kenkwon commited on
Commit
3e9edf9
·
1 Parent(s): cdafa72

Update spaCy model V1.0. Fixed LFS tracking for binary files.

Browse files
Files changed (13) hide show
  1. .gitattributes +2 -37
  2. README.md +17 -14
  3. config.cfg +30 -40
  4. meta.json +37 -7
  5. ner/model +3 -0
  6. ner/moves +1 -1
  7. tok2vec/cfg +3 -0
  8. tok2vec/model +3 -0
  9. tokenizer +3 -0
  10. tokenizer/cfg +0 -1
  11. transformer/cfg +0 -3
  12. vocab/lookups.bin +3 -0
  13. vocab/strings.json +810 -58
.gitattributes CHANGED
@@ -1,38 +1,3 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ner/model filter=lfs diff=lfs merge=lfs -text
37
- transformer/model filter=lfs diff=lfs merge=lfs -text
38
- vi_ner_task-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ner/model filter=lfs diff=lfs merge=lfs -text
2
+ tok2vec/model filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,30 +1,33 @@
1
- ---
2
- tags:
3
- - spacy
4
- - token-classification
5
- language:
6
- - vi
7
- ---
8
  | Feature | Description |
9
  | --- | --- |
10
  | **Name** | `vi_ner_task` |
11
- | **Version** | `0.0.0` |
12
  | **spaCy** | `>=3.7.5,<3.8.0` |
13
- | **Default Pipeline** | `transformer`, `ner` |
14
- | **Components** | `transformer`, `ner` |
15
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
16
  | **Sources** | n/a |
17
  | **License** | n/a |
18
- | **Author** | [n/a]() |
19
 
20
  ### Label Scheme
21
 
22
  <details>
23
 
24
- <summary>View label scheme (3 labels for 1 components)</summary>
25
 
26
  | Component | Labels |
27
  | --- | --- |
28
- | **`ner`** | `DATE`, `TASK`, `TIME` |
29
 
30
- </details>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  | Feature | Description |
2
  | --- | --- |
3
  | **Name** | `vi_ner_task` |
4
+ | **Version** | `1.0.0` |
5
  | **spaCy** | `>=3.7.5,<3.8.0` |
6
+ | **Default Pipeline** | `tok2vec`, `ner` |
7
+ | **Components** | `tok2vec`, `ner` |
8
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
9
  | **Sources** | n/a |
10
  | **License** | n/a |
11
+ | **Author** | [Chánh Hỷ - hlchy11997@gmail.com]() |
12
 
13
  ### Label Scheme
14
 
15
  <details>
16
 
17
+ <summary>View label scheme (4 labels for 1 components)</summary>
18
 
19
  | Component | Labels |
20
  | --- | --- |
21
+ | **`ner`** | `DATE`, `PERSON`, `TASK`, `TIME` |
22
 
23
+ </details>
24
+
25
+ ### Accuracy
26
+
27
+ | Type | Score |
28
+ | --- | --- |
29
+ | `ENTS_F` | 88.71 |
30
+ | `ENTS_P` | 89.19 |
31
+ | `ENTS_R` | 88.24 |
32
+ | `TOK2VEC_LOSS` | 27395.24 |
33
+ | `NER_LOSS` | 12711.07 |
config.cfg CHANGED
@@ -1,27 +1,24 @@
1
  [paths]
2
- train = null
3
- dev = null
4
  vectors = null
5
  init_tok2vec = null
6
 
7
  [system]
8
- seed = 0
9
  gpu_allocator = null
 
10
 
11
  [nlp]
12
- lang = "vi"
13
- pipeline = ["transformer","ner"]
 
14
  disabled = []
15
  before_creation = null
16
  after_creation = null
17
  after_pipeline_creation = null
18
- batch_size = 1000
19
  vectors = {"@vectors":"spacy.Vectors.v1"}
20
 
21
- [nlp.tokenizer]
22
- @tokenizers = "spacy.vi.VietnameseTokenizer"
23
- use_pyvi = true
24
-
25
  [components]
26
 
27
  [components.ner]
@@ -41,56 +38,51 @@ use_upper = true
41
  nO = null
42
 
43
  [components.ner.model.tok2vec]
44
- @architectures = "spacy.HashEmbedCNN.v2"
45
- pretrained_vectors = null
46
- width = 96
47
- depth = 4
48
- embed_size = 2000
49
- window_size = 1
50
- maxout_pieces = 3
51
- subword_features = true
52
 
53
- [components.transformer]
54
- factory = "transformer"
55
- max_batch_items = 4096
56
- set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
57
 
58
- [components.transformer.model]
59
- @architectures = "spacy-transformers.TransformerModel.v3"
60
- name = "vinai/phobert-base"
61
- mixed_precision = false
62
 
63
- [components.transformer.model.get_spans]
64
- @span_getters = "spacy-transformers.strided_spans.v1"
65
- window = 128
66
- stride = 96
 
 
67
 
68
- [components.transformer.model.grad_scaler_config]
69
-
70
- [components.transformer.model.tokenizer_config]
71
- use_fast = true
72
-
73
- [components.transformer.model.transformer_config]
74
 
75
  [corpora]
76
 
77
  [corpora.dev]
78
  @readers = "spacy.Corpus.v1"
79
  path = ${paths.dev}
80
- gold_preproc = false
81
  max_length = 0
 
82
  limit = 0
83
  augmenter = null
84
 
85
  [corpora.train]
86
  @readers = "spacy.Corpus.v1"
87
  path = ${paths.train}
88
- gold_preproc = false
89
  max_length = 0
 
90
  limit = 0
91
  augmenter = null
92
 
93
  [training]
 
 
94
  seed = ${system.seed}
95
  gpu_allocator = ${system.gpu_allocator}
96
  dropout = 0.1
@@ -101,8 +93,6 @@ max_steps = 20000
101
  eval_frequency = 200
102
  frozen_components = []
103
  annotating_components = []
104
- dev_corpus = "corpora.dev"
105
- train_corpus = "corpora.train"
106
  before_to_disk = null
107
  before_update = null
108
 
 
1
  [paths]
2
+ train = "train.spacy"
3
+ dev = "dev.spacy"
4
  vectors = null
5
  init_tok2vec = null
6
 
7
  [system]
 
8
  gpu_allocator = null
9
+ seed = 0
10
 
11
  [nlp]
12
+ lang = "xx"
13
+ pipeline = ["tok2vec","ner"]
14
+ batch_size = 1000
15
  disabled = []
16
  before_creation = null
17
  after_creation = null
18
  after_pipeline_creation = null
19
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
  vectors = {"@vectors":"spacy.Vectors.v1"}
21
 
 
 
 
 
22
  [components]
23
 
24
  [components.ner]
 
38
  nO = null
39
 
40
  [components.ner.model.tok2vec]
41
+ @architectures = "spacy.Tok2VecListener.v1"
42
+ width = ${components.tok2vec.model.encode.width}
43
+ upstream = "*"
 
 
 
 
 
44
 
45
+ [components.tok2vec]
46
+ factory = "tok2vec"
 
 
47
 
48
+ [components.tok2vec.model]
49
+ @architectures = "spacy.Tok2Vec.v2"
 
 
50
 
51
+ [components.tok2vec.model.embed]
52
+ @architectures = "spacy.MultiHashEmbed.v2"
53
+ width = ${components.tok2vec.model.encode.width}
54
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
55
+ rows = [5000,1000,2500,2500]
56
+ include_static_vectors = false
57
 
58
+ [components.tok2vec.model.encode]
59
+ @architectures = "spacy.MaxoutWindowEncoder.v2"
60
+ width = 96
61
+ depth = 4
62
+ window_size = 1
63
+ maxout_pieces = 3
64
 
65
  [corpora]
66
 
67
  [corpora.dev]
68
  @readers = "spacy.Corpus.v1"
69
  path = ${paths.dev}
 
70
  max_length = 0
71
+ gold_preproc = false
72
  limit = 0
73
  augmenter = null
74
 
75
  [corpora.train]
76
  @readers = "spacy.Corpus.v1"
77
  path = ${paths.train}
 
78
  max_length = 0
79
+ gold_preproc = false
80
  limit = 0
81
  augmenter = null
82
 
83
  [training]
84
+ dev_corpus = "corpora.dev"
85
+ train_corpus = "corpora.train"
86
  seed = ${system.seed}
87
  gpu_allocator = ${system.gpu_allocator}
88
  dropout = 0.1
 
93
  eval_frequency = 200
94
  frozen_components = []
95
  annotating_components = []
 
 
96
  before_to_disk = null
97
  before_update = null
98
 
meta.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "lang":"vi",
3
- "name":"ner_task",
4
- "version":"0.0.0",
5
  "description":"",
6
  "author":"",
7
  "email":"",
@@ -16,27 +16,57 @@
16
  "name":null
17
  },
18
  "labels":{
19
- "transformer":[
20
 
21
  ],
22
  "ner":[
23
  "DATE",
 
24
  "TASK",
25
  "TIME"
26
  ]
27
  },
28
  "pipeline":[
29
- "transformer",
30
  "ner"
31
  ],
32
  "components":[
33
- "transformer",
34
  "ner"
35
  ],
36
  "disabled":[
37
 
38
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "requirements":[
40
- "spacy-transformers>=1.3.9,<1.4.0"
41
  ]
42
  }
 
1
  {
2
+ "lang":"xx",
3
+ "name":"vi_ner_task",
4
+ "version":"1.0.0",
5
  "description":"",
6
  "author":"",
7
  "email":"",
 
16
  "name":null
17
  },
18
  "labels":{
19
+ "tok2vec":[
20
 
21
  ],
22
  "ner":[
23
  "DATE",
24
+ "PERSON",
25
  "TASK",
26
  "TIME"
27
  ]
28
  },
29
  "pipeline":[
30
+ "tok2vec",
31
  "ner"
32
  ],
33
  "components":[
34
+ "tok2vec",
35
  "ner"
36
  ],
37
  "disabled":[
38
 
