Update spaCy pipeline

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 la_vectors_floret_md-3.5.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
 la_vectors_floret_md-3.6.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
 la_vectors_floret_md-3.7.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+la_vectors_floret_md-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+vocab/vectors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,61 +1,20 @@
 ---
-license: mit
+tags:
+- spacy
 language:
 - la
-tags:
-- cltk
-- latin
-- floret
-library_name: spacy
+license: mit
 ---
-
-# Model Card for la_vectors_floret_md
-
-Floret vectors for Latin
-
-
-#  Table of Contents
-
-- [Model Details](#model-details)
-  - [Model Description](#model-description)
-- [Citation](#citation)
-- [How to Get Started with the Model](#how-to-get-started-with-the-model)
-
-
-# Model Details
-
-## Model Description
-
-<!-- Provide a longer summary of what this model is/does. -->
-md floret vectors for Latin on Wikipedia, Oscar, and UD data.
-
-- **Developed by:** Patrick J. Burns
-- **Model type:** spaCy model
-- **Language(s) (NLP):** la
-- **License:** mit
-- **Resources for more information:** 
-    - [GitHub Repo](https://github.com/diyclassics/la_core_cltk_md)
-
-# Citation
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-```
-@misc{burns_la_vectors_floret_md_2023,
-  title = {la\_vectors\_floret\_md},  
-  version = 3.7.2, 
-  url = {https://huggingface.co/diyclassics/la_vectors_floret_md},
-  abstract = {md floret vectors model for Latin},
-  urldate = {2023-12-23},
-  author = {Burns, Patrick J.},
-  year = {2023},
-}
-```
-
-# How to Get Started with the Model
-
-- Install with...
-  - `pip install https://huggingface.co/latincy/la_vectors_floret_md/resolve/main/la_vectors_floret_md-3.7.2-py3-none-any.whl
-- Tested on python 3.10.8, spacy==3.7.2
+Code required to train lg floret embeddings for Latin on LatinCy Assets data. Based on spaCy project [Train floret vectors from Wikipedia and OSCAR](https://github.com/explosion/projects/tree/v3/pipelines/floret_wiki_oscar_vectors).
+
+| Feature | Description |
+| --- | --- |
+| **Name** | `la_vectors_floret_md` |
+| **Version** | `3.8.0` |
+| **spaCy** | `>=3.8.3,<3.9.0` |
+| **Default Pipeline** |  |
+| **Components** |  |
+| **Vectors** | -1 keys, 50000 unique vectors (300 dimensions) |
+| **Sources** | UD_Latin-Perseus<br>UD_Latin-PROIEL<br>UD_Latin-ITTB<br>UD_Latin-LLCT<br>UD_Latin-UDante<br>Wikipedia<br>OSCAR<br>Corpus Thomisticum<br>The Latin Library<br>CLTK-Tesserae Latin<br>Patrologia Latina |
+| **License** | `MIT` |
