4 Commits

Author SHA1 Message Date
521b38c550 ci: issue templates, issue config
Some checks failed
CI / Check PR Title (pull_request) Failing after 15s
CI / Go Lint (pull_request) Successful in 31s
CI / Markdown Lint (pull_request) Successful in 17s
CI / Makefile Lint (pull_request) Successful in 31s
CI / Unit Tests (pull_request) Successful in 29s
CI / Fuzz Tests (pull_request) Successful in 1m0s
CI / Mutation Tests (pull_request) Successful in 1m4s
2026-03-29 22:19:46 +02:00
cbe4483326 revert: release.yml
- It is not needed, because this is a library. We are not shipping a binary.
2026-03-29 22:00:54 +02:00
3bb663dc8b ci: release workflow with 'go-releaser' 2026-03-29 21:49:59 +02:00
db2dfb466b ci: add 'check-pr-title' job to pipeline 2026-03-29 21:47:11 +02:00
17 changed files with 243 additions and 249 deletions

View File

@@ -7,20 +7,20 @@ body:
id: context id: context
attributes: attributes:
label: Context label: Context
placeholder: What circumstances led to the bug? description: What circumstances led to the bug?
validations: validations:
required: true required: true
- type: textarea - type: textarea
id: expected-behavior id: expected-behavior
attributes: attributes:
label: Expected Behavior label: Expected Behavior
placeholder: What did you expect would happen? description: What did you expect would happen?
validations: validations:
required: true required: true
- type: textarea - type: textarea
id: actual-behavior id: actual-behavior
attributes: attributes:
label: Actual Behavior label: Actual Behavior
placeholder: What happened, and why was it unexpected? description: What happened, and why was it unexpected?
validations: validations:
required: true required: true

View File

@@ -6,10 +6,18 @@ name: ✨ Feature Request
about: Suggest an idea for this project about: Suggest an idea for this project
title: "[FEATURE]: " title: "[FEATURE]: "
body: body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this feature request! 🤗
Please make sure this feature request hasn't been already submitted by
someone by looking through other open/closed issues. 😃
- type: dropdown - type: dropdown
attributes: attributes:
multiple: false multiple: false
label: Feature Type label: Type of Feature
description: Select the type of feature request.
options: options:
- "✨ New Feature" - "✨ New Feature"
- "📝 Documentation" - "📝 Documentation"
@@ -23,7 +31,7 @@ body:
id: description id: description
attributes: attributes:
label: Description label: Description
placeholder: | description: |
Give us a brief description of the feature or enhancement you would Give us a brief description of the feature or enhancement you would
like! like!
validations: validations:
@@ -32,6 +40,6 @@ body:
id: additional-information id: additional-information
attributes: attributes:
label: Additional Information label: Additional Information
placeholder: | description: |
Give us some additional information on the feature request like proposed Give us some additional information on the feature request like proposed
solutions, links, screenshots, etc. solutions, links, screenshots, etc.

View File

@@ -1,2 +1,2 @@
# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-config.json # yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-config.json
blank_issues_enabled: false blank_issues_enabled: true

View File

@@ -1,17 +0,0 @@
---
name: "New Pull Request"
about: "Standard PR template"
title: ""
ref: "main"
---
## Description
## Changes
### Design Decisions
## Checklist
- [ ] Tests pass
- [ ] Docs updated

View File

@@ -9,12 +9,10 @@ jobs:
check-pr-title: check-pr-title:
name: Check PR Title name: Check PR Title
runs-on: ubuntu-latest runs-on: ubuntu-latest
if: github.event_name == 'pull_request'
env:
TITLE: ${{ gitea.event.pull_request.title }}
steps: steps:
- run: | - run: |
if ! echo "$TITLE" | grep -qE '^(WIP: )?(feat|fix|docs|chore|ci|test|refactor|perf|build|style|revert)(\(.+\))?(!)?: .+'; then TITLE="${{ gitea.event.pull_request.title }}"
if ! echo "$TITLE" | grep -qE '^(feat|fix|docs|chore|ci|test|refactor|perf|build|style|revert)(\(.+\))?(!)?: .+'; then
echo "::error::Pull Request title must follow conventional commits" echo "::error::Pull Request title must follow conventional commits"
exit 1 exit 1
fi fi

