Compare commits
4 Commits
v0.3.0
...
2eeff25efd
| Author | SHA1 | Date | |
|---|---|---|---|
|
2eeff25efd
|
|||
|
6a5b40c097
|
|||
|
395a3560c7
|
|||
|
2fd9da973b
|
@@ -114,9 +114,6 @@ linters:
|
|||||||
# Reports uses of functions with replacement inside the testing package.
|
# Reports uses of functions with replacement inside the testing package.
|
||||||
- usetesting
|
- usetesting
|
||||||
|
|
||||||
# Reports mixed receiver types in structs/interfaces.
|
|
||||||
- recvcheck
|
|
||||||
|
|
||||||
settings:
|
settings:
|
||||||
revive:
|
revive:
|
||||||
rules:
|
rules:
|
||||||
|
|||||||
@@ -1,11 +1,11 @@
|
|||||||
package cuckoo
|
package cuckoo
|
||||||
|
|
||||||
// An EqualFunc determines whethers two keys are 'equal'. Keys that are 'equal'
|
// An EqualFunc determines whethers two keys are 'equal'. Keys that are 'equal'
|
||||||
// are teated as the same by the [Table]. A good EqualFunc is pure,
|
// are teated as the same by the [HashTable]. A good EqualFunc is pure,
|
||||||
// deterministic, and fast. By default, [New] uses [DefaultEqualFunc].
|
// deterministic, and fast. By default, [New] uses [DefaultEqualFunc].
|
||||||
//
|
//
|
||||||
// This function MUST NOT return true if the [Hash] digest of two keys
|
// This function MUST NOT return true if the [Hash] digest of two keys
|
||||||
// are different: the [Table] will not work.
|
// are different: the [HashTable] will not work.
|
||||||
type EqualFunc[K any] = func(a, b K) bool
|
type EqualFunc[K any] = func(a, b K) bool
|
||||||
|
|
||||||
// DefaultEqualFunc compares two keys by strict equality. Returns true if the
|
// DefaultEqualFunc compares two keys by strict equality. Returns true if the
|
||||||
|
|||||||
@@ -73,16 +73,16 @@ func FuzzInsertLookup(f *testing.F) {
|
|||||||
|
|
||||||
delete(expected, step.key)
|
delete(expected, step.key)
|
||||||
|
|
||||||
_, ok := actual.Get(step.key)
|
_, err = actual.Get(step.key)
|
||||||
assert.False(ok)
|
assert.Error(err)
|
||||||
} else {
|
} else {
|
||||||
err := actual.Put(step.key, step.value)
|
err := actual.Put(step.key, step.value)
|
||||||
assert.NoError(err)
|
assert.NoError(err)
|
||||||
|
|
||||||
expected[step.key] = step.value
|
expected[step.key] = step.value
|
||||||
|
|
||||||
found, ok := actual.Get(step.key)
|
found, err := actual.Get(step.key)
|
||||||
assert.True(ok)
|
assert.NoError(err)
|
||||||
assert.Equal(step.value, found)
|
assert.Equal(step.value, found)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -108,12 +108,12 @@ func TestGetMany(t *testing.T) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
for i := range 2_000 {
|
for i := range 2_000 {
|
||||||
value, ok := table.Get(i)
|
value, err := table.Get(i)
|
||||||
if i < 1_000 {
|
if i < 1_000 {
|
||||||
assert.True(ok)
|
assert.NoError(err)
|
||||||
assert.Equal(value, true)
|
assert.Equal(value, true)
|
||||||
} else {
|
} else {
|
||||||
assert.False(ok)
|
assert.Error(err)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -14,19 +14,19 @@ func Example_basic() {
|
|||||||
fmt.Println("Put error:", err)
|
fmt.Println("Put error:", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
if item, ok := table.Get(1); !ok {
|
if item, err := table.Get(1); err != nil {
|
||||||
fmt.Println("Not Found 1!")
|
fmt.Println("Error:", err)
|
||||||
} else {
|
} else {
|
||||||
fmt.Println("Found 1:", item)
|
fmt.Println("Found 1:", item)
|
||||||
}
|
}
|
||||||
|
|
||||||
if item, ok := table.Get(0); !ok {
|
if item, err := table.Get(0); err != nil {
|
||||||
fmt.Println("Not Found 0!")
