2 Commits

Author SHA1 Message Date
931b53cb7c feat: add release ci job, add semantic verioning 2026-03-27 10:04:09 -04:00
12fb18858f feat: test pr/issue template 2026-03-25 07:43:41 -04:00
22 changed files with 481 additions and 467 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)"
]
}
}

71
.gitea/ISSUE_TEMPLATE.yml Normal file
View File

@@ -0,0 +1,71 @@
name: Bug Report
about: File a bug report
title: "[Bug]: "
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this bug report!
# some markdown that will only be visible once the issue has been created
- type: markdown
attributes:
value: |
This issue was created by an issue **template** :)
visible: [content]
- type: input
id: contact
attributes:
label: Contact Details
description: How can we get in touch with you if we need more info?
placeholder: ex. email@example.com
validations:
required: false
- type: textarea
id: what-happened
attributes:
label: What happened?
description: Also tell us, what did you expect to happen?
placeholder: Tell us what you see!
value: "A bug happened!"
validations:
required: true
- type: dropdown
id: version
attributes:
label: Version
description: What version of our software are you running?
options:
- 1.0.2 (Default)
- 1.0.3 (Edge)
validations:
required: true
- type: dropdown
id: browsers
attributes:
label: What browsers are you seeing the problem on?
multiple: true
options:
- Firefox
- Chrome
- Safari
- Microsoft Edge
- type: textarea
id: logs
attributes:
label: Relevant log output
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
render: shell
- type: checkboxes
id: terms
attributes:
label: Code of Conduct
hide_label: true
description: By submitting this issue, you agree to follow our [Code of Conduct](https://example.com)
options:
- label: I agree to follow this project's Code of Conduct
required: true
- label: I have also read the CONTRIBUTION.MD
required: true
visible: [form]
- label: This is a TODO only visible after issue creation
visible: [content]

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 +1,12 @@
--- ---
name: "New Pull Request" name: "Pull Request Template"
about: "Standard PR template" about: "This template is for general pull requests!"
title: "" title: "<type>[optional scope]: <description>"
ref: "main" ref: "main"
assignees: ["user1"]
labels:
- bug
- "help needed"
--- ---
## Description This is the template!
## Changes
### Design Decisions
## Checklist
- [ ] Tests pass
- [ ] Docs updated

View File

@@ -6,19 +6,6 @@ on:
pull_request: pull_request:
jobs: 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: lint-go:
name: Go Lint name: Go Lint
runs-on: ubuntu-latest runs-on: ubuntu-latest

View File

@@ -0,0 +1,22 @@
name: Release
on:
push:
branches: [main]
jobs:
release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: actions/setup-python@v5
with:
python-version: "3.12"
- run: pip install python-semantic-release
- run: semantic-release version --push --vcs-release
env:
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}

1
.gitignore vendored
View File

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

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

@@ -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 [HashTable]. 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 [HashTable] will not work. // are different: the [Table] 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

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

@@ -1,9 +1,7 @@
package cuckoo_test package cuckoo_test
import ( import (
"fmt"
"maps" "maps"
"os"
"testing" "testing"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
@@ -28,7 +26,6 @@ type fuzzStep struct {
type fuzzScenario struct { type fuzzScenario struct {
seedA, seedB uint32 seedA, seedB uint32
capacity, growthFactor uint8
steps []fuzzStep steps []fuzzStep
} }
@@ -43,25 +40,14 @@ func FuzzInsertLookup(f *testing.F) {
return return
} }
seedA, seedB := scenario.seedA, scenario.seedB if scenario.seedA == scenario.seedB {
growthFactor := max(2, int(scenario.growthFactor)) return
capacity := int(scenario.capacity)
// If they are the same number, the hashes will clash, always causing an
// error.
if seedA == seedB {
t.Skip()
} }
fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d\n", actual := cuckoo.NewCustomTable[uint32, uint32](
seedA, seedB, capacity, growthFactor) offsetHash(scenario.seedA),
offsetHash(scenario.seedB),
actual := cuckoo.NewCustom[uint32, uint32](
offsetHash(seedA),
offsetHash(seedB),
func(a, b uint32) bool { return a == b }, func(a, b uint32) bool { return a == b },
cuckoo.Capacity(capacity),
cuckoo.GrowthFactor(growthFactor),
) )
expected := map[uint32]uint32{} expected := map[uint32]uint32{}

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)
@@ -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

@@ -8,7 +8,7 @@ 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)

View File

@@ -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 [HashTable] to evenly distribute values // It is used by the [Table] 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. [HashTable] uses [NewDefaultHash] by default, which is built on // deterministic. [Table] 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

View File

@@ -1,237 +0,0 @@
package cuckoo
import (
"fmt"
"iter"
"math/bits"
"strings"
)
// 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("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
}
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...)
}

13
pyproject.toml Normal file
View File

@@ -0,0 +1,13 @@
#:schema https://json.schemastore.org/pyproject.json
[tool.semantic_release]
commit_parser = "angular"
version_toml = []
tag_format = "v{version}"
[tool.semantic_release.remote]
type = "gitea"
domain = "git.maximhutz.com"
[tool.semantic_release.remote.token]
env = "GITEA_TOKEN"