View File

@@ -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:

103
bucket.go Normal file
View File

@@ -0,0 +1,103 @@
package cuckoo
type entry[K, V any] struct {
key K
value V
}
type slot[K, V any] struct {
entry[K, V]
occupied bool
}
type bucket[K, V any] struct {
hash Hash[K]
slots []slot[K, V]
capacity, size uint64
compare EqualFunc[K]
}
// location determines where in the bucket a certain key would be placed. If the
// capacity is 0, this will panic.
func (b bucket[K, V]) location(key K) uint64 {
return b.hash(key) % b.capacity
}
func (b bucket[K, V]) get(key K) (value V, found bool) {
if b.capacity == 0 {
return
}
slot := b.slots[b.location(key)]
return slot.value, slot.occupied && b.compare(slot.key, key)
}
func (b *bucket[K, V]) drop(key K) (occupied bool) {
if b.capacity == 0 {
return
}
slot := &b.slots[b.location(key)]
if slot.occupied && b.compare(slot.key, key) {
slot.occupied = false
b.size--
return true
}
return false
}
func (b *bucket[K, V]) resize(capacity uint64) {
b.slots = make([]slot[K, V], capacity)
b.capacity = capacity
b.size = 0
}
func (b bucket[K, V]) update(key K, value V) (updated bool) {
if b.capacity == 0 {
return
}
slot := &b.slots[b.location(key)]
if slot.occupied && b.compare(slot.key, key) {
slot.value = value
return true
}
return false
}
func (b *bucket[K, V]) evict(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
if b.capacity == 0 {
return insertion, true
}
slot := &b.slots[b.location(insertion.key)]
if !slot.occupied {
slot.entry = insertion
slot.occupied = true
b.size++
return
}
if b.compare(slot.key, insertion.key) {
slot.value = insertion.value
return
}
insertion, slot.entry = slot.entry, insertion
return insertion, true
}
func newBucket[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) bucket[K, V] {
return bucket[K, V]{
hash: hash,
capacity: capacity,
compare: compare,
size: 0,
slots: make([]slot[K, V], capacity),
}
}

View File

@@ -2,7 +2,7 @@ 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 [Table]. A good EqualFunc is pure,
// deterministic, and fast. By default, [New] uses [DefaultEqualFunc]. // deterministic, and fast. By default, [NewTable] 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 [Table] will not work.

View File

@@ -28,7 +28,7 @@ func ExampleEqualFunc_badEqualFunc() {
// Two users with the same ID are equal. // Two users with the same ID are equal.
isEqual := func(a, b User) bool { return a.ID == b.ID } isEqual := func(a, b User) bool { return a.ID == b.ID }
userbase := cuckoo.NewCustom[User, bool](makeHash(1), makeHash(2), isEqual) userbase := cuckoo.NewCustomTable[User, bool](makeHash(1), makeHash(2), isEqual)
(userbase.Put(User{"1", "Robert Doe"}, true)) (userbase.Put(User{"1", "Robert Doe"}, true))