|
fmt.Println("Error:", err)
|
||||||
} else {
|
} else {
|
||||||
fmt.Println("Found 0:", item)
|
fmt.Println("Found 0:", item)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Output:
|
// Output:
|
||||||
// Found 1: Hello, World!
|
// Found 1: Hello, World!
|
||||||
// Not Found 0!
|
// Error: key '0' not found
|
||||||
}
|
}
|
||||||
|
|||||||
4
hash.go
4
hash.go
@@ -7,9 +7,9 @@ import (
|
|||||||
// A Hash function maps any data to a fixed-length value (in this case, a
|
// A Hash function maps any data to a fixed-length value (in this case, a
|
||||||
// [uint64]).
|
// [uint64]).
|
||||||
//
|
//
|
||||||
// It is used by the [Table] to evenly distribute values
|
// It is used by the [HashTable] to evenly distribute values
|
||||||
// amongst its slots. A good hash function is uniform, [chaotic], and
|
// amongst its slots. A good hash function is uniform, [chaotic], and
|
||||||
// deterministic. [Table] uses [NewDefaultHash] by default, which is built on
|
// deterministic. [HashTable] uses [NewDefaultHash] by default, which is built on
|
||||||
// [maphash.Comparable].
|
// [maphash.Comparable].
|
||||||
//
|
//
|
||||||
// [chaotic]: https://en.wikipedia.org/wiki/Avalanche_effect
|
// [chaotic]: https://en.wikipedia.org/wiki/Avalanche_effect
|
||||||
|
|||||||
246
hash_table.go
Normal file
246
hash_table.go
Normal file
@@ -0,0 +1,246 @@
|
|||||||
|
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 HashTable which uses cuckoo hashing to resolve collision. Create
|
||||||
|
// one with [New]. Or if you want more granularity, use [NewBy] or
|
||||||
|
// [NewCustom].
|
||||||
|
type HashTable[K, V any] struct {
|
||||||
|
tableA, tableB table[K, V]
|
||||||
|
growthFactor uint64
|
||||||
|
minLoadFactor float64
|
||||||
|
}
|
||||||
|
|
||||||
|
// TotalCapacity returns the number of slots allocated for the [HashTable]. To get the
|
||||||
|
// number of slots filled, look at [HashTable.Size].
|
||||||
|
func (t *HashTable[K, V]) TotalCapacity() uint64 {
|
||||||
|
return t.tableA.capacity + t.tableB.capacity
|
||||||
|
}
|
||||||
|
|
||||||
|
// Size returns how many slots are filled in the [HashTable].
|
||||||
|
func (t *HashTable[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 *HashTable[K, V]) maxEvictions() int {
|
||||||
|
return 3 * log2(t.TotalCapacity())
|
||||||
|
}
|
||||||
|
|
||||||
|
func (t *HashTable[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 [HashTable.grow] and
|
||||||
|
// [HashTable.shrink]; use them instead.
|
||||||
|
func (t *HashTable[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 *HashTable[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 *HashTable[K, V]) shrink() error {
|
||||||
|
return t.resize(t.tableA.capacity / t.growthFactor)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Get fetches the value for a key in the [HashTable]. Returns an error if no value
|
||||||
|
// is found.
|
||||||
|
func (t *HashTable[K, V]) Get(key K) (value V, err error) {
|
||||||
|
if item, ok := t.tableA.get(key); ok {
|
||||||
|
return item, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
if item, ok := t.tableB.get(key); ok {
|
||||||
|
return item, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
return value, fmt.Errorf("key '%v' not found", key)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Has returns true if a key has a value in the table.
|
||||||
|
func (t *HashTable[K, V]) Has(key K) (exists bool) {
|
||||||
|
_, err := t.Get(key)
|
||||||
|
return err == nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// Put sets the value for a key. Returns error if its value cannot be set.
