Compare commits

...

8 Commits

Author SHA1 Message Date
cdb5efb4a3 fix: allow 0 capacity for table
- Added guards at the bucket level, to ensure that getting an item in an empty bucket doesn't cause an error.
- Added grow() and shrink() functions to Table, to prevent a capacity of 0 from not being able to grow.
- Updated the fuzz test to use `go_fuzz-utils`.
2026-03-19 20:46:31 -04:00
bb874a2aba test: add Drop to fuzz test, add drop test cases 2026-03-19 20:13:11 -04:00
e2ba398a62 fix: Table.Drop() was not a pointer receiver 2026-03-19 20:05:35 -04:00
c1314f8a3c fix: resize of Table.Drop() now decreases size
- Generalized Table.resize() to accept a capacity size for each bucket.
2026-03-19 20:01:50 -04:00
74ed81761c fix: drop() decrements bucket size 2026-03-19 20:01:14 -04:00
d4acdda95b feat: implement drop functionality
- Added `drop()` function in buckets.
- Implemented `Drop()` function for Table.
2026-03-19 19:54:16 -04:00
2bfaede2d4 ci: add lint makefile job (#5)
All checks were successful
CI / Makefile Lint (push) Successful in 15s
CI / Go Lint (push) Successful in 19s
CI / Unit Tests (push) Successful in 32s
CI / Fuzz Tests (push) Successful in 46s
CI / Mutation Tests (push) Successful in 51s
Currently, there is no CI job to lint the Makefile. This adds one.

Reviewed-on: #5
Co-authored-by: M.V. Hutz <git@maximhutz.me>
Co-committed-by: M.V. Hutz <git@maximhutz.me>
2026-03-19 00:24:25 +00:00
ece10585a5 style: restructure makefile (#4)
All checks were successful
CI / Unit Tests (push) Successful in 13s
CI / Go Lint (push) Successful in 17s
CI / Mutation Tests (push) Successful in 33s
CI / Fuzz Tests (push) Successful in 58s
Currently, the `Makefile` is not well structured, and does not follow best practices. With the help of [`checkmake`](https://github.com/checkmake/checkmake), the Makefile can be forced to follow them.

### Decisions

- Added CI job `lint-makefile`, which forces the Makefile to conform to standards.
- The `make help` was set as the default target. This is common practice in the industry.
- The `make help` uses `grep` | `awk` to create a command table from `##` comments after each target. It seems a bit icky, but it is something that Docker, Kubernetes, and Helm all do.

Reviewed-on: #4
Co-authored-by: M.V. Hutz <git@maximhutz.me>
Co-committed-by: M.V. Hutz <git@maximhutz.me>
2026-03-19 00:14:54 +00:00
10 changed files with 214 additions and 55 deletions

View File

@@ -6,8 +6,8 @@ on:
pull_request: pull_request:
jobs: jobs:
lint: lint-go:
name: Golang Lint name: Go Lint
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v4 - uses: actions/checkout@v4
@@ -23,7 +23,23 @@ jobs:
with: with:
version: latest version: latest
unit-test: lint-makefile:
name: Makefile Lint
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
- name: Install gremlins
run: go install github.com/checkmake/checkmake/cmd/checkmake@latest
- name: Run mutation tests
run: make lint-makefile
test-unit:
name: Unit Tests name: Unit Tests
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
@@ -34,9 +50,9 @@ jobs:
go-version-file: go.mod go-version-file: go.mod
- name: Run unit tests - name: Run unit tests
run: go test ./... -cover -v run: make test-unit
fuzz-test: test-fuzz:
name: Fuzz Tests name: Fuzz Tests
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
@@ -47,12 +63,9 @@ jobs:
go-version-file: go.mod go-version-file: go.mod
- name: Run fuzz tests - name: Run fuzz tests
run: | run: make test-fuzz
for func in $(grep -r --include='*_test.go' -oh 'func Fuzz\w*' . | sed 's/func //'); do
go test ./... -fuzz="^${func}$" -fuzztime=30s
done
mutation-test: test-mutation:
name: Mutation Tests name: Mutation Tests
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
@@ -66,4 +79,4 @@ jobs:
run: go install github.com/go-gremlins/gremlins/cmd/gremlins@latest run: go install github.com/go-gremlins/gremlins/cmd/gremlins@latest
- name: Run mutation tests - name: Run mutation tests
run: gremlins unleash run: make test-mutation

