sql-splitter 1.8.0

High-performance CLI tool for splitting large SQL dump files into individual table files
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

use sql_splitter::parser::ContentFilter;
use sql_splitter::splitter::{Compression, Splitter};
use tempfile::TempDir;

#[test]
fn test_splitter_basic() {
    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql");
    let output_dir = temp_dir.path().join("output");

    std::fs::write(
        &input_file,
        b"CREATE TABLE users (id INT);\nINSERT INTO users VALUES (1);\nCREATE TABLE posts (id INT);\n",
    )
    .unwrap();

    let splitter = Splitter::new(input_file, output_dir.clone());
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 2);
    assert_eq!(stats.statements_processed, 3);

    assert!(output_dir.join("users.sql").exists());
    assert!(output_dir.join("posts.sql").exists());
}

#[test]
fn test_splitter_dry_run() {
    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql");
    let output_dir = temp_dir.path().join("output");

    std::fs::write(&input_file, b"CREATE TABLE users (id INT);").unwrap();

    let splitter = Splitter::new(input_file, output_dir.clone()).with_dry_run(true);
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 1);
    assert!(!output_dir.exists());
}

#[test]
fn test_splitter_table_filter() {
    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql");
    let output_dir = temp_dir.path().join("output");

    std::fs::write(
        &input_file,
        b"CREATE TABLE users (id INT);\nCREATE TABLE posts (id INT);\nCREATE TABLE orders (id INT);",
    )
    .unwrap();

    let splitter = Splitter::new(input_file, output_dir.clone())
        .with_table_filter(vec!["users".to_string(), "orders".to_string()]);
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 2);
    assert!(output_dir.join("users.sql").exists());
    assert!(!output_dir.join("posts.sql").exists());
    assert!(output_dir.join("orders.sql").exists());
}

#[test]
fn test_splitter_schema_only() {
    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql");
    let output_dir = temp_dir.path().join("output");

    std::fs::write(
        &input_file,
        b"CREATE TABLE users (id INT);\nINSERT INTO users VALUES (1);\nINSERT INTO users VALUES (2);",
    )
    .unwrap();

    let splitter = Splitter::new(input_file, output_dir.clone())
        .with_content_filter(ContentFilter::SchemaOnly);
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 1);
    assert_eq!(stats.statements_processed, 1); // Only CREATE TABLE

    let content = std::fs::read_to_string(output_dir.join("users.sql")).unwrap();
    assert!(content.contains("CREATE TABLE"));
    assert!(!content.contains("INSERT"));
}

#[test]
fn test_splitter_data_only() {
    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql");
    let output_dir = temp_dir.path().join("output");

    std::fs::write(
        &input_file,
        b"CREATE TABLE users (id INT);\nINSERT INTO users VALUES (1);\nINSERT INTO users VALUES (2);",
    )
    .unwrap();

    let splitter =
        Splitter::new(input_file, output_dir.clone()).with_content_filter(ContentFilter::DataOnly);
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 1);
    assert_eq!(stats.statements_processed, 2); // Only INSERTs

    let content = std::fs::read_to_string(output_dir.join("users.sql")).unwrap();
    assert!(!content.contains("CREATE TABLE"));
    assert!(content.contains("INSERT"));
}

#[test]
fn test_splitter_gzip_compressed() {
    use flate2::write::GzEncoder;
    use flate2::Compression as GzCompression;
    use std::io::Write;

    let temp_dir = TempDir::new().unwrap();
    let input_file = temp_dir.path().join("input.sql.gz");
    let output_dir = temp_dir.path().join("output");

    // Create gzipped SQL file
    let file = std::fs::File::create(&input_file).unwrap();
    let mut encoder = GzEncoder::new(file, GzCompression::default());
    encoder
        .write_all(b"CREATE TABLE users (id INT);\nINSERT INTO users VALUES (1);")
        .unwrap();
    encoder.finish().unwrap();

    let splitter = Splitter::new(input_file, output_dir.clone());
    let stats = splitter.split().unwrap();

    assert_eq!(stats.tables_found, 1);
    assert_eq!(stats.statements_processed, 2);
    assert!(output_dir.join("users.sql").exists());
}

#[test]
fn test_compression_detection() {
    assert_eq!(
        Compression::from_path(std::path::Path::new("file.sql")),
        Compression::None
    );
    assert_eq!(
        Compression::from_path(std::path::Path::new("file.sql.gz")),
        Compression::Gzip
    );
    assert_eq!(
        Compression::from_path(std::path::Path::new("file.sql.bz2")),
        Compression::Bzip2
    );
    assert_eq!(
        Compression::from_path(std::path::Path::new("file.sql.xz")),
        Compression::Xz
    );
    assert_eq!(
        Compression::from_path(std::path::Path::new("file.sql.zst")),
        Compression::Zstd
    );
}