4 Commits

Author SHA1 Message Date
a815b49b66 docs: information about recommended minimum load
All checks were successful
CI / Makefile Lint (pull_request) Successful in 30s
CI / Markdown Lint (pull_request) Successful in 13s
CI / Go Lint (pull_request) Successful in 40s
CI / Unit Tests (pull_request) Successful in 27s
CI / Fuzz Tests (pull_request) Successful in 59s
CI / Mutation Tests (pull_request) Successful in 58s
2026-03-24 20:59:04 -04:00
b499fa9c05 fix: reduce minimum load in tests to <20% 2026-03-24 20:26:20 -04:00
9e936ebadb fix: prevent users from settings a growthfactor=1
- This always causes errors, it should not be possible.
2026-03-21 13:13:51 -04:00
d07f76207b feat: add options to fuzz testing
- Added the options to `fuzzScenario`.
- They are clamped to non-panic values, so it only tests viable combinations.
2026-03-21 13:07:11 -04:00
19 changed files with 298 additions and 410 deletions

7
.claude/settings.json Normal file
View File

@@ -0,0 +1,7 @@
{
"permissions": {
"allow": [
"Bash(curl -s -w \"\\\\n---HTTP_STATUS:%{http_code}---\" https://raw.githubusercontent.com/kubernetes/kubernetes/master/.markdownlint.yaml)"
]
}
}

View File

@@ -1,26 +0,0 @@
# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-forms.json
name: 🐛 Bug Report
about: Report a bug in this project
title: "[BUG]: "
body:
- type: textarea
id: context
attributes:
label: Context
placeholder: What circumstances led to the bug?
validations:
required: true
- type: textarea
id: expected-behavior
attributes:
label: Expected Behavior
placeholder: What did you expect would happen?
validations:
required: true
- type: textarea
id: actual-behavior
attributes:
label: Actual Behavior
placeholder: What happened, and why was it unexpected?
validations:
required: true

View File

@@ -1,37 +0,0 @@
# 'Feature Request Template' By @cheehwatang
# https://github.com/cheehwatang/.github/blob/master/.github/ISSUE_TEMPLATE/feature_request.yml
#
# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-forms.json
name: ✨ Feature Request
about: Suggest an idea for this project
title: "[FEATURE]: "
body:
- type: dropdown
attributes:
multiple: false
label: Feature Type
options:
- "✨ New Feature"
- "📝 Documentation"
- "🎨 Style and UI"
- "🔨 Code Refactor"
- "⚡ Performance Improvements"
- "✅ New Test"
validations:
required: true
- type: textarea
id: description
attributes:
label: Description
placeholder: |
Give us a brief description of the feature or enhancement you would
like!
validations:
required: true
- type: textarea
id: additional-information
attributes:
label: Additional Information
placeholder: |
Give us some additional information on the feature request like proposed
solutions, links, screenshots, etc.

View File

@@ -1,2 +0,0 @@
# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-config.json
blank_issues_enabled: false

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

@@ -6,19 +6,6 @@ on:
pull_request:
jobs:
check-pr-title:
name: Check PR Title
runs-on: ubuntu-latest
if: github.event_name == 'pull_request'
env:
TITLE: ${{ gitea.event.pull_request.title }}
steps:
- run: |
if ! echo "$TITLE" | grep -qE '^(WIP: )?(feat|fix|docs|chore|ci|test|refactor|perf|build|style|revert)(\(.+\))?(!)?: .+'; then
echo "::error::Pull Request title must follow conventional commits"
exit 1
fi
lint-go:
name: Go Lint
runs-on: ubuntu-latest

1
.gitignore vendored
View File

@@ -24,3 +24,4 @@ go.work.sum
# env file
.env

View File

@@ -114,9 +114,6 @@ linters:
# Reports uses of functions with replacement inside the testing package.
- usetesting
# Reports mixed receiver types in structs/interfaces.
- recvcheck
settings:
revive:
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'
// 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
// are different: the [Table] will not work.

