Compare commits

..

1 Commits

Author SHA1 Message Date
56b1982f8a feat: add drop key functionality (#6)
All checks were successful
CI / Makefile Lint (push) Successful in 16s
CI / Go Lint (push) Successful in 21s
CI / Unit Tests (push) Successful in 15s
CI / Fuzz Tests (push) Successful in 49s
CI / Mutation Tests (push) Successful in 55s
Currently, the `Table.Drop()` function is deprecated because it is not implemented yet. Let's add that functionality.

- Adds true drop functionality to the table, through `Table.Drop()`.
- Adds tests for functionality.
- Rewrites fuzz test using `go_fuzz_utils`, to test arbitrary usage patterns.
- Rewrite `bucket` to allow a capacity of zero.
- Rename `Table.Capacity()` to `Table.TotalCapacity()`, to reflect to different between the capacity of the buckets vs. the whole table.
- Enforce 100% mutation test coverage.

Reviewed-on: #6
Co-authored-by: M.V. Hutz <git@maximhutz.me>
Co-committed-by: M.V. Hutz <git@maximhutz.me>
2026-03-20 01:59:54 +00:00
8 changed files with 218 additions and 26 deletions

View File

@@ -5,3 +5,5 @@ unleash:
workers: 4 workers: 4
dry-run: false dry-run: false
threshold:
efficacy: 1.0

View File

@@ -16,10 +16,12 @@ test-unit: ## Run unit tests with coverage
test-mutation: ## Run mutation tests with gremlins test-mutation: ## Run mutation tests with gremlins
gremlins unleash gremlins unleash
FUZZ_TIME ?= 30
test-fuzz: ## Run all fuzz tests for 30s each test-fuzz: ## Run all fuzz tests for 30s each
@for func in $$(grep -r --include='*_test.go' -oh 'func Fuzz\w*' . | sed 's/func //'); do \ @for func in $$(grep -r --include='*_test.go' -oh 'func Fuzz\w*' . | sed 's/func //'); do \
echo "Fuzzing $$func..."; \ echo "Fuzzing $$func..."; \
go test ./... -fuzz="^$$func$$" -fuzztime=30s; \ go test ./... -fuzz="^$$func$$" -fuzztime=$(FUZZ_TIME)s; \
done done
test: test-unit test-mutation test-fuzz ## Run all tests test: test-unit test-mutation test-fuzz ## Run all tests

View File

@@ -17,16 +17,26 @@ type bucket[K, V any] struct {
compare EqualFunc[K] 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 { func (b bucket[K, V]) location(key K) uint64 {
return b.hash(key) % b.capacity return b.hash(key) % b.capacity
} }
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) { func (b *bucket[K, V]) drop(key K) (occupied 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) {
@@ -45,6 +55,10 @@ 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) {
@@ -56,6 +70,10 @@ 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](
assert.NoError(err) offsetHash(scenario.seedA),
offsetHash(scenario.seedB),
func(a, b uint32) bool { return a == b },
)
found, err := table.Get(key) expected := map[uint32]uint32{}
assert.NoError(err)
assert.Equal(value, found) for _, step := range scenario.steps {
if step.drop {
err := actual.Drop(step.key)
assert.NoError(err)
delete(expected, step.key)
_, 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, err := actual.Get(step.key)
assert.NoError(err)
assert.Equal(step.value, found)
}
assert.Equal(expected, maps.Collect(actual.Entries()))
} }
}) })
} }

View File

@@ -1,6 +1,7 @@
package cuckoo_test package cuckoo_test
import ( import (
"errors"
"maps" "maps"
"math/rand/v2" "math/rand/v2"
"testing" "testing"
@@ -129,7 +130,7 @@ func TestRemove(t *testing.T) {
assert.True(table.Has(0)) assert.True(table.Has(0))
} }
func TestDropItem(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.NewTable[int, bool]() table := cuckoo.NewTable[int, bool]()
@@ -141,3 +142,100 @@ func TestDropItem(t *testing.T) {
assert.Equal(0, table.Size()) assert.Equal(0, table.Size())
assert.False(table.Has(key)) 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))
}
func TestDropItemCapacity(t *testing.T) {
assert := assert.New(t)
key := 0
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(64),
cuckoo.GrowthFactor(2),
)
startingCapacity := table.TotalCapacity()
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)
}
func TestPutNoCapacity(t *testing.T) {
assert := assert.New(t)
key, value := 0, true
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(0),
)
err := table.Put(key, value)
assert.NoError(err)
assert.Equal(1, table.Size())
assert.True(table.Has(key))
}
func TestBadHashCapacity(t *testing.T) {
assert := assert.New(t)
table := cuckoo.NewCustomTable[int, bool](
func(int) uint64 { return 0 },
func(int) uint64 { return 0 },
func(a, b int) bool { return a == b },
cuckoo.Capacity(20),
)
err1 := table.Put(0, true)
err2 := table.Put(1, true)
err3 := table.Put(2, true)
assert.NoError(err1)
assert.NoError(err2)
assert.Error(err3)
assert.Equal(uint64(80), table.TotalCapacity())
}
func TestDropResizeCapacity(t *testing.T) {
assert := assert.New(t)
table := cuckoo.NewTable[int, bool](
cuckoo.Capacity(10),
)
err1 := table.Put(0, true)
err2 := table.Put(1, true)
err3 := table.Drop(1)
assert.NoError(errors.Join(err1, err2, err3))
assert.Equal(uint64(20), table.TotalCapacity())
}
func TestNewTableBy(t *testing.T) {
type User struct {
_ func()
id string
name string
}
assert := assert.New(t)
table := cuckoo.NewTableBy[User, bool](
func(u User) string { return u.id },
)
err := table.Put(User{nil, "1", "Robert"}, true)
assert.NoError(err)
assert.Equal(1, table.Size())
assert.True(table.Has(User{nil, "1", "Robbie"}))
}

3
go.mod
View File

@@ -4,8 +4,11 @@ go 1.25.6
require github.com/stretchr/testify v1.11.1 require github.com/stretchr/testify v1.11.1
require github.com/kr/pretty v0.3.1 // indirect
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
) )

13
go.sum
View File

@@ -1,10 +1,21 @@
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
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/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
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=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= 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/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -28,7 +28,7 @@ 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 {
@@ -36,9 +36,18 @@ func (t Table[K, V]) maxEvictions() int {
} }
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 {
return 1.0
}
return float64(t.Size()) / float64(t.TotalCapacity()) 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 { 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() {
@@ -57,6 +66,26 @@ func (t *Table[K, V]) resize(capacity uint64) error {
return nil 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 // 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) {
@@ -102,7 +131,7 @@ func (t *Table[K, V]) Put(key K, value V) (err error) {
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load()) return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
} }
if err := t.resize(t.growthFactor * t.bucketA.capacity); err != nil { if err := t.grow(); err != nil {
return err return err
} }
@@ -116,7 +145,7 @@ func (t *Table[K, V]) Drop(key K) (err error) {
t.bucketB.drop(key) t.bucketB.drop(key)
if t.load() < t.minLoadFactor { if t.load() < t.minLoadFactor {
return t.resize(t.bucketA.capacity / t.growthFactor) return t.shrink()
} }
return nil return nil