓𝡔𝡕𝡖𝡗𝡘𝡙𝡚𝡛𝡜𝡝𝡞𝡟𝡠𝡡𝡢𝡣𝡤𝡥𝡦𝡧𝡨𝡩𝡪𝡫𝡬𝡭𝡮𝡯𝡰𝡱𝡲𝡳𝡴𝡵𝡶𝡷𝡸𝡹𝡺𝡻𝡼𝡽𝡾𝡿𝢀𝢁𝢂𝢃𝢄𝢅𝢆𝢇𝢈𝢉𝢊𝢋𝢌𝢍𝢎𝢏𝢐𝢑𝢒𝢓𝢔𝢕𝢖𝢗𝢘𝢙𝢚𝢛𝢜𝢝𝢞𝢟𝢠𝢡𝢢𝢣𝢤𝢥𝢦𝢧𝢨𝢩𝢪𝢫𝢬𝢭𝢮𝢯𝢰𝢱𝢲𝢳𝢴𝢵𝢶𝢷𝢸𝢹𝢺𝢻𝢼𝢽𝢾𝢿𝣀𝣁𝣂𝣃𝣄𝣅𝣆𝣇𝣈𝣉𝣊𝣋𝣌𝣍𝣎𝣏𝣐𝣑𝣒𝣓𝣔𝣕𝣖𝣗𝣘𝣙𝣚𝣛𝣜𝣝𝣞𝣟𝣠𝣡𝣢𝣣𝣤𝣥𝣦𝣧𝣨𝣩𝣪𝣫𝣬𝣭𝣮𝣯𝣰𝣱𝣲𝣳𝣴𝣵𝣶𝣷𝣸𝣹𝣺𝣻𝣼𝣽𝣾𝣿𝤀𝤁𝤂𝤃𝤄𝤅𝤆𝤇𝤈𝤉𝤊𝤋𝤌𝤍𝤎𝤏𝤐𝤑𝤒𝤓𝤔𝤕𝤖𝤗𝤘𝤙𝤚𝤛𝤜𝤝𝤞𝤟𝤠𝤡𝤢𝤣𝤤𝤥𝤦𝤧𝤨𝤩𝤪𝤫𝤬𝤭𝤮𝤯𝤰𝤱𝤲𝤳𝤴𝤵𝤶𝤷𝤸𝤹𝤺𝤻𝤼𝤽𝤾𝤿𝥀𝥁𝥂𝥃𝥄𝥅𝥆𝥇𝥈𝥉𝥊𝥋𝥌𝥍𝥎𝥏𝥐𝥑𝥒𝥓𝥔𝥕𝥖𝥗𝥘𝥙𝥚𝥛𝥜𝥝𝥞𝥟𝥠𝥡𝥢𝥣𝥤𝥥𝥦𝥧𝥨𝥩𝥪𝥫𝥬𝥭𝥮𝥯𝥰𝥱𝥲𝥳𝥴𝥵𝥶𝥷𝥸𝥹𝥺𝥻𝥼𝥽𝥾𝥿𝦀𝦁𝦂𝦃𝦄𝦅𝦆𝦇𝦈𝦉𝦊𝦋𝦌𝦍𝦎𝦏𝦐𝦑𝦒𝦓𝦔𝦕𝦖𝦗𝦘𝦙𝦚𝦛𝦜𝦝𝦞𝦟𝦠𝦡𝦢𝦣𝦤𝦥𝦦𝦧𝦨𝦩𝦪𝦫𝦬𝦭𝦮𝦯𝦰𝦱𝦲𝦳𝦴𝦵𝦶𝦷𝦸𝦹𝦺𝦻𝦼𝦽𝦾𝦿𝧀𝧁𝧂𝧃𝧄𝧅𝧆𝧇𝧈𝧉𝧊𝧋𝧌𝧍𝧎𝧏𝧐𝧑𝧒𝧓𝧔𝧕𝧖𝧗𝧘𝧙𝧚𝧛𝧜𝧝𝧞𝧟𝧠𝧡𝧢𝧣𝧤𝧥𝧦𝧧𝧨𝧩𝧪𝧫𝧬𝧭𝧮𝧯𝧰𝧱𝧲𝧳𝧴𝧵𝧶𝧷𝧸𝧹𝧺𝧻𝧼𝧽𝧾𝧿𝨷𝨸𝨹𝨺𝩭𝩮𝩯𝩰𝩱𝩲𝩳𝩴𝩶𝩷𝩸𝩹𝩺𝩻𝩼𝩽𝩾𝩿𝪀𝪁𝪂𝪃𝪅𝪆𝪇𝪈𝪉𝪊𝪋𞅏𞋿𞥞𞥟𞲬𞲰𞴮𞻰𞻱🀀🀁🀂🀃🀄🀅🀆🀇🀈🀉🀊🀋🀌🀍🀎🀏🀐🀑🀒🀓🀔🀕🀖🀗🀘🀙🀚🀛🀜🀝🀞🀟🀠🀡🀢🀣🀤🀥🀦🀧🀨🀩🀪🀫🀰🀱🀲🀳🀴🀵🀶🀷🀸🀹🀺🀻🀼🀽🀾🀿🁀🁁🁂🁃🁄🁅🁆🁇🁈🁉🁊🁋🁌🁍🁎🁏🁐🁑🁒🁓🁔🁕🁖🁗🁘🁙🁚🁛🁜🁝🁞🁟🁠🁡🁢🁣🁤🁥🁦🁧🁨🁩🁪🁫🁬🁭🁮🁯🁰🁱🁲🁳🁴🁵🁶🁷🁸🁹🁺🁻🁼🁽🁾🁿🂀🂁🂂🂃🂄🂅🂆🂇🂈🂉🂊🂋🂌🂍🂎🂏🂐🂑🂒🂓🂠🂡🂢🂣🂤🂥🂦🂧🂨🂩🂪🂫🂬🂭🂮🂱🂲🂳🂴🂵🂶🂷🂸🂹🂺🂻🂼🂽🂾🂿🃁🃂🃃🃄🃅🃆🃇🃈🃉🃊🃋🃌🃍🃎🃏🃑🃒🃓🃔🃕🃖🃗🃘🃙🃚🃛🃜🃝🃞🃟🃠🃡🃢🃣🃤🃥🃦🃧🃨🃩🃪🃫🃬🃭🃮🃯🃰🃱🃲🃳🃴🃵🄍🄎🄏🄐🄑🄒🄓🄔🄕🄖🄗🄘🄙🄚🄛🄜🄝🄞🄟🄠🄡🄢🄣🄤🄥🄦🄧🄨🄩🄪🄫🄬🄭🄮🄯🅊🅋🅌🅍🅎🅏🅪🅫🅬🅭🅮🅯🆊🆋🆌🆍🆎🆏🆐🆑🆒🆓🆔🆕🆖🆗🆘🆙🆚🆛🆜🆝🆞🆟🆠🆡🆢🆣🆤🆥🆦🆧🆨🆩🆪🆫🆬🆭🇦🇧🇨🇩🇪🇫🇬🇭🇮🇯🇰🇱🇲🇳🇴🇵🇶🇷🇸🇹🇺🇻🇼🇽🇾🇿🈀🈁🈂🈐🈑🈒🈓🈔🈕🈖🈗🈘🈙🈚🈛🈜🈝🈞🈟🈠🈡🈢🈣🈤🈥🈦🈧🈨🈩🈪🈫🈬🈭🈮🈯🈰🈱🈲🈳🈴🈵🈶🈷🈸🈹🈺🈻🉀🉁🉂🉃🉄🉅🉆🉇🉈🉐🉑🉠🉡🉢🉣🉤🉥🌀🌁🌂🌃🌄🌅🌆🌇🌈🌉🌊🌋🌌🌍🌎🌏🌐🌑🌒🌓🌔🌕🌖🌗🌘🌙🌚🌛🌜🌝🌞🌟🌠🌡🌢🌣🌤🌥🌦🌧🌨🌩🌪🌫🌬🌭🌮🌯🌰🌱🌲🌳🌴🌵🌶🌷🌸🌹🌺🌻🌼🌽🌾🌿🍀🍁🍂🍃🍄🍅🍆🍇🍈🍉🍊🍋🍌🍍🍎🍏🍐🍑🍒🍓🍔🍕🍖🍗🍘🍙🍚🍛🍜🍝🍞🍟🍠🍡🍢🍣🍤🍥🍦🍧🍨🍩🍪🍫🍬🍭🍮🍯🍰🍱🍲🍳🍴🍵🍶🍷🍸🍹🍺🍻🍼🍽🍾🍿🎀🎁🎂🎃🎄🎅🎆🎇🎈🎉🎊🎋🎌🎍🎎🎏🎐🎑🎒🎓🎔🎕🎖🎗🎘🎙🎚🎛🎜🎝🎞🎟🎠🎡🎢🎣🎤🎥🎦🎧🎨🎩🎪🎫🎬🎭🎮🎯🎰🎱🎲🎳🎴🎵🎶🎷🎸🎹🎺🎻🎼🎽🎾🎿🏀🏁🏂🏃🏄🏅🏆🏇🏈🏉🏊🏋🏌🏍🏎🏏🏐🏑🏒🏓🏔🏕🏖🏗🏘🏙🏚🏛🏜🏝🏞🏟🏠🏡🏢🏣🏤🏥🏦🏧🏨🏩🏪🏫🏬🏭🏮🏯🏰🏱🏲🏳🏴🏵🏶🏷🏸🏹🏺🏻🏼🏽🏾🏿🐀🐁🐂🐃🐄🐅🐆🐇🐈🐉🐊🐋🐌🐍🐎🐏🐐🐑🐒🐓🐔🐕🐖🐗🐘🐙🐚🐛🐜🐝🐞🐟🐠🐡🐢🐣🐤🐥🐦🐧🐨🐩🐪🐫🐬🐭🐮🐯🐰🐱🐲🐳🐴🐵🐶🐷🐸🐹🐺🐻🐼🐽🐾🐿👀👁👂👃👄👅👆👇👈👉👊👋👌👍👎👏👐👑👒👓👔👕👖👗👘👙👚👛👜👝👞👟👠👡👢👣👤👥👦👧👨👩👪👫👬👭👮👯👰👱👲👳👴👵👶👷👸👹👺👻👼👽👾👿💀💁💂💃💄💅💆💇💈💉💊💋💌💍💎💏💐💑💒💓💔💕💖💗💘💙💚💛💜💝💞💟💠💡💢💣💤💥💦💧💨💩💪💫💬💭💮💯💰💱💲💳💴💵💶💷💸💹💺💻💼💽💾💿📀📁📂📃📄📅📆📇📈📉📊📋📌📍📎📏📐📑📒📓📔📕📖📗📘📙📚📛📜📝📞📟📠📡📢📣📤📥📦📧📨📩📪📫📬📭📮📯📰📱📲📳📴📵📶📷📸📹📺📻📼📽📾📿🔀🔁🔂🔃🔄🔅🔆🔇🔈🔉🔊🔋🔌🔍🔎🔏🔐🔑🔒🔓🔔🔕🔖🔗🔘🔙🔚🔛🔜🔝🔞🔟🔠🔡🔢🔣🔤🔥🔦🔧🔨🔩🔪🔫🔬🔭🔮🔯🔰🔱🔲🔳🔴🔵🔶🔷🔸🔹🔺🔻🔼🔽🔾🔿🕀🕁🕂🕃🕄🕅🕆🕇🕈🕉🕊🕋🕌🕍🕎🕏🕐🕑🕒🕓🕔🕕🕖🕗🕘🕙🕚🕛🕜🕝🕞🕟🕠🕡🕢🕣🕤🕥🕦🕧🕨🕩🕪🕫🕬🕭🕮🕯🕰🕱🕲🕳🕴🕵🕶🕷🕸🕹🕺🕻🕼🕽🕾🕿🖀🖁🖂🖃🖄🖅🖆🖇🖈🖉🖊🖋🖌🖍🖎🖏🖐🖑🖒🖓🖔🖕🖖🖗🖘🖙🖚🖛🖜🖝🖞🖟🖠🖡🖢🖣🖤🖥🖦🖧🖨🖩🖪🖫🖬🖭🖮🖯🖰🖱🖲🖳🖴🖵🖶🖷🖸🖹🖺🖻🖼🖽🖾🖿🗀🗁🗂🗃🗄🗅🗆🗇🗈🗉🗊🗋🗌🗍🗎🗏🗐🗑🗒🗓🗔🗕🗖🗗🗘🗙🗚🗛🗜🗝🗞🗟🗠🗡🗢🗣🗤🗥🗦🗧🗨🗩🗪🗫🗬🗭🗮🗯🗰🗱🗲🗳🗴🗵🗶🗷🗸🗹🗺🗻🗼🗽🗾🗿😀😁😂😃😄😅😆😇😈😉😊😋😌😍😎😏😐😑😒😓😔😕😖😗😘😙😚😛😜😝😞😟😠😡😢😣😤😥😦😧😨😩😪😫😬😭😮😯😰😱😲😳😴😵😶😷😸😹😺😻😼😽😾😿🙀🙁🙂🙃🙄🙅🙆🙇🙈🙉🙊🙋🙌🙍🙎🙏🙐🙑🙒🙓🙔🙕🙖🙗🙘🙙🙚🙛🙜🙝🙞🙟🙠🙡🙢🙣🙤🙥🙦🙧🙨🙩🙪🙫🙬🙭🙮🙯🙰🙱🙲🙳🙴🙵🙶🙷🙸🙹🙺🙻🙼🙽🙾🙿🚀🚁🚂🚃🚄🚅🚆🚇🚈🚉🚊🚋🚌🚍🚎🚏🚐🚑🚒🚓🚔🚕🚖🚗🚘🚙🚚🚛🚜🚝🚞🚟🚠🚡🚢🚣🚤🚥🚦🚧🚨🚩🚪🚫🚬🚭🚮🚯🚰🚱🚲🚳🚴🚵🚶🚷🚸🚹🚺🚻🚼🚽🚾🚿🛀🛁🛂🛃🛄🛅🛆🛇🛈🛉🛊🛋🛌🛍🛎🛏🛐🛑🛒🛓🛔🛕🛖🛗🛜🛝🛞🛟🛠🛡🛢🛣🛤🛥🛦🛧🛨🛩🛪🛫🛬🛰🛱🛲🛳🛴🛵🛶🛷🛸🛹🛺🛻🛼🜀🜁🜂🜃🜄🜅🜆🜇🜈🜉🜊🜋🜌🜍🜎🜏🜐🜑🜒🜓🜔🜕🜖🜗🜘🜙🜚🜛🜜🜝🜞🜟🜠🜡🜢🜣🜤🜥🜦🜧🜨🜩🜪🜫🜬🜭🜮🜯🜰🜱🜲🜳🜴🜵🜶🜷🜸🜹🜺🜻🜼🜽🜾🜿🝀🝁🝂🝃🝄🝅🝆🝇🝈🝉🝊🝋🝌🝍🝎🝏🝐🝑🝒🝓🝔🝕🝖🝗🝘🝙🝚🝛🝜🝝🝞🝟🝠🝡🝢🝣🝤🝥🝦🝧🝨🝩🝪🝫🝬🝭🝮🝯🝰🝱🝲🝳🝴🝵🝶🝻🝼🝽🝾🝿🞀🞁🞂🞃🞄🞅🞆🞇🞈🞉🞊🞋🞌🞍🞎🞏🞐🞑🞒🞓🞔🞕🞖🞗🞘🞙🞚🞛🞜🞝🞞🞟🞠🞡🞢🞣🞤🞥🞦🞧🞨🞩🞪🞫🞬🞭🞮🞯🞰🞱🞲🞳🞴🞵🞶🞷🞸🞹🞺🞻🞼🞽🞾🞿🟀🟁🟂🟃🟄🟅🟆🟇🟈🟉🟊🟋🟌🟍🟎🟏🟐🟑🟒🟓🟔🟕🟖🟗🟘🟙🟠🟡🟢🟣🟤🟥🟦🟧🟨🟩🟪🟫🟰🠀🠁🠂🠃🠄🠅🠆🠇🠈🠉🠊🠋🠐🠑🠒🠓🠔🠕🠖🠗🠘🠙🠚🠛🠜🠝🠞🠟🠠🠡🠢🠣🠤🠥🠦🠧🠨🠩🠪🠫🠬🠭🠮🠯🠰🠱🠲🠳🠴🠵🠶🠷🠸🠹🠺🠻🠼🠽🠾🠿🡀🡁🡂🡃🡄🡅🡆🡇🡐🡑🡒🡓🡔🡕🡖🡗🡘🡙🡠🡡🡢🡣🡤🡥🡦🡧🡨🡩🡪🡫🡬🡭🡮🡯🡰🡱🡲🡳🡴🡵🡶🡷🡸🡹🡺🡻🡼🡽🡾🡿🢀🢁🢂🢃🢄🢅🢆🢇🢐🢑🢒🢓🢔🢕🢖🢗🢘🢙🢚🢛🢜🢝🢞🢟🢠🢡🢢🢣🢤🢥🢦🢧🢨🢩🢪🢫🢬🢭🢰🢱🤀🤁🤂🤃🤄🤅🤆🤇🤈🤉🤊🤋🤌🤍🤎🤏🤐🤑🤒🤓🤔🤕🤖🤗🤘🤙🤚🤛🤜🤝🤞🤟🤠🤡🤢🤣🤤🤥🤦🤧🤨🤩🤪🤫🤬🤭🤮🤯🤰🤱🤲🤳🤴🤵🤶🤷🤸🤹🤺🤻🤼🤽🤾🤿🥀🥁🥂🥃🥄🥅🥆🥇🥈🥉🥊🥋🥌🥍🥎🥏🥐🥑🥒🥓🥔🥕🥖🥗🥘🥙🥚🥛🥜🥝🥞🥟🥠🥡🥢🥣🥤🥥🥦🥧🥨🥩🥪🥫🥬🥭🥮🥯🥰🥱🥲🥳🥴🥵🥶🥷🥸🥹🥺🥻🥼🥽🥾🥿🦀🦁🦂🦃🦄🦅🦆🦇🦈🦉🦊🦋🦌🦍🦎🦏🦐🦑🦒🦓🦔🦕🦖🦗🦘🦙🦚🦛🦜🦝🦞🦟🦠🦡🦢🦣🦤🦥🦦🦧🦨🦩🦪🦫🦬🦭🦮🦯🦰🦱🦲🦳🦴🦵🦶🦷🦸🦹🦺🦻🦼🦽🦾🦿🧀🧁🧂🧃🧄🧅🧆🧇🧈🧉🧊🧋🧌🧍🧎🧏🧐🧑🧒🧓🧔🧕🧖🧗🧘🧙🧚🧛🧜🧝🧞🧟🧠🧡🧢🧣🧤🧥🧦🧧🧨🧩🧪🧫🧬🧭🧮🧯🧰🧱🧲🧳🧴🧵🧶🧷🧸🧹🧺🧻🧼🧽🧾🧿🨀🨁🨂🨃🨄🨅🨆🨇🨈🨉🨊🨋🨌🨍🨎🨏🨐🨑🨒🨓🨔🨕🨖🨗🨘🨙🨚🨛🨜🨝🨞🨟🨠🨡🨢🨣🨤🨥🨦🨧🨨🨩🨪🨫🨬🨭🨮🨯🨰🨱🨲🨳🨴🨵🨶🨷🨸🨹🨺🨻🨼🨽🨾🨿🩀🩁🩂🩃🩄🩅🩆🩇🩈🩉🩊🩋🩌🩍🩎🩏🩐🩑🩒🩓🩠🩡🩢🩣🩤🩥🩦🩧🩨🩩🩪🩫🩬🩭🩰🩱🩲🩳🩴🩵🩶🩷🩸🩹🩺🩻🩼🪀🪁🪂🪃🪄🪅🪆🪇🪈🪐🪑🪒🪓🪔🪕🪖🪗🪘🪙🪚🪛🪜🪝🪞🪟🪠🪡🪢🪣🪤🪥🪦🪧🪨🪩🪪🪫🪬🪭🪮🪯🪰🪱🪲🪳🪴🪵🪶🪷🪸🪹🪺🪻🪼🪽🪿🫀🫁🫂🫃🫄🫅🫎🫏🫐🫑🫒🫓🫔🫕🫖🫗🫘🫙🫚🫛🫠🫡🫢🫣🫤🫥🫦🫧🫨🫰🫱🫲🫳🫴🫵🫶🫷🫸🬀🬁🬂🬃🬄🬅🬆🬇🬈🬉🬊🬋🬌🬍🬎🬏🬐🬑🬒🬓🬔🬕🬖🬗🬘🬙🬚🬛🬜🬝🬞🬟🬠🬡🬢🬣🬤🬥🬦🬧🬨🬩🬪🬫🬬🬭🬮🬯🬰🬱🬲🬳🬴🬵🬶🬷🬸🬹🬺🬻🬼🬽🬾🬿🭀🭁🭂🭃🭄🭅🭆🭇🭈🭉🭊🭋🭌🭍🭎🭏🭐🭑🭒🭓🭔🭕🭖🭗🭘🭙🭚🭛🭜🭝🭞🭟🭠🭡🭢🭣🭤🭥🭦🭧🭨🭩🭪🭫🭬🭭🭮🭯🭰🭱🭲🭳🭴🭵🭶🭷🭸🭹🭺🭻🭼🭽🭾🭿🮀🮁🮂🮃🮄🮅🮆🮇🮈🮉🮊🮋🮌🮍🮎🮏🮐🮑🮒🮔🮕🮖🮗🮘🮙🮚🮛🮜🮝🮞🮟🮠🮡🮢🮣🮤🮥🮦🮧🮨🮩🮪🮫🮬🮭🮮🮯🮰🮱🮲🮳🮴🮵🮶🮷🮸🮹🮺🮻🮼🮽🮾🮿🯀🯁🯂🯃🯄🯅🯆🯇🯈🯉🯊"""
