1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
Execution example:
```shell
tokenize \
'TokenMecab("target_class", "-名詞/非自立", "target_class", "-名詞/接尾/人名", "target_class", "名詞", "include_reading", true)' \
'彼の名前は山田さんのはずです。'
# [
# [
# 0,
# 1337566253.89858,
# 0.000355720520019531
# ],
# [
# {
# "value": "彼",
# "position": 0,
# "force_prefix": false,
# "force_prefix_search": false,
# "metadata": {
# "reading": "カレ"
# }
# },
# {
# "value": "名前",
# "position": 1,
# "force_prefix": false,
# "force_prefix_search": false,
# "metadata": {
# "reading": "ナマエ"
# }
# },
# {
# "value": "山田",
# "position": 2,
# "force_prefix": false,
# "force_prefix_search": false,
# "metadata": {
# "reading": "ヤマダ"
# }
# }
# ]
# ]
normalize \
'NormalizerNFKC("unify_to_romaji", true)' \
"カレ" \
WITH_TYPES
# [
# [
# 0,
# 1337566253.89858,
# 0.000355720520019531
# ],
# {
# "normalized": "kare",
# "types": [
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "null"
# ],
# "checks": []
# }
# ]
normalize \
'NormalizerNFKC("unify_to_romaji", true)' \
"ナマエ" \
WITH_TYPES
# [
# [
# 0,
# 1337566253.89858,
# 0.000355720520019531
# ],
# {
# "normalized": "namae",
# "types": [
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "null"
# ],
# "checks": []
# }
# ]
normalize \
'NormalizerNFKC("unify_to_romaji", true)' \
"ヤマダ" \
WITH_TYPES
# [
# [
# 0,
# 1337566253.89858,
# 0.000355720520019531
# ],
# {
# "normalized": "yamada",
# "types": [
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "alpha",
# "null"
# ],
# "checks": []
# }
# ]
```
|