+| **Author** | [Patrick J. Burns](https://diyclassics.github.io/) |

config.cfg

@@ -0,0 +1,93 @@
+[paths]
+train = null
+dev = null
+vectors = null
+init_tok2vec = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "la"
+pipeline = []
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 1000
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[training]
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+before_to_disk = null
+before_update = null
+logger = {"@loggers":"spacy.ConsoleLogger.v1"}
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+
+[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 = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

la_vectors_floret_md-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d2b361d1f74e73916938618414a4e70b60135f15432f907b5f86f8f228814a
+size 53485225

meta.json

@@ -0,0 +1,47 @@
+{
+  "lang":"la",
+  "name":"vectors_floret_md",
+  "version":"3.8.0",
+  "description":"Code required to train lg floret embeddings for Latin on LatinCy Assets data. Based on spaCy project [Train floret vectors from Wikipedia and OSCAR](https://github.com/explosion/projects/tree/v3/pipelines/floret_wiki_oscar_vectors).",
+  "author":"Patrick J. Burns",
+  "email":"[email protected]",
+  "url":"https://diyclassics.github.io/",
+  "license":"MIT",
+  "spacy_version":">=3.8.3,<3.9.0",
+  "spacy_git_version":"be0fa81",
+  "vectors":{
+    "width":300,
+    "vectors":50000,
+    "keys":-1,
+    "name":"la_vectors_floret_md.vectors"
+  },
+  "labels":{
+
+  },
+  "pipeline":[
+
+  ],
+  "components":[
+
+  ],
+  "disabled":[
+
+  ],
+  "title":"la_vectors_floret_lg",
+  "sources":[
+    "UD_Latin-Perseus",
+    "UD_Latin-PROIEL",
+    "UD_Latin-ITTB",
+    "UD_Latin-LLCT",
+    "UD_Latin-UDante",
+    "Wikipedia",
+    "OSCAR",
+    "Corpus Thomisticum",
+    "The Latin Library",
+    "CLTK-Tesserae Latin",
+    "Patrologia Latina"
+  ],
+  "requirements":[
+    "spacy>=3.8.3,<3.9.0"
+  ]
+}

tokenizer

@@ -0,0 +1,3 @@
+��prefix_search��^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^？|^！|^，|^、|^；|^：|^～|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^（|^）|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^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�2�…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|？$|！$|，$|、$|；$|：$|～$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|（$|）$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\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]$|'s$|'S$|’s$|’S$|—$|–$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-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%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|？|！