View File

@@ -3,6 +3,7 @@ package cuckoo_test
import ( import (
"fmt" "fmt"
"maps" "maps"
"math"
"os" "os"
"testing" "testing"
@@ -29,6 +30,7 @@ type fuzzStep struct {
type fuzzScenario struct { type fuzzScenario struct {
seedA, seedB uint32 seedA, seedB uint32
capacity, growthFactor uint8 capacity, growthFactor uint8
load float64
steps []fuzzStep steps []fuzzStep
} }
@@ -46,6 +48,7 @@ func FuzzInsertLookup(f *testing.F) {
seedA, seedB := scenario.seedA, scenario.seedB seedA, seedB := scenario.seedA, scenario.seedB
growthFactor := max(2, int(scenario.growthFactor)) growthFactor := max(2, int(scenario.growthFactor))
capacity := int(scenario.capacity) capacity := int(scenario.capacity)
minimumLoad := math.Abs(math.Mod(scenario.load, 1.0))
// If they are the same number, the hashes will clash, always causing an // If they are the same number, the hashes will clash, always causing an
// error. // error.
@@ -53,15 +56,22 @@ func FuzzInsertLookup(f *testing.F) {
t.Skip() t.Skip()
} }
fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d\n", // If the load is too high, the hashs will not be able to allocate
seedA, seedB, capacity, growthFactor) // properly.
if minimumLoad > 0.20 {
t.Skip()
}
actual := cuckoo.NewCustom[uint32, uint32]( fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d minimumLoad=%f\n",
seedA, seedB, capacity, growthFactor, minimumLoad)
actual := cuckoo.NewCustomTable[uint32, uint32](
offsetHash(seedA), offsetHash(seedA),
offsetHash(seedB), offsetHash(seedB),
func(a, b uint32) bool { return a == b }, func(a, b uint32) bool { return a == b },
cuckoo.Capacity(capacity), cuckoo.Capacity(capacity),
cuckoo.GrowthFactor(growthFactor), cuckoo.GrowthFactor(growthFactor),
cuckoo.MinimumLoad(minimumLoad),
) )
expected := map[uint32]uint32{} expected := map[uint32]uint32{}
@@ -73,16 +83,16 @@ 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)
} }

View File

@@ -11,7 +11,7 @@ func TestMaxEvictions(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
for i := 16; i < 116; i++ { for i := 16; i < 116; i++ {
table := New[int, bool](Capacity(i / 2)) table := NewTable[int, bool](Capacity(i / 2))
expectedEvictions := 3 * math.Floor(math.Log2(float64(i))) expectedEvictions := 3 * math.Floor(math.Log2(float64(i)))
assert.Equal(table.maxEvictions(), int(expectedEvictions)) assert.Equal(table.maxEvictions(), int(expectedEvictions))
@@ -20,7 +20,7 @@ func TestMaxEvictions(t *testing.T) {
func TestLoad(t *testing.T) { func TestLoad(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := New[int, bool](Capacity(8)) table := NewTable[int, bool](Capacity(8))
for i := range 16 { for i := range 16 {
err := table.Put(i, true) err := table.Put(i, true)

