chonkier 0.0.2

🦛 Chonkie, now in Rust 🦀: No-nonsense, ultra-fast, ultra-light chunking library
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

/*
    A module containg the types for the sentence chunker.

    The types are:
    - SentenceChunk: A chunk of text that is a sentence.
    - Sentence: A sentence in the text.
*/

// Import the Display trait
use serde::{Deserialize, Serialize};
use std::fmt;

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct Sentence {
    // The text of the sentence
    pub text: String,
    // The start index of the sentence in the original text
    pub start_index: usize,
    // The end index of the sentence in the original text
    pub end_index: usize,
    // The token count of the sentence
    pub token_count: usize,
}

//
impl Sentence {
    // Create a new sentence
    pub fn new(text: &str, start_index: usize, end_index: usize, token_count: usize) -> Self {
        Self {
            text: text.to_string(),
            start_index,
            end_index,
            token_count,
        }
    }

    // Get the length of the sentence
    pub fn len(&self) -> usize {
        self.text.len()
    }

    pub fn is_empty(&self) -> bool{
        self.text.is_empty()
    }
}

impl fmt::Display for Sentence {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(
            f,
            "Sentence(text: {}, start_index: {}, end_index: {}, token_count: {})",
            self.text, self.start_index, self.end_index, self.token_count
        )
    }
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct SentenceChunk {
    // The text of the chunk
    pub text: String,
    // The start index of the chunk in the original text
    pub start_index: usize,
    // The end index of the chunk in the original text
    pub end_index: usize,
    // The token count of the chunk
    pub token_count: usize,
    // The sentences in the chunk
    pub sentences: Option<Vec<Sentence>>,
}

impl SentenceChunk {
    // Create a new sentence chunk
    pub fn new(
        text: &str,
        start_index: usize,
        end_index: usize,
        token_count: usize,
        sentences: Option<Vec<Sentence>>,
    ) -> Self {
        Self {
            text: text.to_string(),
            start_index,
            end_index,
            token_count,
            sentences,
        }
    }

    // Return a deep copy of the sentence chunk
    pub fn copy(&self) -> Self {
        Self {
            text: self.text.clone(),
            start_index: self.start_index,
            end_index: self.end_index,
            token_count: self.token_count,
            sentences: self.sentences.clone(),
        }
    }

    // Get the length of the sentence chunk
    pub fn len(&self) -> usize {
        self.text.len()
    }

    pub fn is_empty(&self) -> bool{
        self.text.is_empty()
    }
}

impl fmt::Display for SentenceChunk {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(
            f,
            "SentenceChunk(text: {}, start_index: {}, end_index: {}, token_count: {}, sentences: {:?})",
            self.text, self.start_index, self.end_index, self.token_count, self.sentences
        )
    }
}

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

    #[test]
    fn test_sentence_new() {
        let sentence = Sentence::new("Hello, world!", 0, 12, 2);
        assert_eq!(sentence.text, "Hello, world!");
        assert_eq!(sentence.start_index, 0);
        assert_eq!(sentence.end_index, 12);
        assert_eq!(sentence.token_count, 2);
    }

    #[test]
    fn test_sentence_len() {
        let sentence = Sentence::new("Hello, world!", 0, 12, 2);
        assert_eq!(sentence.len(), 13);
    }

    #[test]
    fn test_sentence_display() {
        let sentence = Sentence::new("Hello, world!", 0, 12, 2);
        assert_eq!(
            format!("{}", sentence),
            "Sentence(text: Hello, world!, start_index: 0, end_index: 12, token_count: 2)"
        );
    }

    #[test]
    fn test_sentence_chunk_new() {
        let sentence_chunk = SentenceChunk::new("Hello, world!", 0, 12, 2, None);
        assert_eq!(sentence_chunk.text, "Hello, world!");
        assert_eq!(sentence_chunk.start_index, 0);
        assert_eq!(sentence_chunk.end_index, 12);
        assert_eq!(sentence_chunk.token_count, 2);
    }

    #[test]
    #[cfg(feature = "json")]
    fn test_sentence_chunk_serde() {
        let sentence_chunk = SentenceChunk::new("Hello, world!", 0, 12, 2, None);
        let serialized = serde_json::to_string(&sentence_chunk).unwrap();
        let deserialized: SentenceChunk = serde_json::from_str(&serialized).unwrap();
        assert_eq!(deserialized.text, "Hello, world!");
        assert_eq!(deserialized.start_index, 0);
        assert_eq!(deserialized.end_index, 12);
        assert_eq!(deserialized.token_count, 2);
    }
}