mirror/zig
1
0
Fork 0
mirror of https://github.com/ziglang/zig.git synced 2026-02-12 20:37:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add iterative wyhash api

Browse Source
This commit is contained in:
Marc Tiehuis 2019-07-01 23:23:26 +12:00 committed by Sahnvour
parent c9ce43f59f
commit 83dffc70af
3 changed files with 112 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
std/hash.zig
View File

@ -17,6 +17,7 @@ pub const SipHash128 = siphash.SipHash128;
pub const murmur = @import("hash/murmur.zig");
pub const Murmur2_32 = murmur.Murmur2_32;
pub const Murmur2_64 = murmur.Murmur2_64;
pub const Murmur3_32 = murmur.Murmur3_32;
@ -24,7 +25,8 @@ pub const cityhash = @import("hash/cityhash.zig");
pub const CityHash32 = cityhash.CityHash32;
pub const CityHash64 = cityhash.CityHash64;
pub const wyhash = @import("hash/wyhash.zig").hash;
const wyhash = @import("hash/wyhash.zig");
pub const Wyhash = wyhash.Wyhash;
test "hash" {
_ = @import("hash/adler.zig");

164
std/hash/wyhash.zig
View File

@ -10,7 +10,7 @@ const primes = [_]u64{
};
fn read_bytes(comptime bytes: u8, data: []const u8) u64 {
return mem.readVarInt(u64, data[0..bytes], @import("builtin").endian);
return mem.readVarInt(u64, data[0..bytes], .Little);
}
fn read_8bytes_swapped(data: []const u8) u64 {
@ -18,7 +18,7 @@ fn read_8bytes_swapped(data: []const u8) u64 {
}
fn mum(a: u64, b: u64) u64 {
var r: u128 = @intCast(u128, a) * @intCast(u128, b);
var r = std.math.mulWide(u64, a, b);
r = (r >> 64) ^ r;
return @truncate(u64, r);
}
@ -31,69 +31,117 @@ 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;
pub const Wyhash = struct {
seed: u64,
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,
buf: [32]u8,
buf_len: usize,
msg_len: usize,
pub fn init(seed: u64) Wyhash {
return Wyhash{
.seed = seed,
.buf = undefined,
.buf_len = 0,
.msg_len = 0,
};
}
fn round(self: *Wyhash, b: []const u8) void {
std.debug.assert(b.len == 32);
self.seed = mix0(
read_bytes(8, b[0..]),
read_bytes(8, b[8..]),
self.seed,
) ^ mix1(
read_bytes(8, key[i + 16 ..]),
read_bytes(8, key[i + 24 ..]),
seed,
read_bytes(8, b[16..]),
read_bytes(8, b[24..]),
self.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),
};
pub fn update(self: *Wyhash, b: []const u8) void {
var off: usize = 0;
return mum(seed ^ key.len, primes[4]);
}
// Partial from previous.
if (self.buf_len != 0 and self.buf_len + b.len > 32) {
off += 32 - self.buf_len;
mem.copy(u8, self.buf[self.buf_len..], b[0..off]);
self.round(self.buf[0..]);
self.buf_len = 0;
}
// Full middle blocks.
while (off + 32 <= b.len) : (off += 32) {
@inlineCall(self.round, b[off .. off + 32]);
}
// Remainder for next pass.
mem.copy(u8, self.buf[self.buf_len..], b[off..]);
self.buf_len += @intCast(u8, b[off..].len);
self.msg_len += b.len;
}
pub fn final(self: *Wyhash) u64 {
const seed = self.seed;
const rem_len = @intCast(u5, self.buf_len);
const rem_key = self.buf[0..self.buf_len];
self.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(self.seed ^ self.msg_len, primes[4]);
}
pub fn hash(seed: u64, input: []const u8) u64 {
var c = Wyhash.init(seed);
c.update(input);
return c.final();
}
};
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);
const hash = Wyhash.hash;
expectEqual(hash(0, ""), 0x0);
expectEqual(hash(1, "a"), 0xbed235177f41d328);
expectEqual(hash(2, "abc"), 0xbe348debe59b27c3);
expectEqual(hash(3, "message digest"), 0x37320f657213a290);
expectEqual(hash(4, "abcdefghijklmnopqrstuvwxyz"), 0xd0b270e1d8a7019c);
expectEqual(hash(5, "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789"), 0x602a1894d3bbfe7f);
expectEqual(hash(6, "12345678901234567890123456789012345678901234567890123456789012345678901234567890"), 0x829e9c148b75970e);
}

6
std/hash_map.zig
View File

@ -5,7 +5,7 @@ const testing = std.testing;
const math = std.math;
const mem = std.mem;
const meta = std.meta;
const wyhash = std.hash.wyhash;
const Wyhash = std.hash.Wyhash;
const Allocator = mem.Allocator;
const builtin = @import("builtin");
@ -557,7 +557,7 @@ pub fn autoHash(key: var, seed: u64) u64 {
builtin.TypeId.EnumLiteral,
=> @compileError("cannot hash this type"),
builtin.TypeId.Int => return wyhash(std.mem.asBytes(&key), seed),
builtin.TypeId.Int => return Wyhash.hash(seed, std.mem.asBytes(&key)),
builtin.TypeId.Float => |info| return autoHash(@bitCast(@IntType(false, info.bits), key), seed),
@ -594,7 +594,7 @@ pub fn autoHash(key: var, seed: u64) u64 {
// If there's no unused bits in the child type, we can just hash
// this as an array of bytes.
if (info.child.bit_count % 8 == 0) {
return wyhash(mem.asBytes(&key), seed);
return Wyhash.hash(seed, mem.asBytes(&key));
}
// Otherwise, hash every element.