Update spaCy pipeline

.gitattributes

@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+grc_dep_treebanks_xlm-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+frequency_lemmatizer/table.json filter=lfs diff=lfs merge=lfs -text
+morphologizer/model filter=lfs diff=lfs merge=lfs -text
+trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
+trainable_lemmatizer/trees filter=lfs diff=lfs merge=lfs -text
+tagger/model filter=lfs diff=lfs merge=lfs -text
+parser/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

config.cfg

@@ -0,0 +1,228 @@
+[paths]
+train = "corpus/joint/train.spacy"
+test = null
+dev = "corpus/joint/dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "grc"
+pipeline = ["transformer","tagger","morphologizer","parser","trainable_lemmatizer","frequency_lemmatizer"]
+batch_size = 8
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.frequency_lemmatizer]
+factory = "frequency_lemmatizer"
+fallback_priority = "lookup"
+overwrite = true
+
+[components.morphologizer]
+factory = "morphologizer"
+extend = false
+overwrite = true
+scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
+
+[components.morphologizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.morphologizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.parser]
+factory = "parser"
+learn_tokens = false
+min_action_freq = 30
+moves = null
+scorer = {"@scorers":"spacy.parser_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.parser.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "parser"
+extra_state_tokens = false
+hidden_width = 128
+maxout_pieces = 3
+use_upper = true
+nO = null
+
+[components.parser.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.tagger]
+factory = "tagger"
+neg_prefix = "!"
+overwrite = false
+scorer = {"@scorers":"spacy.tagger_scorer.v1"}
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 1
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 3
+
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "xlm-roberta-base"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 500
+buffer = 256
+get_length = null
+
+[training.logger]
+@loggers = "spacy.WandbLogger.v3"
+project_name = "homerCy"
+remove_config_values = []
+model_log_interval = null
+log_dataset_dir = null
+entity = null
+run_name = null
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = true
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+tag_acc = 0.21
+pos_acc = 0.1
+morph_acc = 0.1
+morph_per_feat = null
+dep_uas = 0.1
+dep_las = 0.1
+dep_las_per_type = null
+sents_p = null
+sents_r = null
+sents_f = 0.0
+lemma_acc = 0.4
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.components.frequency_lemmatizer]
+
+[initialize.components.frequency_lemmatizer.lookup]
+@readers = "srsly.read_json.v1"
+path = "assets/lemmas/lemma_lookup.json"
+
+[initialize.components.frequency_lemmatizer.table]
+@readers = "srsly.read_json.v1"
+path = "assets/lemmas/lemma_table.json"
+
+[initialize.tokenizer]

frequency_lemmatizer/config.json

@@ -0,0 +1 @@
+{"overwrite": true, "fallback_priority": "lookup"}

frequency_lemmatizer/table.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4678164e1be8f5de58fea33c1a25f57c348012986f69762dc6fde547f955ad
+size 26885581

grc_dep_treebanks_xlm-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba03e52d8246f27d441c3db872cc65f100eae01e2e6c95c52f6fcc5b250d58b4
+size 910823635