39
  ],
40
+ "performance":{
41
+ "ents_f":0.8870967742,
42
+ "ents_p":0.8918918919,
43
+ "ents_r":0.8823529412,
44
+ "ents_per_type":{
45
+ "TIME":{
46
+ "p":0.9512195122,
47
+ "r":0.9069767442,
48
+ "f":0.9285714286
49
+ },
50
+ "DATE":{
51
+ "p":0.8888888889,
52
+ "r":0.8888888889,
53
+ "f":0.8888888889
54
+ },
55
+ "TASK":{
56
+ "p":0.8103448276,
57
+ "r":0.8103448276,
58
+ "f":0.8103448276
59
+ },
60
+ "PERSON":{
61
+ "p":0.96875,
62
+ "r":0.96875,
63
+ "f":0.96875
64
+ }
65
+ },
66
+ "tok2vec_loss":273.9524151373,
67
+ "ner_loss":127.1106786892
68
+ },
69
  "requirements":[
70
+
71
  ]
72
  }
ner/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9ea7ea2de49d995def50a6dfd9cedef1bd6d73a5c21ff5b7f0a9f1c714c4f8
3
+ size 130628
ner/moves CHANGED
@@ -1 +1 @@
1
- ��moves٨{"0":{},"1":{"DATE":-1,"TIME":-2,"TASK":-3},"2":{"DATE":-1,"TIME":-2,"TASK":-3},"3":{"DATE":-1,"TIME":-2,"TASK":-3},"4":{"":1,"DATE":-1,"TIME":-2,"TASK":-3},"5":{"":1}}�cfg��neg_key�
 
1
+ ��moves��{"0":{},"1":{"TASK":2657,"DATE":771,"TIME":597,"PERSON":360},"2":{"TASK":2657,"DATE":771,"TIME":597,"PERSON":360},"3":{"TASK":2657,"DATE":771,"TIME":597,"PERSON":360},"4":{"TASK":2657,"DATE":771,"TIME":597,"PERSON":360,"":1},"5":{"":1}}�cfg��neg_key�
tok2vec/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+
3
+ }
tok2vec/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4bab442ff6d338b1ac05318823db887132498a5fc58a8759ebf1cd34c84df9
3
+ size 6009091
tokenizer ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ��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�
2
+ ��A�
3
+ � ��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�;-)�;-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.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�
tokenizer/cfg DELETED
@@ -1 +0,0 @@
1
- {"use_pyvi":true}
 
 
transformer/cfg DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "max_batch_items":4096
3
- }
 
 
 
 
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json CHANGED
@@ -1,13 +1,75 @@
1
  [
2
- " Ba",
3
- " T\u01b0",
4
- " ba",
5
- " t\u01b0",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "/10",
7
  "/11",
8
  "/12",
 
 
 
 
 
9
  "0/1",
10
  "0/9",
 
 
11
  "1",
12
  "1/10",
13
  "1/12",
@@ -15,17 +77,38 @@
15
  "10/10",
16
  "10/11",
17
  "10h",
 
18
  "11",
19
  "11h30",
 
20
  "12/10",
 
 
 
21
  "14",
 
 
22
  "14h",
 
23
  "15",
24
  "15/10",
25
  "15/11",
 
 
 
26
  "17",
27
  "17/10",
 
 
 
 
 
28
  "18h",
 
 
 
 
 
29
  "2",
30
  "2/1",
31
  "2/10",
@@ -34,6 +117,11 @@
34
  "20/11",
35
  "20/12",
36
  "20h",
 
 
 
 
 
37
  "23/12",
38
  "23h59",
39
  "25/10",
@@ -45,52 +133,184 @@
45
  "30/11",
46
  "30/12",
47
  "30/9",
 
 
 
48
  "4",
 
49
  "4h",
50
  "5",
51
  "5h",
52
  "6",
 
 
 
53
  "7",
54
  "7h",
 
55
  "8",
 
 
 
 
 
 
 
56
  "8h",
 
 
57
  "9",
58
  "9h",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  "A",
 
60
  "AI",
 
 
61
  "An",
62
  "Anh",
63
  "B",
 
64
  "Ba",
65
  "Backend",
66
  "B\u00e1ch",
67
  "B\u00ecnh",
 
68
  "B\u1ea3y",
69
  "B\u1ec7nh",
70
  "C",
 
 
 
 
 
 
71
  "Chi\u1ec1u",
72
  "Ch\u00fang",
73
  "Ch\u01a1i",
74
  "Ch\u1ecb",
75
  "Ch\u1ee7",
76
- "Ch\u1ee7 Nh\u1eadt",
77
- "Ch\u1ee7 nh\u1eadt",
78
  "Cu\u1ed1i",
79
  "C\u01b0\u1eddng",
80
  "C\u1ea3",
 
81
  "D",
82
  "Data",
 
83
  "Design",
84
  "Dev",
85
  "DevOps",
86
  "Dung",
87
  "D\u0169ng",
88
  "D\u1ecdn",
 
 
89
  "F",
 
90
  "FPT",
 
91
  "Frontend",
92
  "G",
93
  "G\u00f2n",
 
94
  "H",
95
  "Hai",
96
  "Hoa",
@@ -99,21 +319,37 @@
99
  "Ho\u00e1",
100
  "Huy",
101
  "H\u00e0",
 
102
  "H\u00f3a",
103
  "H\u00f4m",
104
  "H\u00f9ng",
105
  "H\u01b0ng",
 
 
106
  "H\u1ea1nh",
107
  "H\u1ea3i",
 
108
  "H\u1ecdc",
 
 
 
 
109
  "K",
 
110
  "Khoa",
 
 
111
  "Kh\u1ea3i",
 
 
 
112
  "L",
113
  "Lan",
114
  "Linh",
115
  "L\u00e0m",
 
116
  "L\u00e2m",
 
117
  "L\u1ea1t",
118
  "L\u1ecbch",
119
  "M",
@@ -124,29 +360,49 @@
124
  "M\u00f9ng",
125
  "M\u1ed1t",
126
  "N",
 
127
  "Nam",
 
 
 
128
  "Nghe",
129
  "Ng\u00e0y",
130
  "Ng\u1ecdc",
131
  "Ng\u1eef",
132
  "Nh\u00f3m",
133
  "Nh\u1eadt",
 
134
  "N\u0103m",
135
  "N\u1ea5u",
136
  "N\u1eb5ng",
137
  "N\u1ed9i",
 
 
 
 
 
138
  "Ops",
139
  "P",
140
  "Ph\u00e1p",
141
  "Ph\u00f2ng",
142
  "Ph\u00fac",
143
  "Ph\u01b0\u01a1ng",
 
 
144
  "Product",
 
145
  "Q",
146
  "QA",
 
 
147
  "Qu\u00e2n",
 
148
  "ROOT",
 
 
 
149
  "S",
 
150
  "Sinh",
151
  "S\u00e0i",
152
  "S\u00e1ng",
@@ -155,182 +411,333 @@
155
  "S\u1ebfp",
156
  "T",
157
  "TASK",
 
158
  "Team",
 
159
  "Th\u00e1ng",
 
160
  "Th\u1ea3o",
161
  "Th\u1eafng",
 
162
  "Th\u1ee9",
163
- "Th\u1ee9 3",
164
- "Th\u1ee9 Ba",
165
- "Th\u1ee9 B\u1ea3y",
166
- "Th\u1ee9 Hai",
167
- "Th\u1ee9 N\u0103m",
168
- "Th\u1ee9 S\u00e1u",
169
- "Th\u1ee9 T\u01b0",
170
- "Th\u1ee9 ba",
171
- "Th\u1ee9 b\u1ea3y",
172
- "Th\u1ee9 hai",
173
- "Th\u1ee9 n\u0103m",
174
- "Th\u1ee9 s\u00e1u",
175
- "Th\u1ee9 t\u01b0",
176
  "Tin",
177
  "Ti\u1ebfng",
178
  "To\u00e1n",
179
  "Tr\u00e2m",
180
  "Tr\u01b0a",
 
181
  "Tu\u1ea5n",
182
  "Tu\u1ea7n",
 
183
  "T\u00e0u",
184
  "T\u00f4i",
185
  "T\u01b0",
186
  "T\u1eadp",
187
  "T\u1ed1i",
188
  "V",
 
 
 
189
  "Vi\u1ebft",
190
  "Vi\u1ec7t",
 
191
  "V\u0103n",
192
  "V\u0169ng",
193
  "V\u1eadt",
 
 
 
 
 
 
194
  "XX",
195
  "XXX",
 
 
 
196
  "Xem",
197
  "Xx",
198
  "Xxx",
199
- "Xxx Xx",
200
- "Xxx Xxx",
201
- "Xxx Xxxx",
202
- "Xxx d",
203
- "Xxx xx",
204
- "Xxx xxx",
205
- "Xxx xxxx",
206
  "XxxXxx",
207
  "Xxxx",
208
  "Xxxxx",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  "a",
 
 
 
 
 
210
  "ai",
211
  "ail",
212
  "all",
213
  "ame",
214
  "an",
 
215
  "anh",
 
 
216
  "ase",
217
  "ask",
218
  "assignment",
219
  "ata",
220
  "auth",
221
  "b",
 
222
  "ba",
223
  "backend",
 
 
224
  "banh",
 
 
 
 
 
225
  "bug",
226
  "bu\u1ed5i",
227
  "b\u00e0i",
 
 
228
  "b\u00e1ch",
 
 
229
  "b\u00e1o",
 
230
  "b\u00e8",
 
 
231
  "b\u00ecnh",
232
  "b\u00f3ng",
 
233
  "b\u1ea1n",
234
  "b\u1ea3n",
 
235
  "b\u1ea3y",
236
  "b\u1eaft",
237
  "b\u1ec7nh",
238
  "b\u1ecb",
 
 
239
  "b\u1ed9",
 
240
  "c",
 
 
 
241
  "call",
 
242
  "cao",
 
 
 
 
 
