icu_segmenter 0.7.0

Unicode line breaking and text segmentation algorithms for text boundaries analysis
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185

// This file is part of ICU4X. For terms of use, please see the file
// called LICENSE at the top level of the ICU4X source tree
// (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).

use icu_segmenter::LineBreakOptions;
use icu_segmenter::LineBreakRule;
use icu_segmenter::LineBreakSegmenter;
use icu_segmenter::WordBreakRule;

fn check_with_options(
    s: &str,
    expect_utf8: Vec<usize>,
    expect_utf16: Vec<usize>,
    options: LineBreakOptions,
) {
    let segmenter =
        LineBreakSegmenter::try_new_with_options_unstable(&icu_testdata::unstable(), options)
            .expect("Data exists");

    let iter = segmenter.segment_str(s);
    let result: Vec<usize> = iter.collect();
    assert_eq!(expect_utf8, result, "{}", s);

    let s_utf16: Vec<u16> = s.encode_utf16().collect();
    let iter = segmenter.segment_utf16(&s_utf16);
    let result: Vec<usize> = iter.collect();
    assert_eq!(expect_utf16, result, "{}", s);
}

fn break_all(s: &str, expect_utf8: Vec<usize>, expect_utf16: Vec<usize>) {
    let mut options = LineBreakOptions::default();
    options.line_break_rule = LineBreakRule::Strict;
    options.word_break_rule = WordBreakRule::BreakAll;
    options.ja_zh = false;
    check_with_options(s, expect_utf8, expect_utf16, options);
}

fn keep_all(s: &str, expect_utf8: Vec<usize>, expect_utf16: Vec<usize>) {
    let mut options = LineBreakOptions::default();
    options.line_break_rule = LineBreakRule::Strict;
    options.word_break_rule = WordBreakRule::KeepAll;
    options.ja_zh = false;
    check_with_options(s, expect_utf8, expect_utf16, options);
}

fn normal(s: &str, expect_utf8: Vec<usize>, expect_utf16: Vec<usize>) {
    let mut options = LineBreakOptions::default();
    options.line_break_rule = LineBreakRule::Strict;
    options.word_break_rule = WordBreakRule::Normal;
    options.ja_zh = false;
    check_with_options(s, expect_utf8, expect_utf16, options);
}

#[test]
fn wordbreak_breakall() {
    // from css/css-text/word-break/word-break-break-all-000.html
    let s = "\u{65e5}\u{672c}\u{8a9e}";
    break_all(s, vec![3, 6, 9], vec![1, 2, 3]);

    // from css/css-text/word-break/word-break-break-all-001.html
    let s = "latin";
    break_all(s, vec![1, 2, 3, 4, 5], vec![1, 2, 3, 4, 5]);

    // from css/css-text/word-break/word-break-break-all-002.html
    let s = "\u{d55c}\u{ae00}\u{c77e}";
    break_all(s, vec![3, 6, 9], vec![1, 2, 3]);

    // from css/css-text/word-break/word-break-break-all-003.html
    let s = "ภาษาไทยภาษาไทย";
    break_all(
        s,
        vec![3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 36, 39, 42],
        vec![1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14],
    );

    // from css/css-text/word-break/word-break-break-all-004.html
    let s = "التدويل نشاط التدويل";
    break_all(
        s,
        vec![
            2, 4, 6, 8, 10, 12, 15, 17, 19, 21, 24, 26, 28, 30, 32, 34, 36, 38,
        ],
        vec![
            1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20,
        ],
    );

    // from css/css-text/word-break/word-break-break-all-008.html
    let s = "हिन्दी हिन्दी हिन्दी";
    break_all(
        s,
        vec![6, 12, 19, 25, 31, 38, 44, 50, 56],
        vec![2, 4, 7, 9, 11, 14, 16, 18, 20],
    );

    // from css/css-text/word-break/word-break-break-all-014.html
    let s = "\u{1f496}\u{1f494}";
    break_all(s, vec![4, 8], vec![2, 4]);

    // from css/css-text/word-break/word-break-break-all-018.html
    //let s = "XXXX\u{00a0}X";
    //break_all(s, vec![1, 2, 3, 5, 6], vec![1, 2, 3, 5, 6]);

    // from css/css-text/word-break/word-break-break-all-022.html
    //let s = "XX\u{00a0}X";
    //break_all(s, vec![1, 2, 4, 5], vec![1, 2, 3, 4]);

    // from css/css-text/word-break/word-break-break-all-023.html
    let s = "XX XX\u{005C}\u{005C}\u{005C}";
    break_all(s, vec![1, 3, 4, 5, 6, 7, 8], vec![1, 3, 4, 5, 6, 7, 8]);

    // from css/css-text/word-break/word-break-break-all-026.html
    let s = "XX XXX///";
    break_all(s, vec![1, 3, 4, 5, 9], vec![1, 3, 4, 5, 9]);

    // css/css-text/word-break/word-break-break-all-inline-008.html
    let s = "X.";
    break_all(s, vec![2], vec![2]);

    // ID and CJ
    let s = "フォ";
    break_all(s, vec![3, 6], vec![1, 2]);
}

#[test]
fn wordbreak_keepall() {
    // from css/css-text/word-break/word-break-keep-all-000.html
    let s = "latin";
    keep_all(s, vec![5], vec![5]);

    // from css/css-text/word-break/word-break-keep-all-001.html
    let s = "\u{65e5}\u{672c}\u{8a9e}";
    keep_all(s, vec![9], vec![3]);

    // from css/css-text/word-break/word-break-keep-all-002.html
    let s = "한글이";
    keep_all(s, vec![9], vec![3]);

    // from css/css-text/word-break/word-break-keep-all-005.html
    let s = "字\u{3000}字";
    keep_all(s, vec![6, 9], vec![2, 3]);

    // from css/css-text/word-break/word-break-keep-all-006.html
    let s = "字\u{3001}字";
    keep_all(s, vec![6, 9], vec![2, 3]);

    // from css/css-text/word-boundary/word-boundary-107.html
    let s = "しょう。";
    keep_all(s, vec![12], vec![4]);

    // failed test. JL, JV and JT
    let s = "\u{110B}\u{1162}\u{1100}\u{1175}\u{1111}\u{1161}\u{11AB}\u{1103}\u{1161}";
    keep_all(s, vec![27], vec![9]);
}

#[test]
#[cfg_attr(not(feature = "lstm"), ignore)]
fn wordbreak_keepall_lstm() {
    // from css/css-text/word-break/word-break-keep-all-003.html
    let s = "และและ";
    keep_all(s, vec![9, 18], vec![3, 6]);
}

#[test]
fn wordbreak_normal() {
    // from css/css-text/word-break/word-break-normal-th-000.html
    let s = "ภาษาไทยภาษาไทย";
    normal(s, vec![12, 21, 33, 42], vec![4, 7, 11, 14]);
}

#[test]
#[ignore = "We don't have km breaking rule yet"]
fn wordbreak_normal_km() {
    // from css/css-text/word-break/word-break-normal-km-000.html
    let _s = "ភាសាខ្មែរភាសាខ្មែរភាសាខ្មែរ";
    normal(_s, vec![27, 54, 81], vec![9, 18, 27]);
}

#[test]
#[ignore = "We don't have lo breaking rule yet"]
fn wordbreak_normal_lo() {
    // from css/css-text/word-break/word-break-normal-lo-000.html
    let _s = "ພາສາລາວພາສາລາວພາສາລາວ";
    normal(_s, vec![12, 21, 33, 42, 54, 63], vec![4, 7, 11, 14, 18, 21]);
}