lemmatizer.py

@@ -0,0 +1,271 @@
+import os
+import json
+from pathlib import Path
+from typing import Dict, List, Literal, Optional, Union, Iterable
+from typing_extensions import TypedDict, NotRequired
+
+from spacy.language import Language
+from spacy.pipeline import Pipe
+from spacy.pipeline.lemmatizer import lemmatizer_score
+from spacy.util import ensure_path
+from spacy.tokens import Doc, Token
+
+MATCH_ORDER = [
+    "upos",
+    "Tense",
+    "VerbForm",
+    "Voice",
+    "Case",
+    "Gender",
+    "Number",
+    "Degree",
+    "Mood",
+    "Person",
+    "Aspect",
+    "Definite",
+    "PronType",
+    "Polarity",
+    "Poss",
+    "Reflex",
+]
+
+
+class TableEntry(TypedDict):
+    form: str
+    lemma: str
+    upos: str
+    frequency: int
+    Tense: NotRequired[str]
+    VerbForm: NotRequired[str]
+    Voice: NotRequired[str]
+    Case: NotRequired[str]
+    Gender: NotRequired[str]
+    Number: NotRequired[str]
+    Degree: NotRequired[str]
+    Mood: NotRequired[str]
+    Person: NotRequired[str]
+    Aspect: NotRequired[str]
+    Definite: NotRequired[str]
+    PronType: NotRequired[str]
+    Polarity: NotRequired[str]
+    Poss: NotRequired[str]
+    Reflex: NotRequired[str]
+
+
+FrequencyTable = Dict[str, List[TableEntry]]
+
+LookupTable = Dict[str, str]
+
+
+@Language.factory(
+    "frequency_lemmatizer",
+    assigns=["token.lemma"],
+    default_config={
+        "overwrite": True,
+        "fallback_priority": "lookup",
+    },
+    default_score_weights={"lemma_acc": 1.0},
+)
+def make_lemmatizer(
+    nlp: Language,
+    name: str,
+    overwrite: bool,
+    fallback_priority: Literal["lemma", "lookup"],
+):
+    return FrequencyLemmatizer(
+        nlp=nlp,
+        name=name,
+        overwrite=overwrite,
+        fallback_priority=fallback_priority,
+    )  # type: ignore
+
+
+def max_freq_lemma(entries: List[TableEntry]) -> str:
+    """Returns lemma with highest frequency from the given entries."""
+    max_index = 0
+    n_entries = len(entries)
+    for index in range(1, n_entries):
+        if entries[index]["frequency"] > entries[max_index]["frequency"]:
+            max_index = index
+    return entries[max_index]["lemma"]
+
+
+def match_lemma(
+    token_entry: TableEntry, table: FrequencyTable
+) -> Optional[str]:
+    """Returns a lemma for a token if it
+    can be found in the frequency table.
+    """
+    # Tries to find the entries associated with the token in the table
+    match = table.get(token_entry["form"], [])
+    if not match:
+        return None
+    # We go through all the properties to be matched
+    for match_property in MATCH_ORDER:
+        match_new = [
+            entry
+            for entry in match
+            if entry.get(match_property, "")
+            == token_entry.get(match_property, "")
+        ]
+        if not match_new:
+            return max_freq_lemma(entries=match)
+        match = match_new
+    return max_freq_lemma(entries=match)
+
+
+def read_json(path: str) -> Dict:
+    with open(path) as file:
+        res = json.load(file)
+    return res
+
+
+def write_json(object: Dict, path: str) -> None:
+    with open(path, "w") as file:
+        json.dump(object, file)
+
+
+class FrequencyLemmatizer(Pipe):
+    """
+    Part-of-speech and morphology, and frequency
+    sensitive rule-based lemmatizer.
+
+    Parameters
+    ----------
+    overwrite: bool, default True
+        Specifies whether the frequency lemmatizer should overwrite
+        already assigned lemmas.
+    fallback_priority: 'lemma' or 'lookup', default 'lookup'
+        Specifies which fallback should have higher priority
+            if the lemma is not found in
+        the primary table.
+    """
+
+    def __init__(
+        self,
+        nlp: Language,
+        name: str = "freq_lemmatizer",
+        *,
+        overwrite: bool = True,
+        fallback_priority: Literal["lemma", "lookup"] = "lookup",
+    ):
+        self.name = name
+        self.overwrite = overwrite
+        self.scorer = lemmatizer_score
+        self.fallback_priority = fallback_priority
+
+    def initialize(
+        self,
+        get_examples=None,
+        *,
+        nlp=None,
+        table: Optional[FrequencyTable] = None,
+        lookup: Optional[LookupTable] = None,
+    ) -> None:
+        """Initializes the frequency lemmatizer from given lemma table and lookup.
+
+        Parameters
+        ----------
+        table: iterable of entries or None, default None
+            Iterable of all entries in the lemma table
+            with pos tags morph features and frequencies.
+        lookup: dict of str to str or None, default None
+            Backoff lookup table for simple token-lemma lookup.
+        """
+        if table is None:
+            self.table = None
+        else:
+            self.table = table
+        self.lookup = lookup
+
+    def backoff(self, token: Token) -> str:
+        """Gets backoff token based on priority."""
+        orth = token.orth_.lower()
+        lookup = self.lookup
+        in_lookup = (lookup is not None) and (orth in lookup)
+        priority = self.fallback_priority
+        has_lemma = (token.lemma != 0) and (token.lemma_ != token.orth_)
+        if in_lookup:
+            if priority == "lookup":
+                return lookup[orth]  # type: ignore
+            else:
+                if has_lemma:
+                    return token.lemma_
+                else:
+                    return token.orth_
+        else:
+            if has_lemma:
+                return token.lemma_
+            else:
+                return token.orth_
+
+    def lemmatize(self, token: Token) -> str:
+        """Lemmatizes token."""
+        backoff = self.backoff(token)
+        orth = token.orth_.lower()
+        # If the table is empty we early return
+        if self.table is None:
+            return backoff
+        # I only add frequency for type compatibility
+        token_entry: TableEntry = TableEntry(
+            form=orth, upos=token.pos_, frequency=-1, **token.morph.to_dict()
+        )
+        lemma = match_lemma(token_entry=token_entry, table=self.table)
+        if lemma is None:
+            return backoff
+        else:
+            return lemma
+
+    def __call__(self, doc: Doc) -> Doc:
+        """Apply the lemmatization to a document."""
+        error_handler = self.get_error_handler()
+        try:
+            for token in doc:
+                if self.overwrite or token.lemma == 0:
+                    token.lemma_ = self.lemmatize(token)
+            return doc
+        except Exception as e:
+            error_handler(self.name, self, [doc], e)
+
+    def to_disk(
+        self, path: Union[str, Path], *, exclude: Iterable[str] = tuple()
+    ):
+        """Save frequency lemmatizer data to a directory."""
+        path = ensure_path(path)
+        Path(path).mkdir(parents=True, exist_ok=True)
+        config = dict(
+            overwrite=self.overwrite, fallback_priority=self.fallback_priority
+        )
+        with open(os.path.join(path, "config.json"), "w") as config_file:
+            json.dump(config, config_file)
+        if self.table is not None:
+            table_path = os.path.join(path, "table.json")
+            write_json(self.table, path=table_path)
+        if self.lookup is not None:
+            lookup_path = os.path.join(path, "lookup.json")
+            write_json(self.lookup, path=lookup_path)
+
+    def from_disk(
+        self, path: Union[str, Path], *, exclude: Iterable[str] = tuple()
+    ) -> "FrequencyLemmatizer":
+        """Load component from disk."""
+        path = ensure_path(path)
+        config = read_json(os.path.join(path, "config.json"))
+        self.overwrite = config.get("overwrite", self.overwrite)
+        self.fallback_priority = config.get(
+            "fallback_priority", self.fallback_priority
+        )
+        try:
+            table: Optional[FrequencyTable] = read_json(
+                os.path.join(path, "table.json")
+            )
+        except FileNotFoundError:
+            table = None
+        try:
+            lookup: Optional[LookupTable] = read_json(
+                os.path.join(path, "lookup.json")
+            )
+        except FileNotFoundError:
+            lookup = None
+        self.initialize(table=table, lookup=lookup)
+        return self

morphologizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac79b4ca383de69726f4b7d6b1906789e6f863c8f832f042eb440666b52a2e41
+size 4408561

parser/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":30,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

parser/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4935f74b412dc41ba2bc69cd62cb760f1aa2f1024d8a8be348417e8cb8272e0f
+size 2075321

