textprep 0.1.5

Text preprocessing primitives: normalization, tokenization, and fast keyword matching.
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

//! Stopword lists.

use std::collections::HashSet;

/// Sorted list of common English stopwords.
pub const ENGLISH: &[&str] = &[
    "a",
    "about",
    "above",
    "after",
    "again",
    "against",
    "all",
    "am",
    "an",
    "and",
    "any",
    "are",
    "as",
    "at",
    "be",
    "because",
    "been",
    "before",
    "being",
    "below",
    "between",
    "both",
    "but",
    "by",
    "can",
    "did",
    "do",
    "does",
    "doing",
    "don",
    "down",
    "during",
    "each",
    "few",
    "for",
    "from",
    "further",
    "had",
    "has",
    "have",
    "having",
    "he",
    "her",
    "here",
    "hers",
    "herself",
    "him",
    "himself",
    "his",
    "how",
    "i",
    "if",
    "in",
    "into",
    "is",
    "it",
    "its",
    "itself",
    "just",
    "me",
    "more",
    "most",
    "my",
    "myself",
    "no",
    "nor",
    "not",
    "now",
    "of",
    "off",
    "on",
    "once",
    "only",
    "or",
    "other",
    "our",
    "ours",
    "ourselves",
    "out",
    "over",
    "own",
    "s",
    "same",
    "she",
    "should",
    "so",
    "some",
    "such",
    "t",
    "than",
    "that",
    "the",
    "their",
    "theirs",
    "them",
    "themselves",
    "then",
    "there",
    "these",
    "they",
    "this",
    "those",
    "through",
    "to",
    "too",
    "under",
    "until",
    "up",
    "very",
    "was",
    "we",
    "were",
    "what",
    "when",
    "where",
    "which",
    "while",
    "who",
    "whom",
    "why",
    "will",
    "with",
    "you",
    "your",
    "yours",
    "yourself",
    "yourselves",
];

/// Fast membership check for English stopwords.
///
/// The `ENGLISH` list is kept sorted so we can use `binary_search` without
/// allocating a `HashSet`.
pub fn is_english_stopword(token: &str) -> bool {
    ENGLISH.binary_search(&token).is_ok()
}

/// Return the stopword set for a language.
///
/// The English set is cached after the first call to avoid repeated allocation.
/// Unknown languages return an empty set (always a new allocation).
pub fn get(lang: &str) -> HashSet<String> {
    static ENGLISH_SET: std::sync::OnceLock<HashSet<String>> = std::sync::OnceLock::new();

    match lang.to_lowercase().as_str() {
        "en" | "english" => ENGLISH_SET
            .get_or_init(|| ENGLISH.iter().map(|s| s.to_string()).collect())
            .clone(),
        _ => HashSet::new(),
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn english_stopwords_are_sorted_for_binary_search() {
        assert!(
            ENGLISH.windows(2).all(|w| w[0] <= w[1]),
            "ENGLISH stopwords must remain sorted for binary_search"
        );
    }

    #[test]
    fn is_english_stopword_smoke() {
        assert!(is_english_stopword("the"));
        assert!(!is_english_stopword("tokio"));
    }
}