View File

@@ -1,12 +1,44 @@
unit: .PHONY: all help install clean test-unit test-mutation test-fuzz test docs lint-go lint-makefile lint
help: ## Show this help
@grep -E '^[a-zA-Z_-]+:.*##' $(MAKEFILE_LIST) | awk -F ':.*## ' '{printf " %-15s %s\n", $$1, $$2}'
install: ## Install dev tools
go install github.com/golangci/golangci-lint/cmd/golangci-lint@latest
go install github.com/checkmake/checkmake/cmd/checkmake@latest
go install github.com/go-gremlins/gremlins/cmd/gremlins@latest
go install golang.org/x/tools/cmd/godoc@latest
go install golang.org/x/vuln/cmd/govulncheck@latest
test-unit: ## Run unit tests with coverage
go test ./... -cover -v go test ./... -cover -v
mutation: test-mutation: ## Run mutation tests with gremlins
gremlins unleash gremlins unleash
fuzz: FUZZ_TIME ?= 30
go test ./... -fuzz=$(FN)
docs: test-fuzz: ## Run all fuzz tests for 30s each
@echo ">>> Visit: http://localhost:6060/pkg/git.maximhutz.com/tools/dsa/" @for func in $$(grep -r --include='*_test.go' -oh 'func Fuzz\w*' . | sed 's/func //'); do \
echo "Fuzzing $$func..."; \
go test ./... -fuzz="^$$func$$" -fuzztime=$(FUZZ_TIME)s; \
done
test: test-unit test-mutation test-fuzz ## Run all tests
lint-go: ## Lint Go code
golangci-lint run ./...
lint-makefile: ## Lint the Makefile
checkmake Makefile
lint: lint-go lint-makefile ## Lint all code
docs: ## Serve godoc locally
@echo ">>> Visit: http://localhost:6060/pkg/$$(go list -m)"
godoc -http=:6060 godoc -http=:6060
clean: ## Clean build and test caches
go clean -cache -testcache
all: lint test ## Run all checks and tests

View File

@@ -22,10 +22,30 @@ func (b bucket[K, V]) location(key K) uint64 {
} }
func (b bucket[K, V]) get(key K) (value V, found bool) { func (b bucket[K, V]) get(key K) (value V, found bool) {
if b.capacity == 0 {
return
}
slot := b.slots[b.location(key)] 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) {
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) { func (b *bucket[K, V]) resize(capacity uint64) {
b.slots = make([]slot[K, V], capacity) b.slots = make([]slot[K, V], capacity)
b.capacity = capacity b.capacity = capacity
@@ -33,6 +53,10 @@ func (b *bucket[K, V]) resize(capacity uint64) {
} }
func (b bucket[K, V]) update(key K, value V) (updated bool) { func (b bucket[K, V]) update(key K, value V) (updated bool) {
if b.capacity == 0 {
return
}
slot := &b.slots[b.location(key)] slot := &b.slots[b.location(key)]
if slot.occupied && b.compare(slot.key, key) { if slot.occupied && b.compare(slot.key, key) {
@@ -44,6 +68,10 @@ func (b bucket[K, V]) update(key K, value V) (updated bool) {
} }
func (b *bucket[K, V]) evict(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 { if !slot.occupied {