parser/moves

@@ -0,0 +1 @@
+��moves�3{"0":{"":181951},"1":{"":138489},"2":{"det":30514,"advmod":25856,"case":19705,"nsubj":14893,"obj":13046,"obl":9420,"advcl":8875,"nmod":8747,"discourse":8140,"punct":6644,"cc":5133,"mark":4895,"iobj":2542,"xcomp":2221,"cop":1869,"amod":1626,"vocative":1404,"det||nsubj":1381,"nmod||obj":1144,"nmod||nsubj":1039,"nsubj:pass":966,"case||obl":853,"nummod":639,"mark||advcl":633,"obj||advcl":615,"det||obj":507,"obl||advcl":389,"nsubj||ccomp":335,"acl":330,"obj||xcomp":307,"nmod||obl":298,"advmod||advcl":287,"nsubj||advcl":274,"xcomp||nsubj":272,"ccomp":268,"dislocated":261,"orphan":206,"cc||advcl":160,"conj||advcl":158,"det||obl":149,"amod||obj":149,"advmod||advmod":148,"det||nsubj:pass":140,"xcomp||obj":135,"nmod||nmod":135,"obl||xcomp":133,"det||nmod":133,"advmod||xcomp":128,"amod||nsubj":127,"obl:agent":126,"xcomp||advcl":107,"parataxis":106,"obj||ccomp":102,"det||iobj":100,"nmod||xcomp":94,"advmod||ccomp":89,"csubj":82,"iobj||xcomp":81,"iobj||advcl":79,"det||advmod":76,"advmod||nsubj":76,"advmod||obj":74,"obl||ccomp":72,"cc||nsubj":66,"conj||nsubj":60,"nmod||iobj":57,"advmod||nmod":55,"appos||nsubj":53,"advmod||obl":47,"conj||obj":46,"ccomp||advcl":46,"acl||nsubj":45,"amod||obl":42,"cc||obj":41,"obj||csubj":40,"det||xcomp":40,"iobj||ccomp":38,"nsubj||csubj":35,"advcl||ccomp":35,"nsubj:pass||advcl":34,"acl||obj":33,"xcomp||xcomp":32,"nsubj||nsubj":32,"nmod||det":32,"obl||obj":30,"dep":0},"3":{"conj":15241,"cc":14143,"punct":13626,"nmod":11545,"obj":11482,"obl":11254,"advcl":7395,"nsubj":6834,"advmod":6645,"xcomp":4281,"det":4188,"iobj":4162,"ccomp":2904,"cop":2189,"discourse":2107,"acl":1999,"appos":1772,"amod":1681,"nmod||obj":826,"nsubj:pass":710,"advmod||conj":678,"case":573,"nsubj||conj":568,"obj||conj":564,"vocative":527,"nmod||nsubj":510,"orphan":452,"acl||obj":422,"conj||obj":329,"obl||conj":300,"acl||nsubj":287,"nummod":282,"obl:agent":273,"nmod||conj":268,"cc||obj":258,"flat:name":248,"csubj":223,"conj||nsubj":218,"case||conj":213,"xcomp||obj":205,"parataxis":201,"advcl||conj":196,"cc||nsubj":186,"nmod||obl":178,"appos||nsubj":178,"amod||obj":174,"case||obl":170,"appos||obj":165,"xcomp||nsubj":148,"fixed":148,"nmod||nmod":146,"det||nsubj":137,"xcomp||conj":132,"amod||nsubj":131,"conj||obl":130,"cc||obl":120,"csubj:pass":118,"det||obj":117,"obl||xcomp":103,"conj||xcomp":95,"acl||obl":85,"obj||xcomp":81,"conj||nmod":79,"iobj||conj":73,"cc||xcomp":71,"cc||nmod":71,"acl||nmod":71,"advmod||obj":69,"nmod||xcomp":64,"dislocated":59,"appos||obl":58,"advcl||advmod":53,"nsubj||ccomp":52,"det||conj":52,"obj||advcl":51,"advmod||xcomp":49,"iobj||xcomp":45,"nmod||iobj":44,"conj||iobj":44,"advmod||advmod":44,"cop||xcomp":42,"advcl||xcomp":42,"cc||iobj":41,"acl||iobj":36,"cop||ccomp":34,"advmod||nsubj":34,"conj||advcl":33,"obl||advcl":32,"ccomp||conj":32,"obj||ccomp":31,"conj||amod":31,"cop||obj":30,"dep":0},"4":{"ROOT":26490}}�cfg��neg_key�

tagger/cfg

@@ -0,0 +1,839 @@
+{
+  "labels":[
+    "---------",
+    "--p---fa-",
+    "--s---ma-",
+    "-3paia---",
+    "-3paim---",
+    "-3siia---",
+    "A-",
+    "C-",
+    "Df",
+    "Dq",
+    "Du",
+    "F-",
+    "G-",
+    "I-",
+    "Ma",
+    "Mo",
+    "Nb",
+    "Ne",
+    "Pc",
+    "Pd",
+    "Pi",
+    "Pk",
+    "Pp",
+    "Pr",
+    "Ps",
+    "Px",
+    "R-",
+    "S-",
+    "V-",
+    "a--------",
+    "a-------s",
+    "a-d---fa-",
+    "a-d---fd-",
+    "a-d---fg-",
+    "a-d---fn-",
+    "a-d---ma-",
+    "a-d---md-",
+    "a-d---mg-",
+    "a-d---mn-",
+    "a-d---mnc",
+    "a-d---mv-",
+    "a-d---na-",
+    "a-d---ng-",
+    "a-d---nn-",
+    "a-p----dc",
+    "a-p---fa-",
+    "a-p---fac",
+    "a-p---fas",
+    "a-p---fd-",
+    "a-p---fdc",
+    "a-p---fds",
+    "a-p---fg-",
+    "a-p---fgc",
+    "a-p---fn-",
+    "a-p---fnc",
+    "a-p---fns",
+    "a-p---fv-",
+    "a-p---m--",
+    "a-p---m-c",
+    "a-p---ma-",
+    "a-p---mac",
+    "a-p---mas",
+    "a-p---md-",
+    "a-p---mdc",
+    "a-p---mds",
+    "a-p---mg-",
+    "a-p---mgc",
+    "a-p---mgs",
+    "a-p---mn-",
+    "a-p---mnc",
+    "a-p---mns",
+    "a-p---mv-",
+    "a-p---mvs",
+    "a-p---na-",
+    "a-p---nac",
+    "a-p---nas",
+    "a-p---nd-",
+    "a-p---ndc",
+    "a-p---nds",
+    "a-p---ng-",
+    "a-p---ngs",
+    "a-p---nn-",
+    "a-p---nnc",
+    "a-p---nns",
+    "a-p---nv-",
+    "a-s----d-",
+    "a-s----dc",
+    "a-s----g-",
+    "a-s----gc",
+    "a-s---fa-",
+    "a-s---fac",
+    "a-s---fas",
+    "a-s---fd-",
+    "a-s---fds",
+    "a-s---fg-",
+    "a-s---fgc",
+    "a-s---fgs",
+    "a-s---fn-",
+    "a-s---fnc",
+    "a-s---fns",
+    "a-s---fv-",
+    "a-s---m--",
+    "a-s---ma-",
+    "a-s---mac",
+    "a-s---mas",
+    "a-s---md-",
+    "a-s---mdc",
+    "a-s---mds",
+    "a-s---mg-",
+    "a-s---mgc",
+    "a-s---mgs",
+    "a-s---mn-",
+    "a-s---mnc",
+    "a-s---mns",
+    "a-s---mv-",
+    "a-s---mvc",
+    "a-s---mvs",
+    "a-s---na-",
+    "a-s---nac",
+    "a-s---nas",
+    "a-s---nd-",
+    "a-s---ndc",
+    "a-s---nds",
+    "a-s---ng-",
+    "a-s---nn-",
+    "a-s---nnc",
+    "a-s---nns",
+    "a-s---nv-",
+    "a-s---nvs",
+    "c--------",
+    "d--------",
+    "d-------c",
+    "d-------s",
+    "g--------",
+    "i--------",
+    "l--------",
+    "l-d---fa-",
+    "l-d---fg-",
+    "l-d---mg-",
+    "l-d---mn-",
+    "l-d---na-",
+    "l-d---nn-",
+    "l-p---fa-",
+    "l-p---fd-",
+    "l-p---fg-",
+    "l-p---fn-",
+    "l-p---ma-",
+    "l-p---md-",
+    "l-p---mg-",
+    "l-p---mn-",
+    "l-p---na-",
+    "l-p---nd-",
+    "l-p---ng-",
+    "l-p---nn-",
+    "l-s---fa-",
+    "l-s---fd-",
+    "l-s---fg-",
+    "l-s---fn-",
+    "l-s---ma-",
+    "l-s---md-",
+    "l-s---mg-",
+    "l-s---mn-",
+    "l-s---na-",
+    "l-s---nd-",
+    "l-s---ng-",
+    "l-s---nn-",
+    "m--------",
+    "m-p---m--",
+    "m-p---md-",
+    "m-p---nn-",
+    "n-----fg-",
+    "n-----na-",
+    "n-----nn-",
+    "n-d----a-",
+    "n-d---fa-",
+    "n-d---fd-",
+    "n-d---fg-",
+    "n-d---fn-",
+    "n-d---ma-",
+    "n-d---md-",
+    "n-d---mg-",
+    "n-d---mn-",
+    "n-d---mv-",
+    "n-d---na-",
+    "n-d---nn-",
+    "n-p----d-",
+    "n-p----g-",
+    "n-p---fa-",
+    "n-p---fd-",
+    "n-p---fg-",
+    "n-p---fn-",
+    "n-p---fv-",
+    "n-p---ma-",
+    "n-p---md-",
+    "n-p---mg-",
+    "n-p---mn-",
+    "n-p---mv-",
+    "n-p---na-",
+    "n-p---nd-",
+    "n-p---ng-",
+    "n-p---nn-",
+    "n-p---nv-",
+    "n-s----d-",
+    "n-s----g-",
+    "n-s----n-",
+    "n-s----v-",
+    "n-s---fa-",
+    "n-s---fd-",
+    "n-s---fg-",
+    "n-s---fn-",
+    "n-s---fv-",
+    "n-s---m--",
+    "n-s---ma-",
+    "n-s---md-",