 # https://www.compart.com/en/unicode/category
 # https://unicode.org/Public/UNIDATA/UnicodeData.txt
+# NOTE: WAY too large to store as a string of each char
+UNICODE_PUNCT_RANGES = [
+    "\\U00000021-\\U0000002f",
+    "\\U0000003a-\\U00000040",
+    "\\U0000005b-\\U00000060",
+    "\\U0000007b-\\U0000007e",
+    "\\U000000a1-\\U000000a9",
+    "\\U000000ab-\\U000000ac",
+    "\\U000000ae-\\U000000b1",
+    "\\U000000b4",
+    "\\U000000b6-\\U000000b8",
+    "\\U000000bb",
+    "\\U000000bf",
+    "\\U000000d7",
+    "\\U000000f7",
+    "\\U000002c2-\\U000002c5",
+    "\\U000002d2-\\U000002df",
+    "\\U000002e5-\\U000002eb",
+    "\\U000002ed",
+    "\\U000002ef-\\U000002ff",
+    "\\U00000375",
+    "\\U0000037e",
+    "\\U00000384-\\U00000385",
+    "\\U00000387",
+    "\\U000003f6",
+    "\\U00000482",
+    "\\U0000055a-\\U0000055f",
+    "\\U00000589-\\U0000058a",
+    "\\U0000058d-\\U0000058f",
+    "\\U000005be",
+    "\\U000005c0",
+    "\\U000005c3",
+    "\\U000005c6",
+    "\\U000005f3-\\U000005f4",
+    "\\U00000606-\\U0000060f",
+    "\\U0000061b",
+    "\\U0000061d-\\U0000061f",
+    "\\U0000066a-\\U0000066d",
+    "\\U000006d4",
+    "\\U000006de",
+    "\\U000006e9",
+    "\\U000006fd-\\U000006fe",
+    "\\U00000700-\\U0000070d",
+    "\\U000007f6-\\U000007f9",
+    "\\U000007fe-\\U000007ff",
+    "\\U00000830-\\U0000083e",
+    "\\U0000085e",
+    "\\U00000888",
+    "\\U00000964-\\U00000965",
+    "\\U00000970",
+    "\\U000009f2-\\U000009f3",
+    "\\U000009fa-\\U000009fb",
+    "\\U000009fd",
+    "\\U00000a76",
+    "\\U00000af0-\\U00000af1",
+    "\\U00000b70",
+    "\\U00000bf3-\\U00000bfa",
+    "\\U00000c77",
+    "\\U00000c7f",
+    "\\U00000c84",
+    "\\U00000d4f",
+    "\\U00000d79",
+    "\\U00000df4",
+    "\\U00000e3f",
+    "\\U00000e4f",
+    "\\U00000e5a-\\U00000e5b",
+    "\\U00000f01-\\U00000f17",
+    "\\U00000f1a-\\U00000f1f",
+    "\\U00000f34",
+    "\\U00000f36",
+    "\\U00000f38",
+    "\\U00000f3a-\\U00000f3d",
+    "\\U00000f85",
+    "\\U00000fbe-\\U00000fc5",
+    "\\U00000fc7-\\U00000fcc",
+    "\\U00000fce-\\U00000fda",
+    "\\U0000104a-\\U0000104f",
+    "\\U0000109e-\\U0000109f",
+    "\\U000010fb",
+    "\\U00001360-\\U00001368",
+    "\\U00001390-\\U00001399",
+    "\\U00001400",
+    "\\U0000166d-\\U0000166e",