|
||||||
|
func (t *HashTable[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 *HashTable[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 *HashTable[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 *HashTable[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 [HashTable] 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) *HashTable[K, V] {
|
||||||
|
settings := &settings{
|
||||||
|
growthFactor: DefaultGrowthFactor,
|
||||||
|
bucketSize: DefaultCapacity,
|
||||||
|
minLoadFactor: defaultMinimumLoad,
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, option := range options {
|
||||||
|
option(settings)
|
||||||
|
}
|
||||||
|
|
||||||
|
return &HashTable[K, V]{
|
||||||
|
growthFactor: settings.growthFactor,
|
||||||
|
minLoadFactor: settings.minLoadFactor,
|
||||||
|
tableA: newTable[K, V](settings.bucketSize, hashA, compare),
|
||||||
|
tableB: newTable[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 [HashTable] 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) *HashTable[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 [HashTable] 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) *HashTable[K, V] {
|
||||||
|
return NewCustom[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
|
||||||
|
}
|
||||||
14
settings.go
14
settings.go
@@ -2,18 +2,18 @@ package cuckoo
|
|||||||
|
|
||||||
import "fmt"
|
import "fmt"
|
||||||
|
|
||||||
// DefaultCapacity is the initial capacity of a [Table]. It is inspired from
|
// DefaultCapacity is the initial capacity of a [HashTable]. It is inspired from
|
||||||
// Java's [HashMap] implementation, which also uses 16.
|
// Java's [HashMap] implementation, which also uses 16.
|
||||||
//
|
//
|
||||||
// [HashMap]: https://docs.oracle.com/javase/8/docs/api/java/util/HashMap.html#HashMap--
|
// [HashMap]: https://docs.oracle.com/javase/8/docs/api/java/util/HashMap.html#HashMap--
|
||||||
const DefaultCapacity uint64 = 16
|
const DefaultCapacity uint64 = 16
|
||||||
|
|
||||||
// DefaultGrowthFactor is the standard resize multiplier for a [Table]. Most
|
// DefaultGrowthFactor is the standard resize multiplier for a [HashTable]. Most
|
||||||
// implementations use 2.
|
// implementations use 2.
|
||||||
const DefaultGrowthFactor uint64 = 2
|
const DefaultGrowthFactor uint64 = 2
|
||||||
|
|
||||||
// defaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
|
// defaultMinimumLoad is the default lowest acceptable occupancy of a [HashTable].
|
||||||
// The higher the minimum load, the more likely that a [Table.Put] will not
|
// The higher the minimum load, the more likely that a [HashTable.Put] will not
|
||||||
// succeed. The value of 5% is taken from [libcuckoo].
|
// succeed. The value of 5% is taken from [libcuckoo].
|
||||||
//
|
//
|
||||||
// [libcuckoo]: https://github.com/efficient/libcuckoo/blob/656714705a055df2b7a605eb3c71586d9da1e119/libcuckoo/cuckoohash_config.hh#L21
|
// [libcuckoo]: https://github.com/efficient/libcuckoo/blob/656714705a055df2b7a605eb3c71586d9da1e119/libcuckoo/cuckoohash_config.hh#L21
|
||||||
@@ -25,11 +25,11 @@ type settings struct {
|
|||||||
bucketSize uint64
|
bucketSize uint64
|
||||||
}
|
}
|
||||||
|
|
||||||
// An Option modifies the settings of a [Table]. It is used in its constructors
|
// An Option modifies the settings of a [HashTable]. It is used in its constructors
|
||||||
// like [New], for example.
|
// like [New], for example.
|
||||||
type Option func(*settings)
|
type Option func(*settings)
|
||||||
|
|
||||||
// Capacity modifies the starting capacity of each subtable of the [Table]. The
|
// Capacity modifies the starting capacity of each table of the [HashTable]. The
|
||||||
// value must be non-negative.
|
// value must be non-negative.
|
||||||
func Capacity(value int) Option {
|
func Capacity(value int) Option {
|
||||||
if value < 0 {
|
if value < 0 {
|
||||||
@@ -39,7 +39,7 @@ func Capacity(value int) Option {
|
|||||||
return func(s *settings) { s.bucketSize = uint64(value) }
|
return func(s *settings) { s.bucketSize = uint64(value) }
|
||||||
}
|
}
|
||||||
|
|
||||||
// GrowthFactor controls how much the capacity of the [Table] multiplies when
|
// GrowthFactor controls how much the capacity of the [HashTable] multiplies when
|
||||||
// it must resize. The value must be greater than 1.
|
// it must resize. The value must be greater than 1.