+    "n-s---mg-",
+    "n-s---mn-",
+    "n-s---mv-",
+    "n-s---na-",
+    "n-s---nd-",
+    "n-s---ng-",
+    "n-s---nn-",
+    "n-s---nv-",
+    "p--------",
+    "p-d----d-",
+    "p-d----n-",
+    "p-d---fa-",
+    "p-d---fd-",
+    "p-d---fg-",
+    "p-d---fn-",
+    "p-d---ma-",
+    "p-d---md-",
+    "p-d---mg-",
+    "p-d---mn-",
+    "p-d---mv-",
+    "p-p----a-",
+    "p-p----d-",
+    "p-p----g-",
+    "p-p----n-",
+    "p-p---fa-",
+    "p-p---fd-",
+    "p-p---fg-",
+    "p-p---fn-",
+    "p-p---ma-",
+    "p-p---md-",
+    "p-p---mg-",
+    "p-p---mn-",
+    "p-p---na-",
+    "p-p---nd-",
+    "p-p---ng-",
+    "p-p---nn-",
+    "p-s----a-",
+    "p-s----d-",
+    "p-s----g-",
+    "p-s----n-",
+    "p-s---fa-",
+    "p-s---fd-",
+    "p-s---fg-",
+    "p-s---fn-",
+    "p-s---ma-",
+    "p-s---md-",
+    "p-s---mg-",
+    "p-s---mn-",
+    "p-s---mv-",
+    "p-s---na-",
+    "p-s---nd-",
+    "p-s---ng-",
+    "p-s---nn-",
+    "p1p---fa-",
+    "p1p---ma-",
+    "p1p---md-",
+    "p1p---mg-",
+    "p1p---mn-",
+    "p1s---fa-",
+    "p1s---fd-",
+    "p1s---fg-",
+    "p1s---fn-",
+    "p1s---ma-",
+    "p1s---md-",
+    "p1s---mg-",
+    "p1s---mn-",
+    "p2p----a-",
+    "p2p----d-",
+    "p2p---ma-",
+    "p2p---mg-",
+    "p2p---mn-",
+    "p2s----a-",
+    "p2s----d-",
+    "p2s----g-",
+    "p2s----n-",
+    "p2s---ma-",
+    "p2s---md-",
+    "p2s---mg-",
+    "p3s---fa-",
+    "p3s---ma-",
+    "r--------",
+    "u--------",
+    "v---na---",
+    "v--amm---",
+    "v--an----",
+    "v--ana---",
+    "v--ane---",
+    "v--anm---",
+    "v--anp---",
+    "v--fna---",
+    "v--fne---",
+    "v--fnm---",
+    "v--fnp---",
+    "v--pna---",
+    "v--pnd---",
+    "v--pne---",
+    "v--pnp---",
+    "v--ppefa-",
+    "v--ppemn-",
+    "v--rn----",
+    "v--rna---",
+    "v--rne---",
+    "v--rnp---",
+    "v--tna---",
+    "v-dapafn-",
+    "v-dapama-",
+    "v-dapamg-",
+    "v-dapamn-",
+    "v-dapmfn-",
+    "v-dapmmn-",
+    "v-dappma-",
+    "v-dappmn-",
+    "v-dppafg-",
+    "v-dppama-",
+    "v-dppamn-",
+    "v-dppefn-",
+    "v-dppema-",
+    "v-dppemd-",
+    "v-dppemn-",
+    "v-dpppmn-",
+    "v-drpama-",
+    "v-drpamn-",
+    "v-drpefn-",
+    "v-drpemn-",
+    "v-p-pmma-",
+    "v-pap-mn-",
+    "v-papafa-",
+    "v-papafg-",
+    "v-papafn-",
+    "v-papama-",
+    "v-papamd-",
+    "v-papamg-",
+    "v-papamn-",
+    "v-papana-",
+    "v-papand-",
+    "v-papann-",
+    "v-papefn-",
+    "v-papema-",
+    "v-papemn-",
+    "v-papmfa-",
+    "v-papmfg-",
+    "v-papmfn-",
+    "v-papmma-",
+    "v-papmmd-",
+    "v-papmmg-",
+    "v-papmmn-",
+    "v-papmna-",
+    "v-papmng-",
+    "v-papmnn-",
+    "v-pappfd-",
+    "v-pappfg-",
+    "v-pappfn-",
+    "v-pappma-",
+    "v-pappmd-",
+    "v-pappmg-",
+    "v-pappmn-",
+    "v-pappna-",
+    "v-pappng-",
+    "v-pappnn-",
+    "v-pfpama-",
+    "v-pfpamg-",
+    "v-pfpamn-",
+    "v-pfpema-",
+    "v-pfpemn-",
+    "v-pfpmfa-",
+    "v-pfpmfn-",
+    "v-pfpmma-",
+    "v-pfpmmd-",
+    "v-pfpmmg-",
+    "v-pfpmmn-",
+    "v-pfpmnn-",
+    "v-pfppmn-",
+    "v-ppp-mn-",
+    "v-pppafa-",
+    "v-pppafd-",
+    "v-pppafg-",
+    "v-pppafn-",
+    "v-pppafv-",
+    "v-pppama-",
+    "v-pppamd-",
+    "v-pppamg-",
+    "v-pppamn-",
+    "v-pppamv-",
+    "v-pppana-",
+    "v-pppand-",
+    "v-pppang-",
+    "v-pppann-",
+    "v-pppefa-",
+    "v-pppefd-",
+    "v-pppefg-",
+    "v-pppefn-",
+    "v-pppefv-",
+    "v-pppema-",
+    "v-pppemd-",
+    "v-pppemg-",
+    "v-pppemn-",
+    "v-pppemv-",
+    "v-pppena-",
+    "v-pppend-",
+    "v-pppeng-",
+    "v-pppenn-",
+    "v-ppppma-",
+    "v-ppppmd-",
+    "v-ppppmn-",
+    "v-prp-mn-",
+    "v-prpafa-",
+    "v-prpafd-",
