vsf 0.3.4

Versatile Storage Format
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273

use super::traits::{EncodeNumber, EncodeNumberInclusive};

// ==================== UNSIGNED INTEGER ENCODING ====================

impl EncodeNumber for u8 {
    fn encode_number(&self) -> Vec<u8> {
        vec![b'3', *self]
    }
}

impl EncodeNumber for u16 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'4'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for u32 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'5'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for u64 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'6'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for u128 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'7'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for usize {
    fn encode_number(&self) -> Vec<u8> {
        // Auto-select smallest size that fits
        if *self <= u8::MAX as usize {
            vec![b'3', *self as u8]
        } else if *self <= u16::MAX as usize {
            let mut result = vec![b'4'];
            result.extend_from_slice(&(*self as u16).to_be_bytes());
            result
        } else if *self <= u32::MAX as usize {
            let mut result = vec![b'5'];
            result.extend_from_slice(&(*self as u32).to_be_bytes());
            result
        } else if *self <= u64::MAX as usize {
            let mut result = vec![b'6'];
            result.extend_from_slice(&(*self as u64).to_be_bytes());
            result
        } else {
            let mut result = vec![b'7'];
            result.extend_from_slice(&(*self as u128).to_be_bytes());
            result
        }
    }
}

impl EncodeNumberInclusive for usize {
    fn encode_usize_inclusive(&self) -> Vec<u8> {
        let base = 8; // 'u' marker: 8 bits
        let mut size = 8; // Size marker: 8 bits initially
        let mut result = vec![b'u'];

        // Try u3 (8-bit)
        let mut adder = base + size; // 16 bits overhead
        let mut cutoff = 0x80 - adder + 0x80;
        if *self < cutoff {
            result.push(b'3');
            result.push((*self + adder) as u8);
            return result;
        }

        // Try u4 (16-bit)
        size *= 2;
        adder = base + size; // 24 bits overhead
        cutoff = u16::MAX as usize - adder; // FIX: use u16 max for u4
        if *self <= cutoff {
            result.push(b'4');
            result.extend_from_slice(&((*self + adder) as u16).to_be_bytes());
            return result;
        }

        // Try u5 (32-bit)
        size *= 2;
        adder = base + size; // 40 bits overhead
        cutoff = u32::MAX as usize - adder; // FIX: use u32 max for u5
        if *self <= cutoff {
            result.push(b'5');
            result.extend_from_slice(&((*self + adder) as u32).to_be_bytes());
            return result;
        }

        // Try u6 (64-bit)
        size *= 2;
        adder = base + size; // 72 bits overhead
        cutoff = u64::MAX as usize - adder; // FIX: use u64 max for u6
        if *self <= cutoff {
            result.push(b'6');
            result.extend_from_slice(&((*self + adder) as u64).to_be_bytes());
            return result;
        }

        // Try u7 (128-bit)
        size *= 2;
        adder = base + size; // 136 bits overhead
        cutoff = u128::MAX as usize - adder; // FIX: use u128 max for u7
        if *self <= cutoff {
            result.push(b'7');
            result.extend_from_slice(&((*self + adder) as u128).to_be_bytes());
            return result;
        }

        // Try u8 (256-bit) - not yet implemented
        size *= 2;
        adder = base + size;
        cutoff = u128::MAX as usize - adder;
        if *self <= cutoff {
            result.push(b'8');
            result.extend_from_slice(&((*self + adder) as u128).to_be_bytes());
            return result;
        }

        panic!("Value too large for inclusive encoding (u8 not implemented)");
    }
}

// ==================== SIGNED INTEGER ENCODING ====================

impl EncodeNumber for i8 {
    fn encode_number(&self) -> Vec<u8> {
        vec![b'3', *self as u8]
    }
}

impl EncodeNumber for i16 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'4'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for i32 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'5'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for i64 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'6'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for i128 {
    fn encode_number(&self) -> Vec<u8> {
        let mut result = vec![b'7'];
        result.extend_from_slice(&self.to_be_bytes());
        result
    }
}

impl EncodeNumber for isize {
    fn encode_number(&self) -> Vec<u8> {
        // Auto-select smallest size that fits
        // For positive values, use unsigned limits
        // For negative values, use signed limits
        if *self >= 0 {
            if *self <= u8::MAX as isize {
                vec![b'3', *self as u8]
            } else if *self <= u16::MAX as isize {
                let mut result = vec![b'4'];
                result.extend_from_slice(&(*self as i16).to_be_bytes());
                result
            } else if *self <= u32::MAX as isize {
                let mut result = vec![b'5'];
                result.extend_from_slice(&(*self as i32).to_be_bytes());
                result
            } else if *self <= u64::MAX as isize {
                let mut result = vec![b'6'];
                result.extend_from_slice(&(*self as i64).to_be_bytes());
                result
            } else {
                let mut result = vec![b'7'];
                result.extend_from_slice(&(*self as i128).to_be_bytes());
                result
            }
        } else if *self >= i8::MIN as isize {
            vec![b'3', *self as u8]
        } else if *self >= i16::MIN as isize {
            let mut result = vec![b'4'];
            result.extend_from_slice(&(*self as i16).to_be_bytes());
            result
        } else if *self >= i32::MIN as isize {
            let mut result = vec![b'5'];
            result.extend_from_slice(&(*self as i32).to_be_bytes());
            result
        } else if *self >= i64::MIN as isize {
            let mut result = vec![b'6'];
            result.extend_from_slice(&(*self as i64).to_be_bytes());
            result
        } else {
            let mut result = vec![b'7'];
            result.extend_from_slice(&(*self as i128).to_be_bytes());
            result
        }
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_encode_u8() {
        assert_eq!(42u8.encode_number(), vec![b'3', 42]);
        assert_eq!(255u8.encode_number(), vec![b'3', 255]);
    }

    #[test]
    fn test_encode_u16() {
        assert_eq!(300u16.encode_number(), vec![b'4', 0x01, 0x2C]);
        assert_eq!(4096u16.encode_number(), vec![b'4', 0x10, 0x00]);
    }

    #[test]
    fn test_encode_usize_auto() {
        // Should pick smallest size
        assert_eq!(42usize.encode_number(), vec![b'3', 42]);
        assert_eq!(300usize.encode_number(), vec![b'4', 0x01, 0x2C]);
        assert_eq!(
            100000usize.encode_number(),
            vec![b'5', 0x00, 0x01, 0x86, 0xA0]
        );
    }

    #[test]
    fn test_encode_inclusive() {
        // Value 256 in inclusive mode
        // overhead for u4 = 24 bits = 3 bytes
        // 256 + 24 = 280 = 0x0118
        let result = 256usize.encode_usize_inclusive();
        assert_eq!(result[0], b'u');
        assert_eq!(result[1], b'4');
        // 280 in big-endian
        assert_eq!(result[2], 0x01);
        assert_eq!(result[3], 0x18);
    }

    #[test]
    fn test_encode_isize_positive() {
        assert_eq!(42isize.encode_number(), vec![b'3', 42]);
    }

    #[test]
    fn test_encode_isize_negative() {
        assert_eq!((-42isize).encode_number(), vec![b'3', 0xD6]); // -42 as two's complement
    }
}