View File

@@ -14,7 +14,7 @@ import (
func TestNewTable(t *testing.T) { func TestNewTable(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.New[int, bool]() table := cuckoo.NewTable[int, bool]()
assert.NotNil(table) assert.NotNil(table)
assert.Zero(table.Size()) assert.Zero(table.Size())
@@ -23,7 +23,7 @@ func TestNewTable(t *testing.T) {
func TestAddItem(t *testing.T) { func TestAddItem(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key, value := 0, true key, value := 0, true
table := cuckoo.New[int, bool]() table := cuckoo.NewTable[int, bool]()
err := table.Put(key, value) err := table.Put(key, value)
@@ -35,7 +35,7 @@ func TestAddItem(t *testing.T) {
func TestPutOverwrite(t *testing.T) { func TestPutOverwrite(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key, value, newValue := 0, 1, 2 key, value, newValue := 0, 1, 2
table := cuckoo.New[int, int]() table := cuckoo.NewTable[int, int]()
(table.Put(key, value)) (table.Put(key, value))
err := table.Put(key, newValue) err := table.Put(key, newValue)
@@ -50,7 +50,7 @@ func TestPutOverwrite(t *testing.T) {
func TestSameHash(t *testing.T) { func TestSameHash(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
hash := func(int) uint64 { return 0 } hash := func(int) uint64 { return 0 }
table := cuckoo.NewCustom[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int]) table := cuckoo.NewCustomTable[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int])
errA := table.Put(0, true) errA := table.Put(0, true)
errB := table.Put(1, true) errB := table.Put(1, true)
@@ -63,14 +63,14 @@ func TestSameHash(t *testing.T) {
func TestStartingCapacity(t *testing.T) { func TestStartingCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.New[int, bool](cuckoo.Capacity(64)) table := cuckoo.NewTable[int, bool](cuckoo.Capacity(64))
assert.Equal(uint64(128), table.TotalCapacity()) assert.Equal(uint64(128), table.TotalCapacity())
} }
func TestResizeCapacity(t *testing.T) { func TestResizeCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.New[int, bool]( table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(8), cuckoo.Capacity(8),
cuckoo.GrowthFactor(2), cuckoo.GrowthFactor(2),
) )
@@ -85,7 +85,7 @@ func TestResizeCapacity(t *testing.T) {
func TestPutMany(t *testing.T) { func TestPutMany(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
expected, actual := map[int]bool{}, cuckoo.New[int, bool]() expected, actual := map[int]bool{}, cuckoo.NewTable[int, bool]()
for i := range 1_000 { for i := range 1_000 {
expected[i] = true expected[i] = true
@@ -100,7 +100,7 @@ func TestPutMany(t *testing.T) {
func TestGetMany(t *testing.T) { func TestGetMany(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.New[int, bool]() table := cuckoo.NewTable[int, bool]()
for i := range 1_000 { for i := range 1_000 {
err := table.Put(i, true) err := table.Put(i, true)
@@ -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)
} }
} }
} }
@@ -121,7 +121,7 @@ func TestGetMany(t *testing.T) {
func TestDropExistingItem(t *testing.T) { func TestDropExistingItem(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key, value := 0, true key, value := 0, true
table := cuckoo.New[int, bool]() table := cuckoo.NewTable[int, bool]()
(table.Put(key, value)) (table.Put(key, value))
err := table.Drop(key) err := table.Drop(key)
@@ -134,7 +134,7 @@ func TestDropExistingItem(t *testing.T) {
func TestDropNoItem(t *testing.T) { func TestDropNoItem(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key := 0 key := 0
table := cuckoo.New[int, bool]() table := cuckoo.NewTable[int, bool]()
err := table.Drop(key) err := table.Drop(key)
@@ -146,7 +146,7 @@ func TestDropNoItem(t *testing.T) {
func TestDropItemCapacity(t *testing.T) { func TestDropItemCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key := 0 key := 0
table := cuckoo.New[int, bool]( table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(64), cuckoo.Capacity(64),
cuckoo.GrowthFactor(2), cuckoo.GrowthFactor(2),
) )
@@ -164,7 +164,7 @@ func TestDropItemCapacity(t *testing.T) {
func TestPutNoCapacity(t *testing.T) { func TestPutNoCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
key, value := 0, true key, value := 0, true
table := cuckoo.New[int, bool]( table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(0), cuckoo.Capacity(0),
) )
@@ -177,7 +177,7 @@ func TestPutNoCapacity(t *testing.T) {
func TestBadHashCapacity(t *testing.T) { func TestBadHashCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.NewCustom[int, bool]( table := cuckoo.NewCustomTable[int, bool](
func(int) uint64 { return 0 }, func(int) uint64 { return 0 },
func(int) uint64 { return 0 }, func(int) uint64 { return 0 },
func(a, b int) bool { return a == b }, func(a, b int) bool { return a == b },
@@ -197,7 +197,7 @@ func TestBadHashCapacity(t *testing.T) {
func TestDropResizeCapacity(t *testing.T) { func TestDropResizeCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.New[int, bool]( table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(10), cuckoo.Capacity(10),
) )
@@ -217,7 +217,9 @@ func TestNewTableBy(t *testing.T) {
} }
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.NewBy[User, bool](func(u User) string { return u.id }) table := cuckoo.NewTableBy[User, bool](
func(u User) string { return u.id },
)
err := table.Put(User{nil, "1", "Robert"}, true) err := table.Put(User{nil, "1", "Robert"}, true)

4
doc.go
View File

@@ -1,8 +1,8 @@
// Package cuckoo provides a hash table that uses cuckoo hashing to achieve // Package cuckoo provides a hash table that uses cuckoo hashing to achieve
// a worst-case O(1) lookup time. // a worst-case O(1) lookup time.
// //
// While a [New] only supports comparable keys by default, you can create // While a [NewTable] only supports comparable keys by default, you can create
// a table with any key type using [NewCustom]. Custom [Hash] functions and // a table with any key type using [NewCustomTable]. Custom [Hash] functions and
// key comparison are also supported. // key comparison are also supported.
// //
// See more: https://en.wikipedia.org/wiki/Cuckoo_hashing // See more: https://en.wikipedia.org/wiki/Cuckoo_hashing

