tinyklv 0.1.0

The simplest Key-Length-Value (KLV) framework in Rust
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

use tinyklv::codecs::string::dec::{to_string_utf16_be, to_string_utf16_le};
use tinyklv::codecs::string::enc::{from_string_utf16_be, from_string_utf16_le};

#[test]
/// Tests `to_string_utf16_le(4)` decodes `[0x41, 0x00, 0x42, 0x00]` to `"AB"`.
fn utf16_le_known_ab() {
    // "AB" in UTF-16 LE
    let mut input: &[u8] = &[0x41, 0x00, 0x42, 0x00];
    let result = to_string_utf16_le(4)(&mut input).unwrap();
    assert_eq!(result, "AB");
}

#[test]
/// Tests `from_string_utf16_le("AB")` emits `[0x41, 0x00, 0x42, 0x00]`.
fn utf16_le_encode_ab() {
    let encoded = from_string_utf16_le("AB");
    assert_eq!(encoded, vec![0x41, 0x00, 0x42, 0x00]);
}

#[test]
/// Tests UTF-16 LE ASCII string roundtrip.
fn utf16_le_roundtrip_ascii() {
    let text = "Hello";
    let encoded = from_string_utf16_le(text);
    let decoded = to_string_utf16_le(encoded.len())(&mut encoded.as_slice()).unwrap();
    assert_eq!(text, decoded);
}

#[test]
/// Tests UTF-16 LE empty-string encode produces empty bytes and decode produces empty string.
fn utf16_le_empty_string() {
    let encoded = from_string_utf16_le("");
    assert!(encoded.is_empty());
    let decoded = to_string_utf16_le(0)(&mut [].as_slice()).unwrap();
    assert_eq!(decoded, "");
}

#[test]
/// Tests `to_string_utf16_le(3)` errors on odd byte count.
fn utf16_le_odd_length_err() {
    // 3 bytes is odd - not a valid UTF-16 length
    let mut input: &[u8] = &[0x41, 0x00, 0x42];
    let result = to_string_utf16_le(3)(&mut input);
    assert!(result.is_err(), "odd byte length should fail for UTF-16 LE");
}

#[test]
/// Tests UTF-16 LE surrogate-pair emoji roundtrip (U+1F600 encodes to 4 bytes).
fn utf16_le_emoji_roundtrip() {
    // Emoji U+1F600 encodes as a surrogate pair in UTF-16 (4 bytes)
    let text = "\u{1F600}";
    let encoded = from_string_utf16_le(text);
    assert_eq!(encoded.len(), 4, "surrogate pair should produce 4 bytes");
    let decoded = to_string_utf16_le(encoded.len())(&mut encoded.as_slice()).unwrap();
    assert_eq!(text, decoded);
}

#[test]
/// Tests UTF-16 LE roundtrip preserves Latin-1 extended Unicode characters.
fn utf16_le_unicode_roundtrip() {
    let text = "Héllo";
    let encoded = from_string_utf16_le(text);
    assert_eq!(encoded.len() % 2, 0, "UTF-16 encoding must be even-length");
    let decoded = to_string_utf16_le(encoded.len())(&mut encoded.as_slice()).unwrap();
    assert_eq!(text, decoded);
}

#[test]
/// Tests `to_string_utf16_be(4)` decodes `[0x00, 0x41, 0x00, 0x42]` to `"AB"`.
fn utf16_be_known_ab() {
    // "AB" in UTF-16 BE
    let mut input: &[u8] = &[0x00, 0x41, 0x00, 0x42];
    let result = to_string_utf16_be(4)(&mut input).unwrap();
    assert_eq!(result, "AB");
}

#[test]
/// Tests `from_string_utf16_be("AB")` emits `[0x00, 0x41, 0x00, 0x42]`.
fn utf16_be_encode_ab() {
    let encoded = from_string_utf16_be("AB");
    assert_eq!(encoded, vec![0x00, 0x41, 0x00, 0x42]);
}

#[test]
/// Tests UTF-16 BE ASCII string roundtrip.
fn utf16_be_roundtrip_ascii() {
    let text = "KLV";
    let encoded = from_string_utf16_be(text);
    let decoded = to_string_utf16_be(encoded.len())(&mut encoded.as_slice()).unwrap();
    assert_eq!(text, decoded);
}

#[test]
/// Tests UTF-16 BE empty-string encode produces empty bytes and decode produces empty string.
fn utf16_be_empty_string() {
    let encoded = from_string_utf16_be("");
    assert!(encoded.is_empty());
    let decoded = to_string_utf16_be(0)(&mut [].as_slice()).unwrap();
    assert_eq!(decoded, "");
}

#[test]
/// Tests `to_string_utf16_be(3)` errors on odd byte count.
fn utf16_be_odd_length_err() {
    let mut input: &[u8] = &[0x00, 0x41, 0x00];
    let result = to_string_utf16_be(3)(&mut input);
    assert!(result.is_err(), "odd byte length should fail for UTF-16 BE");
}

#[test]
/// Tests UTF-16 BE roundtrip preserves Latin-1 extended Unicode characters.
fn utf16_be_unicode_roundtrip() {
    let text = "Héllo";
    let encoded = from_string_utf16_be(text);
    assert_eq!(encoded.len() % 2, 0, "UTF-16 encoding must be even-length");
    let decoded = to_string_utf16_be(encoded.len())(&mut encoded.as_slice()).unwrap();
    assert_eq!(text, decoded);
}

#[test]
/// Tests that UTF-16 LE and BE encoders produce byte-reversed outputs for the same input.
fn utf16_le_vs_be_differ() {
    let text = "A";
    let le = from_string_utf16_le(text);
    let be = from_string_utf16_be(text);
    assert_eq!(le, vec![0x41, 0x00]);
    assert_eq!(be, vec![0x00, 0x41]);
    assert_ne!(le, be);
}

#[test]
/// Tests that decoding LE-encoded bytes as BE produces incorrect output (mismatched endianness).
fn utf16_cross_decode_differs() {
    // "AB" encoded as LE, then decoded as BE gives wrong result
    let text = "AB";
    let le_encoded = from_string_utf16_le(text);
    let as_be = to_string_utf16_be(le_encoded.len())(&mut le_encoded.as_slice()).unwrap();
    assert_ne!(
        as_be, text,
        "mismatched endian decode should produce garbage"
    );
}