|，|、|；|：|～|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉〈〉⟦⟧)])\.$|(?<=[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-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])\.$�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-\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])�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�@_@�A.��A�A.�A.D.��A�A.D.�A.U.C.��A�A.U.C.�AA.��A�AA.�AAA.��A�AAA.�ACC.��A�ACC.�AGR.��A�AGR.�AP.��A�AP.�APR.��A�APR.�APRIL.��A�APRIL.�AUG.��A�AUG.�Aa.��A�Aa.�Aaa.��A�Aaa.�Acc.��A�Acc.�Agr.��A�Agr.�Ap.��A�Ap.�Apr.��A�Apr.�April.��A�April.�Aug.��A�Aug.�C++��A�C++�C.��A�C.�CAES.��A�CAES.�CAESS.��A�CAESS.�CC.��A�CC.�CN.��A�CN.�COLL.��A�COLL.�CONS.��A�CONS.�CONSS.��A�CONSS.�COS.��A�COS.�COSS.��A�COSS.�Caes.��A�Caes.�Caess.��A�Caess.�Cc.��A�Cc.�Cn.��A�Cn.�Coll.��A�Coll.�Cons.��A�Cons.�Conss.��A�Conss.�Cos.��A�Cos.�Coss.��A�Coss.�D.��A�D.�D.N.��A�D.N.�DAT.��A�DAT.�DD.��A�DD.�DEC.��A�DEC.�DECEMB.��A�DECEMB.�DECEMBR.��A�DECEMBR.�Dat.��A�Dat.�Dd.��A�Dd.�Dec.��A�Dec.�Decemb.��A�Decemb.�Decembr.��A�Decembr.�F.��A�F.�FEB.��A�FEB.�FEBR.��A�FEBR.�FEBRUAR.��A�FEBRUAR.�Feb.��A�Feb.�Febr.��A�Febr.�Februar.��A�Februar.�IAN.��A�IAN.�ID.��A�ID.�IMP.��A�IMP.�IMPP.��A�IMPP.�IMPPP.��A�IMPPP.�IUL.��A�IUL.�IUN.��A�IUN.�Ian.��A�Ian.�Id.��A�Id.�Imp.��A�Imp.�Impp.��A�Impp.�Imppp.��A�Imppp.�Iul.��A�Iul.�Iun.��A�Iun.�K.��A�K.�KAL.��A�KAL.�Kal.��A�Kal.�L.��A�L.�M'.��A�M'.�M.��A�M.�MAI.��A�MAI.�MAM.��A�MAM.�MAR.��A�MAR.�MART.��A�MART.�MED.��A�MED.�Mai.��A�Mai.�Mam.��A�Mam.�Mar.��A�Mar.�Mart.��A�Mart.�Med.��A�Med.�M’.��A�M’.�N.��A�N.�NN.��A�NN.�NOB.��A�NOB.�NON.��A�NON.�NOU.��A�NOU.�NOUEMB.��A�NOUEMB.�NOV.��A�NOV.�NOVEMB.��A�NOVEMB.�Nn.��A�Nn.�Nob.��A�Nob.�Non.��A�Non.�Nou.��A�Nou.�Nouemb.��A�Nouemb.�Nov.��A�Nov.�Novemb.��A�Novemb.�O.O��A�O.O�O.o��A�O.o�OCT.��A�OCT.�OCTOB.��A�OCTOB.�OPET.��A�OPET.�ORD.��A�ORD.�O_O��A�O_O�O_o��A�O_o�Oct.��A�Oct.�Octob.��A�Octob.�Opet.��A�Opet.�Ord.��A�Ord.�P.��A�P.�PAUL.��A�PAUL.�PF.��A�PF.�PL.��A�PL.�PLUR.��A�PLUR.�POST.��A�POST.�PP.��A�PP.�PRID.��A�PRID.�PRO.��A�PRO.�PROCOS.��A�PROCOS.�Paul.��A�Paul.�Pf.��A�Pf.�Pl.��A�Pl.�Plur.��A�Plur.�Post.��A�Post.�Pp.��A�Pp.�Prid.��A�Prid.�Pro.��A�Pro.�Procos.��A�Procos.�Q.��A�Q.�QUINT.��A�QUINT.�Quint.��A�Quint.�S.��A�S.�S.C.��A�S.C.�SCR.��A�SCR.�SEPT.��A�SEPT.�SEPTEMB.��A�SEPTEMB.�SER.��A�SER.�SERT.��A�SERT.�SEX.��A�SEX.�SEXT.��A�SEXT.�ST.��A�ST.�STA.��A�STA.�SUFF.��A�SUFF.�Scr.��A�Scr.�Sept.��A�Sept.�Septemb.��A�Septemb.�Ser.��A�Ser.�Sert.��A�Sert.�Sex.��A�Sex.�Sext.��A�Sext.�St.��A�St.�Sta.��A�Sta.�Suff.��A�Suff.�T.��A�T.�TI.��A�TI.�TRIB.��A�TRIB.�Ti.��A�Ti.�Trib.��A�Trib.�U.��A�U.�UOL.��A�UOL.�UOP.��A�UOP.�UU.��A�UU.