View File

@@ -8,25 +8,25 @@ import (
) )
func Example_basic() { func Example_basic() {
table := cuckoo.New[int, string]() table := cuckoo.NewTable[int, string]()
if err := table.Put(1, "Hello, World!"); err != nil { if err := table.Put(1, "Hello, World!"); err != nil {
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
} }

View File

@@ -9,15 +9,14 @@ import "fmt"
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 [Table]. Most
// implementations use 2. // hash table 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 [Table].
// The higher the minimum load, the more likely that a [Table.Put] will not // 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
const defaultMinimumLoad float64 = 0.05 const DefaultMinimumLoad float64 = 0.05
type settings struct { type settings struct {
growthFactor uint64 growthFactor uint64
@@ -26,10 +25,10 @@ type settings struct {
} }
// An Option modifies the settings of a [Table]. It is used in its constructors // An Option modifies the settings of a [Table]. It is used in its constructors
// like [New], for example. // like [NewTable], 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 bucket of the [Table]. 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 {
@@ -39,6 +38,19 @@ func Capacity(value int) Option {
return func(s *settings) { s.bucketSize = uint64(value) } return func(s *settings) { s.bucketSize = uint64(value) }
} }
// MinimumLoad modifies the [DefaultMinimumLoad] of the [Table]. The value must
// be between 0.00 and 1.00.
//
// The higher the minimum load, the more likely that a [Table.Put] will not
// succeed. Minimum loads above 20% are not tested.
func MinimumLoad(value float64) Option {
if value < 0.00 || value > 1.00 {
panic(fmt.Sprintf("go-cuckoo: MinimumLoad must be between 0.00 and 1.00, got %f", value))
}
return func(s *settings) { s.minLoadFactor = value }
}
// GrowthFactor controls how much the capacity of the [Table] multiplies when // GrowthFactor controls how much the capacity of the [Table] 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 {