+    "\\U0000169b-\\U0000169c",
+    "\\U000016eb-\\U000016ed",
+    "\\U00001735-\\U00001736",
+    "\\U000017d4-\\U000017d6",
+    "\\U000017d8-\\U000017db",
+    "\\U00001800-\\U0000180a",
+    "\\U00001940",
+    "\\U00001944-\\U00001945",
+    "\\U000019de-\\U000019ff",
+    "\\U00001a1e-\\U00001a1f",
+    "\\U00001aa0-\\U00001aa6",
+    "\\U00001aa8-\\U00001aad",
+    "\\U00001b5a-\\U00001b6a",
+    "\\U00001b74-\\U00001b7e",
+    "\\U00001bfc-\\U00001bff",
+    "\\U00001c3b-\\U00001c3f",
+    "\\U00001c7e-\\U00001c7f",
+    "\\U00001cc0-\\U00001cc7",
+    "\\U00001cd3",
+    "\\U00001fbd",
+    "\\U00001fbf-\\U00001fc1",
+    "\\U00001fcd-\\U00001fcf",
+    "\\U00001fdd-\\U00001fdf",
+    "\\U00001fed-\\U00001fef",
+    "\\U00001ffd-\\U00001ffe",
+    "\\U00002010-\\U00002027",
+    "\\U00002030-\\U0000205e",
+    "\\U0000207a-\\U0000207e",
+    "\\U0000208a-\\U0000208e",
+    "\\U000020a0-\\U000020c0",
+    "\\U00002100-\\U00002101",
+    "\\U00002103-\\U00002106",
+    "\\U00002108-\\U00002109",
+    "\\U00002114",
+    "\\U00002116-\\U00002118",
+    "\\U0000211e-\\U00002123",
+    "\\U00002125",
+    "\\U00002127",
+    "\\U00002129",
+    "\\U0000212e",
+    "\\U0000213a-\\U0000213b",
+    "\\U00002140-\\U00002144",
+    "\\U0000214a-\\U0000214d",
+    "\\U0000214f",
+    "\\U0000218a-\\U0000218b",
+    "\\U00002190-\\U00002426",
+    "\\U00002440-\\U0000244a",
+    "\\U0000249c-\\U000024b5",
+    "\\U00002500-\\U00002775",
+    "\\U00002794-\\U00002b73",
+    "\\U00002b76-\\U00002b95",
+    "\\U00002b97-\\U00002bff",
+    "\\U00002ce5-\\U00002cea",
+    "\\U00002cf9-\\U00002cfc",
+    "\\U00002cfe-\\U00002cff",
+    "\\U00002d70",
+    "\\U00002e00-\\U00002e2e",
+    "\\U00002e30-\\U00002e5d",
+    "\\U00002e80-\\U00002e99",
+    "\\U00002e9b-\\U00002ef3",
+    "\\U00002f00-\\U00002fd5",
+    "\\U00002ff0-\\U00002fff",
+    "\\U00003001-\\U00003004",
+    "\\U00003008-\\U00003020",
+    "\\U00003030",
+    "\\U00003036-\\U00003037",
+    "\\U0000303d-\\U0000303f",
+    "\\U0000309b-\\U0000309c",
+    "\\U000030a0",
+    "\\U000030fb",
+    "\\U00003190-\\U00003191",
+    "\\U00003196-\\U0000319f",
+    "\\U000031c0-\\U000031e3",
+    "\\U000031ef",
+    "\\U00003200-\\U0000321e",
+    "\\U0000322a-\\U00003247",
+    "\\U00003250",
+    "\\U00003260-\\U0000327f",
+    "\\U0000328a-\\U000032b0",
+    "\\U000032c0-\\U000033ff",
+    "\\U00004dc0-\\U00004dff",
+    "\\U0000a490-\\U0000a4c6",
+    "\\U0000a4fe-\\U0000a4ff",
+    "\\U0000a60d-\\U0000a60f",
+    "\\U0000a673",
+    "\\U0000a67e",
+    "\\U0000a6f2-\\U0000a6f7",