View File

@@ -1,11 +1,11 @@
package cuckoo_test package cuckoo_test
import ( import (
"bytes" "maps"
"encoding/binary"
"testing" "testing"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
go_fuzz_utils "github.com/trailofbits/go-fuzz-utils"
"git.maximhutz.com/tools/go-cuckoo" "git.maximhutz.com/tools/go-cuckoo"
) )
@@ -19,31 +19,60 @@ func offsetHash(seed uint32) cuckoo.Hash[uint32] {
} }
} }
type fuzzStep struct {
drop bool
key, value uint32
}
type fuzzScenario struct {
seedA, seedB uint32
steps []fuzzStep
}
func FuzzInsertLookup(f *testing.F) { func FuzzInsertLookup(f *testing.F) {
f.Fuzz(func(t *testing.T, data []byte, seedA, seedB uint32) { f.Fuzz(func(t *testing.T, data []byte) {
var scenario fuzzScenario
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.NewCustomTable[uint32, uint32]( if tp, err := go_fuzz_utils.NewTypeProvider(data); err != nil {
offsetHash(seedA), return
offsetHash(seedB), } else if err := tp.Fill(&scenario); err != nil {
func(a, b uint32) bool { return a == b },
)
if seedA == seedB {
return return
} }
r := bytes.NewReader(data) if scenario.seedA == scenario.seedB {
var key, value uint32 return
for binary.Read(r, binary.LittleEndian, &key) == nil && }
binary.Read(r, binary.LittleEndian, &value) == nil {
err := table.Put(key, value) actual := cuckoo.NewCustomTable[uint32, uint32](
offsetHash(scenario.seedA),
offsetHash(scenario.seedB),
func(a, b uint32) bool { return a == b },
)
expected := map[uint32]uint32{}
for _, step := range scenario.steps {
if step.drop {
err := actual.Drop(step.key)
assert.NoError(err) assert.NoError(err)
found, err := table.Get(key) delete(expected, step.key)
_, err = actual.Get(step.key)
assert.Error(err)
} else {
err := actual.Put(step.key, step.value)
assert.NoError(err) assert.NoError(err)
assert.Equal(value, found)
expected[step.key] = step.value
found, err := actual.Get(step.key)
assert.NoError(err)
assert.Equal(step.value, found)
}
assert.Equal(expected, maps.Collect(actual.Entries()))
} }
}) })
} }

View File

@@ -25,6 +25,6 @@ func TestLoad(t *testing.T) {
for i := range 16 { for i := range 16 {
err := table.Put(i, true) err := table.Put(i, true)
assert.NoError(err) assert.NoError(err)
assert.Equal(float64(table.Size())/float64(table.Capacity()), table.load()) assert.Equal(float64(table.Size())/float64(table.TotalCapacity()), table.load())
} }
} }

View File

@@ -64,7 +64,7 @@ func TestStartingCapacity(t *testing.T) {
assert := assert.New(t) assert := assert.New(t)
table := cuckoo.NewTable[int, bool](cuckoo.Capacity(64)) table := cuckoo.NewTable[int, bool](cuckoo.Capacity(64))
assert.Equal(uint64(128), table.Capacity()) assert.Equal(uint64(128), table.TotalCapacity())
} }
func TestResizeCapacity(t *testing.T) { func TestResizeCapacity(t *testing.T) {
@@ -74,12 +74,12 @@ func TestResizeCapacity(t *testing.T) {
cuckoo.GrowthFactor(2), cuckoo.GrowthFactor(2),
) )
for table.Capacity() == 16 { for table.TotalCapacity() == 16 {
err := table.Put(rand.Int(), true) err := table.Put(rand.Int(), true)
assert.NoError(err) assert.NoError(err)
} }
assert.Equal(uint64(32), table.Capacity()) assert.Equal(uint64(32), table.TotalCapacity())
} }
func TestPutMany(t *testing.T) { func TestPutMany(t *testing.T) {
@@ -128,3 +128,28 @@ func TestRemove(t *testing.T) {
assert.True(table.Has(0)) assert.True(table.Has(0))
} }
func TestDropExistingItem(t *testing.T) {
assert := assert.New(t)
key, value := 0, true
table := cuckoo.NewTable[int, bool]()
(table.Put(key, value))
err := table.Drop(key)
assert.NoError(err)
assert.Equal(0, table.Size())
assert.False(table.Has(key))
}
func TestDropNoItem(t *testing.T) {
assert := assert.New(t)
key := 0
table := cuckoo.NewTable[int, bool]()
err := table.Drop(key)
assert.NoError(err)
assert.Equal(0, table.Size())
assert.False(table.Has(key))
}