243
  "chi\u1ec1u",
244
  "cho",
 
 
245
  "chuy\u1ec1n",
246
  "chu\u1ea9n",
 
247
  "ch\u00ednh",
 
 
248
  "ch\u00fang",
249
  "ch\u01a1i",
 
250
  "ch\u1ea1y",
 
251
  "ch\u1ecb",
 
 
252
  "ch\u1ee3",
253
  "ch\u1ee7",
254
- "ch\u1ee7 nh\u1eadt",
255
  "ch\u1ee9c",
 
 
 
256
  "code",
257
  "con",
258
  "concert",
 
 
259
  "cu\u1ed1i",
 
 
260
  "c\u00e0",
 
261
  "c\u00e1",
 
262
  "c\u00e1o",
 
 
263
  "c\u00f3",
264
  "c\u00f4",
265
  "c\u00f4ng",
266
  "c\u00f9ng",
 
267
  "c\u0169",
268
  "c\u01a1m",
269
  "c\u01b0\u1edbi",
270
  "c\u01b0\u1eddng",
 
271
  "c\u1ea3",
 
272
  "c\u1ea7n",
 
273
  "c\u1eadp",
 
 
 
 
274
  "d",
 
 
 
 
 
 
 
275
  "d/d",
276
  "d/dd",
 
 
 
 
277
  "data",
278
  "database",
 
279
  "dd",
280
  "dd/d",
281
  "dd/dd",
 
 
282
  "ddx",
283
  "ddxdd",
 
284
  "deo",
285
  "deploy",
286
  "design",
287
  "dev",
288
  "devops",
 
289
  "du",
290
  "dung",
 
291
  "dx",
 
 
292
  "d\u0169ng",
 
293
  "d\u1ea1o",
 
 
294
  "d\u1eabn",
 
 
295
  "d\u1eb9p",
 
296
  "d\u1ecdn",
297
  "d\u1ee5c",
298
  "d\u1ee5ng",
 
299
  "d\u1ef1",
300
  "e",
 
301
  "eam",
 
 
302
  "email",
303
  "end",
304
  "ent",
305
  "ert",
306
  "est",
307
  "f",
 
 
 
 
 
308
  "fix",
309
  "fpt",
310
  "frontend",
311
  "g",
 
312
  "game",
 
313
  "ghe",
 
 
 
314
  "gia",
 
 
 
315
  "gi\u00e1o",
316
  "gi\u00e3n",
317
  "gi\u1ea3ng",
 
318
  "gi\u1edd",
319
  "guitar",
320
  "gym",
321
  "g\u00e0y",
 
322
  "g\u00f2n",
 
323
  "g\u1eb7p",
324
  "g\u1ecdc",
325
  "g\u1ecdi",
326
  "g\u1eedi",
327
  "h",
 
 
 
 
 
328
  "h30",
 
 
329
  "h59",
330
  "hai",
331
  "ham",
 
332
  "him",
 
 
 
333
  "hoa",
 
 
334
  "hop",
335
  "ho\u00e0n",
336
  "ho\u00e0ng",
@@ -342,49 +749,91 @@
342
  "h\u00e0ng",
343
  "h\u00e1m",
344
  "h\u00e1p",
 
 
345
  "h\u00e2n",
346
  "h\u00eam",
347
  "h\u00ecnh",
 
348
  "h\u00f3a",
349
  "h\u00f3m",
 
350
  "h\u00f4m",
351
  "h\u00f9ng",
352
  "h\u00fac",
353
  "h\u00fat",
 
 
354
  "h\u01a1i",
355
  "h\u01b0ng",
 
356
  "h\u01b0\u1edbng",
 
357
  "h\u1ea1c",
 
358
  "h\u1ea1nh",
359
  "h\u1ea1y",
360
  "h\u1ea3i",
 
361
  "h\u1ea3o",
 
 
362
  "h\u1ea7u",
 
363
  "h\u1ea9m",
 
 
 
364
  "h\u1eadt",
 
365
  "h\u1eafn",
 
 
366
  "h\u1ebft",
367
  "h\u1ec7",
368
  "h\u1ecdc",
369
  "h\u1ecdp",
370
  "h\u1ecfe",
 
 
 
371
  "h\u1ed3",
 
 
 
 
 
 
372
  "h\u1ee9c",
 
373
  "h\u1ef1c",
 
 
 
 
374
  "ide",
375
  "iew",
376
  "ign",
 
377
  "ile",
 
378
  "ine",
379
  "ing",
380
  "inh",
381
  "int",
 
 
382
  "ive",
383
  "i\u00e1o",
384
  "i\u00e3n",
385
  "i\u00ean",
386
  "i\u00eau",
 
 
 
 
387
  "i\u1ebft",
 
388
  "i\u1ec1n",
389
  "i\u1ec1u",
390
  "i\u1ec3m",
@@ -396,195 +845,368 @@
396
  "i\u1ec7p",
397
  "i\u1ec7t",
398
  "i\u1ec7u",
 
 
399
  "k",
 
 
400
  "khai",
401
  "khi",
 
402
  "khoa",
 
 
 
403
  "kh\u00e1ch",
404
  "kh\u00e1m",
 
 
405
  "kh\u1ea3i",
406
  "kh\u1ea3o",
 
 
407
  "kh\u1ecfe",
408
  "kia",
 
 
 
409
  "ki\u1ec3m",
 
 
 
 
 
410
  "k\u00fd",
411
  "k\u1ebf",
 
 
412
  "k\u1ef9",
413
  "l",
 
414
  "lan",
 
 
 
415
  "linh",
416
  "live",
 
 
 
 
417
  "li\u1ec7u",
 
418
  "loy",
419
  "luy\u1ec7n",
420
  "lu\u1eadn",
 
421
  "l\u00e0m",
 
422
  "l\u00e2m",
 
 
423
  "l\u00fac",
424
  "l\u00fd",
425
  "l\u1ea1i",
426
  "l\u1ea1t",
 
427
  "l\u1eadp",
 
 
428
  "l\u1ecbch",
429
  "l\u1ed7i",
 
 
 
430
  "m",
 
431
  "mai",
432
  "mail",
433
  "marketing",
434
  "minh",
 
435
  "mobile",
436
  "module",
437
  "mua",
438
  "mu\u1ed1n",
 
 
 
 
439
  "m\u00f4n",
440
  "m\u00f9ng",
 
 
 
441
  "m\u1eb9",
442
  "m\u1ec1m",
443
  "m\u1ed1t",
444
  "m\u1ed7i",
 
445
  "m\u1edbi",
 
 
446
  "n",
 
447
  "nam",
448
  "nay",
 
 
 
 
449
  "nghe",
 
450
  "nghi\u1ec7m",
451
  "nghi\u1ec7p",
 
 
 
452
  "ngo\u00e0i",
 
453
  "ng\u00e0y",
 
 
454
  "ng\u1ecdc",
455
  "ng\u1ee7",
456
  "ng\u1eef",
 
 
457
  "nh\u00e0",
 
458
  "nh\u00e2n",
459
  "nh\u00f3m",
460
  "nh\u1ea1c",
 
 
461
  "nh\u1eadt",
 
462
  "nh\u1eafn",
 
463
  "nh\u1edb",
 
464
  "nit",
 
465
  "n\u00e0y",
466
  "n\u00e2ng",
 
467
  "n\u0103m",
468
  "n\u0103ng",
 
469
  "n\u1ea5u",
470
  "n\u1eb5ng",
471
  "n\u1ed9i",
472
  "n\u1ed9p",
473
  "n\u1eefa",
474
  "o",
 
 
 
 
 
 
 
 
475
  "ode",
 
476
  "oga",
 
477
  "ong",
478
  "online",
 
 
 
479
  "o\u00e0i",
480
  "o\u00e0n",
481
  "o\u00e1n",
482
  "o\u1ea1i",
483
  "o\u1ea1n",
484
  "o\u1ea1t",
 
485
  "p",
 
 
 
486
  "pha",
487
  "phim",
488
  "phi\u00ean",
489
  "ph\u00e1p",
 
490
  "ph\u00ea",
491
  "ph\u00f2ng",
492
  "ph\u00fac",
493
  "ph\u00fat",
494
  "ph\u01b0\u01a1ng",
 
495
  "ph\u1ea3i",
 
 
496
  "ph\u1ea9m",
 
497
  "ph\u1ecfng",
 
 
 
 
498
  "product",
 
 
499
  "q",
 
500
  "qa",
 
 
 
 
 
 
 
501
  "qu\u00e2n",
 
502
  "qu\u00fd",
 
 
 
503
  "qu\u1ed1c",
504
  "r",
 
 
505
  "rau",
 
 
 
506
  "release",
 
507
  "review",
 
 
 
 
508
  "r\u00e2m",
 
509
  "r\u0103ng",
510
  "r\u01b0a",
 
 
 
511
  "r\u1ed5",
 
 
512
  "r\u1eeda",
 
513
  "s",
 
514
  "sau",
 
515
  "server",
 
516
  "sinh",
517
  "si\u00eau",
518
  "slide",
519
  "so\u1ea1n",
 
 
520
  "sprint",
521
  "stream",
 
522
  "s\u00e0i",
523
  "s\u00e1ch",
524
  "s\u00e1ng",
 
525
  "s\u00e1u",
 
 
526
  "s\u01a1",
 
 
527
  "s\u1eafp",
528
  "s\u1ebd",
529
  "s\u1ebfp",
 
 
 
530
  "s\u1ee9c",
531
  "s\u1eed",
532
  "s\u1eeda",
 
 
533
  "t",
 
 
 
 
534
  "tar",
535
  "task",
536
  "team",
537
  "test",
538
  "tham",
 
 
539
  "thi",
 
 
540
  "tho\u1ea1i",
 
541
  "thuy\u1ebft",
 
 
542
  "th\u00e0nh",
543
  "th\u00e1ng",
544
  "th\u00eam",
545
  "th\u00ed",
 
 
 
 
 