�Uol.��A�Uol.�Uop.��A�Uop.�Uu.��A�Uu.�V.��A�V.�V.V��A�V.V�VOL.��A�VOL.�VOP.��A�VOP.�VV.��A�VV.�V_V��A�V_V�Vol.��A�Vol.�Vop.��A�Vop.�Vv.��A�Vv.�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�a.d.��A�a.d.�a.u.c.��A�a.u.c.�aa.��A�aa.�aaa.��A�aaa.�acc.��A�acc.�agr.��A�agr.�ap.��A�ap.�apr.��A�apr.�april.��A�april.�aug.��A�aug.�b.��A�b.�c.��A�c.�caes.��A�caes.�caess.��A�caess.�cc.��A�cc.�cn.��A�cn.�coll.��A�coll.�cons.��A�cons.�conss.��A�conss.�cos.��A�cos.�coss.��A�coss.�d.��A�d.�d.N.��A�d.N.�d.n.��A�d.n.�dat.��A�dat.�dd.��A�dd.�dec.��A�dec.�decemb.��A�decemb.�decembr.��A�decembr.�e.��A�e.�f.��A�f.�feb.��A�feb.�febr.��A�febr.�februar.��A�februar.�g.��A�g.�h.��A�h.�i.��A�i.�ian.��A�ian.�id.��A�id.�imp.��A�imp.�impp.��A�impp.�imppp.��A�imppp.�iul.��A�iul.�iun.��A�iun.�j.��A�j.�k.��A�k.�kal.��A�kal.�l.��A�l.�m'.��A�m'.�m.��A�m.�mai.��A�mai.�mam.��A�mam.�mar.��A�mar.�mart.��A�mart.�mecum��A�me�A�cum�med.��A�med.�m’.��A�m’.�n.��A�n.�nn.��A�nn.�nob.��A�nob.�nobiscum��A�nobis�A�cum�non.��A�non.�nou.��A�nou.�nouemb.��A�nouemb.�nov.��A�nov.�novemb.��A�novemb.�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�oct.��A�oct.�octob.��A�octob.�opet.��A�opet.�ord.��A�ord.�p.��A�p.�paul.��A�paul.�pf.��A�pf.�pl.��A�pl.�plur.��A�plur.�post.��A�post.�pp.��A�pp.�prid.��A�prid.�pro.��A�pro.�procos.��A�procos.�q.��A�q.�quint.��A�quint.�r.��A�r.�s.��A�s.�s.c.��A�s.c.�scr.��A�scr.�sept.��A�sept.�septemb.��A�septemb.�ser.��A�ser.�sert.��A�sert.�sex.��A�sex.�sext.��A�sext.�st.��A�st.�sta.��A�sta.�suff.��A�suff.�t.��A�t.�tecum��A�te�A�cum�ti.��A�ti.�trib.��A�trib.�u.��A�u.�uobiscum��A�uobis�A�cum�uol.��A�uol.�uop.��A�uop.�uu.��A�uu.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�vobiscum��A�vobis�A�cum�vol.��A�vol.�vop.��A�vop.�vv.��A�vv.�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.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’’��A�’’�faster_heuristics�

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/strings.json

@@ -0,0 +1,1032 @@
+[
+  "\t",
+  "\n",
+  " ",
+  "  ",
+  "\"",
+  "'",
+  "''",
+  "'-(",
+  "'-)",
+  "(",
+  "(((",
+  "(*>",
+  "(*_*)",
+  "(-8",
+  "(-:",
+  "(-;",
+  "(-_-)",
+  "(-d",
+  "(._.)",
+  "(:",
+  "(;",
+  "(=",
+  "(>_<)",
+  "(^_^)",
+  "(o:",
+  "(x:",
+  "(x_x)",
+  "(\u00ac_\u00ac)",
+  "(\u0ca0_\u0ca0)",
+  "(\u256f\u00b0\u25a1\u00b0\uff09\u256f\ufe35\u253b\u2501\u253b",
+  ")",
+  ")))",
+  ")-:",
+  ")/\u00af",
+  "):",
+  "*",
+  "-",
+  "-((",
+  "-))",
+  "-/",
+  "-0",
+  "-3",
+  "-8",
+  "-D",
+  "-O",
+  "-P",
+  "-X",
+  "-_-",
+  "-__-",
+  "-d",
+  "-o",
+  "-p",
+  "-x",
+  "-|",
+  ".",
+  ".C.",
+  ".D.",
+  ".N.",
+  "._.",
+  ".c.",
+  ".d.",