|
||||||
func GrowthFactor(value int) Option {
|
func GrowthFactor(value int) Option {
|
||||||
if value < 2 {
|
if value < 2 {
|
||||||
|
|||||||
103
subtable.go
103
subtable.go
@@ -1,103 +0,0 @@
|
|||||||
package cuckoo
|
|
||||||
|
|
||||||
type entry[K, V any] struct {
|
|
||||||
key K
|
|
||||||
value V
|
|
||||||
}
|
|
||||||
|
|
||||||
type slot[K, V any] struct {
|
|
||||||
entry[K, V]
|
|
||||||
occupied bool
|
|
||||||
}
|
|
||||||
|
|
||||||
type subtable[K, V any] struct {
|
|
||||||
hash Hash[K]
|
|
||||||
slots []slot[K, V]
|
|
||||||
capacity, size uint64
|
|
||||||
compare EqualFunc[K]
|
|
||||||
}
|
|
||||||
|
|
||||||
// location determines where in the subtable a certain key would be placed. If
|
|
||||||
// the capacity is 0, this will panic.
|
|
||||||
func (t *subtable[K, V]) location(key K) uint64 {
|
|
||||||
return t.hash(key) % t.capacity
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *subtable[K, V]) get(key K) (value V, found bool) {
|
|
||||||
if t.capacity == 0 {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
slot := t.slots[t.location(key)]
|
|
||||||
return slot.value, slot.occupied && t.compare(slot.key, key)
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *subtable[K, V]) drop(key K) (occupied bool) {
|
|
||||||
if t.capacity == 0 {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
slot := &t.slots[t.location(key)]
|
|
||||||
|
|
||||||
if slot.occupied && t.compare(slot.key, key) {
|
|
||||||
slot.occupied = false
|
|
||||||
t.size--
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *subtable[K, V]) resize(capacity uint64) {
|
|
||||||
t.slots = make([]slot[K, V], capacity)
|
|
||||||
t.capacity = capacity
|
|
||||||
t.size = 0
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *subtable[K, V]) update(key K, value V) (updated bool) {
|
|
||||||
if t.capacity == 0 {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
slot := &t.slots[t.location(key)]
|
|
||||||
|
|
||||||
if slot.occupied && t.compare(slot.key, key) {
|
|
||||||
slot.value = value
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *subtable[K, V]) evict(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
|
|
||||||
if t.capacity == 0 {
|
|
||||||
return insertion, true
|
|
||||||
}
|
|
||||||
|
|
||||||
slot := &t.slots[t.location(insertion.key)]
|
|
||||||
|
|
||||||
if !slot.occupied {
|
|
||||||
slot.entry = insertion
|
|
||||||
slot.occupied = true
|
|
||||||
t.size++
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
if t.compare(slot.key, insertion.key) {
|
|
||||||
slot.value = insertion.value
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
insertion, slot.entry = slot.entry, insertion
|
|
||||||
return insertion, true
|
|
||||||
}
|
|
||||||
|
|
||||||
func newSubtable[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) subtable[K, V] {
|
|
||||||
return subtable[K, V]{
|
|
||||||
hash: hash,
|
|
||||||
capacity: capacity,
|
|
||||||
compare: compare,
|
|
||||||
size: 0,
|
|
||||||
slots: make([]slot[K, V], capacity),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
286
table.go
286
table.go
@@ -1,253 +1,103 @@
|
|||||||
package cuckoo
|
package cuckoo
|
||||||
|
|
||||||
import (
|
type entry[K, V any] struct {
|
||||||
"errors"
|
key K
|
||||||
"fmt"
|
value V
|
||||||
"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
|
type slot[K, V any] struct {
|
||||||
// number of slots filled, look at [Table.Size].
|
entry[K, V]
|
||||||
func (t *Table[K, V]) TotalCapacity() uint64 {
|
occupied bool
|
||||||
return t.tableA.capacity + t.tableB.capacity
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Size returns how many slots are filled in the [Table].
|
type table[K, V any] struct {
|
||||||
func (t *Table[K, V]) Size() int {
|
hash Hash[K]
|
||||||
return int(t.tableA.size + t.tableB.size)
|
slots []slot[K, V]
|
||||||
|
capacity, size uint64
|
||||||
|
compare EqualFunc[K]
|
||||||
}
|
}
|
||||||
|
|
||||||
func log2(n uint64) (m int) {
|
// location determines where in the table a certain key would be placed. If the
|
||||||
return max(0, bits.Len64(n)-1)
|
// capacity is 0, this will panic.