1
go.mod
View File

@@ -7,5 +7,6 @@ require github.com/stretchr/testify v1.11.1
require ( require (
github.com/davecgh/go-spew v1.1.1 // indirect github.com/davecgh/go-spew v1.1.1 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589
gopkg.in/yaml.v3 v3.0.1 // indirect gopkg.in/yaml.v3 v3.0.1 // indirect
) )

2
go.sum
View File

@@ -4,6 +4,8 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U= github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U= github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589 h1:UmBZCTPdDYore2IEHN+U4eIqEaRq6METh9pKiPumkqc=
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589/go.mod h1:zh+T+w9XT/3o4E0WLEGCdmLJ8Yqx/zY3o538tQY3OjY=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

View File

@@ -16,9 +16,9 @@ type Table[K, V any] struct {
minLoadFactor float64 minLoadFactor float64
} }
// Capacity 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]) Capacity() uint64 { func (t Table[K, V]) TotalCapacity() uint64 {
return t.bucketA.capacity + t.bucketB.capacity return t.bucketA.capacity + t.bucketB.capacity
} }
@@ -28,25 +28,31 @@ func (t Table[K, V]) Size() int {
} }
func log2(n uint64) (m int) { func log2(n uint64) (m int) {
return 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.Capacity()) return 3 * log2(t.TotalCapacity())
} }
func (t Table[K, V]) load() float64 { func (t Table[K, V]) load() float64 {
return float64(t.Size()) / float64(t.Capacity()) // 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
} }
func (t *Table[K, V]) resize() error { return float64(t.Size()) / float64(t.TotalCapacity())
}
func (t *Table[K, V]) resize(capacity uint64) error {
entries := make([]entry[K, V], 0, t.Size()) entries := make([]entry[K, V], 0, t.Size())
for k, v := range t.Entries() { for k, v := range t.Entries() {
entries = append(entries, entry[K, V]{k, v}) entries = append(entries, entry[K, V]{k, v})
} }
t.bucketA.resize(t.growthFactor * t.bucketA.capacity) t.bucketA.resize(capacity)
t.bucketB.resize(t.growthFactor * t.bucketB.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 {
@@ -57,6 +63,22 @@ func (t *Table[K, V]) resize() error {
return nil return nil
} }
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)
}
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 // Get fetches the value for a key in the [Table]. Returns an error if no value
// is found. // is found.
func (t Table[K, V]) Get(key K) (value V, err error) { func (t Table[K, V]) Get(key K) (value V, err error) {
@@ -99,10 +121,10 @@ func (t *Table[K, V]) Put(key K, value V) (err error) {
} }
if t.load() < t.minLoadFactor { if t.load() < t.minLoadFactor {
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.Capacity(), t.load()) return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
} }
if err := t.resize(); err != nil { if err := t.grow(); err != nil {
return err return err
} }
@@ -111,10 +133,15 @@ 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) {
// Deprecated: Do not use. t.bucketA.drop(key)
func (t Table[K, V]) Drop(_ K) { t.bucketB.drop(key)
panic("Not implemented")
if t.load() < t.minLoadFactor {
return t.shrink()
}
return nil
} }
// 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.

View File

@@ -0,0 +1,2 @@
go test fuzz v1
[]byte("B000000000000001000000000000000000000000000000000000000000000000000000000000000000000000000000000")