xls-rs 0.1.2

A powerful CLI tool and library for spreadsheet manipulation with pandas-style operations. Supports CSV, Excel (XLSX, XLS, ODS), Parquet, and Avro formats with formula evaluation, data transformation, and comprehensive analytics capabilities.
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

//! Tests for streaming module

use xls_rs::streaming::{ChunkMetadata, DataChunk, StreamingProcessor};

#[test]
fn test_data_chunk_creation() {
    let data = vec![
        vec!["Name".to_string(), "Age".to_string()],
        vec!["Alice".to_string(), "30".to_string()],
    ];

    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: Some("test.csv".to_string()),
        row_count: 2,
        column_count: 2,
    };

    let chunk = DataChunk {
        sequence: 1,
        data: data.clone(),
        metadata: metadata.clone(),
    };

    assert_eq!(chunk.sequence, 1);
    assert_eq!(chunk.data.len(), 2);
    assert_eq!(chunk.metadata.row_count, 2);
    assert_eq!(chunk.metadata.column_count, 2);
}

#[test]
fn test_streaming_processor_creation() {
    let _processor = StreamingProcessor::new(1000, 10);
}

#[test]
fn test_chunk_metadata_serialization() {
    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: Some("test.csv".to_string()),
        row_count: 100,
        column_count: 5,
    };

    let json = serde_json::to_string(&metadata).unwrap();
    assert!(json.contains("timestamp"));
    assert!(json.contains("test.csv"));
    assert!(json.contains("100"));
}

#[test]
fn test_chunk_metadata_deserialization() {
    let json = r#"{
        "timestamp": "2026-01-26T10:00:00Z",
        "source": "test.csv",
        "row_count": 100,
        "column_count": 5
    }"#;

    let metadata: ChunkMetadata = serde_json::from_str(json).unwrap();
    assert_eq!(metadata.timestamp, "2026-01-26T10:00:00Z");
    assert_eq!(metadata.source, Some("test.csv".to_string()));
    assert_eq!(metadata.row_count, 100);
    assert_eq!(metadata.column_count, 5);
}

#[test]
fn test_data_chunk_clone() {
    let data = vec![vec!["test".to_string()]];
    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: None,
        row_count: 1,
        column_count: 1,
    };

    let chunk = DataChunk {
        sequence: 1,
        data: data.clone(),
        metadata: metadata.clone(),
    };

    let cloned = chunk.clone();
    assert_eq!(cloned.sequence, chunk.sequence);
    assert_eq!(cloned.data, chunk.data);
}

#[test]
fn test_chunk_with_large_data() {
    let data: Vec<Vec<String>> = (0..1000)
        .map(|i| vec![format!("row_{}", i), format!("value_{}", i)])
        .collect();

    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: Some("large.csv".to_string()),
        row_count: 1000,
        column_count: 2,
    };

    let chunk = DataChunk {
        sequence: 1,
        data,
        metadata,
    };

    assert_eq!(chunk.data.len(), 1000);
    assert_eq!(chunk.metadata.row_count, 1000);
}

#[test]
fn test_chunk_with_empty_data() {
    let data: Vec<Vec<String>> = vec![];
    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: None,
        row_count: 0,
        column_count: 0,
    };

    let chunk = DataChunk {
        sequence: 0,
        data,
        metadata,
    };

    assert_eq!(chunk.data.len(), 0);
    assert_eq!(chunk.metadata.row_count, 0);
}

#[test]
fn test_multiple_chunks_sequence() {
    let metadata = ChunkMetadata {
        timestamp: "2026-01-26T10:00:00Z".to_string(),
        source: Some("test.csv".to_string()),
        row_count: 10,
        column_count: 2,
    };

    let chunks: Vec<DataChunk> = (0..5)
        .map(|i| DataChunk {
            sequence: i,
            data: vec![vec![format!("row_{}", i)]],
            metadata: metadata.clone(),
        })
        .collect();

    assert_eq!(chunks.len(), 5);
    assert_eq!(chunks[0].sequence, 0);
    assert_eq!(chunks[4].sequence, 4);
}