View File

@@ -28,7 +28,7 @@ func ExampleEqualFunc_badEqualFunc() {
// Two users with the same ID are equal.
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))

View File

@@ -3,6 +3,7 @@ package cuckoo_test
import (
"fmt"
"maps"
"math"
"os"
"testing"
@@ -29,6 +30,7 @@ type fuzzStep struct {
type fuzzScenario struct {
seedA, seedB uint32
capacity, growthFactor uint8
load float64
steps []fuzzStep
}
@@ -46,6 +48,7 @@ func FuzzInsertLookup(f *testing.F) {
seedA, seedB := scenario.seedA, scenario.seedB
growthFactor := max(2, int(scenario.growthFactor))
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
// error.
@@ -53,37 +56,43 @@ func FuzzInsertLookup(f *testing.F) {
t.Skip()
}
fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d\n",
seedA, seedB, capacity, growthFactor)
// If the load is too high, the hashs will not be able to allocate
// 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(seedB),
func(a, b uint32) bool { return a == b },
cuckoo.Capacity(capacity),
cuckoo.GrowthFactor(growthFactor),
cuckoo.MinimumLoad(minimumLoad),
)
expected := map[uint32]uint32{}
for _, step := range scenario.steps {
if step.drop {
ok := actual.Drop(step.key)
_, has := expected[step.key]
assert.Equal(ok, has)
err := actual.Drop(step.key)
assert.NoError(err)
delete(expected, step.key)
_, ok = actual.Get(step.key)
assert.False(ok)
_, err = actual.Get(step.key)
assert.Error(err)
} else {
err := actual.Put(step.key, step.value)
assert.NoError(err)
expected[step.key] = step.value
found, ok := actual.Get(step.key)
assert.True(ok)
found, err := actual.Get(step.key)
assert.NoError(err)
assert.Equal(step.value, found)
}

