refactor!: shorter constructors, bucket → subtable (#22)
All checks were successful
CI / Check PR Title (push) Has been skipped
CI / Makefile Lint (push) Successful in 47s
CI / Go Lint (push) Successful in 51s
CI / Markdown Lint (push) Successful in 46s
CI / Unit Tests (push) Successful in 47s
CI / Fuzz Tests (push) Successful in 1m19s
CI / Mutation Tests (push) Successful in 1m36s
All checks were successful
CI / Check PR Title (push) Has been skipped
CI / Makefile Lint (push) Successful in 47s
CI / Go Lint (push) Successful in 51s
CI / Markdown Lint (push) Successful in 46s
CI / Unit Tests (push) Successful in 47s
CI / Fuzz Tests (push) Successful in 1m19s
CI / Mutation Tests (push) Successful in 1m36s
## Description Currently, the name of `bucket` is a bit confusing, because it is considered a 'table' in literature (as well as the whole hash table). A `bucket` is better described as a 'subtable', which is used by the total hash table to perform cuckoo hashing. In addition, the constructors `NewTable`, `NewTableBy`, and `NewCustomTable` were given shorter names, because the package name `cuckoo` already implies that `New*` would create a hash table with cuckoo hashing. This package has one use-case, and so it unambiguous what constructors produce. ## Changes - `NewTable` -> `New` - `NewTableBy` -> `NewBy` - `NewCustomTable` -> `NewCustom` - `bucket` -> `subtable` ### Design Decisions - I would have renamed `Table` and `subtable` to map equivalents, but 'submap' implies that a certain subsection of the map is contained within it, which isn't quite right. - I chose not to go with `Map` and `table`, because of the split naming convention. ## Checklist - [x] Tests pass - [x] Docs updated Reviewed-on: #22 Co-authored-by: M.V. Hutz <git@maximhutz.me> Co-committed-by: M.V. Hutz <git@maximhutz.me>
This commit was merged in pull request #22.
This commit is contained in:
86
table.go
86
table.go
@@ -16,35 +16,35 @@ import (
|
||||
// 2. A different [Hash] algorithm.
|
||||
var ErrBadHash = errors.New("bad hash")
|
||||
|
||||
// A Table is hash table that uses cuckoo hashing to resolve collision. Create
|
||||
// one with [NewTable]. Or if you want more granularity, use [NewTableBy] or
|
||||
// [NewCustomTable].
|
||||
// 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 {
|
||||
bucketA, bucketB bucket[K, V]
|
||||
growthFactor uint64
|
||||
minLoadFactor float64
|
||||
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.bucketA.capacity + t.bucketB.capacity
|
||||
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.bucketA.size + t.bucketB.size)
|
||||
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 {
|
||||
func (t *Table[K, V]) maxEvictions() int {
|
||||
return 3 * log2(t.TotalCapacity())
|
||||
}
|
||||
|
||||
func (t Table[K, V]) load() float64 {
|
||||
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 {
|
||||
@@ -54,7 +54,7 @@ func (t Table[K, V]) load() float64 {
|
||||
return float64(t.Size()) / float64(t.TotalCapacity())
|
||||
}
|
||||
|
||||
// resize clears all buckets, changes the sizes of them to a specific capacity,
|
||||
// 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 {
|
||||
@@ -63,8 +63,8 @@ func (t *Table[K, V]) resize(capacity uint64) error {
|
||||
entries = append(entries, entry[K, V]{k, v})
|
||||
}
|
||||
|
||||
t.bucketA.resize(capacity)
|
||||
t.bucketB.resize(capacity)
|
||||
t.tableA.resize(capacity)
|
||||
t.tableB.resize(capacity)
|
||||
|
||||
for _, entry := range entries {
|
||||
if err := t.Put(entry.key, entry.value); err != nil {
|
||||
@@ -75,7 +75,7 @@ func (t *Table[K, V]) resize(capacity uint64) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// grow increases the table's capacity by the [Table.growthFactor]. If the
|
||||
// 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
|
||||
@@ -83,26 +83,26 @@ func (t *Table[K, V]) grow() error {
|
||||
if t.TotalCapacity() == 0 {
|
||||
newCapacity = 1
|
||||
} else {
|
||||
newCapacity = t.bucketA.capacity * t.growthFactor
|
||||
newCapacity = t.tableA.capacity * t.growthFactor
|
||||
}
|
||||
|
||||
return t.resize(newCapacity)
|
||||
}
|
||||
|
||||
// shrink reduces the table's capacity by the [Table.growthFactor]. It may
|
||||
// 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.bucketA.capacity / t.growthFactor)
|
||||
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.bucketA.get(key); ok {
|
||||
if item, ok := t.tableA.get(key); ok {
|
||||
return item, true
|
||||
