reefdb 0.1.0

ReefDB is a minimalistic, in-memory and on-disk database management system written in Rust, implementing basic SQL query capabilities and full-text search.
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

use std::collections::HashSet;
use std::fs::File;
use std::io;
use std::io::Read;
use std::io::Write;

use serde::Deserialize;
use serde::Serialize;

use super::memory::InvertedIndex;
use super::search::Search;
use super::tokenizers::tokenizer::Tokenizer;

#[derive(Debug, Serialize, Deserialize)]
pub struct OnDiskInvertedIndex<T: Tokenizer> {
    index: InvertedIndex<T>,
    file_path: String,
}

impl<T: Tokenizer + Serialize + for<'de> Deserialize<'de>> OnDiskInvertedIndex<T> {
    pub fn load_from_file(&self, file_path: &str) -> io::Result<Self> {
        let mut file = File::open(file_path)?;
        let mut encoded_data = Vec::new();
        file.read_to_end(&mut encoded_data)?;
        let index = bincode::deserialize(&encoded_data)
            .map_err(|err| io::Error::new(io::ErrorKind::InvalidData, err))?;
        Ok(index)
    }

    pub fn save_to_file(&self, file_path: &str) -> io::Result<()> {
        let encoded_data = bincode::serialize(self)
            .map_err(|err| io::Error::new(io::ErrorKind::InvalidData, err))?;
        let mut file = File::create(file_path)?;
        file.write_all(&encoded_data)
    }
}

impl<T: Tokenizer + Serialize + for<'de> Deserialize<'de>> Search for OnDiskInvertedIndex<T> {
    type NewArgs = String;

    fn new(args: Self::NewArgs) -> Self {
        let index = InvertedIndex::new();
        let file_path = args;
        let on_disk_index = OnDiskInvertedIndex {
            index,
            file_path: file_path.clone(),
        };
        on_disk_index
            .load_from_file(&file_path)
            .unwrap_or(on_disk_index)
    }

    fn search(&self, table: &str, column: &str, query: &str) -> HashSet<usize> {
        self.index.search(table, column, query)
    }

    fn add_column(&mut self, table: &str, column: &str) {
        self.index.add_column(table, column);
        self.save_to_file(&self.file_path).unwrap();
    }

    fn add_document(&mut self, table: &str, column: &str, row_id: usize, text: &str) {
        self.index.add_document(table, column, row_id, text);
        self.save_to_file(&self.file_path).unwrap();
    }

    fn remove_document(&mut self, table: &str, column: &str, row_id: usize) {
        self.index.remove_document(table, column, row_id);
        self.save_to_file(&self.file_path).unwrap();
    }

    fn update_document(&mut self, table: &str, column: &str, row_id: usize, text: &str) {
        self.index.update_document(table, column, row_id, text);
        self.save_to_file(&self.file_path).unwrap();
    }

    // Other impl methods for OnDiskInvertedIndex
}

#[cfg(test)]
mod tests {

    use crate::indexes::fts::tokenizers::default::DefaultTokenizer;

    use super::*;

    use tempfile::NamedTempFile;

    #[test]
    fn test_on_disk_inverted_index() {
        let temp_file = NamedTempFile::new().expect("Failed to create temporary file");
        let file_path = temp_file.into_temp_path().to_string_lossy().into_owned();

        let mut on_disk_index: OnDiskInvertedIndex<DefaultTokenizer> =
            OnDiskInvertedIndex::new(file_path);

        // Add documents
        on_disk_index.add_document("table1", "column1", 0, "hello world");
        on_disk_index.add_document("table1", "column1", 1, "goodbye world");
        on_disk_index.add_document("table1", "column2", 0, "rust programming");
        on_disk_index.add_document("table2", "column1", 0, "world peace");

        // Search
        let results = on_disk_index.search("table1", "column1", "world");
        let expected: HashSet<usize> = [0, 1].iter().cloned().collect();
        assert_eq!(results, expected);

        let results = on_disk_index.search("table1", "column2", "rust");
        let expected: HashSet<usize> = [0].iter().cloned().collect();
        assert_eq!(results, expected);

        let results = on_disk_index.search("table2", "column1", "world");
        let expected: HashSet<usize> = [0].iter().cloned().collect();
        assert_eq!(results, expected);

        // Remove document
        on_disk_index.remove_document("table1", "column1", 0);

        // Search after removing document
        let results = on_disk_index.search("table1", "column1", "world");
        let expected: HashSet<usize> = [1].iter().cloned().collect();
        assert_eq!(results, expected);
    }
}