View File

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

View File

@@ -14,7 +14,7 @@ import (
func TestNewTable(t *testing.T) {
assert := assert.New(t)
table := cuckoo.New[int, bool]()
table := cuckoo.NewTable[int, bool]()
assert.NotNil(table)
assert.Zero(table.Size())
@@ -23,7 +23,7 @@ func TestNewTable(t *testing.T) {
func TestAddItem(t *testing.T) {
assert := assert.New(t)
key, value := 0, true
table := cuckoo.New[int, bool]()
table := cuckoo.NewTable[int, bool]()
err := table.Put(key, value)
@@ -35,7 +35,7 @@ func TestAddItem(t *testing.T) {
func TestPutOverwrite(t *testing.T) {
assert := assert.New(t)
key, value, newValue := 0, 1, 2
table := cuckoo.New[int, int]()
table := cuckoo.NewTable[int, int]()
(table.Put(key, value))
err := table.Put(key, newValue)
@@ -50,7 +50,7 @@ func TestPutOverwrite(t *testing.T) {
func TestSameHash(t *testing.T) {
assert := assert.New(t)
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)
errB := table.Put(1, true)
@@ -63,14 +63,14 @@ func TestSameHash(t *testing.T) {
func TestStartingCapacity(t *testing.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())
}
func TestResizeCapacity(t *testing.T) {
assert := assert.New(t)
table := cuckoo.New[int, bool](
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(8),
cuckoo.GrowthFactor(2),
)
@@ -85,7 +85,7 @@ func TestResizeCapacity(t *testing.T) {
func TestPutMany(t *testing.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 {
expected[i] = true
@@ -100,7 +100,7 @@ func TestPutMany(t *testing.T) {
func TestGetMany(t *testing.T) {
assert := assert.New(t)
table := cuckoo.New[int, bool]()
table := cuckoo.NewTable[int, bool]()
for i := range 1_000 {
err := table.Put(i, true)
@@ -108,25 +108,37 @@ func TestGetMany(t *testing.T) {
}
for i := range 2_000 {
value, ok := table.Get(i)
value, err := table.Get(i)
if i < 1_000 {
assert.True(ok)
assert.NoError(err)
assert.Equal(value, true)
} else {
assert.False(ok)
assert.Error(err)
}
}
}
func TestRemove(t *testing.T) {
assert := assert.New(t)
table := cuckoo.NewTable[int, bool]()
assert.False(table.Has(0))
err := table.Put(0, true)
assert.NoError(err)
assert.True(table.Has(0))
}
func TestDropExistingItem(t *testing.T) {
assert := assert.New(t)
key, value := 0, true
table := cuckoo.New[int, bool]()
table := cuckoo.NewTable[int, bool]()
(table.Put(key, value))
had := table.Drop(key)
err := table.Drop(key)
assert.True(had)
assert.NoError(err)
assert.Equal(0, table.Size())
assert.False(table.Has(key))
}
@@ -134,11 +146,11 @@ func TestDropExistingItem(t *testing.T) {
func TestDropNoItem(t *testing.T) {
assert := assert.New(t)
key := 0
table := cuckoo.New[int, bool]()
table := cuckoo.NewTable[int, bool]()
had := table.Drop(key)
err := table.Drop(key)
assert.False(had)
assert.NoError(err)
assert.Equal(0, table.Size())
assert.False(table.Has(key))
}
@@ -146,15 +158,16 @@ func TestDropNoItem(t *testing.T) {
func TestDropItemCapacity(t *testing.T) {
assert := assert.New(t)
key := 0
table := cuckoo.New[int, bool](
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(64),
cuckoo.GrowthFactor(2),
)
startingCapacity := table.TotalCapacity()
table.Drop(key)
err := table.Drop(key)
endingCapacity := table.TotalCapacity()
assert.NoError(err)
assert.Equal(0, table.Size())
assert.Equal(uint64(128), startingCapacity)
assert.Equal(uint64(64), endingCapacity)
@@ -163,7 +176,7 @@ func TestDropItemCapacity(t *testing.T) {
func TestPutNoCapacity(t *testing.T) {
assert := assert.New(t)
key, value := 0, true
table := cuckoo.New[int, bool](
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(0),
)
@@ -176,7 +189,7 @@ func TestPutNoCapacity(t *testing.T) {
func TestBadHashCapacity(t *testing.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(a, b int) bool { return a == b },
@@ -196,15 +209,15 @@ func TestBadHashCapacity(t *testing.T) {
func TestDropResizeCapacity(t *testing.T) {
assert := assert.New(t)
table := cuckoo.New[int, bool](
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(10),
)
err1 := table.Put(0, true)
err2 := table.Put(1, true)
table.Drop(1)
err3 := table.Drop(1)
assert.NoError(errors.Join(err1, err2))
assert.NoError(errors.Join(err1, err2, err3))
assert.Equal(uint64(20), table.TotalCapacity())
}
@@ -216,7 +229,9 @@ func TestNewTableBy(t *testing.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)

7
doc.go
View File

@@ -1,12 +1,9 @@
// Package cuckoo provides a hash table that uses cuckoo hashing to achieve
// a worst-case O(1) lookup time.
//
// While a [New] only supports comparable keys by default, you can create
// a table with any key type using [NewCustom]. Custom [Hash] functions and
// While a [NewTable] only supports comparable keys by default, you can create
// a table with any key type using [NewCustomTable]. Custom [Hash] functions and
// key comparison are also supported.
//
// NOTE: The [Table] is a look-up structure, and not a source of truth. If
// [ErrBadHash] occurs, the data cannot be restored.
//
// See more: https://en.wikipedia.org/wiki/Cuckoo_hashing
package cuckoo

View File

@@ -8,25 +8,25 @@ import (
)
func Example_basic() {
table := cuckoo.New[int, string]()
table := cuckoo.NewTable[int, string]()
if err := table.Put(1, "Hello, World!"); err != nil {
fmt.Println("Put error:", err)
}
if item, ok := table.Get(1); !ok {
fmt.Println("Not Found 1!")
if item, err := table.Get(1); err != nil {
fmt.Println("Error:", err)
} else {
fmt.Println("Found 1:", item)
}
if item, ok := table.Get(0); !ok {
fmt.Println("Not Found 0!")
if item, err := table.Get(0); err != nil {
fmt.Println("Error:", err)
} else {
fmt.Println("Found 0:", item)
}
// Output:
// Found 1: Hello, World!
// Not Found 0!
// Error: key '0' not found
}