|
||||||
}
|
func (t table[K, V]) location(key K) uint64 {
|
||||||
|
return t.hash(key) % t.capacity
|
||||||
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
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func (t table[K, V]) get(key K) (value V, found bool) {
|
||||||
|
if t.capacity == 0 {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// Find fetches the value of a key. Matches direct indexing of a builtin map;
|
slot := t.slots[t.location(key)]
|
||||||
// see [Table.Get] for a comma-ok pattern.
|
return slot.value, slot.occupied && t.compare(slot.key, key)
|
||||||
func (t *Table[K, V]) Find(key K) (value V) {
|
}
|
||||||
value, _ = t.Get(key)
|
|
||||||
|
func (t *table[K, V]) drop(key K) (occupied bool) {
|
||||||
|
if t.capacity == 0 {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// Has returns true if a key has a value in the table.
|
slot := &t.slots[t.location(key)]
|
||||||
func (t *Table[K, V]) Has(key K) (exists bool) {
|
|
||||||
_, exists = t.Get(key)
|
if slot.occupied && t.compare(slot.key, key) {
|
||||||
|
slot.occupied = false
|
||||||
|
t.size--
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
func (t *table[K, V]) resize(capacity uint64) {
|
||||||
|
t.slots = make([]slot[K, V], capacity)
|
||||||
|
t.capacity = capacity
|
||||||
|
t.size = 0
|
||||||
|
}
|
||||||
|
|
||||||
|
func (t table[K, V]) update(key K, value V) (updated bool) {
|
||||||
|
if t.capacity == 0 {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// Put sets the value for a key. Returns error if its value cannot be set.
|
slot := &t.slots[t.location(key)]
|
||||||
func (t *Table[K, V]) Put(key K, value V) (err error) {
|
|
||||||
if t.tableA.update(key, value) {
|
if slot.occupied && t.compare(slot.key, key) {
|
||||||
return nil
|
slot.value = value
|
||||||
|
return true
|
||||||
}
|
}
|
||||||
|
|
||||||
if t.tableB.update(key, value) {
|
return false
|
||||||
return nil
|
|
||||||
}
|
}
|
||||||
|
|
||||||
entry, eviction := entry[K, V]{key, value}, false
|
func (t *table[K, V]) evict(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
|
||||||
for range t.maxEvictions() {
|
if t.capacity == 0 {
|
||||||
if entry, eviction = t.tableA.evict(entry); !eviction {
|
return insertion, true
|
||||||
return nil
|
|
||||||
}
|
}
|
||||||
|
|
||||||
if entry, eviction = t.tableB.evict(entry); !eviction {
|
slot := &t.slots[t.location(insertion.key)]
|
||||||
return nil
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if t.load() < t.minLoadFactor {
|
if !slot.occupied {
|
||||||
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
|
slot.entry = insertion
|
||||||
}
|
slot.occupied = true
|
||||||
|
t.size++
|
||||||
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
|
return
|
||||||
}
|
}
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, slot := range t.tableB.slots {
|
if t.compare(slot.key, insertion.key) {
|
||||||
if slot.occupied {
|
slot.value = insertion.value
|
||||||
if !yield(slot.key, slot.value) {
|
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
}
|
|
||||||
}
|
insertion, slot.entry = slot.entry, insertion
|
||||||
}
|
return insertion, true
|
||||||
}
|
}
|
||||||
|
|
||||||
// String returns the entries of the table as a string in the format:
|
func newTable[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) table[K, V] {
|
||||||
// "table[k1:v1 k2:v2 ...]".
|
return table[K, V]{
|
||||||
func (t *Table[K, V]) String() string {
|
hash: hash,
|
||||||
var sb strings.Builder
|
capacity: capacity,
|
||||||
sb.WriteString("table[")
|
compare: compare,
|
||||||
|
size: 0,
|
||||||
first := true
|
slots: make([]slot[K, V], capacity),
|
||||||
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...)
|
|
||||||
}
|
|
||||||
|
|||||||
Reference in New Issue
Block a user