+    "\\U0000a700-\\U0000a716",
+    "\\U0000a720-\\U0000a721",
+    "\\U0000a789-\\U0000a78a",
+    "\\U0000a828-\\U0000a82b",
+    "\\U0000a836-\\U0000a839",
+    "\\U0000a874-\\U0000a877",
+    "\\U0000a8ce-\\U0000a8cf",
+    "\\U0000a8f8-\\U0000a8fa",
+    "\\U0000a8fc",
+    "\\U0000a92e-\\U0000a92f",
+    "\\U0000a95f",
+    "\\U0000a9c1-\\U0000a9cd",
+    "\\U0000a9de-\\U0000a9df",
+    "\\U0000aa5c-\\U0000aa5f",
+    "\\U0000aa77-\\U0000aa79",
+    "\\U0000aade-\\U0000aadf",
+    "\\U0000aaf0-\\U0000aaf1",
+    "\\U0000ab5b",
+    "\\U0000ab6a-\\U0000ab6b",
+    "\\U0000abeb",
+    "\\U0000fb29",
+    "\\U0000fbb2-\\U0000fbc2",
+    "\\U0000fd3e-\\U0000fd4f",
+    "\\U0000fdcf",
+    "\\U0000fdfc-\\U0000fdff",
+    "\\U0000fe10-\\U0000fe19",
+    "\\U0000fe30-\\U0000fe52",
+    "\\U0000fe54-\\U0000fe66",
+    "\\U0000fe68-\\U0000fe6b",
+    "\\U0000ff01-\\U0000ff0f",
+    "\\U0000ff1a-\\U0000ff20",
+    "\\U0000ff3b-\\U0000ff40",
+    "\\U0000ff5b-\\U0000ff65",
+    "\\U0000ffe0-\\U0000ffe6",
+    "\\U0000ffe8-\\U0000ffee",
+    "\\U0000fffc-\\U0000fffd",
+    "\\U00010100-\\U00010102",
+    "\\U00010137-\\U0001013f",
+    "\\U00010179-\\U00010189",
+    "\\U0001018c-\\U0001018e",
+    "\\U00010190-\\U0001019c",
+    "\\U000101a0",
+    "\\U000101d0-\\U000101fc",
+    "\\U0001039f",
+    "\\U000103d0",
+    "\\U0001056f",
+    "\\U00010857",
+    "\\U00010877-\\U00010878",
+    "\\U0001091f",
+    "\\U0001093f",
+    "\\U00010a50-\\U00010a58",
+    "\\U00010a7f",
+    "\\U00010ac8",
+    "\\U00010af0-\\U00010af6",
+    "\\U00010b39-\\U00010b3f",
+    "\\U00010b99-\\U00010b9c",
+    "\\U00010ead",
+    "\\U00010f55-\\U00010f59",
+    "\\U00010f86-\\U00010f89",
+    "\\U00011047-\\U0001104d",
+    "\\U000110bb-\\U000110bc",
+    "\\U000110be-\\U000110c1",
+    "\\U00011140-\\U00011143",
+    "\\U00011174-\\U00011175",
+    "\\U000111c5-\\U000111c8",
+    "\\U000111cd",
+    "\\U000111db",
+    "\\U000111dd-\\U000111df",
+    "\\U00011238-\\U0001123d",
+    "\\U000112a9",
+    "\\U0001144b-\\U0001144f",
+    "\\U0001145a-\\U0001145b",
+    "\\U0001145d",
+    "\\U000114c6",
+    "\\U000115c1-\\U000115d7",
+    "\\U00011641-\\U00011643",
+    "\\U00011660-\\U0001166c",
+    "\\U000116b9",
+    "\\U0001173c-\\U0001173f",
+    "\\U0001183b",
+    "\\U00011944-\\U00011946",
+    "\\U000119e2",
+    "\\U00011a3f-\\U00011a46",
+    "\\U00011a9a-\\U00011a9c",
+    "\\U00011a9e-\\U00011aa2",
+    "\\U00011b00-\\U00011b09",
+    "\\U00011c41-\\U00011c45",
+    "\\U00011c70-\\U00011c71",
+    "\\U00011ef7-\\U00011ef8",
+    "\\U00011f43-\\U00011f4f",
+    "\\U00011fd5-\\U00011ff1",