View File

@@ -9,20 +9,14 @@ import "fmt"
const DefaultCapacity uint64 = 16
// DefaultGrowthFactor is the standard resize multiplier for a [Table]. Most
// implementations use 2.
// hash table implementations use 2.
const DefaultGrowthFactor uint64 = 2
// defaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
// The higher the minimum load, the more likely that a [Table.Put] will not
// succeed. The value of 5% is taken from [libcuckoo].
// DefaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
// The value of 5% is taken from [libcuckoo].
//
// [libcuckoo]: https://github.com/efficient/libcuckoo/blob/656714705a055df2b7a605eb3c71586d9da1e119/libcuckoo/cuckoohash_config.hh#L21
const defaultMinimumLoad float64 = 0.05
// defaultGrowthLimit is the maximum number of times a [Table] can grow in a
// single [Table.Put], before the library infers it will lead to a stack
// overflow. The value of '64' was chosen arbirarily.
const defaultGrowthLimit uint64 = 64
const DefaultMinimumLoad float64 = 0.05
type settings struct {
growthFactor uint64
@@ -31,10 +25,10 @@ type settings struct {
}
// 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)
// 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.
func Capacity(value int) Option {
if value < 0 {
@@ -44,6 +38,19 @@ func Capacity(value int) Option {
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
// it must resize. The value must be greater than 1.
func GrowthFactor(value int) Option {

View File

@@ -1,107 +0,0 @@
package cuckoo
// An entry is a key-value pair.
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]) resized(capacity uint64) *subtable[K, V] {
return &subtable[K, V]{
slots: make([]slot[K, V], capacity),
capacity: capacity,
hash: t.hash,
compare: t.compare,
}
}
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]) insert(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),
}
}

