moeix 0.6.0

Sub-millisecond code search via sparse trigram indexing.
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

use ix::executor::{Executor, QueryOptions};
use ix::reader::Reader;
use regex::Regex;
use std::io::Cursor;
use std::path::Path;
use tempfile::tempdir;

// Mock Reader for Executor::new
fn create_empty_index(path: &std::path::Path) {
    let mut builder = ix::builder::Builder::new(path).unwrap();
    builder.build().unwrap();
}

#[test]
fn test_streaming_edge_cases() {
    let dir = tempdir().unwrap();
    let index_path = dir.path().join(".ix/shard.ix");
    create_empty_index(dir.path());
    let reader = Reader::open(&index_path).unwrap();
    let executor = Executor::new(&reader);
    let regex = Regex::new("pattern").unwrap();
    let options = QueryOptions::default();

    // 1. Empty stream
    let data: &[u8] = b"";
    let matches = executor
        .verify_stream_for_test(Cursor::new(data), Path::new("test"), &regex, &options)
        .unwrap();
    assert_eq!(matches.len(), 0);

    // 2. Large line
    let large_line = "a".repeat(100_000) + "pattern" + &"b".repeat(100_000);
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(large_line.as_bytes()),
            Path::new("test"),
            &regex,
            &options,
        )
        .unwrap();
    assert_eq!(matches.len(), 1);
    assert_eq!(matches[0].byte_offset, 100_000);

    // 3. Multiple matches one line
    let multi_match = "pattern 1 pattern 2";
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(multi_match.as_bytes()),
            Path::new("test"),
            &regex,
            &options,
        )
        .unwrap();
    // Currently returns 1 because we use regex.find()
    assert_eq!(matches.len(), 1);
}

#[test]
fn test_streaming_binary_detection() {
    let dir = tempdir().unwrap();
    let index_path = dir.path().join(".ix/shard.ix");
    create_empty_index(dir.path());
    let reader = Reader::open(&index_path).unwrap();
    let executor = Executor::new(&reader);
    let regex = Regex::new("pattern").unwrap();
    let options = QueryOptions::default();

    // 1. Binary stream (mostly nulls)
    let binary_data: Vec<u8> = vec![0u8; 1000];
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(binary_data),
            Path::new("test"),
            &regex,
            &options,
        )
        .unwrap();
    assert_eq!(matches.len(), 0);

    // 2. Not binary (mostly text)
    let text_data = "This is a text file with pattern in it.\n".repeat(100);
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(text_data.as_bytes()),
            Path::new("test"),
            &regex,
            &options,
        )
        .unwrap();
    assert_eq!(matches.len(), 100);
}

#[test]
fn test_streaming_context_lookahead() {
    let dir = tempdir().unwrap();
    let index_path = dir.path().join(".ix/shard.ix");
    create_empty_index(dir.path());
    let reader = Reader::open(&index_path).unwrap();
    let executor = Executor::new(&reader);
    let regex = Regex::new("match").unwrap();
    let options = QueryOptions {
        context_lines: 2,
        ..Default::default()
    };

    // Match with context_after near EOF
    let data = "line1\nline2\nmatch\nline4\n";
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(data.as_bytes()),
            Path::new("test"),
            &regex,
            &options,
        )
        .unwrap();
    assert_eq!(matches.len(), 1);
    assert_eq!(matches[0].context_before, vec!["line1", "line2"]);
    assert_eq!(matches[0].context_after, vec!["line4"]);

    // Overlapping matches
    let data = "match1\nline2\nmatch2\nline4\nline5";
    let matches = executor
        .verify_stream_for_test(
            Cursor::new(data.as_bytes()),
            Path::new("test"),
            &Regex::new("match").unwrap(),
            &options,
        )
        .unwrap();
    assert_eq!(matches.len(), 2);
    assert_eq!(matches[0].context_after, vec!["line2", "match2"]);
    assert_eq!(matches[1].context_before, vec!["match1", "line2"]);
    assert_eq!(matches[1].context_after, vec!["line4", "line5"]);
}

#[test]
fn test_streaming_crlf_offsets() {
    let dir = tempdir().unwrap();
    let index_path = dir.path().join(".ix/shard.ix");
    create_empty_index(dir.path());
    let reader = Reader::open(&index_path).unwrap();
    let executor = Executor::new(&reader);
    let regex = Regex::new("match").unwrap();
    let options = QueryOptions::default();

    // CRLF data: "line1\r\nmatch\r\n"
    // line1 is 5 chars + 2 line ending = 7 bytes.
    // "match" starts at byte offset 7.
    let data = b"line1\r\nmatch\r\n";
    let matches = executor
        .verify_stream_for_test(Cursor::new(data), Path::new("test"), &regex, &options)
        .unwrap();

    assert_eq!(matches.len(), 1);
    assert_eq!(
        matches[0].byte_offset, 7,
        "Offset should account for CRLF (2 bytes)"
    );
}