+  ".n.",
+  "/",
+  "/3",
+  "/d",
+  "0",
+  "0.0",
+  "0.o",
+  "0_0",
+  "0_o",
+  "1",
+  "3",
+  "33",
+  "333",
+  "8",
+  "8)",
+  "8-",
+  "8-)",
+  "8-D",
+  "8-d",
+  "8D",
+  "8d",
+  ":",
+  ":'(",
+  ":')",
+  ":'-(",
+  ":'-)",
+  ":(",
+  ":((",
+  ":(((",
+  ":()",
+  ":)",
+  ":))",
+  ":)))",
+  ":*",
+  ":-(",
+  ":-((",
+  ":-(((",
+  ":-)",
+  ":-))",
+  ":-)))",
+  ":-*",
+  ":-/",
+  ":-0",
+  ":-3",
+  ":->",
+  ":-D",
+  ":-O",
+  ":-P",
+  ":-X",
+  ":-]",
+  ":-d",
+  ":-o",
+  ":-p",
+  ":-x",
+  ":-|",
+  ":-}",
+  ":/",
+  ":0",
+  ":1",
+  ":3",
+  ":>",
+  ":D",
+  ":O",
+  ":P",
+  ":X",
+  ":]",
+  ":d",
+  ":o",
+  ":o)",
+  ":p",
+  ":x",
+  ":x)",
+  ":|",
+  ":}",
+  ":\u2019(",
+  ":\u2019)",
+  ":\u2019-(",
+  ":\u2019-)",
+  ";",
+  ";)",
+  ";-)",
+  ";-D",
+  ";-X",
+  ";-d",
+  ";D",
+  ";X",
+  ";_;",
+  ";d",
+  "<",
+  "<.<",
+  "</3",
+  "</d",
+  "<3",
+  "<33",
+  "<333",
+  "<d",
+  "<dd",
+  "<ddd",
+  "<space>",
+  "<xxxx>",
+  "=",
+  "=(",
+  "=)",
+  "=/",
+  "=3",
+  "=D",
+  "=X",
+  "=[",
+  "=]",
+  "=d",
+  "=|",
+  ">",
+  ">.<",
+  ">.>",
+  ">:(",
+  ">:o",
+  ">:x",
+  "><(((*>",
+  "@",
+  "@_@",
+  "A",
+  "A.",
+  "A.D.",
+  "A.U.C.",
+  "AA",
+  "AA.",
+  "AAA",
+  "AAA.",
+  "ACC",
+  "ACC.",
+  "AES",
+  "AGR",
+  "AGR.",
+  "AI.",
+  "AL.",
+  "AM.",
+  "AN.",
+  "AP",
+  "AP.",
+  "APR",
+  "APR.",
+  "APRIL",
+  "APRIL.",
+  "AR.",
+  "ART",
+  "AT.",
+  "AUG",
+  "AUG.",
+  "AUL",
+  "Aa",
+  "Aa.",
+  "Aaa",
+  "Aaa.",
+  "Acc",
+  "Acc.",
+  "Agr",
+  "Agr.",
+  "Ap",
+  "Ap.",
+  "Apr",
+  "Apr.",
+  "April",
+  "April.",
+  "Aug",
+  "Aug.",
+  "BR.",
+  "C",
+  "C++",
+  "C.",
+  "CAES",
+  "CAES.",
+  "CAESS",
+  "CAESS.",
+  "CC",
+  "CC.",
+  "CN",
+  "CN.",
+  "COLL",
+  "COLL.",
+  "CONS",
+  "CONS.",
+  "CONSS",
+  "CONSS.",
+  "COS",
+  "COS.",
+  "COSS",
+  "COSS.",
+  "CR.",
+  "CT.",
+  "Caes",
+  "Caes.",
+  "Caess",
+  "Caess.",
+  "Cc",
+  "Cc.",
+  "Cn",
+  "Cn.",
+  "Coll",
+  "Coll.",
+  "Cons",
+  "Cons.",
+  "Conss",
+  "Conss.",
+  "Cos",
+  "Cos.",
+  "Coss",
+  "Coss.",
+  "D",
+  "D.",
+  "D.N.",
+  "DAT",
+  "DAT.",
+  "DD",
+  "DD.",
+  "DEC",
+  "DEC.",
+  "DECEMB",
+  "DECEMB.",
+  "DECEMBR",
+  "DECEMBR.",
+  "Dat",
+  "Dat.",
+  "Dd",
+  "Dd.",
+  "Dec",
+  "Dec.",
+  "Decemb",
+  "Decemb.",
+  "Decembr",
+  "Decembr.",
+  "EB.",
+  "EBR",
+  "EC.",
+  "ED.",
+  "EMB",
+  "EPT",
+  "ER.",
+  "ERT",
+  "ES.",
+  "ESS",
+  "ET.",
+  "EX.",
+  "EXT",
+  "F",
+  "F.",
+  "FEB",
+  "FEB.",
+  "FEBR",
+  "FEBR.",
+  "FEBRUAR",
+  "FEBRUAR.",
+  "FF.",
+  "Feb",
+  "Feb.",
+  "Febr",
+  "Febr.",
