Skip to content

feat: tuple update sketch #69

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
freakyzoidberg merged 3 commits into from
Dec 10, 2025
Merged

feat: tuple update sketch #69

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5ce2d6a
feat: tuple update sketch
proost Dec 9, 2025
cd6b9ae
perf: use sentinel error
proost Dec 10, 2025
01a44ea
perf: use equal
proost Dec 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions tuple/hashtable.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ package tuple

import (
"errors"
"fmt"
"math"

"github.com/apache/datasketches-go/internal"
Expand All @@ -41,7 +40,8 @@ var (
ErrKeyNotFoundAndNoEmptySlots = errors.New("key not found and no empty slots")
// ErrZeroHashValue is used to indicate that the hash value is zero.
// Zero is a reserved value for empty slots in the hash table.
ErrZeroHashValue = errors.New("zero hash value")
ErrZeroHashValue = errors.New("zero hash value")
ErrHashExceedsTheta = errors.New("hash exceeds theta")
)

type entry[S Summary] struct {
Expand Down Expand Up @@ -104,7 +104,7 @@ func (t *hashtable[S]) HashStringAndScreen(data string) (uint64, error) {
h1, _ := internal.HashCharSliceMurmur3([]byte(data), 0, len(data), t.seed)
hash := h1 >> 1
if hash >= t.theta {
return 0, fmt.Errorf("hash %d is greater than or equal to theta %d", hash, t.theta)
return 0, ErrHashExceedsTheta
}
if hash == 0 {
return 0, ErrZeroHashValue
Expand All @@ -118,7 +118,7 @@ func (t *hashtable[S]) HashInt32AndScreen(data int32) (uint64, error) {
h1, _ := internal.HashInt32SliceMurmur3([]int32{data}, 0, 1, t.seed)
hash := h1 >> 1
if hash >= t.theta {
return 0, fmt.Errorf("hash %d is greater than or equal to theta %d", hash, t.theta)
return 0, ErrHashExceedsTheta
}
if hash == 0 {
return 0, ErrZeroHashValue
Expand All @@ -132,7 +132,7 @@ func (t *hashtable[S]) HashInt64AndScreen(data int64) (uint64, error) {
h1, _ := internal.HashInt64SliceMurmur3([]int64{data}, 0, 1, t.seed)
hash := h1 >> 1
if hash >= t.theta {
return 0, fmt.Errorf("hash %d is greater than or equal to theta %d", hash, t.theta)
return 0, ErrHashExceedsTheta
}
if hash == 0 {
return 0, ErrZeroHashValue
Expand All @@ -146,7 +146,7 @@ func (t *hashtable[S]) HashBytesAndScreen(data []byte) (uint64, error) {
h1, _ := internal.HashByteArrMurmur3(data, 0, len(data), t.seed)
hash := h1 >> 1
if hash >= t.theta {
return 0, fmt.Errorf("hash %d is greater than or equal to theta %d", hash, t.theta)
return 0, ErrHashExceedsTheta
}
if hash == 0 {
return 0, ErrZeroHashValue
Expand Down
8 changes: 4 additions & 4 deletions tuple/hashtable_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ func TestHashtable_HashStringAndScreen(t *testing.T) {
data: "test",
theta: 1,
seed: theta.DefaultSeed,
wantErrMsg: "is greater than or equal to theta 1",
wantErrMsg: "hash exceeds theta",
},
{
name: "different seed",
Expand Down Expand Up @@ -150,7 +150,7 @@ func TestHashtable_HashInt32AndScreen(t *testing.T) {
data: 12345,
theta: 1,
seed: theta.DefaultSeed,
wantErrMsg: "is greater than or equal to theta 1",
wantErrMsg: "hash exceeds theta",
},
{
name: "different seed",
Expand Down Expand Up @@ -240,7 +240,7 @@ func TestHashtable_HashInt64AndScreen(t *testing.T) {
data: 1234567890,
theta: 1,
seed: theta.DefaultSeed,
wantErrMsg: "is greater than or equal to theta 1",
wantErrMsg: "hash exceeds theta",
},
{
name: "different seed",
Expand Down Expand Up @@ -337,7 +337,7 @@ func TestHashtable_HashBytesAndScreen(t *testing.T) {
data: []byte{1, 2, 3, 4, 5},
theta: 100,
seed: theta.DefaultSeed,
wantErrMsg: "is greater than or equal to theta 1",
wantErrMsg: "hash exceeds theta",
},
{
name: "different seed",
Expand Down
Loading