546
  "th\u01b0",
547
  "th\u1ea3o",
548
  "th\u1ea7u",
 
549
  "th\u1eafng",
550
  "th\u1ec3",
551
  "th\u1ecb",
552
  "th\u1ed1ng",
 
 
553
  "th\u1ee9",
554
- "th\u1ee9 2",
555
- "th\u1ee9 3",
556
- "th\u1ee9 4",
557
- "th\u1ee9 5",
558
- "th\u1ee9 6",
559
- "th\u1ee9 7",
560
- "th\u1ee9 Ba",
561
- "th\u1ee9 B\u1ea3y",
562
- "th\u1ee9 Hai",
563
- "th\u1ee9 N\u0103m",
564
- "th\u1ee9 S\u00e1u",
565
- "th\u1ee9 T\u01b0",
566
- "th\u1ee9 ba",
567
- "th\u1ee9 b\u1ea3y",
568
- "th\u1ee9 hai",
569
- "th\u1ee9 n\u0103m",
570
- "th\u1ee9 s\u00e1u",
571
- "th\u1ee9 t\u01b0",
572
  "th\u1ef1c",
 
573
  "tin",
 
 
 
574
  "ti\u1ebfng",
 
 
575
  "ti\u1ec1n",
576
  "ti\u1ec3u",
577
  "ti\u1ec7c",
 
 
 
578
  "to\u00e1n",
579
  "tra",
580
  "training",
 
 
581
  "tri\u1ec3n",
582
  "trong",
583
  "trung",
 
 
584
  "tr\u00e2m",
 
 
585
  "tr\u00ecnh",
586
  "tr\u01b0a",
587
  "tr\u01b0\u1edbc",
 
 
 
 
 
 
 
588
  "tu\u1ea5n",
589
  "tu\u1ea7n",
590
  "ty",
@@ -592,36 +1214,70 @@
592
  "t\u00e0u",
593
  "t\u00e1c",
594
  "t\u00e2m",
 
 
 
 
 
 
595
  "t\u00f4i",
596
  "t\u01b0",
 
597
  "t\u1ea1i",
 
 
 
598
  "t\u1eadp",
 
 
599
  "t\u1ebf",
 
600
  "t\u1ed1i",
 
 
601
  "t\u1ed5",
 
602
  "t\u1edbi",
603
  "t\u1ee5",
 
 
604
  "t\u1eeb",
605
  "u",
 
 
606
  "uct",
 
607
  "ule",
 
608
  "ung",
609
  "unit",
610
  "uth",
 
 
611
  "u\u00e2n",
 
612
  "u\u1ea5n",
 
613
  "u\u1ea7n",
614
  "u\u1ea9n",
615
  "u\u1eadn",
 
616
  "u\u1ed1c",
617
  "u\u1ed1i",
618
  "u\u1ed1n",
619
  "u\u1ed1ng",
620
  "u\u1ed5i",
 
 
621
  "v",
 
 
 
622
  "ver",
623
- "vi",
624
  "video",
 
 
 
625
  "vi\u00ean",
626
  "vi\u1ebft",
627
  "vi\u1ec7c",
@@ -629,34 +1285,75 @@
629
  "vi\u1ec7t",
630
  "v\u00e0",
631
  "v\u00e0o",
 
632
  "v\u0103n",
633
  "v\u0169ng",
 
634
  "v\u1ea5n",
635
  "v\u1eadt",
 
636
  "v\u1ec1",
637
  "v\u1edbi",
638
  "w",
 
 
639
  "workshop",
640
  "x",
 
 
 
 
 
 
 
 
 
 
 
 
 
641
  "xe",
642
  "xem",
643
  "xin",
 
644
  "xx",
645
  "xxx",
646
- "xxx Xx",
647
- "xxx Xxx",
648
- "xxx d",
649
- "xxx xxx",
650
- "xxx xxxx",
651
  "xxxx",
 
 
652
  "x\u1ebfp",
 
 
653
  "y",
 
654
  "yoga",
 
 
655
  "y\u1ebft",
656
  "y\u1ec1n",
 
657
  "y\u1ec7n",
 
658
  "z",
 
 
 
 
659
  "\u00a0",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
660
  "\u00d4",
661
  "\u00d4n",
662
  "\u00e0ng",
@@ -665,72 +1362,127 @@
665
  "\u00e1ch",
666
  "\u00e1n",
667
  "\u00e1ng",
 
 
668
  "\u00e2ng",
 
 
 
669
  "\u00ecnh",
 
670
  "\u00ednh",
671
  "\u00f2ng",
672
  "\u00f3ng",
673
  "\u00f4",
674
  "\u00f4n",
675
  "\u00f4ng",
 
 
676
  "\u00f9ng",
677
  "\u00fang",
 
 
678
  "\u0103",
679
  "\u0103n",
680
  "\u0103ng",
681
  "\u0110",
682
  "\u0110i",
683
  "\u0110\u00e0",
 
684
  "\u0110\u1ecba",
685
  "\u0110\u1ecdc",
686
  "\u0110\u1ee9c",
 
687
  "\u0111",
688
  "\u0111a",
 
689
  "\u0111i",
690
  "\u0111i\u1ec7n",
691
  "\u0111\u00e0",
 
 
692
  "\u0111\u00e1",
 
 
693
  "\u0111\u00ecnh",
694
  "\u0111\u00f3n",
695
  "\u0111\u00f3ng",
 
 
696
  "\u0111\u01b0a",
 
697
  "\u0111\u1ea7u",
 
698
  "\u0111\u1eb7t",
699
  "\u0111\u1ebfn",
700
  "\u0111\u1ec1",
 
701
  "\u0111\u1ecba",
 
702
  "\u0111\u1ecdc",
 
703
  "\u0111\u1ed1i",
704
  "\u0111\u1ed3",
705
  "\u0111\u1ed3ng",
 
 
 
706
  "\u0111\u1ed9i",
 
 
 
707
  "\u0111\u1ee9c",
 
708
  "\u0169ng",
709
  "\u01a1ng",
 
 
 
710
  "\u01b0ng",
 
711
  "\u01b0\u1edbc",
712
  "\u01b0\u1edbi",
 
 
 
 
 
713
  "\u1ea1ch",
714
  "\u1ea1nh",
 
715
  "\u1ea3ng",
 
 
 
716
  "\u1eafng",
 
717
  "\u1eb5ng",
 
718
  "\u1ebfng",
719
  "\u1ec7nh",
 
720
  "\u1ecbch",
 
 
721
  "\u1ecfng",
722
  "\u1ed1ng",
723
  "\u1ed3ng",
 
 
724
  "\u1edbng",
725
  "\u1eddng",
726
  "\u1edf",
 
727
  "\u1ee5ng",
728
  "\u1ee9",
729
- "\u1ee9 2",
730
- "\u1ee9 3",
731
- "\u1ee9 4",
732
- "\u1ee9 5",
733
- "\u1ee9 6",
734
- "\u1ee9 7",
735
- "\u1ee9ng"
 
 
 
736
  ]
 
1
  [
2
+ "\t",
3
+ "\n",
4
+ " ",
5
+ " ",
6
+ "!",
7
+ "\"",
8
+ "'",
9
+ "''",
10
+ "'-(",
11
+ "'-)",
12
+ "(",
13
+ "(((",
14
+ "(*>",
15
+ "(*_*)",
16
+ "(-8",
17
+ "(-:",
18
+ "(-;",
19
+ "(-_-)",
20
+ "(-d",
21
+ "(._.)",
22
+ "(:",
23
+ "(;",
24
+ "(=",
25
+ "(>_<)",
26
+ "(^_^)",
27
+ "(o:",
28
+ "(x:",
29
+ "(x_x)",
30
+ "(\u00ac_\u00ac)",
31
+ "(\u0ca0_\u0ca0)",
32
+ "(\u256f\u00b0\u25a1\u00b0\uff09\u256f\ufe35\u253b\u2501\u253b",
33
+ ")",
34
+ ")))",
35
+ ")-:",
36
+ ")/\u00af",
37
+ "):",
38
+ "*",
39
+ ",",
40
+ "-",
41
+ "-((",
42
+ "-))",
43
+ "-/",
44
+ "-0",
45
+ "-3",
46
+ "-8",
47
+ "-D",
48
+ "-O",
49
+ "-P",
50
+ "-X",
51
+ "-_-",
52
+ "-__-",
53
+ "-d",
54
+ "-o",
55
+ "-p",
56
+ "-x",
57
+ "-|",
58
+ ".",
59
+ "._.",
60
+ "/",
61
  "/10",
62
  "/11",
63
  "/12",
64
+ "/3",
65
+ "/d",
66
+ "0",
67
+ "0.0",
68
+ "0.o",
69
  "0/1",
70
  "0/9",
71
+ "0_0",
72
+ "0_o",
73
  "1",
74
  "1/10",
75
  "1/12",
 
77
  "10/10",
78
  "10/11",
79
  "10h",
80
+ "10h00",
81
  "11",
82
  "11h30",
83
+ "12",
84
  "12/10",
85
+ "12h",
86
+ "12h00",
87
+ "13h15",
88
  "14",
89
+ "14:00",
90
+ "14:30",
91
  "14h",
92
+ "14h30",
93
  "15",
94
  "15/10",
95
  "15/11",
96
+ "15h",
97
+ "15h00",
98
+ "16h45",
99
  "17",
100
  "17/10",
101
+ "17:30",
102
+ "17h",
103
+ "17h30",
104
+ "18/10",
105
+ "18:00",
106
  "18h",
107
+ "18h20",
108
+ "19h00",
109
+ "19h30",
110
+ "19h50",
111
+ "1h",
112
  "2",
113
  "2/1",
114
  "2/10",
 
117
  "20/11",
118
  "20/12",
119
  "20h",
120
+ "20h00",
121
+ "21h",
122
+ "21h00",
123
+ "22/11",
124
+ "22h00",
125
  "23/12",
126
  "23h59",
127
  "25/10",
 