+    "v-prpafn-",
+    "v-prpama-",
+    "v-prpamd-",
+    "v-prpamg-",
+    "v-prpamn-",
+    "v-prpana-",
+    "v-prpang-",
+    "v-prpefa-",
+    "v-prpefd-",
+    "v-prpefg-",
+    "v-prpefn-",
+    "v-prpema-",
+    "v-prpemd-",
+    "v-prpemg-",
+    "v-prpemn-",
+    "v-prpena-",
+    "v-prpend-",
+    "v-prpeng-",
+    "v-prpenn-",
+    "v-prppfn-",
+    "v-prppmn-",
+    "v-sagamn-",
+    "v-saiamn-",
+    "v-samp---",
+    "v-sap-mg-",
+    "v-sap-mn-",
+    "v-sapafa-",
+    "v-sapafd-",
+    "v-sapafg-",
+    "v-sapafn-",
+    "v-sapama-",
+    "v-sapamd-",
+    "v-sapamg-",
+    "v-sapamn-",
+    "v-sapamv-",
+    "v-sapana-",
+    "v-sapang-",
+    "v-sapann-",
+    "v-sapanv-",
+    "v-sapema-",
+    "v-sapemn-",
+    "v-sapmfa-",
+    "v-sapmfd-",
+    "v-sapmfg-",
+    "v-sapmfn-",
+    "v-sapmma-",
+    "v-sapmmd-",
+    "v-sapmmg-",
+    "v-sapmmn-",
+    "v-sapmna-",
+    "v-sapmng-",
+    "v-sapmnn-",
+    "v-sappfa-",
+    "v-sappfd-",
+    "v-sappfg-",
+    "v-sappfn-",
+    "v-sappma-",
+    "v-sappmd-",
+    "v-sappmg-",
+    "v-sappmn-",
+    "v-sappna-",
+    "v-sappng-",
+    "v-sappnn-",
+    "v-sappnv-",
+    "v-sfpafa-",
+    "v-sfpafd-",
+    "v-sfpafn-",
+    "v-sfpama-",
+    "v-sfpamd-",
+    "v-sfpamg-",
+    "v-sfpamn-",
+    "v-sfpmfa-",
+    "v-sfpmfd-",
+    "v-sfpmfg-",
+    "v-sfpmfn-",
+    "v-sfpmma-",
+    "v-sfpmmg-",
+    "v-sfpmmn-",
+    "v-sfpmna-",
+    "v-sfppma-",
+    "v-spiamn-",
+    "v-spp-mn-",
+    "v-spp-nn-",
+    "v-sppa---",
+    "v-sppafa-",
+    "v-sppafd-",
+    "v-sppafg-",
+    "v-sppafn-",
+    "v-sppafv-",
+    "v-sppama-",
+    "v-sppamd-",
+    "v-sppamg-",
+    "v-sppamn-",
+    "v-sppamv-",
+    "v-sppana-",
+    "v-sppand-",
+    "v-sppang-",
+    "v-sppann-",
+    "v-sppanv-",
+    "v-sppefa-",
+    "v-sppefd-",
+    "v-sppefg-",
+    "v-sppefn-",
+    "v-sppema-",
+    "v-sppemd-",
+    "v-sppemg-",
+    "v-sppemn-",
+    "v-sppemv-",
+    "v-sppena-",
+    "v-sppend-",
+    "v-sppeng-",
+    "v-sppenn-",
+    "v-spppfa-",
+    "v-spppfd-",
+    "v-spppfg-",
+    "v-spppfn-",
+    "v-spppma-",
+    "v-spppmn-",
+    "v-srp-mn-",
+    "v-srpafa-",
+    "v-srpafd-",
+    "v-srpafg-",
+    "v-srpafn-",
+    "v-srpama-",
+    "v-srpamd-",
+    "v-srpamg-",
+    "v-srpamn-",
+    "v-srpamv-",
+    "v-srpana-",
+    "v-srpand-",
+    "v-srpang-",
+    "v-srpann-",
+    "v-srpefa-",
+    "v-srpefd-",
+    "v-srpefg-",
+    "v-srpefn-",
+    "v-srpema-",
+    "v-srpemd-",
+    "v-srpemg-",
+    "v-srpemn-",
+    "v-srpemv-",
+    "v-srpena-",
+    "v-srpend-",
+    "v-srpeng-",
+    "v-srpenn-",
+    "v-srppfn-",
+    "v-srppma-",
+    "v-srppmn-",
+    "v-srppmv-",
+    "v1paia---",
+    "v1paim---",
+    "v1paip---",
+    "v1paoa---",
+    "v1paom---",
+    "v1paop---",
+    "v1pasa---",
+    "v1pase---",
+    "v1pasm---",
+    "v1pasp---",
+    "v1pfia---",
+    "v1pfim---",
+    "v1pfom---",
+    "v1piia---",
+    "v1piie---",
+    "v1plia---",
+    "v1plie---",
+    "v1ppia---",
+    "v1ppie---",
+    "v1ppip---",
+    "v1ppoa---",
+    "v1ppoe---",
+    "v1ppsa---",
+    "v1ppse---",
+    "v1pria---",
+    "v1prie---",
+    "v1prsa---",
+    "v1prse---",
+    "v1ptie---",
+    "v1s-sa---",
+    "v1sa-a---",
+    "v1saia---",
+    "v1saie---",
+    "v1saim---",
+    "v1saip---",
+    "v1sao----",
+    "v1saoa---",
+    "v1saoe---",
+    "v1saom---",
+    "v1saop---",
+    "v1sasa---",
+    "v1sase---",
+    "v1sasm---",
+    "v1sasp---",
+    "v1sfi----",
+    "v1sfia---",
+    "v1sfie---",
+    "v1sfim---",
+    "v1sfip---",
+    "v1siia---",
+    "v1siie---",
+    "v1slia---",
+    "v1slie---",
+    "v1slim---",
+    "v1spia---",
+    "v1spie---",
+    "v1spoa---",
+    "v1spoe---",
+    "v1spsa---",
