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
17 changed files with 241 additions and 272 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"
about: "Standard PR template"
title: ""
name: "Pull Request Template"
about: "This template is for general pull requests!"
title: "<type>[optional scope]: <description>"
ref: "main"
assignees: ["user1"]
labels:
- bug
- "help needed"
---
## Description
## Changes
### Design Decisions
## Checklist
- [ ] Tests pass
- [ ] Docs updated
This is the template!

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

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

View File

@@ -1,13 +1,12 @@
package cuckoo
// An Entry is a key-value pair.
type Entry[K, V any] struct {
Key K
Value V
type entry[K, V any] struct {
key K
value V
}
type slot[K, V any] struct {
Entry[K, V]
entry[K, V]
occupied bool
}
@@ -30,7 +29,7 @@ func (b bucket[K, V]) get(key K) (value V, found bool) {
}
slot := b.slots[b.location(key)]
return slot.Value, slot.occupied && b.compare(slot.Key, key)
return slot.value, slot.occupied && b.compare(slot.key, key)
}
func (b *bucket[K, V]) drop(key K) (occupied bool) {
@@ -40,7 +39,7 @@ func (b *bucket[K, V]) drop(key K) (occupied bool) {
slot := &b.slots[b.location(key)]
if slot.occupied && b.compare(slot.Key, key) {
if slot.occupied && b.compare(slot.key, key) {
slot.occupied = false
b.size--
return true
@@ -49,13 +48,10 @@ func (b *bucket[K, V]) drop(key K) (occupied bool) {
return false
}
func (b *bucket[K, V]) resized(capacity uint64) bucket[K, V] {
return bucket[K, V]{
slots: make([]slot[K, V], capacity),
capacity: capacity,
hash: b.hash,
compare: b.compare,
}
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) {
@@ -65,34 +61,34 @@ func (b bucket[K, V]) update(key K, value V) (updated bool) {
slot := &b.slots[b.location(key)]
if slot.occupied && b.compare(slot.Key, key) {
slot.Value = value
if slot.occupied && b.compare(slot.key, key) {
slot.value = value
return true
}
return false
}
func (b *bucket[K, V]) insert(insertion Entry[K, V]) (evicted Entry[K, V], eviction bool) {
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)]
slot := &b.slots[b.location(insertion.key)]
if !slot.occupied {
slot.Entry = insertion
slot.entry = insertion
slot.occupied = true
b.size++
return
}
if b.compare(slot.Key, insertion.Key) {
slot.Value = insertion.Value
if b.compare(slot.key, insertion.key) {
slot.value = insertion.value
return
}
insertion, slot.Entry = slot.Entry, insertion
insertion, slot.entry = slot.entry, insertion
return insertion, true
}

View File

@@ -1,9 +1,7 @@
package cuckoo_test
import (
"fmt"
"maps"
"os"
"testing"
"github.com/stretchr/testify/assert"
@@ -28,7 +26,6 @@ type fuzzStep struct {
type fuzzScenario struct {
seedA, seedB uint32
capacity, growthFactor uint8
steps []fuzzStep
}
@@ -43,41 +40,29 @@ func FuzzInsertLookup(f *testing.F) {
return
}
seedA, seedB := scenario.seedA, scenario.seedB
growthFactor := max(2, int(scenario.growthFactor))
capacity := int(scenario.capacity)
// If they are the same number, the hashes will clash, always causing an
// error.
if seedA == seedB {
t.Skip()
if scenario.seedA == scenario.seedB {
return
}
fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d\n",
seedA, seedB, capacity, growthFactor)
actual := cuckoo.NewCustomTable[uint32, uint32](
offsetHash(seedA),
offsetHash(seedB),
offsetHash(scenario.seedA),
offsetHash(scenario.seedB),
func(a, b uint32) bool { return a == b },
cuckoo.Capacity(capacity),
cuckoo.GrowthFactor(growthFactor),
)
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)
_, err := actual.Get(step.key)
_, err = actual.Get(step.key)
assert.Error(err)
} else {
_, err := actual.Put(step.key, step.value)
err := actual.Put(step.key, step.value)
assert.NoError(err)
expected[step.key] = step.value