133
  "30/11",
134
  "30/12",
135
  "30/9",
136
+ "33",
137
+ "333",
138
+ "3h",
139
  "4",
140
+ "45",
141
  "4h",
142
  "5",
143
  "5h",
144
  "6",
145
+ "6h",
146
+ "6h00",
147
+ "6h30",
148
  "7",
149
  "7h",
150
+ "7h45",
151
  "8",
152
+ "8)",
153
+ "8-",
154
+ "8-)",
155
+ "8-D",
156
+ "8-d",
157
+ "8D",
158
+ "8d",
159
  "8h",
160
+ "8h00",
161
+ "8h10",
162
  "9",
163
  "9h",
164
+ "9h15",
165
+ "9h30",
166
+ ":",
167
+ ":'(",
168
+ ":')",
169
+ ":'-(",
170
+ ":'-)",
171
+ ":(",
172
+ ":((",
173
+ ":(((",
174
+ ":()",
175
+ ":)",
176
+ ":))",
177
+ ":)))",
178
+ ":*",
179
+ ":-(",
180
+ ":-((",
181
+ ":-(((",
182
+ ":-)",
183
+ ":-))",
184
+ ":-)))",
185
+ ":-*",
186
+ ":-/",
187
+ ":-0",
188
+ ":-3",
189
+ ":->",
190
+ ":-D",
191
+ ":-O",
192
+ ":-P",
193
+ ":-X",
194
+ ":-]",
195
+ ":-d",
196
+ ":-o",
197
+ ":-p",
198
+ ":-x",
199
+ ":-|",
200
+ ":-}",
201
+ ":/",
202
+ ":0",
203
+ ":00",
204
+ ":1",
205
+ ":3",
206
+ ":30",
207
+ ":>",
208
+ ":D",
209
+ ":O",
210
+ ":P",
211
+ ":X",
212
+ ":]",
213
+ ":d",
214
+ ":o",
215
+ ":o)",
216
+ ":p",
217
+ ":x",
218
+ ":x)",
219
+ ":|",
220
+ ":}",
221
+ ";",
222
+ ";)",
223
+ ";-)",
224
+ ";-D",
225
+ ";-X",
226
+ ";-d",
227
+ ";D",
228
+ ";X",
229
+ ";_;",
230
+ ";d",
231
+ "<",
232
+ "<.<",
233
+ "</3",
234
+ "</d",
235
+ "<3",
236
+ "<33",
237
+ "<333",
238
+ "<d",
239
+ "<dd",
240
+ "<ddd",
241
+ "<space>",
242
+ "<xxxx>",
243
+ "=",
244
+ "=(",
245
+ "=)",
246
+ "=/",
247
+ "=3",
248
+ "=D",
249
+ "=X",
250
+ "=[",
251
+ "=]",
252
+ "=d",
253
+ "=|",
254
+ ">",
255
+ ">.<",
256
+ ">.>",
257
+ ">:(",
258
+ ">:o",
259
+ ">:x",
260
+ "><(((*>",
261
+ "@",
262
+ "@_@",
263
  "A",
264
+ "ABC",
265
  "AI",
266
+ "ASK",
267
+ "ATE",
268
  "An",
269
  "Anh",
270
  "B",
271
+ "B.",
272
  "Ba",
273
  "Backend",
274
  "B\u00e1ch",
275
  "B\u00ecnh",
276
+ "B\u1ea3n",
277
  "B\u1ea3y",
278
  "B\u1ec7nh",
279
  "C",
280
+ "C++",
281
+ "C.",
282
+ "CGV",
283
+ "CNTT",
284
+ "CRM",
285
+ "CV",
286
  "Chi\u1ec1u",
287
  "Ch\u00fang",
288
  "Ch\u01a1i",
289
  "Ch\u1ecb",
290
  "Ch\u1ee7",
 
 
291
  "Cu\u1ed1i",
292
  "C\u01b0\u1eddng",
293
  "C\u1ea3",
294
+ "C\u1ea7n",
295
  "D",
296
  "Data",
297
+ "Deadline",
298
  "Design",
299
  "Dev",
300
  "DevOps",
301
  "Dung",
302
  "D\u0169ng",
303
  "D\u1ecdn",
304
+ "D\u1ef1",
305
+ "EIC",
306
  "F",
307
+ "F.",
308
  "FPT",
309
+ "Facebook",
310
  "Frontend",
311
  "G",
312
  "G\u00f2n",
313
+ "G\u1ea5p",
314
  "H",
315
  "Hai",
316
  "Hoa",
 
319
  "Ho\u00e1",
320
  "Huy",
321
  "H\u00e0",
322
+ "H\u00f2a",
323
  "H\u00f3a",
324
  "H\u00f4m",
325
  "H\u00f9ng",
326
  "H\u01b0ng",
327
+ "H\u01b0\u01a1ng",
328
+ "H\u1ea1",
329
  "H\u1ea1nh",
330
  "H\u1ea3i",
331
+ "H\u1eb1ng",
332
  "H\u1ecdc",
333
+ "I",
334
+ "II",
335
+ "IME",
336
+ "IT",
337
  "K",
338
+ "K.",
339
  "Khoa",
340
+ "Khuya",
341
+ "Kh\u00f4ng",
342
  "Kh\u1ea3i",
343
+ "Kh\u1ea9n",
344
+ "Ki\u00ean",
345
+ "Ki\u1ec1u",
346
  "L",
347
  "Lan",
348
  "Linh",
349
  "L\u00e0m",
350
+ "L\u00e1t",
351
  "L\u00e2m",
352
+ "L\u00fac",
353
  "L\u1ea1t",
354
  "L\u1ecbch",
355
  "M",
 
360
  "M\u00f9ng",
361
  "M\u1ed1t",
362
  "N",
363
+ "NTT",
364
  "Nam",
365
+ "Netflix",
366
+ "Nga",
367
+ "Ngay",
368
  "Nghe",
369
  "Ng\u00e0y",
370
  "Ng\u1ecdc",
371
  "Ng\u1eef",
372
  "Nh\u00f3m",
373
  "Nh\u1eadt",
374
+ "Nh\u1edb",
375
  "N\u0103m",
376
  "N\u1ea5u",
377
  "N\u1eb5ng",
378
  "N\u1ed9i",
379
+ "O",
380
+ "O.O",
381
+ "O.o",
382
+ "O_O",
383
+ "O_o",
384
  "Ops",
385
  "P",
386
  "Ph\u00e1p",
387
  "Ph\u00f2ng",
388
  "Ph\u00fac",
389
  "Ph\u01b0\u01a1ng",
390
+ "Ph\u01b0\u1edbc",
391
+ "Ph\u1ea3i",
392
  "Product",
393
+ "Python",
394
  "Q",
395
  "QA",
396
+ "Quan",
397
+ "Quang",
398
  "Qu\u00e2n",
399
+ "R",
400
  "ROOT",
401
+ "React",
402
+ "ReactJS",
403
+ "R\u1ea5t",
404
  "S",
405
+ "SON",
406
  "Sinh",
407
  "S\u00e0i",
408
  "S\u00e1ng",
 
411
  "S\u1ebfp",
412
  "T",
413
  "TASK",
414
+ "TOEIC",
415
  "Team",
416
+ "Thu",
417
  "Th\u00e1ng",
418
+ "Th\u00fay",
419
  "Th\u1ea3o",
420
  "Th\u1eafng",
421
+ "Th\u1ee7",
422
  "Th\u1ee9",
 
 
 
 
 
 
 
 
 
 
 
 
 
423
  "Tin",
424
  "Ti\u1ebfng",
425
  "To\u00e1n",
426
  "Tr\u00e2m",
427
  "Tr\u01b0a",
428
+ "Tr\u01b0\u1edbc",
429
  "Tu\u1ea5n",
430
  "Tu\u1ea7n",
431
+ "T\u00e0i",
432
  "T\u00e0u",
433
  "T\u00f4i",
434
  "T\u01b0",
435
  "T\u1eadp",
436
  "T\u1ed1i",
437
  "V",
438
+ "V.V",
439
+ "VIP",
440
+ "V_V",
441
  "Vi\u1ebft",
442
  "Vi\u1ec7t",
443
+ "V\u00e2n",
444
  "V\u0103n",
445
  "V\u0169ng",
446
  "V\u1eadt",
447
+ "X++",
448
+ "X.",
449
+ "X.X",
450
+ "X.x",
451
+ "XD",
452
+ "XDD",
453
  "XX",
454
  "XXX",
455
+ "XXXX",
456
+ "X_X",
457
+ "X_x",
458
  "Xem",
459
  "Xx",
460
  "Xxx",
 
 
 
 
 
 
 
461
  "XxxXxx",
462
  "Xxxx",
463
  "Xxxxx",
464
+ "XxxxxXX",
465
+ "Y",
466
+ "Y\u00eau",
467
+ "Y\u1ebfn",
468
+ "Z",
469
+ "Zoom",
470
+ "[",
471
+ "[-:",
472
+ "[:",
473
+ "[=",
474
+ "\\",
475
+ "\\\")",
476
+ "\\n",
477
+ "\\t",
478
+ "\\x",
479
+ "]",
480
+ "]=",
481
+ "^",
482
+ "^_^",
483
+ "^__^",
484
+ "^___^",
485
+ "_*)",
486
+ "_-)",
487
+ "_.)",
488
+ "_<)",
489
+ "_^)",
490
+ "__-",
491
+ "__^",
492
+ "_\u00ac)",
493
+ "_\u0ca0)",
494
  "a",
495
+ "a.",
496
+ "abc",
497
+ "ace",
498
+ "ack",
499
+ "act",
500
  "ai",
501
  "ail",
502
  "all",
503
  "ame",
504
  "an",
505
+ "ang",
506
  "anh",
507
+ "ano",
508
+ "app",
509
  "ase",
510
  "ask",
511
  "assignment",
512
  "ata",
513
  "auth",
514
  "b",
515
+ "b.",
516
  "ba",
517
  "backend",
518
+ "backup",
519
+ "ban",
520
  "banh",
521
+ "banner",
522
+ "bi\u00ean",
523
+ "bi\u1ec3n",
524
+ "blog",
525
+ "buffet",
526
  "bug",
527
  "bu\u1ed5i",
528
  "b\u00e0i",
529
+ "b\u00e0n",
530
+ "b\u00e1c",
531
  "b\u00e1ch",
532
+ "b\u00e1n",
533
+ "b\u00e1nh",
534
  "b\u00e1o",
535
+ "b\u00e1t",
536
  "b\u00e8",
537
+ "b\u00e9",
538
+ "b\u00ean",
539
  "b\u00ecnh",
540
  "b\u00f3ng",
541
+ "b\u01a1i",
542
  "b\u1ea1n",
543
  "b\u1ea3n",
544
+ "b\u1ea3o",
545
  "b\u1ea3y",
546
  "b\u1eaft",
547
  "b\u1ec7nh",
548
  "b\u1ecb",
549
+ "b\u1ed1",
550
+ "b\u1ed5ng",
551
  "b\u1ed9",
552
+ "b\u1ee5i",
553
  "c",
554
+ "c++",
555
+ "c.",
556
+ "ca",
557
  "call",
558
+ "can",
559
  "cao",
560
+ "ce>",
561
+ "cgv",
562
+ "chi",
563
+ "chi\u1ebfc",
564
+ "chi\u1ebfn",
565
  "chi\u1ec1u",
566
  "cho",
567
+ "chung",
568
+ "chuy\u1ebfn",
569
  "chuy\u1ec1n",
570
  "chu\u1ea9n",
571
+ "ch\u00e1u",
572
  "ch\u00ednh",
573
+ "ch\u00f3",
574
+ "ch\u00f3t",
575
  "ch\u00fang",
576
  "ch\u01a1i",
577
+ "ch\u01b0\u01a1ng",
578
  "ch\u1ea1y",
579
+ "ch\u1ec9nh",
580
  "ch\u1ecb",
581
+ "ch\u1ed1t",
582
+ "ch\u1ed7",
583
  "ch\u1ee3",
584
  "ch\u1ee7",
 