+    "\\U00011fff",
+    "\\U00012470-\\U00012474",
+    "\\U00012ff1-\\U00012ff2",
+    "\\U00016a6e-\\U00016a6f",
+    "\\U00016af5",
+    "\\U00016b37-\\U00016b3f",
+    "\\U00016b44-\\U00016b45",
+    "\\U00016e97-\\U00016e9a",
+    "\\U00016fe2",
+    "\\U0001bc9c",
+    "\\U0001bc9f",
+    "\\U0001cf50-\\U0001cfc3",
+    "\\U0001d000-\\U0001d0f5",
+    "\\U0001d100-\\U0001d126",
+    "\\U0001d129-\\U0001d164",
+    "\\U0001d16a-\\U0001d16c",
+    "\\U0001d183-\\U0001d184",
+    "\\U0001d18c-\\U0001d1a9",
+    "\\U0001d1ae-\\U0001d1ea",
+    "\\U0001d200-\\U0001d241",
+    "\\U0001d245",
+    "\\U0001d300-\\U0001d356",
+    "\\U0001d6c1",
+    "\\U0001d6db",
+    "\\U0001d6fb",
+    "\\U0001d715",
+    "\\U0001d735",
+    "\\U0001d74f",
+    "\\U0001d76f",
+    "\\U0001d789",
+    "\\U0001d7a9",
+    "\\U0001d7c3",
+    "\\U0001d800-\\U0001d9ff",
+    "\\U0001da37-\\U0001da3a",
+    "\\U0001da6d-\\U0001da74",
+    "\\U0001da76-\\U0001da83",
+    "\\U0001da85-\\U0001da8b",
+    "\\U0001e14f",
+    "\\U0001e2ff",
+    "\\U0001e95e-\\U0001e95f",
+    "\\U0001ecac",
+    "\\U0001ecb0",
+    "\\U0001ed2e",
+    "\\U0001eef0-\\U0001eef1",
+    "\\U0001f000-\\U0001f02b",
+    "\\U0001f030-\\U0001f093",
+    "\\U0001f0a0-\\U0001f0ae",
+    "\\U0001f0b1-\\U0001f0bf",
+    "\\U0001f0c1-\\U0001f0cf",
+    "\\U0001f0d1-\\U0001f0f5",
+    "\\U0001f10d-\\U0001f12f",
+    "\\U0001f14a-\\U0001f14f",
+    "\\U0001f16a-\\U0001f16f",
+    "\\U0001f18a-\\U0001f1ad",
+    "\\U0001f1e6-\\U0001f202",
+    "\\U0001f210-\\U0001f23b",
+    "\\U0001f240-\\U0001f248",
+    "\\U0001f250-\\U0001f251",
+    "\\U0001f260-\\U0001f265",
+    "\\U0001f300-\\U0001f6d7",
+    "\\U0001f6dc-\\U0001f6ec",
+    "\\U0001f6f0-\\U0001f6fc",
+    "\\U0001f700-\\U0001f776",
+    "\\U0001f77b-\\U0001f7d9",
+    "\\U0001f7e0-\\U0001f7eb",
+    "\\U0001f7f0",
+    "\\U0001f800-\\U0001f80b",
+    "\\U0001f810-\\U0001f847",
+    "\\U0001f850-\\U0001f859",
+    "\\U0001f860-\\U0001f887",
+    "\\U0001f890-\\U0001f8ad",
+    "\\U0001f8b0-\\U0001f8b1",
+    "\\U0001f900-\\U0001fa53",
+    "\\U0001fa60-\\U0001fa6d",
+    "\\U0001fa70-\\U0001fa7c",
+    "\\U0001fa80-\\U0001fa88",
+    "\\U0001fa90-\\U0001fabd",
+    "\\U0001fabf-\\U0001fac5",
+    "\\U0001face-\\U0001fadb",
+    "\\U0001fae0-\\U0001fae8",
+    "\\U0001faf0-\\U0001faf8",
+    "\\U0001fb00-\\U0001fb92",
+    "\\U0001fb94-\\U0001fbca",
+    "\\U000f1990-\\U000f199d",  # UCSUR punctuation
+]
+
+UCSUR_PUNCT_RANGES = UNICODE_PUNCT_RANGES[-1]  # NOTE: THIS CAN CHANGE
+
+UNICODE_PUNCT = find_unicode_chars(UNICODE_PUNCT_RANGES)
+# this is a large string.
 
