zig/std/hash/wyhash.zig

100 lines
6.1 KiB
Zig
Raw Normal View History

const std = @import("std");
const mem = std.mem;
const primes = [_]u64{
0xa0761d6478bd642f,
0xe7037ed1a0b428db,
0x8ebc6af09c88c6e3,
0x589965cc75374cc3,
0x1d8e4e27c47d124f,
};
fn read_bytes(comptime bytes: u8, data: []const u8) u64 {
return mem.readVarInt(u64, data[0..bytes], @import("builtin").endian);
}
fn read_8bytes_swapped(data: []const u8) u64 {
return (read_bytes(4, data) << 32 | read_bytes(4, data[4..]));
}
fn mum(a: u64, b: u64) u64 {
var r: u128 = @intCast(u128, a) * @intCast(u128, b);
r = (r >> 64) ^ r;
return @truncate(u64, r);
}
fn mix0(a: u64, b: u64, seed: u64) u64 {
return mum(a ^ seed ^ primes[0], b ^ seed ^ primes[1]);
}
fn mix1(a: u64, b: u64, seed: u64) u64 {
return mum(a ^ seed ^ primes[2], b ^ seed ^ primes[3]);
}
pub fn hash(key: []const u8, initial_seed: u64) u64 {
var seed = initial_seed;
var i: usize = 0;
while (i + 32 <= key.len) : (i += 32) {
seed = mix0(
read_bytes(8, key[i..]),
read_bytes(8, key[i + 8 ..]),
seed,
) ^ mix1(
read_bytes(8, key[i + 16 ..]),
read_bytes(8, key[i + 24 ..]),
seed,
);
}
const rem_len = @truncate(u5, key.len);
const rem_key = key[i..];
seed = switch (rem_len) {
0 => seed,
1 => mix0(read_bytes(1, rem_key), primes[4], seed),
2 => mix0(read_bytes(2, rem_key), primes[4], seed),
3 => mix0((read_bytes(2, rem_key) << 8) | read_bytes(1, rem_key[2..]), primes[4], seed),
4 => mix0(read_bytes(4, rem_key), primes[4], seed),
5 => mix0((read_bytes(4, rem_key) << 8) | read_bytes(1, rem_key[4..]), primes[4], seed),
6 => mix0((read_bytes(4, rem_key) << 16) | read_bytes(2, rem_key[4..]), primes[4], seed),
7 => mix0((read_bytes(4, rem_key) << 24) | (read_bytes(2, rem_key[4..]) << 8) | read_bytes(1, rem_key[6..]), primes[4], seed),
8 => mix0(read_8bytes_swapped(rem_key), primes[4], seed),
9 => mix0(read_8bytes_swapped(rem_key), read_bytes(1, rem_key[8..]), seed),
10 => mix0(read_8bytes_swapped(rem_key), read_bytes(2, rem_key[8..]), seed),
11 => mix0(read_8bytes_swapped(rem_key), (read_bytes(2, rem_key[8..]) << 8) | read_bytes(1, rem_key[10..]), seed),
12 => mix0(read_8bytes_swapped(rem_key), read_bytes(4, rem_key[8..]), seed),
13 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 8) | read_bytes(1, rem_key[12..]), seed),
14 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 16) | read_bytes(2, rem_key[12..]), seed),
15 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 24) | (read_bytes(2, rem_key[12..]) << 8) | read_bytes(1, rem_key[14..]), seed),
16 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed),
17 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(1, rem_key[16..]), primes[4], seed),
18 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(2, rem_key[16..]), primes[4], seed),
19 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(2, rem_key[16..]) << 8) | read_bytes(1, rem_key[18..]), primes[4], seed),
20 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(4, rem_key[16..]), primes[4], seed),
21 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 8) | read_bytes(1, rem_key[20..]), primes[4], seed),
22 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 16) | read_bytes(2, rem_key[20..]), primes[4], seed),
23 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 24) | (read_bytes(2, rem_key[20..]) << 8) | read_bytes(1, rem_key[22..]), primes[4], seed),
24 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), primes[4], seed),
25 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(1, rem_key[24..]), seed),
26 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(2, rem_key[24..]), seed),
27 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(2, rem_key[24..]) << 8) | read_bytes(1, rem_key[26..]), seed),
28 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(4, rem_key[24..]), seed),
29 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 8) | read_bytes(1, rem_key[28..]), seed),
30 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 16) | read_bytes(2, rem_key[28..]), seed),
31 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 24) | (read_bytes(2, rem_key[28..]) << 8) | read_bytes(1, rem_key[30..]), seed),
};
return mum(seed ^ key.len, primes[4]);
}
test "test vectors" {
const expectEqual = std.testing.expectEqual;
expectEqual(hash("", 0), 0x0);
expectEqual(hash("a", 1), 0xbed235177f41d328);
expectEqual(hash("abc", 2), 0xbe348debe59b27c3);
expectEqual(hash("message digest", 3), 0x37320f657213a290);
expectEqual(hash("abcdefghijklmnopqrstuvwxyz", 4), 0xd0b270e1d8a7019c);
expectEqual(hash("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789", 5), 0x602a1894d3bbfe7f);
expectEqual(hash("12345678901234567890123456789012345678901234567890123456789012345678901234567890", 6), 0x829e9c148b75970e);
}