585
  "ch\u1ee9c",
586
+ "ch\u1ee9ng",
587
+ "ch\u1eefa",
588
+ "cntt",
589
  "code",
590
  "con",
591
  "concert",
592
+ "crm",
593
+ "cung",
594
  "cu\u1ed1i",
595
+ "cu\u1ed9c",
596
+ "cv",
597
  "c\u00e0",
598
+ "c\u00e0y",
599
  "c\u00e1",
600
+ "c\u00e1c",
601
  "c\u00e1o",
602
+ "c\u00e2y",
603
+ "c\u00f2n",
604
  "c\u00f3",
605
  "c\u00f4",
606
  "c\u00f4ng",
607
  "c\u00f9ng",
608
+ "c\u0103ng",
609
  "c\u0169",
610
  "c\u01a1m",
611
  "c\u01b0\u1edbi",
612
  "c\u01b0\u1eddng",
613
+ "c\u1ea1nh",
614
  "c\u1ea3",
615
+ "c\u1ea5p",
616
  "c\u1ea7n",
617
+ "c\u1ea7u",
618
  "c\u1eadp",
619
+ "c\u1ee7",
620
+ "c\u1ee7a",
621
+ "c\u1ee9u",
622
+ "c\u1eeda",
623
  "d",
624
+ "d)",
625
+ "d-",
626
+ "d-)",
627
+ "d-X",
628
+ "d.",
629
+ "d.d",
630
+ "d.x",
631
  "d/d",
632
  "d/dd",
633
+ "dX",
634
+ "d_d",
635
+ "d_x",
636
+ "danh",
637
  "data",
638
  "database",
639
+ "date",
640
  "dd",
641
  "dd/d",
642
  "dd/dd",
643
+ "dd:dd",
644
+ "ddd",
645
  "ddx",
646
  "ddxdd",
647
+ "deadline",
648
  "deo",
649
  "deploy",
650
  "design",
651
  "dev",
652
  "devops",
653
+ "di\u1ec7t",
654
  "du",
655
  "dung",
656
+ "duy\u1ec7t",
657
  "dx",
658
+ "dxdd",
659
+ "d\u00e3",
660
  "d\u0169ng",
661
+ "d\u01b0\u1ee1ng",
662
  "d\u1ea1o",
663
+ "d\u1ea1y",
664
+ "d\u1ea7u",
665
  "d\u1eabn",
666
+ "d\u1eady",
667
+ "d\u1eaft",
668
  "d\u1eb9p",
669
+ "d\u1ecbch",
670
  "d\u1ecdn",
671
  "d\u1ee5c",
672
  "d\u1ee5ng",
673
+ "d\u1eef",
674
  "d\u1ef1",
675
  "e",
676
+ "e.",
677
  "eam",
678
+ "eic",
679
+ "em",
680
  "email",
681
  "end",
682
  "ent",
683
  "ert",
684
  "est",
685
  "f",
686
+ "f.",
687
+ "facebook",
688
+ "feedback",
689
+ "fet",
690
+ "file",
691
  "fix",
692
  "fpt",
693
  "frontend",
694
  "g",
695
+ "g.",
696
  "game",
697
+ "gay",
698
  "ghe",
699
+ "gh\u1ec7",
700
+ "gh\u1ec9",
701
+ "gh\u1ecb",
702
  "gia",
703
+ "gian",
704
+ "giao",
705
+ "gi\u00e1",
706
  "gi\u00e1o",
707
  "gi\u00e3n",
708
  "gi\u1ea3ng",
709
+ "gi\u1eb7t",
710
  "gi\u1edd",
711
  "guitar",
712
  "gym",
713
  "g\u00e0y",
714
+ "g\u00e2n",
715
  "g\u00f2n",
716
+ "g\u1ea5p",
717
  "g\u1eb7p",
718
  "g\u1ecdc",
719
  "g\u1ecdi",
720
  "g\u1eedi",
721
  "h",
722
+ "h.",
723
+ "h00",
724
+ "h10",
725
+ "h15",
726
+ "h20",
727
  "h30",
728
+ "h45",
729
+ "h50",
730
  "h59",
731
  "hai",
732
  "ham",
733
+ "hay",
734
  "him",
735
+ "hip",
736
+ "hi\u1ec3u",
737
+ "hi\u1ec7u",
738
  "hoa",
739
+ "hoan",
740
+ "hon",
741
  "hop",
742
  "ho\u00e0n",
743
  "ho\u00e0ng",
 
749
  "h\u00e0ng",
750
  "h\u00e1m",
751
  "h\u00e1p",
752
+ "h\u00e1t",
753
+ "h\u00e1u",
754
  "h\u00e2n",
755
  "h\u00eam",
756
  "h\u00ecnh",
757
+ "h\u00f2a",
758
  "h\u00f3a",
759
  "h\u00f3m",
760
+ "h\u00f3t",
761
  "h\u00f4m",
762
  "h\u00f9ng",
763
  "h\u00fac",
764
  "h\u00fat",
765
+ "h\u00fay",
766
+ "h\u0103m",
767
  "h\u01a1i",
768
  "h\u01b0ng",
769
+ "h\u01b0\u01a1ng",
770
  "h\u01b0\u1edbng",
771
+ "h\u1ea1",
772
  "h\u1ea1c",
773
+ "h\u1ea1n",
774
  "h\u1ea1nh",
775
  "h\u1ea1y",
776
  "h\u1ea3i",
777
+ "h\u1ea3n",
778
  "h\u1ea3o",
779
+ "h\u1ea5t",
780
+ "h\u1ea7n",
781
  "h\u1ea7u",
782
+ "h\u1ea7y",
783
  "h\u1ea9m",
784
+ "h\u1ea9n",
785
+ "h\u1ea9u",
786
+ "h\u1eadn",
787
  "h\u1eadt",
788
+ "h\u1eafc",
789
  "h\u1eafn",
790
+ "h\u1eb1ng",
791
+ "h\u1eb9n",
792
  "h\u1ebft",
793
  "h\u1ec7",
794
  "h\u1ecdc",
795
  "h\u1ecdp",
796
  "h\u1ecfe",
797
+ "h\u1ecfi",
798
+ "h\u1ecfng",
799
+ "h\u1ed1t",
800
  "h\u1ed3",
801
+ "h\u1ed3i",
802
+ "h\u1ed7",
803
+ "h\u1ed9i",
804
+ "h\u1ed9p",
805
+ "h\u1eddi",
806
+ "h\u1ee3p",
807
  "h\u1ee9c",
808
+ "h\u1eefa",
809
  "h\u1ef1c",
810
+ "i",
811
+ "i.",
812
+ "ian",
813
+ "iao",
814
  "ide",
815
  "iew",
816
  "ign",
817
+ "ii",
818
  "ile",
819
+ "in",
820
  "ine",
821
  "ing",
822
  "inh",
823
  "int",
824
+ "it",
825
+ "ite",
826
  "ive",
827
  "i\u00e1o",
828
  "i\u00e3n",
829
  "i\u00ean",
830
  "i\u00eau",
831
+ "i\u1eb7t",
832
+ "i\u1ebfc",
833
+ "i\u1ebfm",
834
+ "i\u1ebfn",
835
  "i\u1ebft",
836
+ "i\u1ec1m",
837
  "i\u1ec1n",
838
  "i\u1ec1u",
839
  "i\u1ec3m",
 