+    "v1spse---",
+    "v1sria---",
+    "v1srie---",
+    "v1sroa---",
+    "v1sroe---",
+    "v1srsa---",
+    "v1stie---",
+    "v1stim---",
+    "v2daia---",
+    "v2dama---",
+    "v2dasa---",
+    "v2dase---",
+    "v2dfia---",
+    "v2dfim---",
+    "v2diia---",
+    "v2diie---",
+    "v2dpia---",
+    "v2dpma---",
+    "v2dpme---",
+    "v2dria---",
+    "v2drma---",
+    "v2paia---",
+    "v2paim---",
+    "v2paip---",
+    "v2pama---",
+    "v2pame---",
+    "v2pamm---",
+    "v2paoa---",
+    "v2paom---",
+    "v2paop---",
+    "v2pasa---",
+    "v2pase---",
+    "v2pasm---",
+    "v2pasp---",
+    "v2pfia---",
+    "v2pfim---",
+    "v2piia---",
+    "v2piie---",
+    "v2ppia---",
+    "v2ppie---",
+    "v2ppma---",
+    "v2ppme---",
+    "v2ppoa---",
+    "v2ppoe---",
+    "v2ppsa---",
+    "v2pria---",
+    "v2prie---",
+    "v2prma---",
+    "v2prmp---",
+    "v2proa---",
+    "v2prsa---",
+    "v2saia---",
+    "v2saie---",
+    "v2saim---",
+    "v2saip---",
+    "v2sam----",
+    "v2sama---",
+    "v2same---",
+    "v2samm---",
+    "v2samp---",
+    "v2saoa---",
+    "v2saoe---",
+    "v2saom---",
+    "v2saop---",
+    "v2sasa---",
+    "v2sase---",
+    "v2sasm---",
+    "v2sasp---",
+    "v2sfi----",
+    "v2sfia---",
+    "v2sfie---",
+    "v2sfim---",
+    "v2sfip---",
+    "v2siia---",
+    "v2siie---",
+    "v2siip---",
+    "v2slia---",
+    "v2slie---",
+    "v2slim---",
+    "v2spia---",
+    "v2spie---",
+    "v2spma---",
+    "v2spme---",
+    "v2spoa---",
+    "v2spoe---",
+    "v2spsa---",
+    "v2spse---",
+    "v2sria---",
+    "v2srie---",
+    "v2srma---",
+    "v2srme---",
+    "v2sroa---",
+    "v2srsa---",
+    "v2stie---",
+    "v3-roe---",
+    "v3daia---",
+    "v3daim---",
+    "v3daip---",
+    "v3daoa---",
+    "v3dfia---",
+    "v3dfim---",
+    "v3diia---",
+    "v3diie---",
+    "v3dlia---",
+    "v3dlie---",
+    "v3dlim---",
+    "v3dpia---",
+    "v3dpie---",
+    "v3dpma---",
+    "v3dpme---",
+    "v3dpsa---",
+    "v3dria---",
+    "v3pai----",
+    "v3paia---",
+    "v3paie---",
+    "v3paim---",
+    "v3paip---",
+    "v3pamm---",
+    "v3paoa---",
+    "v3paoe---",
+    "v3paom---",
+    "v3paop---",
+    "v3pasa---",
+    "v3pase---",
+    "v3pasm---",
+    "v3pasp---",
+    "v3pfia---",
+    "v3pfie---",
+    "v3pfim---",
+    "v3piia---",
+    "v3piie---",
+    "v3piip---",
+    "v3plia---",
+    "v3plie---",
+    "v3plim---",
+    "v3plip---",
+    "v3ppia---",
+    "v3ppie---",
+    "v3ppip---",
+    "v3ppma---",
+    "v3ppme---",
+    "v3ppoa---",
+    "v3ppoe---",
+    "v3ppsa---",
+    "v3ppse---",
+    "v3pria---",
+    "v3prie---",
+    "v3prip---",
+    "v3sai----",
+    "v3saia---",
+    "v3saie---",
+    "v3saim---",
+    "v3saip---",
+    "v3sama---",
+    "v3samm---",
+    "v3samp---",
+    "v3sana---",
+    "v3sao----",
+    "v3saoa---",
+    "v3saoe---",
+    "v3saom---",
+    "v3saop---",
+    "v3sas----",
+    "v3sasa---",
+    "v3sase---",
+    "v3sasm---",
+    "v3sasp---",
+    "v3sfi----",
+    "v3sfia---",
+    "v3sfie---",
+    "v3sfim---",
+    "v3sfip---",
+    "v3sfoa---",
+    "v3sii----",
+    "v3siia---",
+    "v3siie---",
+    "v3siip---",
+    "v3sli----",
+    "v3slia---",
+    "v3slie---",
+    "v3slim---",
+    "v3slip---",
+    "v3spia---",
+    "v3spie---",
+    "v3spip---",
+    "v3spma---",
+    "v3spme---",
+    "v3spoa---",
+    "v3spoe---",
+    "v3spop---",
+    "v3spsa---",
+    "v3spse---",
+    "v3sria---",
+    "v3srie---",
+    "v3srip---",
+    "v3srma---",
+    "v3sroa---",
+    "v3srsa---",
+    "v3stie---",
+    "v3stim---",
+    "v3stip---",
+    "x--------",
+    "x-p----d-",
+    "x-p---nn-"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

