layered-nlp 0.1.1

Highly-flexible data-oriented NLP framework
Documentation 
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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132

use super::*;

fn split_input(input: &str) -> String {
    format!("{:#?}", test_line(input).ll_tokens())
}

#[test]
fn test_tokenizing() {
    let input = ". 1 000.23. € .5";

    insta::assert_display_snapshot!(split_input(&input), @r###"
    [
        LLToken {
            token_idx: 0,
            pos_starts_at: 0,
            pos_ends_at: 1,
            token: Text(
                ".",
                PUNC,
            ),
        },
        LLToken {
            token_idx: 1,
            pos_starts_at: 1,
            pos_ends_at: 2,
            token: Text(
                " ",
                SPACE,
            ),
        },
        LLToken {
            token_idx: 2,
            pos_starts_at: 2,
            pos_ends_at: 3,
            token: Text(
                "1",
                NATN,
            ),
        },
        LLToken {
            token_idx: 3,
            pos_starts_at: 3,
            pos_ends_at: 4,
            token: Text(
                " ",
                SPACE,
            ),
        },
        LLToken {
            token_idx: 4,
            pos_starts_at: 4,
            pos_ends_at: 7,
            token: Text(
                "000",
                NATN,
            ),
        },
        LLToken {
            token_idx: 5,
            pos_starts_at: 7,
            pos_ends_at: 8,
            token: Text(
                ".",
                PUNC,
            ),
        },
        LLToken {
            token_idx: 6,
            pos_starts_at: 8,
            pos_ends_at: 10,
            token: Text(
                "23",
                NATN,
            ),
        },
        LLToken {
            token_idx: 7,
            pos_starts_at: 10,
            pos_ends_at: 11,
            token: Text(
                ".",
                PUNC,
            ),
        },
        LLToken {
            token_idx: 8,
            pos_starts_at: 11,
            pos_ends_at: 12,
            token: Text(
                " ",
                SPACE,
            ),
        },
        LLToken {
            token_idx: 9,
            pos_starts_at: 12,
            pos_ends_at: 13,
            token: Text(
                "€",
                SYMB,
            ),
        },
        LLToken {
            token_idx: 10,
            pos_starts_at: 13,
            pos_ends_at: 14,
            token: Text(
                " ",
                SPACE,
            ),
        },
        LLToken {
            token_idx: 11,
            pos_starts_at: 14,
            pos_ends_at: 15,
            token: Text(
                ".",
                PUNC,
            ),
        },
        LLToken {
            token_idx: 12,
            pos_starts_at: 15,
            pos_ends_at: 16,
            token: Text(
                "5",
                NATN,
            ),
        },
    ]
    "###);
}