845
  "i\u1ec7p",
846
  "i\u1ec7t",
847
  "i\u1ec7u",
848
+ "j",
849
+ "j.",
850
  "k",
851
+ "k.",
852
+ "karaoke",
853
  "khai",
854
  "khi",
855
+ "kho",
856
  "khoa",
857
+ "kho\u1ea3n",
858
+ "khu",
859
+ "khuya",
860
  "kh\u00e1ch",
861
  "kh\u00e1m",
862
+ "kh\u00f3a",
863
+ "kh\u00f4ng",
864
  "kh\u1ea3i",
865
  "kh\u1ea3o",
866
+ "kh\u1ea9n",
867
+ "kh\u1ea9u",
868
  "kh\u1ecfe",
869
  "kia",
870
+ "ki\u00ean",
871
+ "ki\u1ebfm",
872
+ "ki\u1ec1u",
873
  "ki\u1ec3m",
874
+ "ki\u1ec7n",
875
+ "km",
876
+ "kup",
877
+ "k\u00e8m",
878
+ "k\u00ea",
879
  "k\u00fd",
880
  "k\u1ebf",
881
+ "k\u1ebft",
882
+ "k\u1ef3",
883
  "k\u1ef9",
884
  "l",
885
+ "l.",
886
  "lan",
887
+ "lao",
888
+ "lax",
889
+ "lin",
890
  "linh",
891
  "live",
892
+ "livestream",
893
+ "lix",
894
+ "li\u00ean",
895
+ "li\u1ec1n",
896
  "li\u1ec7u",
897
+ "log",
898
  "loy",
899
  "luy\u1ec7n",
900
  "lu\u1eadn",
901
+ "l\u00e0",
902
  "l\u00e0m",
903
+ "l\u00e1t",
904
  "l\u00e2m",
905
+ "l\u00ean",
906
+ "l\u00f4ng",
907
  "l\u00fac",
908
  "l\u00fd",
909
  "l\u1ea1i",
910
  "l\u1ea1t",
911
+ "l\u1ea9u",
912
  "l\u1eadp",
913
+ "l\u1eafp",
914
+ "l\u1ec5",
915
  "l\u1ecbch",
916
  "l\u1ed7i",
917
+ "l\u1edbn",
918
+ "l\u1edbp",
919
+ "l\u1eddi",
920
  "m",
921
+ "m.",
922
  "mai",
923
  "mail",
924
  "marketing",
925
  "minh",
926
+ "mi\u1ec1n",
927
  "mobile",
928
  "module",
929
  "mua",
930
  "mu\u1ed1n",
931
+ "mu\u1ed9n",
932
+ "m\u00e0n",
933
+ "m\u00e1y",
934
+ "m\u00ec",
935
  "m\u00f4n",
936
  "m\u00f9ng",
937
+ "m\u1ea5t",
938
+ "m\u1eabu",
939
+ "m\u1eadt",
940
  "m\u1eb9",
941
  "m\u1ec1m",
942
  "m\u1ed1t",
943
  "m\u1ed7i",
944
+ "m\u1ed9t",
945
  "m\u1edbi",
946
+ "m\u1ee5c",
947
+ "m\u1ef1c",
948
  "n",
949
+ "n.",
950
  "nam",
951
  "nay",
952
+ "ner",
953
+ "netflix",
954
+ "nga",
955
+ "ngay",
956
  "nghe",
957
+ "nghi\u00ean",
958
  "nghi\u1ec7m",
959
  "nghi\u1ec7p",
960
+ "ngh\u1ec7",
961
+ "ngh\u1ec9",
962
+ "ngh\u1ecb",
963
  "ngo\u00e0i",
964
+ "ngo\u1ea1i",
965
  "ng\u00e0y",
966
+ "ng\u00e2n",
967
+ "ng\u01b0\u1eddi",
968
  "ng\u1ecdc",
969
  "ng\u1ee7",
970
  "ng\u1eef",
971
+ "nha",
972
+ "nhanh",
973
  "nh\u00e0",
974
+ "nh\u00e1p",
975
  "nh\u00e2n",
976
  "nh\u00f3m",
977
  "nh\u1ea1c",
978
+ "nh\u1ea5t",
979
+ "nh\u1eadn",
980
  "nh\u1eadt",
981
+ "nh\u1eafc",
982
  "nh\u1eafn",
983
+ "nh\u1ecf",
984
  "nh\u1edb",
985
+ "nic",
986
  "nit",
987
+ "ntt",
988
  "n\u00e0y",
989
  "n\u00e2ng",
990
+ "n\u00ean",
991
  "n\u0103m",
992
  "n\u0103ng",
993
+ "n\u01b0\u1edbc",
994
  "n\u1ea5u",
995
  "n\u1eb5ng",
996
  "n\u1ed9i",
997
  "n\u1ed9p",
998
  "n\u1eefa",
999
  "o",
1000
+ "o.",
1001
+ "o.0",
1002
+ "o.O",
1003
+ "o.o",
1004
+ "o_0",
1005
+ "o_O",
1006
+ "o_o",
1007
+ "oan",
1008
  "ode",
1009
+ "offline",
1010
  "oga",
1011
+ "oke",
1012
  "ong",
1013
  "online",
1014
+ "ook",
1015
+ "oom",
1016
+ "ops",
1017
  "o\u00e0i",
1018
  "o\u00e0n",
1019
  "o\u00e1n",
1020
  "o\u1ea1i",
1021
  "o\u1ea1n",
1022
  "o\u1ea1t",
1023
+ "o\u1ea3n",
1024
  "p",
1025
+ "p.",
1026
+ "pam",
1027
+ "person",
1028
  "pha",
1029
  "phim",
1030
  "phi\u00ean",
1031
  "ph\u00e1p",
1032
+ "ph\u00e2n",
1033
  "ph\u00ea",
1034
  "ph\u00f2ng",
1035
  "ph\u00fac",
1036
  "ph\u00fat",
1037
  "ph\u01b0\u01a1ng",
1038
+ "ph\u01b0\u1edbc",
1039
  "ph\u1ea3i",
1040
+ "ph\u1ea3n",
1041
+ "ph\u1ea7n",
1042
  "ph\u1ea9m",
1043
+ "ph\u1eadn",
1044
  "ph\u1ecfng",
1045
+ "ph\u1ed1",
1046
+ "ph\u1edf",
1047
+ "piano",
1048
+ "picnic",
1049
  "product",
1050
+ "pull",
1051
+ "python",
1052
  "q",
1053
+ "q.",
1054
  "qa",
1055
+ "qua",
1056
+ "quan",
1057
+ "quang",
1058
+ "quanh",
1059
+ "quen",
1060
+ "qu\u00e0",
1061
+ "qu\u00e1n",
1062
  "qu\u00e2n",
1063
+ "qu\u00ean",
1064
  "qu\u00fd",
1065
+ "qu\u1ea3",
1066
+ "qu\u1ea3ng",
1067
+ "qu\u1ea7n",
1068
  "qu\u1ed1c",
1069
  "r",
1070
+ "r.",
1071
+ "ra",
1072
  "rau",
1073
+ "react",
1074
+ "reactjs",
1075
+ "relax",
1076
  "release",
1077
+ "request",
1078
  "review",
1079
+ "ri\u00eang",
1080
+ "ro",
1081
+ "rus",
1082
+ "r\u00e1c",
1083
  "r\u00e2m",
1084
+ "r\u00ean",
1085
  "r\u0103ng",
1086
  "r\u01b0a",
1087
+ "r\u1ea3nh",
1088
+ "r\u1ea5t",
1089
+ "r\u1ed3i",
1090
  "r\u1ed5",
1091
+ "r\u1eddi",
1092
+ "r\u1ee7i",
1093
  "r\u1eeda",
1094
+ "r\u1ef1c",
1095
  "s",
1096
+ "s.",
1097
  "sau",
1098
+ "scan",
1099
  "server",
1100
+ "ship",
1101
  "sinh",
1102
  "si\u00eau",
1103
  "slide",
1104
  "so\u1ea1n",
1105
+ "space",
1106
+ "spam",
1107
  "sprint",
1108
  "stream",
1109
+ "su\u1ea5t",
1110
  "s\u00e0i",
1111
  "s\u00e1ch",
1112
  "s\u00e1ng",
1113
+ "s\u00e1t",
1114
  "s\u00e1u",
1115
+ "s\u00e2n",
1116
+ "s\u0129",
1117
  "s\u01a1",
1118
+ "s\u1ea1n",
1119
+ "s\u1ea3n",
1120
  "s\u1eafp",
1121
  "s\u1ebd",
1122
  "s\u1ebfp",
1123
+ "s\u1ed1",
1124
+ "s\u1edbm",
1125
+ "s\u1edf",
1126
  "s\u1ee9c",
1127
  "s\u1eed",
1128
  "s\u1eeda",
1129
+ "s\u1eefa",
1130
+ "s\u1ef1",
1131
  "t",
1132
+ "t.",
1133
+ "tJS",
1134
+ "ta",
1135
+ "tan",
1136
  "tar",
1137
  "task",
1138
  "team",
1139
  "test",
1140
  "tham",
1141
+ "thanh",
1142
+ "thay",
1143
  "thi",
1144
+ "thi\u1ebft",
1145
+ "thi\u1ec7n",
1146
  "tho\u1ea1i",
1147
+ "thu",
1148
  "thuy\u1ebft",
1149
+ "thu\u1eadt",
1150
+ "thu\u1ed1c",
1151
  "th\u00e0nh",
1152
  "th\u00e1ng",
1153
  "th\u00eam",
1154
  "th\u00ed",
1155
+ "th\u00edch",
1156
+ "th\u00f4ng",
1157
+ "th\u00fac",
1158
+ "th\u00fay",
1159
+ "th\u0103m",
1160
  "th\u01b0",
1161
  "th\u1ea3o",
1162
  "th\u1ea7u",
1163
+ "th\u1ea7y",
1164
  "th\u1eafng",
1165
  "th\u1ec3",
1166
  "th\u1ecb",
1167
  "th\u1ed1ng",
1168
+ "th\u1eddi",
1169
+ "th\u1ee7",
1170
  "th\u1ee9",
1171
+ "th\u1eed",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1172
  "th\u1ef1c",
1173
+ "time",
1174
  "tin",
1175
+ "ti\u00ean",
1176
+ "ti\u00eau",
1177
+ "ti\u1ebfn",
1178
  "ti\u1ebfng",
1179
+ "ti\u1ebft",
1180
+ "ti\u1ec1m",
1181
  "ti\u1ec1n",
1182
  "ti\u1ec3u",
1183
  "ti\u1ec7c",
1184
+ "tjs",
1185
+ "toeic",
1186
+ "to\u00e0n",
1187
  "to\u00e1n",
1188
  "tra",
1189
  "training",
1190
+ "trang",
1191
+ "tranh",
1192
  "tri\u1ec3n",
1193
  "trong",
1194
  "trung",
1195
+ "truy\u1ec1n",
1196
+ "tr\u00e0",
1197
  "tr\u00e2m",
1198
+ "tr\u00ean",
1199
+ "tr\u00ec",
1200
  "tr\u00ecnh",
1201
  "tr\u01b0a",
1202
  "tr\u01b0\u1edbc",
1203
+ "tr\u01b0\u1eddng",
1204
+ "tr\u1ea3",
1205
+ "tr\u1ecdng",
1206
+ "tr\u1ee3",
1207
+ "tr\u1ef1c",
1208
+ "tuy\u1ebfn",
1209
+ "tuy\u1ec3n",
1210
  "tu\u1ea5n",
1211
  "tu\u1ea7n",
1212
  "ty",
 