View File

@@ -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),
}
}

120
table.go
View File

@@ -1,50 +1,41 @@
package cuckoo package cuckoo
import ( import (
"errors"
"fmt" "fmt"
"iter" "iter"
"math/bits" "math/bits"
"strings" "strings"
) )
// ErrBadHash occurs when the hashes given to a [Table] cause too many key // A Table is hash table that uses cuckoo hashing to resolve collision. Create
// collisions. Try rebuilding the table using: // one with [NewTable]. Or if you want more granularity, use [NewTableBy] or
// // [NewCustomTable].
// 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 { type Table[K, V any] struct {
tableA, tableB subtable[K, V] bucketA, bucketB bucket[K, V]
growthFactor uint64 growthFactor uint64
minLoadFactor float64 minLoadFactor float64
} }
// TotalCapacity returns the number of slots allocated for the [Table]. To get the // TotalCapacity returns the number of slots allocated for the [Table]. To get the
// number of slots filled, look at [Table.Size]. // number of slots filled, look at [Table.Size].
func (t *Table[K, V]) TotalCapacity() uint64 { func (t Table[K, V]) TotalCapacity() uint64 {
return t.tableA.capacity + t.tableB.capacity return t.bucketA.capacity + t.bucketB.capacity
} }
// Size returns how many slots are filled in the [Table]. // Size returns how many slots are filled in the [Table].
func (t *Table[K, V]) Size() int { func (t Table[K, V]) Size() int {
return int(t.tableA.size + t.tableB.size) return int(t.bucketA.size + t.bucketB.size)
} }
func log2(n uint64) (m int) { func log2(n uint64) (m int) {
return max(0, bits.Len64(n)-1) 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()) 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%. // When there are no slots in the table, we still treat the load as 100%.
// Every slot in the table is full. // Every slot in the table is full.
if t.TotalCapacity() == 0 { if t.TotalCapacity() == 0 {
@@ -54,7 +45,7 @@ func (t *Table[K, V]) load() float64 {
return float64(t.Size()) / float64(t.TotalCapacity()) return float64(t.Size()) / float64(t.TotalCapacity())
} }
// resize clears all tables, changes the sizes of them to a specific capacity, // resize clears all buckets, changes the sizes of them to a specific capacity,
// and fills them back up again. It is a helper function for [Table.grow] and // and fills them back up again. It is a helper function for [Table.grow] and
// [Table.shrink]; use them instead. // [Table.shrink]; use them instead.
func (t *Table[K, V]) resize(capacity uint64) error { func (t *Table[K, V]) resize(capacity uint64) error {
@@ -63,8 +54,8 @@ func (t *Table[K, V]) resize(capacity uint64) error {
entries = append(entries, entry[K, V]{k, v}) entries = append(entries, entry[K, V]{k, v})
} }
t.tableA.resize(capacity) t.bucketA.resize(capacity)
t.tableB.resize(capacity) t.bucketB.resize(capacity)
for _, entry := range entries { for _, entry := range entries {
if err := t.Put(entry.key, entry.value); err != nil { if err := t.Put(entry.key, entry.value); err != nil {
@@ -75,7 +66,7 @@ func (t *Table[K, V]) resize(capacity uint64) error {
return nil return nil
} }
// grow increases the table's capacity by the growth factor. If the // grow increases the table's capacity by the [Table.growthFactor]. If the
// capacity is 0, it increases it to 1. // capacity is 0, it increases it to 1.
func (t *Table[K, V]) grow() error { func (t *Table[K, V]) grow() error {
var newCapacity uint64 var newCapacity uint64
@@ -83,68 +74,61 @@ func (t *Table[K, V]) grow() error {
if t.TotalCapacity() == 0 { if t.TotalCapacity() == 0 {
newCapacity = 1 newCapacity = 1
} else { } else {
newCapacity = t.tableA.capacity * t.growthFactor newCapacity = t.bucketA.capacity * t.growthFactor
} }
return t.resize(newCapacity) return t.resize(newCapacity)
} }
// shrink reduces the table's capacity by the growth factor. It may // shrink reduces the table's capacity by the [Table.growthFactor]. It may
// reduce it down to 0. // reduce it down to 0.
func (t *Table[K, V]) shrink() error { func (t *Table[K, V]) shrink() error {
return t.resize(t.tableA.capacity / t.growthFactor) return t.resize(t.bucketA.capacity / t.growthFactor)
} }
// Get fetches the value for a key in the [Table]. Matches the comma-ok pattern // Get fetches the value for a key in the [Table]. Returns an error if no value
// of a builtin map; see [Table.Find] for plain indexing. // is found.
func (t *Table[K, V]) Get(key K) (value V, ok bool) { func (t Table[K, V]) Get(key K) (value V, err error) {
if item, ok := t.tableA.get(key); ok { if item, ok := t.bucketA.get(key); ok {
return item, true return item, nil
} }
if item, ok := t.tableB.get(key); ok { if item, ok := t.bucketB.get(key); ok {
return item, true return item, nil
} }
return return value, fmt.Errorf("key '%v' not found", key)
}
// 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. // Has returns true if a key has a value in the table.
func (t *Table[K, V]) Has(key K) (exists bool) { func (t Table[K, V]) Has(key K) (exists bool) {
_, exists = t.Get(key) _, err := t.Get(key)
return return err == nil
} }
// Put sets the value for a key. Returns error if its value cannot be set. // 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) { func (t *Table[K, V]) Put(key K, value V) (err error) {
if t.tableA.update(key, value) { if t.bucketA.update(key, value) {