}
|
||||
|
||||
if item, ok := t.bucketB.get(key); ok {
|
||||
if item, ok := t.tableB.get(key); ok {
|
||||
return item, true
|
||||
}
|
||||
|
||||
@@ -124,21 +124,21 @@ func (t Table[K, V]) Has(key K) (exists bool) {
|
||||
|
||||
// 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.bucketA.update(key, value) {
|
||||
if t.tableA.update(key, value) {
|
||||
return nil
|
||||
}
|
||||
|
||||
if t.bucketB.update(key, value) {
|
||||
if t.tableB.update(key, value) {
|
||||
return nil
|
||||
}
|
||||
|
||||
entry, eviction := entry[K, V]{key, value}, false
|
||||
for range t.maxEvictions() {
|
||||
if entry, eviction = t.bucketA.evict(entry); !eviction {
|
||||
if entry, eviction = t.tableA.evict(entry); !eviction {
|
||||
return nil
|
||||
}
|
||||
|
||||
if entry, eviction = t.bucketB.evict(entry); !eviction {
|
||||
if entry, eviction = t.tableB.evict(entry); !eviction {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
@@ -157,8 +157,8 @@ func (t *Table[K, V]) Put(key K, value V) (err error) {
|
||||
// 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.bucketA.drop(key)
|
||||
t.bucketB.drop(key)
|
||||
t.tableA.drop(key)
|
||||
t.tableB.drop(key)
|
||||
|
||||
if t.load() < t.minLoadFactor {
|
||||
return t.shrink()
|
||||
@@ -168,9 +168,9 @@ func (t *Table[K, V]) Drop(key K) (err error) {
|
||||
}
|
||||
|
||||
// Entries returns an unordered sequence of all key-value pairs in the table.
|
||||
func (t Table[K, V]) Entries() iter.Seq2[K, V] {
|
||||
func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
|
||||
return func(yield func(K, V) bool) {
|
||||
for _, slot := range t.bucketA.slots {
|
||||
for _, slot := range t.tableA.slots {
|
||||
if slot.occupied {
|
||||
if !yield(slot.key, slot.value) {
|
||||
return
|
||||
@@ -178,7 +178,7 @@ func (t Table[K, V]) Entries() iter.Seq2[K, V] {
|
||||
}
|
||||
}
|
||||
|
||||
for _, slot := range t.bucketB.slots {
|
||||
for _, slot := range t.tableB.slots {
|
||||
if slot.occupied {
|
||||
if !yield(slot.key, slot.value) {
|
||||
return
|
||||
@@ -189,8 +189,8 @@ func (t Table[K, V]) Entries() iter.Seq2[K, V] {
|
||||
}
|
||||
|
||||
// String returns the entries of the table as a string in the format:
|
||||
// "table[k1:v1 h2:v2 ...]".
|
||||
func (t Table[K, V]) String() string {
|
||||
// "table[k1:v1 k2:v2 ...]".
|
||||
func (t *Table[K, V]) String() string {
|
||||
var sb strings.Builder
|
||||
sb.WriteString("table[")
|
||||
|
||||
@@ -208,9 +208,9 @@ func (t Table[K, V]) String() string {
|
||||
return sb.String()
|
||||
}
|
||||
|
||||
// NewCustomTable creates a [Table] with custom [Hash] and [EqualFunc]
|
||||
// NewCustom creates a [Table] with custom [Hash] and [EqualFunc]
|
||||
// functions, along with any [Option] the user provides.
|
||||
func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
|
||||
func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
|
||||
settings := &settings{
|
||||
growthFactor: DefaultGrowthFactor,
|
||||
bucketSize: DefaultCapacity,
|
||||
@@ -224,8 +224,8 @@ func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], option
|
||||
return &Table[K, V]{
|
||||
growthFactor: settings.growthFactor,
|
||||
minLoadFactor: settings.minLoadFactor,
|
||||
bucketA: newBucket[K, V](settings.bucketSize, hashA, compare),
|
||||
bucketB: newBucket[K, V](settings.bucketSize, hashB, compare),
|
||||
tableA: newSubtable[K, V](settings.bucketSize, hashA, compare),
|
||||
tableB: newSubtable[K, V](settings.bucketSize, hashB, compare),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -233,10 +233,10 @@ 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)) }
|
||||
}
|
||||
|
||||
// NewTableBy creates a [Table] for any key type by using keyFunc to derive a
|
||||
// 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 NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
|
||||
return NewCustomTable[K, V](
|
||||
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) },
|
||||
@@ -244,10 +244,10 @@ func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *T
|
||||
)
|
||||
}
|
||||
|
||||
// NewTable creates a [Table] using the default [Hash] and [EqualFunc]. Use
|
||||
// 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
|
||||
// [NewTableBy] or [NewCustomTable].
|
||||
func NewTable[K comparable, V any](options ...Option) *Table[K, V] {
|
||||
return NewCustomTable[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
|
||||
// [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