 # `\p{posix_punct}` character class
 POSIX_PUNCT = r"""-!"#$%&'()*+,./:;<=>?@[\]^_`{|}~"""
-ALL_PUNCT_RANGES = "".join(find_unicode_ranges(POSIX_PUNCT + UNICODE_PUNCT))
+POSIX_PUNCT_RANGES = find_unicode_ranges(POSIX_PUNCT)
+
+ALL_PUNCT = "".join(sorted(list(set(POSIX_PUNCT + UNICODE_PUNCT))))
+ALL_PUNCT_RANGES = "".join(find_unicode_ranges(ALL_PUNCT))
+# combined bc the result could be simpler
+
 SENTENCE_PUNCT = """.?!:;'"()[-]“”·…"""
 
 
@@ -35,38 +390,84 @@ ALLOWABLES = {
     "wxw",  # wile ala wile
 }
 
+IGNORABLES = {
+    # o, e, n are not here bc they're not frequently problematic in english messages
+    "a",
+    "am",
+    "an",
+    "i",
+    "in",
+    "is",
+    "l",  # they'll
+    "m",  # i'm
+    "me",
+    "no",
+    "s",  # let's
+    "so",
+    "t",  # don't
+    "to",
+    "u",  # you
+    "we",
+    "un",  # un-
+    "use",
+    "some",
+    "like",
+}
+
+UCSUR_RANGES = [
+    "\\U000F1900-\\U000F1977",  # pu
+    "\\U000F1978-\\U000F1988",  # ku suli
+    "\\U000F19A0-\\U000F19A3",  # ku lili
+]
+NIMI_UCSUR = find_unicode_chars(UCSUR_RANGES)
+
+
+# NIMI_PU_UCSUR_RANGES = ["\\U000F1900-\\U000F1977"]
+# NIMI_PU_ALE_UCSUR_RANGES = NIMI_PU_UCSUR_RANGES + ["\\U000F1978-\\U000F197A"]
+
+
+def category_helper(data: Dict[str, Dict[str, str]], key: str, value: str) -> List[str]:
+    return [d["word"] for d in data.values() if d[key] == value]
+
+
 with open(LINKU) as f:
     linku: Dict[str, Dict[str, str]] = json.loads(f.read())
-    NIMI_PU: List[str] = [d["word"] for d in linku.values() if d["book"] == "pu"]
+    NIMI_PU: List[str] = category_helper(linku, "book", "pu")
     NIMI_PU_SYNONYMS: List[str] = ["namako", "kin", "oko"]
-    NIMI_LINKU: List[str] = [
-        d["word"] for d in linku.values() if d["usage_category"] in ["core", "common"]
-    ]
-    NIMI_LINKU_LILI: List[str] = [
-        d["word"]
-        for d in linku.values()
-        if d["usage_category"] not in ["core", "common"]
-    ]
+
+    NIMI_KU_SULI = category_helper(linku, "book", "ku suli")
+    NIMI_KU_LILI = category_helper(linku, "book", "ku lili")
+
+    NIMI_LINKU_CORE = category_helper(linku, "usage_category", "core")
+    NIMI_LINKU_COMMON = category_helper(linku, "usage_category", "common")
+    NIMI_LINKU_UNCOMMON = category_helper(linku, "usage_category", "uncommon")
+    NIMI_LINKU_OBSCURE = category_helper(linku, "usage_category", "obscure")
 
 with open(SANDBOX) as f:
     sandbox: Dict[str, Dict[str, str]] = json.loads(f.read())
-    NIMI_LINKU_SANDBOX: List[str] = NIMI_LINKU_LILI + [
-        d["word"] for d in sandbox.values()
-    ]
+    NIMI_LINKU_SANDBOX: List[str] = [d["word"] for d in sandbox.values()]
 
