Files
go-cuckoo/table.go

254 lines
6.4 KiB
Go

package cuckoo
import (
"errors"
"fmt"
"iter"
"math/bits"
"strings"
)
// ErrBadHash occurs when the hashes given to a [Table] cause too many key
// collisions. Try rebuilding the table using:
//
// 1. Different hash seeds. Equal seeds produce equal hash functions, which
// always cycle.
// 2. A different [Hash] algorithm.
var ErrBadHash = errors.New("bad hash")
// A Table which uses cuckoo hashing to resolve collision. Create
// one with [New]. Or if you want more granularity, use [NewBy] or
// [NewCustom].
type Table[K, V any] struct {
tableA, tableB subtable[K, V]
growthFactor uint64
minLoadFactor float64
}
// TotalCapacity returns the number of slots allocated for the [Table]. To get the
// number of slots filled, look at [Table.Size].
func (t *Table[K, V]) TotalCapacity() uint64 {
return t.tableA.capacity + t.tableB.capacity
}
// Size returns how many slots are filled in the [Table].
func (t *Table[K, V]) Size() int {
return int(t.tableA.size + t.tableB.size)
}
func log2(n uint64) (m int) {
return max(0, bits.Len64(n)-1)
}
func (t *Table[K, V]) maxEvictions() int {
return 3 * log2(t.TotalCapacity())
}
func (t *Table[K, V]) load() float64 {
// When there are no slots in the table, we still treat the load as 100%.
// Every slot in the table is full.
if t.TotalCapacity() == 0 {
return 1.0
}
return float64(t.Size()) / float64(t.TotalCapacity())
}
// resize clears all tables, changes the sizes of them to a specific capacity,
// and fills them back up again. It is a helper function for [Table.grow] and
// [Table.shrink]; use them instead.
func (t *Table[K, V]) resize(capacity uint64) error {
entries := make([]entry[K, V], 0, t.Size())
for k, v := range t.Entries() {
entries = append(entries, entry[K, V]{k, v})
}
t.tableA.resize(capacity)
t.tableB.resize(capacity)
for _, entry := range entries {
if err := t.Put(entry.key, entry.value); err != nil {
return err
}
}
return nil
}
// grow increases the table's capacity by the growth factor. If the
// capacity is 0, it increases it to 1.
func (t *Table[K, V]) grow() error {
var newCapacity uint64
if t.TotalCapacity() == 0 {
newCapacity = 1
} else {
newCapacity = t.tableA.capacity * t.growthFactor
}
return t.resize(newCapacity)
}
// shrink reduces the table's capacity by the growth factor. It may
// reduce it down to 0.
func (t *Table[K, V]) shrink() error {
return t.resize(t.tableA.capacity / t.growthFactor)
}
// Get fetches the value for a key in the [Table]. Matches the comma-ok pattern
// of a builtin map; see [Table.Find] for plain indexing.
func (t *Table[K, V]) Get(key K) (value V, ok bool) {
if item, ok := t.tableA.get(key); ok {
return item, true
}
if item, ok := t.tableB.get(key); ok {
return item, true
}
return
}
// Find fetches the value of a key. Matches direct indexing of a builtin map;
// see [Table.Get] for a comma-ok pattern.
func (t *Table[K, V]) Find(key K) (value V) {
value, _ = t.Get(key)
return
}
// Has returns true if a key has a value in the table.
func (t *Table[K, V]) Has(key K) (exists bool) {
_, exists = t.Get(key)
return
}
// Put sets the value for a key. Returns error if its value cannot be set.
func (t *Table[K, V]) Put(key K, value V) (err error) {
if t.tableA.update(key, value) {
return nil
}
if t.tableB.update(key, value) {
return nil
}
entry, eviction := entry[K, V]{key, value}, false
for range t.maxEvictions() {
if entry, eviction = t.tableA.evict(entry); !eviction {
return nil
}
if entry, eviction = t.tableB.evict(entry); !eviction {
return nil
}
}
if t.load() < t.minLoadFactor {
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
}
if err := t.grow(); err != nil {
return err
}
return t.Put(entry.key, entry.value)
}
// Drop removes a value for a key in the table. Returns an error if its value
// cannot be removed.
func (t *Table[K, V]) Drop(key K) (err error) {
t.tableA.drop(key)
t.tableB.drop(key)
if t.load() < t.minLoadFactor {
return t.shrink()
}
return nil
}
// Entries returns an unordered sequence of all key-value pairs in the table.
func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
return func(yield func(K, V) bool) {
for _, slot := range t.tableA.slots {
if slot.occupied {
if !yield(slot.key, slot.value) {
return
}
}
}
for _, slot := range t.tableB.slots {
if slot.occupied {
if !yield(slot.key, slot.value) {
return
}
}
}
}
}
// String returns the entries of the table as a string in the format:
// "table[k1:v1 k2:v2 ...]".
func (t *Table[K, V]) String() string {
var sb strings.Builder
sb.WriteString("table[")
first := true
for k, v := range t.Entries() {
if !first {
sb.WriteString(" ")
}
fmt.Fprintf(&sb, "%v:%v", k, v)
first = false
}
sb.WriteString("]")
return sb.String()
}
// NewCustom creates a [Table] with custom [Hash] and [EqualFunc]
// functions, along with any [Option] the user provides.
func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
settings := &settings{
growthFactor: DefaultGrowthFactor,
bucketSize: DefaultCapacity,
minLoadFactor: defaultMinimumLoad,
}
for _, option := range options {
option(settings)
}
return &Table[K, V]{
growthFactor: settings.growthFactor,
minLoadFactor: settings.minLoadFactor,
tableA: newSubtable[K, V](settings.bucketSize, hashA, compare),
tableB: newSubtable[K, V](settings.bucketSize, hashB, compare),
}
}
func pipe[X, Y, Z any](a func(X) Y, b func(Y) Z) func(X) Z {
return func(x X) Z { return b(a(x)) }
}
// NewBy creates a [Table] for any key type by using keyFunc to derive a
// comparable key. Two keys with the same derived key are treated as equal.
func NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
return NewCustom[K, V](
pipe(keyFunc, NewDefaultHash[C]()),
pipe(keyFunc, NewDefaultHash[C]()),
func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
options...,
)
}
// New creates a [Table] using the default [Hash] and [EqualFunc]. Use
// the [Option] functions to configure its behavior. Note that this constructor
// is only provided for comparable keys. For arbitrary keys, consider
// [NewBy] or [NewCustom].
func New[K comparable, V any](options ...Option) *Table[K, V] {
return NewCustom[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
}