View File

@@ -1,23 +1,20 @@
package cuckoo package cuckoo
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 [HashTable]. 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 [HashTable]. // DefaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
// The higher the minimum load, the more likely that a [HashTable.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
@@ -25,26 +22,24 @@ type settings struct {
bucketSize uint64 bucketSize uint64
} }
// An Option modifies the settings of a [HashTable]. 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 table of the [HashTable]. The // Capacity modifies the starting capacity of each bucket of the [Table]. The
// value must be non-negative. // value must be greater than 0.
func Capacity(value int) Option { func Capacity(value int) Option {
if value < 0 {
panic(fmt.Sprintf("go-cuckoo: Capacity must be non-negative, got %d", value))
}
return func(s *settings) { s.bucketSize = uint64(value) } return func(s *settings) { s.bucketSize = uint64(value) }
} }
// GrowthFactor controls how much the capacity of the [HashTable] multiplies when // MinimumLoad modifies the [DefaultMinimumLoad] of the [Table]. The value must
// it must resize. The value must be greater than 1. // be between 0.00 and 1.00.
func GrowthFactor(value int) Option { func MinimumLoad(value float64) Option {
if value < 2 { return func(s *settings) { s.minLoadFactor = value }
panic(fmt.Sprintf("go-cuckoo: GrowthFactor must be greater than 1, got %d", 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 {
return func(s *settings) { s.growthFactor = uint64(value) } return func(s *settings) { s.growthFactor = uint64(value) }
} }

304
table.go
View File

@@ -1,103 +1,237 @@
package cuckoo package cuckoo
type entry[K, V any] struct { import (
key K "fmt"
value V "iter"
"math/bits"
"strings"
)
// 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 {
bucketA, bucketB bucket[K, V]
growthFactor uint64
minLoadFactor float64
} }
type slot[K, V any] struct { // TotalCapacity returns the number of slots allocated for the [Table]. To get the
entry[K, V] // number of slots filled, look at [Table.Size].
occupied bool func (t Table[K, V]) TotalCapacity() uint64 {
return t.bucketA.capacity + t.bucketB.capacity
} }
type table[K, V any] struct { // Size returns how many slots are filled in the [Table].
hash Hash[K] func (t Table[K, V]) Size() int {
slots []slot[K, V] return int(t.bucketA.size + t.bucketB.size)
capacity, size uint64
compare EqualFunc[K]
} }
// location determines where in the table a certain key would be placed. If the func log2(n uint64) (m int) {
// capacity is 0, this will panic. return max(0, bits.Len64(n)-1)
func (t table[K, V]) location(key K) uint64 {
return t.hash(key) % t.capacity
} }
func (t table[K, V]) get(key K) (value V, found bool) { func (t Table[K, V]) maxEvictions() int {
if t.capacity == 0 { 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 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() {
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
}
}
return nil
}
// 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() error {
var newCapacity uint64
if t.TotalCapacity() == 0 {
newCapacity = 1
} else {
newCapacity = t.bucketA.capacity * t.growthFactor
}
return t.resize(newCapacity)
}
// shrink reduces the table's capacity by the [Table.growthFactor]. It may
// reduce it down to 0.
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]. 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.bucketB.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 Table[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 *Table[K, V]) Put(key K, value V) (err error) {
if t.bucketA.update(key, value) {
return nil
}
if t.bucketB.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 {
return nil
}
if entry, eviction = t.bucketB.evict(entry); !eviction {
return nil
}
}
if t.load() < t.minLoadFactor {
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
}
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] {
return func(yield func(K, V) bool) {
for _, slot := range t.bucketA.slots {
if slot.occupied {
if !yield(slot.key, slot.value) {
return return
} }
}
slot := t.slots[t.location(key)]
return slot.value, slot.occupied && t.compare(slot.key, key)
} }
func (t *table[K, V]) drop(key K) (occupied bool) { for _, slot := range t.bucketB.slots {
if t.capacity == 0 { if slot.occupied {
if !yield(slot.key, slot.value) {
return 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 *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
}
slot := &t.slots[t.location(key)]
if slot.occupied && t.compare(slot.key, key) {
slot.value = value
return true
}
return false
}
func (t *table[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 newTable[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) table[K, V] {
return table[K, V]{
hash: hash,
capacity: capacity,
compare: compare,
size: 0,
slots: make([]slot[K, V], capacity),
} }
} }
}
}
// 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 {
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()
}
// NewCustomTable 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] {
settings := &settings{
growthFactor: DefaultGrowthFactor,
bucketSize: DefaultCapacity,
minLoadFactor: DefaultMinimumLoad,
}
for _, option := range options {
option(settings)
}
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),
}
}
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
// 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](
pipe(keyFunc, NewDefaultHash[C]()),
pipe(keyFunc, NewDefaultHash[C]()),
func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
options...,
)
}
// 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
// [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...)
}