View File

@@ -23,7 +23,7 @@ func TestLoad(t *testing.T) {
table := NewTable[int, bool](Capacity(8))
for i := range 16 {
_, err := table.Put(i, true)
err := table.Put(i, true)
assert.NoError(err)
assert.Equal(float64(table.Size())/float64(table.TotalCapacity()), table.load())
}

View File

@@ -25,7 +25,7 @@ func TestAddItem(t *testing.T) {
key, value := 0, true
table := cuckoo.NewTable[int, bool]()
_, err := table.Put(key, value)
err := table.Put(key, value)
assert.NoError(err)
assert.Equal(1, table.Size())
@@ -38,7 +38,7 @@ func TestPutOverwrite(t *testing.T) {
table := cuckoo.NewTable[int, int]()
(table.Put(key, value))
_, err := table.Put(key, newValue)
err := table.Put(key, newValue)
assert.NoError(err)
assert.Equal(1, table.Size())
@@ -52,9 +52,9 @@ func TestSameHash(t *testing.T) {
hash := func(int) uint64 { return 0 }
table := cuckoo.NewCustomTable[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int])
_, errA := table.Put(0, true)
_, errB := table.Put(1, true)
_, errC := table.Put(2, true)
errA := table.Put(0, true)
errB := table.Put(1, true)
errC := table.Put(2, true)
assert.NoError(errA)
assert.NoError(errB)
@@ -76,7 +76,7 @@ func TestResizeCapacity(t *testing.T) {
)
for table.TotalCapacity() == 16 {
_, err := table.Put(rand.Int(), true)
err := table.Put(rand.Int(), true)
assert.NoError(err)
}
@@ -89,7 +89,7 @@ func TestPutMany(t *testing.T) {
for i := range 1_000 {
expected[i] = true
_, err := actual.Put(i, true)
err := actual.Put(i, true)
assert.NoError(err)
}
@@ -103,7 +103,7 @@ func TestGetMany(t *testing.T) {
table := cuckoo.NewTable[int, bool]()
for i := range 1_000 {
_, err := table.Put(i, true)
err := table.Put(i, true)
assert.NoError(err)
}
@@ -124,9 +124,9 @@ func TestDropExistingItem(t *testing.T) {
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))
}
@@ -136,9 +136,9 @@ func TestDropNoItem(t *testing.T) {
key := 0
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))
}
@@ -152,9 +152,10 @@ func TestDropItemCapacity(t *testing.T) {
)
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)
@@ -167,7 +168,7 @@ func TestPutNoCapacity(t *testing.T) {
cuckoo.Capacity(0),
)
_, err := table.Put(key, value)
err := table.Put(key, value)
assert.NoError(err)
assert.Equal(1, table.Size())
@@ -183,9 +184,9 @@ func TestBadHashCapacity(t *testing.T) {
cuckoo.Capacity(20),
)
_, err1 := table.Put(0, true)
_, err2 := table.Put(1, true)
_, err3 := table.Put(2, true)
err1 := table.Put(0, true)
err2 := table.Put(1, true)
err3 := table.Put(2, true)
assert.NoError(err1)
assert.NoError(err2)
@@ -200,11 +201,11 @@ func TestDropResizeCapacity(t *testing.T) {
cuckoo.Capacity(10),
)
_, err1 := table.Put(0, true)
_, err2 := table.Put(1, true)
table.Drop(1)
err1 := table.Put(0, true)
err2 := table.Put(1, true)
err3 := table.Drop(1)
assert.NoError(errors.Join(err1, err2))
assert.NoError(errors.Join(err1, err2, err3))
assert.Equal(uint64(20), table.TotalCapacity())
}
@@ -220,7 +221,7 @@ func TestNewTableBy(t *testing.T) {
func(u User) string { return u.id },
)
_, err := table.Put(User{nil, "1", "Robert"}, true)
err := table.Put(User{nil, "1", "Robert"}, true)
assert.NoError(err)
assert.Equal(1, table.Size())