+  "Februar",
+  "Februar.",
+  "GR.",
+  "I",
+  "IAN",
+  "IAN.",
+  "IB.",
+  "ID.",
+  "IL.",
+  "IMP",
+  "IMP.",
+  "IMPP",
+  "IMPP.",
+  "IMPPP",
+  "IMPPP.",
+  "INT",
+  "IUL",
+  "IUL.",
+  "IUN",
+  "IUN.",
+  "Ian",
+  "Ian.",
+  "Id",
+  "Id.",
+  "Imp",
+  "Imp.",
+  "Impp",
+  "Impp.",
+  "Imppp",
+  "Imppp.",
+  "Iul",
+  "Iul.",
+  "Iun",
+  "Iun.",
+  "K",
+  "K.",
+  "KAL",
+  "KAL.",
+  "Kal",
+  "Kal.",
+  "L",
+  "L.",
+  "LL.",
+  "LUR",
+  "M",
+  "M'.",
+  "M.",
+  "MAI",
+  "MAI.",
+  "MAM",
+  "MAM.",
+  "MAR",
+  "MAR.",
+  "MART",
+  "MART.",
+  "MB.",
+  "MBR",
+  "MED",
+  "MED.",
+  "MP.",
+  "MPP",
+  "Mai",
+  "Mai.",
+  "Mam",
+  "Mam.",
+  "Mar",
+  "Mar.",
+  "Mart",
+  "Mart.",
+  "Med",
+  "Med.",
+  "M\u2019.",
+  "N",
+  "N.",
+  "NN",
+  "NN.",
+  "NOB",
+  "NOB.",
+  "NON",
+  "NON.",
+  "NOU",
+  "NOU.",
+  "NOUEMB",
+  "NOUEMB.",
+  "NOV",
+  "NOV.",
+  "NOVEMB",
+  "NOVEMB.",
+  "NS.",
+  "NSS",
+  "NT.",
+  "Nn",
+  "Nn.",
+  "Nob",
+  "Nob.",
+  "Non",
+  "Non.",
+  "Nou",
+  "Nou.",
+  "Nouemb",
+  "Nouemb.",
+  "Nov",
+  "Nov.",
+  "Novemb",
+  "Novemb.",
+  "O",
+  "O.O",
+  "O.o",
+  "OB.",
+  "OCT",
+  "OCT.",
+  "OCTOB",
+  "OCTOB.",
+  "OL.",
+  "OLL",
+  "ON.",
+  "ONS",
+  "OP.",
+  "OPET",
+  "OPET.",
+  "ORD",
+  "ORD.",
+  "OS.",
+  "OSS",
+  "OST",
+  "OU.",
+  "OV.",
+  "O_O",
+  "O_o",
+  "Oct",
+  "Oct.",
+  "Octob",
+  "Octob.",
+  "Opet",
+  "Opet.",
+  "Ord",
+  "Ord.",
+  "P",
+  "P.",
+  "PAUL",
+  "PAUL.",
+  "PET",
+  "PF",
+  "PF.",
+  "PL",
+  "PL.",
+  "PLUR",
+  "PLUR.",
+  "POST",
+  "POST.",
+  "PP",
+  "PP.",
+  "PPP",
+  "PR.",
+  "PRID",
+  "PRID.",
+  "PRO",
+  "PRO.",
+  "PROCOS",
+  "PROCOS.",
+  "PT.",
+  "Paul",
+  "Paul.",
+  "Pf",
+  "Pf.",
+  "Pl",
+  "Pl.",
+  "Plur",
+  "Plur.",
+  "Post",
+  "Post.",
+  "Pp",
+  "Pp.",
+  "Prid",
+  "Prid.",
+  "Pro",
+  "Pro.",
+  "Procos",
+  "Procos.",
+  "Q",
+  "Q.",
+  "QUINT",
+  "QUINT.",
+  "Quint",
+  "Quint.",
+  "RD.",
+  "RIB",
+  "RID",
+  "RIL",
+  "RO.",
+  "RT.",
+  "S",
+  "S.",
+  "S.C.",
+  "SCR",
+  "SCR.",
+  "SEPT",
+  "SEPT.",
+  "SEPTEMB",
+  "SEPTEMB.",
+  "SER",
+  "SER.",
+  "SERT",
+  "SERT.",
+  "SEX",
+  "SEX.",
+  "SEXT",
+  "SEXT.",
+  "SS.",
+  "ST",
+  "ST.",
+  "STA",
+  "STA.",
+  "SUFF",
+  "SUFF.",
+  "Scr",
+  "Scr.",
+  "Sept",
+  "Sept.",
+  "Septemb",
+  "Septemb.",
+  "Ser",
+  "Ser.",
+  "Sert",
+  "Sert.",
+  "Sex",
+  "Sex.",
+  "Sext",
+  "Sext.",
+  "St",
+  "St.",
+  "Sta",
+  "Sta.",
+  "Suff",
+  "Suff.",
+  "T",
+  "T.",
+  "TA.",
+  "TI",
+  "TI.",
+  "TOB",
+  "TRIB",
+  "TRIB.",
+  "Ti",
+  "Ti.",
+  "Trib",
+  "Trib.",
+  "U",