return nil return nil
} }
if t.tableB.update(key, value) { if t.bucketB.update(key, value) {
return nil return nil
} }
entry, eviction := entry[K, V]{key, value}, false entry, eviction := entry[K, V]{key, value}, false
for range t.maxEvictions() { for range t.maxEvictions() {
if entry, eviction = t.tableA.evict(entry); !eviction { if entry, eviction = t.bucketA.evict(entry); !eviction {
return nil return nil
} }
if entry, eviction = t.tableB.evict(entry); !eviction { if entry, eviction = t.bucketB.evict(entry); !eviction {
return nil return nil
} }
} }
if t.load() < t.minLoadFactor { if t.load() < t.minLoadFactor {
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash) return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
} }
if err := t.grow(); err != nil { if err := t.grow(); err != nil {
@@ -157,8 +141,8 @@ 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 // Drop removes a value for a key in the table. Returns an error if its value
// cannot be removed. // cannot be removed.
func (t *Table[K, V]) Drop(key K) (err error) { func (t *Table[K, V]) Drop(key K) (err error) {
t.tableA.drop(key) t.bucketA.drop(key)
t.tableB.drop(key) t.bucketB.drop(key)
if t.load() < t.minLoadFactor { if t.load() < t.minLoadFactor {
return t.shrink() return t.shrink()
@@ -168,9 +152,9 @@ func (t *Table[K, V]) Drop(key K) (err error) {
} }
// Entries returns an unordered sequence of all key-value pairs in the table. // 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) { return func(yield func(K, V) bool) {
for _, slot := range t.tableA.slots { for _, slot := range t.bucketA.slots {
if slot.occupied { if slot.occupied {
if !yield(slot.key, slot.value) { if !yield(slot.key, slot.value) {
return return
@@ -178,7 +162,7 @@ func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
} }
} }
for _, slot := range t.tableB.slots { for _, slot := range t.bucketB.slots {
if slot.occupied { if slot.occupied {
if !yield(slot.key, slot.value) { if !yield(slot.key, slot.value) {
return return
@@ -189,8 +173,8 @@ func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
} }
// String returns the entries of the table as a string in the format: // String returns the entries of the table as a string in the format:
// "table[k1:v1 k2:v2 ...]". // "table[k1:v1 h2:v2 ...]".
func (t *Table[K, V]) String() string { func (t Table[K, V]) String() string {
var sb strings.Builder var sb strings.Builder
sb.WriteString("table[") sb.WriteString("table[")
@@ -208,13 +192,13 @@ func (t *Table[K, V]) String() string {
return sb.String() return sb.String()
} }
// NewCustom creates a [Table] with custom [Hash] and [EqualFunc] // NewCustomTable creates a [Table] with custom [Hash] and [EqualFunc]
// functions, along with any [Option] the user provides. // 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] { func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
settings := &settings{ settings := &settings{
growthFactor: DefaultGrowthFactor, growthFactor: DefaultGrowthFactor,
bucketSize: DefaultCapacity, bucketSize: DefaultCapacity,
minLoadFactor: defaultMinimumLoad, minLoadFactor: DefaultMinimumLoad,
} }
for _, option := range options { for _, option := range options {
@@ -224,8 +208,8 @@ func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...
return &Table[K, V]{ return &Table[K, V]{
growthFactor: settings.growthFactor, growthFactor: settings.growthFactor,
minLoadFactor: settings.minLoadFactor, minLoadFactor: settings.minLoadFactor,
tableA: newSubtable[K, V](settings.bucketSize, hashA, compare), bucketA: newBucket[K, V](settings.bucketSize, hashA, compare),
tableB: newSubtable[K, V](settings.bucketSize, hashB, compare), bucketB: newBucket[K, V](settings.bucketSize, hashB, compare),
} }
} }
@@ -233,10 +217,10 @@ 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)) } return func(x X) Z { return b(a(x)) }
} }
// NewBy creates a [Table] for any key type by using keyFunc to derive a // NewTableBy 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. // 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] { func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
return NewCustom[K, V]( return NewCustomTable[K, V](
pipe(keyFunc, NewDefaultHash[C]()), pipe(keyFunc, NewDefaultHash[C]()),
pipe(keyFunc, NewDefaultHash[C]()), pipe(keyFunc, NewDefaultHash[C]()),
func(a, b K) bool { return keyFunc(a) == keyFunc(b) }, func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
@@ -244,10 +228,10 @@ func NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[
) )
} }
// New creates a [Table] using the default [Hash] and [EqualFunc]. Use // NewTable creates a [Table] using the default [Hash] and [EqualFunc]. Use
// the [Option] functions to configure its behavior. Note that this constructor // the [Option] functions to configure its behavior. Note that this constructor
// is only provided for comparable keys. For arbitrary keys, consider // is only provided for comparable keys. For arbitrary keys, consider
// [NewBy] or [NewCustom]. // [NewTableBy] or [NewCustomTable].
func New[K comparable, V any](options ...Option) *Table[K, V] { func NewTable[K comparable, V any](options ...Option) *Table[K, V] {
return NewCustom[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...) return NewCustomTable[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
} }