View File

@@ -10,7 +10,7 @@ import (
func Example_basic() {
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)
}

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

@@ -1,7 +1,5 @@
package cuckoo
import "fmt"
// DefaultCapacity is the initial capacity of a [Table]. It is inspired from
// Java's [HashMap] implementation, which also uses 16.
//
@@ -12,17 +10,11 @@ const DefaultCapacity uint64 = 16
// 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
@@ -35,21 +27,19 @@ type settings struct {
type Option func(*settings)
// 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 {
if value < 0 {
panic(fmt.Sprintf("go-cuckoo: Capacity must be non-negative, got %d", 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.
func MinimumLoad(value float64) Option {
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 {
if value < 2 {
panic(fmt.Sprintf("go-cuckoo: GrowthFactor must be greater than 1, got %d", value))
}
return func(s *settings) { s.growthFactor = uint64(value) }
}

134
table.go
View File

@@ -45,61 +45,30 @@ 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.bucketA.update(entry.Key, entry.Value) {
return
}
if t.bucketB.update(entry.Key, entry.Value) {
return
}
for range t.maxEvictions() {
if entry, homeless = t.bucketA.insert(entry); !homeless {
return
}
if entry, homeless = t.bucketB.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,
bucketA: t.bucketA.resized(capacity),
bucketB: t.bucketB.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 [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 {
@@ -113,7 +82,7 @@ func (t *Table[K, V]) grow() bool {
// shrink reduces the table's capacity by the [Table.growthFactor]. It may
// reduce it down to 0.
func (t *Table[K, V]) shrink() bool {
func (t *Table[K, V]) shrink() error {
return t.resize(t.bucketA.capacity / t.growthFactor)
}
@@ -137,52 +106,49 @@ func (t Table[K, V]) Has(key K) (exists bool) {
return err == nil
}
// Put sets the value for a key. If it cannot be set, an error is returned,
// along with the last displaced entry.
//
// On failure, the returned entry and the current table contents together
// preserve all previously inserted entries and the attempted entry.
func (t *Table[K, V]) Put(key K, value V) (displaced Entry[K, V], err error) {
var (
entry = Entry[K, V]{key, value}
homeless bool
)
for range defaultGrowthLimit {
if entry, homeless = t.insert(entry); !homeless {
return
// 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
}
}
// 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 entry, fmt.Errorf("bad hash: resize on load %d/%d", t.Size(), t.TotalCapacity())
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
}
// 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 entry, fmt.Errorf("bad hash: could not redistribute entries into larger table")
}
if err := t.grow(); err != nil {
return err
}
return entry, fmt.Errorf("bad hash: could not place entry after %d resizes", defaultGrowthLimit)
return t.Put(entry.key, entry.value)
}
// 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.bucketA.drop(key) || t.bucketB.drop(key)
// 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 {
// The error is not handled here, because table-shrinking is an internal
// optimization.
t.shrink()
return t.shrink()
}
return occupied
return nil
}
// Entries returns an unordered sequence of all key-value pairs in the table.
@@ -190,7 +156,7 @@ 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) {
if !yield(slot.key, slot.value) {
return
}
}
@@ -198,7 +164,7 @@ func (t Table[K, V]) Entries() iter.Seq2[K, V] {
for _, slot := range t.bucketB.slots {
if slot.occupied {
if !yield(slot.Key, slot.Value) {
if !yield(slot.key, slot.value) {
return
}
}
@@ -232,7 +198,7 @@ func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], option
settings := &settings{
growthFactor: DefaultGrowthFactor,
bucketSize: DefaultCapacity,
minLoadFactor: defaultMinimumLoad,
minLoadFactor: DefaultMinimumLoad,
}
for _, option := range options {