+  "U.",
+  "UAR",
+  "UFF",
+  "UG.",
+  "UL.",
+  "UN.",
+  "UOL",
+  "UOL.",
+  "UOP",
+  "UOP.",
+  "UR.",
+  "UU",
+  "UU.",
+  "Uol",
+  "Uol.",
+  "Uop",
+  "Uop.",
+  "Uu",
+  "Uu.",
+  "V",
+  "V.",
+  "V.V",
+  "VOL",
+  "VOL.",
+  "VOP",
+  "VOP.",
+  "VV",
+  "VV.",
+  "V_V",
+  "Vol",
+  "Vol.",
+  "Vop",
+  "Vop.",
+  "Vv",
+  "Vv.",
+  "X'.",
+  "X++",
+  "X.",
+  "X.X",
+  "X.X.",
+  "X.X.X.",
+  "X.x",
+  "XD",
+  "XDD",
+  "XT.",
+  "XX",
+  "XX.",
+  "XXX",
+  "XXX.",
+  "XXXX",
+  "XXXX.",
+  "X_X",
+  "X_x",
+  "Xx",
+  "Xx.",
+  "Xxx",
+  "Xxx.",
+  "Xxxx",
+  "Xxxx.",
+  "Xxxxx",
+  "Xxxxx.",
+  "X\u2019.",
+  "[",
+  "[-:",
+  "[:",
+  "[=",
+  "\\",
+  "\\\")",
+  "\\n",
+  "\\t",
+  "\\x",
+  "]",
+  "]=",
+  "^",
+  "^_^",
+  "^__^",
+  "^___^",
+  "_*)",
+  "_-)",
+  "_.)",
+  "_<)",
+  "_^)",
+  "__-",
+  "__^",
+  "_\u00ac)",
+  "_\u0ca0)",
+  "a",
+  "a.",
+  "a.d",
+  "a.d.",
+  "a.u.c",
+  "a.u.c.",
+  "aa",
+  "aa.",
+  "aaa",
+  "aaa.",
+  "acc",
+  "acc.",
+  "ace",
+  "aes",
+  "agr",
+  "agr.",
+  "ai.",
+  "al.",
+  "am.",
+  "an.",
+  "ap",
+  "ap.",
+  "apr",
+  "apr.",
+  "april",
+  "april.",
+  "ar.",
+  "art",
+  "at.",
+  "aug",
+  "aug.",
+  "aul",
+  "b",
+  "b.",
+  "bis",
+  "br.",
+  "c",
+  "c++",
+  "c.",
+  "caes",
+  "caes.",
+  "caess",
+  "caess.",
+  "cc.",
+  "ce>",
+  "cn",
+  "cn.",
+  "coll",
+  "coll.",
+  "cons",
+  "cons.",
+  "conss",
+  "conss.",
+  "cos",
+  "cos.",
+  "coss",
+  "coss.",
+  "cr.",
+  "ct.",
+  "cum",
+  "d",
+  "d)",
+  "d-",
+  "d-)",
+  "d-X",
+  "d.",
+  "d.N.",
+  "d.d",
+  "d.n",
+  "d.n.",
+  "d.x",
+  "dX",
+  "d_d",
+  "d_x",
+  "dat",
+  "dat.",
+  "dd",
+  "dd.",
+  "ddd",
+  "dec",
+  "dec.",
+  "decemb",
+  "decemb.",
+  "decembr",
+  "decembr.",
+  "e",
+  "e.",
+  "eb.",
+  "ebr",
+  "ec.",
+  "ed.",
+  "emb",
+  "ept",
+  "er.",
+  "ert",
+  "es.",
+  "ess",
+  "et.",
+  "ex.",
+  "ext",
+  "f",
+  "f.",
+  "feb",
+  "feb.",
+  "febr",
+  "febr.",
+  "februar",
+  "februar.",
+  "ff.",
+  "g",
+  "g.",
+  "gr.",
+  "h",
+  "h.",
+  "i",
+  "i.",
+  "ian",
+  "ian.",
+  "ib.",
+  "id",
+  "id.",
+  "il.",
+  "imp",
+  "imp.",
+  "impp",
+  "impp.",
+  "imppp",
+  "imppp.",
+  "int",
+  "iul",
+  "iul.",
+  "iun",
+  "iun.",
+  "j",
+  "j.",
+  "k",
+  "k.",
+  "kal",
+  "kal.",
+  "l",
+  "l.",
+  "la",
+  "ll.",
+  "lur",
+  "m",
+  "m'.",
+  "m.",
+  "mai",
+  "mai.",
+  "mam",
+  "mam.",
+  "mar",
+  "mar.",
+  "mart",
+  "mart.",
+  "mb.",
+  "mbr",
+  "me",
+  "med",
+  "med.",
+  "mp.",
+  "mpp",
+  "m\u2019.",
+  "n",
+  "n.",
+  "nn.",
+  "nob",
+  "nob.",
+  "nobis",
+  "non",
+  "non.",
+  "nou",