 del linku
 del sandbox
 
 __all__ = [
+    "ALLOWABLES",
+    "ALL_PUNCT",
+    "ALL_PUNCT_RANGES",
     "ALPHABET",
     "CONSONANTS",
-    "NIMI_LINKU",
-    "NIMI_LINKU_LILI",
+    "NIMI_KU_LILI",
+    "NIMI_KU_SULI",
+    "NIMI_LINKU_COMMON",
+    "NIMI_LINKU_CORE",
+    "NIMI_LINKU_OBSCURE",
     "NIMI_LINKU_SANDBOX",
+    "NIMI_LINKU_UNCOMMON",
     "NIMI_PU",
     "NIMI_PU_SYNONYMS",
-    "VOWELS",
-    "UNICODE_PUNCT",
-    "ALLOWABLES",
     "POSIX_PUNCT",
+    "POSIX_PUNCT_RANGES",
+    "UNICODE_PUNCT",
+    "UNICODE_PUNCT_RANGES",
+    "VOWELS",
 ]

sonatoki/utils.py

@@ -1,10 +1,23 @@
 # STL
 import re
-from typing import List
+from typing import Set, List, Iterable
+
+# LOCAL
+from sonatoki.Cleaners import Lowercase, ConsecutiveDuplicates
 
 TO_ESCAPE = ["\\", "^", "[", "]", "-"]
 
 
+def prep_dictionary(words: Iterable[str]) -> Set[str]:
+    out: Set[str] = set()
+    cleaners = [Lowercase, ConsecutiveDuplicates]
+    for word in words:
+        for c in cleaners:
+            word = c.clean(word)
+        out.add(word)
+    return out
+
+
 def regex_escape(s: str) -> str:
     """Escape all characters which must be escaped when embedded in a character class."""
     for c in TO_ESCAPE:
@@ -43,12 +56,37 @@ def find_unicode_ranges(chars: str) -> List[str]:
     return ranges
 
 
+def find_unicode_chars(ranges: List[str]) -> str:
+    result: List[str] = []
+    for item in ranges:
+        if "-" in item:
+            start, end = item.split("-")
+            start = int(start.lstrip("\\U"), 16)
+            end = int(end.lstrip("\\U"), 16)
+            result.extend(chr(code_point) for code_point in range(start, end + 1))
+        else:
+            result.append(chr(int(item.lstrip("\\U"), 16)))
+    return "".join(result)
+
+
 if __name__ == "__main__":
     """
     Helper script to fetch UNICODE_PUNCT in constants.py
     """
 
-    PUNCT_CATEGORIES = {"Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps", "Sm", "Sk",  "Sc", "So"}
+    PUNCT_CATEGORIES = {
+        "Pc",
+        "Pd",
+        "Pe",
+        "Pf",
+        "Pi",
+        "Po",
+        "Ps",
+        "Sm",
+        "Sk",
+        "Sc",
+        "So",
+    }
     # Connector, Dash, Close (end), Final, Initial, Other, Open (sOpen), Math, Modifier (kModifier), Currency, Other
 
     # NOTE: UnicodeData.txt lists character ranges if there would be many characters.

{sonatoki-0.2.2.dist-info → sonatoki-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sonatoki
-Version: 0.2.2
+Version: 0.3.1
 Summary: ilo li moku e toki li pana e sona ni: ni li toki ala toki pona?
 Author-Email: "jan Kekan San (@gregdan3)" <gregory.danielson3@gmail.com>
 License: AGPL-3.0-or-later
@@ -12,15 +12,22 @@ Description-Content-Type: text/markdown
 
 # sona toki
 
+<div align="center">
+
+![Test workflow for this library](https://github.com/gregdan3/sona-toki/workflows/Tests/badge.svg)
+[![Version number for this library](https://img.shields.io/pypi/v/sonatoki?logo=python&logoColor=%23cccccc)](https://pypi.org/project/sonatoki)
+
+</div>
+
 ## What is **sona toki**?
 
-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.
+This library, "Language Knowledge," helps you identify whether a message is in Toki Pona. It does so by determining whether a large enough number of words in a statement are "in Toki Pona". No grammar checking, yet.
 
-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.
+I wrote this library 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 now uses this library to great success!
 
-If you've ever worked on a similar project, you know the question "is this message in [language]" is not a consistent one- the environment, time, preferences of the speaker, and much more, can all alter whether a given message is "in" any specific language, and this question applies to Toki Pona too.
+If you've ever worked on a similar project, you know the question "is this message in [language]" is not a consistent one- the environment, time, preferences of the speaker, and much more, can all alter whether a given message is "in" any specific language. This complexity applies to Toki Pona too.
 
-This project "solves" that complex problem by offering a highly configurable parser, so you can tune it to your preferences and goals.
+So, this project "solves" that complex problem by offering an opinionated tokenizer and a configurable parser, allowing you to tune its output to your preferences and goals. [Even silly ones.](https://sona.pona.la/wiki/isipin_epiku).
 
 ## Quick Start
 
@@ -53,12 +60,12 @@ Or if you'd prefer to configure on your own:
 from copy import deepcopy
 from sonatoki.ilo import Ilo
 from sonatoki.Configs import BaseConfig
-from sonatoki.Filters import NimiPuAle, Phonotactic, ProperName
+from sonatoki.Filters import NimiLinkuCore, Phonotactic, ProperName
 from sonatoki.Scorers import SoftPassFail
 
 def main():
     config = deepcopy(BaseConfig)
-    config["scoring_filters"].extend([NimiPuAle, Phonotactic, ProperName])
+    config["scoring_filters"].extend([NimiLinkuCore, Phonotactic, ProperName])
     config["scorer"] = SoftPassFail
 
     ilo = Ilo(**config)
@@ -88,24 +95,28 @@ After our proposal has been examined and a result given by the committee, I will
 
 ### What's the deal with the tokenizers?
 
-The Toki Pona tokenizer `word_tokenize_tok` is very specific in always separating writing characters from punctuation, and leaving contiguous punctuation as contiguous- this is a level of precision that NLTK's English tokenizer does not want for several reasons, such as that English words can have "punctuation" characters in them.
-
-Toki Pona doesn't have any mid-word symbols when rendered in the Latin alphabet, so a more aggressive tokenizer is highly desirable.
+The Toki Pona tokenizer `sonatoki.Tokenizers.WordTokenizer` has the goal of tokenizing statements such that every token either represents a word candidate ("toki", "mumumu") or a complete non-candidate ("..!", "123").
+This design is highly undesirable for NLTK's English tokenizer because English words can have "punctuation" characters in them.
+But Toki Pona doesn't have any mid-word symbols when rendered in the Latin alphabet or in [Private Use Area Unicode characters](https://www.kreativekorp.com/ucsur/), so a more aggressive tokenizer is highly desirable.
 
