justext 0.2.0

Rust port of JusText — paragraph-level boilerplate removal for HTML
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

// Port of test_utils.py — stoplist tests

use justext::{available_languages, get_all_stoplists, get_stoplist};

#[test]
fn test_available_languages_count() {
    let languages = available_languages();
    assert_eq!(languages.len(), 100);
}

#[test]
fn test_available_languages_contains_english() {
    let languages = available_languages();
    assert!(languages.contains(&"English"));
}

#[test]
fn test_get_stoplist_english() {
    let stoplist = get_stoplist("English").unwrap();
    assert!(!stoplist.is_empty());
    // "the" should be in the English stoplist
    assert!(stoplist.contains("the"));
    assert!(stoplist.contains("a"));
    assert!(stoplist.contains("is"));
}

#[test]
fn test_get_stoplist_case_insensitive() {
    let lower = get_stoplist("english").unwrap();
    let upper = get_stoplist("ENGLISH").unwrap();
    let mixed = get_stoplist("English").unwrap();
    assert_eq!(lower, upper);
    assert_eq!(lower, mixed);
}

#[test]
fn test_get_stoplist_slovak() {
    let stoplist = get_stoplist("Slovak").unwrap();
    assert!(!stoplist.is_empty());
}

#[test]
fn test_get_stoplist_missing() {
    assert!(get_stoplist("Klingon").is_err());
}

#[test]
fn test_get_all_stoplists_nonempty() {
    let all = get_all_stoplists();
    assert!(!all.is_empty());
    // Should contain words from multiple languages
    assert!(all.contains("the")); // English
}

#[test]
fn test_stoplist_words_are_lowercased() {
    let stoplist = get_stoplist("English").unwrap();
    for word in &stoplist {
        assert_eq!(
            word,
            &word.to_lowercase(),
            "stopword not lowercased: {word}"
        );
    }
}

#[test]
fn test_all_100_languages() {
    let expected = vec![
        "Afrikaans",
        "Albanian",
        "Arabic",
        "Aragonese",
        "Armenian",
        "Aromanian",
        "Asturian",
        "Azerbaijani",
        "Basque",
        "Belarusian",
        "Belarusian_Taraskievica",
        "Bengali",
        "Bishnupriya_Manipuri",
        "Bosnian",
        "Breton",
        "Bulgarian",
        "Catalan",
        "Cebuano",
        "Chuvash",
        "Croatian",
        "Czech",
        "Danish",
        "Dutch",
        "English",
        "Esperanto",
        "Estonian",
        "Finnish",
        "French",
        "Galician",
        "Georgian",
        "German",
        "Greek",
        "Gujarati",
        "Haitian",
        "Hebrew",
        "Hindi",
        "Hungarian",
        "Icelandic",
        "Ido",
        "Igbo",
        "Indonesian",
        "Irish",
        "Italian",
        "Javanese",
        "Kannada",
        "Kazakh",
        "Korean",
        "Kurdish",
        "Kyrgyz",
        "Latin",
        "Latvian",
        "Lithuanian",
        "Lombard",
        "Low_Saxon",
        "Luxembourgish",
        "Macedonian",
        "Malay",
        "Malayalam",
        "Maltese",
        "Marathi",
        "Neapolitan",
        "Nepali",
        "Newar",
        "Norwegian_Bokmal",
        "Norwegian_Nynorsk",
        "Occitan",
        "Persian",
        "Piedmontese",
        "Polish",
        "Portuguese",
        "Quechua",
        "Romanian",
        "Russian",
        "Samogitian",
        "Serbian",
        "Serbo_Croatian",
        "Sicilian",
        "Simple_English",
        "Slovak",
        "Slovenian",
        "Spanish",
        "Sundanese",
        "Swahili",
        "Swedish",
        "Tagalog",
        "Tamil",
        "Telugu",
        "Turkish",
        "Turkmen",
        "Ukrainian",
        "Urdu",
        "Uzbek",
        "Vietnamese",
        "Volapuk",
        "Walloon",
        "Waray_Waray",
        "Welsh",
        "West_Frisian",
        "Western_Panjabi",
        "Yoruba",
    ];

    let languages = available_languages();
    for lang in &expected {
        assert!(languages.contains(lang), "missing language: {lang}");
    }
}