1214
  "t\u00e0u",
1215
  "t\u00e1c",
1216
  "t\u00e2m",
1217
+ "t\u00ean",
1218
+ "t\u00ecm",
1219
+ "t\u00ecnh",
1220
+ "t\u00edch",
1221
+ "t\u00ednh",
1222
+ "t\u00f3m",
1223
  "t\u00f4i",
1224
  "t\u01b0",
1225
+ "t\u01b0\u1edbi",
1226
  "t\u1ea1i",
1227
+ "t\u1ea1o",
1228
+ "t\u1ea3i",
1229
+ "t\u1ea5t",
1230
  "t\u1eadp",
1231
+ "t\u1eaft",
1232
+ "t\u1eb7ng",
1233
  "t\u1ebf",
1234
+ "t\u1ed1c",
1235
  "t\u1ed1i",
1236
+ "t\u1ed1t",
1237
+ "t\u1ed3n",
1238
  "t\u1ed5",
1239
+ "t\u1ed5ng",
1240
  "t\u1edbi",
1241
  "t\u1ee5",
1242
+ "t\u1ee7",
1243
+ "t\u1ee9c",
1244
  "t\u1eeb",
1245
  "u",
1246
+ "u.",
1247
+ "uan",
1248
  "uct",
1249
+ "uen",
1250
  "ule",
1251
+ "ull",
1252
  "ung",
1253
  "unit",
1254
  "uth",
1255
+ "uya",
1256
+ "u\u00e1n",
1257
  "u\u00e2n",
1258
+ "u\u00ean",
1259
  "u\u1ea5n",
1260
+ "u\u1ea5t",
1261
  "u\u1ea7n",
1262
  "u\u1ea9n",
1263
  "u\u1eadn",
1264
+ "u\u1eadt",
1265
  "u\u1ed1c",
1266
  "u\u1ed1i",
1267
  "u\u1ed1n",
1268
  "u\u1ed1ng",
1269
  "u\u1ed5i",
1270
+ "u\u1ed9c",
1271
+ "u\u1ed9n",
1272
  "v",
1273
+ "v.",
1274
+ "v.v",
1275
+ "v_v",
1276
  "ver",
 
1277
  "video",
1278
+ "violin",
1279
+ "vip",
1280
+ "virus",
1281
  "vi\u00ean",
1282
  "vi\u1ebft",
1283
  "vi\u1ec7c",
 
1285
  "vi\u1ec7t",
1286
  "v\u00e0",
1287
  "v\u00e0o",
1288
+ "v\u00e2n",
1289
  "v\u0103n",
1290
  "v\u0169ng",
1291
+ "v\u01b0\u1eddn",
1292
  "v\u1ea5n",
1293
  "v\u1eadt",
1294
+ "v\u1ebd",
1295
  "v\u1ec1",
1296
  "v\u1edbi",
1297
  "w",
1298
+ "w.",
1299
+ "website",
1300
  "workshop",
1301
  "x",
1302
+ "x.",
1303
+ "x.X",
1304
+ "x.d",
1305
+ "x.x",
1306
+ "xD",
1307
+ "xDD",
1308
+ "xX",
1309
+ "xXX",
1310
+ "x_X",
1311
+ "x_d",
1312
+ "x_x",
1313
+ "xd",
1314
+ "xdd",
1315
  "xe",
1316
  "xem",
1317
  "xin",
1318
+ "xu\u1ea5t",
1319
  "xx",
1320
  "xxx",
 
 
 
 
 
1321
  "xxxx",
1322
+ "x\u00e1c",
1323
+ "x\u1ea1",
1324
  "x\u1ebfp",
1325
+ "x\u1eed",
1326
+ "x\ufe35x",
1327
  "y",
1328
+ "y.",
1329
  "yoga",
1330
+ "y\u00eau",
1331
+ "y\u1ebfn",
1332
  "y\u1ebft",
1333
  "y\u1ec1n",
1334
+ "y\u1ec3n",
1335
  "y\u1ec7n",
1336
+ "y\u1ec7t",
1337
  "z",
1338
+ "z.",
1339
+ "zoom",
1340
+ "|",
1341
+ "}",
1342
  "\u00a0",
1343
+ "\u00ac",
1344
+ "\u00ac_\u00ac",
1345
+ "\u00af",
1346
+ "\u00af\\(x)/\u00af",
1347
+ "\u00af\\(\u30c4)/\u00af",
1348
+ "\u00b0",
1349
+ "\u00b0C.",
1350
+ "\u00b0F.",
1351
+ "\u00b0K.",
1352
+ "\u00b0X.",
1353
+ "\u00b0c.",
1354
+ "\u00b0f.",
1355
+ "\u00b0k.",
1356
+ "\u00b0x.",
1357
  "\u00d4",
1358
  "\u00d4n",
1359
  "\u00e0ng",
 
1362
  "\u00e1ch",
1363
  "\u00e1n",
1364
  "\u00e1ng",
1365
+ "\u00e1nh",
1366
+ "\u00e1o",
1367
  "\u00e2ng",
1368
+ "\u00e4",
1369
+ "\u00e4.",
1370
+ "\u00eang",
1371
  "\u00ecnh",
1372
+ "\u00edch",
1373
  "\u00ednh",
1374
  "\u00f2ng",
1375
  "\u00f3ng",
1376
  "\u00f4",
1377
  "\u00f4n",
1378
  "\u00f4ng",
1379
+ "\u00f6",
1380
+ "\u00f6.",
1381
  "\u00f9ng",
1382
  "\u00fang",
1383
+ "\u00fc",
1384
+ "\u00fc.",
1385
  "\u0103",
1386
  "\u0103n",
1387
  "\u0103ng",
1388
  "\u0110",
1389
  "\u0110i",
1390
  "\u0110\u00e0",
1391
+ "\u0110\u1ec3",
1392
  "\u0110\u1ecba",
1393
  "\u0110\u1ecdc",
1394
  "\u0110\u1ee9c",
1395
+ "\u0110\u1eebng",
1396
  "\u0111",
1397
  "\u0111a",
1398
+ "\u0111em",
1399
  "\u0111i",
1400
  "\u0111i\u1ec7n",
1401
  "\u0111\u00e0",
1402
+ "\u0111\u00e0n",
1403
+ "\u0111\u00e0o",
1404
  "\u0111\u00e1",
1405
+ "\u0111\u00e1nh",
1406
+ "\u0111\u00e3",
1407
  "\u0111\u00ecnh",
1408
  "\u0111\u00f3n",
1409
  "\u0111\u00f3ng",
1410
+ "\u0111\u0103ng",
1411
+ "\u0111\u01a1n",
1412
  "\u0111\u01b0a",
1413
+ "\u0111\u1ea1i",
1414
  "\u0111\u1ea7u",
1415
+ "\u0111\u1ea7y",
1416
  "\u0111\u1eb7t",
1417
  "\u0111\u1ebfn",
1418
  "\u0111\u1ec1",
1419
+ "\u0111\u1ec3",
1420
  "\u0111\u1ecba",
1421
+ "\u0111\u1ecbnh",
1422
  "\u0111\u1ecdc",
1423
+ "\u0111\u1ecdng",
1424
  "\u0111\u1ed1i",
1425
  "\u0111\u1ed3",
1426
  "\u0111\u1ed3ng",
1427
+ "\u0111\u1ed5",
1428
+ "\u0111\u1ed5i",
1429
+ "\u0111\u1ed9",
1430
  "\u0111\u1ed9i",
1431
+ "\u0111\u1ed9ng",
1432
+ "\u0111\u1ee3t",
1433
+ "\u0111\u1ee7",
1434
  "\u0111\u1ee9c",
1435
+ "\u0111\u1eebng",
1436
  "\u0169ng",
1437
  "\u01a1ng",
1438
+ "\u01af",
1439
+ "\u01afu",
1440
+ "\u01b0",
1441
  "\u01b0ng",
1442
+ "\u01b0u",
1443
  "\u01b0\u1edbc",
1444
  "\u01b0\u1edbi",
1445
+ "\u01b0\u1eddi",
1446
+ "\u01b0\u1eddn",
1447
+ "\u0ca0",
1448
+ "\u0ca0_\u0ca0",
1449
+ "\u0ca0\ufe35\u0ca0",
1450
  "\u1ea1ch",
1451
  "\u1ea1nh",
1452
+ "\u1ea3",
1453
  "\u1ea3ng",
1454
+ "\u1ea3nh",
1455
+ "\u1ea5",
1456
+ "\u1ea5y",
1457
  "\u1eafng",
1458
+ "\u1eb1ng",
1459
  "\u1eb5ng",
1460
+ "\u1eb7ng",
1461
  "\u1ebfng",
1462
  "\u1ec7nh",
1463
+ "\u1ec9nh",
1464
  "\u1ecbch",
1465
+ "\u1ecbnh",
1466
+ "\u1ecdng",
1467
  "\u1ecfng",
1468
  "\u1ed1ng",
1469
  "\u1ed3ng",
1470
+ "\u1ed5ng",
1471
+ "\u1ed9ng",
1472
  "\u1edbng",
1473
  "\u1eddng",
1474
  "\u1edf",
1475
+ "\u1ee1ng",
1476
  "\u1ee5ng",
1477
  "\u1ee9",
1478
+ "\u1ee9ng",
1479
+ "\u1eebng",
1480
+ "\u2014",
1481
+ "\u2501",
1482
+ "\u253b",
1483
+ "\u253b\u2501\u253b",
1484
+ "\u256f",
1485
+ "\u25a1",
1486
+ "\ufe35",
1487
+ "\uff09"
1488
  ]