tagger/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bfc381f7bf45ed55fe9ae93417b5915f60dcd0d621f6b61c13cb02e58108b5
+size 2562961

tokenizer

@@ -0,0 +1,4 @@
+��prefix_search�{^†|^⸏|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^？|^！|^，|^、|^；|^：|^～|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^（|^）|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�
+�…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|？$|！$|，$|、$|；$|：$|～$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|（$|）$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|†$|⸎$|(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]$�infix_finditer�?!\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉〈〉⟦⟧])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉〈〉⟦⟧])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])(?:-|–|—|--|---|——|~)(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[\u1F00-\u1FFF\u0370-\u03FF])—�token_match��url_match�
+��A�
+� ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°）╯︵┻━┻��A�(╯°□°）╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�:’(��A�:’(�:’)��A�:’)�:’-(��A�:’-(�:’-)��A�:’-)�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�p.��A�p.�q.��A�q.�r.��A�r.�s.��A�s.�t.��A�t.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C�  �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�Δ'��A�Δ'C�δέ�Δι'��A�Δι'C�διά�Δι’��A�Δι’C�διά�Δ’��A�Δ’C�δέ�Εφ'��A�Εφ'C�επί�Εφ’��A�Εφ’C�επί�Καθ'��A�Καθ'C�κατά�Καθ’��A�Καθ’C�κατά�Κατ'��A�Κατ'C�κατά�Κατ’��A�Κατ’C�κατά�Μ'��A�Μ'C�με�Μετ'��A�Μετ'C�μετά�Μετ’��A�Μετ’C�μετά�Μ’��A�Μ’C�με�Παρ'��A�Παρ'C�παρά�Παρ’��A�Παρ’C�παρά�Σ'��A�Σ'C�σε�Σ’��A�Σ’C�σε�Τ'��A�Τ'C�τε�Τ’��A�Τ’C�τε�αὑτός��A�αὑC�ὁ�A�τόςC�αὐτός�αὑτὸς��A�αὑC�ὁ�A�τὸςC�αὐτός�δ'��A�δ'C�δέ�δι'��A�δι'C�διά�διὰ��A�διὰC�διά�δι’��A�δι’C�διά�δὲ��A�δὲC�δέ�δ’��A�δ’C�δέ�εφ'��A�εφ'C�επί�εφ’��A�εφ’C�επί�θοἰμάτιον��A�θοC�τό�A�ἰμάτιον�θἡμέρᾳ��A�θC�τῇ�A�ἡμέρᾳ�καθ'��A�καθ'C�κατά�καθ’��A�καθ’C�κατά�κατ'��A�κατ'C�κατά�κατὰ��A�κατὰC�κατά�κατ’��A�κατ’C�κατά�καὐτός��A�κC�καί�A�αὐτός�καὐτὸς��A�κC�καί�A�αὐτὸςC�αὐτός�καὶ��A�καὶC�καί�κεἰ��A�κC�καί�A�εἰ�κεἰς��A�κC�καί�A�εἰς�κοὐ��A�κC�καί�A�οὐ�κἀγώ��A�κἀC�καί�A�γώC�ἐγώ�κἀγὼ��A�κἀC�καί�A�γὼC�ἐγώ�κἀν��A�κC�καί�A�ἀνC�ἐν�κἀς��A�κC�καί�A�ἀςC�ἐς�κᾆτα��A�κC�καί�A�ᾆταC�εἶτα�μ'��A�μ'C�με�μέ��A�μέC�με�μεθ'��A�μεθ'C�μετά�μεθ’��A�μεθ’C�μετά�μετ'��A�μετ'C�μετά�μετὰ��A�μετὰC�μετά�μετ’��A�μετ’C�μετά�μοὔστι��A�μοὔC�μοί�A�στιC�ἐστι�μοὖστι��A�μοὖC�μοί�A�στιC�ἐστι�μὲ��A�μὲC�με�μὲν��A�μὲνC�μέν�μὴν��A�μὴνC�μήν�μ’��A�μ’C�με�οὑμοί��A�οὑC�οἱ�A�μοίC�ἐμoί�οὑμοὶ��A�οὑC�οἱ�A�μοὶC�ἐμoί�οὑμός��A�οὑC�ὁ�A�μόςC�ἐμός�οὑμὸς��A�οὑC�ὁ�A�μὸςC�ἐμός�οὑν��A�οὑC�ὁ�A�νC�ἐν�παρ��A�παρC�παρά�παρ'��A�παρ'C�παρά�παρὰ��A�παρὰC�παρά�παρ’��A�παρ’C�παρά�προὔχοντα��A�προὔC�πρό�A�χονταC�ἔχοντα�προὔχων��A�προὔC�πρό�A�χωνC�ἔχων�σ'��A�σ'C�σε�σέ��A�σέC�σε�σοὐστί��A�σοὐC�σοί�A�στίC�ἐστί�σοὐστὶ��A�σοὐC�σοί�A�στὶC�ἐστί�σοὔστι��A�σοὔC�σοί�A�στιC�ἐστι�σὲ��A�σὲC�σε�σ’��A�σ’C�σε�τ'��A�τ'C�τε�τέ��A�τέC�τε�ταὐτοῦ��A�τC�τοῦ�A�αὐτοῦ�τοὔνομα��A�τοὔC�τό�A�νομαC�ὄνομα�τἀνδρί��A�τC�τῷ�A�ἀνδρί�τἀνδρός��A�τC�τοῦ�A�ἀνδρός�τἀνδρὶ��A�τC�τῷ�A�ἀνδρὶC�ἀνδρί�τἀνδρὸς��A�τC�τοῦ�A�ἀνδρὸςC�ἀνδρός�τἄλλα��A�τC�τὰ�A�ἄλλα�τἆλλα��A�τἆC�τὰ�A�λλαC�ἄλλα�τὠληθές��A�τὠC�τὸ�A�ληθέςC�ἀληθές�τὲ��A�τὲC�τε�τὴν��A�τὴνC�τήν�τὸν��A�τὸνC�τόν�τ’��A�τ’C�τε�χοἱ��A�χC�καί�A�οἱ�χἡ��A�χC�καί�A�ἡ�χἱκετεύετε��A�χC�καί�A�ἱκετεύετε�χὤπως��A�χC�καί�A�ὤπωςC�ὅπως�χὤταν��A�χC�καί�A�ὤτανC�ὅταν�χὤτε��A�χC�καί�A�ὤτεC�ὅτε�χὤτι��A�χC�καί�A�ὤτιC�ὅτι�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�ἀλλ'��A�ἀλλ'C�ἀλλά�ἀλλὰ��A�ἀλλὰC�ἀλλά�ἀλλ’��A�ἀλλ’C�ἀλλά�ἀπὸ��A�ἀπὸC�από�ἀφ'��A�ἀφ'C�από�ἀφ’��A�ἀφ’C�από�ἁγαθαί��A�ἁC�αἱ�A�γαθαίC�ἀγαθαί�ἁγαθαὶ��A�ἁC�αἱ�A�γαθαὶC�ἀγαθαί�ἁγώ��A�ἁC�ἃ�A�γώC�ἐγώ�ἁγὼ��A�ἁC�ἃ�A�γὼC�ἐγώ�ἁλήθεια��A�ἁC�ἡ�A�λήθειαC�ἀλήθεια�ἁνήρ��A�ἁC�ὁ�A�νήρC�ἀνήρ�ἁνὴρ��A�ἁC�ὁ�A�νὴρC�ἀνήρ�ἅνδρες��A�ἅC�οἱ�A�νδρεςC�ἄνδρες�ἅνθρωπος��A�ἅC�ὁ�A�νθρωποςC�ἄνθρωπος�ἐγᾦδα��A�ἐγC�ἐγώ�A�ᾦδαC�οἶδα�ἐγᾦμαι��A�ἐγC�ἐγώ�A�ᾦμαιC�οἶμαι�ἐπ'��A�ἐπ'C�επί�ἐπὶ��A�ἐπὶC�επί�ἐπ’��A�ἐπ’C�επί�Ἐπ'��A�Ἐπ'C�επί�Ἐπ’��A�Ἐπ’C�επί�ὑπ'��A�ὑπ'C�ὑπό�ὑπ’��A�ὑπ’C�ὑπό�ὑφ'��A�ὑφ'C�ὑπό�ὑφ’��A�ὑφ’C�ὑπό�Ὑπ'��A�Ὑπ'C�ὑπό�Ὑπ’��A�Ὑπ’C�ὑπό�ὥνεκα��A�ὥC�οὗ�A�νεκαC�ἕνεκα�ὦνδρες��A�ὦC�ὦ�A�νδρεςC�ἄνδρες�ὦνερ��A�ὦC�ὦ�A�νερC�ἄνερ�᾽ΑΠ'��A�᾽ΑΠ'C�από�᾽ΑΠ’��A�᾽ΑΠ’C�από�᾽Αλλ'��A�᾽Αλλ'C�ἀλλά�᾽Αλλ’��A�᾽Αλλ’C�ἀλλά�᾽Απ'��A�᾽Απ'C�από�᾽Απ’��A�᾽Απ’C�από�᾽Αφ��A�᾽ΑφC�από�—��A�—�’��A�’�’’��A�’’�faster_heuristics�

trainable_lemmatizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d373ea41f35545993049be1488bd1e1e7d4d3d830d7b080f7bcfacf4ba3b99e
+size 71957523

trainable_lemmatizer/trees

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82dcb591674572ec7124a40c85666b79e6c71f5bdedaf91dd76459b773fee605
+size 2400258

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75dc46a394d2e2b7ab298a757a318d7222d401127fe5408a17cb40c4c8f524b
+size 1134411305

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}