+  "nou.",
+  "nouemb",
+  "nouemb.",
+  "nov",
+  "nov.",
+  "novemb",
+  "novemb.",
+  "ns.",
+  "nss",
+  "nt.",
+  "o",
+  "o.",
+  "o.0",
+  "o.O",
+  "o.o",
+  "o_0",
+  "o_O",
+  "o_o",
+  "ob.",
+  "oct",
+  "oct.",
+  "octob",
+  "octob.",
+  "ol.",
+  "oll",
+  "on.",
+  "ons",
+  "op.",
+  "opet",
+  "opet.",
+  "ord",
+  "ord.",
+  "os.",
+  "oss",
+  "ost",
+  "ou.",
+  "ov.",
+  "p",
+  "p.",
+  "paul",
+  "paul.",
+  "pet",
+  "pf",
+  "pf.",
+  "pl",
+  "pl.",
+  "plur",
+  "plur.",
+  "post",
+  "post.",
+  "pp",
+  "pp.",
+  "ppp",
+  "pr.",
+  "prid",
+  "prid.",
+  "pro",
+  "pro.",
+  "procos",
+  "procos.",
+  "pt.",
+  "q",
+  "q.",
+  "quint",
+  "quint.",
+  "r",
+  "r.",
+  "rd.",
+  "rib",
+  "rid",
+  "ril",
+  "ro.",
+  "rt.",
+  "s",
+  "s.",
+  "s.c",
+  "s.c.",
+  "scr",
+  "scr.",
+  "sept",
+  "sept.",
+  "septemb",
+  "septemb.",
+  "ser",
+  "ser.",
+  "sert",
+  "sert.",
+  "sex",
+  "sex.",
+  "sext",
+  "sext.",
+  "space",
+  "ss.",
+  "st",
+  "st.",
+  "sta",
+  "sta.",
+  "suff",
+  "suff.",
+  "t",
+  "t.",
+  "ta.",
+  "te",
+  "ti",
+  "ti.",
+  "tob",
+  "trib",
+  "trib.",
+  "u",
+  "u.",
+  "u.c",
+  "uar",
+  "uff",
+  "ug.",
+  "ul.",
+  "un.",
+  "uobis",
+  "uol",
+  "uol.",
+  "uop",
+  "uop.",
+  "ur.",
+  "uu",
+  "uu.",
+  "v",
+  "v.",
+  "v.v",
+  "v_v",
+  "vobis",
+  "vol",
+  "vol.",
+  "vop",
+  "vop.",
+  "vv",
+  "vv.",
+  "w",
+  "w.",
+  "x",
+  "x'.",
+  "x.",
+  "x.X",
+  "x.X.",
+  "x.d",
+  "x.x",
+  "x.x.",
+  "x.x.x",
+  "x.x.x.",
+  "xD",
+  "xDD",
+  "xX",
+  "xXX",
+  "x_X",
+  "x_d",
+  "x_x",
+  "xd",
+  "xdd",
+  "xt.",
+  "xx",
+  "xx.",
+  "xxx",
+  "xxx.",
+  "xxxx",
+  "xxxx.",
+  "x\u2019.",
+  "x\ufe35x",
+  "y",
+  "y.",
+  "z",
+  "z.",
+  "|",
+  "}",
+  "\u00a0",
+  "\u00ac",
+  "\u00ac_\u00ac",
+  "\u00af",
+  "\u00af\\(x)/\u00af",
+  "\u00af\\(\u30c4)/\u00af",
+  "\u00b0",
+  "\u00b0C.",
+  "\u00b0F.",
+  "\u00b0K.",
+  "\u00b0X.",
+  "\u00b0c.",
+  "\u00b0f.",
+  "\u00b0k.",
+  "\u00b0x.",
+  "\u00e4",
+  "\u00e4.",
+  "\u00f6",
+  "\u00f6.",
+  "\u00fc",
+  "\u00fc.",
+  "\u0ca0",
+  "\u0ca0_\u0ca0",
+  "\u0ca0\ufe35\u0ca0",
+  "\u2014",
+  "\u2019",
+  "\u2019-(",
+  "\u2019-)",
+  "\u2019\u2019",
+  "\u2501",
+  "\u253b",
+  "\u253b\u2501\u253b",
+  "\u256f",
+  "\u25a1",
+  "\ufe35",
+  "\uff09"
+]

vocab/vectors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b9e7d75775781430de3b558b9ec4263bd6b45f9b77dc45f16aea5541866b65
+size 60000128

vocab/vectors.cfg

@@ -0,0 +1,10 @@
+{
+  "mode":"floret",
+  "minn":3,
+  "maxn":6,
+  "hash_count":2,
+  "hash_seed":2166136261,
+  "bow":"<",
+  "eow":">",
+  "attr":65
+}