226
table.go
View File

@@ -1,50 +1,41 @@
package cuckoo
import (
"errors"
"fmt"
"iter"
"math/bits"
"strings"
)
// ErrBadHash occurs when the hashes given to a [Table] cause too many key
// collisions. Discard the old table, rebuild it from your source data, and try:
//
// 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].
// 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].
type Table[K, V any] struct {
tableA, tableB *subtable[K, V]
bucketA, bucketB bucket[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
func (t Table[K, V]) TotalCapacity() uint64 {
return t.bucketA.capacity + t.bucketB.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 (t Table[K, V]) Size() int {
return int(t.bucketA.size + t.bucketB.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 {
@@ -54,153 +45,116 @@ func (t *Table[K, V]) load() float64 {
return float64(t.Size()) / float64(t.TotalCapacity())
}
// insert attempts to put/update an entry in the table, without modifying the
// size of the table. Returns a displaced entry and 'homeless = true' if an
// entry could not be placed after exhausting evictions.
func (t *Table[K, V]) insert(entry entry[K, V]) (displaced entry[K, V], homeless bool) {
if t.tableA.update(entry.key, entry.value) {
return
}
if t.tableB.update(entry.key, entry.value) {
return
}
for range t.maxEvictions() {
if entry, homeless = t.tableA.insert(entry); !homeless {
return
}
if entry, homeless = t.tableB.insert(entry); !homeless {
return
}
}
return entry, true
}
// resized creates an empty copy of the table, with a new capacity for each
// bucket.
func (t *Table[K, V]) resized(capacity uint64) *Table[K, V] {
return &Table[K, V]{
growthFactor: t.growthFactor,
minLoadFactor: t.minLoadFactor,
tableA: t.tableA.resized(capacity),
tableB: t.tableB.resized(capacity),
}
}
// resize creates a new [Table.resized] with 'capacity', inserts all items into
// the array, and replaces the current table. It is a helper function for
// [Table.grow] and [Table.shrink]; use them instead.
func (t *Table[K, V]) resize(capacity uint64) bool {
updated := t.resized(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
// [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() {
if _, failed := updated.insert(entry[K, V]{k, v}); failed {
return false
entries = append(entries, entry[K, V]{k, v})
}
t.bucketA.resize(capacity)
t.bucketB.resize(capacity)
for _, entry := range entries {
if err := t.Put(entry.key, entry.value); err != nil {
return err
}
}
*t = *updated
return true
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.
func (t *Table[K, V]) grow() bool {
func (t *Table[K, V]) grow() error {
var newCapacity uint64
if t.TotalCapacity() == 0 {
newCapacity = 1
} else {
newCapacity = t.tableA.capacity * t.growthFactor
newCapacity = t.bucketA.capacity * t.growthFactor
}
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.
func (t *Table[K, V]) shrink() bool {
return t.resize(t.tableA.capacity / t.growthFactor)
func (t *Table[K, V]) shrink() error {
return t.resize(t.bucketA.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
// Get fetches the value for a key in the [Table]. Returns an error if no value
// is found.
func (t Table[K, V]) Get(key K) (value V, err error) {
if item, ok := t.bucketA.get(key); ok {
return item, nil
}
if item, ok := t.tableB.get(key); ok {
return item, true
if item, ok := t.bucketB.get(key); ok {
return item, nil
}
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
return value, fmt.Errorf("key '%v' not found", key)
}
// 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
func (t Table[K, V]) Has(key K) (exists bool) {
_, err := t.Get(key)
return err == nil
}
// Put sets the value for a key. If it cannot be set, an error is returned.
// 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) {
var (
entry = entry[K, V]{key, value}
homeless bool
)
for range defaultGrowthLimit {
if entry, homeless = t.insert(entry); !homeless {
return
if t.bucketA.update(key, value) {
return nil
}
// Both this and the growth limit are necessary: this catches bad hashes
// early when the table is sparse, while the latter catches cases where
// growing never helps.
if t.load() < t.minLoadFactor {
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
if t.bucketB.update(key, value) {
return nil
}
// It is theoretically possible to have a table with a larger capacity
// that is valid. But this chance is astronomically small, so we ignore
// it in this implementation.
if grew := t.grow(); !grew {
return fmt.Errorf("could not redistribute entries into larger table: %w", ErrBadHash)
}
entry, eviction := entry[K, V]{key, value}, false
for range t.maxEvictions() {
if entry, eviction = t.bucketA.evict(entry); !eviction {
return nil
}
return fmt.Errorf("could not place entry after %d resizes: %w", defaultGrowthLimit, ErrBadHash)
if entry, eviction = t.bucketB.evict(entry); !eviction {
return nil
}
}
// Drop removes a value for a key in the table. Returns whether the key had
// existed.
func (t *Table[K, V]) Drop(key K) bool {
occupied := t.tableA.drop(key) || t.tableB.drop(key)
if t.load() < t.minLoadFactor {
// The error is not handled here, because table-shrinking is an internal
// optimization.
t.shrink()
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
}
return occupied
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.bucketA.drop(key)
t.bucketB.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] {
func (t Table[K, V]) Entries() iter.Seq2[K, V] {
return func(yield func(K, V) bool) {
for _, slot := range t.tableA.slots {
for _, slot := range t.bucketA.slots {
if slot.occupied {
if !yield(slot.key, slot.value) {
return
@@ -208,7 +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 !yield(slot.key, slot.value) {
return
@@ -219,8 +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:
// "table[k1:v1 k2:v2 ...]".
func (t *Table[K, V]) String() string {
// "table[k1:v1 h2:v2 ...]".
func (t Table[K, V]) String() string {
var sb strings.Builder
sb.WriteString("table[")
@@ -238,13 +192,13 @@ func (t *Table[K, V]) String() 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.
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{
growthFactor: DefaultGrowthFactor,
bucketSize: DefaultCapacity,
minLoadFactor: defaultMinimumLoad,
minLoadFactor: DefaultMinimumLoad,
}
for _, option := range options {
@@ -254,8 +208,8 @@ func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...
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),
bucketA: newBucket[K, V](settings.bucketSize, hashA, compare),
bucketB: newBucket[K, V](settings.bucketSize, hashB, compare),
}
}
@@ -263,10 +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)) }
}
// 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.
func NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
return NewCustom[K, V](
func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
return NewCustomTable[K, V](
pipe(keyFunc, NewDefaultHash[C]()),
pipe(keyFunc, NewDefaultHash[C]()),
func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
@@ -274,10 +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
// 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...)
// [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...)
}