-The other tokenizers are provided as a comparison case more than anything. I do not recommend their use.
+The goal of splitting into word candidates and non-candidates is important, because any [encoding of Toki Pona's logographic script](https://www.kreativekorp.com/ucsur/charts/sitelen.html) will require each character be split into its own token, where the default behavior would be to leave consecutive non-punctuation together.
 
 ### Aren't there a lot of false positives?
 
-Yes. It's up to you to use this tool responsibly on input you've done your best to clean, and better, use stronger filters before weaker ones. For now though, here's a list of relevant false positives:
+Yes, depending on the filter you choose and how you apply it.
+It's up to you to use this tool responsibly on input you've done your best to clean, such as by using stronger filters before weaker ones.
+For now though, here's a list of relevant false positives:
 
-- `ProperName` will errantly match text in languages without a capital/lowercase distinction, artificially inflating the scores.
-- `Alphabetic` will match a _lot_ of undesirable text- it essentially allows 14 letters of the English alphabet.
+- `ProperName` will errantly match text in languages without a capital/lowercase distinction, artificially increasing scores.
+- `Alphabetic` will match a _lot_ of undesirable text- it essentially allows 14 letters of the English alphabet. For example, "I'm well" would match as _three_ words: "i", "m", "well".
+- `NimiPu` and other sets containing `a`, `mute`, `open`, and others will unavoidably match those words in English text too.
 
 ### Don't some of the cleaners/filters conflict?
 
-Yes. Some do so
+Yes, though not terribly much.
 
 - `ConsecutiveDuplicates` may errantly change a word's validity. For example, "manna" is phonotactically invalid in Toki Pona, but would become "mana" which is valid.
-- `ConsecutiveDuplicates` will not work correctly with syllabaries (alphabets, but representing a pair of consonant and vowel).
+- `ConsecutiveDuplicates` will not work correctly with syllabaries, though this should not change the validity of the analyzed word unless you attempt to dictionary match these words.
+- If you build your own `MemberFilter` with words that have capital letters or consecutive duplicates, they will never match unless you use `prep_dictionary`.
 
-You'll notice a _lot_ of these are troubles regarding the application of latin alphabet filters to non-latin text. Working on it!
+You'll notice these are mostly casued by applying latin alphabet filters to non-latin text. Working on it!

sonatoki-0.3.1.dist-info/RECORD

@@ -0,0 +1,18 @@
+sonatoki-0.3.1.dist-info/METADATA,sha256=nWomuM-AeE98VwnWen7qffNclw8emxAf-oFtXwba8wI,6341
+sonatoki-0.3.1.dist-info/WHEEL,sha256=vnE8JVcI2Wz7GRKorsPArnBdnW2SWKWGow5gu5tHlRU,90
+sonatoki-0.3.1.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+sonatoki/Cleaners.py,sha256=m0j1a1vs9Mdqp724r9Xfh1Y_tyP6GYCkihv8rH8m7lA,1871
+sonatoki/Configs.py,sha256=NS1_esoDNna8LyH_9bPMkxbo2sMSilYhG1PwYLdq6L8,3402
+sonatoki/Filters.py,sha256=-j5xSZ8URjqalQVGMBabMvJ5ofZWazfN7YPfXkM_4uQ,9429
+sonatoki/Preprocessors.py,sha256=aMXXuFBDlJudvzvukvCa7BixuROXXEb62un7I-TGOGs,4441
+sonatoki/Scorers.py,sha256=W-1uYiqjsDejJzoe592ixs7wHazjJXPhuo-41zuJ26U,3643
+sonatoki/Tokenizers.py,sha256=So5_Tu6J98MD3yVcwB_X3lw2uMG0TN6XHcTbQjFCu5Q,4254
+sonatoki/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sonatoki/__main__.py,sha256=6xc-wIrrFo9wTyn4zRQNAmqwmJBtVvCMwV-CrM-hueA,82
+sonatoki/constants.py,sha256=XTFmEcnLBXwdYXjTq_EuW9e_TWLtnNLz2vFCf8m-sz0,12844
+sonatoki/ilo.py,sha256=yyLgNPI0Hmb4f1BzX6IRHr11FPChfL2xDR_9odlr8_8,3849
+sonatoki/linku.json,sha256=B5KNdhyM5UEfMciROgh1ECHr3i-ASBeMvwrkzNJX47c,271013
+sonatoki/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sonatoki/sandbox.json,sha256=hx6LRsfvmmTtqXcXIyCsfSaGK3DZ-GCdbM8xhZQBHoA,77650
+sonatoki/utils.py,sha256=OMaRyoNvKGKYQCBDjQyaCI58-wMpQ0wrrNjTJKsEZ9Y,3550
+sonatoki-0.3.1.dist-info/RECORD,,

sonatoki-0.2.2.dist-info/RECORD

@@ -1,17 +0,0 @@
-sonatoki-0.2.2.dist-info/METADATA,sha256=XhDkXgLI0iFR0ceadVnXNUBlA6DcXkfVmZHxycL1tNA,5160
-sonatoki-0.2.2.dist-info/WHEEL,sha256=vnE8JVcI2Wz7GRKorsPArnBdnW2SWKWGow5gu5tHlRU,90
-sonatoki-0.2.2.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-sonatoki/Cleaners.py,sha256=AMonXBUk3w1vdRiDrpB9XJAdjYaMPoqRtdX5oLI6r38,1744
-sonatoki/Configs.py,sha256=5mucu-Zsnt2p7GMiaM7GXUeL1F1fBq9sycjm4V7xsrI,1929
-sonatoki/Filters.py,sha256=qUhPWxAnNvQV9hCPJNu5RKGpx-_hWFvmL5Ab2-j_peo,5342
-sonatoki/Preprocessors.py,sha256=aMXXuFBDlJudvzvukvCa7BixuROXXEb62un7I-TGOGs,4441
-sonatoki/Scorers.py,sha256=W-1uYiqjsDejJzoe592ixs7wHazjJXPhuo-41zuJ26U,3643
-sonatoki/Tokenizers.py,sha256=zJ_5h9dlDIiJlLc6inuiOodWYt52nD83wS0QwSZixiM,3326
-sonatoki/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sonatoki/__main__.py,sha256=6xc-wIrrFo9wTyn4zRQNAmqwmJBtVvCMwV-CrM-hueA,82
-sonatoki/constants.py,sha256=pOa1wb7B8w8RN772FcO5AYqqQAWlhbuLWM3N_sYlkdU,31232
-sonatoki/ilo.py,sha256=yyLgNPI0Hmb4f1BzX6IRHr11FPChfL2xDR_9odlr8_8,3849
-sonatoki/linku.json,sha256=B5KNdhyM5UEfMciROgh1ECHr3i-ASBeMvwrkzNJX47c,271013
-sonatoki/sandbox.json,sha256=hx6LRsfvmmTtqXcXIyCsfSaGK3DZ-GCdbM8xhZQBHoA,77650
-sonatoki/utils.py,sha256=jDwjRg-QpRIBalF65vIQWsX8wFLsITStihwfqimY-5E,2670
-sonatoki-0.2.2.dist-info/RECORD,,